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

Abstract

The invention relates to the technical field of computers, in particular to an interaction method, an interaction device and a computer readable storage medium. The interaction method comprises the following steps: displaying a first entrance on a live broadcast interface; in response to a trigger operation on the first entry, displaying a session interface, the session interface being used for performing a session with the virtual assistant; and in response to the first session message, displaying a second session message on a session interface, the first session message being associated with an object provided by the live broadcast initiator, and the second session message belonging to a reply message of the virtual assistant for the first session message. According to the interaction method, the operation convenience and efficiency of consulting the object by the user in the live broadcast process are improved, the virtual assistant can reply the user more efficiently, and the interaction experience of the user in the live broadcast process is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an interactive method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] With the development of internet technology, the live streaming industry has grown rapidly. Live streamers can conduct various formats, some of which introduce one or more subjects, such as goods, services, or tourist attractions. Viewers can post comments during the live stream, which are displayed in a scrolling manner on the live stream interface. Summary of the Invention

[0003] According to some embodiments of this application, an interaction method is provided, including: displaying a first entry point on a live streaming interface; displaying a conversation interface in response to a triggering operation on the first entry point, wherein the conversation interface is used to conduct a conversation with a virtual assistant; and displaying a second conversation message on the conversation interface in response to a first conversation message, wherein the first conversation message is associated with an object provided by the live streaming initiator, and the second conversation message is a reply message from the virtual assistant to the first conversation message.

[0004] According to other embodiments of this application, an interactive device is provided, comprising: a first display module configured to display a first entry point on a live streaming interface; a second display module configured to display a conversation interface in response to a triggering operation on the first entry point, wherein the conversation interface is used for conversing with a virtual assistant; and a third display module configured to display a second conversation message on the conversation interface in response to a first conversation message, wherein the first conversation message is associated with an object provided by the live streaming initiator, and the second conversation message is a reply message from the virtual assistant to the first conversation message.

[0005] According to some other embodiments of this application, an electronic device is provided, including: a processor; and a memory coupled to the processor for storing instructions, which, when executed by the processor, cause the processor to perform an interactive method according to any embodiment of this application.

[0006] According to some other embodiments of this application, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the interactive method as described in any embodiment of this application.

[0007] According to some other embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements an interactive method as described in any embodiment of this application.

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

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

[0010] Figure 1 This is a schematic diagram illustrating a system architecture according to some embodiments of this application;

[0011] Figure 2 This is a flowchart illustrating an interaction method according to some embodiments of this application;

[0012] Figures 3-9 This is a schematic diagram illustrating a display interface according to some embodiments of this application;

[0013] Figure 10 A block diagram of an interactive device according to some embodiments of this application is shown;

[0014] Figure 11 A block diagram of an electronic device according to some embodiments of this application is shown;

[0015] Figure 12 Block diagrams of electronic devices according to other embodiments of this application are shown. Detailed Implementation

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0017] It should be understood that the various steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect. Unless otherwise specifically stated, the relative arrangement of components and steps set forth in these embodiments should be interpreted as merely exemplary and does not limit the scope of this application.

[0018] The term "comprising" and its variations as used in this application are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". The term "based on" means "at least partially based on".

[0019] It should be noted that the concepts of "first," "second," etc., mentioned in this application are used only to distinguish different devices, modules, or units, and are not used to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described so far must be in a given order in time, space, ranking, or any other way.

[0020] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] The embodiments of this application are described in detail below with reference to the accompanying drawings, but this application is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this application.

[0022] Live stream initiators can launch various types of live streams, and viewers can post comments during the stream. These comments are displayed in the comment area of ​​the live stream interface (which can be called the public chat). The live stream initiator can include the host. The host can reply to the comments. For example, if the host is explaining information about a certain object during the live stream, and a viewer asks a question about that object as a comment, the host can then answer the question. However, with a large number of comments scrolling across the live stream interface, the host cannot reply to each comment in a timely manner, resulting in a poor viewing experience. Besides the controls for inputting and posting comments, the live stream interface lacks other entry points for viewers to consult with the live stream initiator. Viewers who want to have a private conversation with the host or other personnel related to the live stream initiator need to perform complex operations to find the conversation entry point, which is inefficient and provides a poor user experience.

[0023] In view of the above problems, this application proposes an interaction method. A first entry point is displayed on the live streaming interface. In response to triggering the first entry point, a conversation interface for interacting with a virtual assistant is displayed. In response to a first conversation message, a second conversation message, in which the virtual assistant replies to the first conversation message, is displayed on the conversation interface. The first conversation message can be associated with an object provided by the live streaming initiator. This application provides a virtual assistant for live streaming and directly displays a first entry point for interacting with the virtual assistant on the live streaming interface. Users (or viewers) can trigger the display of the conversation interface at any time through the first entry point while watching the live stream and interact with the virtual assistant, asking questions associated with the object provided by the live streaming initiator. Through the setting of the first entry point and the virtual assistant, the convenience and efficiency of users (or viewers) consulting with objects during the live stream are improved, and the virtual assistant can respond to users more efficiently, enhancing the user's interactive experience during the live stream.

[0024] Figure 1 This is a schematic diagram illustrating the system architecture according to some embodiments of this application.

[0025] Figure 1 The system architecture 100 shown includes one or more client devices 102 connected to network 101, one or more servers 103, and external services 104, for implementing the interaction method of the embodiments of this application.

[0026] Network 101 can be a public network, such as the Internet, or a private network, such as a local area network (LAN) or a wide area network (WAN), or a combination thereof.

[0027] Client device 102 can be a personal computer (PC), laptop computer, mobile phone, tablet computer (Tablet PC), personal digital assistant (PDA), portable media player (PMP), set-top box, television, video game console, digital assistant, wearable device, desktop computer, or any other computing device. Client device 102 can run an operating system that manages the hardware and software of client device 102.

[0028] Server 103 can be a rack server, router, computer, personal computer, portable digital assistant, mobile phone, laptop computer, tablet computer, camera, camcorder, netbook, desktop computer, media center, or any combination thereof.

[0029] Client device 102 can provide client-side functionality, including user-oriented input and output processing, such as displaying various media content, receiving and responding to user operations, and communication with server 104. Server 103 includes various interfaces to client device 102, processing modules, data and models, and interfaces with external service 104. Server 103 communicates with external service 104 via network 101 for task completion or information retrieval.

[0030] The following is combined with Figures 2-9 This application describes the interaction method. The interaction method of this application can be executed by an interactive device or electronic device, which can be implemented by software and / or hardware. For example, the interactive device or electronic device can be the aforementioned client device or system. The interactive device can also be an application program, etc.

[0031] Figure 2 Flowcharts showing some embodiments of the interaction method of this application. For example... Figure 2 As shown, the interaction method of this embodiment includes steps S1 to S3.

[0032] In step S1, the first entry point is displayed on the live streaming interface.

[0033] The live streaming interface can display the live feed, which can be associated with one or more objects. For example, the host can explain one or more objects during the live stream. The first entry point is used to access the conversation interface corresponding to the virtual assistant and engage in conversation with the virtual assistant. The first entry point can be displayed anywhere on the live streaming interface. For example, the first entry point can be displayed at the top of the live streaming interface. The first entry point can be displayed as an interactive element of any style, such as a button, icon, or text link.

[0034] In step S2, in response to the triggering operation of the first entry point, the session interface is displayed.

[0035] The conversation interface is used to interact with the virtual assistant. The virtual assistant can interact with the user (or viewer) based on a machine learning model. The virtual assistant can be a virtual customer service representative, an intelligent agent, etc., and is not limited to the examples given. Users can trigger the primary entry point through actions such as clicking, long-pressing, or voice commands, and is not limited to the examples given. For example, the conversation interface can be displayed on top of the live stream interface in the form of a window, overlay, panel, or card, or it can be switched from the live stream interface to the conversation interface. The display style of the conversation interface and its relationship with the live stream interface are not limited to the examples given above.

[0036] In step S3, in response to the first session message, the second session message is displayed on the session interface.

[0037] The first conversation message can be sent by the user to the virtual assistant. This message is associated with an object provided by the live stream initiator. For example, the first conversation message could be a question addressed to one or more objects. The second conversation message is the virtual assistant's response to the first conversation message. For example, the second conversation message could be a response generated by the virtual assistant based on the first conversation message and information from one or more objects. The virtual assistant can generate response messages based on machine learning models, making it more efficient than human customer service responses.

[0038] In the above interaction method, a first entry point is displayed on the live stream interface. In response to triggering the first entry point, a conversation interface for interacting with the virtual assistant is displayed. In response to the first conversation message, a second conversation message, in which the virtual assistant replies to the first conversation message, is displayed on the conversation interface. The first conversation message can be associated with an object provided by the live stream initiator. This interaction method provides a virtual assistant for the live stream and directly displays a first entry point for interacting with the virtual assistant on the live stream interface. Users (or viewers) can trigger the display of the conversation interface at any time through the first entry point while watching the live stream and interact with the virtual assistant, asking questions associated with the object provided by the live stream initiator. Through the setting of the first entry point and the virtual assistant, the convenience and efficiency of users (or viewers) consulting with objects during the live stream are improved, and the virtual assistant can respond to users more efficiently, enhancing the user's interactive experience during the live stream.

[0039] The following describes how to display the first entry point and the first session message.

[0040] In one scenario, displaying the first entry point on the live stream interface includes: displaying a first input area on the live stream interface, and displaying the first entry point outside the first input area, wherein the first input area is used to input comment information.

[0041] The first input area can be displayed on top of the live streaming interface. For example, the first input area can have two states: active and inactive. In the inactive state, the first input area can include an input box; in the active state, it can include both an input box and a virtual keyboard. Users can activate the first input area by triggering the input box. Users can then input comments through the first input area. In the active state, the first input area can also include a send control, which, in response to inputting comments in the input box and triggering the send control, displays the comments in the comment area (or interaction area) of the live streaming interface. Multiple comments can be scrolled. The first entry point can be displayed outside the first input area. For example, it can be displayed adjacent to the first input area. The first entry point can also be displayed within the first input area. The first entry point can be fixed or dynamically displayed. For example, it can dynamically float on top of the live streaming interface, and so on, without being limited to the examples given.

[0042] like Figure 3 As shown, the live streaming interface 300 can display a first input area 301 and a first entry point 302. The first input area 301 and the first entry point 302 can be interactive elements at the same level.

[0043] In the above method, displaying the first entry point outside the first input area allows users to more clearly identify and locate the first entry point, making it easier for users to trigger the first entry point and interact with the virtual assistant.

[0044] In one scenario, the conversation interface includes a message display area and a second input area. The message display area is used to display conversation messages, and the second input area is used to input conversation messages. The second input area is similar to the first input area and can also correspond to both active and inactive states, which will not be elaborated further. Users can input the first conversation message through the second input area. For example, in response to inputting the first conversation message in the second input area and a send operation, the first conversation message is displayed in the message display area. Users can access the conversation interface...

[0045] In one scenario, displaying the session interface in response to a triggering operation on the first entry point includes: displaying the session interface in response to inputting first comment information in the first input area and triggering the first entry point, and displaying the first comment information in the session interface as a first session message.

[0046] Users can either enter and post comments in the first input area to inquire about issues related to a specific object, or they can engage in a conversation with the virtual assistant in the conversation interface to inquire about issues related to a specific object. If, after entering the first comment in the first input area, the send control in the first input area is not triggered, but the first entry point is activated instead, the first comment can be displayed as the first conversation message in the conversation interface. For example, in response to entering the first comment in the first input area and triggering the first entry point, the conversation interface is displayed, the first comment is displayed in the second input area of ​​the conversation interface, and in response to triggering the send control in the second input area, the first comment is displayed in the message display area as the first conversation message. As another example, in response to entering the first comment in the first input area and triggering the first entry point, the conversation interface is displayed, and the first comment is displayed in the message display area of ​​the conversation interface as the first conversation message. If the first comment is displayed in the second input area, in response to modifying the first comment, the modified first comment is displayed, and in response to triggering the send control in the second input area, the modified first comment is displayed in the message display area as the first conversation message.

[0047] The above method links and synchronizes the first comment information entered in the first input area with the conversation interface, and displays the first comment information that the user has not published as the first conversation message in the conversation interface, reducing the user's repetitive input operations, improving the conversation efficiency between the user and the virtual assistant, and enhancing the user's interactive experience.

[0048] In one scenario, in response to a triggering operation on the first entry point, displaying the session interface includes: in response to inputting second comment information in the first input area and publishing the second comment information, displaying the second comment information in the comment area, wherein the comment area is displayed on the live streaming interface; in response to a triggering operation on the first entry point and no reply to the second comment information, displaying the session interface and displaying the second comment information in the session interface as the first session message.

[0049] Users can first post a second comment through the first input area. If the second comment does not receive a reply, the user can trigger the first entry point to consult the virtual assistant. For example, the time elapsed between posting the second comment and triggering the first entry point is within a specified range. For instance, in response to triggering the first entry point and no reply to the second comment, a conversation interface is displayed, showing the second comment in the second input area. In response to triggering the send control in the second input area, the second comment is displayed in the message display area as the first conversation message. Alternatively, in response to triggering the first entry point and no reply to the second comment, a conversation interface is displayed, showing the second comment in the message display area as the first conversation message. If the second comment has received a reply, the conversation interface can be displayed, but the second comment will not be displayed there. If the second comment is displayed in the second input area, in response to modifying the second comment, the modified comment is displayed. In response to triggering the send control in the second input area, the modified comment is displayed in the message display area as the first conversation message.

[0050] like Figure 3 As shown, multiple comments are displayed on the live streaming interface 300, such as comment information 303. Comment information 303 may include the content of the comment and information such as the identifier of the user who posted the comment. In response to a trigger operation on the first entry point 302, the following can be displayed: Figure 4 The session interface shown is 400.

[0051] like Figure 4 As shown, the conversation interface 400 can be displayed on top of the live streaming interface 300. The conversation interface 400 displays a first conversation message 401, indicating that the comment information 303 has not received a reply and the user triggers the first entry point 302. The first conversation message 401 can be the comment information 303. The conversation message is displayed in the message display area. The conversation interface 400 can also display a second input area 402, through which the first conversation message 401 can also be entered. Alternatively, the first conversation message 401 can also be entered through the first input area 301, as described in the previous embodiment, and will not be repeated here.

[0052] In the above method, the comment information on the live broadcast interface is linked and synchronized with the conversation interface. The second comment information posted by the user that has not received a reply is displayed as the first conversation message on the conversation interface, which reduces the user's repetitive input operations, better meets the user's consultation needs, improves the conversation efficiency between the user and the virtual assistant, and enhances the user's interactive experience.

[0053] Users can send a first-session message to the virtual assistant in several ways. The virtual assistant then replies with a second-session message based on the first-session message. The following describes how to display the second-session message.

[0054] In one scenario, displaying a second session message in response to a first session message includes: displaying information about at least one candidate object based on the first session message, wherein the at least one candidate object belongs to an object provided by the live stream initiator; and displaying the second session message in the session interface based on the information of the first object in response to a selection operation of a first object among the at least one candidate object.

[0055] For example, the information for each candidate object includes its identifier, preview image, one or more attribute information, and at least one piece of related service information. For example, one or more attribute information may include the amount of resources required, the amount already acquired, color, size, model, etc., and is not limited to the examples given. Different objects may correspond to different attribute information. Related service information may include, for example, delivery services, return and exchange services, etc., and is not limited to the examples given. The information for at least one candidate object may be displayed in an information encapsulation, for example, a card, etc., and is not limited to the examples given. When displaying information for multiple candidate objects, the information for multiple objects is displayed as multiple information items within the information encapsulation. In response to the user's selection of a first object, the virtual assistant may generate and reply with a second session message based on the first session message and the information of the first object.

[0056] The above method provides users with information on at least one candidate object based on the first conversation message for the user to choose from, and displays a second conversation message based on the information of the first object selected by the user, thereby improving the accuracy of the virtual assistant's response and enhancing the interactive experience.

[0057] The following describes several scenarios for displaying at least one candidate object.

[0058] In one scenario, displaying information about at least one candidate object based on a first session message includes: in response to determining that the first session message is associated with a third object, displaying the third object as at least one candidate object, wherein the third object is determined based on the first session message and an object provided by the live stream initiator, and the third object may be the same as or different from the first object.

[0059] If, based on the first session message and the object provided by the live stream initiator, it is determined that the first session message is associated with a third object, the third object can be displayed as at least one candidate object. For example, semantic analysis can be performed on the first session message, and based on the semantics and the information of the object provided by the live stream initiator, it can be determined whether the first session message is associated with a certain object, and the third object associated with the first session message can be identified.

[0060] The third object can be either an unacquired object or an acquired object. An unacquired object can refer to an object provided by the live stream initiator but not acquired by the current user. An acquired object can refer to an object provided by the live stream initiator and acquired by the current user. Users can inquire about both unacquired and acquired objects, such as pre-sales and after-sales inquiries. If it can be determined that the first session message is associated with the third object, only the information of the third object can be displayed for the user to confirm or refer to.

[0061] The above method, by determining the association between the first session message and the third object and displaying the third object as at least one candidate object, can better match the user's intent, improve the display accuracy of at least one candidate object, and enhance the interactive experience.

[0062] In one scenario, at least one candidate object includes at least one unacquired object. The unacquired object includes at least one of a first candidate object, a second candidate object, and a third candidate object. The first candidate object is an object being explained in the live broadcast and the difference between the explanation time and the current time is less than a threshold. The second candidate object is an object that has been viewed. The third candidate object is an object other than the first and second candidate objects. The first and second candidate objects are different. Displaying information about at least one candidate object includes: for each unacquired object, displaying a first information item, wherein the first information item includes the identifier and first state of the unacquired object, and the first states corresponding to the first, second, and third candidate objects are different from each other.

[0063] For example, the difference between the explanation time of the first candidate object and the current time is less than 30 seconds. For example, the second candidate object is an object that has been viewed and is available. For example, from the object list of the live stream initiator, in addition to the first and second candidate objects, a third candidate object is selected according to the order of object arrangement. For example, there can be one or more first, second, and third candidate objects. An upper limit can be set for candidate objects; the first candidate object is selected first, and if the upper limit is not reached, the second candidate object is selected. One or more second candidate objects can be selected according to the interval between the viewing time and the current time, from largest to smallest, to determine if the upper limit has been reached; if not, the third candidate object is selected, and so on, until the upper limit is reached.

[0064] At least one candidate object can also include only the first candidate object. For example, if the first comment is used as the first session message, the user is likely to inquire about the object currently being discussed, so only the first candidate object (the object currently being discussed) can be displayed. Further, it can be determined whether the first session message and the information of the object currently being discussed match; if they match, only the first candidate object (the object currently being discussed) is displayed.

[0065] For example, if the second comment is used as the first conversation message, the object being discussed when the second comment was posted can be identified as the first candidate object. If the second comment matches the object being discussed at the time of posting, only the first candidate object can be displayed.

[0066] like Figure 4 As shown, information about multiple candidate objects is displayed in the message display area of ​​the session interface 400. This information can be displayed in cards. For example, the information about the multiple candidate objects includes a first information item 403. The first information item 403 may include an identifier and a first status of the unacquired object, such as a name and a first status such as "Understanding". The first information item 403 may also include a preview image of the unacquired object; the first status can be displayed in association with the preview image or in another location. The first information item 403 may also include one or more attribute information. The first information item 403 may also include a selection control 404; in response to the triggering operation of the selection control 404, the information about the unacquired object is displayed as a user's session message in the message display area. The information about the unacquired object in the session message may be the same as or different from the information about the unacquired object in the first information item, but it must at least include the identifier of the unacquired object.

[0067] like Figure 4 As shown, the card can also display a toggle control 405, which, in response to a triggering operation on the toggle control 405, switches the display of one or more candidate objects. For example, if the first and second candidate objects are currently displayed, one or more third candidate objects may be displayed after switching.

[0068] like Figure 5 As shown, the first information item 501 can display only one candidate object. For example, if the first session message is determined to be associated with a third object, the first information item 501 can be the information item for the third object. Alternatively, if the first comment information or the second comment information is used as the first session message, the first information item 501 can be the information item for the first candidate object. Similar to the first information item 403, the first information item 501 can include the identifier of the unacquired object, its first state, a preview image, one or more attribute information, etc. The first information item 501 can be displayed in association with the second input area 402. The first information item 501 can include a selection control 502 and a toggle control 503. In response to a trigger operation of the selection control 502, the information of the unacquired object is displayed as the user's session message in the message display area. In response to a trigger operation of the toggle control 503, one or more candidate objects are displayed.

[0069] In the above method, at least one of the first, second, and third candidate objects is provided for the user to choose from. For each unacquired object, information such as its identifier and first status is displayed. This allows the user to more clearly and accurately locate the object they want to consult, better match the user's intent, improve the display accuracy of at least one candidate object, and enhance the interactive experience.

[0070] In one scenario, at least one candidate object includes at least one acquired object, and at least one acquired object includes at least one of a fourth candidate object and a fifth candidate object. The fourth candidate object is associated with the live stream, and the fifth candidate object is not related to the live stream. Displaying information about at least one candidate object includes: for each acquired object, displaying a second information item, wherein the second information item includes the identifier of the acquired object and a second status, and the second status is used to indicate the processing progress of the acquired object by the live stream initiator.

[0071] For example, a specified number of acquired objects can be selected based on the interval between their acquisition time and the current time, from largest to smallest. This specified number of acquired objects may include a fourth candidate object and / or a fifth candidate object. There can be one or more fourth candidate objects, and one or more fifth candidate objects. The fifth candidate object can be an object from the live stream initiator's historical live streams, or an object from the live stream initiator's service point, etc. The processing progress of the acquired objects by the live stream initiator, such as whether the acquired objects have been shipped, their logistics status, etc., is not limited to the examples given.

[0072] The display style of at least one captured object can be similar to the display style of at least one uncaptured object, for example, Figure 3 or Figure 4 As shown, this will not be repeated here. At least one candidate object can include both unacquired and acquired objects, which will not be repeated here either.

[0073] The above method provides users with at least one of the fourth and fifth candidate objects to choose from, and displays information such as identifiers and second status for each acquired object. This allows users to more clearly and accurately locate the object they want to consult, better match the user's intent, improve the display accuracy of at least one candidate object, and enhance the interactive experience.

[0074] In response to a selection operation of a first object among at least one candidate object, information about the first object is displayed in the message display area. This information about the first object can be part of a first session message or presented separately as a third session message.

[0075] like Figure 6As shown, in response to a selection operation of a first object among at least one candidate object, information of the first object is displayed in the message display area as a third session message 601. The third session message 601 may include at least one of the following: the identifier of the first object, a preview image, one or more attribute information, status (first status or second status), and related service information.

[0076] In one scenario, for each acquired object, in response to a first session message including a modification request related to the acquired object, a second session message includes a modification result referenced by the virtual assistant, the modification result being generated based on the modification request and sent to the virtual assistant.

[0077] For each acquired object, the user can obtain information for modification, such as changing address information or modifying attribute values ​​(color, size), etc., and is not limited to the examples given. The virtual assistant can modify the object according to the modification requirements and obtain the modification result, or send modification requests to other service assistants (e.g., human customer service) and obtain the modification result, displaying the referenced modification result in the second session message.

[0078] like Figure 6 As shown, the second session message 602 is displayed in the message display area of ​​the session interface 400. The second session message includes messages referencing other service assistants, such as modification results.

[0079] The above method allows users to modify relevant information about acquired objects through a virtual assistant, improving the convenience and efficiency of user operations and enhancing the interactive experience.

[0080] The virtual assistant can determine the user's intent based on the initial session message, the context of the initial session message, and the user's historical behavior data. For example, it can determine whether the user's intent is for an unacquired object or an acquired object. Based on the user's intent, the virtual assistant provides at least one unacquired object or an acquired object as at least one candidate object. For example, the machine learning model corresponding to the virtual assistant may include an intent determination module, which can be used to determine the user's intent.

[0081] The foregoing embodiments describe methods for users to have conversations with a virtual assistant in a chat interface. The virtual assistant can also directly reply to the user's comments, which will be described below.

[0082] In one scenario, the interaction method further includes: in response to the posting of a third comment, displaying the third comment in a comment area, wherein the comment area is displayed on the live streaming interface; and displaying a fourth comment in the comment area, wherein the fourth comment is a reply from the virtual assistant to the third comment.

[0083] A fourth comment can be generated based on the third comment using the machine learning model corresponding to the virtual assistant. This fourth comment can be displayed directly in the comment area, allowing users to quickly and accurately locate and view it, thus improving the user experience. The fourth comment is visible only to the user and the broadcaster, but not to other users, minimizing interference.

[0084] In one scenario, the fourth comment information includes at least one of the following: text, a first interactive element corresponding to an image, a second interactive element corresponding to a video, and a third interactive element corresponding to a second object.

[0085] The fourth comment information may include at least one modality of information, such as text, images, videos, and interactive elements. To reduce the area occupied by the fourth comment information on the live streaming interface, images and videos may be represented using the first and second interactive elements. If it is determined that the third comment information is associated with the second object or that the user intends to obtain the second object, the fourth comment information may also include the third interactive element corresponding to the second object.

[0086] The above method allows the fourth comment information in the virtual assistant's reply to include information from multiple modalities, which increases the richness of the reply content, makes the fourth comment information more referential and effective, and enhances the interactive experience.

[0087] In one scenario, the interaction method further includes at least one of the following: displaying an image in response to a fourth comment message including a first interactive element and a triggering operation on the first interactive element; displaying a video in response to a fourth comment message including a second interactive element and a triggering operation on the second interactive element; and displaying an interface of a second object in response to a fourth comment message including a third interactive element and a triggering operation on the third interactive element, wherein the interface of the second object includes information about the second object and a retrieval control, the retrieval control being used to retrieve the second object.

[0088] For example, the first, second, and third interactive elements can be displayed as icons, text links, thumbnails, etc., and are not limited to the examples given. The interface of the second object can be displayed in the form of windows, overlays, panels, cards, etc., and is not limited to the examples given. Users can directly access the second object through its interface.

[0089] The above method allows the fourth comment information to include one or more interactive elements, enabling users to further view images, videos, and second objects, thus enhancing the interactive experience.

[0090] like Figure 7As shown, the live stream interface 300 displays the third comment information 701, and the virtual assistant can directly reply with the fourth comment information 702 within the live stream interface 300. The third comment information 701 and the fourth comment information 702 can be displayed within the same encapsulated element. For example... Figure 7 As shown, the fourth comment information 702 may include the third interactive element of the second object.

[0091] In one scenario, in response to a user posting other comments within a specified time prior to the publication time of the third comment, the fourth comment references the third comment; otherwise, the fourth comment does not reference the third comment. This allows users to more accurately determine that the fourth comment is a response to the third comment, thus improving the user experience.

[0092] In one scenario, in response to the association of the third comment information with the second object, the fourth comment information is determined based on the information of the third comment information and the second object. If the second object corresponding to the third comment information can be identified, the virtual assistant can directly reply with the fourth comment information related to the second object.

[0093] In one scenario, in response to the inability to determine the object associated with the third comment information, the fourth comment information includes a second entry point corresponding to the virtual assistant. This second entry point is used to trigger the display of the conversation interface. If the object associated with the third comment information cannot be determined, the user can be guided to the conversation interface to engage in a conversation with the virtual assistant.

[0094] In one scenario, the fourth comment information includes the second entry point corresponding to the virtual assistant, and the interaction method further includes: in response to the triggering operation of the second entry point, displaying the conversation interface, and displaying the third comment information in the conversation interface as the first conversation message.

[0095] The third comment information can be displayed as the first conversation message in the conversation interface. At least one candidate object can also be displayed for the user to select. Please refer to the above embodiments, which will not be repeated here.

[0096] The above method displays a second entry point in the fourth comment information, allowing users to quickly and conveniently access the corresponding conversation interface of the virtual assistant for detailed consultation, thus improving user efficiency and convenience, and enhancing the interactive experience.

[0097] In one scenario, the fourth comment information is used to query the object related to the third comment information and guide the triggering operation of the second entry point.

[0098] For example, the fourth comment could be, "Which person do you want to ask about? You can send me a private message." This allows us to determine the intent of the third comment, identifying whether it's directed at an unreachable or already reached person. The fourth comment can be determined based on this intent; different intents can correspond to different fourth comment messages.

[0099] The above method uses the fourth comment information to guide users to trigger the second entry point and engage in a conversation with the virtual assistant, thereby effectively solving users' problems and improving their interactive experience.

[0100] In one scenario, if the object associated with the third comment information is not determined and the number of times the associated object is not determined does not exceed a specified number, the fourth comment information is displayed. The fourth comment information is used to guide the user to trigger the second or first entry point; otherwise, the fourth comment information is not displayed.

[0101] For example, in response to the posting of a third comment, the system determines the user's intent. If the user's intent includes an intent towards an unacquired object or an intent towards an acquired object, it determines to invoke the virtual assistant to reply. It then determines whether the third comment is associated with an object. If the third comment is associated with a second object, a fourth comment is generated based on the information from the third comment and the second object and displayed on the live streaming interface. If the object associated with the third comment is not determined, the fourth comment is displayed to guide the user into a conversation with the virtual assistant.

[0102] Users may post multiple comments without being able to identify the associated object. If this exceeds a specified number of times, the user can no longer be guided to trigger the second entry point, reducing the interference of duplicate information. A first specified number of times can be set for a single live stream, and a second specified number of times for the same user within a unit of time. If the number of times a user fails to identify the associated object within a single live stream does not exceed the first specified number, and the number of times a user fails to identify the associated object within a unit of time does not exceed the second specified number, then a fourth comment will be displayed.

[0103] In one scenario, if the object associated with the third comment information is not determined and the time elapsed since the last time the associated object was not determined exceeds a specified time, the fourth comment information is displayed. The fourth comment information is used to guide the user to trigger the second or first entry point; otherwise, the fourth comment information is not displayed.

[0104] If the user has already been guided to trigger the second or first entry point within a short period of time, the same information can be avoided by not displaying it repeatedly, thus reducing the interference of repetitive information on the user.

[0105] In one scenario, in response to displaying the fourth comment, the third comment is displayed in the replied category of the anchor's interactive information interface.

[0106] like Figure 8 As shown, the broadcaster can display an interactive information interface 800, which includes multiple categories of interactive information. A third comment 802 can be displayed in the replied category 801. The broadcaster can then choose not to reply to the third comment, reducing their response workload. For example, in response to a third comment being associated with a second object and a fourth comment being displayed, the third comment is displayed in the replied category of the broadcaster's interactive information interface. If the second object is identified, the fourth comment is considered a valid reply, and the third comment can be categorized as a replied comment.

[0107] To facilitate users in triggering conversations with the virtual assistant, a third entry point can also be displayed, which is described below.

[0108] In one scenario, the interaction method further includes: displaying a first input area on the live streaming interface; displaying a third entry point associated with the first input area in response to a trigger operation on the first input area; and displaying a session interface in response to a trigger operation on the third entry point.

[0109] For example, the live streaming interface displays an inactive first input area and a first entry point. In response to a trigger operation on the first input area, the activated first input area is displayed, and a third entry point is displayed in association with the first input area.

[0110] like Figure 3 As shown, the live streaming interface 300 displays an inactive first input area 301. In response to a trigger operation on the first input area, the following can be displayed: Figure 9 The live stream interface shown is 300. (As shown) Figure 9 As shown, the live streaming interface 300 displays the first input area 301 in an active state, and the third entry 901 is displayed in association with the first input area 301. The session interface is displayed in response to the trigger operation of the third entry 901.

[0111] The above method associates the third entry point with the first input area, allowing users to easily and quickly trigger the display of the conversation interface and improve the interactive experience.

[0112] In one scenario, in response to a closing action on the session interface, a closing animation is displayed. This could be, for example, an animation showing the session interface being added to the first entry point, or more, but is not limited to the examples given.

[0113] In one scenario, the conversation interface is used for conversations among multiple members in a group, including virtual assistants and one or more service assistants corresponding to the live stream initiator.

[0114] One or more service assistants can be human customer service representatives, or other virtual assistants, etc., and are not limited to the examples given. For example, in response to a virtual assistant being unable to reply to a message in the first session, one or more service assistants are added to a group. For example, an object provided by the live stream initiator can correspond to one or more object providers, and in response to determining that a message in the first session is associated with a third object, the service assistant of the object provider of the third object is added to the group.

[0115] The above method, which establishes groups to communicate with users, can more accurately answer users' inquiries and improve the user's interactive experience.

[0116] The foregoing embodiments described a virtual assistant that can respond to user conversation messages and comments. The virtual assistant can correspond to a machine learning model. This machine learning model may include an intent recognition module, which can be used to identify the user's intent, such as an intent regarding an unacquired object or an intent regarding an acquired object. Further, intents regarding unacquired objects may include inquiring about details, restocking information, attribute information, service information, usage information, etc., and are not limited to the examples given. Intents regarding acquired objects may include inquiring about logistics information, service guarantee information, order information, problem feedback, etc., and are not limited to the examples given. The machine learning model can identify the user's intent based on conversation messages (or comment information), context, and the user's historical behavior.

[0117] The machine learning model can also include a response module. For example, the response module can be trained based on training data, which includes primary basic data of the objects provided by the live streamer and secondary basic data of the users. For objects not yet acquired, the primary basic data includes at least one of the following: object identifier, one or more attribute information, usage instructions, activity information, related service information, precautions, and logistics and inventory information. For acquired objects, the primary basic data can include at least one of the following: real-time order information, logistics tracking data, after-sales rules, feedback data, and historical session context. The primary basic data can also include live stream data. The secondary basic data includes at least one of the following: historical session data, historical comment data, historical browsing data, historical acquisition data, and historical sharing behavior data for each user. The machine learning model is trained based on the above training data, enabling it to determine the associated objects based on the user's session messages and generate response messages.

[0118] For example, when a user sends a conversation message (or comment), the system retrieves the user's historical behavior data. Using a machine learning model, it identifies a third object based on the user's historical behavior data, the conversation message (or comment), the initial basic data of the object provided by the live streamer, and the live stream content. The time range of the live stream content can be determined based on the sending time and specified duration of the conversation message (or comment). The live stream content can be used to help determine whether the conversation message (or comment) is related to the currently discussed object. The specific data included in the initial basic data can be determined based on the user's intent as determined by the intent module.

[0119] This application also provides an interactive device, which is described below in conjunction with... Figure 10 Describe it.

[0120] Figure 10 These are structural diagrams of some embodiments of the interactive device of this application. For example... Figure 10 As shown, the interactive device 100 in this embodiment includes: a first display module 1010, a second display module 1020, and a third display module 1030.

[0121] The first display module 1010 is configured to display the first entry point on the live streaming interface.

[0122] The second display module 1020 is configured to display a conversation interface in response to a trigger operation on the first entry point, wherein the conversation interface is used to have a conversation with the virtual assistant.

[0123] The third display module 1030 is configured to display a second session message in response to the first session message on the session interface. The first session message is associated with an object provided by the live stream initiator, and the second session message is a reply message from the virtual assistant to the first session message.

[0124] The aforementioned interactive device displays a first entry point on the live streaming interface. In response to triggering the first entry point, a conversation interface for interacting with the virtual assistant is displayed. In response to a first conversation message, a second conversation message, in which the virtual assistant replies to the first conversation message, is displayed on the conversation interface. The first conversation message can be associated with an object provided by the live streaming initiator. This interactive device provides a virtual assistant for the live stream and directly displays a first entry point on the live streaming interface for interacting with the virtual assistant. Users (or viewers) can trigger the display of the conversation interface at any time during the live stream through the first entry point and interact with the virtual assistant, asking questions associated with the object provided by the live streaming initiator. Through the first entry point and the virtual assistant, the convenience and efficiency of users (or viewers) consulting with objects during the live stream are improved, and the virtual assistant can respond to users more efficiently, enhancing the user's interactive experience during the live stream.

[0125] In one scenario, the first display module 1010 is configured to display a first input area on the live streaming interface and a first entry point outside the first input area, wherein the first input area is used to input comment information.

[0126] In one scenario, the second display module 1020 is configured to display a session interface in response to inputting first comment information in the first input area and triggering an operation on the first entry point, and to display the first comment information in the session interface as a first session message.

[0127] In one scenario, the second display module 1020 is configured to display the second comment information in a comment area in response to inputting and publishing the second comment information in the first input area, wherein the comment area is displayed on the live streaming interface; and to display a conversation interface in response to a triggering operation on the first entry point and no reply to the second comment information, and to display the second comment information in the conversation interface as a first conversation message.

[0128] In one scenario, the third display module 1030 is configured to, in response to a first session message, display information about at least one candidate object based on the first session message, wherein the at least one candidate object belongs to an object provided by the live stream initiator; and in response to a selection operation of a first object among the at least one candidate object, display a second session message in the session interface based on the information of the first object.

[0129] In one scenario, at least one candidate object includes at least one unacquired object, which includes at least one of a first candidate object, a second candidate object, and a third candidate object. The first candidate object is an object being explained in the live broadcast and the difference between the explanation time and the current time is less than a threshold. The second candidate object is an object that has been viewed. The third candidate object is an object other than the first and second candidate objects. The first candidate object and the second candidate object are different. The third display module 1030 is configured to display a first information item for each unacquired object. The first information item includes the identifier and first state of the unacquired object. The first states of the first candidate object, the second candidate object, and the third candidate object are different from each other.

[0130] In one scenario, at least one candidate object includes at least one acquired object, and at least one acquired object includes at least one of a fourth candidate object and a fifth candidate object. The fourth candidate object is associated with the live stream, and the fifth candidate object is not related to the live stream. The third display module 1030 is configured to display a second information item for each acquired object, wherein the second information item includes the identifier of the acquired object and a second status. The second status is used to indicate the processing progress of the acquired object by the live stream initiator.

[0131] In one scenario, for each acquired object, in response to a first session message including a modification request related to the acquired object, a second session message includes a modification result referenced by the virtual assistant, the modification result being generated based on the modification request and sent to the virtual assistant.

[0132] In one scenario, the interactive device further includes a fourth display module 1040, configured to display the third comment information in a comment area in response to the posting operation of the third comment information, wherein the comment area is displayed on the live streaming interface; and to display a fourth comment information in the comment area, wherein the fourth comment information is a reply from the virtual assistant to the third comment information.

[0133] In one scenario, the fourth comment information includes at least one of the following: text, a first interactive element corresponding to an image, a second interactive element corresponding to a video, and a third interactive element corresponding to a second object.

[0134] In one scenario, the fourth display module 1040 is further configured to perform at least one of the following: displaying an image in response to fourth comment information including a first interactive element and a trigger operation on the first interactive element; displaying a video in response to fourth comment information including a second interactive element and a trigger operation on the second interactive element; and displaying an interface of a second object in response to fourth comment information including a third interactive element and a trigger operation on the third interactive element, wherein the interface of the second object includes information about the second object and a retrieval control for retrieving the second object.

[0135] In one scenario, the fourth comment information includes the second entry point corresponding to the virtual assistant, and the second display module 1020 is further configured to display a session interface in response to a trigger operation on the second entry point, and to display the third comment information in the session interface as the first session message.

[0136] In one scenario, the fourth comment information is used to query the object related to the third comment information and guide the triggering operation of the second entry point.

[0137] In one scenario, the first display module 1010 is further configured to display a first input area on the live streaming interface; in response to a trigger operation on the first input area, a third entry point is displayed in association with the first input area; the second display module 1020 is further configured to display a session interface in response to a trigger operation on the third entry point.

[0138] In one scenario, the conversation interface is used for conversations among multiple members in a group, including virtual assistants and one or more service assistants corresponding to the live stream initiator.

[0139] In one scenario, the third display module 1030 is configured to display the third object as at least one candidate object in response to determining that the first session message is associated with the third object, wherein the third object is determined based on the first session message and the object provided by the live broadcast initiator, and the third object may be the same as or different from the first object.

[0140] This application also provides an electronic device, Figure 11 A block diagram of an electronic device according to some embodiments of this application is shown.

[0141] like Figure 11 As shown, the electronic device 11 includes: a processor 112; and a memory 111 coupled to the processor for storing instructions, which, when executed by the processor 112, cause the processor to perform the interactive method of any embodiment of this application.

[0142] The aforementioned electronic device displays a primary entry point on the live streaming interface. In response to triggering this entry point, a conversation interface for interacting with the virtual assistant is displayed. In response to a first conversation message, a second conversation message, in which the virtual assistant replies to the first conversation message, is displayed on the conversation interface. This first conversation message can be associated with an object provided by the live streaming initiator. The electronic device provides a virtual assistant for the live stream and directly displays a primary entry point on the live streaming interface for interacting with the virtual assistant. Users (or viewers) can trigger the display of the conversation interface at any time during the live stream through this primary entry point and interact with the virtual assistant, asking questions associated with the object provided by the live streaming initiator. The primary entry point and virtual assistant setup improve the convenience and efficiency of users (or viewers) consulting with objects during the live stream, and the virtual assistant can respond to users more efficiently, enhancing the user's interactive experience during the live stream.

[0143] Memory 111 is used to store one or more computer-readable instructions. Memory 111 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 111 may, for example, store operating systems, applications, bootloaders, databases, and other programs, as well as various applications and various data.

[0144] The processor 112 is configured to execute computer-readable instructions to implement the interactive method of any of the foregoing embodiments. Specific implementations of each step of the method can be found in the above embodiments; repeated details will not be elaborated upon here.

[0145] The processor 112 can be various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The central processing unit (CPU) can be based on x86 or ARM architectures, etc.

[0146] The processor 112 and the memory 111 can communicate with each other directly or indirectly. For example, the processor 112 and the memory 111 can communicate via a network. The network can include a wireless network, a wired network, and / or any combination of wireless and wired networks. The processor 112 and the memory 111 can also communicate with each other via a system bus, which is not limited in this application.

[0147] It should be noted that Figure 11 The components of the electronic device 11 shown are merely exemplary and not limiting; the electronic device 11 may have other components as needed for the actual application. The processor 112 can control other components in the electronic device 11 to perform desired functions.

[0148] Electronic device 11 can be implemented by software, firmware and / or hardware, and can be integrated into a device with relevant applications installed.

[0149] Figure 12 A block diagram of an electronic device according to some embodiments of this application is shown.

[0150] Figure 12 The electronic device 12 shown can be a computer system with a dedicated hardware structure, which can perform corresponding functions when the relevant application is installed.

[0151] Electronic devices include, but are not limited to, various mobile terminals and fixed terminals such as digital televisions and desktop computers.

[0152] like Figure 12 As shown, the Central Processing Unit (CPU) 121 performs various processes based on a program stored in the Read-Only Memory (ROM) 122 or a program loaded from the storage section 128 into the Random Access Memory (RAM) 123. The RAM 123 stores data required as needed when the CPU 121 performs various processes, etc. The CPU is merely exemplary; it could also be other types of processors, such as the various processors described above. The ROM 122, RAM 123, and storage section 128 can be various forms of computer-readable storage media. It should be noted that although... Figure 12The image shows ROM 122, RAM 123 and storage section 128, but one or more of them may be combined or located in the same or different memory or storage modules.

[0153] CPU 121, ROM 122 and RAM 123 are interconnected via bus 124. Input / output interface 125 is also connected to bus 124.

[0154] The following components are connected to the input / output interface 125: input section 126, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 127, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 1210, including hard disk, magnetic tape, etc.; and communication section 129, including network interface cards such as LAN cards, modems, etc. Communication section 129 allows communication processing via a network such as the Internet. It is easy to understand that, although... Figure 12 The portion of the electronic device 12 shown communicates via bus 124, but it may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0155] As needed, drive 1210 is also connected to input / output interface 125. Removable media 1211, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 1210 as needed, so that computer programs read from them can be installed into storage section 128 as needed.

[0156] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or from a storage medium such as a removable medium 1211.

[0157] According to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. This application also provides a computer program product, including a computer program that, when executed by a processor, implements the interactive method of any embodiment of this application.

[0158] The aforementioned computer program product displays a primary entry point on the live streaming interface. In response to triggering this entry point, a conversation interface for interacting with the virtual assistant is displayed. In response to a first conversation message, a second conversation message, in which the virtual assistant replies to the first conversation message, is displayed on the conversation interface. This first conversation message can be associated with an object provided by the live streaming initiator. The aforementioned computer program product provides a virtual assistant for live streaming and directly displays a primary entry point on the live streaming interface for interacting with the virtual assistant. Users (or viewers) can trigger the display of the conversation interface at any time during the live stream through this primary entry point and interact with the virtual assistant, asking questions associated with the object provided by the live streaming initiator. Through the primary entry point and the virtual assistant, the convenience and efficiency of users (or viewers) consulting with objects during the live stream are improved, and the virtual assistant can respond to users more efficiently, enhancing the user's interactive experience during the live stream.

[0159] For example, some embodiments of this application include a computer program product that, when run on a computer, causes the computer to implement the interactive method of any of the foregoing embodiments. The computer program product includes computer instructions carried on a computer-readable medium, containing program code for performing the methods shown in the flowchart. In such embodiments, the computer instructions can be downloaded and installed from a network via communication section 129, or installed from storage section 128, or installed from ROM 122. When the computer program is executed by CPU 121, the interactive method of the embodiments of this application is performed.

[0160] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the interactive method of any embodiment of this application.

[0161] The aforementioned computer-readable storage medium displays a first entry point on the live streaming interface. In response to triggering the first entry point, a conversation interface for interacting with the virtual assistant is displayed. In response to a first conversation message, a second conversation message, in which the virtual assistant replies to the first conversation message, is displayed on the conversation interface. The first conversation message can be associated with an object provided by the live streaming initiator. This computer-readable storage medium provides a virtual assistant for the live streaming and directly displays a first entry point on the live streaming interface for interacting with the virtual assistant. Users (or viewers) can trigger the display of the conversation interface at any time during the live stream through the first entry point and interact with the virtual assistant, asking questions associated with the object provided by the live streaming initiator. Through the first entry point and the virtual assistant, the convenience and efficiency of users (or viewers) consulting with objects during the live stream are improved, and the virtual assistant can respond to users more efficiently, enhancing the user's interactive experience during the live stream.

[0162] It should be noted that, in the context of this application, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0163] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0164] Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Computer instructions are stored on the computer-readable storage medium, which, when executed by a processor, implement the interactive methods of any of the foregoing embodiments.

[0165] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0166] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0167] In one embodiment, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the methods of any of the foregoing embodiments. For example, the instructions may be embodied in computer program code.

[0168] In embodiments of this application, computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer via any type of network, or it can be connected to an external computer.

[0169] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0170] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0171] While specific embodiments of this application have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of this application. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this application. The scope of this application is defined by the appended claims.

Claims

1. An interaction method, comprising: The primary entry point is displayed on the live stream interface; In response to a trigger operation on the first entry point, a conversation interface is displayed, wherein the conversation interface is used to have a conversation with the virtual assistant; In response to the first session message, a second session message is displayed on the session interface, wherein the first session message is associated with an object provided by the live stream initiator, and the second session message is a reply message from the virtual assistant to the first session message.

2. The interaction method according to claim 1, wherein, The first entry point displayed on the live streaming interface includes: The live streaming interface displays a first input area, and the first entry point is displayed outside the first input area. The first input area is used to input comment information.

3. The interaction method according to claim 2, wherein, The step of displaying the session interface in response to a trigger operation on the first entry point includes: In response to the input of first comment information in the first input area and the triggering operation of the first entry point, the conversation interface is displayed, and the first comment information is displayed in the conversation interface as the first conversation message.

4. The interaction method according to claim 2, wherein, The step of displaying the session interface in response to a trigger operation on the first entry point includes: In response to the input of second comment information in the first input area and the posting of the second comment information, the second comment information is displayed in the comment area, wherein the comment area is displayed on the live streaming interface; In response to a triggering operation on the first entry point and no reply to the second comment information, the conversation interface is displayed, and the second comment information is displayed in the conversation interface as the first conversation message.

5. The interaction method according to claim 1, wherein, The step of displaying a second session message on the session interface in response to a first session message includes: In response to the first session message, based on the first session message, information of at least one candidate object is displayed, wherein the at least one candidate object belongs to an object provided by the live stream initiator; In response to the selection operation of a first object among the at least one candidate object, the second session message is displayed in the session interface based on the information of the first object.

6. The interaction method according to claim 5, wherein, The at least one candidate object includes at least one unacquired object, which includes at least one of a first candidate object, a second candidate object, and a third candidate object. The first candidate object is an object being discussed in the live stream, and the difference between the discussion time and the current time is less than a threshold. The second candidate object is an object that has already been viewed. The third candidate object is an object other than the first candidate object and the second candidate object. The first candidate object and the second candidate object are different. The information for displaying at least one candidate object includes: For each unacquired object, a first information item is displayed, wherein the first information item includes the identifier and first state of the unacquired object, and the first state corresponding to the first candidate object, the second candidate object and the third candidate object are different from each other.

7. The interaction method according to claim 5, wherein, The at least one candidate object includes at least one acquired object, and the at least one acquired object includes at least one of a fourth candidate object and a fifth candidate object. The fourth candidate object is associated with the live stream, and the fifth candidate object is unrelated to the live stream. The information for displaying at least one candidate object includes: For each acquired object, a second information item is displayed, wherein the second information item includes the identifier of the acquired object and a second status, the second status being used to indicate the processing progress of the acquired object by the live broadcast initiator.

8. The interaction method according to claim 7, wherein, For each acquired object, in response to the first session message including a modification request related to the acquired object, the second session message includes a modification result referenced by the virtual assistant, the modification result being generated based on the modification request and sent to the virtual assistant.

9. The interaction method according to any one of claims 1-8, further comprising: In response to the posting of a third comment, the third comment is displayed in the comment area, wherein the comment area is displayed on the live streaming interface; A fourth comment is displayed in the comment area, wherein the fourth comment is a response from the virtual assistant to the third comment.

10. The interaction method according to claim 9, wherein, The fourth comment information includes at least one of the following: a first interactive element corresponding to text or an image, a second interactive element corresponding to a video, and a third interactive element corresponding to a second object.

11. The interaction method according to claim 10, further comprising at least one of the following: In response to the fourth comment information including the first interactive element and the triggering operation on the first interactive element, the image is displayed; In response to the fourth comment information including the second interactive element and the triggering operation on the second interactive element, the video is displayed; In response to the fourth comment information, including the third interactive element and the triggering operation on the third interactive element, the interface of the second object is displayed, wherein, The interface of the second object includes information about the second object and a retrieval control, which is used to retrieve the second object.

12. The interaction method according to claim 9, wherein, The fourth comment information includes the second entry point corresponding to the virtual assistant, and the interaction method further includes: In response to the triggering operation of the second entry, the session interface is displayed, and the third comment information is displayed in the session interface as the first session message.

13. The interaction method according to claim 12, wherein, The fourth comment information is used to query the object related to the third comment information and guide the triggering operation of the second entry.

14. The interaction method according to any one of claims 1-8, further comprising: The first input area is displayed on the live streaming interface; In response to a trigger operation on the first input area, a third entry point is displayed in association with the first input area; In response to a trigger operation on the third entry point, the session interface is displayed.

15. The interaction method according to any one of claims 1-8, wherein, The chat interface is used for multiple members in a group to have a conversation. The multiple members include the virtual assistant and one or more service assistants corresponding to the live stream initiator.

16. The interaction method according to claim 5, wherein, The step of displaying information about at least one candidate object based on the first session message includes: In response to determining that the first session message is associated with a third object, the third object is displayed as one of the at least one candidate objects, wherein the third object is determined based on the first session message and the object provided by the live stream initiator, and the third object may be the same as or different from the first object.

17. An interactive device, comprising: The first display module is configured to display the first entry point on the live streaming interface; The second display module is configured to display a conversation interface in response to a trigger operation on the first entry point, wherein the conversation interface is used to have a conversation with the virtual assistant; The third display module is configured to display a second session message in response to a first session message on the session interface, wherein the first session message is associated with an object provided by the live stream initiator, and the second session message is a reply message from the virtual assistant to the first session message.

18. An electronic device comprising: processor; as well as A memory coupled to the processor is used to store instructions that, when executed by the processor, cause the processor to perform the interactive method of any one of claims 1 to 16.

19. A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the interactive method of any one of claims 1 to 16.

20. A computer program product comprising a computer program that, when executed by a processor, implements the interactive method of any one of claims 1 to 16.

Images