Live broadcast interaction method and device

Abstract

The embodiment of the invention discloses a live broadcast interaction method and device, and the main technical scheme comprises the steps: displaying a live broadcast picture, the live broadcast picture comprising a plurality of anchor users, and the plurality of anchor users at least comprising a target anchor; at least receiving a binding relationship between a character recognition result corresponding to the target anchor and the anchor identification information from the server side; and in response to an operation of triggering resource transfer, sending information of a target resource and anchor identification information of a target anchor to a server, so as to transfer the target resource from an account of the audience user to an account of the target anchor, the operation of triggering resource transfer comprises a first operation of selecting a target resource in the live broadcast picture and a second operation performed on a picture region corresponding to the target anchor, and the anchor identification information of the target anchor is determined based on a character recognition result of the target anchor and a binding relationship. The interaction between the audience user and the anchor user can be improved in a multi-user live broadcast scene, and the experience feeling of the audience user is further improved.

Description

Technical Field

[0001] This application relates to the field of Internet application technologies, and particularly to a live interactive method and apparatus. Background Art

[0002] With the continuous development of the Internet, live broadcasts have become popular among a large number of viewers. During the process of viewers watching a live broadcast, they can transfer resources to their favorite anchor users, such as sending virtual resources. However, in the scenario of multiple people jointly hosting a live broadcast, the interactivity and viewing experience of the viewer users still need to be improved. Summary of the Invention

[0003] In view of this, this application provides a live interactive method to improve the interactivity between viewer users and the anchor and the viewing experience.

[0004] This application provides the following solutions:

[0005] According to a first aspect, a live interactive method is provided, and the method includes:

[0006] Display a live broadcast screen, where the live broadcast screen includes multiple anchor users, and the multiple anchor users at least include a target anchor;

[0007] Receive at least from the server the binding relationship between the person recognition result corresponding to the target anchor and the anchor identification information;

[0008] In response to an operation triggering resource transfer, where the operation triggering resource transfer includes a first operation of selecting a target resource in the live broadcast screen and a second operation on the screen area corresponding to the target anchor, send the information of the target resource and the anchor identification information of the target anchor to the server, so as to transfer the target resource from the viewer user's account to the target anchor's account, where the anchor identification information of the target anchor is determined based on the person recognition result of the target anchor and the binding relationship.

[0009] According to an implementable manner in an embodiment of this application, the person recognition result of the target anchor is obtained by using a face recognition model, and the person recognition result is a face identifier:

[0010] The binding relationship is the binding relationship between the face identifier and the anchor identification information.

[0011] According to an implementable manner in an embodiment of this application, the second operation on the screen area corresponding to the target anchor includes:

[0012] The operation triggered for the person area corresponding to the target anchor, which is generated based on the prompt information in the live broadcast screen, and the prompt information is displayed in the live broadcast screen in response to the first operation; and / or,

[0013] The operation triggered for the first component used to prompt the selection of the target anchor, and the first component is displayed in the screen area corresponding to the target anchor in the live broadcast screen in response to the first operation.

[0014] According to an implementable manner in an embodiment of the present application, the method further includes:

[0015] In response to the first display of the first component in the live broadcast screen, display a first special effect for the first component; and / or,

[0016] In response to no trigger operation for the first component being detected within a preset duration, display a first special effect for the first component.

[0017] According to an implementable manner in an embodiment of the present application, the step of, in response to the operation of triggering resource transfer, sending the information of the target resource and the anchor identification information of the target anchor to the server side includes:

[0018] In response to the first operation of selecting the target resource in the live broadcast screen, based on the person recognition results of at least one anchor user among the multiple anchor users and the binding relationship, determine the anchor identification information of the at least one anchor user, and the at least one anchor user includes the target anchor;

[0019] In the screen areas corresponding to the at least one anchor user in the live broadcast screen, respectively display the first component, and the first component includes the anchor identification information of the corresponding anchor user;

[0020] In response to the operation of the first component corresponding to the target anchor being triggered, send the information of the target resource and the anchor identification information of the target anchor to the server side.

[0021] According to an implementable manner in an embodiment of the present application, the method further includes:

[0022] In response to receiving the message of successful resource transfer, display a second special effect in the screen area corresponding to the target anchor in the live broadcast screen, and the second special effect is used to prompt the successful transfer of the target resource.

[0023] According to a second aspect, there is provided a live broadcast interaction method, which is applied to the client of an anchor user, and the method includes:

[0024] Collect and display the live broadcast screen, where the live broadcast screen includes multiple host users, and the multiple host users at least include the target host;

[0025] In response to an operation triggering the binding function, the operation triggering the binding function includes a third operation on the screen area corresponding to the target host in the live broadcast screen, and display a configuration panel, where the configuration panel includes the host identification information of the multiple host users;

[0026] In response to selecting one of the host identification information from the configuration panel, send the binding relationship between the person recognition result of the target host and the selected host identification information to the server side.

[0027] According to an implementable manner in the embodiments of the present application, the third operation on the screen area corresponding to the target host in the live broadcast screen includes:

[0028] An operation in which the person area corresponding to the target host is triggered, and this operation is generated according to the prompt information in the live broadcast screen, and the prompt information is displayed in the live broadcast screen in response to identifying a new person recognition result from the multiple host users; and / or,

[0029] An operation in which a second component for prompting to bind the target host is triggered, and the second component is displayed in the live broadcast screen in response to identifying a new person recognition result from the multiple host users.

[0030] According to an implementable manner in the embodiments of the present application, the step of, in response to selecting one of the host identification information from the configuration panel, sending the binding relationship between the person recognition result of the target host and the selected host identification information to the server side includes:

[0031] In response to selecting one of the host identification information from the configuration panel, display a third component for binding the person recognition result of the target host and the selected host identification information;

[0032] In response to the positive feedback of the host user on the third component, send the binding relationship between the person recognition result of the target host and the selected host identification information to the server side.

[0033] According to an implementable manner in the embodiments of the present application, the method further includes:

[0034] In response to receiving a message indicating successful resource transfer, where the resource transfer includes transferring target resources from the account of the audience user to the account of the target host, display a third special effect in the screen area corresponding to the target host in the live broadcast screen, and the third special effect is used to prompt the successful transfer of the target resources.

[0035] According to a third aspect, a live interaction method is provided, which is applied to a server side. The method includes:

[0036] Receiving, from the client of the host user, the binding relationship between the person recognition result of the target host and the host identification information;

[0037] Sending the binding relationship to the client of the viewer user;

[0038] Receiving, from the client of the viewer user, the information of the target resource and the host identification information of the target host, and determining the account information of the target host according to the host identification information of the target host;

[0039] Transferring the target resource from the account of the viewer user to the account of the target host.

[0040] According to a fourth aspect, a live interaction device is provided, which is set on the client of the viewer user. The device includes:

[0041] A first display unit, configured to display a live broadcast screen, where the live broadcast screen includes a plurality of host users, and the plurality of host users at least include a target host;

[0042] A first receiving unit, configured to receive at least the binding relationship between the person recognition result corresponding to the target host and the host identification information from the server side;

[0043] A first sending unit, configured to, in response to an operation of triggering resource transfer, where the operation of triggering resource transfer includes a first operation of selecting a target resource in the live broadcast screen and a second operation on the screen area corresponding to the target host, send the information of the target resource and the host identification information of the target host to the server side, so as to transfer the target resource from the account of the viewer user to the account of the target host, where the host identification information of the target host is determined based on the person recognition result of the target host and the binding relationship.

[0044] According to a fifth aspect, a live interaction device is provided, which is set on the client of the host user. The device includes:

[0045] A second display unit, configured to collect and display a live broadcast screen, where the live broadcast screen includes a plurality of host users, and the plurality of host users at least include a target host;

[0046] The second display unit is further configured to respond to an operation of triggering a binding function, where the operation of triggering the binding function includes a third operation performed on a screen area corresponding to the target anchor in the live broadcast screen, and display a configuration panel, where the configuration panel includes anchor identification information of the multiple anchor users;

[0047] The second sending unit is configured to respond to selecting one of the anchor identification information from the configuration panel and send a binding relationship between the person recognition result of the target anchor and the selected anchor identification information to the server side.

[0048] According to a sixth aspect, there is provided a live broadcast interaction device, which is arranged on the server side, and the device includes:

[0049] The second receiving unit is configured to receive a binding relationship between the person recognition result of the target anchor and the anchor identification information from the client of the anchor user;

[0050] The third sending unit is configured to send the binding relationship to the client of the audience user;

[0051] The second receiving unit is further configured to receive information of the target resource and the anchor identification information of the target anchor from the client of the audience user;

[0052] The resource transfer unit is configured to determine the account information of the target anchor according to the anchor identification information of the target anchor, and transfer the target resource from the account of the audience user to the account of the target anchor.

[0053] According to a seventh aspect, there is provided a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in any one of the first aspect, the second aspect, and the third aspect are implemented.

[0054] According to an eighth aspect, there is provided an electronic device, including:

[0055] One or more processors; and

[0056] A memory associated with the one or more processors, where the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, the steps of the method described in any one of the first aspect, the second aspect, and the third aspect are executed.

[0057] According to a ninth aspect, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any one of the first aspect, the second aspect, and the third aspect are implemented.

[0058] According to the specific embodiments provided in the present application, the present application discloses the following technical effects:

[0059] 1) Through the present application, the host identification information of the target host can be determined based on the binding relationship between the person recognition result corresponding to the target host and the host identification information, so as to transfer the target resource from the viewer user's account to the target host's account. On the one hand, through the person recognition result, the target host that the viewer user wants to transfer the resource to can be accurately located from the multi-person live broadcast screen, realizing precise interaction, enhancing the viewing experience of the viewer user, and conforming to the current trend of developing towards deeper interaction and diversified experience; on the other hand, even if the viewer user does not know the host identification information of the target host, only the second operation on the screen area corresponding to the target host can be used to perform precise resource transfer, improving the interaction efficiency and experience between the viewer user and the host user.

[0060] 2) Through the face recognition model, precise face positioning is achieved, enabling the viewer user to quickly and conveniently transfer the target resource to the host user they like in the live broadcast screen, enhancing the interaction experience between the viewer user and the host user, and improving the sense of participation and satisfaction of the viewer user.

[0061] 3) In the present application, the second operation can be an operation triggered by the person area corresponding to the target host, or an operation triggered by the first component used to prompt the selection of the target host. Different technical means can be adopted for different real-world scenarios, and the implementation methods are more diverse and flexible, further enhancing the viewing experience of the viewer user.

[0062] 4) In order to enhance the prompt guidance effect and further improve the visual experience of the viewer user, the present application can also display the first special effect for the first component to remind the viewer user to select their favorite host user for interaction.

[0063] 5) The present application can display the host identification information of the corresponding host user in the first component to prompt the viewer user to accurately select their favorite host user, and the process is simpler and faster, improving the interaction efficiency and interaction experience of the viewer user.

[0064] 6) When the resource transfer is successful, the second special effect is displayed in the screen area corresponding to the target host. In this way, the second special effect can be displayed in the screen area corresponding to the target host. On the one hand, it can provide precise result feedback for the user to transfer the target resource to a specific target host, and on the other hand, it can also avoid full-screen special effects from interfering with other host users or viewer users, reducing information overload, and thus improving the viewing experience of the viewer user.

[0065] 7) The client of the host user can bind the host identification information of multiple host users with the person recognition result, so that when the viewer user transfers resources, the resources can be accurately transferred to the account of the favorite host user. Moreover, for a live broadcast, there is no need to perform resource sharing subsequently, but the resources are transferred to the corresponding host user's account during the resource transfer, saving labor costs and improving the efficiency of the live broadcast.

[0066] 8) The third operation can be an operation triggered by the person area corresponding to the target host, or an operation triggered by the second component used to prompt the target host. Different technical means can be adopted for different real-world scenarios to further enhance the experience and satisfaction of the host user. No matter which way is used to trigger the binding function, the binding efficiency of the host user can be improved.

[0067] 9) When it is determined to bind the person recognition result of the target host with the host identification information selected in the configuration panel, further confirmation can be performed through the third component, avoiding the waste of time resources caused by the wrong selection of the host user, and also prompting the host user to perform the binding accurately, improving the live broadcast experience and binding efficiency of the host user.

[0068] 10) When the resource transfer is successful, a third special effect is displayed in the screen area corresponding to the target host. In this way, the third special effect can be displayed in the screen area corresponding to the target host. On the one hand, it can provide an accurate result display for the user to transfer the target resources to a specific target host. On the other hand, it can avoid full-screen special effects from interfering with other host users or viewer users, reducing information overload, and thus improving the experience of the host user.

[0069] 11) For the server side, when the viewer user enters the live broadcast room, the binding relationship obtained from the client of the host user can be sent to the client of the viewer user, laying a foundation for the subsequent transfer of resources by the viewer user to the corresponding host user's account, achieving accurate resource transfer and improving the efficiency of resource transfer at the same time.

[0070] Of course, it is not necessary for any product implementing this application to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0072] Figure 1 FIG. is the system architecture diagram applicable to the embodiments of the present application;

[0073] Figure 2 Flowchart of the live interaction method executed by the client of the audience user provided by the embodiment of the present application;

[0074] Figure 3 Schematic diagram of the page where the resource panel is located provided by the embodiment of the present application;

[0075] Figure 4a Schematic diagram of the page where one of the prompt messages is located provided by the embodiment of the present application;

[0076] Figure 4b Schematic diagram of the page where another prompt message is located provided by the embodiment of the present application;

[0077] Figure 5 Schematic diagram of the page where the first component is located provided by the embodiment of the present application;

[0078] Figure 6 Flowchart of the live interaction method executed by the client of the host user provided by the embodiment of the present application;

[0079] Figure 7 Schematic diagram of the page where the configuration panel is located provided by the embodiment of the present application;

[0080] Figure 8 Schematic diagram of the page where the second component is located provided by the embodiment of the present application;

[0081] Figure 9 Schematic diagram of the page where the third component is located provided by the embodiment of the present application;

[0082] Figure 10 Flowchart of the live interaction method executed by the server side provided by the embodiment of the present application;

[0083] Figure 11 Overall flowchart of the live interaction method provided by the embodiment of the present application;

[0084] Figure 12 Schematic block diagram of the live interaction device provided on the client of the audience user provided by the embodiment of the present application;

[0085] Figure 13 Schematic block diagram of the live interaction device provided on the client of the host user provided by the embodiment of the present application;

[0086] Figure 14 Schematic block diagram of the live interaction device provided on the server side provided by the embodiment of the present application;

[0087] Figure 15 Schematic block diagram of the electronic device provided by the embodiment of the present application. Detailed implementation mode

[0088] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0089] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0090] It should be understood that the term " / and" used herein is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0091] Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" may be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".

[0092] It should be noted that the "first", "second", etc. limitations involved in the present disclosure do not have limitations in terms of size, order, quantity, etc., and are only used to distinguish by name. For example, "the first special effect" and "the second special effect" are used to distinguish two special effects.

[0093] Currently, there are already some live broadcast interaction technologies. During the process of viewers watching the live broadcast, they can send virtual resources to their favorite anchor users. However, for multi-person live broadcasts, viewers cannot accurately transfer the virtual resources to the accounts of their favorite anchor users, which reduces the viewing experience of the viewers.

[0094] In view of this, the present application provides a new idea. For the convenience of understanding the present application, the system architecture on which the present application is based will be described first. Figure 1 An exemplary system architecture to which the embodiments of the present application can be applied is shown, as Figure 1 shown in, the system architecture may include: the client of the anchor user, the client of the viewer user, and the server side.

[0095] The server side and the client side are two main parts of the application service. Among them, the server side uses the server as the main hardware infrastructure and may include one or more service modules in the form of software. In the embodiments of the present application, it is mainly responsible for processing the reception and transmission of the binding relationship and forms the front and back ends that work together with the client side.

[0096] The user terminal where the client side is located may include, but is not limited to, intelligent mobile terminals, wearable devices, PCs (Personal Computers), etc. Among them, intelligent mobile devices may include, such as mobile phones, tablet computers, PDAs (Personal Digital Assistants), Internet car terminals, etc. Wearable devices may include, such as smart watches, smart glasses, smart bracelets, VR (Virtual Reality) devices, AR (Augmented Reality) devices, mixed reality devices (i.e., devices that can support virtual reality and augmented reality), and so on.

[0097] The client side of the host user and the client side of the viewer user may be applications located in the user terminal, or may also be functional units such as plugins or Software Development Kits (SDKs) set in the application.

[0098] The server may be an independent server, a server group, or a cloud server. A cloud server, also known as a cloud computing server or a cloud host, is a host product in the cloud computing service system, which solves the defects of high management difficulty and weak service scalability existing in traditional physical hosts and Virtual Private Server (VPS) services.

[0099] It should be understood that Figure 1 the server side and the client side in [[ ]] are only illustrative. According to the implementation requirements, there may be any number of server sides and client sides.

[0100] Figure 2 The flowchart of the live interaction method provided for the embodiments of the present application, this method may be executed by Figure 1 the client side of the viewer user in the system shown in [[ ]]. As Figure 2 shown in [[ ]], this method may include the following steps:

[0101] Step 201, display the live broadcast screen, where the live broadcast screen includes multiple host users, and the multiple host users include at least the target host.

[0102] Step 202: Receive at least the binding relationship between the person recognition result corresponding to the target anchor and the anchor identification information from the server side.

[0103] Step 203: In response to an operation triggering resource transfer, where the operation triggering resource transfer includes a first operation of selecting a target resource in the live broadcast screen and a second operation on the screen area corresponding to the target anchor, send the information of the target resource and the anchor identification information of the target anchor to the server side, so as to transfer the target resource from the viewer user's account to the target anchor's account. Among them, the anchor identification information of the target anchor is determined based on the person recognition result of the target anchor and the binding relationship.

[0104] As can be seen from the above process, through the present application, the anchor identification information of the target anchor can be determined based on the binding relationship between the person recognition result corresponding to the target anchor and the anchor identification information, so as to transfer the target resource from the viewer user's account to the target anchor's account. On the one hand, through the person recognition result, the target anchor that the viewer user wants to transfer resources can be accurately located from the multi-person live broadcast screen, realizing precise interaction and enhancing the viewing experience of the viewer user, which conforms to the current trend of developing towards deeper interaction and diversified experience; on the other hand, even if the viewer user does not know the anchor identification information of the target anchor, only the second operation on the screen area corresponding to the target anchor can be used to perform precise resource transfer, improving the interaction efficiency and experience between the viewer user and the anchor user.

[0105] Next, each step in the above process and the further effects that can be generated will be described in detail in combination with embodiments.

[0106] First, the above step 201, that is, "display the live broadcast screen", will be described in detail in combination with embodiments.

[0107] In the embodiment of the present application, the client of the viewer user responds to the operation of the viewer user triggering to watch the live broadcast, and displays the live broadcast screen on the corresponding page. In the live broadcast screen mentioned in the present application, there are multiple anchor users (that is, at least two anchor users), and the multiple anchor users at least include the target anchor (that is, the anchor that the viewer user is interested in and wants to transfer resources). Among them, the live broadcast screen displayed by the client of the viewer user is the same as the live broadcast screen collected by the client of the anchor user.

[0108] Next, the above step 202, that is, "receive at least the binding relationship between the person recognition result corresponding to the target anchor and the anchor identification information from the server side", will be described in detail in combination with embodiments.

[0109] Generally, when a viewer user enters a live stream, the server side can send the binding relationship to the client of the viewer user. Specifically, the client of the viewer user can, in response to the operation of the viewer user triggering to watch the live stream, receive the binding relationship between the person recognition result and the host identifier information sent by the server side. Among them, the binding relationship can be the binding relationship between the person recognition results corresponding to all hosts in the live stream video and the host identifier information, or the binding relationship between the person recognition results corresponding to some hosts in the live stream video and the host identifier information, but at least includes the binding relationship between the person recognition result corresponding to the target host and the host identifier information. The host identifier information can refer to information such as the host number, host label, host account, host name, host avatar, etc. that can uniquely represent the host user.

[0110] Of course, the client of the viewer user can also, in response to the first operation of selecting a target resource in the live stream video, receive at least the binding relationship between the person recognition result corresponding to the target host and the host identifier information from the server side. That is to say, this application does not limit the time when the client of the viewer user receives the binding relationship, and it is sufficient to obtain the binding relationship before determining the host identifier information of the target host based on the person recognition result of the target host and the binding relationship.

[0111] For the person recognition result mentioned in the above process, it can be a person recognition result obtained by means such as gait analysis, clothing recognition, label recognition (for example, recognition through work cards, labels, etc. worn by the person), etc.

[0112] In a multi-person live stream scenario, a face detection algorithm, such as OpenCV (Open Source Computer Vision Library), Dlib (Dlib C++ library), or a deep learning model, can also be used to perform real-time scanning on the live stream video, identify the faces in the live stream video, and assign a unique identifier, that is, a face identifier (faceID), to each detected face for subsequent tracking of positions and special effect display. This application provides a relatively preferred solution. The person recognition result of the target host is obtained by using a face recognition model. Among them, the person recognition result is the face identifier, and at this time, the binding relationship is the binding relationship between the face identifier and the host identifier information.

[0113] It should be noted that the client of the viewer user can deploy a face recognition model locally and use the locally deployed face recognition model to recognize the live broadcast screen, obtaining face identifiers corresponding to multiple host users; the client of the viewer user can also send the live broadcast screen to the server side, and the server side uses the face recognition model deployed on the server side to recognize the received live broadcast screen, obtaining face identifiers corresponding to multiple host users, and returning the face identifiers to the client of the viewer user. In this way, the client of the viewer user does not need to deploy a face recognition model locally, saving local resource space.

[0114] The following describes in detail the above step 203, that is, "in response to an operation triggering resource transfer, send the information of the target resource and the host identifier information of the target host to the server side to transfer the target resource from the account of the viewer user to the account of the target host".

[0115] In the embodiment of the present application, the client of the viewer user, in response to an operation triggering resource transfer, sends the information of the target resource and the host identifier information of the target host to the server side, so that the server side transfers the target resource from the account of the viewer user to the account of the target host. Among them, the operation triggering resource transfer includes a first operation of selecting the target resource in the live broadcast screen and a second operation on the screen area corresponding to the target host, and the host identifier information of the target host is determined based on the person recognition result of the target host and the binding relationship. The resource transfer here can actually refer to the transfer of virtual gifts, virtual currency, currency, etc.

[0116] Among them, the first operation of selecting the target resource in the live broadcast screen can refer to clicking on one of the various resources in the resource panel as Figure 3 shown.

[0117] And the second operation on the screen area corresponding to the target host may include but is not limited to the following two (the two forms can exist in the live broadcast screen at the same time):

[0118] One is an operation in which the person area corresponding to the target host is triggered, and this operation is generated according to the prompt information in the live broadcast screen. The prompt information is displayed in the live broadcast screen in response to the first operation. As Figure 4a , Figure 4b shown, in Figure 4a , the prompt information is the position outlined by the dotted square box. At this time, the operation in which the person area corresponding to the target host is triggered is a double-click operation. In Figure 4b , the prompt information is the position outlined by the dotted square box. At this time, the operation in which the person area corresponding to the target host is triggered is an operation of outlining the person.

[0119] Another is an operation that triggers the first component for prompting to select a target host. The first component is displayed in the corresponding screen area of the target host in the live broadcast screen in response to the first operation. The first component can refer to, for example, a pop-up window, an indicator box, etc. As Figure 5 shown, the first component can refer to the position enclosed by the dashed square box in the figure.

[0120] In addition, while displaying the prompt message or the first component, a prompt special effect such as the flickering of the character edge can also be displayed in the corresponding screen area of the host user.

[0121] It should be noted that this application does not specifically limit the order of the first operation and the second operation. That is, the viewer user can first select a resource from multiple resources as the target resource, and then select a host user from multiple host users as the target host; or the viewer user can first select a host user from multiple host users as the target host, and then select a resource from multiple resources as the target resource.

[0122] As a relatively preferred implementation manner, the client of the viewer user can respond to the viewer user's click on one of the multiple resources as shown in Figure 3 as the target resource. Then, in response to the operation of the viewer user clicking the "Send" button, the resource panel is collapsed, and a page as shown in Figure 4a , Figure 4b or Figure 5 is displayed to prompt the viewer user to select one of the multiple host users. Further, in response to the second operation on the corresponding screen area of the target host, the information of the target resource and the host identifier information of the target host are sent to the server side, where the host identifier information of the target host is determined based on the person recognition result and the binding relationship of the target host.

[0123] Of course, in this application, it can also be to first display a page as shown in Figure 4a , Figure 4b or Figure 5 . In response to the second operation on the corresponding screen area of the target host, the selected host user by the viewer user is used as the target host, and a page as shown in Figure 3 is displayed. Further, in response to the viewer user's click on one of the multiple resources as shown in Figure 3 as the target resource, and in response to the operation of the viewer user clicking the "Send" button, the information of the target resource and the host identifier information of the target host are sent to the server side, where the host identifier information of the target host is determined based on the person recognition result and the binding relationship of the target host.

[0124] It should be noted that in this application, there may also be no such as Figure 3For the "Send" button shown, after the viewer user selects one of the resources as the target resource and one of the host users as the target host, the information of the target resource and the host identification information of the target host will be sent to the server side.

[0125] It should also be noted that the client of the viewer user can respond to the situation that no first operation of selecting the target resource in the live video is detected within a preset duration (such as within 10s or 20s), and can collapse Figure 3 the resource panel shown in

[0126] To enhance the visual effect, the client of the viewer user can display a first special effect for the first component. Specifically, in response to the first display of the first component in the live video, display the first special effect for the first component; and / or, in response to no trigger operation for the first component being detected within a preset duration, display the first special effect for the first component. For example, when the first component is a pop-up window or an indicator box, the first special effect can be a transparency fade or a highlight flash for the edge of the pop-up window or the indicator box at a cycle of 1 - 2 seconds.

[0127] To more clearly prompt the viewer user to select their favorite host from multiple host users, host identification information such as the host avatar, host account, host name, host number, host label, etc. can also be displayed in the first component.

[0128] Specifically, as an implementable embodiment, the client of the viewer user can, in response to the operation of the viewer user triggering to watch the live video, determine the host identification information of at least one host user based on the person recognition result of at least one host user among multiple host users and the received binding relationship. At least one host user includes the target host. Then, in response to the first operation of selecting the target resource in the live video, in the corresponding screen areas of at least one host user in the live video, display the first component respectively, and the first component includes the host identification information of the corresponding host user. Further, in response to the operation of the first component of the target host being triggered, send the information of the target resource and the host identification information of the target host to the server side.

[0129] As another implementable embodiment, the client of the viewer user can, in response to the first operation of selecting the target resource in the live video, determine the host identification information of at least one host user based on the person recognition result of at least one host user among multiple host users and the received binding relationship. At least one host user includes the target host. Then, in the corresponding screen areas of at least one host user in the live video, display the first component respectively, and the first component includes the host identification information of the corresponding host user. Further, in response to the operation of the first component of the target host being triggered, send the information of the target resource and the host identification information of the target host to the server side.

[0130] Further, in order to bring a richer interactive experience to the viewer users, the client of the viewer users can display a second special effect in the live broadcast screen. The second special effect can refer to text special effects, animation special effects, etc. for the target resource. As a relatively preferred embodiment, in response to receiving a message indicating successful resource transfer, a second special effect is displayed in the screen area corresponding to the target anchor in the live broadcast screen, and the second special effect is used to prompt the successful resource transfer. For example, assuming that the target resource sent by the viewer user is a flower, a second special effect, such as the special effect of a flower blooming, can be displayed at the corresponding position of the target anchor (such as the head, chest, hand, etc.) based on the position information corresponding to the person recognition result of the target anchor.

[0131] It should be noted that the first component, the second special effect, etc. in this application all act on the real-time live broadcast screen. When the position of the anchor user in the screen moves, the first component and the second special effect can also move along with the movement of the anchor user.

[0132] Figure 6 is a flowchart of the live interaction method provided by the embodiment of this application. This method can be executed by Figure 1 the client of the anchor user in the system shown. As shown in Figure 6 the method may include the following steps:

[0133] Step 601, collect and display the live broadcast screen, where the live broadcast screen includes multiple anchor users, and the multiple anchor users at least include the target anchor.

[0134] Step 602, in response to an operation triggering the binding function, the operation triggering the binding function includes a third operation on the screen area corresponding to the target anchor in the live broadcast screen, and display a configuration panel, where the configuration panel includes the anchor identification information of multiple anchor users.

[0135] Step 603, in response to selecting one of the anchor identification information from the configuration panel, send the binding relationship between the person recognition result of the target anchor and the selected anchor identification information to the server side.

[0136] From the above process, it can be seen that the client of the anchor user can bind the anchor identification information of multiple anchor users with the person recognition result, so that when the viewer user transfers resources, the resources can be accurately transferred to the account of the favorite anchor user. And for a live broadcast, there is no need to perform resource sharing subsequently, but the resources are transferred to the corresponding anchor user's account during the resource transfer, saving labor costs and improving the efficiency of the live broadcast.

[0137] The following will respectively describe in detail each step in the above process and the further effects that can be generated in combination with the embodiments.

[0138] First, the above step 601, that is, "collect and display the live broadcast screen", will be described in detail in combination with the embodiments.

[0139] In the embodiments of the present application, the client of the host user collects and displays the live broadcast screen, and the live broadcast screen is sent to the server side, and then sent by the server side to the client of the viewer user in the form of a media stream. Among them, the live broadcast screen includes multiple host users, and the multiple host users at least include the target host.

[0140] Next, the above step 602, that is, "in response to an operation triggering the binding function, display the configuration panel", will be described in detail in combination with the embodiments.

[0141] In the embodiments of the present application, the client of the host user responds to an operation triggering the binding function and displays the configuration panel, as Figure 7 shown. Here, the operation triggering the binding function includes a third operation on the screen area corresponding to the target host in the live broadcast screen. The configuration panel includes the host identification information of multiple host users, and the host identification information can refer to information such as the host number, host label, host account, host avatar, host name, etc. that can uniquely represent the host user.

[0142] Among them, the third operation on the screen area corresponding to the target host in the live broadcast screen may include, but is not limited to, the following two (the two forms may exist in the live broadcast screen at the same time):

[0143] One is an operation in which the person area corresponding to the target host is triggered. This operation is generated according to the prompt information in the live broadcast screen, and the prompt information is displayed in the live broadcast screen in response to identifying a new person recognition result from multiple host users. For example, the operation in which the person area corresponding to the target host is triggered may be a double-click operation on the person area, or for another example, the operation in which the person area corresponding to the target host is triggered may be an operation of selecting a person by framing the person area.

[0144] The other is an operation in which a second component for prompting to bind the target host is triggered. The second component is displayed in the live broadcast screen in response to identifying a new person recognition result from multiple host users, as Figure 8 shown, Figure 8 the position framed by the dotted line in is the second component, and the second component may refer to, for example, a pop-up window, an indication box, etc.

[0145] It should be noted that the prompt information or the second component can also be displayed on the live broadcast screen in response to detecting that there is no binding relationship between the recognized person recognition result and the host identifier information. That is to say, even if the detected person recognition result is not a new person recognition result, as long as the condition that the person recognition result is not bound to the host identifier information is met, the prompt information or the second component is displayed on the live broadcast screen. And while displaying the prompt information or the second component, prompt special effects such as flashing of the person's edge can also be displayed in the screen area corresponding to the host user.

[0146] The following describes in detail step 603 above, that is, "in response to selecting one of the host identifier information from the configuration panel, send the binding relationship between the person recognition result of the target host and the selected host identifier information to the server side" in combination with the embodiments.

[0147] In the embodiment of the present application, the host user sends the binding relationship between the person recognition result of the target host and the selected host identifier information to the server side in response to selecting one of the host identifier information from the configuration panel. The person recognition result obtained here is the same as the process in step 202 and will not be elaborated here.

[0148] As a relatively preferred implementation manner, in actual application, the client of the host user can confirm again whether to bind the person recognition result of the target host to the selected host identifier information. Specifically, in response to selecting one of the host identifier information from the configuration panel, a third component for binding the person recognition result of the target host to the selected host identifier information is displayed, as Figure 9 shown. The client of the host user sends the binding relationship between the person recognition result of the target host and the selected host identifier information to the server side in response to the positive feedback of the host user for the third component (such as clicking the Figure 9 "OK" button in).

[0149] It should be noted that after the client of the host user selects one of the host identifier information from the configuration panel, it can send the binding relationship between the person recognition result of the target host and the selected host identifier information to the server side, or it can first store the binding relationship between the person recognition result of the target host and the selected host identifier information in the local client. When all the host identifier information is bound to multiple host users in the live broadcast screen one by one, a binding relationship table is formed and the binding relationship table is sent to the server side.

[0150] It should also be noted that the binding relationship of this application can also be modified on the client of the host user. For example, the client of the host user can display a fourth component for modifying the binding relationship in the live broadcast screen. In response to the operation of triggering the fourth component, the binding relationships corresponding to all the host identification information in the configuration panel are released, and the second component for prompting to bind to the target host is respectively displayed again for multiple host users in the live broadcast screen to prompt the host user to re-bind. Or, a fifth component for prompting to modify the bound host user is respectively displayed for multiple host users in the live broadcast screen to prompt the host user to re-bind the host user for which the binding relationship needs to be modified.

[0151] For a certain host user in the live broadcast screen, a shielding operation can also be performed. Briefly speaking, the viewer user cannot transfer resources to the shielded host user. Specifically, while displaying the second component for prompting to bind to the target host in the corresponding screen area of the target host in the live broadcast screen, a sixth component for prompting to shield the target host (the sixth component can be a pop-up window, an indication box, etc.) can also be displayed. In response to the operation of triggering the sixth component, the target host is set to the shielded state. In this state, the second component for prompting to bind to the target host is no longer displayed on the client of the host user, and the first component for prompting to select the target host is no longer displayed on the client of the viewer user.

[0152] Generally, the host identification information of the host user displayed in the configuration panel can be pre-configured, and the number of the host identification information should be consistent with the number of host users in the live broadcast screen. However, in actual situations, if a new host user is added, an existing host user is deleted, or the host identification information of an existing host user is modified during the live broadcast, the host identification information in the configuration panel can also be added, modified, deleted, etc. Correspondingly, after adding new host identification information, the person recognition result of the new host user can be bound to the added host identification information in the configuration panel; after deleting the existing host identification information, a shielding operation can be performed on the deleted host user.

[0153] To improve the interactive experience of the host user, when the viewer user transfers resources on the client of the viewer user, the client of the host user can receive a message indicating that the resource transfer is successful. In response to receiving the message indicating that the resource transfer is successful, the resource transfer includes the transfer of the target resource from the viewer user's account to the target host's account, and a third special effect is displayed in the corresponding screen area of the target host in the live broadcast screen. The third special effect is used to prompt that the target resource transfer is successful. The third special effect can refer to a text special effect, an animation special effect, etc. for the target resource. After the target resource transfer is successful, the third special effect can be displayed at the corresponding position of the target host (such as the head, chest, hand, etc.) based on the position information corresponding to the person recognition result of the target host.

[0154] It should be noted that the client of the host user in this application may refer to the client of one of the multiple host users, or may refer to the clients of multiple host users. Moreover, if the client of the host user in this application refers to the clients of multiple host users, when displaying the third special effect, the third special effect may be displayed only on the client of the selected target host.

[0155] Figure 10 The following is a flowchart of the live interactive method provided by the embodiments of this application. This method can be executed by Figure 1 the server side in the system shown in Figure 10 As shown in

[0156] Step 1001: Receive the binding relationship between the person recognition result of the target host and the host identification information from the client of the host user.

[0157] Step 1002: Send the binding relationship to the client of the audience user.

[0158] Step 1003: Receive the information of the target resource and the host identification information of the target host from the client of the audience user, and determine the account information of the target host according to the host identification information of the target host.

[0159] Step 1004: Transfer the target resource from the account of the audience user to the account of the target host.

[0160] As can be seen from the above process, for the server side, when the audience user enters the live broadcast room, the binding relationship obtained from the client of the host user can be sent to the client of the audience user, laying a foundation for the subsequent transfer of resources from the audience user to the corresponding host user's account, realizing accurate resource transfer and improving the efficiency of resource transfer at the same time.

[0161] In the embodiment of the present application, the client of the host user sends the obtained binding relationship to the server side in response to the operation of the host user to bind one by one the person recognition results of multiple host users in the live broadcast screen and the host identification information in the configuration panel. The server side receives the binding relationship from the client of the host user, where the binding relationship at least includes the binding relationship between the person recognition result of the target host and the host identification information. When the viewer user enters the host room (i.e., the viewer user starts watching the live broadcast), the server side can send the binding relationship between the person recognition results of multiple host users in the live broadcast screen and the host identification information in the configuration panel to the client of the viewer user. When the viewer user is watching the live broadcast and wants to express their love for one of the host users, they can perform resource transfer. After the viewer user selects one of the host users as the target host and one of the resources as the target resource according to the relevant steps (see step 203 for details), the server side receives the information of the target resource and the host identification information of the target host from the client of the viewer user, determines the account information of the target host based on the host identification information of the target host, and transfers the target resource from the viewer user's account to the target host's account.

[0162] Next, a more preferred embodiment will be used to fully illustrate the methods involved in the client and server side of the present application, as Figure 11 shown. It can be seen from Figure 11 that the client of the host user can detect the face identifiers of all host users in the live broadcast screen in real time and determine whether a new face identifier appears. When a new face identifier appears, a second component for prompting to bind the host user is displayed in the screen area of the host user corresponding to the new face identifier. In response to the binding operation of the host user between the face identifier of the host user and the host identification information, the binding relationship between the face identifier of the host user and the host identification information is stored in the local binding relationship table. Then, the client of the host user sends the binding relationship table to the server side in response to the trigger of the sending operation for the binding relationship table.

[0163] The server side stores the binding relationship table and sends the binding relationship table to the client of the viewer user.

[0164] In response to an operation by the viewer user to watch a live stream, the client of the viewer user receives a binding relationship table. In response to an operation by the viewer user to select a target resource, the client uses a face recognition model to obtain the face identifiers of multiple host users in the live stream video. Based on the binding relationship table, in the picture areas corresponding to the multiple host users in the live stream video, a first component is respectively displayed. The first component includes the host identifier information corresponding to the host user. In response to an operation in which the first component corresponding to the target host selected by the viewer user is triggered (i.e., the viewer user confirms sending the resource), the client of the viewer user sends the information of the target resource and the host identifier information of the target host to the server side.

[0165] The server side transfers the target resource from the account of the viewer user to the account of the target host, and then the server side sends a message indicating successful resource transfer to the client of the host user.

[0166] The client of the host user receives the message indicating successful resource transfer, which includes the information of the target resource and the host identifier information of the target host. Based on the binding relationship table, the face identifier of the target host is determined, and then a third special effect is displayed in the picture area corresponding to the target host in the live stream video.

[0167] In addition, the server side can also send the message indicating successful resource transfer to the client of the viewer user, and the client of the viewer user displays a second special effect in the picture area corresponding to the target host in the live stream video. This part is not shown in the figure.

[0168] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0169] According to an embodiment of another aspect, a live interaction device is provided. Figure 12 A schematic block diagram of the live interaction device according to an embodiment is shown. The device is arranged in Figure 1 the client of the viewer user in the architecture shown. As Figure 12 shown, the device 1200 includes:

[0170] A first display unit 1201, configured to display a live stream video, which includes multiple host users, and the multiple host users include at least the target host.

[0171] A first receiving unit 1202, configured to receive at least the binding relationship between the person recognition result corresponding to the target host and the host identifier information from the server side.

[0172] The first sending unit 1203 is configured to, in response to an operation that triggers resource transfer, where the operation that triggers resource transfer includes a first operation of selecting a target resource in the live broadcast screen and a second operation performed on the screen area corresponding to the target anchor, send the information of the target resource and the anchor identification information of the target anchor to the server side, so as to transfer the target resource from the viewer user's account to the target anchor's account, where the anchor identification information of the target anchor is determined based on the person recognition result of the target anchor and the binding relationship.

[0173] As one possible implementation, the person recognition result of the target anchor is obtained by using a face recognition model, the person recognition result is a face identifier, and the binding relationship is the binding relationship between the face identifier and the anchor identification information.

[0174] As one possible implementation, the second operation performed on the screen area corresponding to the target anchor includes: an operation triggered on the person area corresponding to the target anchor, which is generated according to the prompt information in the live broadcast screen, and the prompt information is displayed in the live broadcast screen in response to the first operation; and / or, an operation triggered on the first component used to prompt the selection of the target anchor, and the first component is displayed in the screen area corresponding to the target anchor in the live broadcast screen in response to the first operation.

[0175] As one possible implementation, the first display unit 1201 can also be configured to: in response to the first component being first displayed in the live broadcast screen, display a first special effect for the first component; and / or, in response to no trigger operation on the first component being detected within a preset duration, display a first special effect for the first component.

[0176] As one possible implementation, the first display unit 1201 can be specifically configured to: in response to the first operation of selecting a target resource in the live broadcast screen, determine the anchor identification information of at least one anchor user based on the person recognition result and the binding relationship of at least one anchor user among multiple anchor users, where the at least one anchor user includes the target anchor; and display the first component in the screen areas corresponding to the at least one anchor user in the live broadcast screen, and the first component includes the anchor identification information of the corresponding anchor user.

[0177] The first sending unit 1203 can be specifically configured to: in response to the operation of the first component of the target anchor being triggered, send the information of the target resource and the anchor identification information of the target anchor to the server side.

[0178] As one possible implementation, the first display unit 1201 can also be configured to: in response to receiving a message indicating successful resource transfer, display a second special effect in the picture area corresponding to the target anchor in the live broadcast picture, where the second special effect is used to indicate the successful transfer of the target resource.

[0179] According to an embodiment of another aspect, a live interactive device is provided. Figure 13 The schematic block diagram of the live interactive device according to an embodiment is shown, and the device is arranged in Figure 1 the client of the anchor user in the shown architecture. As Figure 13 shown, the device 1300 includes:

[0180] A second display unit 1301, configured to collect and display a live broadcast picture, where the live broadcast picture includes multiple anchor users, and the multiple anchor users at least include a target anchor.

[0181] The second display unit 1301 is further configured to, in response to an operation triggering the binding function, where the operation triggering the binding function includes a third operation on the picture area corresponding to the target anchor in the live broadcast picture, display a configuration panel, and the configuration panel includes the anchor identification information of multiple anchor users.

[0182] A second sending unit 1302, configured to, in response to selecting one of the anchor identification information from the configuration panel, send the binding relationship between the person recognition result of the target anchor and the selected anchor identification information to the server side.

[0183] As one possible implementation, the third operation on the picture area corresponding to the target anchor in the live broadcast picture includes: an operation triggering the person area corresponding to the target anchor, where the operation is generated based on the prompt information in the live broadcast picture, and the prompt information is displayed in the live broadcast picture in response to identifying a new person recognition result from multiple anchor users; and / or, an operation triggering the second component for prompting to bind the target anchor, where the second component is displayed in the live broadcast picture in response to identifying a new person recognition result from multiple anchor users.

[0184] As one possible implementation, the second display unit 1301 can be specifically configured to: in response to selecting one of the anchor identification information from the configuration panel, display a third component for binding the person recognition result of the target anchor and the selected anchor identification information;

[0185] The second sending unit 1302 can be specifically configured to: in response to the positive feedback of the anchor user on the third component, send the binding relationship between the person recognition result of the target anchor and the selected anchor identification information to the server side.

[0186] The second display unit 1301 may also be configured to: in response to receiving a message indicating successful resource transfer, where the resource transfer includes transferring the target resource from the viewer user's account to the target anchor's account, display a third special effect in the picture area corresponding to the target anchor in the live broadcast picture, and the third special effect is used to indicate the successful resource transfer.

[0187] According to an embodiment of another aspect, a live interactive device is provided. Figure 14 A schematic block diagram of the live interactive device according to an embodiment is shown, and the device is disposed at Figure 1 the server side in the shown architecture. As Figure 14 shown, the device 1400 includes:

[0188] A second receiving unit 1401, configured to receive the binding relationship between the person recognition result of the target anchor and the anchor identification information from the client of the anchor user.

[0189] A third sending unit 1402, configured to send the binding relationship to the client of the viewer user.

[0190] The second receiving unit 1401 is further configured to receive the information of the target resource and the anchor identification information of the target anchor from the client of the viewer user.

[0191] A resource transfer unit 1403, configured to determine the account information of the target anchor according to the anchor identification information of the target anchor, and transfer the target resource from the viewer user's account to the target anchor's account.

[0192] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments. The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0193] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0194] In addition, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method described in any one of the foregoing method embodiments are implemented.

[0195] And an electronic device, including:

[0196] One or more processors; and

[0197] A memory associated with the one or more processors, the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, the steps of the method described in any one of the foregoing method embodiments are executed.

[0198] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of the foregoing method embodiments are implemented.

[0199] Among them, Figure 15 An exemplary architecture of the electronic device is shown, which may specifically include a processor 1510, a video display adapter 1511, a disk drive 1512, an input / output interface 1513, a network interface 1514, and a memory 1520. The above-mentioned processor 1510, video display adapter 1511, disk drive 1512, input / output interface 1513, network interface 1514, and the memory 1520 can be communicatively connected through a communication bus 1530.

[0200] Among them, the processor 1510 can be implemented in ways such as a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided by the present application.

[0201] The memory 1520 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1520 can store an operating system 1521 for controlling the operation of the electronic device 1500, and a Basic Input / Output System (BIOS) 1522 for controlling the low-level operations of the electronic device 1500. Additionally, it can also store a web browser 1523, a data storage management system 1524, and the live interactive device 1200 / 1300 / 1400, etc. The above-mentioned host interactive device 1200 / 1300 / 1400 can be the application program that specifically implements the operations of the foregoing steps in the embodiments of the present application. In summary, when implementing the technical solution provided by the present application through software or firmware, the relevant program codes are stored in the memory 1520 and are called and executed by the processor 1510.

[0202] The input / output interface 1513 is used to connect to the input / output module to achieve information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Among them, the input devices can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices can include a display, a speaker, a vibrator, an indicator light, etc.

[0203] The network interface 1514 is used to connect to a communication module (not shown in the figure) to achieve communication interaction between this device and other devices. Among them, the communication module can achieve communication through a wired method (such as USB, network cable, etc.) or can also achieve communication through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.).

[0204] The bus 1530 includes a path for transmitting information between various components of the device (such as the processor 1510, the video display adapter 1511, the disk drive 1512, the input / output interface 1513, the network interface 1514, and the memory 1520).

[0205] It should be noted that although the above device only shows the processor 1510, the video display adapter 1511, the disk drive 1512, the input / output interface 1513, the network interface 1514, the memory 1520, the bus 1530, etc., in the specific implementation process, this device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the present application and does not necessarily include all the components shown in the figure.

[0206] As can be seen from the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art can be embodied in the form of a computer program product, which can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0207] The technical solution provided by this application has been introduced in detail above. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A live interactive method, applied to the client of the audience user, characterized in that, The method includes: Displaying a live broadcast screen, where the live broadcast screen includes multiple host users, and the multiple host users at least include a target host; Receiving at least the binding relationship between the person recognition result corresponding to the target host and the host identification information from the server side; In response to an operation for triggering resource transfer, the operation for triggering resource transfer includes a first operation of selecting a target resource in the live broadcast screen and a second operation on the screen area corresponding to the target host, sending the information of the target resource and the host identification information of the target host to the server side, so as to transfer the target resource from the account of the viewer user to the account of the target host, where the host identification information of the target host is determined based on the person recognition result of the target host and the binding relationship.

2. The method according to claim 1, characterized in that The person recognition result of the target host is obtained by using a face recognition model, and the person recognition result is a face identifier: The binding relationship is the binding relationship between the face identifier and the host identification information.

3. The method according to claim 1, wherein The second operation on the screen area corresponding to the target host includes: An operation for triggering the person area corresponding to the target host, and this operation is generated according to the prompt information in the live broadcast screen, and the prompt information is displayed in the live broadcast screen in response to the first operation; and / or, An operation for triggering the first component for prompting to select the target host, and the first component is displayed in the screen area corresponding to the target host in the live broadcast screen in response to the first operation.

4. The method according to claim 3, wherein The method further includes: In response to the first display of the first component in the live broadcast screen, displaying a first special effect for the first component; and / or, In response to no triggering operation for the first component being detected within a preset duration, displaying a first special effect for the first component.

5. According to the method described in claim 3, the step of, in response to the operation for triggering resource transfer, sending the information of the target resource and the host identification information of the target host to the server side includes: In response to the first operation of selecting a target resource in the live broadcast screen, determining the host identification information of at least one host user among the multiple host users based on the person recognition result of at least one host user among the multiple host users and the binding relationship, and the at least one host user includes the target host; Respectively displaying a first component in the screen area corresponding to the at least one host user in the live broadcast screen, and the first component includes the host identification information of the corresponding host user; In response to the operation for triggering the first component of the target host, sending the information of the target resource and the host identification information of the target host to the server side.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: In response to receiving a message indicating successful resource transfer, displaying a second special effect in the screen area corresponding to the target host in the live broadcast screen, and the second special effect is used to prompt the successful transfer of the target resource.

7. A live interaction method, applied to the client of the host user, characterized in that The method includes: Collecting and displaying a live broadcast screen, where the live broadcast screen includes multiple host users, and the multiple host users at least include a target host; In response to an operation that triggers the binding function, the operation that triggers the binding function includes a third operation performed on the screen area corresponding to the target anchor in the live broadcast screen, and a configuration panel is displayed. The configuration panel includes the anchor identification information of the multiple anchor users; In response to selecting one of the anchor identification information from the configuration panel, the binding relationship between the person recognition result of the target anchor and the selected anchor identification information is sent to the server side.

8. The method according to claim 7, wherein The third operation performed on the screen area corresponding to the target anchor in the live broadcast screen includes: An operation in which the person area corresponding to the target anchor is triggered, and this operation is generated according to the prompt information in the live broadcast screen. The prompt information is displayed in the live broadcast screen in response to identifying a new person recognition result from the multiple anchor users; and / or, An operation in which a second component used to prompt binding of the target anchor is triggered, and the second component is displayed in the live broadcast screen in response to identifying a new person recognition result from the multiple anchor users.

9. The method according to claim 7, wherein The step of, in response to selecting one of the anchor identification information from the configuration panel, sending the binding relationship between the person recognition result of the target anchor and the selected anchor identification information to the server side includes: In response to selecting one of the anchor identification information from the configuration panel, a third component for binding the person recognition result of the target anchor and the selected anchor identification information is displayed; In response to the positive feedback of the anchor user on the third component, the binding relationship between the person recognition result of the target anchor and the selected anchor identification information is sent to the server side.

10. The method according to claim 7, characterized in that, The method further includes: In response to receiving a message indicating successful resource transfer, where the resource transfer includes transferring the target resource from the viewer user's account to the target anchor's account, a third special effect is displayed in the screen area corresponding to the target anchor in the live broadcast screen, and the third special effect is used to prompt the successful transfer of the target resource.

11. A live interactive method, applied to a server side, characterized in that, The method includes: Receiving, from the client of the anchor user, the binding relationship between the person recognition result of the target anchor and the anchor identification information; Sending the binding relationship to the client of the viewer user; Receiving, from the client of the viewer user, the information of the target resource and the anchor identification information of the target anchor, and determining the account information of the target anchor according to the anchor identification information of the target anchor; Transferring the target resource from the viewer user's account to the target anchor's account.

12. A live interactive device is provided on the client side of the audience user, characterized in that, The device includes: A first display unit configured to display a live broadcast screen, where the live broadcast screen includes multiple anchor users, and the multiple anchor users at least include a target anchor; A first receiving unit configured to receive at least the binding relationship between the person recognition result corresponding to the target anchor and the anchor identification information from the server side; A first sending unit, configured to, in response to an operation for triggering resource transfer, where the operation for triggering resource transfer includes a first operation of selecting a target resource in the live broadcast screen and a second operation performed on a screen area corresponding to the target anchor, send information of the target resource and anchor identification information of the target anchor to a server side, so as to transfer the target resource from an account of the viewer user to an account of the target anchor, where the anchor identification information of the target anchor is determined based on a person recognition result of the target anchor and the binding relationship.

13. A live interactive device is provided on the client of the host user, characterized in that, The apparatus includes: A second display unit, configured to collect and display a live broadcast screen, where the live broadcast screen includes a plurality of anchor users, and the plurality of anchor users at least includes a target anchor; The second display unit is further configured to, in response to an operation for triggering a binding function, where the operation for triggering the binding function includes a third operation performed on a screen area corresponding to the target anchor in the live broadcast screen, display a configuration panel, and the configuration panel includes anchor identification information of the plurality of anchor users; A second sending unit, configured to, in response to selecting one of the anchor identification information from the configuration panel, send a binding relationship between a person recognition result of the target anchor and the selected anchor identification information to the server side.

14. A live interactive device is provided on the server side, characterized in that, The apparatus includes: A second receiving unit, configured to receive a binding relationship between a person recognition result of a target anchor and anchor identification information from a client of the anchor user; A third sending unit, configured to send the binding relationship to a client of the viewer user; The second receiving unit is further configured to receive information of a target resource and anchor identification information of the target anchor from the client of the viewer user; A resource transfer unit, configured to determine account information of the target anchor based on the anchor identification information of the target anchor, and transfer the target resource from an account of the viewer user to an account of the target anchor.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

16. An electronic device, characterized in that, Including: One or more processors; And A memory associated with the one or more processors, where the memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, the steps of the method according to any one of claims 1 to 11 are executed.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images