Live streaming interactive methods and devices, live streaming configuration methods and devices
By displaying individual information in a preset background layer in the live stream, the problem of viewers having difficulty identifying the streamer's individual information in multi-person live streams is solved, enabling viewers to efficiently identify and interact within the same live stream interface, thus improving the interaction efficiency of multi-person live streams.
Patent Information
- Application Number
- CN202611373287.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-04
- Publication Date
- 2026-11-17
AI Technical Summary
In multi-person live streaming scenarios, it is difficult for viewers to quickly identify individual information of the streamer and interact in real time. The static labeling or overall image processing methods of existing technologies result in insufficient information carrying capacity, which cannot meet the real-time identification and interaction needs of viewers.
By displaying individual information of target participants in the preset background layer of the live broadcast room, including individual image, introductory information and virtual resource interaction entry, the recognizability and information viewability of target participants are enhanced. Pre-configured static image materials, video materials or screenshots of live broadcast video streams are used to enhance the display of individual images.
It improves the identifiability of target participants and the viewability of individual information, allowing viewers to identify and interact with target participants without leaving the current live stream, thus enhancing the interaction efficiency when the space for multi-person live streams is limited.
Smart Images

Figure CN123123602A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of Internet technology, and in particular to a live interactive method and apparatus, and a live configuration method and apparatus. Background Technology
[0002] In multi-person live streaming scenarios (such as group broadcasts), viewers need to quickly identify the streamer in the same frame and learn about the streamer's individual information and interact with the streamer.
[0003] In related technologies, common methods include overlaying independent text labels on the live stream screen, darkening or blurring non-performing subjects, or displaying general atmospheric elements. These methods generally rely on static annotations or overall screen processing, which limits the information they can convey. When the streamer moves or undergoes other changes in status, a disconnect can easily arise between the individual information displayed about the streamer and their actual state, failing to meet the actual needs of viewers for real-time identification, status tracking, and interaction with the target streamer. Summary of the Invention
[0004] In view of this, this application provides a live streaming interaction method and apparatus, and a live streaming configuration method and apparatus, to improve the efficiency of audience identification and interaction with the streamer in multi-person live streaming scenarios.
[0005] This application provides the following solution: According to the first aspect, a live streaming interaction method is provided, the method being executed by a viewer's client, the method comprising: The live stream is displayed, and the live stream includes multiple on-screen participants; In response to an event that triggers the determination of a target participant, the target participant is determined from the plurality of on-screen participants and the individual information of the target participant is obtained, the individual information including at least an individual image; The individual information of the target participant is displayed in a preset background layer in the live broadcast room. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast.
[0006] According to the second aspect, a live streaming configuration method is provided, the method being executed by the user's client, the method comprising: The live streaming configuration interface is displayed, which includes an entry point for editing information on multiple participants associated with the live streaming room; In response to an operation that triggers the editing entry of one of the participants, the information editing interface of the triggered participant is displayed, the information editing interface including components for editing the individual information of the triggered participant; The individual information includes at least an individual image. The individual information is used to display the individual information of the target participant in the preset background layer of the live broadcast room when the triggered participant is the target participant during the live broadcast. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
[0007] According to a third aspect, a live streaming interactive device is provided, the device being applied to a user terminal of a viewer, the device comprising: The first interface interaction unit is used to respond to an event that triggers the determination of a target participant, determine the target participant from multiple on-screen participants and obtain the individual information of the target participant, the individual information including at least an individual image; The first interface display unit is used to display the live broadcast screen, which includes multiple on-screen participants; and to display the individual information of the target participants in a preset background layer of the live broadcast room, wherein the individual image of the target participants displayed in the preset background layer is used to enhance the original image of the target participants in the live broadcast screen.
[0008] According to the fourth aspect, a live streaming configuration device is provided, the device being applied to a user terminal of a live streamer, the method comprising: The second interface display unit is used to display the live streaming configuration interface, which includes an entry point for editing information of multiple participants associated with the live streaming room. The second interface interaction unit is used to respond to the operation of triggering the editing entry of one of the participants and display the information editing interface of the triggered participant. The information editing interface includes components for editing the individual information of the triggered participant. The individual information includes at least an individual image. The individual information is used to display the individual information of the target participant in the preset background layer of the live broadcast room when the triggered participant is the target participant during the live broadcast. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
[0009] According to a fifth aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0010] According to a sixth aspect, an electronic device is provided, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any one of the first aspects above.
[0011] According to a seventh aspect, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects above.
[0012] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application enhances the individual image of a participant by displaying their personal information within a preset background layer in a live stream containing multiple participants. This improves the visibility of the target participant and the viewability of their personal information without deviating from the current live stream or directly obscuring other participants. Furthermore, integrating the target participant's personal information into the live stream background reduces the information limitations of static text labels, enabling viewers to identify, view, and interact with the target participant within the same live stream interface. This also improves interaction efficiency in situations where the space for multiple participants in a live stream is limited.
[0013] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description
[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0015] Figure 1 This is a system architecture diagram applicable to the embodiments of this application.
[0016] Figure 2 A flowchart illustrating a live interactive method provided in an embodiment of this application.
[0017] Figure 3 This is a schematic diagram of a live streaming interface provided in an embodiment of this application.
[0018] Figure 4 This is another interactive diagram of a live streaming interface provided in an embodiment of this application.
[0019] Figure 5 This is another interactive diagram of a live streaming interface provided in an embodiment of this application.
[0020] Figure 6 This is a flowchart illustrating a live streaming configuration method provided in an embodiment of this application.
[0021] Figure 7 This is a schematic diagram of a live streaming configuration interaction interface provided in an embodiment of this application.
[0022] Figure 8 This is a schematic block diagram of a live interactive device provided in an embodiment of this application.
[0023] Figure 9 This is a schematic block diagram of a live streaming configuration device provided in an embodiment of this application.
[0024] Figure 10 A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.
[0026] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.
[0027] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.
[0028] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."
[0029] In live streaming scenarios featuring multiple participants, to enable viewers to identify the streamers and view their individual information, common technologies involve overlaying static text labels onto the live stream screen or darkening the areas where other streamers are located. Specifically, this approach identifies the streamer's location within the frame and places a label containing their name near the participant's head, or reduces the brightness of areas outside the performers' areas. The core principle is to identify or define the streamer's area and then provide identification cues or visual focus using independently overlaid layers or image processing methods.
[0030] However, when this solution is applied to scenarios such as vertical multi-person group broadcasts, where multiple broadcasters stand side-by-side or in rows and take turns performing in the same frame, its performance is less than ideal. A fundamental contradiction lies in the fact that, in order to reduce obstruction of the live broadcast, this solution typically limits information display to small-sized text labels or only reduces non-target areas. While maintaining the overall visibility of the screen, its inherent design inevitably limits the visible area and information capacity of a single broadcaster, making it difficult for viewers to effectively view the broadcaster's image details and individual information that they are interested in. Specifically, when viewers need to identify a target participant, view their facial features and clothing details, or initiate interaction with that participant, static text labels can only provide a small amount of text information such as the name, while the darkening process only reduces interference in other areas. Viewers cannot obtain a more recognizable image of the broadcaster and other relevant information without leaving the current screen.
[0031] In view of this, this application provides a new approach. To facilitate understanding of this application, the system architecture on which this application is based will first be described. Figure 1 An exemplary system architecture that can be applied to embodiments of this application is shown, such as Figure 1 As shown, the system architecture may include: the user client for viewers, the user client for broadcasters, and the server.
[0032] The server-side and the user-side for viewers and broadcasters constitute the main components of the application service. The server-side, using a server as its primary hardware infrastructure, can include one or more software service modules, forming a collaborative front-end and back-end system with the user-sides for viewers and broadcasters.
[0033] The user terminals used by both viewers and broadcasters can include, but are not limited to, smart mobile terminals, wearable devices, and PCs (Personal Computers). Smart mobile devices can include devices such as mobile phones, tablets, PDAs (Personal Digital Assistants), and connected car terminals. Wearable devices can include devices such as smartwatches, smart glasses, smart bracelets, VR (Virtual Reality) devices, AR (Augmented Reality) devices, and mixed reality devices (devices that support both virtual and augmented reality).
[0034] The user terminals for both viewers and broadcasters can be client applications, mini-programs, or web applications running on the user terminal.
[0035] A server can be a standalone server, a server cluster, or a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a hosting product within the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) services, such as high management difficulty and weak service scalability.
[0036] It should be understood that Figure 1 The server-side, viewer-side, and broadcaster-side interfaces shown are merely illustrative. Depending on implementation needs, any number of server-side, viewer-side, and broadcaster-side interfaces can be included.
[0037] Figure 2 A flowchart illustrating a live interactive method provided in this application embodiment, the method can be... Figure 1 The system shown executes the commands on the user's end, which can specifically be executed by the viewer's user's end. For example... Figure 2 As shown, the method may include the following steps: Step S210: Display the live stream, which includes multiple on-screen participants.
[0038] Step S220: In response to the event of triggering the determination of the target participant, the target participant is determined from the plurality of on-camera participants and the individual information of the target participant is obtained, the individual information including at least the individual image.
[0039] Step S230: Display the individual information of the target participant in the preset background layer of the live broadcast room, wherein the individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
[0040] As can be seen from the above process, this application enhances the individual image of a participant by displaying their individual information in a preset background layer of a live stream containing multiple participants, thus improving the recognizability of the target participant and the viewability of their individual information without deviating from the current live stream or directly obscuring other participants. At the same time, by integrating the individual information of the target participant into the background area of the live stream, the problem of insufficient information from a single static text label is reduced, enabling viewers to identify, view, and interact with the target participant within the same live stream interface, thereby improving the interaction efficiency when the space for multiple participants in a live stream is limited.
[0041] The following describes in detail each step of the above process and the effects that can be further produced, with reference to the embodiments. It should be noted that the terms "first" and "second" involved in this disclosure do not have limitations in terms of size, order, or quantity, but are only used to distinguish them in name. For example, "first individual information" and "second individual information" are used to distinguish between two types of individual information.
[0042] First, in conjunction with the embodiments, the above step 220, namely "in response to the event of triggering the determination of the target participant, determining the target participant from the plurality of on-camera participants and obtaining the individual information of the target participant, wherein the individual information includes at least an individual image", will be described in detail.
[0043] In some embodiments, the individual image is obtained from at least one of pre-configured static image material, pre-configured video material, or a screenshot of the live stream.
[0044] Pre-configured static image materials can be avatars, half-body photos, full-body photos, image posters, or human portrait materials that have been cut out and uploaded in advance by the live stream administrator. These are suitable for scenarios where it is desired to stably and clearly display the identity and image of the target participant within a preset background layer. Pre-configured video materials can be short video clips, personal presentation clips, performance clips, or personal music video clips of the target participant. These are suitable for scenarios where the target participant is in a performance state, in a central position, or in other scenarios that require dynamic emphasis. Video stream screenshots from the live stream can be captured by the user client based on real-time video frames during the current live stream, or they can be captured by the server and then distributed. These are used to generate individual images when no dedicated materials are configured, pre-configured materials fail to load, or when it is necessary to reflect the current makeup, clothing, or action status.
[0045] In practice, the server can maintain the material address, material type, material version number, and display priority for each on-screen participant in the live stream metadata. After identifying the target participant, the client can request the corresponding material based on the participant's identifier and select the material source according to the live stream configuration or local strategy. For example, when network conditions are weak or the target participant is only in a normal selected state, the client can prioritize loading static image materials; when the target participant is performing, competing, or in the center position, the client can prioritize loading video materials; when pre-configured materials are missing, expired, or significantly different from the current screen, the client can capture video frames from the live stream and perform cropping, scaling, sharpening, or background weakening processing to use as the individual image. The client can also cache loaded static image or video materials and determine whether updates are needed based on the material version number, thereby reducing duplicate requests and background switching latency.
[0046] When using the above-mentioned sources of materials, users can select the content to display based on the status of the live stream, the availability of materials, and network conditions. Static image materials help reduce transmission and rendering costs and keep the identities and images of the target participants stable; video materials help create dynamic display effects during performances, making the preset background layer match the atmosphere of the live stream; video stream screenshots help keep the images in the preset background layer consistent with the current live stream screen, enhancing the correlation between the background display and the real-time screen.
[0047] As an alternative implementation, the user client can also combine static image materials with video stream screenshots, for example, using a pre-configured image as the main body and clothing or posture areas in the real-time screenshot as supplements; or static image materials can be displayed before video materials are loaded, and then smoothly switched after the video materials are loaded, in order to reduce blankness, flickering or abruptness during the background switching process.
[0048] In some embodiments, the individual information further includes at least one of the target participant's introduction information, virtual resource interaction entry, and performance status information; the virtual resource interaction entry is used to trigger the display of candidate virtual resources for the target participant in the live streaming interface.
[0049] In addition to the aforementioned individual image, individual information may also include at least one of the following: introductory information of the target participant, virtual resource interaction entry points, and performance status information. Introductory information may include, for example, nickname, stage name, height, weight, affiliated group, representative talent, personal profile, number of followers, ranking within the live stream, current role, or custom fields within the live stream. Virtual resource interaction entry points can be presented as buttons, icons, card areas, floating controls, or triggerable areas combined with information cards, used to display candidate virtual resources for the target participant in the live stream interface, such as gift candidates, on-demand resources, support resources, voting resources, or other interactive resources. Performance status information may include states such as waiting, performing, moving, PK, and exiting the stage, where moving refers to the spatial position change of the on-screen participant from one position to another during the performance.
[0050] Specifically, after identifying the target participant, the user client can request individual information from the server, carrying the live stream identifier and the participant identifier. The server can then retrieve pre-bound information based on the live stream identifier and the participant identifier, and return the individual's profile, introduction, virtual resource configuration, and status fields. The live stream identifier can be used to identify the current live stream room or group broadcast room, and the participant identifier can be used to identify the specific on-screen participant selected, thus giving the individual information a clear data traceability relationship.
[0051] like Figure 3 The diagram illustrates a live streaming interface interaction according to an embodiment of this application. See also... Figure 3 In (a)-(b), the user terminal responds to the viewer's click operation by rendering the individual's image in a preset background layer, while simultaneously displaying introductory information and virtual resource interaction entry points in the information card. The information card may include an avatar area, nickname area, introduction area, status area, and interaction entry point area, etc., and each area can be adaptively arranged according to the screen width, live broadcast screen ratio, and whether there is a risk of obstruction.
[0052] See Figure 3 In sections (b)-(c), when a viewer triggers a virtual resource interaction entry point, the user client can display a list of candidate virtual resources for the target participant in the interaction information layer (e.g., displaying candidate gifts in the form of a gift panel), and associate the selected virtual resource with the target participant. This association can carry the live stream identifier, participant identifier, virtual resource identifier, and interaction quantity, so that the server can attribute the interaction to the corresponding target participant. In this way, viewers can identify, view, and interact within the same live stream interface, reducing the need to switch from the screen to a separate list and then search for the target object.
[0053] As an alternative implementation method, the introductory information, performance status information, and virtual resource interaction entry can be selectively displayed according to the gameplay of the live broadcast room or the screen size. They can also be displayed in sections, pages, or folded within the same information card, or expanded when triggered by the audience, thereby achieving a balance between information carrying capacity and live broadcast visibility.
[0054] In some embodiments, determining a target participant from the plurality of on-camera participants in response to triggering an event to determine a target participant includes at least one of the following: determining the first on-camera participant as the target participant in response to detecting a trigger operation targeting the location area of the first on-camera participant among the plurality of on-camera participants; determining the second on-camera participant as the target participant in response to detecting that the second on-camera participant among the plurality of on-camera participants is in a preset state, wherein the preset state includes a preset performance state and / or spatial location state.
[0055] Events that trigger the identification of a target participant can include user-initiated events and system-initiated events. For user-initiated events, the user can detect a trigger operation targeting the location area of the first on-screen participant and identify that participant as the target. This trigger operation can be a preset interactive action such as clicking, long-pressing, double-tapping, swiping, or a voice command. For example, clicking can view individual information and display an interactive entry point; long-pressing can view local details; double-tapping can quickly follow or open a virtual resource entry point; swiping can switch between adjacent participants; and voice commands can select a target without touching the screen.
[0056] For automatically triggered events, the user client can respond to the detection of a second on-screen participant in a preset state and identify that second on-screen participant as the target participant. The preset state can include at least one of a performance state and a spatial position state. For example, when the server issues a performance start signal, or when the user client determines, based on screen recognition, that a certain on-screen participant is in the center position, has entered the C position, has started a talent performance, or has entered a PK state, the user client can automatically identify that on-screen participant as the target participant and trigger the display or upgrade of individual information in the preset background layer. The above automatic triggering can be coordinated with the gameplay state machine of the live broadcast room. The gameplay state machine can include enumerable states such as initial state, waiting state, selected state, execution state, performance in progress state, and settlement state, and the switching is driven by events such as the host starting the gameplay, the audience clicking on a member, the audience confirming the operation, the server returning a success signal, the gameplay signal pushing the performance start signal, and the performance end signal.
[0057] When using the above implementation method, the user terminal can simultaneously support both viewer-initiated selection and automatic linkage during the live broadcast. Viewer-initiated selection can satisfy their personalized needs to view information about a specific participant, while automatic system triggering can promptly update the displayed content in the preset background layer when the target participant enters performance mode or changes position.
[0058] As an alternative implementation, the user client can set the priority of different trigger events. For example, user-selected target participants take precedence over ordinary automatically recommended participants. Automatic triggers corresponding to performance states can override ordinary selection states for a preset duration, or automatic trigger switching can be allowed only after the audience explicitly cancels the selection. The user client can also set anti-shake time to prevent rapid background flickering caused by multiple participants frequently meeting preset states within a short period. By setting trigger priorities and state switching rules, viewing interference caused by frequent switching in multi-person scenarios can be reduced, and the background display can maintain stable synchronization with the live broadcast process.
[0059] In some embodiments, determining the first on-screen participant as the target participant includes: obtaining location information of the triggered location on the live stream screen; determining the first on-screen participant selected by the viewer as the target participant based on the location information of the triggered location and the region mapping information corresponding to each on-screen participant in the live stream screen, wherein the region mapping information includes the bounding box information of each on-screen participant in the coordinate system of the live stream screen; or, performing region cropping based on the location information of the triggered location, and obtaining the on-screen participant corresponding to the face recognition result of the cropped region as the target participant.
[0060] The location information of the triggered position can be screen coordinates or, after coordinate transformation, normalized coordinates in the live stream coordinate system. Since the live stream may be scaled proportionally, cropped, have black borders, or be offset on different devices, the user client can first obtain the size and offset of the player's display area, and then convert the screen touch coordinates into position coordinates in the live stream coordinate system. The user client can then determine the first on-screen participant selected by the viewer based on the location information of the triggered position and the area mapping information corresponding to each on-screen participant in the live stream.
[0061] The region mapping information can include the bounding box information of each on-screen participant in the live broadcast coordinate system. The bounding box information can include fields such as x, y, width, and height. x and y can represent the normalized position of the top-left corner of the bounding box in the live broadcast coordinate system, while width and height can represent the normalized proportions of the bounding box's width and height within the live broadcast screen size. The coordinates in the live broadcast coordinate system can be represented using normalized values within the range of 0 to 1 to adapt to different resolutions, screen ratios, and player display sizes. The bounding box information can be obtained based on the merged video feed, that is, using the coordinate system of the main video stream after merging multiple broadcaster videos as a unified coordinate system, rather than solely based on the coordinate system of a single original video stream. This ensures that the user's touch hit detection, information card anchoring, and background layer highlighting are consistent with the live broadcast actually seen by the viewer.
[0062] Specifically, the server can perform human contour segmentation, face detection, or human detection on the individual broadcast video streams before merging, and map the detection results to the merging screen coordinate system. Alternatively, it can directly perform object detection on the merged live video stream to obtain the bounding rectangle region of each on-screen participant in the merging screen coordinate system. The server can send the region mapping information to the user terminal in the form of lightweight signaling. This signaling can be in JSON format and includes fields such as live room identifier, participant identifier, bounding box information (x, y, width, height), current status, and timestamp.
[0063] Upon receiving a touch event, the client converts the touch point to the live stream coordinate system and determines whether the touch point falls within the area corresponding to a bounding box. If the touch point hits only one bounding box, the on-screen participant corresponding to that bounding box is identified as the first on-screen participant. If the touch point falls within the areas corresponding to multiple bounding boxes, the client can determine a unique target object according to a preset priority. For example, it can prioritize on-screen participants currently performing; if multiple objects are performing, it can select the object whose touch point is closer to the center of the bounding box, or the object with higher priority in the status signaling; if none of them are performing, it can select the on-screen participant with the larger bounding box area to reduce the probability of misselection caused by overlapping areas.
[0064] As another implementation, the user client can perform region cropping based on the location information of the triggered location, and obtain the on-screen participants corresponding to the facial recognition results of the cropped area as the target participants. For example, the user client can crop a local image of a predetermined size around the touch point and match the facial features in the local image with the facial features of registered participants in the live stream. This method is suitable for scenarios where bounding box information is not delivered in a timely manner, participants are densely packed, or there is significant occlusion. The two methods can be used individually or in combination. For example, bounding box hit detection can be performed first, and facial recognition verification can be performed when the candidate objects are not unique, thereby improving the accuracy of target participant determination.
[0065] The aforementioned method for identifying target participants uses two paths: bounding box matching and region-based facial recognition. This allows for accurate mapping of the viewer's trigger position on the live stream to a specific on-screen participant, reducing the probability of misselection when participants' regions overlap or are densely packed in multi-person scenarios. Furthermore, even when bounding box information is not delivered in a timely manner, participants are heavily obscured, or region recognition is not unique, facial recognition verification can still be performed based on local images surrounding the trigger position. This provides a more accurate and robust object foundation for the subsequent display of individual information of the target participant.
[0066] The following describes in detail step 230, namely, "displaying the individual information of the target participant in the preset background layer of the live broadcast room, wherein the individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen," with reference to the embodiments.
[0067] In some embodiments, the "enhanced presentation" of the target participant's original image may specifically manifest itself in at least one of the following aspects: The display area of an individual's image in the preset background layer is larger than the original display area of the target participant in the live stream; The resolution of the individual image is higher than that of the original image; The brightness or contrast of the individual image is higher than that of the original image; The individual image is accompanied by visual identifiers that distinguish it from the original image.
[0068] As a result, viewers can quickly identify target participants, view their profile information, and further interact with them without leaving the live stream.
[0069] In some embodiments, the triggering operation for the location area of the first on-camera participant among the plurality of on-camera participants includes: clicking on the location area of the first on-camera participant; the displaying of the individual information of the target participant in the preset background layer of the live broadcast room includes: displaying the first body information of the first on-camera participant in the preset background layer, the first individual information including at least the first body image displayed in the first area of the preset background layer, and also including the first introduction information and virtual resource interaction entry of the first on-camera participant displayed in the preset background layer in the form of an information card, the first body image being a pre-configured static image material or a screenshot of the video stream of the live broadcast.
[0070] Continue to refer to Figure 3 In (a)-(b), the triggering operation for the area where the first on-screen participant is located can be a click on that area. After the user detects the click and identifies the first on-screen participant, the user can display the first body information of the first on-screen participant in a preset background layer. The first body information includes at least the first body image displayed in the first area of the preset background layer, and may also include the first introductory information and virtual resource interaction entry displayed in the form of an information card. The first area can be located in the upper, lower, or side of the background of the live broadcast screen, or in a large semi-transparent background area, as long as it can serve as the background area of the live broadcast room and overlap with the screen.
[0071] The first image can be a pre-configured static image or a screenshot from the live stream. The user can enlarge and render the first image at a predetermined ratio, making its display area larger than the original display area of the first participant in the live stream, or giving it a clearer outline, facial features, or compositional proportions. The information card can be anchored near the first image, near the bounding box information of the first participant, or at a preset fixed position on the background layer. To avoid obscuring faces and limbs in the live stream, the position of the information card can be adaptively adjusted based on the screen boundaries and bounding box information. By clicking to trigger the display of the first image's information, viewers can view the identity, introduction, and interaction options of the clicked object without leaving the live stream interface.
[0072] As an alternative implementation, the click operation can be replaced by double-click, short press, preset swipe gesture or voice selection command; the first volume image can also be generated by overlaying static image materials with real-time screenshots to balance stable display and real-time performance.
[0073] In some embodiments, the triggering operation for the location area of the first on-camera participant among the plurality of on-camera participants includes: a long press operation on the location area of the first on-camera participant; the individual image includes a partially enlarged image, and the display of the individual information of the target participant in the preset background layer of the live broadcast includes: displaying a partially enlarged image of the first on-camera participant in the preset background layer, the partially enlarged image of the first on-camera participant being obtained by taking a screenshot and partially enlarging the video stream of the live broadcast; updating the partially enlarged image of the first on-camera participant in response to an operation where the position of the contact point corresponding to the long press changes; and canceling the display of the partially enlarged image of the first on-camera participant in response to an operation where the long press ends.
[0074] like Figure 4 The diagram illustrates another interactive schematic of a live streaming interface provided in this application embodiment. The user can trigger a magnified display when the long press duration exceeds a preset threshold. The preset threshold can be adjusted according to the device system's gesture rules, live streaming room configuration, or user settings. The long press operation can include the operation where the pressing contact point does not leave the area corresponding to the first on-screen participant within a preset time, or it can include the operation where the moving distance of the pressing contact point within a preset time is less than a preset distance threshold, to reduce the possibility of swiping, accidental touches, or other operations being incorrectly identified as long presses. The individual image here can include a magnified image, which is an image obtained by taking a screenshot of the live stream video stream and proportionally magnifying a local area in the screenshot, used to view the target participant's facial features, clothing, posture, or other details.
[0075] Specifically, see Figure 4 In (a)-(b), after detecting a long-press operation, the user terminal can first determine the sampling area based on the location of the long-press contact point. The sampling area can be centered on the long-press contact point, or it can be constrained according to the bounding box information of the first on-screen participant, so that the sampling area is within the bounding box of the first on-screen participant. The user terminal can extract the sampling area from the current video frame and scale the sampling area proportionally according to a predetermined magnification factor to obtain a locally magnified image. The predetermined magnification factor can be a fixed factor, or it can be dynamically determined based on the original display area of the first on-screen participant in the live broadcast, the terminal screen size, or the user terminal settings. For example, when the bounding box area of the first on-screen participant in the live broadcast is small, a larger magnification factor can be used; when the bounding box area is large, a smaller magnification factor can be used to maintain a balance between display clarity and occlusion area in the locally magnified image.
[0076] In terms of display, the user can render a magnified image onto a preset background layer or onto a magnified display area associated with the preset background layer. The magnified display area can be circular, elliptical, rectangular, rounded rectangle, or other shapes suitable for displaying local details. Edge strokes, shadows, semi-transparent masks, or magnifying glass borders can be added to visually distinguish it from the original live stream. The magnified display area can be located near the long-press contact point or offset according to the screen boundaries. For example, when the contact point is near the left side of the screen, the magnified display area is displayed to the right of the contact point; when the contact point is near the top edge of the screen, the magnified display area is offset downwards to prevent it from exceeding the screen boundaries or being obscured by the finger.
[0077] See Figure 4 In (b)-(c), in response to a change in the position of the touch point during a long press, the user can redetermine the sampling area and capture a partial image from the current video frame based on the new touch point position. Alternatively, the user can move the sampling window within the captured image or consecutive video frames to update the magnified local image. If the touch point moves within the bounding box of the first participant in the video, the magnified display area can move synchronously with the finger's drag trajectory or remain at the predetermined display position. In response to an action that triggers the end of the long press, such as the finger being lifted, the touch point leaving the participant's area, or the long press being canceled by the system, the user cancels the display of the magnified local image.
[0078] The long-press zoom and click background display mentioned above can be considered as independent yet complementary interaction methods. Long-press zoom solves the problem of small original display area and difficulty in seeing local details in multi-person live broadcasts; clicking background display is mainly used to view individual information of target participants and trigger subsequent interactions.
[0079] As an alternative implementation, the magnification, size, and shape of the magnified display area can be adjusted according to the screen size; the local image can be generated based on the current frame, a fused image of multiple consecutive frames, or a high-definition screenshot returned by the server; when the drag trajectory is detected to exceed the bounding box information of the target participant during a long press, the last valid magnified image can be retained, or the magnified display can be canceled.
[0080] In some embodiments, the step of having the second on-camera participant among the plurality of on-camera participants in a preset state includes: the second on-camera participant being in a performance state and / or being in the center position of the plurality of on-camera participants; the step of displaying the individual information of the target participant in a preset background layer of the live broadcast room includes: displaying the second individual information of the second on-camera participant in the preset background layer, the second individual information including at least a second individual image displayed in a second area of the preset background layer, and also including the second introduction information and performance status information of the second on-camera participant displayed in the preset background layer in the form of an information card, the second individual image being pre-configured video material.
[0081] like Figure 5 The diagram illustrates another live streaming interface interaction provided by an embodiment of this application. For the scenario where the second on-camera participant is in a preset state, the preset state can include at least one of the following: the second on-camera participant is in a performance state or is in the center position among multiple on-camera participants. The center position can be the C position in a group broadcast, i.e., the middle position used for displaying the current performer in a multi-person standing arrangement, or a preset main performance position. When the user terminal determines that the second on-camera participant is in the above-mentioned preset state based on server signaling, local identification results, or standing rules, the second individual information of the second on-camera participant can be displayed in a preset background layer. See also... Figure 5 In (a)-(b), when it is detected that the on-camera participant 2 moves from the original position to the preset main performance position, the background layer is triggered to display the individual information of the on-camera participant 2.
[0082] The second individual information includes at least the second individual image displayed in the second area of the preset background layer, and may also include second introductory information and performance status information displayed in the form of information cards in the preset background layer. The second area can be larger than the first area of the aforementioned embodiment, for example, displayed in the form of full screen, large semi-transparent background, background video wall, etc., to form a display level that matches the current state. The second individual image can be pre-configured video material, such as personal MV clips, performance clips, or dynamic image material. The user can switch the conventional single portrait plus introduction display to a large information card or video material display when the second on-screen participant enters the center position or begins performing; when the second on-screen participant leaves the center position or the performance ends, it can switch back to other display content.
[0083] When the second on-screen participant is in a performance state and / or in the center position of multiple on-screen participants, the second figure is displayed in a second area, and the second introductory information and performance status information are displayed through information cards, so that the background display level matches the current performance status or spatial position status of the target participant; when entering the center position or starting the performance, the display is switched to a large area of information cards or video materials, which can enhance the live broadcast atmosphere and dynamic performance, and enable the audience to establish a more intuitive understanding of the current main performer and their status.
[0084] As an alternative implementation method, the preset state can be explicitly issued by the server or determined by the user based on whether the bounding box information is close to the center of the screen, the posture change, or the state field; the second volume image can also be generated by combining video footage, dynamic information cards, and real-time screenshots.
[0085] In some embodiments, the method further includes: in response to the second on-camera participant being restored from the preset state to the original state, restoring the second individual information of the second on-camera participant displayed in the preset background layer to the information displayed in the original state, the original state including the original performance state and / or spatial location state; in response to the second on-camera participant leaving the live broadcast screen, restoring the second individual information of the second on-camera participant displayed in the preset background layer to the default background information.
[0086] In practice, when the second on-screen participant is in a preset state, the user terminal can display the second participant's information in a preset background layer. This could be a large image of the second participant, an information card displaying their introduction and performance status, and the image could be pre-configured video footage. When the second on-screen participant returns from the preset state to their original state, the user terminal restores the information displayed in the preset background layer to what it showed in the original state. This original state can include the original performance status and / or spatial position status, such as returning from "performing" to "waiting," or returning from "center position" to their original location.
[0087] The restoration process can be understood as follows: the content displayed in the preset background layer reverts from a large, dynamic display linked to the preset state to the information already displayed in the live stream background layer before the second on-screen participant entered the preset state, corresponding to that original state. For example, if a viewer previously selected host A, and then host A moves to the center position to begin performing, when host A finishes performing and returns to the original state, the user can restore the individual information of host A displayed in the preset background layer during the performance state (such as a large personal music video, personal information card) to the individual information displayed when host A was selected by the viewer before the performance (such as a personal portrait, introduction), to maintain the continuity of the viewer's selection relationship. Of course, if no host was selected before the performance, host A's personal portrait and introduction can continue to be displayed after the performance.
[0088] When the second participant leaves the live stream, the user's device will restore the information displayed for that individual in the preset background layer to the default background information. The default information can be the basic background of the live stream, gameplay introduction, group information, PK atmosphere background, or a state where no special background is displayed.
[0089] By distinguishing between two recovery scenarios, namely "restoring from the preset state to the original state" and "leaving the live broadcast screen", the user terminal can maintain a reasonable state switching relationship between automatic performance linkage and user active selection, avoiding the mistaken overwriting of the target participants selected by the audience after the performer's performance ends, reducing the misleading content of the display and making the background information state clear and controllable.
[0090] As an alternative implementation, the recovery action can be executed immediately, or after the performance ends with an animation, the video footage finishes playing, or after a preset delay. The specific content of the original state can include various forms, such as recovering from "performing" to "standby," or returning to the original position from "center position." The user can determine whether the second on-screen participant has recovered from the preset state to the original state based on the status field sent by the server or the local recognition result. The default information can also be replaced with prompt information, such as indicating that the participant has left and guiding the audience to select other on-screen participants, thereby further reducing the confusion of the audience in multi-person live broadcasts. During the recovery process, the background display content can also be smoothly switched through fade-in, fade-out, or transition animations to reduce the visual abruptness caused by state switching.
[0091] In some embodiments, the live streaming room is configured with a curtain layer, a screen layer, and an interactive information layer from bottom to top in a layered rendering manner; the preset background layer is the curtain layer; displaying the individual information of the target participant in the preset background layer of the live streaming room includes: rendering the individual information of the target participant in the curtain layer, rendering the live streaming screen in the screen layer, and rendering interactive components in the interactive information layer; the curtain layer is overlaid with the screen layer through a transparency channel.
[0092] The live streaming room can employ a layered rendering approach, with a backdrop layer, a video layer, and an interactive information layer arranged sequentially from bottom to top. The default background layer serves as the backdrop layer. The backdrop layer primarily renders individual information about the target participants, gameplay details, team member identification, or background atmosphere. The video layer renders the live stream visuals, such as the main video stream after multiple video feeds have been merged. The interactive information layer renders interactive components such as comments, gift effects, the bottom toolbar, and virtual resource candidate panels. These three layers can be composited using the same rendering engine or stacked hierarchically using different view containers.
[0093] The backdrop layer can be overlaid with the image layer using a transparency channel. The transparency channel can be implemented using an alpha channel, with alpha values ranging from 0 to 1. Lower alpha values result in more transparent pixels and higher visibility of the live stream within the image layer; higher alpha values make the information content in the backdrop layer more prominent. On the user's end, non-content areas of the backdrop layer can be set to transparent or low transparency, while areas containing individual avatars, information cards, and virtual resource interaction entry points can be set to higher opacity. This ensures that participants appearing in the live stream are still visible, and that background information areas are located behind or in unobstructed areas as much as possible.
[0094] The above method can maintain the continuous visibility of the live broadcast while carrying a relatively rich amount of individual information; the non-information areas in the screen layer can remain transparent or have low transparency, so that the background information is located behind the participants or in an unobstructed area as much as possible, thereby reducing the direct obstruction of the main content of the live broadcast and improving the integration effect of individual information display and live broadcast.
[0095] As an alternative implementation, different areas within the backdrop layer can be masked with varying degrees of transparency, blur, or color. Bounding box information can also be used to avoid obscuring the facial and limb areas of the target participant. This layered rendering method can convey relatively rich individual information without directly obscuring the main content of the live stream.
[0096] In some embodiments, the method further includes: in response to an event that triggers the determination of a target participant, rendering the area where the target participant is located in the backdrop layer in a style that is distinct from the area where other on-screen participants are located.
[0097] See also Figure 3 (a)-(b), for example, the user can render outlines, soft lighting, highlighted textures, position labels, semi-transparent background blocks, or local color emphasis in the backdrop layer based on the bounding box information of the target participant. This style can differ from the normal area style of other on-screen participants, allowing viewers to quickly locate the target participant in a multi-person scene.
[0098] Specifically, the highlight style can be anchored to the top center point of the target participant's bounding box information, the edge of the circumscribed rectangle, or the area where the participant stands, and moves as the bounding box information is updated. When the target participant is in a performance state, the highlight style can change synchronously with the performance state information, such as adding dynamic outlines or background video effects; when the target participant returns to a normal state, the highlight style can be downgraded to a normal outline or canceled.
[0099] The above processing method enables viewers to quickly locate the target participant in a multi-person scene, enhancing the visual correspondence between the target participant and their individual information; the distinguishing style can move as the bounding box information is updated and can change synchronously with the performance status, improving the recognizability and operational feedback of the target participant without changing the video content of the picture layer.
[0100] As an alternative implementation, the differentiation style does not have to be brightness enhancement; it can also be to reduce the contrast of other non-target areas, change the color of the target area label, display small identification cards, or add position markers. By rendering the differentiation style in the backdrop layer, the correspondence between target participants and individual information can be enhanced without changing the video content of the picture layer.
[0101] In some embodiments, the bounding box information of each on-screen participant in the live broadcast coordinate system is obtained through at least one of the following methods: in response to the bounding box information and corresponding timestamp of each on-screen participant sent by the server at preset time intervals, the bounding box information of each on-screen participant is interpolated and updated according to the timestamp corresponding to the bounding box information of each on-screen participant and the current timestamp to obtain the current bounding box information of each on-screen participant; target recognition and tracking are performed on each on-screen participant in the video frame of the live broadcast, and the current bounding box information of each on-screen participant is determined according to the target recognition and tracking results of each on-screen participant; in response to the initial bounding box information of each on-screen participant sent by the server, target tracking is performed on each on-screen participant according to the initial bounding box information of each on-screen participant, and the current bounding box information of each on-screen participant is determined according to the target tracking results of each on-screen participant.
[0102] The bounding box information of each participant in the live stream can be obtained through server-side delivery, local recognition and tracking on the user's end, or a combination of both. When using server-side delivery, the server can calculate the bounding box information of each participant at preset time intervals or every N frames, and send it to the user's end along with the corresponding timestamp. The user's end then performs interpolation updates based on the timestamp corresponding to the bounding box information and the current timestamp to obtain the current bounding box information of each participant. The interpolation update can use linear interpolation or smoothing filtering to reduce positional jumps caused by network latency or detection intervals.
[0103] When using a local user-side identification and tracking method, the user can identify and track each participant appearing in the live video frame, and determine the current bounding box information based on the identification and tracking results. This method reduces reliance on continuous location data transmission from the server and is suitable for scenarios with a small number of participants or where the user has sufficient computing power.
[0104] When using a hybrid approach, the client can respond to the initial bounding box information of each on-screen participant sent by the server, use the initial bounding box information as anchor points for local target tracking, and fine-tune the bounding box information based on the local tracking results. If the local tracking confidence decreases or the participant is severely occluded, the client can use the bounding box information sent by the server again for correction.
[0105] By sending bounding box information from the server and combining it with timestamp interpolation, local recognition and tracking on the client, or a combination of both, the bounding box information of each participant in the live broadcast frame is obtained. This method supports click-to-hit, long-press to zoom in, information card anchoring, highlight style rendering, and background display position updates. Server-side calculation can unify the recognition results and reduce the computing power consumption on the user side, while local recognition and tracking can reduce position update latency. The hybrid method balances accuracy and smoothness, reduces position jumps caused by network latency or detection intervals, and improves the stability of position tracking in multi-person live broadcasts.
[0106] As an alternative implementation, the bounding box information can be obtained by converting face boxes, body boxes, contour segmentation regions, or standing regions; the coordinates can be normalized coordinates or pixel coordinates, which can be converted on the user side according to the player size; the timestamp can be a video frame timestamp, a server signaling timestamp, or a local playback timestamp on the user side, etc.
[0107] Figure 6 A flowchart illustrating a live streaming configuration method provided in this application embodiment, the method can be... Figure 1 The system shown executes the commands on the user's end, specifically the broadcaster's user's end. For example... Figure 6 As shown, the method may include the following steps: Step S610: Display the live streaming configuration interface, which includes an entry point for editing information of multiple participants associated with the live streaming room.
[0108] Step S620: In response to the operation of triggering the editing entry of one of the participants, the information editing interface of the triggered participant is displayed. The information editing interface includes a component for editing the individual information of the triggered participant. The individual information includes at least an individual image. The individual information is used to display the individual information of the target participant in the preset background layer of the live broadcast room when the triggered participant is the target participant during the live broadcast. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
[0109] As can be seen from the above process, this application, by providing a live streaming configuration interface and multiple entry points for editing participant information, can pre-configure information such as the individual image of participants, thus establishing a stable binding relationship between individual information and specific participants. During the live stream, when a participant is identified as a target participant, the audience can display a more recognizable individual image and related information corresponding to their identity in a preset background layer. This ensures that the original image in the live stream and the image displayed in the preset background layer correspond to each other, guaranteeing a stable source of content displayed by each participant in a multi-person live stream and controllable updates. It also provides a data foundation for the audience's subsequent background display, information card display, and virtual resource interaction.
[0110] See Figure 7 This diagram illustrates a live streaming configuration interface provided in an embodiment of this application. The live streaming configuration interface can be displayed on the user's client. (See also...) Figure 7 As shown in the upper part, the live streaming configuration interface can include editing entry points for multiple participants associated with the target live streaming room. Each participant can be displayed in a list, card, or grid format, with each participant corresponding to an information item. This information item can display the participant's avatar, nickname abbreviation, and editing controls. Live streaming administrators can configure the individual information of a specified participant by clicking or triggering the editing entry point in the corresponding participant's information item.
[0111] In some embodiments, in response to an action that triggers the editing entry of one of the participants, the client may display the information editing interface of the triggered participant. See also Figure 7As shown in the lower half, the information editing interface can include multiple components for editing the participant's individual information. For example, it may include a member name input area, an information input area, and a personal profile configuration area. The information input area may further include edit boxes for fields such as height, gender, and weight, used to enter or modify the participant's introductory information. It should be noted that the fields shown in the figure are merely examples and can be flexibly adjusted and expanded according to actual scenario requirements.
[0112] In some embodiments, the personal avatar configuration area can be used to edit or upload the participant's individual avatar. The avatar can be static image material, such as a headshot, half-body photo, full-body photo, or image poster, or in other embodiments, it can be extended to video material. Live stream administrators can use this area to select local images, replace existing materials, or crop to generate a suitable avatar for display, making it more recognizable than the participant's original image in the live stream. For example, by selecting a clearer frontal image, a larger half-body composition, or a simpler promotional image, the subsequent display and recognition effect in the preset background layer of the live stream can be improved.
[0113] In some embodiments, the information editing interface may also include an effect preview area. See also Figure 7 The lower half of the image shows the preview area, which allows the live stream administrator to view the configured participant information in real time after completing the information entry or uploading of materials. For example, the preview area can display the participant's nickname, height, and other introductory information, as well as their configured personal image. This allows the live stream administrator to visually confirm the completeness of the displayed content, the rationality of the layout, and the sufficient recognizability of the individual image before saving. This preview method helps to verify the configuration results in advance, reducing the need for repeated modifications during the actual live stream due to missing information, unclear images, or poor display effects.
[0114] In some embodiments, after the live stream administrator completes editing, they can submit the edited individual information through the completion editing control in the interface. The user client can save the individual information corresponding to the participant locally and / or upload it to the server to establish a binding relationship between the participant and their individual information. Subsequently, during the live stream, when the viewer's client identifies the participant as the target participant, the viewer can obtain the configured individual information and display it in the preset background layer of the live stream. Thus, a correspondence is formed between the original on-screen image in the live stream and the highly recognizable individual image in the preset background layer.
[0115] According to another embodiment, a live interactive device is provided. Figure 8 This diagram illustrates a schematic block diagram of a live interactive device provided in an embodiment of this application. The device is disposed in... Figure 1 The user-side architecture shown can be specifically applied to the user-side of viewers. For example... Figure 8 As shown, the device 800 includes: The first interface interaction unit 810 is used to respond to an event that triggers the determination of a target participant, determine the target participant from multiple on-screen participants and obtain the individual information of the target participant, wherein the individual information includes at least an individual image.
[0116] The first interface display unit 820 is used to display a live broadcast screen, which includes multiple on-screen participants; and to display the individual information of the target participants in a preset background layer of the live broadcast room, wherein the individual image of the target participants displayed in the preset background layer is used to enhance the original image of the target participants in the live broadcast screen.
[0117] In some embodiments, the individual image is obtained from at least one of pre-configured static image material, pre-configured video material, or a screenshot of the live stream.
[0118] In some embodiments, the individual information further includes at least one of the target participant's introduction information, virtual resource interaction entry, and performance status information; the virtual resource interaction entry is used to trigger the display of candidate virtual resources for the target participant in the live streaming interface.
[0119] In some embodiments, the first interface interaction unit 810 may be specifically configured to: in response to detecting a trigger operation targeting the location area of the first on-camera participant among the plurality of on-camera participants, determine the first on-camera participant as the target participant; in response to detecting that the second on-camera participant among the plurality of on-camera participants is in a preset state, determine the second on-camera participant as the target participant, the preset state including a preset performance state and / or spatial location state.
[0120] In some embodiments, the first interface interaction unit 810 may be specifically configured to: obtain the location information of the triggered location on the live broadcast screen; determine the first on-screen participant selected by the audience as the target participant based on the location information of the triggered location and the region mapping information corresponding to each on-screen participant in the live broadcast screen, wherein the region mapping information includes the bounding box information of each on-screen participant in the coordinate system of the live broadcast screen; or, perform region cropping based on the location information of the triggered location, and obtain the on-screen participant corresponding to the face recognition result of the cropped region as the target participant.
[0121] In some embodiments, the triggering operation for the location area of the first on-camera participant among the plurality of on-camera participants includes: clicking on the location area of the first on-camera participant; the first interface display unit 820 may be specifically configured to: display the first individual information of the first on-camera participant in the preset background layer, the first individual information including at least the first individual image displayed in the first area of the preset background layer, and also including the first introduction information and virtual resource interaction entry of the first on-camera participant displayed in the preset background layer in the form of an information card, the first individual image being a pre-configured static image material or a screenshot of the live broadcast video stream.
[0122] In some embodiments, the triggering operation for the location area of the first on-camera participant among the plurality of on-camera participants includes: a long press operation on the location area of the first on-camera participant; the individual image includes a partially enlarged image, and the first interface display unit 820 can be specifically configured to: display the partially enlarged image of the first on-camera participant in the preset background layer, the partially enlarged image of the first on-camera participant being obtained by taking a screenshot and partially enlarging the video stream of the live broadcast; update the partially enlarged image of the first on-camera participant in response to an operation where the position of the contact point corresponding to the long press changes; and cancel the display of the partially enlarged image of the first on-camera participant in response to an operation where the long press ends.
[0123] In some embodiments, the setting of the second on-camera participant being in a preset state among the plurality of on-camera participants includes: the second on-camera participant being in a performance state and / or being in the center position of the plurality of on-camera participants; the first interface display unit 820 may be specifically configured to: display the second individual information of the second on-camera participant in the preset background layer, the second individual information including at least the second individual image displayed in the second area of the preset background layer, and also including the second introduction information and performance status information of the second on-camera participant displayed in the preset background layer in the form of an information card, the second individual image being pre-configured video material.
[0124] In some embodiments, the first interface display unit 820 may be specifically configured to: in response to the second on-camera participant returning to the original state from the preset state, restore the second individual information of the second on-camera participant displayed in the preset background layer to the information displayed in the original state, the original state including the original performance state and / or spatial position state; in response to the second on-camera participant leaving the live broadcast screen, restore the second individual information of the second on-camera participant displayed in the preset background layer to the default background information.
[0125] In some embodiments, the live streaming room is provided with a curtain layer, a picture layer and an interactive information layer in a layered rendering manner from bottom to top; the preset background layer is the curtain layer; the first interface display unit 820 can be specifically configured to: render the individual information of the target participant in the curtain layer, render the live streaming picture in the picture layer, and render interactive components in the interactive information layer; the curtain layer is superimposed on the picture layer through a transparency channel.
[0126] In some embodiments, the first interface display unit 820 may be specifically configured to: in response to an event that triggers the determination of a target participant, render the area where the target participant is located in the curtain layer in a style that is different from the area where other on-screen participants are located.
[0127] In some embodiments, the bounding box information of each on-screen participant in the live broadcast coordinate system is obtained through at least one of the following methods: in response to the bounding box information and corresponding timestamp of each on-screen participant sent by the server at preset time intervals, the bounding box information of each on-screen participant is interpolated and updated according to the timestamp corresponding to the bounding box information of each on-screen participant and the current timestamp to obtain the current bounding box information of each on-screen participant; target recognition and tracking are performed on each on-screen participant in the video frame of the live broadcast, and the current bounding box information of each on-screen participant is determined according to the target recognition and tracking results of each on-screen participant; in response to the initial bounding box information of each on-screen participant sent by the server, target tracking is performed on each on-screen participant according to the initial bounding box information of each on-screen participant, and the current bounding box information of each on-screen participant is determined according to the target tracking results of each on-screen participant.
[0128] According to another embodiment, a live streaming configuration device is provided. Figure 9 This diagram illustrates a schematic block diagram of a live streaming configuration device provided in an embodiment of this application. The device is disposed in... Figure 1 The client-side architecture shown can be specifically applied to the client-side of broadcaster users. For example... Figure 9 As shown, the device 900 includes: The second interface display unit 910 is used to display the live broadcast configuration interface, which includes an entry point for editing information of multiple participants associated with the live broadcast room.
[0129] The second interface interaction unit 920 is used to respond to the operation of triggering the editing entry of one of the participants and display the information editing interface of the triggered participant. The information editing interface includes a component for editing the individual information of the triggered participant. The individual information includes at least an individual image. The individual information is used to display the individual information of the target participant in the preset background layer of the live broadcast room when the triggered participant is the target participant during the live broadcast. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
[0130] The foregoing has described 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 that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0131] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the description of the method embodiments. The system and device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.
[0132] 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 used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.
[0133] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.
[0134] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.
[0135] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.
[0136] in, Figure 10 An exemplary architecture of an electronic device is shown, which may include a processor 1010, a video display adapter 1011, a disk drive 1012, an input / output interface 1013, a network interface 1014, and a memory 1020. The processor 1010, video display adapter 1011, disk drive 1012, input / output interface 1013, network interface 1014, and memory 1020 can communicate with each other via a communication bus 1030.
[0137] The processor 1010 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.
[0138] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system 1021 for controlling the operation of the electronic device 1000, and the basic input / output system (BIOS) 1022 for controlling the low-level operations of the electronic device 1000. Additionally, it can store a web browser 1023, a data storage management system 1024, etc. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 1020 and called and executed by the processor 1010.
[0139] Input / output interface 1013 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.
[0140] The network interface 1014 is used to connect the communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).
[0141] Bus 1030 includes a pathway for transmitting information between various components of the device, such as processor 1010, video display adapter 1011, disk drive 1012, input / output interface 1013, network interface 1014, and memory 1020.
[0142] It should be noted that although the above-described device only shows the processor 1010, video display adapter 1011, disk drive 1012, input / output interface 1013, network interface 1014, memory 1020, bus 1030, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.
[0143] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this 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. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.
[0144] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A live streaming interactive method, characterized in that, The method is executed by the user's client, and the method includes: The live stream is displayed, and the live stream includes multiple on-screen participants; In response to an event that triggers the determination of a target participant, the target participant is determined from the plurality of on-screen participants and the individual information of the target participant is obtained, the individual information including at least an individual image; The individual information of the target participant is displayed in a preset background layer in the live broadcast room. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
2. The live streaming interactive method according to claim 1, characterized in that, The individual image is obtained from at least one of the following: pre-configured static image material, pre-configured video material, or a screenshot of the live stream.
3. The live streaming interactive method according to claim 1, characterized in that, The individual information also includes at least one of the target participant's introduction information, virtual resource interaction entry point, and performance status information; The virtual resource interaction entry is used to trigger the display of candidate virtual resources for the target participant in the live broadcast interface.
4. The method according to claim 1, characterized in that, The method of determining the target participant from the plurality of on-camera participants in response to an event that triggers the determination of the target participant includes at least one of the following: In response to detecting a trigger operation targeting the location area of the first on-camera participant among the plurality of on-camera participants, the first on-camera participant is identified as the target participant; In response to detecting that the second on-camera participant among the plurality of on-camera participants is in a preset state, the second on-camera participant is identified as the target participant, the preset state including a preset performance state and / or spatial location state.
5. The live streaming interactive method according to claim 4, characterized in that, The step of identifying the first on-camera participant as the target participant includes: Obtain the location information of the triggered position on the live stream screen; Based on the location information of the triggered location and the region mapping information corresponding to each on-screen participant in the live broadcast, the first on-screen participant selected by the viewer is determined as the target participant, and the region mapping information includes the bounding box information of each on-screen participant in the coordinate system of the live broadcast; or, based on the location information of the triggered location, a region is cropped, and the on-screen participant corresponding to the face recognition result of the cropped region is obtained as the target participant.
6. The live streaming interactive method according to claim 4, characterized in that, The triggering operation for the location area of the first on-camera participant among the multiple on-camera participants includes: clicking on the location area of the first on-camera participant; The step of displaying the individual information of the target participant in a preset background layer in the live broadcast room includes: The first individual information of the first on-camera participant is displayed in the preset background layer. The first individual information includes at least the first individual image displayed in the first area of the preset background layer, as well as the first introduction information of the first on-camera participant and the virtual resource interaction entry displayed in the preset background layer in the form of an information card. The first individual image is a pre-configured static image material or a screenshot of the video stream of the live broadcast.
7. The live streaming interactive method according to claim 4, characterized in that, The triggering operation for the location area of the first on-camera participant among the multiple on-camera participants includes: long-pressing the location area of the first on-camera participant. The individual image includes a magnified portion of the image, and the display of the target participant's individual information in the preset background layer of the live stream includes: A magnified partial image of the first on-camera participant is displayed in the preset background layer. The magnified partial image of the first on-camera participant is obtained by taking a screenshot and magnifying a portion of the video stream of the live broadcast. In response to the operation that the position of the corresponding contact point changes when the long press is pressed, the magnified image of the first on-screen participant is updated; In response to the triggering end of the long press, the display of the magnified partial image of the first on-screen participant is canceled.
8. The live interactive method according to claim 4, characterized in that, The phrase "the second on-camera participant among the plurality of on-camera participants is in a preset state" includes: the second on-camera participant is in a performance state and / or is in the center position of the plurality of on-camera participants; The step of displaying the individual information of the target participant in a preset background layer in the live broadcast room includes: The second individual information of the second on-camera participant is displayed in the preset background layer. The second individual information includes at least the second individual image displayed in the second area of the preset background layer, as well as the second introduction information and performance status information of the second on-camera participant displayed in the form of an information card in the preset background layer. The second individual image is pre-configured video material.
9. The live streaming interactive method according to claim 8, characterized in that, The method further includes: In response to the second on-camera participant being restored from the preset state to the original state, the second individual information of the second on-camera participant displayed in the preset background layer is restored to the information displayed in the original state, the original state including the original performance state and / or spatial position state; In response to the second on-screen participant leaving the live stream, the second individual information of the second on-screen participant displayed in the preset background layer is restored to the default background information.
10. The live interactive method according to any one of claims 1-9, characterized in that, The live streaming room uses a layered rendering method, with a screen layer, a picture layer, and an interactive information layer set from the bottom to the top. The preset background layer is the curtain layer; The step of displaying the individual information of the target participant in a preset background layer in the live broadcast room includes: The individual information of the target participant is rendered in the backdrop layer, the live broadcast screen is rendered in the image layer, and the interactive components are rendered in the interactive information layer. The screen layer is superimposed on the image layer through a transparent channel.
11. The method according to claim 10, characterized in that, The method further includes: In response to an event that triggers the identification of a target participant, the area where the target participant is located is rendered in the backdrop layer in a style that distinguishes it from the area where other on-screen participants are located.
12. The live streaming interactive method according to claim 5, characterized in that, The bounding box information of each on-screen participant in the live broadcast coordinate system is obtained through at least one of the following methods: In response to the bounding box information and corresponding timestamp of each on-camera participant sent by the server at preset time intervals, the bounding box information of each on-camera participant is interpolated and updated according to the timestamp corresponding to the bounding box information of each on-camera participant and the current timestamp to obtain the current bounding box information of each on-camera participant. Target recognition and tracking are performed on each participant appearing in the video frame of the live broadcast, and the current bounding box information of each participant is determined based on the target recognition and tracking results. In response to the initial bounding box information of each on-camera participant sent by the server, target tracking is performed on each on-camera participant based on the initial bounding box information of each on-camera participant, and the current bounding box information of each on-camera participant is determined based on the target tracking results of each on-camera participant.
13. A live streaming configuration method, characterized in that, The method is executed by the broadcaster's client, and the method includes: The live streaming configuration interface is displayed, which includes an entry point for editing information of multiple participants associated with the live streaming room; In response to an operation that triggers the editing entry of one of the participants, the information editing interface of the triggered participant is displayed, the information editing interface including components for editing the individual information of the triggered participant; The individual information includes at least an individual image. The individual information is used to display the individual information of the target participant in the preset background layer of the live broadcast room when the triggered participant is the target participant during the live broadcast. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
14. A live interactive device, characterized in that, The device is applied to the user terminal of the audience user, and the device includes: The first interface interaction unit is used to respond to an event that triggers the determination of a target participant, determine the target participant from multiple on-screen participants and obtain the individual information of the target participant, the individual information including at least an individual image; The first interface display unit is used to display the live broadcast screen, which includes multiple on-screen participants; and to display the individual information of the target participants in a preset background layer of the live broadcast room, wherein the individual image of the target participants displayed in the preset background layer is used to enhance the original image of the target participants in the live broadcast screen.
15. A live streaming configuration device, characterized in that, The device is applied to the user terminal of the broadcaster, and the method includes: The second interface display unit is used to display the live streaming configuration interface, which includes an entry point for editing information of multiple participants associated with the live streaming room. The second interface interaction unit is used to respond to the operation of triggering the editing entry of one of the participants and display the information editing interface of the triggered participant. The information editing interface includes components for editing the individual information of the triggered participant. The individual information includes at least an individual image. The individual information is used to display the individual information of the target participant in the preset background layer of the live broadcast room when the triggered participant is the target participant during the live broadcast. The individual image of the target participant displayed in the preset background layer is used to enhance the original image of the target participant in the live broadcast screen.
16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1-12, or the steps of the method according to claim 13.
17. An electronic device, characterized in that, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method of any one of claims 1-12, or perform the steps of the method of claim 13.
18. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1-12, or the steps of the method according to claim 13.
