WO2022121558A1 - 一种直播演唱方法、装置、设备和介质 - Google Patents

一种直播演唱方法、装置、设备和介质 Download PDF

Info

Publication number
WO2022121558A1
WO2022121558A1 PCT/CN2021/128073 CN2021128073W WO2022121558A1 WO 2022121558 A1 WO2022121558 A1 WO 2022121558A1 CN 2021128073 W CN2021128073 W CN 2021128073W WO 2022121558 A1 WO2022121558 A1 WO 2022121558A1
Authority
WO
WIPO (PCT)
Prior art keywords
singing
song
virtual object
action
video content
Prior art date
Application number
PCT/CN2021/128073
Other languages
English (en)
French (fr)
Inventor
杨沐
王骁玮
Original Assignee
北京字跳网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字跳网络技术有限公司 filed Critical 北京字跳网络技术有限公司
Publication of WO2022121558A1 publication Critical patent/WO2022121558A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4758—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for providing answers, e.g. voting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/65—Transmission of management data between client and server
    • H04N21/658—Transmission by the client directed to the server
    • H04N21/6587—Control parameters, e.g. trick play commands, viewpoint selection
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/816—Monomedia components thereof involving special video data, e.g 3D video

Definitions

  • the present disclosure relates to the technical field of live broadcast, and in particular, to a method, device, equipment and medium for live broadcast singing.
  • Live broadcast is the abbreviation of online live broadcast, which is the public broadcast of real-time images on the Internet.
  • the "person” performing or hosting in the instant video is generally referred to as the "host of the live broadcast” and the "host”, and the “person” who enters the live broadcast room to watch the above-mentioned instant video is called the “audience”.
  • the biggest difference between live broadcast and video recording is that the “viewer” can instantly interact with the host by leaving a message, and the "host” can adjust the live broadcast content in real time according to the "viewer”'s feedback on the live broadcast content to meet the needs of the "viewer”.
  • a typical scene of live broadcast is "live broadcast singing".
  • the "host” can sing songs according to the selection of the "audience”.
  • the singing screen of the "host” in the live broadcast room usually does not match the song, the correlation is low, and the interaction effect is general, which affects the user experience.
  • the present disclosure provides a method, apparatus, device and medium for live singing.
  • Embodiments of the present disclosure provide a method for live singing, the method comprising:
  • the screen angle of the singing video content and/or the action of the virtual object in the singing video content are switched.
  • Embodiments of the present disclosure also provide a method for live singing, the method comprising:
  • the switching is performed according to the change of the attribute characteristic of the singing song.
  • Embodiments of the present disclosure also provide a live singing device, the device comprising:
  • a live singing module configured to display the live room page of the virtual object, and play the singing video content corresponding to the singing song of the virtual object on the live room page;
  • the switching module is used to switch the screen viewing angle of the singing video content according to the change of the attribute characteristics of the singing song during the process of playing the singing video content, and/or the action of the virtual object follows the movement of the singing song. Switch according to the change of attribute characteristics.
  • Embodiments of the present disclosure also provide a live singing device, the device comprising:
  • a song determination module for determining the singing song of the virtual object
  • a singing video data module configured to obtain singing video data according to at least one of motion image data and perspective image data corresponding to the singing song, and audio data of the singing song;
  • a data sending module configured to send the singing video data to the terminal, so that the terminal can play the singing video content based on the singing video data, the picture angle of the singing video content, and/or the content of the singing video content.
  • the action of the virtual object is switched with the change of the attributes of the sung song.
  • An embodiment of the present disclosure further provides an electronic device, the electronic device includes: a processor; a memory for storing instructions executable by the processor; the processor for reading the memory from the memory The instructions can be executed, and the instructions can be executed to implement the live singing method provided by the embodiments of the present disclosure.
  • An embodiment of the present disclosure also provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program is used to execute the live singing method provided by the embodiment of the present disclosure.
  • the technical solution provided by the embodiment of the present disclosure has the following advantages: the live singing solution provided by the embodiment of the present disclosure displays the live room page of the virtual object, and plays the singing video content of the virtual object on the live room page of the virtual object ; During the process of playing the virtual object singing video content, the viewing angle of the singing video content and/or the action of the virtual object are switched with the change of the attributes of the singing song.
  • the above technical solution uses the virtual object as the host, and during the process of the virtual object singing songs live, the actions of the virtual object and/or the viewing angle of the singing video content can be automatically changed based on the song, and the singing video content of the virtual object is similar to the singing song. Matching and high correlation make the effect of the virtual object live singing songs better, improve the variety and interest of the virtual object display, and further improve the user experience effect in the process of the virtual object live singing songs.
  • FIG. 1 is a schematic flowchart of a method for live singing according to an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of a live singing provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of another live singing provided by an embodiment of the present disclosure.
  • FIG. 4 is a schematic diagram of yet another live singing provided by an embodiment of the present disclosure.
  • FIG. 5 is a schematic diagram of a song-ordering panel provided by an embodiment of the present disclosure.
  • FIG. 6 is a schematic flowchart of another method for live singing according to an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of a live singing apparatus according to an embodiment of the present disclosure.
  • FIG. 8 is a schematic structural diagram of another live singing apparatus according to an embodiment of the present disclosure
  • FIG. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
  • the term “including” and variations thereof are open-ended inclusions, ie, "including but not limited to”.
  • the term “based on” is “based at least in part on.”
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; the term “some embodiments” means “at least some embodiments”. Relevant definitions of other terms will be given in the description below.
  • FIG. 1 is a schematic flowchart of a method for live singing according to an embodiment of the present disclosure.
  • the method can be executed by a live singing apparatus, wherein the apparatus can be implemented by software and/or hardware, and can generally be integrated in an electronic device.
  • the method is applied to the terminals of multiple viewers entering the live room of the virtual object, including:
  • Step 101 Display the live room page of the virtual object, and play the singing video content of the virtual object on the live room page.
  • Step 102 During the process of playing the singing video content, the viewing angle of the singing video content and/or the action of the virtual object are switched according to the change of the attributes of the singing song.
  • the virtual object can be a three-dimensional model pre-created based on artificial intelligence (Artificial Intelligence, AI) technology
  • a controllable digital object can be set for the computer, and the body movements and facial information of the real person can be obtained through the motion capture device and the face capture device.
  • the specific types of virtual objects may include multiple types, and different virtual objects may have different appearances.
  • the virtual objects may specifically be virtual animals or virtual characters of different styles.
  • virtual objects through the combination of artificial intelligence technology and live video technology, virtual objects can replace real people to realize live video.
  • the live room page refers to a page used to display the live room, and the page may be a web page or a page in an application client.
  • the singing video content refers to the video content generated according to the singing video data for playing.
  • the angle of view of the picture represents the angle of view of different shots when shooting the picture of the singing video content, and the shots can include static shots and dynamic shots.
  • a static lens refers to a lens with a fixed position
  • a dynamic lens refers to a movable lens.
  • a dynamic image can be captured by moving the lens.
  • a dynamic lens can include a surround lens, an orbital lens, and the like.
  • the singing video content of the virtual object played on the page of the live broadcast room is specifically the singing video content corresponding to the singing song of the virtual object.
  • the singing video data of the virtual object is received, wherein the singing video data includes at least one of motion image data and perspective image data corresponding to the singing song, and audio data of the singing song, wherein the virtual object corresponding to the action image data
  • the action of the object and the viewing angle corresponding to the viewing angle image data match the attribute characteristics of the audio data; based on the singing video data of the singing song, the singing video content of the virtual object is generated and played.
  • the singing video data can be understood as the data used to realize the live broadcast of the virtual object, specifically the data pre-configured for the singing song in the server.
  • the singing video data may include a series of data corresponding to the singing song, and specifically may include audio data of the singing song, and motion image data and/or perspective image data corresponding to the singing song.
  • the action of the virtual object corresponding to the action image data and the picture perspective corresponding to the perspective image data match the attribute characteristics of the audio data, and the attribute characteristics matched by the action of the virtual object may be the same or different from the attribute characteristics matched by the screen perspective. Set according to the actual situation.
  • the audio data of the singing song refers to the pre-recorded song audio corresponding to the singing song, which may be recorded by a real person or artificially synthesized according to the timbre of a virtual object.
  • the action image data may include picture data of a virtual object performing multiple continuous actions, that is, the action image data may include a plurality of action pictures used to describe one or more body movements and/or facial movements of the virtual object, forming a group of actions. image.
  • a variety of motion image data can be preset for the virtual object, and each song can be set with corresponding motion image data according to its song type. For example, for a song whose song type is an ancient style, it can correspond to relatively soft motion image data; For songs whose song type is rock, the beat is heavier, and more rock-like motion image data can be used.
  • the viewing angle image data may include action images from different viewing angles.
  • the viewing angle may be the viewing angle when the virtual object is captured by the camera.
  • Display information corresponding to different viewing angles is different, and the display information may include the display size and/or display direction of the action image. For example, when the perspective of the screen is switched from the perspective of the far-lens to the perspective of the near-lens, the display size of the action image is enlarged from small, and when the perspective of the screen is switched from the perspective of the left camera to the perspective of the right camera, the display direction of the action image is switched from left to right. side.
  • the terminal can display the live room page of the virtual object based on the trigger operation of the audience in the live broadcast application, and receive the singing video data sent by the server, and can generate the singing video content of the virtual object by decoding the singing video data. And play the singing video content on the live room page.
  • the viewing angle of the singing video content can be switched according to the change of the attribute characteristics of the singing song, and/or the actions of the virtual objects in the singing video content are carried out according to the change of the attribute characteristics of the singing song. switch.
  • the singing song may be a preset song, or may be a song selected by the user at a historical moment, which is not particularly limited.
  • the live singing method may further include: in response to the singing video content being switched from the first picture perspective to the second picture perspective, adjusting the action image of the virtual object based on the second picture perspective.
  • the singing song is associated with at least one perspective identifier and at least one action identifier.
  • the timestamp associated with the singing song is associated with the perspective identifier and the action identifier.
  • the timestamp associated with the action identifier and the timestamp associated with the perspective identifier may be the same or different.
  • the viewing angle identifier corresponds to at least one picture viewing angle
  • the action identifier corresponds to at least one group of actions
  • the viewing angle identifier and the action identifier associated with the singing song may be determined based on the attributes of the singing song.
  • the viewing angle of the first picture and the viewing angle of the second picture are the viewing angle identifiers of the two different viewing angles of the picture.
  • the display information corresponding to the second viewing angle may adjust the action image data used to generate the singing video content, thereby adjusting the virtual corresponding action image corresponding to the timestamp identified by the second viewing angle, and displaying the adjusted action image.
  • the attribute feature may include at least one of rhythm, melody, and duration, etc.
  • the screen perspective of the singing video content and/or the action of the virtual object is switched with the change of the attribute feature of the singing song, including: responding to Due to changes in rhythm, melody and/or duration of singing songs, the content of the singing video is switched from the third screen perspective to the fourth screen perspective, and/or the action of the virtual object is switched from the first action to the second action, wherein, Actions of virtual objects include facial expressions and/or body movements.
  • the above-mentioned third picture perspective and fourth picture perspective are used to generally refer to different picture perspectives corresponding to the perspective identifiers associated with the singing song, that is, the singing video content can also be switched to different picture perspectives as the attributes of the singing song change.
  • the singing song is associated with a viewing angle indicator, which corresponds to the screen viewing angle surrounding the camera.
  • the screen viewing angle of the virtual object can be switched to the screen viewing angle under the ambient lens, that is, the virtual camera position.
  • the first action and the second action are also used to generally refer to the actions of different virtual objects corresponding to the action identifiers associated with the singing song, and the virtual objects can switch between different actions as the attributes of the singing song change.
  • FIG. 2 is a schematic diagram of a live singing provided by an embodiment of the present disclosure.
  • a live room page of a virtual object 11 is displayed in the figure, and the live room page of the virtual object 11 is displayed.
  • the action of the virtual object 11 is to expand its arms, the viewing angle of the screen is that of the front camera, and a microphone in the scene is also displayed in front of the virtual object 11 .
  • the upper left corner of the live room page in FIG. 2 also displays the avatar and name of the virtual object 11 , which is named "Little A", and the focus button 12 .
  • FIG. 3 is a schematic diagram of another live singing provided by an embodiment of the present disclosure.
  • the action of the virtual object 11 in FIG. 3 remains unchanged.
  • the display size of the virtual object 11 under the display lens becomes smaller, the display direction also changes, and the display direction and display size of the microphone in the figure also change.
  • FIG. 4 is a schematic diagram of another live singing provided by an embodiment of the present disclosure.
  • the action of the virtual object 11 in FIG. 4 changes, and the action changes to arms down, and the viewing angle of the screen is that of the rear camera. Viewing angle, the display size of the virtual object 11 under the display lens becomes larger than that in FIG. 2 , the display direction also changes, and the display direction and display size of the microphone in the figure also change accordingly.
  • the live room page of the virtual object is displayed, and the singing video content of the virtual object is played on the virtual object live room page; in the process of playing the singing video content of the virtual object, the screen perspective of the singing video content, And/or the action of the virtual object is switched according to the change of the attributes of the sung song.
  • the action of the virtual object and/or the viewing angle of the singing video content can be automatically changed based on the song, and the singing video content of the virtual host matches the singing song, and the correlation
  • the higher the value the better the effect of the virtual object live-singing songs is improved, the variety and interest of the virtual object display are improved, and the user's experience effect in the process of the virtual object live-streaming singing songs is improved.
  • the live singing method may further include: displaying a song-ordering panel on the page of the live-streaming room, wherein the song-ordering panel includes interactive information of at least one song; receiving a triggering operation of a user (such as a viewer) on the target song, Update the interactive information of the target song.
  • the target song is any song in the song request panel.
  • the song-ordering panel may be an interface set on the live room page of the virtual object for supporting users to order songs, the song-ordering panel may include interactive information of at least one song, and the interactive information of the song may be triggered by the user number of votes.
  • song request information of the song may also be displayed in the song request panel.
  • the song request information refers to the related information of the song.
  • the song request information may include at least one of the song name, song cover and song duration.
  • the song-ordering panel may be displayed to the user on the live broadcast room page, and the user's triggering operation on any song in the song-ordering panel may be received,
  • the song is the target song, increase the number of votes for the target song in the song-ordering panel by the number corresponding to the triggering operation, and display the updated number of votes, that is, display the updated interactive information. For example, if the user triggers a song twice in the song-ordering panel, the original number of votes for the song is 2, and the original number of votes is increased by 2 to display the updated number of votes 4.
  • the above triggering operation may be various operations, for example, the triggering operation may be a click operation or a double-click operation.
  • FIG. 5 is a schematic diagram of a song-ordering panel provided by an embodiment of the present disclosure.
  • the song-ordering panel 17 includes song-ordering information and the number of votes for 5 songs, song 2 and song 4.
  • the number of votes for each song is the same, 5 votes, and the number of votes for song 5 is the highest.
  • the song cover of each song can be personalized according to the song in advance. As shown in Figure 5, the song covers of each song are different.
  • the lower part of the song request panel 17 also displays the information of the currently playing song 6, and the song 6 has no votes.
  • the information of the songs that the virtual object can sing live can be displayed, and users can vote on the songs, and the number of votes can be displayed to the users, so that the users can know the current song voting information in real time and improve the performance of the song.
  • the singing song is determined based on the quantity of interactive information of the at least one song
  • the method for live singing may further include: receiving a playlist, the playlist includes song information of the at least one song to be sung, and the at least one song to be sung. It is determined based on the amount of interactive information of at least one song; the song list is displayed on the song request panel.
  • the singing song can be the song with the highest amount of interactive information in the song-ordering panel, that is, the song with the highest number of votes by users.
  • the singing song can be updated continuously over time. After the virtual object sings a singing song live, it can perform the next singing song. Live singing. Optionally, the live broadcast prompt information of the next singing song can also be displayed in the song request panel.
  • the upper part of the song request panel 17 displays the live broadcast prompt information of “--:-- start playing the song list/song with the highest number of votes”, and “--:--” can indicate that there are still How long to sing the next song live, the time is determined according to the progress of the current song. It can be understood that when no user votes for the song, the default song can be set as the singing song, for example, the song 6 shown in FIG. 5 is the singing song when no one votes.
  • Users can choose the song they want the virtual object to sing by voting on the song in the song-ordering panel. If the number of votes for a song is the highest, the virtual object can sing the song live, and the virtual object can live broadcast according to the choice of the user watching the live broadcast. Singing further optimizes the interactive diversity of live singing, making the user's interactive experience better.
  • the playlist is a list of songs in the live music library pre-set for the virtual object
  • the live music library may include multiple playlists
  • each playlist may include song information of at least one song to be sung.
  • the at least one song to be sung can be determined based on the amount of interactive information of the at least one song, specifically, the set number of songs with the highest number of interactive information can be determined as the songs to be sung, and the set number is the number of songs to be sung, It can be set according to the actual situation. Multiple songs to be sung in the playlist can also be customized according to the song type.
  • each playlist is pre-configured with live broadcast information such as live broadcast time, live broadcast sequence, and live broadcast times.
  • the live broadcast time can include the live broadcast start time and live broadcast end time preconfigured for the playlist.
  • the order of live broadcast of songs, and the number of live broadcasts refers to the number of times the virtual object sings the song list live. For example, for the morning playlist, the set live broadcast time can be from 8:00 am to 10:00 pm; for the evening playlist, the set live broadcast time can be from 8:00:00 pm to 10:00 pm.
  • the terminal may receive a playlist including song information of at least one song to be sung sent by the server, and display the playlist in the song request panel.
  • the terminal can sequentially receive the singing video data of each song to be sung in the playlist during the live broadcast time of the playlist.
  • the singing video content of the object is played, that is, the virtual object can sing the songs to be sung in sequence according to the live broadcast order of the playlist.
  • the virtual object can be sung live at the corresponding live broadcast time, which is more in line with the scene of the song, and can meet the user's live viewing needs at different times, further improving the user's live broadcast.
  • the effect is more in line with the scene of the song, and can meet the user's live viewing needs at different times, further improving the user's live broadcast.
  • the live singing method may further include: displaying interactive information from multiple audiences on the live broadcast room page; in response to the interactive information and/or the singing song satisfying a preset condition, playing a virtual object on the live broadcast room page for the interactive information
  • the reply multimedia content for the reply may further include: displaying interactive information from multiple audiences on the live broadcast room page; in response to the interactive information and/or the singing song satisfying a preset condition, playing a virtual object on the live broadcast room page for the interactive information
  • the reply multimedia content for the reply may further include: displaying interactive information from multiple audiences on the live broadcast room page; in response to the interactive information and/or the singing song satisfying a preset condition, playing a virtual object on the live broadcast room page for the interactive information
  • the reply multimedia content for the reply may further include: displaying interactive information from multiple audiences on the live broadcast room page; in response to the interactive information and/or the singing song satisfying a preset condition, playing a virtual object on the live broadcast room page for the interactive information
  • the reply multimedia content for the reply may further include: displaying
  • the interactive information refers to interactive texts sent by multiple viewers watching the live broadcast of the virtual object.
  • the terminal can receive interactive information from multiple viewers, display the interactive information on the live room page of the virtual object, and send the interactive information to the server. If the server determines that the number of preset keywords included in the interactive information reaches a preset threshold, and/or determines that the number of historical singing songs has reached the number threshold or that the duration of singing songs has reached the preset duration, it is determined that the preset conditions are met,
  • the reply multimedia data determined based on the interaction information can be sent to the terminal. After receiving the reply multimedia data, the terminal can generate reply multimedia content based on the reply multimedia data, and play the reply multimedia content in which the virtual object replies to the interactive information on the live broadcast room page.
  • the bottom of the live room page displays the interactive information sent by different users watching the live performance, for example, “Why don’t you sing” sent by user A in the figure, and “Hello?” sent by user B. ", and "I'm coming for you” sent by User C.
  • the bottom of the live room page also shows the editing area 13 for the current user to send interactive information and other function buttons, such as the song request button 14, the interactive button 15, and the activity and reward button 16 in the figure. Different function buttons have different functions. Function.
  • the virtual object when it is determined that the scene switching conditions are met based on the interactive information and/or the singing song, the virtual object can be switched from live singing to live chatting, and the interactive information of the audience can be responded to, thus realizing the switching of the two live scenes of the virtual object, satisfying the A variety of interactive needs have been improved, and the diversity of virtual object live broadcasts has been improved.
  • FIG. 6 is a schematic flowchart of another live singing method provided by an embodiment of the present disclosure; the method may be executed by a live singing apparatus, wherein the apparatus may be implemented by software and/or hardware, and may generally be integrated in an electronic device. As shown in Figure 6, the method is applied to the server side of the virtual object, including:
  • Step 201 Determine the singing song of the virtual object.
  • determining the singing song of the virtual object includes: receiving interactive information of at least one song, and determining the singing song according to the interactive information quantity of the interactive information of the at least one song.
  • the interactive information of the song may be the information displayed on the song-ordering panel on the terminal, based on the number of votes triggered by the user.
  • the server can obtain the interactive information of multiple songs in the song-ordering panel, determine the number of interactive information of the song, and determine the song with the highest amount of interactive information as the singing song, that is, the song with the highest number of votes by the user as the singing song.
  • the live singing method may further include: determining at least one song to be sung based on the amount of interactive information of at least one song; generating a playlist based on the song information of the at least one song to be sung and sending it to the terminal, so that the terminal can The song order panel displays the song list.
  • the server can determine the set number of songs with the highest number of interactive information as the songs to be sung, and the set number is the number of songs with singing, which can be set according to the actual situation. Generate a playlist based on the song information of at least one song to be sung, and send the playlist to the terminal.
  • the terminal can receive the playlist including the song information of at least one song to be sung sent by the server, and display it in the song order panel song list.
  • the server can send the singing video data of each song to be sung to the terminal at one time during the live broadcast time of the playlist, and the specific sending order is the live broadcast order set for the playlist in advance.
  • the singing video data of the singing song generates the singing video content of the virtual object for playback, that is, the virtual object can sing the songs to be sung in sequence according to the live broadcast order of the playlist.
  • Step 202 Determine the audio data of the singing song, and the motion image data and perspective image data corresponding to the singing song, and obtain the singing video data.
  • the singing video data may include a series of data corresponding to the singing song, and specifically may include audio data of the singing song, and motion image data and/or perspective image data corresponding to the singing song.
  • the action of the virtual object corresponding to the action image data and the picture perspective corresponding to the perspective image data match the attribute characteristics of the audio data, and the attribute characteristics matched by the action of the virtual object may be the same or different from the attribute characteristics matched by the screen perspective. Set according to the actual situation.
  • the audio data of the singing song refers to the pre-recorded song audio corresponding to the singing song, which can be recorded by a real person.
  • the singing video data may be obtained according to at least one of motion image data and perspective image data corresponding to the singing song, and audio data of the singing song. Specifically, by searching a preset database, the audio data of the singing song, and the motion image data and perspective image data corresponding to the singing song can be determined, and the singing video data can be obtained.
  • the live singing method may further include: matching corresponding action image data and/or perspective image data based on attribute features of the audio data, wherein the action of the virtual object corresponding to the action image data and the screen corresponding to the perspective image data The angle of view is matched with attribute features of the audio data, and the attribute features include at least one of rhythm, melody, and duration.
  • the action image data may include picture data of a virtual object performing multiple continuous actions, that is, the action image data may include a plurality of action pictures used to describe one or more body movements and/or facial movements of the virtual object, forming a group of actions.
  • the viewing angle image data may include action images under different screen viewing angles.
  • the screen viewing angles may be the viewing angles when different lenses are used to capture virtual objects.
  • the display information corresponding to different screen viewing angles may be different, and the display information may include the display size and/or display direction of the action images.
  • matching the corresponding action image data and perspective image data based on the attribute feature of the audio data may include: setting at least one action mark and/or at least one perspective mark in the playback timeline of the singing song based on the attribute feature of the audio data. ; the action image data of the audio segment corresponding to the matching action identifier, and/or the picture viewing angle corresponding to the matching viewing angle identifier, wherein the action image data includes an action image of the virtual object performing at least one set of actions.
  • the attribute feature may include at least one of tempo, melody, duration, and the like.
  • At least one action identification and/or at least one viewing angle identification may be set in the playback timeline of the singing song, and the timestamp associated with the action identification and the timestamp associated with the viewing angle identification may be the same or different;
  • the action image data of the audio segment corresponding to each action identifier is matched, that is, at least one group of actions corresponding to the action identifier is matched, and the picture view angle corresponding to each view point identifier is matched.
  • the method for live singing may further include: based on a pre-built correspondence between the picture perspective and the display information, determining the target display information of the picture perspective corresponding to the perspective identifier, wherein the display information includes the display size of the action image and/or display direction; adjusting the action image of the virtual object based on the target display information to obtain the viewing angle image data of the viewing angle corresponding to the viewing angle identifier.
  • the target display information corresponding to each screen viewing angle can be determined, and based on the target display information, the action images corresponding to the timestamps where the viewing angle identifications are located can be adjusted to obtain the viewing angle corresponding to the viewing angle identification. image data.
  • matching may also be performed based on the song type of the singing song.
  • the genre of the song can be determined based on the melody of the sung song, and the corresponding motion image data can be obtained by matching based on the genre of the song.
  • the song types may include multiple types, for example, the song types may include rock, pop, antique, and modern.
  • each song type may correspond to one piece of motion image data, that is, each song type corresponds to a set of actions of the virtual object. For example, for a song whose song type is Antiquity, it can correspond to relatively soft motion data; while for a song whose song type is Rock, the beat is heavier, and it can correspond to more rocky motion data.
  • the matching relationship can be stored in the database, and then the singing video data of the singing song of the virtual object can be quickly found, which improves the performance of the virtual object. Efficiency of live performances.
  • Step 203 sending the singing video data to the terminal, so that the terminal based on the singing video data, in the process of playing the singing video content of the virtual object, the screen perspective of the singing video content, and/or the action of the virtual object varies with the attributes of the singing song. switch to change.
  • the server After the server determines the performance video singing data of the singing song of the virtual object, it can send the singing video data to the terminal, so that the terminal generates the corresponding singing video content based on the singing video data, and plays the singing video content of the virtual object on the live room page, In the process of playing the singing video content of the virtual object, the viewing angle of the singing video content and/or the action of the virtual object are switched according to the change of the attributes of the singing song.
  • the live singing method may further include: receiving interactive information from multiple audiences; if it is determined based on the interactive information and/or the singing song that a preset condition is met, generating reply multimedia data based on the interactive information and sending it to the terminal, So that the terminal plays the reply multimedia content that the virtual object replies to the interactive information based on the reply multimedia data on the live room page.
  • the interactive information refers to interactive texts sent by multiple viewers watching the live broadcast of the virtual object.
  • the terminal can receive interactive information from multiple viewers, display the interactive information on the live room page of the virtual object, and send the interactive information to the server. If the server determines that the number of preset keywords included in the interactive information reaches a preset threshold, and/or determines that the number of historical singing songs has reached the number threshold or that the duration of singing songs has reached the preset duration, it is determined that the preset conditions are met,
  • the reply multimedia data determined based on the interaction information can be sent to the terminal. After receiving the reply multimedia data, the terminal can generate reply multimedia content based on the reply multimedia data, and play the reply multimedia content in which the virtual object replies to the interactive information on the live broadcast room page.
  • the server determines the singing song of the virtual object, determines the audio data of the singing song, and the motion image data and perspective image data corresponding to the singing song, obtains the singing video data, and sends it
  • the singing video data is sent to the terminal, so that in the process of playing the singing video content of the virtual object based on the singing video data, the screen perspective of the singing video content, and/or the virtual object Actions are switched as the attributes of the sung song change.
  • the singing video data of the virtual object includes motion image data and perspective image data corresponding to the song
  • the actions of the virtual object and/or Or the viewing angle of the singing video content can be automatically changed based on the song.
  • the content of the singing video of the virtual anchor matches the singing song, and the correlation is high, which makes the effect of the virtual object live singing the song better, and improves the variety of the virtual object display. This improves the user experience in the process of live singing songs by virtual objects.
  • FIG. 7 is a schematic structural diagram of a live singing apparatus according to an embodiment of the present disclosure.
  • the apparatus may be implemented by software and/or hardware, and may generally be integrated into an electronic device. As shown in Figure 7, the device includes:
  • the live singing module 301 is configured to display the live room page of the virtual object, and play the singing video content corresponding to the singing song of the virtual object on the live room page;
  • the switching module 302 is configured to switch the viewing angle of the singing video content and/or the action of the virtual object according to the change of the attributes of the singing song during the process of playing the singing video content.
  • the picture angle of view represents the angle of view when the lens captures the picture of the singing video content
  • the lens includes a static lens and a dynamic lens
  • the static lens includes a long-range lens, a close-up lens, a panoramic lens, an overhead shot and a Shoot at least one of the head.
  • the live singing module 301 is specifically used for:
  • the singing video data includes at least one of motion image data and perspective image data corresponding to the singing song of the virtual object, and audio data of the singing song, and the action
  • the action of the virtual object corresponding to the image data and the screen perspective corresponding to the perspective image data match the attribute feature of the audio data
  • the singing video content is generated and played.
  • the device further includes an image adjustment module for:
  • adjusting motion image data used to generate the singing video content based on the second picture perspective to adjust the performance of the singing video content Motion images of virtual objects.
  • the singing song is associated with at least one perspective identifier and at least one action identifier
  • the perspective identifier corresponds to at least one screen perspective
  • the action identifier corresponds to at least one group of actions
  • the perspective identifier associated with the singing song and the The action identification is determined based on the attribute characteristics of the sung song.
  • the attribute feature includes at least one of rhythm, melody and duration
  • the switching module 302 is specifically configured to:
  • the singing video content is switched from the third picture perspective to the fourth picture perspective, and/or, the action of the virtual object is changed from the first picture perspective.
  • the action is switched to a second action, wherein the action of the virtual object includes an expression action and/or a body action.
  • the device also includes a song request module, which is specifically used for:
  • a song-ordering panel is displayed on the live room page, wherein the song-ordering panel includes interactive information of at least one song;
  • the singing song is determined based on the quantity of interactive information of the at least one song
  • the device further includes a song list module for:
  • the playlist includes song information of at least one song to be sung, and the at least one song to be sung is determined based on the quantity of interactive information of the at least one song;
  • the song list is displayed on the song request panel.
  • the device further includes a scene switching module, configured to: display interactive information from multiple viewers on the live room page;
  • the reply multimedia content in which the virtual object replies to the interactive information is played on the live room page.
  • the live singing apparatus provided by the embodiment of the present disclosure can execute the live singing method provided by any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to the execution method.
  • FIG. 8 is a schematic structural diagram of another live singing apparatus provided by an embodiment of the present disclosure.
  • the apparatus may be implemented by software and/or hardware, and may generally be integrated into an electronic device. As shown in Figure 8, the device includes:
  • Song determination module 401 used to determine the singing song of the virtual object
  • a singing video data module 402 configured to obtain singing video data according to at least one of motion image data and perspective image data corresponding to the singing song, and audio data of the singing song;
  • a data sending module 403 configured to send the singing video data to the terminal, so that the terminal can play the singing video content, the screen perspective of the singing video content, and/or the action of the virtual object based on the singing video data Switching is performed according to the change of the attribute characteristics of the sung song.
  • the song determining module 401 is specifically used for:
  • the interactive information of at least one song is received, and the singing song is determined according to the quantity of the interactive information of the at least one song.
  • the device also includes a song list generation module for:
  • a playlist is generated based on the song information of the at least one song to be sung and sent to the terminal, so that the terminal displays the playlist on the song request panel.
  • the device further includes a data matching module for:
  • the corresponding motion image data and/or perspective image data based on the attribute features of the audio data, wherein the action of the virtual object corresponding to the motion image data, the screen perspective corresponding to the perspective image data and the audio
  • the attribute features of the data are matched, and the attribute features include at least one of rhythm, melody, and duration.
  • the data matching module is specifically used for:
  • the action image data includes an action image of the virtual object performing at least one set of actions.
  • the data matching module is specifically used for:
  • the target display information of the picture perspective corresponding to the perspective identifier Based on the pre-built correspondence between the picture perspective and the display information, determine the target display information of the picture perspective corresponding to the perspective identifier, wherein the display information includes the display size and/or the display direction of the action image;
  • the action image of the virtual object is adjusted based on the target display information, and the view angle image data of the screen view angle corresponding to the view angle identifier is obtained.
  • the device further includes a reply switching module for:
  • reply multimedia data is generated based on the interactive information and sent to the terminal, so that the terminal can use the reply multimedia data on the live room page based on the reply multimedia data Playing the reply multimedia content in which the virtual object replies to the interactive information.
  • the live singing apparatus provided by the embodiment of the present disclosure can execute the live singing method provided by any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to the execution method.
  • FIG. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. Referring specifically to FIG. 9 below, it shows a schematic structural diagram of an electronic device 500 suitable for implementing an embodiment of the present disclosure.
  • the electronic device 500 in the embodiment of the present disclosure may include, but is not limited to, such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), an in-vehicle terminal ( For example, mobile terminals such as car navigation terminals) and the like, and stationary terminals such as digital TVs, desktop computers, and the like.
  • the electronic device shown in FIG. 9 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • an electronic device 500 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 501 that may be loaded into random access according to a program stored in a read only memory (ROM) 502 or from a storage device 508 Various appropriate actions and processes are executed by the programs in the memory (RAM) 503 . In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored.
  • the processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504.
  • An input/output (I/O) interface 505 is also connected to bus 504 .
  • I/O interface 505 input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration
  • An output device 507 such as a computer
  • a storage device 508 including, for example, a magnetic tape, a hard disk, etc.
  • Communication means 509 may allow electronic device 500 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 9 shows electronic device 500 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication device 509, or from the storage device 508, or from the ROM 502.
  • the processing device 501 When the computer program is executed by the processing device 501, the above-mentioned functions defined in the live singing method of the embodiment of the present disclosure are executed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the client and server can use any currently known or future developed network protocols such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium.
  • Data communications eg, communication networks
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • LAN local area networks
  • WAN wide area networks
  • the Internet eg, the Internet
  • peer-to-peer networks eg, ad hoc peer-to-peer networks
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device is made to: display the live room page of the virtual object, and play the virtual live room page on the live room page.
  • the singing video content of the object; in the process of playing the singing video content, the screen angle of the singing video content and/or the action of the virtual object are switched with the change of the attributes of the singing song.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device can: determine the singing song of the virtual object; determine the audio data of the singing song, and the motion image data and perspective image data corresponding to the singing song, to obtain the singing video data; send the singing video data to the terminal, so that the terminal plays the singing video of the virtual object based on the singing video data During the content process, the screen view angle of the singing video content and/or the action of the virtual object is switched according to the change of the attributes of the singing song.
  • Computer program code for performing operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and This includes conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments of the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner. Among them, the name of the unit does not constitute a limitation of the unit itself under certain circumstances.
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chips (SOCs), Complex Programmable Logical Devices (CPLDs) and more.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLDs Complex Programmable Logical Devices
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the present disclosure provides a live singing method, including:
  • the screen angle of the singing video content and/or the action of the virtual object are switched.
  • the action data includes picture data of the virtual object performing a plurality of continuous actions
  • the shot data includes at least one shot control for showing a shot information
  • the picture angle of view represents the angle of view of the scene when the scene of the singing video content is captured by the lens
  • the lens includes a static lens and a dynamic lens
  • the The static lens includes at least one of a telephoto lens, a close-up lens, a panoramic lens, an overhead shot, and an overhead shot.
  • playing the singing video content of the virtual object on the live room page includes:
  • the singing video data includes at least one of motion image data and perspective image data corresponding to the singing song, and audio data of the singing song, the action image data corresponding to The action of the virtual object, the picture perspective corresponding to the perspective image data and the attribute feature of the audio data match;
  • the singing video content is generated and played.
  • the method further includes:
  • adjusting motion image data used to generate the singing video content based on the second picture perspective to adjust the performance of the singing video content Motion images of virtual objects.
  • the singing song is associated with at least one perspective identifier and at least one action identifier
  • the perspective identifier corresponds to at least one screen perspective
  • the action identifier corresponds to At least one set of actions
  • the perspective identifier and the action identifier associated with the singing song are determined based on the attribute characteristics of the singing song.
  • the attribute feature includes at least one of rhythm, melody, and duration, and according to the change of the attribute feature of the singing song, switching the The screen perspective of the singing video content and/or the action of the virtual object in the singing video content, including:
  • the singing video content is switched from the third picture perspective to the fourth picture perspective, and/or, the virtual video content in the singing video content is switched.
  • the action of the object is switched from the first action to the second action, wherein the action of the virtual object includes an expression action and/or a body action.
  • the method further includes:
  • a song-ordering panel is displayed on the live room page, wherein the song-ordering panel includes interactive information of at least one song;
  • the singing song is determined based on the quantity of interactive information of the at least one song, and the method further includes:
  • the playlist includes song information of at least one song to be sung, and the at least one song to be sung is determined based on the quantity of interactive information of the at least one song;
  • the song list is displayed on the song request panel.
  • the method further includes:
  • the reply multimedia content in which the virtual object replies to the interactive information is played on the live room page.
  • the present disclosure provides a live singing method, including:
  • determining the singing song of the virtual object includes:
  • the interactive information of at least one song is received, and the singing song is determined according to the quantity of the interactive information of the at least one song.
  • the method further includes:
  • a playlist is generated based on the song information of the at least one song to be sung and sent to the terminal, so that the terminal displays the playlist on the song request panel.
  • the method further includes:
  • the corresponding motion image data and/or perspective image data based on the attribute features of the audio data, wherein the action of the virtual object corresponding to the motion image data, the screen perspective corresponding to the perspective image data and the audio
  • the attribute features of the data are matched, and the attribute features include at least one of rhythm, melody, and duration.
  • matching corresponding motion image data and perspective image data based on the attribute features of the audio data includes:
  • the action image data includes the action image of the virtual object performing at least one set of actions.
  • the method further includes:
  • the target display information of the picture perspective corresponding to the perspective identifier Based on the pre-built correspondence between the picture perspective and the display information, determine the target display information of the picture perspective corresponding to the perspective identifier, wherein the display information includes the display size and/or the display direction of the action image;
  • the action image of the virtual object is adjusted based on the target display information, and the view angle image data of the screen view angle corresponding to the view angle identifier is obtained.
  • the method further includes:
  • reply multimedia data is generated based on the interactive information and sent to the terminal, so that the terminal can use the reply multimedia data on the live room page based on the reply multimedia data Playing the reply multimedia content in which the virtual object replies to the interactive information.
  • the present disclosure provides a live singing apparatus, including:
  • a live singing module configured to display the live room page of the virtual object, and play the singing video content corresponding to the singing song of the virtual object on the live room page;
  • the switching module is configured to switch the viewing angle of the singing video content and/or the action of the virtual object according to the change of the attribute characteristics of the singing song during the process of playing the singing video content.
  • the picture angle of view represents the angle of view of the lens when the scene of the singing video content is captured
  • the lens includes a static lens and a dynamic lens
  • the The static lens includes at least one of a telephoto lens, a close-up lens, a panoramic lens, an overhead shot, and an overhead shot.
  • the live singing module is specifically used for:
  • the singing video data includes at least one of motion image data and perspective image data corresponding to the singing song, and audio data of the singing song, the action image data corresponding to The action of the virtual object, the picture perspective corresponding to the perspective image data and the attribute feature of the audio data match;
  • the singing video content is generated and played.
  • the device further includes an image adjustment module for:
  • adjusting motion image data used to generate the singing video content based on the second picture perspective to adjust the performance of the singing video content Motion images of virtual objects.
  • the singing song is associated with at least one perspective identifier and at least one action identifier
  • the perspective identifier corresponds to at least one screen perspective
  • the action identifier corresponds to At least one set of actions
  • the perspective identifier and the action identifier associated with the singing song are determined based on the attribute characteristics of the singing song.
  • the attribute feature includes at least one of rhythm, melody and duration
  • the switching module is used for:
  • the singing video content is switched from the third picture perspective to the fourth picture perspective, and/or, the virtual video content in the singing video content is switched.
  • the action of the object is switched from the first action to the second action, wherein the action of the virtual object includes an expression action and/or a body action.
  • the device further includes a song request module, which is specifically used for:
  • a song-ordering panel is displayed on the live room page, wherein the song-ordering panel includes interactive information of at least one song;
  • the singing song is determined based on the quantity of interactive information of the at least one song, and the device further includes a playlist module for:
  • the playlist includes song information of at least one song to be sung, and the at least one song to be sung is determined based on the quantity of interactive information of the at least one song;
  • the song list is displayed on the song request panel.
  • the device further includes a scene switching module, configured to: display interactive information from multiple audiences on the live room page;
  • the reply multimedia content in which the virtual object replies to the interactive information is played on the live room page.
  • the present disclosure provides a live singing apparatus, including:
  • a song determination module for determining the singing song of the virtual object
  • a singing video data module configured to obtain singing video data according to at least one of motion image data and perspective image data corresponding to the singing song, and audio data of the singing song;
  • a data sending module configured to send the singing video data to the terminal, so that the terminal plays the singing video content based on the singing video data, and the screen perspective of the singing video content and/or the action of the virtual object follows the singing Switch according to the change of the attribute characteristics of the song.
  • the song determining module is specifically used for:
  • the interactive information of at least one song is received, and the singing song is determined according to the quantity of the interactive information of the at least one song.
  • the device further includes a playlist generation module for:
  • a playlist is generated based on the song information of the at least one song to be sung and sent to the terminal, so that the terminal displays the playlist on the song request panel.
  • the device further includes a data matching module for:
  • the corresponding motion image data and/or perspective image data based on the attribute features of the audio data, wherein the action of the virtual object corresponding to the motion image data, the screen perspective corresponding to the perspective image data and the audio
  • the attribute features of the data are matched, and the attribute features include at least one of rhythm, melody, and duration.
  • the data matching module is specifically used for:
  • the action image data includes an action image of the virtual object performing at least one set of actions.
  • the data matching module is specifically used for:
  • the target display information of the picture perspective corresponding to the perspective identifier Based on the pre-built correspondence between the picture perspective and the display information, determine the target display information of the picture perspective corresponding to the perspective identifier, wherein the display information includes the display size and/or the display direction of the action image;
  • the action image of the virtual object is adjusted based on the target display information, and the view angle image data of the screen view angle corresponding to the view angle identifier is obtained.
  • the device further includes a reply switching module for:
  • the present disclosure provides an electronic device, comprising:
  • a memory for storing the processor-executable instructions
  • the processor is configured to read the executable instructions from the memory, and execute the instructions to implement any one of the live singing methods provided in the present disclosure.
  • the present disclosure provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program is used to execute any of the live broadcasts provided by the present disclosure singing method.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开实施例涉及一种直播演唱方法、装置、设备及介质，其中该方法包括：显示虚拟对象的直播间页面，在虚拟对象直播间页面播放与虚拟对象的演唱歌曲对应的演唱视频内容；在播放虚拟对象演唱视频内容的过程中，根据演唱歌曲的属性特征的变化，切换演唱视频内容的画面视角和/或虚拟对象的动作。采用上述技术方案，在虚拟对象直播演唱歌曲的过程中，虚拟对象的动作和/或演唱视频内容的画面视角均可以基于歌曲进行自动变化，虚拟主播的演唱视频内容与演唱歌曲相匹配，关联性较高，使虚拟对象直播演唱歌曲的效果更优，提高了虚拟对象展示的多样性和趣味性，进而提升了虚拟对象直播演唱歌曲过程中用户的体验效果。

Description

一种直播演唱方法、装置、设备和介质
本申请要求于2020年12月11日提交国家知识产权局、申请号为202011460147.0、申请名称为“一种直播演唱方法、装置、设备及介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及直播技术领域，尤其涉及一种直播演唱方法、装置、设备及介质。
背景技术
随着直播技术的不断发展，观看直播成为人们生活中的一项重要的娱乐活动。直播是网络直播的简称，具体是在互联网上公开播出即时影像。该即时影像中演出或主持的“人”一般称为“直播主”、“主播”，进入直播间观看上述即时影像的“人”称为“观众”。直播与录影的最大差异在于“观众”可以通过留言等方式和主播即时交互，“主播”可以根据“观众”对直播内容的反馈即时调整直播内容，以满足“观众”的需求。
目前，直播的一种典型场景是“直播演唱”。具体地，在直播过程中，“主播”可以根据“观众”的选择进行歌曲的演唱。但是，直播间中“主播”的演唱画面通常和歌曲并不匹配，关联性较低，互动效果一般，影响了用户体验。
发明内容
为了解决上述技术问题或者至少部分地解决上述技术问题，本公开提供了一种直播演唱方法、装置、设备及介质。
本公开实施例提供了一种直播演唱方法，所述方法包括：
显示虚拟对象的直播间页面，在所述直播间页面播放与所述虚拟对象的演唱歌曲对应的演唱视频内容，；
在播放所述演唱视频内容的过程中，根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述演唱视频内容中所述虚拟对象的动作。
本公开实施例还提供了一种直播演唱方法，所述方法包括：
确定虚拟对象的演唱歌曲；
根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，获得演唱视频数据；
发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据播放演唱视频内容，所述演唱视频内容的画面视角，和/或所述演唱视频内容中所述虚拟对象的动作随所述演唱歌曲的属性特征的变化而进行切换。
本公开实施例还提供了一种直播演唱装置，所述装置包括：
直播演唱模块，用于显示虚拟对象的直播间页面，在所述直播间页面播放所述虚拟对象的演唱歌曲对应的演唱视频内容；
切换模块，用于在播放所述演唱视频内容的过程中，根据所述演唱歌曲的属性特征的 变化，切换所述演唱视频内容的画面视角，和/或所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
本公开实施例还提供了一种直播演唱装置，所述装置包括：
歌曲确定模块，用于确定虚拟对象的演唱歌曲；
演唱视频数据模块，用于根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，获得演唱视频数据；
数据发送模块，用于发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据播放演唱视频内容，所述演唱视频内容的画面视角，和/或所述演唱视频内容中所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
本公开实施例还提供了一种电子设备，所述电子设备包括：处理器；用于存储所述处理器可执行指令的存储器；所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现如本公开实施例提供的直播演唱方法。
本公开实施例还提供了一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行如本公开实施例提供的直播演唱方法。
本公开实施例提供的技术方案与现有技术相比具有如下优点：本公开实施例提供的直播演唱方案，显示虚拟对象的直播间页面，在虚拟对象的直播间页面播放虚拟对象的演唱视频内容；在播放虚拟对象演唱视频内容的过程中，演唱视频内容的画面视角，和/或虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。上述技术方案以虚拟对象为主播，在虚拟对象直播演唱歌曲的过程中，虚拟对象的动作和/或演唱视频内容的画面视角均可以基于歌曲进行自动变化，虚拟对象的演唱视频内容与演唱歌曲相匹配，关联性较高，使虚拟对象直播演唱歌曲的效果更优，提高了虚拟对象展示的多样性和趣味性，进而提升了虚拟对象直播演唱歌曲过程中用户的体验效果。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1为本公开实施例提供的一种直播演唱方法的流程示意图；
图2为本公开实施例提供的一种直播演唱的示意图；
图3为本公开实施例提供的另一种直播演唱的示意图；
图4为本公开实施例提供的又一种直播演唱的示意图；
图5为本公开实施例提供的一种点歌面板的示意图；
图6为本公开实施例提供的另一种直播演唱方法的流程示意图；
图7为本公开实施例提供的一种直播演唱装置的结构示意图；
图8为本公开实施例提供的另一种直播演唱装置的结构示意图
图9为本公开实施例提供的一种电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
图1为本公开实施例提供的一种直播演唱方法的流程示意图，该方法可以由直播演唱装置执行，其中该装置可以采用软件和/或硬件实现，一般可集成在电子设备中。如图1所示，该方法应用于进入虚拟对象的直播间的多个观众的终端，包括：
步骤101、显示虚拟对象的直播间页面，在直播间页面播放虚拟对象的演唱视频内容。
步骤102、在播放演唱视频内容的过程中，演唱视频内容的画面视角，和/或虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
其中，虚拟对象可以为基于人工智能(Artificial Intelligence，AI)技术预先创建的一个三维模型，可以为计算机设置可控制的数字化对象，通过动作捕捉设备和面部捕捉设备可以获取真人的肢体动作和面部信息来驱动虚拟对象。虚拟对象的具体类型可以包括多种，不同的虚拟对象可以具有不同的外貌形象，虚拟对象具体可以为虚拟动物，也可以为不同风格的虚拟人物。本公开实施例中，通过人工智能技术与视频直播技术的结合，虚拟对象可以代替真人实现视频直播。
其中，直播间页面是指用于展示直播间的页面，该页面可以是网页页面，也可以是应用程序客户端中的页面。演唱视频内容是指根据演唱视频数据生成的用于进行播放的视频内容。画面视角表征不同镜头拍摄该演唱视频内容的画面时的视角，镜头可以包括静态镜头和动态镜头，静态镜头包括远镜头、近镜头、全景镜头、俯拍镜头和仰拍境头等中的至少一个。静态镜头是指位置固定的镜头，动态镜头是指可移动的镜头，通过镜头的移动拍摄可以拍摄得到动态画面，例如动态镜头可以包括环绕镜头、轨道镜头等。
本公开实施例中，在直播间页面播放的虚拟对象的演唱视频内容，具体是与虚拟对象的演唱歌曲对应的演唱视频内容。具体实现时，接收虚拟对象的演唱视频数据，其中，演 唱视频数据包括与演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及演唱歌曲的音频数据，其中，动作图像数据对应的虚拟对象的动作、视角图像数据对应的画面视角与音频数据的属性特征相匹配；基于演唱歌曲的演唱视频数据生成虚拟对象的演唱视频内容并进行播放。
演唱视频数据可以理解为用于实现虚拟对象直播的数据，具体为服务端中预先为演唱歌曲配置好的数据。演唱视频数据中可以包括与演唱歌曲相对应的一系列数据，具体可以包括演唱歌曲的音频数据，以及与演唱歌曲对应的动作图像数据和/或视角图像数据。动作图像数据对应的虚拟对象的动作、视角图像数据对应的画面视角与音频数据的属性特征相匹配，虚拟对象的动作所匹配的属性特征，与画面视角所匹配的属性特征可以相同也可以不同，具体根据实际情况进行设置。演唱歌曲的音频数据是指演唱歌曲对应的预先录制好的歌曲音频，可以为真人录制，也可以根据虚拟对象音色人工合成。
动作图像数据可以包括虚拟对象进行多个连续动作的画面数据，也即动作图像数据可以包括用于描述虚拟对象的一个或多个肢体运动和/或表情运动的多个动作画面，组成一组动作图像。本公开实施例中针对虚拟对象可以预先设置多种动作图像数据，每个歌曲根据其歌曲类型可以设置对应的动作图像数据，例如对于歌曲类型为古风的歌曲，可以对应比较柔和的动作图像数据；而对于歌曲类型为摇滚的歌曲，节拍较重，可以对于更加摇滚的动作图像数据。
视角图像数据可以包括不同画面视角下的动作图像，画面视角可以为镜头拍摄虚拟对象时的视角，不同画面视角对应的展示信息不同，展示信息可以包括动作图像的展示大小和/或展示方向。例如，当画面视角从远镜头的视角切换近镜头的视角时，动作图像的展示大小从小放大，当画面视角从左镜头切换到右镜头的视角时，动作图像的展示方向从左侧切换到右侧。
具体的，终端可以在直播应用程序基于观众的触发操作，显示虚拟对象的直播间页面，并接收服务端发送的演唱视频数据，通过对演唱视频数据进行解码处理可以生成虚拟对象的演唱视频内容，并在直播间页面中播放该演唱视频内容。在播放演唱视频内容的过程中，演唱视频内容的画面视角可以随演唱歌曲的属性特征的变化而进行切换，和/或，演唱视频内容中虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。演唱歌曲可以为按照预先设置一个歌曲，也可以为历史时刻用户选择的歌曲，具体不限。
本公开实施例中，直播演唱方法还可以包括：响应于演唱视频内容从第一画面视角切换到第二画面视角，基于第二画面视角调整虚拟对象的动作图像。演唱歌曲关联至少一个视角标识以及至少一个动作标识，具体基于演唱歌曲的时间戳与视角标识、动作标识进行关联，动作标识关联的时间戳与视角标识关联的时间戳可以相同也可以不同。视角标识对应至少一个画面视角，动作标识对应至少一组动作，演唱歌曲关联的视角标识和动作标识可以基于演唱歌曲的属性特征确定。第一画面视角与第二画画面视角是两个不同的画面视角的视角标识。
在播放演唱视频内容的过程中，如果演唱歌曲从第一视角标识对应的时间戳播放到第二视角标识对应的时间戳，响应于演唱视频内容从第一画面视角切换到第二画面视角，基 于第二画面视角对应的展示信息可以调整用于生成所述演唱视频内容的动作图像数据，从而调整第二视角标识的时间戳对应的虚拟对应的动作图像，展示调整后的动作图像。
本公开实施例中，属性特征可以包括节奏、旋律和时长等中的至少一个，演唱视频内容的画面视角，和/或虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换，包括：响应于演唱歌曲的节奏变化、旋律变化和/或时长变化，演唱视频内容从第三画面视角切换为第四画面视角，和/或，虚拟对象的动作从第一动作切换为第二动作，其中，虚拟对象的动作包括表情动作和/或肢体动作。
上述第三画面视角和第四画面视角用于泛指演唱歌曲关联的视角标识对应的不同的画面视角，也即随着演唱歌曲的属性特征变化演唱视频内容也可以切换不同的画面视角。例如，演唱歌曲中关联了一个视角标识，对应环绕镜头的画面视角，演唱歌曲播放到视角标识对应的时间点时，可以切换虚拟对象的画面视角为环境镜头下的画面视角，也即虚拟机位做一个环绕行为，实现虚拟对象的环绕展示。第一动作和第二动作也用于泛指演唱歌曲关联的动作标识对应的不同虚拟对象的动作，随着演唱歌曲的属性特征变化虚拟对象可以切换不同的动作。
示例性的，图2为本公开实施例提供的一种直播演唱的示意图，如图2所示，图中展示了一个虚拟对象11的直播间页面，该直播间页面中展示了虚拟对象11的直播演唱过程中的一个直播画面，虚拟对象11的动作为双臂展开，画面视角为前镜头的视角，虚拟对象11前方还展示有场景中的话筒。图2中的直播间页面的左上角还展示了虚拟对象11的头像和名称，名称为“小A”，以及关注按键12。
图3为本公开实施例提供的另一种直播演唱的示意图，图3与图2相比，图3中虚拟对象11的动作没有改变依然是双臂展开，画面视角为左镜头的视角，在该展示镜头下虚拟对象11的展示大小相较于图2变小，展示方向也发生变化，图中话筒的展示方向和展示大小也发生变化。图4为本公开实施例提供的又一种直播演唱的示意图，图4与图2相比，图4中虚拟对象11的动作发生变化，动作变为双臂向下，画面视角为后镜头的视角，在该展示镜头下虚拟对象11的展示大小相较于图2变大，展示方向也发生变化，图中话筒的展示方向和展示大小也相应变化。
基于上述图2、图3和图4的直播演唱的示意图，展示了同一个虚拟对象11在直播演唱同一个演唱歌曲过程中动作和画面视角的变化。上述仅为示例，实际直播演唱的过程中，虚拟对象在直播演唱一首歌曲的过程中，动作的变化和画面视角的切换可以为多种，具体不限。
本公开实施例提供的直播演唱方案，显示虚拟对象的直播间页面，在虚拟对象直播间页面播放虚拟对象的演唱视频内容；在播放虚拟对象演唱视频内容的过程中，演唱视频内容的画面视角，和/或虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。采用上述技术方案，在虚拟对象直播演唱歌曲的过程中，虚拟对象的动作和/或演唱视频内容的画面视角均可以基于歌曲进行自动变化，虚拟主播的演唱视频内容与演唱歌曲相匹配，关联性较高，使虚拟对象直播演唱歌曲的效果更优，提高了虚拟对象展示的多样性和趣味性，进而提升了虚拟对象直播演唱歌曲过程中用户的体验效果。
在一些实施例中，直播演唱方法还可以包括：在直播间页面展示点歌面板，其中，点歌面板中包括至少一首歌曲的互动信息；接收用户(例如观众)对目标歌曲的触发操作，更新目标歌曲的互动信息，目标歌曲为任一首点歌面板中歌曲。
其中，点歌面板可以为虚拟对象的直播间页面上设置的用于支持用户进行点歌的界面，该点歌面板中可以包括至少一首歌曲的互动信息，歌曲的互动信息可以为基于用户触发的投票数量。可选的，点歌面板中还可以展示歌曲的点歌信息，点歌信息是指歌曲的相关信息，例如点歌信息可以包括歌曲名称、歌曲封面和歌曲时长等信息中的至少一个。
具体的，在接收到用户对预设的点歌按键或点歌提示信息的触发操作之后，可以在直播间页面展示点歌面板给用户，接收用户对点歌面板中任意一个歌曲的触发操作，该歌曲为目标歌曲，将点歌面板中该目标歌曲的投票数量增加触发操作对应的数量，并展示更新后的投票数量，也即展示更新后的互动信息。例如用户对点歌面板中的一个歌曲触发两次，则该歌曲的原本投票数量为2，将原本投票数量加2，展示更新后的投票数量4。上述触发操作可以为多种操作，例如触发操作可以为点击操作或双击操作等。
参见图2，图2中虚拟对象11的直播间页面中展示有点歌按键14，当接收用户对该点歌按键11的触发操作之后，可以展示点歌面板给用户。示例性的，图5为本公开实施例提供的一种点歌面板的示意图，如图5所示，点歌面板17中包括了5个歌曲的点歌信息以及投票数量，歌曲2和歌曲4的投票数量相同，均为5票，歌曲5的投票数量最高，每个歌曲的歌曲封面可以为预先根据歌曲进行个性化制作，如图5中各歌曲的歌曲封面均不相同。点歌面板17的下方还展示有正在播放的歌曲6的信息，歌曲6无人投票。
上述方案中，通过点歌面板的设置，可以展示虚拟对象能够直播演唱的歌曲的信息，并且支持用户对歌曲的投票，将投票数量展示给用户，使用户可以实时了解当前的歌曲投票信息，提高了虚拟对象的互动效果。
在一些实施例中，演唱歌曲基于至少一首歌曲的互动信息数量确定，直播演唱方法还可以包括：接收歌单，歌单中包括至少一首待演唱歌曲的歌曲信息，至少一首待演唱歌曲是基于至少一首歌曲的互动信息数量确定的；在点歌面板展示歌单。
演唱歌曲可以为点歌面板中互动信息数量最高的歌曲，也即用户投票数量最高的歌曲，演唱歌曲可以随着时间不断更新，虚拟对象对一个演唱歌曲直播演唱之后，可以进行下一个演唱歌曲的直播演唱，可选的，在点歌面板中还可以展示下一演唱歌曲的直播提示信息。
示例性的，参见图5，点歌面板17的上方展示有“--:--后开始播放票数第一的歌单/歌曲”的直播提示信息，“--:--”可以表示还有多长时间直播演唱下一歌曲，该时间根据当前演唱歌曲的进度进行确定。可以理解的是，当没有用户对歌曲进行投票时，可以设置默认歌曲为演唱歌曲，例如图5所示的歌曲6即为无人投票时的演唱歌曲。
用户通过在点歌面板中对歌曲的投票，可以选择希望虚拟对象演唱的歌曲，如果一个歌曲的投票数量最高，则虚拟对象可以直播演唱该歌曲，虚拟对象可以根据观看直播的用户的选择进行直播演唱，进一步优化了直播演唱的交互多样性，使得用户的交互体验更优。
其中，歌单为预先为虚拟对象设置的直播曲库中的歌曲清单，直播曲库中可以包括多个歌单，每个歌单中可以包括至少一首待演唱歌曲的歌曲信息。至少一首待演唱歌曲可以 基于至少一首歌曲的互动信息数量确定的，具体可以将互动信息数量靠前的设定数量首歌曲确定为待演唱歌曲，设定数量即为待演唱歌曲的数量，可以根据实际情况设定。歌单中的多首待演唱歌曲也可以根据歌曲类型自定义配置。可选的，每个歌单预先配置有直播时间、直播顺序以及直播次数等直播信息，直播时间可以包括预先为歌单配置的直播起始时间和直播结束时间，直播顺序是指歌单中各歌曲直播的先后顺序，直播次数是指虚拟对象直播演唱歌单的次数。例如对于早起歌单，设置的直播时间可以为早上8点-10点，对于晚间歌单，设置的直播时间可以为晚上8点-10点。
本实施例中，终端可以接收服务端发送的包括至少一首待演唱歌曲的歌曲信息的歌单，并在点歌面板中展示歌单。终端在歌单的直播时间可以依次接收歌单中各首待演唱歌曲的演唱视频数据，具体接收顺序为预先为该歌单设置的直播顺序，并基于各首待演唱歌曲的演唱视频数据生成虚拟对象的演唱视频内容进行播放，也即虚拟对象可以按照歌单的直播顺序依次对各首待演唱歌曲进行演唱。
上述方案中，通过预先为虚拟对象设置歌单，可以在对应的直播时间进行虚拟对象的直播演唱，更加符合歌曲的场景，并且可以满足用户在不同时间的直播观看需求，进一步提高了用户的直播体验效果。
在一些实施例中，直播演唱方法还可以包括：在直播间页面展示来自多个观众的互动信息；响应于互动信息和/或演唱歌曲满足预设条件，在直播间页面播放虚拟对象针对互动信息进行回复的回复多媒体内容。
其中，互动信息是指观看虚拟对象直播的多个观众发送的互动文本。终端可以接收来自多个观众的互动信息，并将互动信息在虚拟对象的直播间页面进行展示，并发送互动信息至服务端。如果服务端确定互动信息中包括预设关键词的数量达到预设阈值，和/或，确定历史的演唱歌曲的数量达到数量阈值或演唱歌曲的时长达到预设时长，则确定满足预设条件，可以发送基于互动信息确定的回复多媒体数据给终端。终端接收到回复多媒体数据，可以基于回复多媒体数据生成回复多媒体内容，并在直播间页面播放虚拟对象针对互动信息进行回复的回复多媒体内容。
示例性的，参见图2，直播间页面的下方展示了观看直播演唱中的不同用户发送的互动信息，例如图中的用户A发送的“你怎么还不唱歌”，用户B发送的“你好”，以及用户C发送的“我来找你啦”。直播间页面的最下方还展示了当前用户发送互动信息的编辑区域13以及其他功能按键，例如图中的点歌按键14、互动按键15以及活动及奖励按键16等，不同的功能按键具备不同的功能。
上述方案中，当基于互动信息和/或演唱歌曲确定满足场景切换条件时，可以将虚拟对象从直播演唱切换到直播聊天，回复观众的互动信息，实现了虚拟对象两种直播场景的切换，满足了多种互动需求，提高了虚拟对象直播的多样性。
图6为本公开实施例提供的另一种直播演唱方法的流程示意图；该方法可以由直播演唱装置执行，其中该装置可以采用软件和/或硬件实现，一般可集成在电子设备中。如图6所示，该方法应用于虚拟对象的服务端，包括：
步骤201、确定虚拟对象的演唱歌曲。
本公开实施例中，确定虚拟对象的演唱歌曲，包括：接收至少一首歌曲的互动信息，根据至少一首歌曲的互动信息的互动信息数量确定演唱歌曲。
歌曲的互动信息可以为在终端上展示在点歌面板上的信息，以为基于用户触发的投票数量。服务端可以获取点歌面板中多个歌曲的互动信息，并确定歌曲的互动信息数量，将互动信息数量最高的歌曲确定为演唱歌曲，也即将用户投票数量最高的歌曲确定为演唱歌曲。
可选的，直播演唱方法还可以包括：基于至少一首歌曲的互动信息数量确定至少一首待演唱歌曲；基于至少一首待演唱歌曲的歌曲信息生成歌单并发送至终端，以使终端在点歌面板展示歌单。
具体的，服务端可以将互动信息数量靠前的设定数量首歌曲确定为待演唱歌曲，设定数量即为带演唱歌曲的数量，可以根据实际情况设定。基于至少一首待演唱歌曲的歌曲信息生成歌单，将歌单发送至终端中，终端可以接收服务端发送的包括至少一首待演唱歌曲的歌曲信息的歌单，并在点歌面板中展示歌单。服务端可以在歌单的直播时间可以一次发送各首待演唱歌曲的演唱视频数据给终端，具体发送顺序为预先为该歌单设置的直播顺序，终端接收到演唱视频数据之后，基于各首待演唱歌曲的演唱视频数据生成虚拟对象的演唱视频内容进行播放，也即虚拟对象可以按照歌单的直播顺序依次对各首待演唱歌曲进行演唱。
步骤202、确定演唱歌曲的音频数据，以及与演唱歌曲对应的动作图像数据和视角图像数据，得到演唱视频数据。
演唱视频数据中可以包括与演唱歌曲相对应的一系列数据，具体可以包括演唱歌曲的音频数据，以及与演唱歌曲对应的动作图像数据和/或视角图像数据。动作图像数据对应的虚拟对象的动作、视角图像数据对应的画面视角与音频数据的属性特征相匹配，虚拟对象的动作所匹配的属性特征，与画面视角所匹配的属性特征可以相同也可以不同，具体根据实际情况进行设置。演唱歌曲的音频数据是指演唱歌曲对应的预先录制好的歌曲音频，可以为真人录制得到。
本公开实施例中，可以根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及演唱歌曲的音频数据，获得演唱视频数据。具体的，通过查找预设的数据库，可以确定演唱歌曲的音频数据，以及与演唱歌曲对应的动作图像数据和视角图像数据，得到演唱视频数据。
本公开实施例中，直播演唱方法还可以包括：基于音频数据的属性特征匹配对应的动作图像数据和/或视角图像数据，其中，动作图像数据对应的虚拟对象的动作、视角图像数据对应的画面视角与音频数据的属性特征相匹配，属性特征包括节奏、旋律和时长中的至少一个。
动作图像数据可以包括虚拟对象进行多个连续动作的画面数据，也即动作图像数据可以包括用于描述虚拟对象的一个或多个肢体运动和/或表情运动的多个动作画面，组成一组动作图像。视角图像数据可以包括不同画面视角下的动作图像，画面视角可以为不同镜头 拍摄虚拟对象时的视角，不同画面视角对应的展示信息不同，展示信息可以包括动作图像的展示大小和/或展示方向。
可选的，基于音频数据的属性特征匹配对应的动作图像数据和视角图像数据，可以包括：基于音频数据的属性特征在演唱歌曲的播放时间轴中设置至少一个动作标识和/或至少一个视角标识；匹配动作标识对应的音频片段的动作图像数据，和/或匹配视角标识对应的画面视角，其中动作图像数据包括虚拟对象进行至少一组动作的动作图像。属性特征可以包括节奏、旋律和时长等中的至少一个。
基于演唱歌曲的音频数据的属性特征可以在演唱歌曲的播放时间轴中设置至少一个动作标识和/或至少一个视角标识，动作标识关联的时间戳与视角标识关联的时间戳可以相同也可以不同；匹配各动作标识对应的音频片段的动作图像数据，也即匹配动作标识对应的至少一组动作，匹配各视角标识对应的画面视角。
本公开实施例中，直播演唱方法还可以包括：基于预先构建的画面视角与展示信息之间的对应关系，确定视角标识对应的画面视角的目标展示信息，其中，展示信息包括动作图像的展示大小和/或展示方向；基于目标展示信息调整虚拟对象的动作图像，得到视角标识对应的画面视角的视角图像数据。
基于演唱歌曲的属性特征设置视角标识并匹配对应的画面视角之后，可以确定各画面视角对应的目标展示信息，并基于目标展示信息调整视角标识所在时间戳对应的动作图像，得到视角标识对应的视角图像数据。
可选的，确定演唱歌曲对应的动作图像数据，还可以基于演唱歌曲的歌曲类型进行匹配。基于演唱歌曲的旋律可以确定歌曲类型，并基于歌曲类型匹配得到对应的动作图像数据。歌曲类型可以包括多种，例如歌曲类型可以包括摇滚、流行、古风和现代等类型。本公开实施例中，每种歌曲类型可以对应一个动作图像数据，也即每种歌曲类型对应虚拟对象的一套动作。例如，对于歌曲类型为古风的歌曲，可以对应比较柔和的动作数据；而对于歌曲类型为摇滚的歌曲，节拍较重，可以对于更加摇滚的动作数据。
上述方案中，通过预先对演唱歌曲进行动作图像数据和/或视角图像数据的匹配，可以将匹配关系存储在数据库中，进而可以快速查找到虚拟对象的演唱歌曲的演唱视频数据，提高了虚拟对象进行直播演唱的效率。
步骤203、发送演唱视频数据至终端，以使终端基于演唱视频数据在播放虚拟对象的演唱视频内容的过程中，演唱视频内容的画面视角，和/或虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
服务端确定虚拟对象的演唱歌曲的演视频唱数据之后，可以发送演唱视频数据至终端，以使终端基于演唱视频数据生成对应的演唱视频内容，并在直播间页面播放虚拟对象的演唱视频内容，在播放虚拟对象的演唱视频内容的过程中，演唱视频内容的画面视角，和/或虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
本公开实施例中，直播演唱方法还可以包括：接收来自多个观众的互动信息；如果基于互动信息和/或演唱歌曲确定满足预设条件，则基于互动信息生成回复多媒体数据并发送至终端，以使终端在直播间页面基于回复多媒体数据播放虚拟对象针对互动信息进行回复 的回复多媒体内容。
其中，互动信息是指观看虚拟对象直播的多个观众发送的互动文本。终端可以接收来自多个观众的互动信息，并将互动信息在虚拟对象的直播间页面进行展示，并发送互动信息至服务端。如果服务端确定互动信息中包括预设关键词的数量达到预设阈值，和/或，确定历史的演唱歌曲的数量达到数量阈值或演唱歌曲的时长达到预设时长，则确定满足预设条件，可以发送基于互动信息确定的回复多媒体数据给终端。终端接收到回复多媒体数据，可以基于回复多媒体数据生成回复多媒体内容，并在直播间页面播放虚拟对象针对互动信息进行回复的回复多媒体内容。这样设置的好处在于，实现了虚拟对象两种直播场景的切换，满足了多种互动需求，提高了虚拟对象直播的多样性。
本公开实施例提供的直播演唱方案，服务端确定虚拟对象的演唱歌曲，确定所述演唱歌曲的音频数据，以及与所述演唱歌曲对应的动作图像数据和视角图像数据，得到演唱视频数据，发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据在播放所述虚拟对象的演唱视频内容的过程中，所述演唱视频内容的画面视角，和/或所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。采用上述技术方案，由于虚拟对象的演唱视频数据中包括歌曲对应的动作图像数据和视角图像数据，演唱视频数据发送至用户端之后，在虚拟对象直播演唱歌曲的过程中，虚拟对象的动作和/或演唱视频内容的画面视角均可以基于歌曲进行自动变化，虚拟主播的演唱视频内容与演唱歌曲相匹配，关联性较高，使虚拟对象直播演唱歌曲的效果更优，提高了虚拟对象展示的多样性和趣味性，进而提升了虚拟对象直播演唱歌曲过程中用户的体验效果。
图7为本公开实施例提供的一种直播演唱装置的结构示意图，该装置可由软件和/或硬件实现，一般可集成在电子设备中。如图7所示，该装置包括：
直播演唱模块301，用于显示虚拟对象的直播间页面，在所述直播间页面播放所述虚拟对象的演唱歌曲对应的演唱视频内容；
切换模块302，用于在播放所述演唱视频内容的过程中，根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述虚拟对象的动作。
可选的，所述画面视角表征镜头拍摄所述演唱视频内容的画面时的视角，所述镜头包括静态镜头和动态镜头，所述静态镜头包括远镜头、近镜头、全景镜头、俯拍镜头和仰拍境头中的至少一个。
可选的，所述直播演唱模块301具体用于：
接收虚拟对象的演唱视频数据，其中，所述演唱视频数据包括与所述虚拟对象的演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配；
基于所述演唱歌曲的演唱视频数据生成演唱视频内容并进行播放。
可选的，所述装置还包括图像调整模块，用于：
响应于所述演唱视频内容从第一画面视角切换到第二画面视角，基于所述第二画面视 角调整用于生成所述演唱视频内容的动作图像数据，以调整所述演唱视频内容中所述虚拟对象的动作图像。
可选的，所述演唱歌曲关联至少一个视角标识以及至少一个动作标识，所述视角标识对应至少一个画面视角，所述动作标识对应至少一组动作，演唱歌曲关联的所述视角标识和所述动作标识基于演唱歌曲的属性特征确定。
可选的，所述属性特征包括节奏、旋律和时长中的至少一个，所述切换模块302具体用于：
响应于所述演唱歌曲的节奏变化、旋律变化和/或时长变化，将所述演唱视频内容从第三画面视角切换为第四画面视角，和/或，将所述虚拟对象的动作从第一动作切换为第二动作，其中，所述虚拟对象的动作包括表情动作和/或肢体动作。
可选的，所述装置还包括点歌模块，具体用于：
在所述直播间页面展示点歌面板，其中，所述点歌面板中包括至少一首歌曲的互动信息；
接收用户对目标歌曲的触发操作，更新所述目标歌曲的互动信息，所述目标歌曲为任一首所述点歌面板中歌曲。
可选的，所述演唱歌曲基于所述至少一首歌曲的互动信息数量确定，所述装置还包括歌单模块，用于：
接收歌单，所述歌单中包括至少一首待演唱歌曲的歌曲信息，所述至少一首待演唱歌曲是基于所述至少一首歌曲的互动信息数量确定的；
在所述点歌面板展示所述歌单。
可选的，所述装置还包括场景切换模块，用于：在所述直播间页面展示来自多个观众的互动信息；
响应于所述互动信息和/或所述演唱歌曲满足预设条件，在所述直播间页面播放所述虚拟对象针对所述互动信息进行回复的回复多媒体内容。
本公开实施例所提供的直播演唱装置可执行本公开任意实施例所提供的直播演唱方法，具备执行方法相应的功能模块和有益效果。
图8为本公开实施例提供的另一种直播演唱装置的结构示意图，该装置可由软件和/或硬件实现，一般可集成在电子设备中。如图8所示，该装置包括：
歌曲确定模块401，用于确定虚拟对象的演唱歌曲；
演唱视频数据模块402，用于根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，获得演唱视频数据；
数据发送模块403，用于发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据播放演唱视频内容，所述演唱视频内容的画面视角，和/或所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
可选的，所述歌曲确定模块401具体用于：
接收至少一首歌曲的互动信息，根据所述至少一首歌曲的互动信息数量确定所述演唱 歌曲。
可选的，所述装置还包括歌单生成模块，用于：
基于所述至少一首歌曲的互动信息数量确定至少一首待演唱歌曲；
基于所述至少一首待演唱歌曲的歌曲信息生成歌单并发送至所述终端，以使所述终端在点歌面板展示所述歌单。
可选的，所述装置还包括数据匹配模块，用于：
基于所述音频数据的属性特征匹配对应的动作图像数据和/或视角图像数据，其中，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配，所述属性特征包括节奏、旋律和时长中的至少一个。
可选的，所述数据匹配模块具体用于：
基于所述音频数据的属性特征在所述演唱歌曲的播放时间轴中设置至少一个动作标识和/或至少一个视角标识；
匹配所述动作标识对应的音频片段的动作图像数据，和/或匹配所述视角标识对应的画面视角，其中所述动作图像数据包括所述虚拟对象进行至少一组动作的动作图像。
可选的，所述数据匹配模块具体用于：
基于预先构建的画面视角与展示信息之间的对应关系，确定所述视角标识对应的画面视角的目标展示信息，其中，所述展示信息包括动作图像的展示大小和/或展示方向；
基于所述目标展示信息调整所述虚拟对象的动作图像，得到所述视角标识对应的画面视角的视角图像数据。
可选的，所述装置还包括回复切换模块，用于：
接收来自多个观众的互动信息；
当所述互动信息和/或所述演唱歌曲确定满足预设条件时，基于所述互动信息生成回复多媒体数据并发送至所述终端，以使所述终端在直播间页面基于所述回复多媒体数据播放所述虚拟对象针对所述互动信息进行回复的回复多媒体内容。
本公开实施例所提供的直播演唱装置可执行本公开任意实施例所提供的直播演唱方法，具备执行方法相应的功能模块和有益效果。
图9为本公开实施例提供的一种电子设备的结构示意图。下面具体参考图9，其示出了适于用来实现本公开实施例中的电子设备500的结构示意图。本公开实施例中的电子设备500可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图9示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图9所示，电子设备500可以包括处理装置(例如中央处理器、图形处理器等)501，其可以根据存储在只读存储器(ROM)502中的程序或者从存储装置508加载到随机访问存储器(RAM)503中的程序而执行各种适当的动作和处理。在RAM 503中，还存储有电子设备500操作所需的各种程序和数据。处理装置501、ROM 502以及RAM 503通过总线 504彼此相连。输入/输出(I/O)接口505也连接至总线504。
通常，以下装置可以连接至I/O接口505：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置506；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置507；包括例如磁带、硬盘等的存储装置508；以及通信装置509。通信装置509可以允许电子设备500与其他设备进行无线或有线通信以交换数据。虽然图9示出了具有各种装置的电子设备500，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置509从网络上被下载和安装，或者从存储装置508被安装，或者从ROM 502被安装。在该计算机程序被处理装置501执行时，执行本公开实施例的直播演唱方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务端可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：显示虚拟对象的直播间页面，在所述直播间页面播放所述虚 拟对象的演唱视频内容；在播放所述演唱视频内容的过程中，所述演唱视频内容的画面视角，和/或所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
或者，上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：确定虚拟对象的演唱歌曲；确定所述演唱歌曲的音频数据，以及与所述演唱歌曲对应的动作图像数据和视角图像数据，得到演唱视频数据；发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据在播放所述虚拟对象的演唱视频内容的过程中，所述演唱视频内容的画面视角，和/或所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务端上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存 储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，本公开提供了一种直播演唱方法，包括：
显示虚拟对象的直播间页面，在所述直播间页面播放与所述虚拟对象的演唱歌曲对应的演唱视频内容；
在播放所述演唱视频内容的过程中，根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述虚拟对象的动作。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述动作数据包括所述虚拟对象进行多个连续动作的画面数据，所述镜头数据包括至少一个展示镜头的镜头控制信息。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述画面视角表征镜头拍摄所述演唱视频内容的画面时的视角，所述镜头包括静态镜头和动态镜头，所述静态镜头包括远镜头、近镜头、全景镜头、俯拍镜头和仰拍境头中的至少一个。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，在所述直播间页面播放所述虚拟对象的演唱视频内容，包括：
接收虚拟对象的演唱视频数据，其中，所述演唱视频数据包括与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配；
基于所述演唱歌曲的演唱视频数据生成演唱视频内容并进行播放。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述方法还包括：
响应于所述演唱视频内容从第一画面视角切换到第二画面视角，基于所述第二画面视角调整用于生成所述演唱视频内容的动作图像数据，以调整所述演唱视频内容中所述虚拟对象的动作图像。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述演唱歌曲关联至少一个视角标识以及至少一个动作标识，所述视角标识对应至少一个画面视角，所述动作标识对应至少一组动作，所述演唱歌曲关联的所述视角标识和所述动作标识基于演唱歌曲的属性特征确定。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述属性特征包括节奏、旋律和时长中的至少一个，所述根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述演唱视频内容中所述虚拟对象的动作，包括：
响应于所述演唱歌曲的节奏变化、旋律变化和/或时长变化，将所述演唱视频内容从第三画面视角切换为第四画面视角，和/或，将所述演唱视频内容中所述虚拟对象的动作从第一动作切换为第二动作，其中，所述虚拟对象的动作包括表情动作和/或肢体动作。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述方法还包括：
在所述直播间页面展示点歌面板，其中，所述点歌面板中包括至少一首歌曲的互动信 息；
接收用户对目标歌曲的触发操作，更新所述目标歌曲的互动信息，所述目标歌曲为任一首所述点歌面板中歌曲。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述演唱歌曲基于所述至少一首歌曲的互动信息数量确定，所述方法还包括：
接收歌单，所述歌单中包括至少一首待演唱歌曲的歌曲信息，所述至少一首待演唱歌曲是基于所述至少一首歌曲的互动信息数量确定的；
在所述点歌面板展示所述歌单。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述方法还包括：
在所述直播间页面展示来自多个观众的互动信息；
响应于所述互动信息和/或所述演唱歌曲满足预设条件，在所述直播间页面播放所述虚拟对象针对所述互动信息进行回复的回复多媒体内容。
根据本公开的一个或多个实施例，本公开提供了一种直播演唱方法，包括：
确定虚拟对象的演唱歌曲；
根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，获得演唱视频数据；
发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据播放演唱视频内容，所述演唱视频内容的画面视角和/或播放演唱视频内容中所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，确定所述虚拟对象的演唱歌曲，包括：
接收至少一首歌曲的互动信息，根据所述至少一首歌曲的互动信息数量确定所述演唱歌曲。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述方法还包括：
基于所述至少一首歌曲的互动信息数量确定至少一首待演唱歌曲；
基于所述至少一首待演唱歌曲的歌曲信息生成歌单并发送至所述终端，以使所述终端在点歌面板展示所述歌单。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述方法还包括：
基于所述音频数据的属性特征匹配对应的动作图像数据和/或视角图像数据，其中，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配，所述属性特征包括节奏、旋律和时长中的至少一个。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，基于所述音频数据的属性特征匹配对应的动作图像数据和视角图像数据，包括：
基于所述音频数据的属性特征在所述演唱歌曲的播放时间轴中设置至少一个动作标识和/或至少一个视角标识；
匹配所述动作标识对应的音频片段的动作图像数据，和/或匹配所述视角标识对应的画 面视角，其中所述动作图像数据包括所述虚拟对象进行至少一组动作的动作图像。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述方法还包括：
基于预先构建的画面视角与展示信息之间的对应关系，确定所述视角标识对应的画面视角的目标展示信息，其中，所述展示信息包括动作图像的展示大小和/或展示方向；
基于所述目标展示信息调整所述虚拟对象的动作图像，得到所述视角标识对应的画面视角的视角图像数据。
根据本公开的一个或多个实施例，本公开提供的直播演唱方法中，所述方法还包括：
接收来自多个观众的互动信息；
当所述互动信息和/或所述演唱歌曲确定满足预设条件时，基于所述互动信息生成回复多媒体数据并发送至所述终端，以使所述终端在直播间页面基于所述回复多媒体数据播放所述虚拟对象针对所述互动信息进行回复的回复多媒体内容。
根据本公开的一个或多个实施例，本公开提供了一种直播演唱装置，包括：
直播演唱模块，用于显示虚拟对象的直播间页面，在所述直播间页面播放与所述虚拟对象的演唱歌曲对应的演唱视频内容；
切换模块，用于在播放所述演唱视频内容的过程中，根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述虚拟对象的动作。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述画面视角表征镜头拍摄所述演唱视频内容的画面时的视角，所述镜头包括静态镜头和动态镜头，所述静态镜头包括远镜头、近镜头、全景镜头、俯拍镜头和仰拍境头中的至少一个。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述直播演唱模块具体用于：
接收虚拟对象的演唱视频数据，其中，所述演唱视频数据包括与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配；
基于所述演唱歌曲的演唱视频数据生成演唱视频内容并进行播放。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述装置还包括图像调整模块，用于：
响应于所述演唱视频内容从第一画面视角切换到第二画面视角，基于所述第二画面视角调整用于生成所述演唱视频内容的动作图像数据，以调整所述演唱视频内容中所述虚拟对象的动作图像。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述演唱歌曲关联至少一个视角标识以及至少一个动作标识，所述视角标识对应至少一个画面视角，所述动作标识对应至少一组动作，所述演唱歌曲关联的所述视角标识和所述动作标识基于演唱歌曲的属性特征确定。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述属性特征包括 节奏、旋律和时长中的至少一个，所述切换模块用于：
响应于所述演唱歌曲的节奏变化、旋律变化和/或时长变化，将所述演唱视频内容从第三画面视角切换为第四画面视角，和/或，将所述演唱视频内容中所述虚拟对象的动作从第一动作切换为第二动作，其中，所述虚拟对象的动作包括表情动作和/或肢体动作。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述装置还包括点歌模块，具体用于：
在所述直播间页面展示点歌面板，其中，所述点歌面板中包括至少一首歌曲的互动信息；
接收观众对目标歌曲的触发操作，更新所述目标歌曲的互动信息，所述目标歌曲为任一首所述点歌面板中的任一首歌曲。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述演唱歌曲基于所述至少一首歌曲的互动信息数量确定，所述装置还包括歌单模块，用于：
接收歌单，所述歌单中包括至少一首待演唱歌曲的歌曲信息，所述至少一首待演唱歌曲是基于所述至少一首歌曲的互动信息数量确定的；
在所述点歌面板展示所述歌单。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述装置还包括场景切换模块，用于：在所述直播间页面展示来自多个观众的互动信息；
响应于所述互动信息和/或所述演唱歌曲满足预设条件，在所述直播间页面播放所述虚拟对象针对所述互动信息进行回复的回复多媒体内容。
根据本公开的一个或多个实施例，本公开提供了一种直播演唱装置，包括：
歌曲确定模块，用于确定虚拟对象的演唱歌曲；
演唱视频数据模块，用于根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，获得演唱视频数据；
数据发送模块，用于发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据播放演唱视频内容，所述演唱视频内容的画面视角和/或所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述歌曲确定模块具体用于：
接收至少一首歌曲的互动信息，根据所述至少一首歌曲的互动信息数量确定所述演唱歌曲。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述装置还包括歌单生成模块，用于：
基于所述至少一首歌曲的互动信息数量确定至少一首待演唱歌曲；
基于所述至少一首待演唱歌曲的歌曲信息生成歌单并发送至所述终端，以使所述终端在点歌面板展示所述歌单。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述装置还包括数 据匹配模块，用于：
基于所述音频数据的属性特征匹配对应的动作图像数据和/或视角图像数据，其中，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配，所述属性特征包括节奏、旋律和时长中的至少一个。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述数据匹配模块具体用于：
基于所述音频数据的属性特征在所述演唱歌曲的播放时间轴中设置至少一个动作标识和/或至少一个视角标识；
匹配所述动作标识对应的音频片段的动作图像数据，和/或匹配所述视角标识对应的画面视角，其中所述动作图像数据包括所述虚拟对象进行至少一组动作的动作图像。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述数据匹配模块具体用于：
基于预先构建的画面视角与展示信息之间的对应关系，确定所述视角标识对应的画面视角的目标展示信息，其中，所述展示信息包括动作图像的展示大小和/或展示方向；
基于所述目标展示信息调整所述虚拟对象的动作图像，得到所述视角标识对应的画面视角的视角图像数据。
根据本公开的一个或多个实施例，本公开提供的直播演唱装置中，所述装置还包括回复切换模块，用于：
接收来自多个观众的互动信息；
当所述互动信息和/或所述演唱歌曲满足预设条件时，基于所述互动信息生成回复多媒体数据并发送至所述终端，以使所述终端在直播间页面基于所述回复多媒体数据播放所述虚拟对象针对所述互动信息进行回复的回复多媒体内容。
根据本公开的一个或多个实施例，本公开提供了一种电子设备，包括：
处理器；
用于存储所述处理器可执行指令的存储器；
所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现如本公开提供的任一所述的直播演唱方法。
根据本公开的一个或多个实施例，本公开提供了一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行如本公开提供的任一所述的直播演唱方法。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出 的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (20)

  1. 一种直播演唱方法，其特征在于，所述方法包括：
    显示虚拟对象的直播间页面，在所述直播间页面播放与所述虚拟对象的演唱歌曲对应的演唱视频内容；
    在播放所述演唱视频内容的过程中，根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述演唱视频内容中所述虚拟对象的动作随。
  2. 根据权利要求1所述的方法，其特征在于，所述画面视角表征镜头拍摄所述演唱视频内容的画面时的视角，所述镜头包括静态镜头和动态镜头，所述静态镜头包括远镜头、近镜头、全景镜头、俯拍镜头和仰拍境头中的至少一个。
  3. 根据权利要求1所述的方法，其特征在于，在所述直播间页面播放与所述虚拟对象的演唱歌曲对应的演唱视频内容，包括：
    接收虚拟对象的演唱视频数据，其中，所述演唱视频数据包括与所述虚拟对象的演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配；
    基于所述演唱歌曲的演唱视频数据生成演唱视频内容并进行播放。
  4. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    响应于所述演唱视频内容从第一画面视角切换到第二画面视角，基于所述第二画面视角调整用于生成所述演唱视频内容的动作图像数据，以调整所述演唱视频内容中所述虚拟对象的动作。
  5. 根据权利要求3或4所述的方法，其特征在于，所述演唱歌曲关联至少一个视角标识以及至少一个动作标识，所述视角标识对应至少一个画面视角，所述动作标识对应至少一组动作，所述演唱歌曲关联的所述视角标识和所述动作标识基于所述演唱歌曲的属性特征确定。
  6. 根据权利要求2所述的方法，其特征在于，所述属性特征包括节奏、旋律和时长中的至少一个，所述根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述演唱视频内容中所述虚拟对象的动作，包括：
    响应于所述演唱歌曲的节奏变化、旋律变化和/或时长变化，将所述演唱视频内容从第三画面视角切换为第四画面视角，和/或，将所述演唱视频内容中所述虚拟对象的动作从第一动作切换为第二动作，其中，所述虚拟对象的动作包括表情动作和/或肢体动作。
  7. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述直播间页面展示点歌面板，其中，所述点歌面板中包括至少一首歌曲的互动信息；
    接收观众对目标歌曲的触发操作，更新所述目标歌曲的互动信息，所述目标歌曲为所述点歌面板中的任一首歌曲。
  8. 根据权利要求7所述的方法，其特征在于，所述方法还包括：
    接收歌单，所述歌单中包括至少一首待演唱歌曲的歌曲信息，所述至少一首待演唱歌曲是基于所述至少一首歌曲的互动信息数量确定的；
    在所述点歌面板展示所述歌单。
  9. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述直播间页面展示来自多个观众的互动信息；
    响应于所述互动信息和/或所述演唱歌曲满足预设条件，在所述直播间页面播放回复多媒体内容，所述回复多媒体内容为所述虚拟对象针对所述互动信息的回复。
  10. 一种直播演唱方法，其特征在于，所述方法包括：
    确定虚拟对象的演唱歌曲；
    根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，获得演唱视频数据；
    发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据播放演唱视频内容，所述演唱视频内容的画面视角，和/或所述演唱视频内容中所述虚拟对象的动作随所述演唱歌曲的属性特征的变化而进行切换。
  11. 根据权利要求10所述的方法，其特征在于，确定所述虚拟对象的演唱歌曲，包括：
    接收至少一首歌曲的互动信息，根据所述至少一首歌曲的互动信息数量确定所述演唱歌曲。
  12. 根据权利要求11所述的方法，其特征在于，所述方法还包括：
    基于所述至少一首歌曲的互动信息数量确定至少一首待演唱歌曲；
    基于所述至少一首待演唱歌曲的歌曲信息生成歌单并发送至所述终端，以使所述终端在点歌面板展示所述歌单。
  13. 根据权利要求10所述的方法，其特征在于，所述方法还包括：
    基于所述音频数据的属性特征匹配对应的动作图像数据和/或视角图像数据，其中，所述动作图像数据对应的所述虚拟对象的动作、所述视角图像数据对应的画面视角与所述音频数据的属性特征相匹配，所述属性特征包括节奏、旋律和时长中的至少一个。
  14. 根据权利要求13所述的方法，其特征在于，基于所述音频数据的属性特征匹配对应的动作图像数据和/或视角图像数据，包括：
    基于所述音频数据的属性特征在所述演唱歌曲的播放时间轴中设置至少一个动作标识和/或至少一个视角标识；
    匹配所述动作标识对应的音频片段的动作图像数据，和/或匹配所述视角标识对应的画面视角，其中所述动作图像数据包括所述虚拟对象进行至少一组动作的动作图像。
  15. 根据权利要求14所述的方法，其特征在于，所述方法还包括：
    基于预先构建的画面视角与展示信息之间的对应关系，确定所述视角标识对应的画面视角的目标展示信息，其中，所述展示信息包括动作图像的展示大小和/或展示方向；
    基于所述目标展示信息调整所述虚拟对象的动作图像，得到所述视角标识对应的画面视角的视角图像数据。
  16. 根据权利要求10所述的方法，其特征在于，所述方法还包括：
    接收来自多个观众的互动信息；
    当所述互动信息和/或所述演唱歌曲满足预设条件时，基于所述互动信息生成回复多媒体数据并发送至所述终端，以使所述终端在直播间页面基于所述回复多媒体数据播放所述虚拟对象针对所述互动信息进行回复的回复多媒体内容。
  17. 一种直播演唱装置，其特征在于，所述装置包括：
    直播演唱模块，用于显示虚拟对象的直播间页面，在所述直播间页面播放与所述虚拟对象的演唱歌曲对应的演唱视频内容；
    切换模块，用于在播放所述演唱视频内容的过程中，根据所述演唱歌曲的属性特征的变化，切换所述演唱视频内容的画面视角和/或所述演唱视频内容中所述虚拟对象的动作。
  18. 一种直播演唱装置，其特征在于，所述装置包括：
    歌曲确定模块，用于确定虚拟对象的演唱歌曲；
    演唱视频数据模块，用于根据与所述演唱歌曲对应的动作图像数据、视角图像数据中的至少一个，以及所述演唱歌曲的音频数据，获得演唱视频数据；
    数据发送模块，用于发送所述演唱视频数据至终端，以使所述终端基于所述演唱视频数据播放演唱视频内容，所述演唱视频内容的画面视角，和/或所述演唱视频内容中所述虚拟对象的动作随演唱歌曲的属性特征的变化而进行切换。
  19. 一种电子设备，其特征在于，所述电子设备包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现上述权利要求1-16中任一所述的直播演唱方法。
  20. 一种计算机可读存储介质，其特征在于，所述存储介质存储有计算机程序，所述计算机程序用于执行上述权利要求1-16中任一所述的直播演唱方法。
PCT/CN2021/128073 2020-12-11 2021-11-02 一种直播演唱方法、装置、设备和介质 WO2022121558A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011460147.0A CN112637622A (zh) 2020-12-11 2020-12-11 一种直播演唱方法、装置、设备及介质
CN202011460147.0 2020-12-11

Publications (1)

Publication Number Publication Date
WO2022121558A1 true WO2022121558A1 (zh) 2022-06-16

Family

ID=75312334

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/128073 WO2022121558A1 (zh) 2020-12-11 2021-11-02 一种直播演唱方法、装置、设备和介质

Country Status (2)

Country Link
CN (1) CN112637622A (zh)
WO (1) WO2022121558A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115657862A (zh) * 2022-12-27 2023-01-31 海马云（天津）信息技术有限公司 虚拟ktv场景画面自动切换的方法、装置、存储介质及设备

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112637622A (zh) * 2020-12-11 2021-04-09 北京字跳网络技术有限公司 一种直播演唱方法、装置、设备及介质
CN115239916A (zh) * 2021-04-22 2022-10-25 北京字节跳动网络技术有限公司 虚拟形象的互动方法、装置和设备
CN113205575A (zh) * 2021-04-29 2021-08-03 广州繁星互娱信息科技有限公司 直播唱歌信息的显示方法、装置、终端及存储介质
CN113518235B (zh) * 2021-04-30 2023-11-28 广州繁星互娱信息科技有限公司 直播视频数据生成方法、装置及存储介质
US11769289B2 (en) * 2021-06-21 2023-09-26 Lemon Inc. Rendering virtual articles of clothing based on audio characteristics
CN113766340B (zh) * 2021-09-27 2023-03-31 广州方硅信息技术有限公司 连麦直播下的舞曲互动方法、系统、装置及计算机设备
CN114120943B (zh) * 2021-11-22 2023-07-04 腾讯科技（深圳）有限公司 虚拟演唱会的处理方法、装置、设备及存储介质
CN114155322A (zh) * 2021-12-01 2022-03-08 北京字跳网络技术有限公司 一种场景画面的展示控制方法、装置以及计算机存储介质
CN114363689B (zh) * 2022-01-11 2024-01-23 广州博冠信息科技有限公司 直播控制方法、装置、存储介质及电子设备
CN114745598B (zh) * 2022-04-12 2024-03-19 北京字跳网络技术有限公司 视频数据展示方法、装置、电子设备及存储介质
CN114938364A (zh) * 2022-05-13 2022-08-23 杭州网易云音乐科技有限公司 音频排序方法、音频排序装置、设备、介质和计算设备

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101414322A (zh) * 2007-10-16 2009-04-22 盛趣信息技术（上海）有限公司 虚拟角色的展示方法及系统
CN104899302A (zh) * 2015-06-10 2015-09-09 百度在线网络技术（北京）有限公司 向用户推荐音乐的方法和装置
CN106445460A (zh) * 2016-10-18 2017-02-22 渡鸦科技（北京）有限责任公司 控制方法及装置
CN107422862A (zh) * 2017-08-03 2017-12-01 嗨皮乐镜（北京）科技有限公司 一种虚拟现实场景中虚拟影像交互的方法
JP2018109940A (ja) * 2017-08-21 2018-07-12 株式会社コロプラ 情報処理方法及び当該情報処理方法をコンピュータに実行させるためのプログラム
CN109189541A (zh) * 2018-09-17 2019-01-11 福建星网视易信息系统有限公司 界面显示方法及计算机可读存储介质
CN210112145U (zh) * 2019-02-18 2020-02-21 阿里巴巴集团控股有限公司 音视频会议系统及设备
CN110850983A (zh) * 2019-11-13 2020-02-28 腾讯科技（深圳）有限公司 视频直播中的虚拟对象控制方法、装置和存储介质
CN111343509A (zh) * 2020-02-17 2020-06-26 聚好看科技股份有限公司 一种虚拟形象的动作控制方法及显示设备
CN112637622A (zh) * 2020-12-11 2021-04-09 北京字跳网络技术有限公司 一种直播演唱方法、装置、设备及介质

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9940970B2 (en) * 2012-06-29 2018-04-10 Provenance Asset Group Llc Video remixing system
JP6488290B2 (ja) * 2013-06-28 2019-03-20 コーニンクレッカ フィリップス エヌ ヴェＫｏｎｉｎｋｌｉｊｋｅ Ｐｈｉｌｉｐｓ Ｎ．Ｖ． Ｂｌｕｅｔｏｏｔｈ（登録商標）パーティモードのためのシステム、方法、及び、装置
CN104679378A (zh) * 2013-11-27 2015-06-03 苏州蜗牛数字科技股份有限公司 基于虚拟头像的音乐媒体播放方式
CN104102146B (zh) * 2014-07-08 2016-09-07 苏州乐聚一堂电子科技有限公司 虚拟伴舞通用控制系统
US9691431B2 (en) * 2015-10-16 2017-06-27 Google Inc. Generating videos of media items associated with a user
CN106303732A (zh) * 2016-08-01 2017-01-04 北京奇虎科技有限公司 基于视频直播的互动方法、装置及系统
CN111405357A (zh) * 2019-01-02 2020-07-10 阿里巴巴集团控股有限公司 音视频编辑方法、装置及存储介质
CN110119700B (zh) * 2019-04-30 2020-05-15 广州虎牙信息科技有限公司 虚拟形象控制方法、虚拟形象控制装置和电子设备
CN111179385B (zh) * 2019-12-31 2021-04-02 网易（杭州）网络有限公司 一种舞蹈动画的处理方法及装置、电子设备、存储介质

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101414322A (zh) * 2007-10-16 2009-04-22 盛趣信息技术（上海）有限公司 虚拟角色的展示方法及系统
CN104899302A (zh) * 2015-06-10 2015-09-09 百度在线网络技术（北京）有限公司 向用户推荐音乐的方法和装置
CN106445460A (zh) * 2016-10-18 2017-02-22 渡鸦科技（北京）有限责任公司 控制方法及装置
CN107422862A (zh) * 2017-08-03 2017-12-01 嗨皮乐镜（北京）科技有限公司 一种虚拟现实场景中虚拟影像交互的方法
JP2018109940A (ja) * 2017-08-21 2018-07-12 株式会社コロプラ 情報処理方法及び当該情報処理方法をコンピュータに実行させるためのプログラム
CN109189541A (zh) * 2018-09-17 2019-01-11 福建星网视易信息系统有限公司 界面显示方法及计算机可读存储介质
CN210112145U (zh) * 2019-02-18 2020-02-21 阿里巴巴集团控股有限公司 音视频会议系统及设备
CN110850983A (zh) * 2019-11-13 2020-02-28 腾讯科技（深圳）有限公司 视频直播中的虚拟对象控制方法、装置和存储介质
CN111343509A (zh) * 2020-02-17 2020-06-26 聚好看科技股份有限公司 一种虚拟形象的动作控制方法及显示设备
CN112637622A (zh) * 2020-12-11 2021-04-09 北京字跳网络技术有限公司 一种直播演唱方法、装置、设备及介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115657862A (zh) * 2022-12-27 2023-01-31 海马云（天津）信息技术有限公司 虚拟ktv场景画面自动切换的方法、装置、存储介质及设备

Also Published As

Publication number Publication date
CN112637622A (zh) 2021-04-09

Similar Documents

Publication Publication Date Title
WO2022121558A1 (zh) 一种直播演唱方法、装置、设备和介质
WO2022121601A1 (zh) 一种直播互动方法、装置、设备及介质
KR101664754B1 (ko) 정보 취득 방법, 장치, 프로그램 및 기록매체
WO2022152064A1 (zh) 视频生成方法、装置、电子设备和存储介质
WO2022121557A1 (zh) 一种直播互动方法、装置、设备及介质
WO2020077855A1 (zh) 视频拍摄方法、装置、电子设备及计算机可读存储介质
US11227598B2 (en) Method for controlling terminal by voice, terminal, server and storage medium
US20210281909A1 (en) Method and apparatus for sharing video, and storage medium
CN109729372B (zh) 直播间切换方法、装置、终端、服务器及存储介质
KR20220103110A (ko) 비디오 생성 장치 및 방법, 전자 장치, 및 컴퓨터 판독가능 매체
JP2010541415A (ja) マルチメディアイベントのプレゼンテーションの合成
CN112995759A (zh) 互动业务处理方法、系统、装置、设备及存储介质
WO2022042035A1 (zh) 视频制作方法、装置、设备及存储介质
US20220222881A1 (en) Video display device and display control method for same
TW201416888A (zh) 場景片段播放系統、方法及其記錄媒體
CN112261481B (zh) 互动视频的创建方法、装置、设备及可读存储介质
CN113365134A (zh) 音频分享方法、装置、设备及介质
CN112291590A (zh) 视频处理方法及设备
US20220078221A1 (en) Interactive method and apparatus for multimedia service
WO2023185809A1 (zh) 视频数据生成方法、装置、电子设备及存储介质
JP2024513640A (ja) 仮想対象のアクション処理方法およびその装置、コンピュータプログラム
CN112969093A (zh) 互动业务处理方法、装置、设备及存储介质
CN114501064B (zh) 一种视频生成方法、装置、设备、介质及产品
WO2024067157A1 (zh) 生成特效视频的方法、装置、电子设备及存储介质
WO2024037480A1 (zh) 交互方法、装置、电子设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21902265

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21902265

Country of ref document: EP

Kind code of ref document: A1