WO2022223029A1

WO2022223029A1 - Avatar interaction method, apparatus, and device

Info

Publication number: WO2022223029A1
Application number: PCT/CN2022/088522
Authority: WO
Inventors: 李娣; 林克; 周萍萍; 冯培林; 陈建平; 赖镇威; 赵晶鑫
Original assignee: 北京字节跳动网络技术有限公司
Priority date: 2021-04-22
Filing date: 2022-04-22
Publication date: 2022-10-27
Also published as: CN115239916A

Abstract

The present disclosure relates to an avatar interaction method, apparatus, and device. The method comprises: after a singing live broadcast is started in a virtual live broadcast room, in response to an instruction of a user in the virtual live broadcast room, the avatar of the user can be configured and a target drive mode of the avatar of the user can be started; and when the user is singing in the virtual live broadcast room, the avatar of the user who simulates a target action corresponding to the target drive mode can be displayed performing singing in the virtual live broadcast room.

Description

Interactive method, device and device for avatar

This disclosure claims the priority of the Chinese patent application with the application number 202110436963.6 and the invention title "Interactive Method, Apparatus and Device for Virtual Image", filed with the State Intellectual Property Office of China on April 22, 2021, the entire contents of which are incorporated by reference in this disclosure.

technical field

The present disclosure relates to the technical field of live broadcasting, and in particular, to an interactive method, device and device for virtual images.

Background technique

With the continuous development of Internet technology, webcasting has emerged as the times require, providing users with a rich and colorful entertainment life. Through webcasting, real-time interaction between multiple parties and different places can be realized. Generally, different access addresses (or link addresses) are allocated for different webcasting, which is referred to as a virtual live broadcast room. Thus, users can enter the virtual live broadcast room to watch and interact. For example, the user can enter the virtual live room in the singing room scene to sing.

SUMMARY OF THE INVENTION

In order to solve the above technical problem or at least partially solve the above technical problem, the embodiments of the present disclosure provide a method, apparatus and device for interacting with a virtual image.

In a first aspect, an embodiment of the present disclosure provides a method for interacting with an avatar, including:

After the singing live broadcast is started in a virtual live broadcast room, in response to an instruction of a user in the virtual live broadcast room, configure the user's avatar and activate the target drive mode of the user's avatar; during the process of the user singing in the virtual live broadcast room , displaying the avatar of the user who simulates the target action corresponding to the target driving mode and sings in the virtual live room.

In a possible design, the method further includes: taking a photograph of the user through a camera; determining an avatar of the user based on the photograph of the user; and determining a target driving mode.

In a possible design, the method further includes: acquiring the user's album photos from the local storage space; determining the user's avatar based on the user's album photos; determining the target driving mode.

In a possible design, the method further includes: determining an avatar of the user based on a default avatar; and determining a target-driven mode.

In a possible design, when the target driving mode is the real-time driving mode, displaying the avatar of the user who simulates the target action corresponding to the target driving mode and sings in the virtual live room, including: capturing the head of the user in real time through a camera The head action of the user is determined as the target action; the avatar of the user that simulates the head action of the user in real time is displayed to sing in the virtual live broadcast room.

In a possible design, the method further includes: when the user starts singing in the virtual live broadcast room, displaying first prompt information in the virtual live broadcast room, where the first prompt information is used to prompt the user's avatar to simulate real-time acquisition by a camera the user's head motion.

In a possible design, the method further includes: after the user's head leaves the recognition area of the camera, displaying second prompt information in the virtual live broadcast room, where the second prompt information is used to prompt the user to adjust the user's head.

In a possible design, when the target driving mode is the default driving mode, the avatar of the user who simulates the target action corresponding to the target driving mode is displayed to sing in the virtual live room, including: based on the rhythm of the song sung by the user and/or tone, determine the default action; determine the default action as the target action; display the avatar of the user who simulates the default action to sing in the virtual live room.

In a second aspect, an embodiment of the present disclosure provides an interactive device for a virtual image, including:

The configuration module is used to configure the user's avatar and start the target drive mode of the user's avatar in response to an instruction of a user in the virtual live broadcast room after the singing live broadcast is opened in a virtual live broadcast room;

The display module is used for displaying the avatar of the user who simulates the target action corresponding to the target driving mode to sing in the virtual live broadcast room.

In a possible design, the interactive device of the avatar further includes:

a first acquisition module, used for capturing a photo of the user through a camera;

a first determining module, configured to determine the avatar of the user based on the photograph taken by the user;

The first determining module is further configured to determine the target driving mode.

In a possible design, the interactive device of the avatar further includes:

The second acquisition module is used to acquire the user's album photos from the local storage space;

The second determining module is used to determine the avatar of the user based on the photo album of the user;

The second determining module is further configured to determine the target driving mode.

In a possible design, the interactive device of the avatar further includes:

The third determination module is used for determining the avatar of the user based on a default image; the third determination module is further used for determining the target driving mode.

In a possible design, when the target driving mode is the real-time driving mode, the display module is specifically used to collect the user's head movement in real time through the camera; determine the user's head movement as the target movement; display the real-time simulated user head movement The avatar of the user who performs the action will sing in the virtual live room.

In a possible design, the display module is further configured to display first prompt information in the virtual live broadcast room when the user starts singing in the virtual live broadcast room, where the first prompt information is used to prompt the user's avatar to simulate a camera in real time The head movements of the user are collected in real time.

In a possible design, the display module is further configured to display second prompt information in the virtual live broadcast room after the user's head leaves the recognition area of the camera, where the second prompt information is used to prompt the user to adjust the user's head .

In a possible design, when the target driving mode is the default driving mode, the display module is specifically configured to determine a default action based on the rhythm and/or pitch of the song sung by the user; determine the default action as the target action; display the simulation The avatar of the user in the default action sings in the virtual live room.

In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions in the memory so that the electronic device executes the first aspect and any of the first aspects. An interactive approach to avatars in a possible design.

In a fourth aspect, an embodiment of the present disclosure provides a computer storage medium, including computer instructions, when the computer instructions are executed on an electronic device, the electronic device enables the electronic device to execute the first aspect and any possible design of the first aspect. The interactive method of the image.

In a fifth aspect, an embodiment of the present disclosure provides a computer program product, which, when the computer program product runs on a computer, enables the computer to execute the first aspect and the interactive method of the avatar in any possible design of the first aspect.

In a sixth aspect, an embodiment of the present disclosure provides a chip system, the chip system includes: a processor; when the processor executes a computer instruction stored in a memory, the electronic device executes the first aspect and any possible design of the first aspect Interactive methods for avatars in .

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure, and together with the description serve to explain the principles of the embodiments of the disclosure.

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the accompanying drawings required for describing the embodiments or related technologies will be briefly introduced below. Obviously, for those skilled in the art, On the premise of no creative labor, other drawings can also be obtained from these drawings.

1A-1Z are schematic diagrams of human-computer interaction interfaces provided by embodiments of the present disclosure;

FIG. 2 is a schematic flowchart of a method for interacting with a virtual image according to an embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of an interactive device for a virtual image provided by an embodiment of the present disclosure;

FIG. 4 is a schematic structural diagram of an interactive device for a virtual image provided by an embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of an interactive device for a virtual image provided by an embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of a virtual image interaction device according to an embodiment of the present disclosure.

Detailed ways

In order to more clearly understand the above objects, features and advantages of the embodiments of the present disclosure, the solutions of the embodiments of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments may be combined with each other under the condition of no conflict.

Many specific details are set forth in the following description to facilitate a full understanding of the embodiments of the present disclosure, but the embodiments of the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the present disclosure examples, but not all examples.

With the continuous development of Internet technology, live webcasting emerges as the times require, providing users with a rich and colorful entertainment life. Users can enter the virtual live room to watch and interact. For example, the user can enter the virtual live room in the singing room scene to sing. However, the virtual live broadcast room in the song room scenario only activates the microphone or camera to complete the user's singing, and cannot realize the user's interaction in the virtual live broadcast room, which makes the virtual live broadcast room in the song room scene less playable.

Based on this, exemplary embodiments of the present disclosure provide an interactive method, device, device, computer storage medium, and computer program product for an avatar. By introducing an avatar into a virtual live room in a singing room scenario, A personalized avatar corresponding to the user is created, which deeply restores the onlineization of offline scenes. It makes the virtual live broadcast room in the singing room scene more realistic, which satisfies the user's interactive psychology in expressing himself in the virtual world, and increases the interactive playability of the virtual live broadcast room through vivid appearance, expressions, body movements, etc. for the purpose of user stickiness.

Wherein, the interaction method of the virtual image in the embodiment of the present disclosure is performed by an electronic device or a live broadcast application (Application, APP), a webpage, and an official account in the electronic device. Electronic devices can be tablet computers, mobile phones (such as folding screen mobile phones, large-screen mobile phones, etc.), wearable devices, in-vehicle devices, augmented reality (AR)/virtual reality (VR) devices, laptops, super Mobile personal computer (ultra-mobile personal computer, UMPC), netbook, personal digital assistant (personal digital assistant, PDA), smart TV, smart screen, high-definition TV, 4K TV, smart speaker, smart projector and other equipment, the implementation of the present disclosure The example does not impose any restrictions on the specific type of electronic equipment.

Wherein, the embodiment of the present disclosure does not limit the type of the operating system of the electronic device. For example, Android system, Linux system, Windows system, iOS system, etc.

Based on the foregoing description, the embodiment of the present disclosure will take a live broadcast APP in an electronic device as an example, and in conjunction with the accompanying drawings and application scenarios, to describe in detail the method for interacting with an avatar provided by the embodiment of the present disclosure.

With reference to FIGS. 1A-1Z , a specific implementation process of the method for interacting with a virtual image according to an embodiment of the present disclosure is introduced. 1A-1Z, the electronic device is a mobile phone, the live APP installed in the mobile phone is a short video social APP 1 (referred to as application 1), and the user who uses the mobile phone is user 1 as an example for illustration.

Please refer to FIG. 1A-FIG. 1Z. FIGS. 1A-1Z are schematic diagrams of a human-computer interaction interface provided by an embodiment of the present disclosure.

1. User 1 enters a virtual live room 1 in a singing room scene

The application 1 can display the user interface 10 exemplarily shown in FIG. 1A on the mobile phone. The user interface 10 is used to display the virtual live room 1 of the application 1 , so that the user 1 can sing songs in the virtual live room 1 .

It should be noted that the user 1 may be the host of the virtual live room 1, or may be another user except the host, which is not limited in this embodiment of the present disclosure. The host mentioned in the embodiment of the present disclosure is the user who creates the virtual live room 1 in the application 1 .

For convenience of description, the embodiment of the present disclosure takes User 1 as another user other than the host as an example for illustration.

The user interface 10 may include: area 101 , area 102 , area 103 , area 104 , public screen 105 and area 106 .

The area 101 is used to display the account of the host of the virtual live room 1, the profile picture of the host's account, the total number of likes, and status information such as the account of the user entering the virtual live room 1, and the account picture of the user. In addition, the area 101 is also used to enter other virtual live broadcast rooms and display notification information of other virtual live broadcast rooms.

The area 102 is used to display the displayed image of the user, the user's account number, the number of gifts received by the user, the lyrics of the song sung by the user, and the like during the process of the user singing a song. The area 102 may display the display image of the corresponding user based on different singing modes. In the voice singing mode, the area 102 may display the user's account avatar. In the singing mode of the video, the area 102 can display the real-time captured user image in the video. In the avatar's singing mode, the area 102 may display the user's avatar.

The area 103 is used to display the song singing queue of the virtual live room 1, such as the host's account avatar, the account avatars of other users, and the corresponding singing states such as singing, ready, mute, etc. Among them, the users who enter the virtual live room 1 mentioned in the embodiments of the present disclosure are not waiting for the users in the song singing queue. Users who enter the virtual live room 1 may not join the song singing queue, but may also join the song singing queue. The users in the song singing queue need to enter the virtual live broadcast room 1 .

The area 104 is used to display animation special effects such as entering the venue and giving gifts. Additionally, the area 104 and the common screen 105 may not overlap or partially overlap.

The public screen 105 is used to scroll and display various types of messages, such as comment messages, entry notification messages, share notification messages, gift notification messages, like notification messages, follow notification messages, and the like.

The area 106 is used to provide user 1 with an entry for inputting comment information, sharing, liking, giving gifts, following, etc. For example, area 106 may include an input box and a number of controls.

2. User 1 joins the song singing queue

In FIG. 1A , the area 103 may include one or more controls (eg, control 1031 ), each of which is used to join the song singing queue, that is, other users can apply for a connection to the host in order to join the song singing queue . After the user joins the song singing queue, each control is also used to display the account avatar of the user in the song singing queue. In general, the first position of the area 103 can be fixed by default with a control for displaying the host's account avatar, and by default the host has joined the song singing queue. In addition, the area 103 can display multiple controls by sliding up and down or left and right, so as to completely display the account avatars of all users in the song singing queue.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1031 in the area 103 shown in FIG. 1A , the application 1 can display the account avatar of the user 1 exemplarily shown in FIG. 1B on the control 1031 .

In addition, the application 1 can also display the control 201 exemplarily shown in FIG. 1B in the user interface 10 . The control 201 is used to notify the user 1 that the connection is successful, which means that the user 1 has joined the song singing queue.

3. User 1 orders songs after joining the song singing queue

In FIG. 1B , the user interface 10 may further include: a control 300 , where the control 300 is used to provide an entrance to order songs and display the number of songs that all users in the song singing queue have ordered.

After the application 1 receives that the user 1 performs an operation such as clicking the control 300 in the user interface 10 shown in FIG. 1B , the application 1 can display the window 107 exemplarily shown in FIG. 1C on the user interface 10, and the window 107 is used to provide Songs that can be sung, such as the display of related information such as the song name, the account number of the singer who sang the song, the duration of the song, and the cover of the song. In addition, the window 107 is also used to display the number of songs that have been clicked by all users in the song singing queue and to provide an entry for searching songs.

The window 107 may include: a control 1071 and a control 1072, the control 1071 is used to provide an entry to select (ie use) the song of the song title 4, and the control 1072 is used to display the number of songs that have been clicked by all users in the song singing queue.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1071 in the window 107 shown in FIG. 1C , the application 1 can display the control 1071 and the control 1072 after the state change exemplarily shown in FIG. 1D on the window 107 , The state-changed control 1071 is used to display that the song of song name 4 has been selected by user 1, and the state-changed control 1072 is used for the number of songs currently selected by all users in the song singing queue, that is, from number 1 to number 2 .

After the application 1 receives that the user 1 performs an operation such as exiting the window 107 in the user interface 10 shown in FIG. 1D , the application 1 can display the user interface 10 exemplarily shown in FIG. 1E on the mobile phone, and the controls in the user interface 10 300 is used to display the number of songs currently played by all users in the song singing queue.

In addition, the application 1 can also display the control 202 exemplarily shown in FIG. 1E in the user interface 10 , and the control 202 is used to notify the user that the song 1 is successfully connected and the ranking of the song.

It should be noted that, in addition to the above manner, after application 1 receives that user 1 performs an operation such as clicking on control 300 in user interface 10 shown in FIG. 1A , application 1 can display the window shown in FIG. 1C . After the application 1 receives that the user 1 performs an operation such as clicking the control 1071 in the window 107 shown in FIG. 1C , the application 1 may display the state-changed control 1071 and the control 1072 exemplarily shown in FIG. 1D on the window 107 . After the application 1 receives that the user 1 performs an operation such as exiting the window 107 in the user interface 10 shown in FIG. 1D , the application 1 can display the user interface 10 exemplarily shown in FIG. 1E on the mobile phone to realize adding to the song singing queue in the process of requesting a song.

To sum up, user 1 has joined the song singing queue and has ordered songs.

4. The avatar of user 1 configured in area 102 by user 1

After the application 1 receives that the user 1 performs an operation such as clicking the control 1031 in the area 103 shown in FIG. 1F , the application 1 can display the window 108 exemplarily shown in FIG. 1G on the mobile phone, and the window 108 is used to provide a configuration connection Status, such as disconnected, muted when connected, not muted when connected, singing mode when connected, etc.

The window 108 may include: a control 1081, and the control 1081 is used to configure the singing mode when connected.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1081 in the window 108 shown in FIG. 1G , the application 1 can display the window 109 exemplarily shown in FIG. 1H on the mobile phone, and the window 109 is used to provide various performances. mode, such as voice singing mode, video singing mode, avatar singing mode, etc.

The window 109 may include: a control 1091 and a control 1092. Control 1091 is used to configure the singing mode of the avatar. The control 1092 is used to set the exclusive avatar of the user 1 in the singing mode of the avatar.

It should be noted that when the application displays the window 109 again, the singing mode in the window 109 is the singing mode selected by the user when the application 1 opened the window 109 last time. If the singing mode is the singing mode of the avatar, the user's exclusive avatar in the singing mode of the avatar is the avatar set previously. In addition, when the application 1 opens the window 109 for the first time, the singing mode in the window 109 may be the singing mode of the voice by default. In addition, the window 109 may include: a determination control, where the determination control is used to determine the singing mode selected by the user 1 and the configured exclusive avatar.

To sum up, after user 1 completes the song ordering, application 1 can select the singing mode of user 1 based on the trigger operation on user 1's account avatar, so as to configure the display image of user 1 in area 102 .

After application 1 receives that user 1 performs an operation such as clicking on control 1091 in window 109 shown in FIG. 1H , application 1 may display control 1091 exemplarily shown in FIG. User 1 notifies that the singing mode of the avatar has been selected.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1092 in the window 109 shown in FIG. 1I, the application 1 can display the window 110 exemplarily shown in FIG. 1J on the window 109, and the window 110 is used to provide various Create a way to create an avatar of User 1.

In FIG. 1J , the window 110 may include: option 1101 , option 1102 and option 1103 . Option 1101 is used to create an avatar of User 1 through camera recognition. Option 1102 is used to create an avatar of User 1 through photo recognition. The above two options can identify the user's facial features, hair color, face shape and other parameters, so as to adjust parameters such as skin, hair quality, light perception and other parameters on the basis of the aforementioned parameters, so that the avatar of user 1 is more vivid and three-dimensional. Option 1103 is used to configure the avatar of the user 1 through a default image, which can be set with one image for each male and female, such as default parameters such as clothing, hairstyle, and face shape.

In addition, the window 110 is also used to cancel the singing mode of the avatar, so as to return to the window 109 to select the singing mode again or return to the user interface 10 to not continue to select the singing mode.

51. User 1 creates a virtual image of User 1 through camera recognition

After the application 1 receives that the user 1 performs an operation such as clicking the control 1101 in the window 110 shown in FIG. 1J , the application 1 can display the window 111 exemplarily shown in FIG. 1K on the mobile phone, and the window 111 is used to provide the camera identification creation Authorized entry for user 1's avatar.

In FIG. 1K , the window 111 may include: a control 1111 , and the control 1111 is used to select whether to agree to start the camera (ie, the camera).

After the application 1 receives that the user 1 performs an operation such as clicking the control 1111 in the window 111 shown in FIG. 1K , the application 1 can display the updated window 111 exemplarily shown in FIG. 1L on the mobile phone.

In FIG. 1L, the window 111 may include a control 1112, and the control 1111 is used to select whether to agree to the agreement for the camera to shoot the avatar.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1112 in the window 111 shown in FIG. 1L, the application 1 can display the window 112 exemplarily shown in FIG. 1M on the mobile phone, and the window 112 is used to show the real-time shooting of the camera to the captured photo of user 1.

It should be noted that, after application 1 receives for the first time that the user performs an operation such as clicking on the control 1101 in the window 110 shown in FIG. 1J , the application 1 can sequentially display the windows 111 exemplarily shown in FIGS. 1K and 1L on the mobile phone , the user 1 can choose to agree to start the camera and agree to the agreement of the camera to shoot the avatar in turn.

In addition, after user 1 has agreed to start the camera and agree to the agreement for the camera to shoot avatars, after application 1 again receives that user 1 performs an operation such as clicking the control 1101 in the window 110 shown in FIG. 1J , application 1 can no longer be displayed. The window 111 exemplarily shown in FIG. 1K and FIG. 1L can directly display the window 112 exemplarily shown in FIG. 1M .

In addition, the embodiment of the present disclosure does not limit the display order of the controls in the window 110 shown in FIG. 1K and FIG. 1L. Also, the controls shown in FIGS. 1K and 1L may be displayed in one window 110 at the same time.

After the application 1 obtains the photographed photo of the user 1 from the window 112, and in the process of recognizing the photographed photograph of the user 1, the application 1 may display the window 113 exemplarily shown in FIG. 1N on the mobile phone. The window 113 is used to preview and display the avatar of user 1 based on the photos taken by user 1, and to provide various driving modes of the avatar, so that the avatar of user 1 can simulate corresponding parts such as head and / or movements of limbs, etc.

In addition, the window 113 is also used to provide an entrance to reconfigure the avatar of User 1, such as returning to the window 110 shown in FIG. 1J to re-select to create the avatar of User 1, or returning to the window 115 shown in FIG. 1M Re-create the avatar of user 1 through camera recognition.

When the driving mode is the real-time driving mode, the action is the action of the user 1 captured by the camera in real time, so that the avatar of the user 1 can rhythm in real time with the action of the user 1 . In some embodiments, the avatar may rhythm with facial movements. When the driving mode is the default driving mode, the action is the default action, so that the avatar of the user 1 can rhythm with the default action. In some embodiments, the avatar may rhythm repeatedly with the default action interval for a preset duration. Wherein, the embodiment of the present disclosure does not limit the specific size of the preset duration.

The default action may be designed to perform actions based on the rhythm and/or pitch of the song clicked by user 1, so that the action is issued when the song is played to a corresponding pitch or a preset position (eg, an interlude prelude). In some embodiments, the default action may be a number of actions that are set according to the pitch of the song. In other embodiments, the default action can also be set as an action such as raising the microphone when the song performs an interlude. The default actions may include, but are not limited to, laughing, turning around, dancing, walking, and the like. As the application 1 creates the avatar of the user 1 based on the photographed photos of the user 1 , the application 1 may display the avatar of the user exemplarily shown in FIG. 10 in the window 113 . In addition, the application 1 may also display the control 203 exemplarily shown in FIG. 1M in the window 113, and the control 203 is used to notify the user 1 that the avatar is successfully created by means of camera recognition.

It should be noted that, in addition to the above methods, after application 1 obtains the photographed photo of user 1 from the window 112 and successfully identifies the photographed photograph of user 1, application 1 can display the example of FIG. 10 on the mobile phone The window 113 shown illustratively is not displayed, and the window 113 exemplarily shown in FIG. 1N is not displayed.

In FIG. 10 , the window 113 may include: a preview area 1131 and a control 1132 , and the preview area is used to preview the avatar of the user 1 created by the camera recognition. The control 1132 is used to provide a real-time driving mode or a default driving mode, that is, to select whether the avatar of the user 1 simulates the actions of the user 1 captured by the camera in real time when the user 1 sings a song. In addition, in addition to actions, the avatar of the user 1 can also simulate the appearance, expressions, etc. of the user 1 captured by the camera in real time. After the application 1 receives that the user 1 performs an operation such as clicking the control 1132 in the window 113 shown in FIG. 10 , the application 1 can display the updated control 1132 exemplarily shown in FIG. 1P on the window 113 . The updated control 1132 is used to indicate that the user 1 has selected the real-time driving mode, so that the avatar of the user 1 can simulate in real time the actions of the user 1 captured by the camera in real time during the process of the user 1 singing a song.

It should be noted that, if the user 1 does not perform an operation such as clicking the control 1132 in the window 113 shown in FIG. 10 , then the application 1 can determine that the user 1 has selected the default drive mode, so that the avatar of the user 1 sings in the user 1 The default action can be simulated during the song.

In FIG. 1P , the window 113 may further include: a control 1133 for determining whether to use the avatar of the user 1 in the preview area 1131 to simulate the action of the user 1 captured by the camera in real time in the area 102 .

After the application 1 receives that the user 1 performs an operation such as clicking the control 1133 in the window 113 shown in FIG. 1P , the application 1 can display the user interface 10 exemplarily shown in FIG. 1F on the mobile phone, so that the application 1 determines to use the preview area The avatar of the user 1 in 1131 simulates the actions of the user 1 captured by the camera in real time in the area 102 .

To sum up, the application 1 can create an avatar of the user 1 through camera recognition and activate the avatar of the user 1 to simulate actions corresponding to the driving mode in real time.

52. User 1 creates an avatar of User 1 through photo recognition

After the application 1 receives that the user 1 performs an operation such as clicking the control 1102 in the window 110 shown in FIG. 1J , the application 1 can display the window 114 exemplarily shown in FIG. way to create an authorized entry for the avatar of user 1.

In FIG. 1Q, the window 114 may include: a control 1141, and the control 1141 is used to select whether to agree to access the local storage space (eg photo album) of the mobile phone.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1141 in the window 114 shown in FIG. 1Q , the application 1 may display the updated window 114 exemplarily shown in FIG. 1R on the mobile phone.

In FIG. 1R, the window 114 may include a control 1142, and the control 1142 is used to select whether to agree to the protocol for creating an avatar by means of photo recognition.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1142 in the window 114 shown in FIG. 1R , the application 1 can display the window 115 exemplarily shown in FIG. 1S on the mobile phone, and the window 115 is used to display the storage in the album. Thumbnails of all photos of .

It should be noted that, after application 1 receives for the first time that the user performs an operation such as clicking on the control 1102 in the window 110 shown in FIG. 1J , the application 1 can sequentially display the windows 114 exemplarily shown in FIG. 1Q and FIG. 1R on the mobile phone , so that the user 1 can sequentially agree to access the album and agree to the agreement of creating a virtual image by means of photo identification.

And, after user 1 has agreed to start the photo album and agree to the agreement to create an avatar by means of photo recognition, after application 1 receives again that user 1 performs an operation such as clicking on the control 1102 in the window 110 shown in FIG. 1J , application 1 The window 114 exemplarily shown in FIGS. 1Q and 1R may no longer be displayed, and the window 115 exemplarily shown in FIG. 1S may be directly displayed.

In addition, the embodiment of the present disclosure does not limit the display order of the controls in the window 114 shown in FIG. 1Q and FIG. 1R . Also, the controls shown in FIGS. 1Q and 1R may be displayed in one window 114 at the same time.

In FIG. 1S, the window 115 may include: a control 1151, and the control 1151 is used to display a thumbnail of a photo stored in the album.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1151 in the window 115 shown in FIG. 1S , the application 1 can display the window 116 exemplarily shown in FIG. 1T on the mobile phone, and the window 116 is used to load the user 1 from A selected album photo1 in the album.

In FIG. 1T , the application 1 can determine whether the album photo 1 meets the conditions of being an avatar based on the identification specification. Wherein, the embodiments of the present disclosure do not limit the specific implementation manner of the identification specification.

When the album photo 1 does not meet the conditions for being an avatar, the application 1 may display prompt information to notify the user 1 to move the album photo 1 so that the album photo 1 meets the conditions for being an avatar.

After the album photo 1 meets the conditions for being an avatar, the application 1 can display the window 113 exemplarily shown in FIG. 10 on the mobile phone.

It should be noted that the function of the window 113 here is the same as the window 113 mentioned above, but the window 113 here is used to preview the avatar of the user 1 based on the album photo 1 and provide various driving modes of the avatar. In addition, the window 113 is also used to provide an entrance to reconfigure the avatar of the user 1, such as returning to the window 110 shown in FIG. 1J to re-select to create the avatar of the user 1, or returning to the window 115 shown in FIG. 1S Recreate the avatar of User 1 through photo recognition.

In addition, after the application 1 receives that the user 1 performs an operation such as clicking the control 1151 in the window 115 shown in FIG. 1S , the application 1 can also display the window 113 exemplarily shown in FIG. 1N on the mobile phone. Thus, the application 1 can judge whether the album photo 1 meets the conditions of being an avatar based on the identification specification. The foregoing judgment process may refer to the foregoing description, which will not be repeated here.

In addition, the application 1 can also display the control 203 exemplarily shown in FIG. 10 in the window 113, and the control 203 is used to notify the user 1 that the avatar is successfully created by means of photo recognition.

Correspondingly, in FIG. 10 , the window 113 may include: a preview area 1131 and a control 1132 , and the preview area is used to preview the avatar of the user 1 created by photo recognition. For the specific implementation of the control 1132, reference may be made to the description of the control 1132 mentioned above, which will not be repeated here.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1132 in the window 113 shown in FIG. 10 , the application 1 can display the updated control 1132 exemplarily shown in FIG. 1P on the window 113 . The updated control For the specific implementation of 1132, reference may be made to the description of the updated control 1132 mentioned above, which will not be repeated here.

In FIG. 1P , the window 113 may further include: a control 1133 . For the specific implementation of the control 1133 , reference may be made to the description of the control 1133 mentioned above, which will not be repeated here.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1133 in the window 113 shown in FIG. 1P , the application 1 can display the user interface 10 exemplarily shown in FIG. 1F on the mobile phone, so that the application 1 determines to use FIG. 10 The avatar of user 1 in the shown preview area 1131 simulates the actions of user 1 captured by the camera in real time in the area 102 .

To sum up, the application 1 can create an avatar of the user 1 through photo recognition and activate the avatar of the user 1 to simulate actions corresponding to the driving mode in real time.

53. User 1 configures the avatar of User 1 through the default image

After the application 1 receives that the user 1 performs an operation such as clicking the control 1103 in the window 110 shown in FIG. 1J , the application 1 can display the window 113 exemplarily shown in FIG. 1U on the mobile phone.

It should be noted that the function of the window 113 in FIG. 1U is the same as that of the window 113 in FIG. 10 , but the window 113 in FIG. 1U is used to preview and display the avatar of the user 1 based on the default avatar, and provide various drivers for the avatar. model. In addition, window 113 is also used to provide an entry to reconfigure User 1's avatar, such as by returning to window 110 shown in FIG. 1J to re-select to create User 1's avatar.

Correspondingly, in FIG. 1U , the window 113 may include: a preview area 1131 and a control 1132 , and the preview area is used to preview the avatar of the user 1 created by the default avatar. For the specific implementation of the control 1132, reference may be made to the description of the control 1132 in FIG. 10 , which will not be repeated here.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1132 in the window 113 shown in FIG. 1U , the application 1 can display the updated control 1132 exemplarily shown in FIG. 1V on the window 113 . The updated control For the specific implementation of 1132, reference may be made to the description of the updated control 1132 in FIG. 10, which will not be repeated here.

In FIG. 1V, the window 113 may further include: a control 1133. For the specific implementation of the control 1133, reference may be made to the description of the control 1133 in FIG. 1P, which will not be repeated here.

After the application 1 receives that the user 1 performs an operation such as clicking the control 1133 in the window 113 shown in FIG. 1V , the application 1 can display the user interface 10 exemplarily shown in FIG. 1F on the mobile phone, so that the application 1 determines to use the operation shown in FIG. 1U The avatar of user 1 in the shown preview area 1131 simulates the actions of user 1 captured by the camera in real time in the area 102 .

To sum up, the application 1 can configure the avatar of the user 1 through the default avatar and activate the avatar of the user 1 to simulate actions corresponding to the driving mode in real time.

It should be noted that, when the application 1 cannot create the avatar of the user 1 based on the photos taken by the user 1 or the photo album 1, the application 1 can use the default avatar as the avatar of the user 1 .

6. The avatar of User 1 in the process of User 1 singing a song

During the process of user 1 singing the song requested by user 1, application 1 may display the avatar of user 1 as exemplarily shown in FIG. 1W or FIG. 1X on area 102, and the avatar of user 1 is captured in real time with the camera. The rhythm of the user 1's actions, and the control 1031 in the area 103 can display that the singing state of the user 1 exemplarily shown in FIG. 1W or FIG. 1X is singing. The avatar of the user 1 in FIG. 1W is created based on camera or photo recognition, and the avatar of the user 1 in FIG. 1X is created based on the default avatar.

Wherein, taking FIG. 1W as an example, when user 1 starts to sing the song requested by user 1, application 1 can display control 204 exemplarily shown in FIG. 1Y on user interface 10, and control 204 is used to notify user 1 that the The camera is turned on, and the avatar of user 1 will rhythm with the movements of user 1 captured by the camera in real time, so as to meet user 1's needs for expressing himself, and improve user 1's interactive experience.

Wherein, taking FIG. 1W as an example, when the camera cannot detect the action of the user 1, the application 1 can display the control 205 exemplarily shown in FIG. 1Z on the user interface 10, and the control 205 is used to notify the user 1 of the action of the user 1. Leaving the recognition area of the camera, it is convenient for the user 1 to adjust the actions of the user 1 in time.

It should be noted that the user information such as the user's account avatar, album photos, captured photos, avatars, and user actions involved in Figures 1A-1Z are all obtained by the user's desired electronic device/live APP, and are obtained with the user's consent. of.

Based on the description of the embodiments of FIGS. 1A-1Z , and with reference to FIG. 2 , a specific implementation process of the virtual image interaction method provided by the embodiments of the present disclosure will be described in detail.

Please refer to FIG. 2 , which is a schematic flowchart of a method for interacting with an avatar according to an embodiment of the present disclosure. As shown in FIG. 2 , the interaction method of the avatar provided by the embodiment of the present disclosure may include:

S301. After the singing live broadcast is started in a virtual live broadcast room, in response to an instruction of a user in the virtual live broadcast room, configure the user's avatar and activate the target drive mode of the user's avatar.

After the singing live broadcast is started in a virtual live broadcast room, the live broadcast APP can receive an instruction from a user in the virtual live broadcast room.

The virtual live broadcast room is a virtual live broadcast room in a singing scene, such as a KTV virtual live broadcast room. A user in the virtual live broadcast room may be a host or other user in the virtual live broadcast room, which is not limited in this embodiment of the present disclosure.

Wherein, the instruction of the user is used to instruct to configure the avatar and the target driving mode of the avatar for the user. The embodiments of the present disclosure do not limit the specific implementation manner of the user's instruction. In some embodiments, the user's instruction may be implemented by operations such as clicking, double-clicking, long-pressing, sliding, and the like. For example, the user's instruction is for User 1 to execute in the window 113 shown in FIG. 1P or FIG. 1V as follows: Click the control 1133 operation.

After receiving the user's instruction, the live broadcast APP can configure the user's avatar and activate the target driving mode of the user's avatar.

The target driving mode is a driving manner for driving the rhythm of the avatar of the user, and is used to determine the target action simulated by the avatar of the user. The embodiments of the present disclosure do not limit the specific implementation manner of the target driving mode and the target action. In some embodiments, the target motion may be a motion of parts such as the head and/or limbs.

S302. During the process of the user singing in the virtual live broadcast room, display the avatar of the user who simulates the target action corresponding to the target driving mode to sing in the virtual live broadcast room.

As the user sings in the virtual live broadcast room, the live broadcast APP can control the user's avatar to rhythm by simulating the target action during the user's singing, and display the user's avatar simulating the target action in the virtual Sing in the live room. That is, the live broadcast APP shows that the user's avatar sings in the virtual live broadcast room. During this process, the user's avatar simulates the target action, and the target action corresponds to the target drive mode.

In the method for interacting with an avatar provided by the embodiments of the present disclosure, after a singing live broadcast is started in a virtual live broadcast room, in response to an instruction of a user in the virtual live broadcast room, the user's avatar can be configured and the user's avatar can be activated. target-driven mode. During the process of the user singing in the virtual live broadcast room, an avatar of the user simulating the target action corresponding to the target driving mode may be displayed to sing in the virtual live broadcast room. Therefore, the virtual image singing mode is added to the virtual live broadcast room in the singing room scene, which makes the virtual live broadcast room in the singing room scene more realistic, satisfies the user's interactive psychology in expressing themselves in the virtual world, and improves the virtual reality. The interactive playability of the live broadcast room is conducive to increasing the user traffic of the virtual live broadcast room in the singing room scenario.

Based on the descriptions of the above embodiments, the live APP can use various ways to configure the avatar of the user and activate the target driving mode of the avatar of the user.

In some embodiments, the live broadcast APP can take a photograph of the user through a camera, and based on the photograph taken by the user, the live broadcast APP can determine the avatar of the user. For the specific implementation process of the above steps, reference may be made to the description of the embodiments in FIG. 1J to FIG. 10 , which will not be repeated here. The live APP can determine the target driving mode. For the specific implementation process of the above steps, reference may be made to the descriptions of the embodiments in FIG. 10 to FIG. 1P , which will not be repeated here.

Therefore, after receiving the user's instruction, the live broadcast APP can configure the user's avatar and start the target driving mode. For the specific implementation process of the above steps, reference may be made to the description of the embodiment in FIG. 1P , which will not be repeated here.

In summary, the live broadcast APP can support the creation of personalized avatars through camera recognition to sing in the virtual live broadcast room, which is beneficial to deeply restore the offline singing scene of users through vivid appearance, expressions and body movements, so that users can interact with each other. more realistic.

In other embodiments, the live broadcast APP can obtain the user's album photos from the local storage space of the electronic device, and based on the user's album photos, the live broadcast APP can determine the user's avatar. For the specific implementation process of the above steps, reference may be made to the descriptions of the embodiments in FIGS. 1J , 1Q-1R, and 1N-1O, which will not be repeated here. The live APP can determine the target driving mode. For the specific implementation process of the above steps, reference may be made to the descriptions of the embodiments in FIG. 10 to FIG. 1P , which will not be repeated here.

To sum up, the live broadcast APP can support the creation of personalized avatars through photo recognition to sing in the virtual live broadcast room, which is beneficial to deeply restore the offline singing scene of users through vivid appearance, expressions and body movements, so that users can interact with each other. more realistic.

In other embodiments, the live broadcast APP may determine the user's avatar based on a default avatar. For the specific implementation process of the above steps, reference may be made to the descriptions of the embodiments in FIG. 1J and FIG. 1U , which will not be repeated here. The live APP can determine the target driving mode. For the specific implementation process of the above steps, reference may be made to the description of the embodiments in FIG. 1U-FIG. 1V, which will not be repeated here.

Therefore, after receiving the user's instruction, the live broadcast APP can configure the user's avatar and start the target driving mode. For the specific implementation process of the above steps, reference may be made to the description of the embodiment in FIG. 1V , which will not be repeated here.

In summary, the live broadcast APP can support the creation of personalized avatars by default images to sing in the virtual live broadcast room, which is conducive to the delivery of the default actions of the avatars through parameters such as the pitch and/or position of the songs sung by the user. , which lowers the operating threshold of virtual images, making user interaction more realistic.

It should be noted that the steps of determining the avatar of the user and the steps of determining the target driving mode may not be sequenced, and the two steps may be performed sequentially or simultaneously, which is not limited in this embodiment of the present disclosure.

In addition, in the case that the user's avatar cannot be determined based on the user's photographed photos or the user's album photos, the live broadcast APP can determine the default image as the user's avatar.

Based on the descriptions of the above embodiments, the live broadcast APP can provide various driving modes.

In some embodiments, when the target driving mode is the real-time driving mode, the live broadcast APP can collect the user's head movement in real time through the camera, and determine the user's head movement as the target movement.

Therefore, the live broadcast APP can display the avatar of the user who simulates the user's head movements in real time and sing in the virtual live broadcast room. That is, the live broadcast APP displays the user's avatar singing in the virtual live broadcast room, and the user's avatar simulates the user's head movements in real time during the process.

For the specific implementation process of the above steps, reference may be made to the description of the embodiment in FIG. 1W or FIG. 1X , which will not be repeated here.

In summary, during the process of the user's avatar singing in the virtual live broadcast room, the user's avatar can rhythm in real time with the user's head movements captured by the camera in real time, which deeply restores the user's offline singing scene. Improve the interactive playability of the virtual live room.

In addition, when the user starts singing in the virtual live broadcast room, the live broadcast APP can display the first prompt information in the virtual live broadcast room, and the first prompt information is used to prompt the user's avatar to simulate the user's head movement captured by the camera in real time in real time. , so that users can express themselves in time, which is conducive to improving user interaction.

Wherein, the embodiment of the present disclosure does not limit the specific implementation manner of the first prompt information. In some embodiments, the embodiments of the present disclosure may display the first prompt information by means of text information or the like, such as the control 204 in FIG. 1Y . In addition, for the specific implementation process of the above steps, reference may be made to the description of the embodiment in FIG. 1Y , which will not be repeated here.

In addition, after the user's head leaves the recognition area of the camera, the live broadcast APP can display second prompt information in the virtual live broadcast room, and the second prompt information is used to prompt the user to adjust the user's head, so that the user can timely The head is adjusted to the recognition area of the camera, which is conducive to improving user interaction.

Wherein, the embodiment of the present disclosure does not limit the specific implementation manner of the second prompt information. In some embodiments, the embodiments of the present disclosure may display the second prompt information by means of text information or the like, such as the control 205 in FIG. 1Z . In addition, the live broadcast APP may display the identification area of the camera on the page of the virtual live broadcast room, and the embodiment of the present disclosure does not limit the specific implementation of the identification area of the camera. In addition, for the specific implementation process of the above steps, reference may be made to the description of the embodiment in FIG. 1Z, which will not be repeated here.

In other embodiments, when the target driving mode is the default driving mode, the live APP may determine the default action based on the rhythm and/or pitch of the song sung by the user. The live APP can determine the default action as the target action.

Therefore, the live broadcast APP can display the avatar of the user who simulates the default action to sing in the virtual live broadcast room. That is, the live broadcast APP displays that the user's avatar sings in the virtual live broadcast room, and the user's avatar simulates a default action in the process.

The specific implementation process of the above steps may refer to the description of the embodiment in FIG. 1X , and the specific implementation of the default action may refer to the foregoing description, which will not be repeated here.

To sum up, during the process of the user's avatar singing in the virtual live broadcast room, the user's avatar can rhythm with the default action in real time, which reduces the threshold for avatar operation and improves the interactive playability of the virtual live broadcast room. .

Exemplarily, an embodiment of the present disclosure provides an interactive device for a virtual image.

Please refer to FIG. 3 , which is a schematic structural diagram of an interactive device for virtual images provided by an embodiment of the present disclosure. The avatar interaction apparatus according to the embodiment of the present disclosure can be set in an electronic device, and the avatar interaction method in the above-mentioned embodiments of FIGS. 1A-1Z and FIG.

As shown in FIG. 3 , the virtual image interaction device 100 provided by the embodiment of the present disclosure may include: a configuration module 401 and a display module 402 .

The configuration module 401 is used to configure the avatar of the user and start the target drive mode of the avatar of the user in response to an instruction of a user in the virtual live broadcast room after the singing live broadcast is opened in a virtual live broadcast room;

The display module 402 is configured to display the avatar of the user who simulates the target action corresponding to the target driving mode to sing in the virtual live broadcast room.

Please refer to FIG. 4 . FIG. 4 is a schematic structural diagram of an interactive device for virtual images according to an embodiment of the present disclosure. As shown in FIG. 4 , on the basis of the device structure shown in FIG. 3 , the virtual image interaction device 100 provided by the embodiment of the present disclosure may further include: a first acquisition module 403 and a first determination module 404 .

The first obtaining module 403 is used for taking a photograph of the user through a camera;

a first determining module 404, configured to determine the avatar of the user based on the photograph taken by the user;

The first determining module 404 is further configured to determine the target driving mode.

Please refer to FIG. 5 . FIG. 5 is a schematic structural diagram of a virtual image interaction device according to an embodiment of the present disclosure. As shown in FIG. 5 , on the basis of the device structure shown in FIG. 3 , the virtual image interaction device 100 provided by the embodiment of the present disclosure may further include: a second acquisition module 405 and a second determination module 406 .

The second obtaining module 405 is used to obtain the user's album photos from the local storage space;

The second determination module 406 is used to determine the avatar of the user based on the photo album of the user;

The second determining module 406 is further configured to determine the target driving mode.

Please refer to FIG. 6 . FIG. 6 is a schematic structural diagram of an interactive device for virtual images according to an embodiment of the present disclosure. As shown in FIG. 6 , on the basis of the device structure shown in FIG. 3 , the virtual image interaction device 100 provided by the embodiment of the present disclosure may further include: a third determination module 407 .

A third determining module 407, configured to determine the avatar of the user based on a default image;

The third determining module 407 is further configured to determine the target driving mode.

In some embodiments, when the target driving mode is the real-time driving mode, the display module 402 is specifically configured to collect the user's head movement in real time through the camera; determine the user's head movement as the target movement; display the real-time simulated user head The avatar of the moving user sings in the virtual live room.

In some embodiments, the display module 402 is further configured to display first prompt information in the virtual live broadcast room when the user starts singing in the virtual live broadcast room, where the first prompt information is used to prompt the user's avatar to simulate the real-time camera in real time The collected head movements of the user.

In some embodiments, the display module 402 is further configured to display second prompt information in the virtual live room after the user's head leaves the recognition area of the camera, where the second prompt information is used to prompt the user to adjust the user's head.

In some embodiments, when the target drive mode is the default drive mode, the display module 402 is specifically configured to determine a default action based on the rhythm and/or pitch of the song sung by the user; determine the default action as the target action; display the simulated default action The avatar of the moving user sings in the virtual live room.

The virtual image interaction device provided by the embodiments of the present disclosure can execute the above-mentioned method embodiments, and the specific implementation principles and technical effects thereof may refer to the above-mentioned method embodiments, which will not be repeated here.

Exemplarily, embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a memory; and one or more computer programs; wherein the one or more computer programs are stored in the memory; one or more When the processor executes one or more computer programs, the electronic device implements the avatar interaction method of the foregoing embodiments.

Exemplarily, an embodiment of the present disclosure provides a chip system, which is applied to an electronic device including a memory and a sensor; the chip system includes: a processor; when the processor executes the avatar interaction method of the foregoing embodiments.

Exemplarily, an embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to cause an electronic device to implement the avatar interaction method of the foregoing embodiments.

Exemplarily, the embodiments of the present disclosure provide a computer program product, which, when the computer program product runs on a computer, causes the computer to execute the avatar interaction method of the foregoing embodiments.

In the above embodiments, all or part of the functions may be implemented by software, hardware, or a combination of software and hardware. When implemented in software, it can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the procedures or functions according to the embodiments of the present disclosure result in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device. Computer instructions may be stored in a computer-readable storage medium. A computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that includes an integration of one or more available media. Useful media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state disks (SSDs)), and the like.

It should be noted that, in this document, relational terms such as "first" and "second" etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these There is no such actual relationship or sequence between entities or operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

The above descriptions are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

A virtual image interaction method, the method includes:

After the singing live broadcast is started in a virtual live broadcast room, in response to an instruction of a user in the virtual live broadcast room, configure the avatar of the user and start the target drive mode of the avatar of the user;

During the process of the user singing in the virtual live broadcast room, the avatar of the user simulating the target action corresponding to the target driving mode is displayed to sing in the virtual live broadcast room.
The method of claim 1, wherein the method further comprises:

Taking a photograph of the user through a camera;

determining the avatar of the user based on the photograph taken by the user;

The target drive mode is determined.
The method of claim 1, wherein the method further comprises:

Obtain the user's album photos from the local storage space;

determining an avatar of the user based on the user's photo album;

The target drive mode is determined.
The method of claim 1, wherein the method further comprises:

determining an avatar of the user based on a default avatar;

The target drive mode is determined.
The method according to any one of claims 1-4, wherein, when the target driving mode is a real-time driving mode, the avatar of the user displaying the target action corresponding to the target driving mode is displayed at Singing in the virtual live room includes:

Real-time capture of the head movement of the user through a camera;

determining the head action of the user as the target action;

Displaying the avatar of the user who simulates the head movement of the user in real time and sings in the virtual live broadcast room.
The method of claim 5, wherein the method further comprises:

When the user starts singing in the virtual live broadcast room, first prompt information is displayed in the virtual live broadcast room, and the first prompt information is used to prompt the user's avatar to simulate the real-time capture of the camera. the head movement of the user.
The method of claim 6, wherein the method further comprises:

After the user's head leaves the recognition area of the camera, second prompt information is displayed in the virtual live room, where the second prompt information is used to prompt the user to adjust the user's head.
The method according to any one of claims 1-4, wherein, when the target driving mode is a default driving mode, the avatar of the user displaying the target action corresponding to the target driving mode is displayed in Singing in the virtual live room includes:

determining a default action based on the tempo and/or pitch of the song sung by the user;

determining the default action as the target action;

The avatar of the user simulating the default action is displayed to sing in the virtual live room.
A virtual image interactive device, the device includes:

A configuration module, configured to configure the user's avatar and start the target drive mode of the user's avatar in response to an instruction of a user in the virtual live broadcast room after the singing live broadcast is turned on in a virtual live broadcast room;

The display module is configured to display the avatar of the user who simulates the target action corresponding to the target driving mode to sing in the virtual live broadcast room.
An electronic device comprising: one or more processors; a memory; and one or more computer programs; wherein the one or more computer programs are stored in the memory; characterized in that the one or more computer programs When the processor executes the one or more computer programs, the electronic device implements the method for interacting with the avatar according to any one of claims 1-8.
A computer storage medium, comprising computer instructions, when the computer instructions are executed on an electronic device, the electronic device causes the electronic device to execute the avatar interaction method according to any one of claims 1-8.
A computer program product, when the computer program product runs on a computer, causes the computer to execute the method for interacting with an avatar according to any one of claims 1-8.