Video-based interaction method, apparatus and device, and storage medium

Abstract

The present disclosure provides a video-based interaction method, apparatus and device, and a storage medium. The method comprises: firstly, displaying a preset portrait generation entrance on a playback page of a first target video, wherein the first target video is used for displaying a first artificial intelligence (AI) effect portrait; and then in response to a trigger operation for the preset portrait generation entrance, displaying a portrait generation page; and in response to a portrait generation operation triggered on the portrait generation page for a target image material and a target AI effect resource, obtaining a second AI effect portrait on the basis of the target image material and the target AI effect resource, wherein the second AI effect portrait is used for setting a user portrait. Therefore, according to the embodiments of the present disclosure, the generation of AI effect portraits is triggered on the basis of a preset portrait generation entrance displayed on a video playback page, so that the video-related interaction function is enriched, and the user experience is improved.

Description

Video-based interactive method, device, equipment, and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese invention patent application with application number 202311415712.5, entitled “A video-based interactive method, device, equipment and storage medium” and filing date October 27, 2023, and the entire application is incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of data processing, and in particular to a video-based interaction method, apparatus, device, and storage medium. Background Art

[0004] With the continuous development of computer technology, video-related interactive functions emerge in an endless stream, and users' demands for video-related interactive functions are becoming more and more diverse.

[0005] In order to meet users' growing demand for diversified video-related interactive functions, how to enrich video-related interactive functions is a technical problem that needs to be solved urgently.

[0006] Summary of the Invention

[0007] In order to solve the above technical problems, the embodiments of the present disclosure provide a video-based interaction method.

[0008] In a first aspect, the present disclosure provides a video-based interaction method, the method comprising:

[0009] Displaying a preset avatar generation entrance on the playback page of a first target video; wherein the first target video is used to display a first artificial intelligence AI effect avatar;

[0010] In response to a triggering operation on the preset avatar generation entrance, displaying an avatar generation page;

[0011] In response to an avatar generation operation triggered by a target image material and a target AI effect resource on the avatar generation page, a second AI effect avatar is obtained based on the target image material and the target AI effect resource; wherein the second AI effect avatar is used to set a user avatar.

[0012] In an optional implementation, an avatar setting control is provided on the avatar generation page, and the method further includes:

[0013] In response to a triggering operation on the avatar setting control on the avatar generation page, the second AI effect avatar is set as the user avatar of the target user.

[0014] In an optional embodiment, a material upload control is provided on the avatar generation page, and after the avatar generation page is displayed in response to a triggering operation on the preset avatar generation entrance, the method further includes:

[0015] In response to a triggering operation on the material upload control on the avatar generation page, displaying a user material page;

[0016] In response to a selection operation on any image material on the user material page, the image material is determined as a target image material.

[0017] In an optional implementation, a video generation control is provided on the avatar generation page, and the method further includes:

[0018] In response to a triggering operation on the video generation control on the avatar generation page, a second target video is generated based on the second AI effect avatar; wherein the second target video is used to display the second AI effect avatar.

[0019] In an optional embodiment, in response to the avatar generation operation triggered for the target image material and the target AI effect resource on the avatar generation page, obtaining a second AI effect avatar based on the target image material and the target AI effect resource includes:

[0020] In response to the avatar generation operation triggered by the target image material and the target AI effect resource on the avatar generation page, the target image material is switched and displayed as a second AI effect avatar according to a preset switching effect; wherein, the second AI effect avatar is obtained based on the target image material and the target AI effect resource.

[0021] In an optional implementation, the first target video is a gyroscope video, the first target video includes multiple layers, and the multiple layers include the layer where the first AI effect avatar is located. The method further includes:

[0022] Obtaining a deflection angle corresponding to the playback page of the first target video;

[0023] According to the deflection angle, the first AI effect avatar in the first target video is controlled to be offset within the offset range corresponding to the layer in which it is located.

[0024] In an optional implementation, the method further includes:

[0025] The target page is displayed; wherein, the target page displays the current user avatar of the target user, and AI effect prompt information is displayed on the current user avatar, and the AI ​​effect prompt information is used to prompt the generation of the AI ​​effect avatar.

[0026] In an optional implementation, the method further includes:

[0027] In response to an AI effect avatar generation trigger operation acting on the target page, a third AI effect avatar is obtained based on the current user avatar of the target user; wherein, the third AI effect avatar is used to trigger the setting of the user avatar of the target user.

[0028] In a second aspect, the present disclosure provides a video-based interactive device, the device comprising:

[0029] A first display module is configured to display a preset avatar generation entry on a playback page of a first target video; wherein the first target video is configured to display a first artificial intelligence (AI) effect avatar;

[0030] a second display module, configured to display an avatar generation page in response to a triggering operation on the preset avatar generation entrance;

[0031] The first acquisition module is used to respond to the avatar generation operation triggered by the target image material and the target AI effect resource on the avatar generation page, and obtain a second AI effect avatar based on the target image material and the target AI effect resource; wherein, the second AI effect avatar is used to set the user avatar.

[0032] In a third aspect, the present disclosure provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium. When the instructions are executed on a terminal device, the terminal device implements the above method.

[0033] In a fourth aspect, the present disclosure provides a video-based interactive device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method when executing the computer program.

[0034] In a fifth aspect, the present disclosure provides a computer program product, which includes a computer program / instructions, and the computer program / instructions implement the above method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0036] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0037] FIG1 is a flow chart of a video-based interaction method provided by an embodiment of the present disclosure;

[0038] FIG2 is a schematic diagram of a playback page of a first target video provided by an embodiment of the present disclosure;

[0039] FIG3 is a schematic diagram of an avatar generation page provided by an embodiment of the present disclosure;

[0040] FIG4 is a schematic diagram of another avatar generation page provided by an embodiment of the present disclosure;

[0041] FIG5 is a schematic diagram of another avatar generation page provided by an embodiment of the present disclosure;

[0042] FIG6 is a schematic diagram of another avatar generation page provided by an embodiment of the present disclosure;

[0043] FIG7 is a schematic diagram of another avatar generation page provided by an embodiment of the present disclosure;

[0044] FIG8 is a schematic diagram of a user's personal homepage provided by an embodiment of the present disclosure;

[0045] FIG9 is a schematic structural diagram of a video-based interactive device provided in an embodiment of the present disclosure;

[0046] FIG10 is a schematic structural diagram of a video-based interactive device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0049] With the continuous development of computer technology, video-related interactive functions emerge in an endless stream, and users' demands for video-related interactive functions are becoming more and more diverse.

[0050] In order to meet users' growing demand for diversified video-related interactive functions, how to enrich video-related interactive functions is a technical problem that needs to be solved urgently.

[0051] To this end, the embodiment of the present disclosure provides a video-based interaction method, first, a preset avatar generation entrance is displayed on the playback page of the first target video, wherein the first target video is used to display a first artificial intelligence AI effect avatar, and in response to a trigger operation on the preset avatar generation entrance, an avatar generation page is displayed, and in response to an avatar generation operation triggered on the avatar generation page for the target image material and the target AI effect resource, a second AI effect avatar is obtained based on the target image material and the target AI effect resource, wherein the second AI effect avatar is used to set the user avatar. It can be seen that the embodiment of the present disclosure can support the generation of AI effect avatars based on the preset avatar generation entrance displayed on the video playback page, enriching the video-related interactive functions and improving the user experience.

[0052] Based on this, an embodiment of the present disclosure provides a video-based interaction method. Referring to FIG1 , which is a flow chart of a video-based interaction method provided by an embodiment of the present disclosure, the method specifically includes:

[0053] S101: Displaying a preset avatar generation entrance on the playback page of the first target video.

[0054] Among them, the first target video is used to display the first artificial intelligence AI effect avatar.

[0055] The video-based interaction method provided by the embodiments of the present disclosure can be applied to a client, for example, a client deployed on a mobile terminal such as a smart phone, a client deployed on a personal computer (PC), etc.

[0056] In the embodiment of the present disclosure, the first target video displays a first artificial intelligence AI effect avatar, that is, the first target video is a video related to the first artificial intelligence AI effect avatar, and specifically can be a video created and published by a video creation user that includes the first artificial intelligence AI effect avatar.

[0057] The playback page of the first target video can be used to play the first target video based on the media information stream, and supports the function of switching the playback video based on the media information stream, wherein the media information stream can include a recommended video stream, etc.

[0058] Among them, a preset avatar generation entrance is displayed on the playback page of the first target video, and by triggering the preset avatar generation entrance, the relevant page for displaying AI effect avatar generation can be triggered.

[0059] In the embodiment of the present disclosure, the first artificial intelligence AI effect avatar refers to an avatar with AI effects, for example, an avatar generated based on any one or more AI effect resources.

[0060] In the disclosed embodiment, a preset avatar generation entry is displayed on the playback page of the first target video. The preset avatar generation entry can be displayed in any area on the playback page of the first target video, and the disclosed embodiment does not impose any restrictions on this. The preset avatar generation entry can be displayed in the form of an anchor point on the playback page, a preset control, or other forms, and the disclosed embodiment does not impose any restrictions on this.

[0061] As shown in Figure 2, a schematic diagram of a playback page of a first target video provided in an embodiment of the present disclosure is provided, wherein the playback page is displaying the first target video, wherein the first target video can be in a playback state or a paused playback state, etc. The first target video is a video associated with a first artificial intelligence (AI) effect avatar, that is, the first target video displays the first AI effect avatar. In addition, a preset avatar generation entry 201 is displayed on the playback page of the first target video.

[0062] S102: In response to a triggering operation on the preset avatar generation entrance, displaying an avatar generation page.

[0063] Among them, the triggering operation for the preset avatar generation entrance may include interactive operations such as single-click operation, double-click operation, long press operation, etc. triggered for the preset avatar generation entrance on the playback page of the first target video, which is used to trigger the display to switch from the playback page of the first target video to the avatar generation page.

[0064] In an embodiment of the present disclosure, after the playback page of the first target video is switched to the avatar generation page, the target image material and the target AI effect resource are determined based on the avatar generation page.

[0065] In actual applications, the target image material used to generate the second AI effect avatar is a user material authorized by the user, that is, under the premise of user authorization, the generation of the second AI effect avatar based on the target image material and the target AI effect resource can be triggered.

[0066] In an optional implementation, before displaying the avatar generation page, an authorization pop-up window may be displayed. After obtaining user authorization based on the authorization pop-up window, the avatar generation page is displayed, and subsequent avatar generation operations are triggered based on the avatar generation page.

[0067] S103: In response to an avatar generation operation triggered on the avatar generation page for a target image material and a target AI effect resource, a second AI effect avatar is obtained based on the target image material and the target AI effect resource.

[0068] Among them, the second AI effect avatar is used to set the user avatar.

[0069] In the embodiment of the present disclosure, the target image material may include a personal avatar set by the current user, picture materials in the current user's photo album, and picture materials taken by the current user based on a photo taking page.

[0070] The avatar generation page includes target image materials and AI effect resources, where the target AI effect resource can be any AI effect resource. Specifically, the target AI effect resource can be the first AI effect resource among the AI ​​effect resources. The target AI effect resource can also be determined based on the user's selected operation.

[0071] Here, the target AI effect resource is determined based on the user's selection operation, which means that the target AI effect resource can be switched based on the selection operation.

[0072] In an optional embodiment, when a trigger operation is received for a preset avatar generation entrance, the avatar generation page is displayed. When an upload operation for a target image material and a selection operation for a target AI effect resource are received on the avatar generation page, the execution progress information for the avatar generation operation is displayed on the avatar generation page.

[0073] For example, as shown in FIG3 , which is a schematic diagram of an avatar generation page provided in an embodiment of the present disclosure, the avatar generation page displays a selected AI effect resource, namely, a target AI effect resource 301, and execution progress information, as shown in 302. When the AI ​​avatar generation operation is triggered and completed, the avatar generation page displays the effect of switching from the target image material to the second AI effect avatar.

[0074] In actual applications, in order to show users the comparison of effects before and after avatar generation to further enhance user experience, in the embodiment of the present disclosure, the target image material is switched and displayed as a second AI effect avatar based on a preset switching effect, wherein the preset switching effect can be set based on demand.

[0075] Specifically, after the generation of the AI ​​avatar is completed based on the target image material and the target AI effect resources, the target image material can be switched to display the generated second AI effect avatar according to the preset switching effect, wherein the second AI effect avatar is generated based on the target image material and the target AI effect resources.

[0076] As shown in Figure 4, a schematic diagram of another avatar generation page provided in an embodiment of the present disclosure is shown. The avatar generation page displays the process of switching from a target image material to a second AI effect avatar, wherein the target image material 401, the second AI effect avatar 402, and the second AI effect avatar 402 replacing the target image material 401 until the complete second AI effect avatar is displayed.

[0077] In addition, the processing process of generating a second AI effect avatar based on the target image material and the target AI effect resource can be implemented on the client side or on the server side. The embodiments of the present disclosure do not impose any restrictions on this.

[0078] In an optional embodiment, when an avatar generation operation triggered by a target image material and a target AI effect resource is received on an avatar generation page, a process of generating a second AI effect avatar based on the target image material and the target AI effect resource can be implemented on the client, for example, by using an AI avatar generation module deployed on the client.

[0079] In another optional embodiment, when an avatar generation operation triggered by a target image material and a target AI effect resource on an avatar generation page is received, the client sends the target image material and the target AI effect resource to the target server, and the target server generates a second AI effect avatar based on the target image material and the target AI effect resource, and the client obtains the second AI effect avatar from the target server.

[0080] In actual applications, in order to support setting the generated AI effect avatar, that is, the second AI effect avatar, as the user avatar of the target user to meet user needs and improve user experience, in the embodiment of the present disclosure, an avatar setting control is set on the avatar generation page, and the avatar setting control can be used to trigger the second AI effect avatar to be set as the user avatar.

[0081] In an optional implementation, when a trigger operation for an avatar setting control on the avatar generation page is received, the second AI effect avatar displayed on the avatar generation page is set as the user avatar of the target user.

[0082] In addition, in order to remind the user that the avatar setting operation has been completed, a notification message of successful avatar setting can also be displayed on the avatar generation page to further enhance the user experience.

[0083] Based on the above embodiment, an avatar saving control can also be set on the avatar generation page, and the avatar saving control can trigger the saving of the second AI effect avatar.

[0084] For example, as shown in Figure 5, a schematic diagram of an avatar generation page provided in an embodiment of the present disclosure is shown. The avatar generation page displays a second AI effect avatar 501, an avatar setting control 502, and an avatar save control 503. When a trigger operation is received for the avatar setting control on the avatar generation page, the second AI effect avatar displayed on the avatar generation page is set as the user avatar of the target user, and an avatar setting success notification message 504 is displayed on the avatar generation page.

[0085] In the video-based interaction method provided by the embodiment of the present disclosure, first, a preset avatar generation entry is displayed on the playback page of the first target video, wherein the first target video is used to display a first artificial intelligence AI effect avatar, and in response to a trigger operation on the preset avatar generation entry, an avatar generation page is displayed, and in response to an avatar generation operation triggered on the avatar generation page for the target image material and the target AI effect resource, a second AI effect avatar is obtained based on the target image material and the target AI effect resource, wherein the second AI effect avatar is used to set the user avatar. It can be seen that the embodiment of the present disclosure can support the generation of an AI effect avatar based on the preset avatar generation entry displayed on the video playback page, thereby enriching the video-related interactive functions and improving the user experience.

[0086] In an optional implementation, the first target video may be a gyroscope video, and the first target video includes multiple layers, including the layer where the first AI effect avatar is located.

[0087] During the playback of the first target video, the deflection angle corresponding to the playback page of the first target video can be obtained through the gyroscope in the device, and then the first AI effect avatar in the first target video is controlled to offset within the offset range corresponding to the layer in which it is located according to the deflection angle.

[0088] If the device adjusts the display angle, the gyroscope in the device can detect the change in the deflection angle corresponding to the playback page of the first target video, and then control the first AI effect avatar in the first target video to shift within the offset range corresponding to the layer in which it is located according to the change in the deflection angle, giving the user a three-dimensional spatial video playback experience.

[0089] In actual applications, in order to support users to re-upload target image materials, in the embodiment of the present disclosure, when a trigger operation for a preset avatar generation entrance is received, after the avatar generation page is displayed, a material upload control can also be set on the avatar generation page, and the material upload control can be used to trigger the re-determination of the target image material.

[0090] Specifically, when a trigger operation is received for the material upload control on the avatar generation page, the user material page is displayed. When a selection operation is received for any image material on the user material page, the image material is determined as the target image material.

[0091] It should be noted that before the user triggers the avatar generation operation, the material upload control can be triggered to re-upload the target image material; after the user triggers the avatar generation operation, the material upload control can also be triggered to re-upload the target image material, and then trigger the re-generation of the AI ​​effect avatar operation based on the re-uploaded target image material.

[0092] As shown in FIG5 , the avatar generation page displays a material upload control 505. When a trigger operation is received on the material upload control 505, the user material page is displayed. When a selection operation is received for any image material on the user material page, the image material is determined as the target image material. The user material page is used to display all images in the user's album.

[0093] In actual applications, in order to avoid the situation where the target image material has not been uploaded or the target image material does not contain a portrait on the avatar generation page, the embodiment of the present disclosure will perform image recognition and other operations on the target image material before triggering the avatar generation operation, and display a notification message when the target image material has not been uploaded or the target image material does not contain a portrait. Among them, the image recognition module can be deployed based on demand for the image recognition operation, and the embodiment of the present disclosure does not impose any restrictions on this.

[0094] In one optional embodiment, after the avatar generation page is displayed, image recognition is performed on the target image material. If the recognition results include a result that no portrait is recognized, a notification message for uploading a portrait image is displayed on the avatar generation page. The target image material can be re-uploaded by triggering the material upload control on the avatar generation page. The notification message for uploading a portrait image is used to remind the user to re-upload the target image material.

[0095] As shown in FIG6 , a schematic diagram of an avatar generation page provided by an embodiment of the present disclosure is provided. When the target image material is recognized, if no portrait is recognized in the recognition result, a notification message for uploading a portrait picture is displayed on the avatar generation page, as shown in 601 .

[0096] In another optional implementation, when it is detected that the avatar generation page does not contain the target image material, a notification message for uploading the portrait picture is displayed on the avatar generation page.

[0097] As shown in FIG7 , an embodiment of the present disclosure provides a schematic diagram of an avatar generation page. When it is detected that the avatar generation page does not contain the target image material, a notification message 701 for uploading a portrait image is displayed on the avatar generation page.

[0098] Based on the above embodiment, a video generation control can also be set on the avatar generation page to support the generation of a second target video based on the generated second AI effect avatar, thereby further improving the user experience. In addition, a preview effect control can also be set on the avatar generation page to facilitate the user to preview and view the generated second target video.

[0099] Specifically, when a trigger operation is received for the video generation control on the avatar generation page, a second target video is generated based on the second AI effect avatar, wherein the second target video is used to display the second AI effect avatar.

[0100] In an optional embodiment, a second AI effect avatar is displayed on the avatar generation page. When a video generation control trigger operation is received, a second target video is generated based on the second AI effect avatar. When a preview effect control trigger operation is received, a preview page is displayed, and the second target video is displayed on the preview page. When a publishing control trigger operation is received for the first target video, the first target video is sent to the published works on the user's personal homepage.

[0101] In another optional implementation, the video generation control can be selected by default when the avatar generation operation is triggered. After the second AI effect avatar is generated, the user can trigger the preview effect control to display a preview page. The preview page displays the second target video generated based on the second AI effect avatar, as well as the publishing control. By triggering the publishing control, the current user is triggered to publish the second target video.

[0102] For example, the avatar generation page shown in Figure 5 above displays a video generation control 507 in a selected state and a preview effect control 508. When a trigger operation for the preview effect control is received, the preview page is displayed. Through the preview page, you can view the second target video generated based on the second AI effect avatar, and then trigger the current user to publish the second target video by triggering the publishing control on the preset page.

[0103] By setting the video generation control on the avatar generation page, the function of generating a second target video based on the second AI effect avatar is realized, enriching the video-related interactive functions.

[0104] In actual applications, in order to prompt the user to set the currently set personal avatar to an AI effect avatar, AI effect prompt information can also be displayed on the target page to prompt the triggering of the generation of the AI ​​effect avatar, wherein the target page contains the personal avatar set by the current user, and the personal avatar is in an editable state. For example, the target page can be the user's personal homepage or the profile editing page.

[0105] Specifically, a target page is displayed, wherein the target page displays the current user avatar of the target user, and AI effect prompt information is displayed on the current user avatar, and the AI ​​effect prompt information is used to prompt and trigger the generation of the AI ​​effect avatar.

[0106] When a trigger operation for generating an AI effect avatar acting on the target page is received, a third AI effect avatar is obtained based on the current user avatar of the target user, wherein the third AI effect avatar is used to trigger the setting of the user avatar of the target user.

[0107] Among them, AI effect prompt information can be set based on needs. Specifically, it can be an animation effect, such as an animation effect showing aperture.

[0108] In one optional embodiment, a user's personal homepage is displayed, which displays the target user's current user avatar and display effect prompt information. When a trigger operation is received for the user avatar on the target page, an avatar settings panel is pulled up on the user's personal homepage, and the avatar settings panel displays the AI ​​avatar settings control. When a trigger operation is received for setting an AI avatar on the avatar settings panel, an avatar generation page is displayed, and a third AI effect avatar is obtained based on the target user's current user avatar. The specific process of generating the third AI effect avatar can be referred to the above discussion.

[0109] As shown in Figure 8, a schematic diagram of a user personal homepage provided by an embodiment of the present disclosure is shown on the user personal homepage. The current user avatar 801 of the target user is displayed, as well as AI effect prompt information. When a trigger operation is received for the user avatar 801 on the target page, an avatar setting panel 802 is pulled up on the user personal homepage. The avatar setting panel displays a setting AI avatar control 803. When a trigger operation is received for the setting AI avatar control 803 on the avatar setting panel, an avatar generation page is displayed, and a third AI effect avatar is obtained based on the current user avatar of the target user. The third AI effect avatar is used to trigger the setting of the user avatar of the target user.

[0110] Based on the above method embodiment, the present disclosure further provides a video-based interaction device. Referring to FIG9 , which is a schematic structural diagram of a video-based interaction device provided in an embodiment of the present disclosure, the device includes:

[0111] The first display module 901 is used to display a preset avatar generation entrance on the playback page of a first target video; wherein the first target video is used to display a first artificial intelligence AI effect avatar;

[0112] A second display module 902 is configured to display an avatar generation page in response to a triggering operation on the preset avatar generation entry;

[0113] The first acquisition module 903 is used to obtain a second AI effect avatar based on the target image material and the target AI effect resource in response to the avatar generation operation triggered by the target image material and the target AI effect resource on the avatar generation page; wherein the second AI effect avatar is used to set the user avatar.

[0114] In an optional implementation, an avatar setting control is provided on the avatar generation page, and the device further includes:

[0115] A setting module is configured to set the second AI effect avatar as the user avatar of the target user in response to a triggering operation on the avatar setting control on the avatar generation page.

[0116] In an optional implementation, a material upload control is provided on the avatar generation page, and the device further includes:

[0117] a third display module, configured to display a user material page in response to a triggering operation on the material upload control on the avatar generation page;

[0118] The determining module is configured to determine any image material as a target image material in response to a selection operation on any image material on the user material page.

[0119] In an optional implementation, a video generation control is provided on the avatar generation page, and the device further includes:

[0120] The first generation module is used to generate a second target video based on the second AI effect avatar in response to a triggering operation on the video generation control on the avatar generation page; wherein the second target video is used to display the second AI effect avatar.

[0121] In an optional implementation manner, the first obtaining module is specifically configured to:

[0122] In response to the avatar generation operation triggered by the target image material and the target AI effect resource on the avatar generation page, the target image material is switched and displayed as a second AI effect avatar according to a preset switching effect; wherein, the second AI effect avatar is obtained based on the target image material and the target AI effect resource.

[0123] In an optional embodiment, the first target video is a gyroscope video, the first target video includes multiple layers, the multiple layers include the layer where the first AI effect avatar is located, and the device further includes:

[0124] An acquisition module, configured to acquire a deflection angle corresponding to the playback page of the first target video;

[0125] A control module is used to control the first AI effect avatar in the first target video to shift within an offset range corresponding to the layer in which it is located according to the deflection angle.

[0126] In an optional embodiment, the device further includes:

[0127] The fourth display module is used to display the target page; wherein, the target page displays the current user avatar of the target user, and the current user avatar is displayed with AI effect prompt information, and the AI ​​effect prompt information is used to prompt the generation of the AI ​​effect avatar.

[0128] In an optional embodiment, the device further includes:

[0129] The second acquisition module is used to respond to the AI ​​effect avatar generation trigger operation acting on the target page, and obtain a third AI effect avatar based on the current user avatar of the target user; wherein, the third AI effect avatar is used to trigger the setting of the user avatar of the target user.

[0130] In the video-based interactive device provided by the embodiment of the present disclosure, first, a preset avatar generation entry is displayed on the playback page of the first target video, wherein the first target video is used to display a first artificial intelligence AI effect avatar, and in response to a trigger operation on the preset avatar generation entry, an avatar generation page is displayed, and in response to an avatar generation operation triggered on the avatar generation page for the target image material and the target AI effect resource, a second AI effect avatar is obtained based on the target image material and the target AI effect resource, wherein the second AI effect avatar is used to set the user avatar. It can be seen that the embodiment of the present disclosure can support the generation of AI effect avatars based on the preset avatar generation entry displayed on the video playback page, enriching the video-related interactive functions and improving the user experience.

[0131] In addition to the above-mentioned methods and apparatus, the embodiments of the present disclosure further provide a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal device, the terminal device implements the video-based interaction method described in the embodiments of the present disclosure.

[0132] The embodiments of the present disclosure further provide a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the video-based interaction method described in the embodiments of the present disclosure is implemented.

[0133] In addition, the embodiment of the present disclosure further provides a video-based interactive device, as shown in FIG10 , which may include:

[0134] Processor 1001, memory 1002, input device 1003, and output device 1004. The number of processors 1001 in the video-based interactive device can be one or more, and Figure 10 uses one processor as an example. In some embodiments of the present disclosure, the processor 1001, memory 1002, input device 1003, and output device 1004 can be connected via a bus or other means, wherein Figure 10 uses a bus connection as an example.

[0135] The memory 1002 can be used to store software programs and modules. The processor 1001 executes various functional applications and data processing of the video-based interactive device by running the software programs and modules stored in the memory 1002. The memory 1002 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application required for a function, etc. In addition, the memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. The input device 1003 may be used to receive input digital or character information, and to generate signal input related to user settings and function control of the video-based interactive device.

[0136] Specifically in this embodiment, the processor 1001 will load the executable files corresponding to the processes of one or more applications into the memory 1002 according to the following instructions, and the processor 1001 will run the applications stored in the memory 1002, thereby realizing the various functions of the above-mentioned video-based interactive device.

[0137] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0138] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general 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 rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A video-based interactive method, comprising: Displaying a preset avatar generation entrance on the playback page of the first target video; wherein the first target video is used to display a first artificial intelligence AI effect avatar; In response to a triggering operation on the preset avatar generation entrance, displaying an avatar generation page; In response to an avatar generation operation triggered by a target image material and a target AI effect resource acting on the avatar generation page, a second AI effect avatar is obtained based on the target image material and the target AI effect resource; wherein the second AI effect avatar is used to set a user avatar.

2. The method according to claim 1, wherein: The avatar generation page is provided with an avatar setting control, and the method further comprises: In response to a triggering operation on the avatar setting control on the avatar generation page, the second AI effect avatar is set as a user avatar of the target user.

3. The method according to claim 1, wherein: The avatar generation page is provided with a material upload control, and after the avatar generation page is displayed in response to a trigger operation on the preset avatar generation entrance, the method further includes: In response to a triggering operation on the material upload control on the avatar generation page, displaying a user material page; In response to a selection operation on any image material on the user material page, the image material is determined as a target image material.

4. The method according to claim 1, wherein: A video generation control is provided on the avatar generation page, and the method further includes: In response to a trigger operation on the video generation control on the avatar generation page, a second target video is generated based on the second AI effect avatar; wherein the second target video is used to display the second AI effect avatar.

5. The method according to claim 1, wherein: The step of obtaining a second AI effect avatar based on the target image material and the target AI effect resource in response to the avatar generation operation triggered on the avatar generation page includes: In response to the avatar generation operation triggered by the target image material and the target AI effect resource on the avatar generation page, the target image material is switched and displayed as a second AI effect avatar according to a preset switching effect; wherein the second AI effect avatar is obtained based on the target image material and the target AI effect resource.

6. The method according to claim 1, wherein: The first target video is a gyroscope video, the first target video includes multiple layers, the multiple layers include the layer where the first AI effect avatar is located, and the method further includes: Obtaining a deflection angle corresponding to the playback page of the first target video; According to the deflection angle, the first AI effect avatar in the first target video is controlled to be offset within an offset range corresponding to the layer in which it is located.

7. The method according to claim 1, further comprising: The target page is displayed; wherein the target page displays the current user avatar of the target user, and AI effect prompt information is displayed on the current user avatar, and the AI ​​effect prompt information is used to prompt and trigger the generation of the AI ​​effect avatar.

8. The method according to claim 7, further comprising: In response to an AI effect avatar generation trigger operation acting on the target page, a third AI effect avatar is obtained based on the current user avatar of the target user; wherein the third AI effect avatar is used to trigger the setting of the user avatar of the target user.

9. A video-based interactive device, comprising: A first display module, used to display a preset avatar generation entrance on a playback page of a first target video; wherein the first target video is used to display a first artificial intelligence AI effect avatar; A second display module, configured to display an avatar generation page in response to a trigger operation on the preset avatar generation entry; The first obtaining module is used to respond to the target on the avatar generation page. The avatar generation operation is triggered by the target image material and the target AI effect resource, and a second AI effect avatar is obtained based on the target image material and the target AI effect resource; wherein the second AI effect avatar is used to set the user avatar.

10. A computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium. When the instructions are executed on a terminal device, the terminal device implements the method according to any one of claims 1 to 8.

11. A video-based interactive device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images