Live broadcast interaction method and device, electronic equipment and storage medium

Abstract

The invention relates to a live broadcast interaction method and device, electronic equipment and a storage medium. The method comprises the following steps: displaying at least one candidate video identifier in a virtual resource panel corresponding to a first audience account in a live broadcast room; in response to a resource presentation instruction triggered by the first audience account based on a target video identifier, displaying a first video; the target video identifier is any video identifier in the at least one candidate video identifier, the first video is a presented video corresponding to the target video identifier, and the first video is generated based on first historical interaction information of the first audience account and an anchor account; the anchor account is a live broadcast initiating account corresponding to the live broadcast room. According to the invention, personalized interaction between the audience and the anchor in the live broadcasting room is realized.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a live interactive method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of computer technology, live streaming has gradually become a popular form of entertainment. More and more users are participating in live streaming rooms and experiencing live interaction with the streamers. Among these interactions, virtual resource gifting is the core carrier of live streaming interaction. Users can express their support for the streamers by purchasing and gifting virtual resources, while also triggering visual effects and enhancing the atmosphere of the live streaming room.

[0003] In related technologies, viewers in a live stream can send virtual gifts by selecting preset virtual resources provided by the live streaming platform. However, different viewers can only select the same preset virtual resources, which makes it difficult to meet the personalized interactive needs of viewers in the live stream. Summary of the Invention

[0004] This disclosure provides a live streaming interaction method, apparatus, electronic device, and storage medium to at least solve the problem in related technologies that it is difficult to meet the personalized interaction needs of live streaming viewers. The technical solution of this disclosure is as follows: According to a first aspect of the present disclosure, a live interactive method is provided, the method comprising: At least one candidate video identifier is displayed in the virtual resource panel corresponding to the first viewer's account in the live broadcast room; In response to a resource donation instruction triggered by the first viewer account based on a target video identifier, a first video is displayed; the target video identifier is any one of the at least one candidate video identifiers, the first video is the donation video corresponding to the target video identifier, the first video is generated based on the first historical interaction information between the first viewer account and the broadcaster account, and the broadcaster account is the live broadcast initiating account corresponding to the live broadcast room.

[0005] In one exemplary embodiment, the first video is obtained by performing video generation processing on the first historical interaction information using an artificial intelligence model.

[0006] In one exemplary embodiment, the method further includes: When the streamer's account receives multiple gifted videos, a merged video is displayed; the merged video is obtained by merging the multiple gifted videos; the multiple gifted videos are videos gifted to the streamer's account within a preset time period, or a preset number of videos that are continuously gifted to the streamer's account.

[0007] In one exemplary embodiment, the plurality of gifted videos are videos gifted by the first viewer's account; When the streamer's account receives multiple gifted videos, the merged video is displayed, including: When the first viewer account continuously sends the multiple gifted videos to the streamer account, the merged video is displayed.

[0008] In an exemplary embodiment, the plurality of gifted videos are videos gifted by the first viewer account and the second viewer account, wherein the second viewer account is at least one viewer account other than the first viewer account among the viewer accounts corresponding to the live broadcast room; When the streamer's account receives multiple gifted videos, the merged video is displayed, including: When the first viewer account and the second viewer account continuously send the multiple gifted videos to the streamer account, the fused video is displayed; the gifted video sent by the second viewer account is generated based on the second historical interaction information between the second viewer account and the streamer account.

[0009] In one exemplary embodiment, the first video presents a preset story corresponding to the first historical interaction information; The method further includes: If a story element matching the first recommended object exists in the preset story, the first recommended object will be displayed during the display of the first video.

[0010] In an exemplary embodiment, displaying the first recommended object during the display of the first video includes: The first recommended object and its recommendation entry point are displayed during the presentation of the first video.

[0011] In one exemplary embodiment, displaying the first video includes: The first video displays a preset story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0012] In one exemplary embodiment, the method further includes: When the first video is displayed, in response to a sharing instruction for the first video, the first video is published on the associated content publishing platform.

[0013] In one exemplary embodiment, the method further includes: When the first video is displayed, in response to the editing instruction on the first video, an edited first video is generated; the edited first video is generated by adjusting the first video using a preset template, and / or the edited first video is generated by processing the first video based on target adjustment prompts using an artificial intelligence model.

[0014] In one exemplary embodiment, the method further includes: Display custom guidance information; the custom guidance information is used to guide the creation of a video to be gifted to the streamer's account; In response to a video customization instruction triggered by the first viewer account based on the customized guidance information, a custom page is displayed; the custom page includes at least one story element configuration item. In response to the first viewer account's information configuration operation on the target configuration item, a second video is obtained; the target configuration item is at least one of the at least one story element configuration items, and the second video is generated based on the first historical interaction information and the target story element, which is determined based on the information configuration operation on the target configuration item.

[0015] In an exemplary embodiment, after obtaining the second video in response to an information configuration operation on a target configuration item, the method further includes: In response to the resource donation instruction triggered by the first viewer account based on the second video, the second video is displayed; the first historical interaction information in the second video is presented according to the storyline corresponding to the target story element.

[0016] In one exemplary embodiment, the second video is obtained by performing information fusion processing on the first historical interaction information and the target story element through an artificial intelligence model.

[0017] In one exemplary embodiment, the target story element includes a first character and a second character, wherein the first character is the character corresponding to the first viewer account, and the second character is the character corresponding to the broadcaster account; The display of the second video includes: The second video displays the first historical interaction information performed by the first character and the second character, as well as the target story obtained by fusing the target story elements.

[0018] In one exemplary embodiment, the second video is generated based on the first historical interaction information, the target story element, and the real-time live streaming information of the live streaming room.

[0019] In one exemplary embodiment, the real-time live streaming information includes real-time audience information for the live streaming room; The display of the second video includes: The second video displays the first historical interaction information performed by the first character, the second character, and the third character, as well as the target story obtained by fusing the target story elements; the third character is generated based on the real-time audience information of the live broadcast room, and the third character is used to assist the first character and the second character in performing the story.

[0020] In one exemplary embodiment, the real-time audience information of the live stream includes the number of viewers in the live stream and the live stream comments in the live stream; The number of third-person characters in the first video is related to the number of viewers, and the status of the third-person characters is obtained by performing sentiment analysis on the live stream comments.

[0021] In one exemplary embodiment, the real-time live streaming information further includes the live stream footage from the live streaming room; In the second video, the second person is presented as the target person; the target person is the image of the anchor obtained from the live broadcast.

[0022] In one exemplary embodiment, the target story element further includes at least one of a first action corresponding to the first character and a second action corresponding to the second character; The second video presents at least one of the following: The first character performs the first action while performing the target story; The second character performs the second action while performing the target story.

[0023] In one exemplary embodiment, the method further includes: If the story elements of the target story match the second recommended object, the second recommended object is displayed during the presentation of the second video.

[0024] In one exemplary embodiment, displaying the second recommended object during the display process in the second video includes: The second recommended object and its recommendation entry point are displayed during the presentation of the second video.

[0025] In one exemplary embodiment, displaying the second video includes: The second video displays the target story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0026] According to a second aspect of the present disclosure, a live interactive device is provided, comprising: The first display unit is configured to display at least one candidate video identifier in the virtual resource panel corresponding to the first viewer account in the live broadcast room. The second display unit is configured to execute a resource gifting instruction triggered by the first viewer account based on a target video identifier and display a first video; the target video identifier is any one of the at least one candidate video identifiers, the first video is the gifted video corresponding to the target video identifier, the first video is generated based on the first historical interaction information between the first viewer account and the anchor account, and the anchor account is the live broadcast initiating account corresponding to the live broadcast room.

[0027] In one exemplary embodiment, the first video is obtained by performing video generation processing on the first historical interaction information using an artificial intelligence model.

[0028] In one exemplary embodiment, the apparatus further includes a fused video display unit configured to perform: When the streamer's account receives multiple gifted videos, a merged video is displayed; the merged video is obtained by merging the multiple gifted videos; the multiple gifted videos are videos gifted to the streamer's account within a preset time period, or a preset number of videos that are continuously gifted to the streamer's account.

[0029] In one exemplary embodiment, the plurality of gifted videos are videos gifted by the first viewer's account; The fused video display unit is configured to perform: When the first viewer account continuously sends the multiple gifted videos to the streamer account, the merged video is displayed.

[0030] In an exemplary embodiment, the plurality of gifted videos are videos gifted by the first viewer account and the second viewer account, wherein the second viewer account is at least one viewer account other than the first viewer account among the viewer accounts corresponding to the live broadcast room; The fused video display unit is configured to perform: When the first viewer account and the second viewer account continuously send the multiple gifted videos to the streamer account, the fused video is displayed; the gifted video sent by the second viewer account is generated based on the second historical interaction information between the second viewer account and the streamer account.

[0031] In one exemplary embodiment, the first video presents a preset story corresponding to the first historical interaction information; The device further includes a first recommended object display unit, configured to perform: If a story element matching the first recommended object exists in the preset story, the first recommended object will be displayed during the display of the first video.

[0032] In an exemplary embodiment, the first recommendation object display unit is configured to perform: The first recommended object and its recommendation entry point are displayed during the presentation of the first video.

[0033] In one exemplary embodiment, the second display unit is configured to perform: The first video displays a preset story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0034] In one exemplary embodiment, the apparatus further includes a video publishing unit configured to perform: When the first video is displayed, in response to a sharing instruction for the first video, the first video is published on the associated content publishing platform.

[0035] In one exemplary embodiment, the apparatus further includes a video editing unit configured to perform: When the first video is displayed, in response to the editing instruction on the first video, an edited first video is generated; the edited first video is generated by adjusting the first video using a preset template, and / or the edited first video is generated by processing the first video based on target adjustment prompts using an artificial intelligence model.

[0036] In one exemplary embodiment, the apparatus further includes: The guidance information display unit is configured to display custom guidance information; the custom guidance information is used to guide the creation of a video to be gifted to the streamer's account. The custom page display unit is configured to execute a video custom instruction triggered by the first viewer account based on the custom guidance information and display a custom page; the custom page includes at least one story element configuration item. The second video generation unit is configured to perform an information configuration operation in response to the first viewer account on a target configuration item to obtain a second video; the target configuration item is at least one of the at least one story element configuration items, and the second video is generated based on the first historical interaction information and the target story element, the target story element being determined based on the information configuration operation on the target configuration item.

[0037] In one exemplary embodiment, the apparatus further includes a third display unit configured to perform: In response to the resource donation instruction triggered by the first viewer account based on the second video, the second video is displayed; the first historical interaction information in the second video is presented according to the storyline corresponding to the target story element.

[0038] In one exemplary embodiment, the second video is obtained by performing information fusion processing on the first historical interaction information and the target story element through an artificial intelligence model.

[0039] In one exemplary embodiment, the target story element includes a first character and a second character, wherein the first character is the character corresponding to the first viewer account, and the second character is the character corresponding to the broadcaster account; The third display unit is configured to execute: The second video displays the first historical interaction information performed by the first character and the second character, as well as the target story obtained by fusing the target story elements.

[0040] In one exemplary embodiment, the second video is generated based on the first historical interaction information, the target story element, and the real-time live streaming information of the live streaming room.

[0041] In one exemplary embodiment, the real-time live streaming information includes real-time audience information for the live streaming room; The third display unit is configured to execute: The second video displays the first historical interaction information jointly performed by the first character, the second character, and the third character, as well as the target story obtained by fusing the target story elements; the third character is generated based on the real-time audience information of the live broadcast room, and the third character is used to assist the first character and the second character in performing the story.

[0042] In one exemplary embodiment, the real-time audience information of the live stream includes the number of viewers in the live stream and the live stream comments in the live stream; The number of third-person characters in the first video is related to the number of viewers, and the status of the third-person characters is obtained by performing sentiment analysis on the live stream comments.

[0043] In one exemplary embodiment, the real-time live streaming information further includes the live stream footage from the live streaming room; In the second video, the second person is presented as the target person; the target person is the image of the anchor obtained from the live broadcast.

[0044] In one exemplary embodiment, the target story element further includes at least one of a first action corresponding to the first character and a second action corresponding to the second character; The second video presents at least one of the following: The first character performs the first action while performing the target story; The second character performs the second action while performing the target story.

[0045] In one exemplary embodiment, the apparatus further includes a second recommended object display unit, configured to perform: If the story elements of the target story match the second recommended object, the second recommended object is displayed during the presentation of the second video.

[0046] In one exemplary embodiment, the second recommendation object display unit is configured to perform: The second recommended object and its recommendation entry point are displayed during the presentation of the second video.

[0047] In one exemplary embodiment, displaying the second video includes: The second video displays the target story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0048] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the live interactive method as described above.

[0049] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the live interactive method as described above.

[0050] According to a fifth aspect of the present disclosure, a computer program product is provided, the computer program product including a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from the readable storage medium and executes the computer program, causing the device to perform the above-described live interactive method.

[0051] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: This disclosure can display at least one candidate video identifier in the virtual resource panel corresponding to the first viewer account in the live broadcast room. Each candidate video identifier can correspond to a video that can be gifted to the broadcaster account. In response to the resource gifting instruction triggered by the first viewer account based on the target video identifier, the first video can be displayed. The first video is the gifting video corresponding to the target video identifier, and the first video is generated based on the first historical interaction information between the first viewer account and the broadcaster account. Thus, the first viewer account can gift a video containing exclusive memories of the first viewer account and the live broadcast account to the broadcaster account. Unlike related technologies, where different viewers in the live broadcast room can choose to gift the same preset virtual resources to the broadcaster, this disclosure can generate a video containing exclusive memories based on the first historical interaction information between the viewer account and the broadcaster account. This allows the viewer account to gift the video containing exclusive memories to the broadcaster account. Different viewer accounts have different historical interaction information with the broadcaster account, and the corresponding videos containing exclusive memories generated are also different. Consequently, different viewer accounts gift different videos containing exclusive memories to the broadcaster account, realizing personalized interaction between the live broadcast room viewers and the broadcaster.

[0052] Furthermore, by generating videos that can be gifted to the streamer's account based on the first historical interaction information between the first viewer's account and the streamer's account, the number and format of virtual resources in the live stream can be expanded on the basis of the preset virtual resources provided in the live stream, providing a wider range of virtual resource choices for live stream viewers and thus improving the interaction rate of the live stream.

[0053] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0054] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0055] Figure 1 This is a schematic diagram of an implementation environment according to an exemplary embodiment.

[0056] Figure 2 This is a flowchart illustrating a live interactive method according to an exemplary embodiment.

[0057] Figure 3 This is a schematic diagram illustrating the distribution of live video in a live streaming room according to an exemplary embodiment.

[0058] Figure 4 This is a schematic diagram illustrating a first display of a fused video according to an exemplary embodiment.

[0059] Figure 5 This is a schematic diagram illustrating a second display of a fused video according to an exemplary embodiment.

[0060] Figure 6 This is a schematic diagram illustrating a first recommended object according to an exemplary embodiment.

[0061] Figure 7 This is a schematic diagram illustrating the operation of the first video after it has been sent, according to an exemplary embodiment.

[0062] Figure 8 This is a flowchart illustrating a video customization method according to an exemplary embodiment.

[0063] Figure 9 This is a schematic diagram illustrating video customization operation according to an exemplary embodiment.

[0064] Figure 10 This is a block diagram of a live interactive device according to an exemplary embodiment.

[0065] Figure 11 This is a schematic diagram of an electronic device structure according to an exemplary embodiment.

[0066] Figure 12 This is a schematic diagram of another electronic device structure according to an exemplary embodiment. Detailed Implementation

[0067] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0068] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0069] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0070] Please see Figure 1The illustration shows an implementation environment provided by an embodiment of the present disclosure. The implementation environment may include at least one terminal 110 and a server 120, which can communicate with each other via a network.

[0071] Optionally, terminal 110 may include: smartphones, tablets, laptops, digital assistants, smart wearable devices, in-vehicle terminals, servers, etc. Terminal 110 has an interactive application installed and running. In this embodiment, the interactive application may be an application providing live streaming functionality, or it may be a social application, instant messaging application, live streaming application, game application, e-commerce application, virtual reality (VR) application, augmented reality (AR) application, etc. This application embodiment does not limit the specific type of application.

[0072] Optionally, server 120 provides background services for the interactive application installed on terminal 110. Terminal 110 can communicate with server 120 based on browser / server (B / S) mode or client / server (C / S) mode. The operating system running on terminal 110 in this embodiment may include, but is not limited to, Android, iOS, Linux, Windows, etc.

[0073] Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0074] To address the issue that in related technologies, viewers in a live stream can choose preset virtual resources provided by the live streaming platform to send as gifts, but different viewers can only choose the same preset virtual resources, making it difficult to meet the personalized interaction needs of live stream viewers, this disclosure provides a live streaming interaction method. The execution subject of this method can be the aforementioned terminal. Please refer to [link to relevant documentation]. Figure 2 The method may include: S210. Display at least one candidate video identifier in the virtual resource panel corresponding to the first viewer account in the live broadcast room.

[0075] The first viewer account in the live stream can be any viewer account in the live stream. The virtual resource panel corresponding to the first viewer account in the live stream can be used to hold virtual resources that the first viewer account can gift to the streamer account. Optionally, the virtual resource panel corresponding to the first viewer account can be used to hold preset virtual resources corresponding to the live stream and at least one candidate video identifier. Each candidate video identifier can correspond to a video to be gifted. The video to be gifted corresponding to any candidate video identifier can be a generated video or a video to be generated. By triggering an operation on any candidate video identifier, the video corresponding to any candidate video identifier can be gifted to the streamer account.

[0076] In one optional embodiment, any candidate video identifier may be displayed using at least one form of information such as images or text. Optionally, any candidate video identifier may be presented in a combination of images and text. For example, the image in any candidate video identifier may be a general image or a key video frame in the video corresponding to any candidate video identifier; the text in any candidate video identifier may be text guidance information such as "video gift" or "give away video".

[0077] In one optional embodiment, when at least one candidate video identifier is displayed in the virtual item panel, and at least one candidate video identifier corresponds to a generated video, the generated video corresponding to any candidate video identifier can be directly gifted in response to a resource gifting instruction triggered on any candidate video identifier. In another optional embodiment, when at least one candidate video identifier is displayed in the virtual item panel, the video corresponding to at least one candidate video identifier has not been generated. In response to a resource gifting instruction triggered on any candidate video identifier, the video corresponding to any candidate video identifier can be generated first, and then the generated video can be gifted. The specific implementation can be determined according to the actual situation and is not limited here.

[0078] In one exemplary embodiment, the virtual resource panel corresponding to the first viewer account may display a candidate video identifier. At different times, in response to a resource gifting instruction triggered based on this candidate video identifier, the gifted video will be different. In another exemplary embodiment, the virtual resource panel corresponding to the first viewer account may display multiple candidate video identifiers. Different candidate video identifiers may correspond to different videos to be gifted. Resource gifting instructions triggered based on different candidate video identifiers will result in different gifted videos.

[0079] Optionally, in this embodiment, the video corresponding to at least one candidate video identifier displayed in the virtual resource panel corresponding to the first viewer account can be a video generated based on the first historical interaction information between the first viewer account and the streamer account. The first historical interaction information includes at least one of the following interactions: the first viewer account's following interaction information with the streamer account; the first viewer account's virtual resource gifting interaction information with the streamer account; the interaction information regarding the increased association between the first viewer account and the streamer account; the first viewer account's support interaction information with the live stream account; the first viewer account's real-time audio and video interaction information with the live stream account; the first viewer account's interaction information regarding the acquisition of recommended objects corresponding to the live stream account; the first viewer account's liking interaction information with the live stream account; and the first viewer account's commenting interaction information with the live stream account. Accordingly, when a candidate video identifier is displayed in the virtual resource panel corresponding to the first viewer, in response to a resource gifting instruction triggered based on the candidate video identifier, the gifted video can be generated based on at least one of the aforementioned first historical interaction information, and the currently generated video corresponding to the first viewer account is different from the videos already gifted by the first viewer account in the live stream. When multiple candidate video identifiers are displayed in the virtual resource panel corresponding to the first viewer, different candidate video identifiers can correspond to videos generated by different first historical interaction information. The video corresponding to each candidate video identifier can be generated based on at least one of the first historical interaction information. For example, multiple candidate video identifiers may include a first video identifier, a second video identifier, a third video identifier, etc., where the first video identifier corresponds to a video generated based on follow interaction information, the second video identifier corresponds to a video generated based on virtual resource gifting interaction information, and the third video identifier corresponds to a video generated based on point interaction information and comment interaction information, etc.

[0080] S220. In response to a resource donation instruction triggered by the first viewer account based on a target video identifier, display a first video; the target video identifier is any one of the at least one candidate video identifiers, the first video is the donation video corresponding to the target video identifier, the first video is generated based on the first historical interaction information between the first viewer account and the broadcaster account, and the broadcaster account is the live broadcast initiating account corresponding to the live broadcast room.

[0081] The resource gifting instruction triggered by the first viewer account based on the target video identifier can be triggered by the resource gifting control in the virtual resource panel when the target video identifier is selected. When the target video identifier is displayed in the virtual resource panel, and a video corresponding to the target video identifier has already been generated, the first video corresponding to the target video identifier can be directly gifted to the broadcaster account in response to the resource gifting instruction triggered by the first viewer account based on the target video identifier. When the target video identifier is displayed in the virtual resource panel, and a video corresponding to the target video identifier has not yet been generated, the first video can be generated first based on the first historical interaction information between the first viewer account and the broadcaster account in response to the resource gifting instruction triggered by the first viewer account based on the target video identifier, and then the first video can be gifted to the broadcaster account. When the first video is gifted to the broadcaster account, the first video can be displayed accordingly. Optionally, the first video can be automatically generated based on the terminal or server.

[0082] In an exemplary embodiment, the first historical interaction information includes the following interaction information of the first viewer account to the streamer account, the virtual resource gifting interaction information of the first viewer account to the streamer account, and the interaction information of the relationship upgrade between the first viewer account and the streamer account. The following interaction information may include the following time, the following location, etc. The resource gifting interaction information may include the resource gifting time and the resources gifted. The relationship upgrade interaction information may include the upgrade time, the level before the upgrade, and the level after the upgrade, etc. The corresponding first video may present a storyline in which the first character corresponding to the first viewer account and the second character corresponding to the streamer account meet during the following time, gift resource 'a' during the resource gifting time, and upgrade their intimacy from the first level to the second level during the upgrade time.

[0083] Please see Figure 3 The diagram illustrates the presentation of video gifting in the live stream. In the virtual resource panel 310 corresponding to the first viewer account, candidate video identifiers 320 and multiple preset virtual resources are displayed. Taking one candidate video identifier as an example, when the candidate video identifier 320 is selected and the resource gifting command is triggered by the resource gifting control 330, the first video 340 generated based on the first historical interaction information between the first viewer account and the streamer account can be gifted to the streamer account, and the first video 340 can be displayed.

[0084] This disclosure can display at least one candidate video identifier in the virtual resource panel corresponding to the first viewer account in the live broadcast room. Each candidate video identifier can correspond to a video that can be gifted to the broadcaster account. In response to the resource gifting instruction triggered by the first viewer account based on the target video identifier, the first video can be displayed. The first video is the gifting video corresponding to the target video identifier, and the first video is generated based on the first historical interaction information between the first viewer account and the broadcaster account. Thus, the first viewer account can gift a video containing exclusive memories of the first viewer account and the live broadcast account to the broadcaster account. Unlike related technologies, where different viewers in the live broadcast room can choose to gift the same preset virtual resources to the broadcaster, this disclosure can generate a video containing exclusive memories based on the first historical interaction information between the viewer account and the broadcaster account. This allows the viewer account to gift the video containing exclusive memories to the broadcaster account. Different viewer accounts have different historical interaction information with the broadcaster account, and the corresponding videos containing exclusive memories generated are also different. Consequently, different viewer accounts gift different videos containing exclusive memories to the broadcaster account, realizing personalized interaction between the live broadcast room viewers and the broadcaster. Furthermore, by generating videos that can be gifted to the streamer's account based on the first historical interaction information between the first viewer's account and the streamer's account, the number and format of virtual resources in the live stream can be expanded on the basis of the preset virtual resources provided in the live stream, providing a wider range of virtual resource choices for live stream viewers and thus improving the interaction rate of the live stream.

[0085] In one alternative embodiment, the first video is obtained by performing video generation processing on the first historical interaction information using an artificial intelligence model.

[0086] The artificial intelligence model can be a pre-trained model with processing capabilities such as text-to-video and image-to-video generation. By inputting the initial historical interaction information into the AI ​​model, it can process the information to generate a video. Thus, leveraging the powerful and outstanding processing capabilities of the AI ​​model, the quality and efficiency of the generated video can be improved.

[0087] In one exemplary embodiment, each viewer account in the live stream can send videos generated based on historical interaction information to the streamer account; correspondingly, the live stream interaction method in this embodiment may further include: When the streamer's account receives multiple gifted videos, a merged video is displayed; the merged video is obtained by merging the multiple gifted videos; the multiple gifted videos are videos gifted to the streamer's account within a preset time period, or a preset number of videos that are continuously gifted to the streamer's account.

[0088] In one exemplary embodiment, multiple gifted videos can be concatenated based on their respective gifting times to obtain a merged video; for example, multiple gifted videos can be concatenated in chronological order of their gifting times to obtain a merged video. Please refer to [link to relevant documentation]. Figure 4 The diagram shows the first display of the merged video, in which multiple gifted videos are video 410 gifted by viewer account 1 to the live broadcast account and video 420 gifted by viewer account 2 to the streamer account; the merged video includes video 410 and video 420, and the gifting time corresponding to video 410 is earlier than the gifting time corresponding to video 420. Accordingly, in the process of displaying the merged video, video 410 can be displayed first, and video 420 can be displayed after video 410 has been displayed.

[0089] In another exemplary embodiment, multiple gifted videos can be concatenated based on the interaction type of their respective historical interaction information to obtain a fused video; for example, gifted videos with the same interaction type can be concatenated first to obtain multiple combined videos, and then the multiple combined videos can be fused to obtain a fused video.

[0090] In another exemplary embodiment, multiple complimentary videos can be spliced ​​together in a multi-screen format, meaning that at least two video frames corresponding to each complimentary video can be displayed within the same frame. For example, at least two complimentary videos can be spliced ​​together to generate multiple spliced ​​videos, and then these multiple spliced ​​videos can be concatenated to obtain a merged video. Please refer to [link to relevant documentation]. Figure 5 The diagram shows a second display of the merged video, in which multiple gifted videos are video 510 gifted by viewer account 1 to the live broadcast account and video 520 gifted by viewer account 2 to the streamer account; the merged video includes video 510 and video 520, and correspondingly, during the display of the merged video, video 510 and video 520 can be displayed on the same screen, that is, video 510 and video 520 are displayed on the same screen.

[0091] Multiple gifted videos can be videos gifted to the streamer's account within a preset time period. The preset time period can be a pre-set live stream time period or a randomly selected live stream time period. At the end of the preset time period, the merged videos can be displayed accordingly.

[0092] Multiple gifted videos can be a preset number of videos that are continuously gifted to the streamer's account; for example, if the preset number of videos that are continuously gifted to the streamer's account is detected, a fusion video can be displayed accordingly.

[0093] In this embodiment, when the broadcaster's account receives multiple gift videos, a merged video obtained by merging the multiple gift videos can be displayed. Since the merged video includes multiple gift videos received by the broadcaster's account, the visual presentation of the gift videos can be enhanced. Both the viewers and the broadcaster in the live stream can review the corresponding gift videos, further improving the interaction rate of the live stream.

[0094] In one optional embodiment, the multiple gifted videos may be videos gifted by the same viewer account; optionally, the multiple gifted videos may be videos gifted by the first viewer account. When the streamer's account receives multiple gifted videos, the merged video is displayed, including: When the first viewer account continuously sends the multiple gifted videos to the streamer account, the merged video is displayed.

[0095] The multiple videos gifted by the first viewer account to the streamer account can be videos gifted by the first viewer account to the streamer account within a preset time period; or they can be a preset number of videos gifted by the first account to the streamer account consecutively. For example, if it is detected that the first account has consecutively gifted a preset number of videos to the streamer account, a fused video generated based on multiple gifted videos can be displayed.

[0096] In this embodiment, by merging multiple gifted videos continuously sent from the first viewer account to the streamer account and displaying the merged video, the resource gifting effect from the first viewer account to the streamer account can be further enhanced. Both the viewers and the streamer in the live broadcast room can review the corresponding gifted videos, further improving the interaction rate of the first viewer account in the live broadcast room.

[0097] In another alternative embodiment, the multiple gifted videos can be videos gifted by different viewer accounts; optionally, the multiple gifted videos are videos gifted by the first viewer account and the second viewer account, where the second viewer account is at least one viewer account other than the first viewer account among the viewer accounts corresponding to the live broadcast room. When the streamer's account receives multiple gifted videos, the merged video is displayed, including: When the first viewer account and the second viewer account continuously send the multiple gifted videos to the streamer account, the fused video is displayed; the gifted video sent by the second viewer account is generated based on the second historical interaction information between the second viewer account and the streamer account.

[0098] The number of second viewer accounts can be one or more. The multiple videos gifted by the first viewer account and the second viewer account to the live broadcast account can be videos gifted by the first viewer account and the second viewer account to the broadcaster account within a preset time period; or they can be a preset number of videos gifted by the first viewer account and the second viewer account to the broadcaster account consecutively. For example, if it is detected that the first viewer account and the second viewer account have consecutively gifted a preset number of videos to the broadcaster account, a fused video generated based on multiple gifted videos can be displayed.

[0099] In this embodiment, multiple gift videos sent by the first and second viewer accounts to the streamer account are merged and the merged video is displayed accordingly. During the display of the merged video, an atmosphere and effect of video gift relay among the viewers in the live broadcast room can be created, thereby realizing the interaction between the various viewer accounts in the live broadcast room and improving the interaction rate of each viewer account in the live broadcast room.

[0100] The first video, automatically generated based on a terminal or server, can present a preset story corresponding to the first historical interaction information, that is, display the first historical interaction information in the form of a story narrative. In an exemplary embodiment, the first historical interaction information includes the following interaction information of the first viewer account to the anchor account, the virtual resource gifting interaction information of the first viewer account to the anchor account, and the interaction information of the relationship upgrade between the first viewer account and the anchor account. The following interaction information may include the following time, the following location, etc.; the resource gifting interaction information may include the resource gifting time and the resources already gifted; the relationship upgrade interaction information may include the upgrade time, the level before the upgrade, and the level after the upgrade, etc. The corresponding first video can present a storyline in which the first character corresponding to the first viewer account and the second character corresponding to the anchor account meet during the following time, gift resource 'a' during the resource gifting time, and the intimacy level upgrades from the first level to the second level during the upgrade time. Accordingly, the method of this embodiment may also include: If a story element matching the first recommended object exists in the preset story, the first recommended object will be displayed during the display of the first video.

[0101] In one optional embodiment, in addition to the first historical interaction information, the first video may also include extended story elements. These story elements may include characters, scenes, actions, etc. These extended story elements may be added to the first video during the generation process based on the first historical interaction information, and may or may not be associated with the first historical interaction information. Correspondingly, there may be recommended objects associated with characters, recommended objects associated with scenes, recommended objects associated with actions, etc.

[0102] For example, the first video could show the first person corresponding to the first viewer's account and the second person corresponding to the streamer's account meeting at a coffee shop during the viewing time; here, the coffee shop can be a scene element in the story elements, and correspondingly, recommended objects associated with the coffee shop can be obtained, such as coffee cups or coffee.

[0103] The first recommended object can be displayed during the first video's presentation. This can be done by directly including the first recommended object within the first video, i.e., displaying the first recommended object as a content element of the first video; or it can be displayed in a separate display area from the first video's presentation, such as through an object card or a pop-up window.

[0104] In this embodiment, when there are story elements in the preset story that match the first recommended object, the first recommended object is displayed during the display of the first video. This enables the combination of story presentation and object recommendation in the first video, improving the audience's acceptance of the recommended object and enriching the form of information display.

[0105] Furthermore, displaying the first recommended object during the display of the first video includes: The first recommended object and its recommendation entry point are displayed during the presentation of the first video.

[0106] The first recommended object and its recommendation entry can be displayed together, that is, the recommendation entry of the first recommended object is attached to the first recommended object for display; or the first recommended object and its recommendation entry can be displayed independently, for example, the recommendation entry of the first recommended object can be an independent entry control.

[0107] Please see Figure 6 The diagram illustrates the display of the first recommended object. For example, in the first video 610, the first person corresponding to the first viewer's account and the second person corresponding to the streamer's account meet at a coffee shop during the viewing time. Here, the coffee shop can be a scene element in the story, and corresponding recommended objects associated with the coffee shop can be obtained. These recommended objects can be coffee cups. During the display of the first video 610, object cards 620 can be displayed, including a coffee cup 630 and a recommendation entry point 640. Specifically, this can be a retrieval control; by triggering the recommendation entry point 640, the recommended coffee cup 630 can be retrieved.

[0108] In this embodiment, when a story element matching the first recommended object exists in the preset story, the first recommended object is displayed during the display of the first video. This combines the story presentation of the first video with object recommendation, increasing viewer acceptance of the recommended object and enriching the information display format. Furthermore, by displaying the recommendation entry point for the first recommended object, users can easily access the first recommended object through the recommendation entry point, improving the efficiency of obtaining the first recommended object.

[0109] In one optional embodiment, in addition to generating the first video based on historical interaction information in the live streaming platform, the first video can also be generated by combining associated interaction information from external platforms other than the live streaming platform; correspondingly, displaying the first video includes: The first video displays a preset story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0110] The associated platform can be a content publishing platform or e-commerce platform associated with the live streaming platform. The corresponding associated interaction information may include at least one of the following: the first viewer account's historical interaction information on content publishing platforms other than the live streaming platform and the first viewer account's historical purchase information on e-commerce platforms. Through the first viewer account's historical interaction information on social platforms other than the live streaming platform, at least one of the first viewer account's preferred characters, items, or scenes can be determined. Accordingly, at least one of the first viewer account's preferred characters, items, or scenes can be incorporated into the first video as a story element. Through the first viewer account's historical purchase information on e-commerce platforms, the first viewer account's purchase preferences can be determined. Accordingly, purchase preferences can be incorporated into the first video as a story element.

[0111] In this embodiment, during the generation of the first video, the first historical interaction information of the first viewer account on the live streaming platform and the interaction information of the first viewer account on the associated platform can be combined to generate the first video. This breaks through the data limitations of the live streaming platform, realizes data connectivity between the live streaming platform and external platforms, realizes cross-platform story generation, and further improves the richness of the storyline of the preset story.

[0112] In an optional embodiment, the first video that has already been displayed can be shared and forwarded; accordingly, the method further includes: When the first video is displayed, in response to a sharing instruction for the first video, the first video is published on the associated content publishing platform.

[0113] When a viewer's account gifts a first video to a broadcaster's account, and the first video is displayed, a sharing control can be shown. This control can then trigger a sharing command, sharing the first video to the associated content publishing platform. Alternatively, the first video can be saved upon creation, and a sharing command can be triggered on the saved video to publish it on the associated content publishing platform.

[0114] In this embodiment, once the first video has been generated or gifted, it can also be shared to publish the first video to the associated content publishing platform. This allows the first video to be displayed not only in the live broadcast room but also on the associated content publishing platform, thereby expanding the display scope of the first video and improving content reuse efficiency.

[0115] In another alternative embodiment, the already generated first video can also be further edited; optionally, the method further includes: When the first video is displayed, in response to the editing instruction on the first video, an edited first video is generated; the edited first video is generated by adjusting the first video using a preset template, and / or the edited first video is generated by processing the first video based on target adjustment prompts using an artificial intelligence model.

[0116] When a viewer's account gifts a first video to a broadcaster's account, and the first video is displayed, editing controls can be shown. Responding to editing commands triggered by these controls, a video editing page for the first video can be displayed. The video editing page can display preset templates, which can be changed to present the video content based on the modified template. The preset templates can include replaceable elements such as scenes, characters, actions, and time. The video editing page may also include an AI dialogue area. By entering video adjustment prompts in the AI ​​dialogue area, secondary editing of the first video can be achieved, resulting in an edited version.

[0117] Please see Figure 7 The diagram illustrates the operation of the first video after it has been gifted. After gifting the first video to the broadcaster's account and after the first video has been displayed, a sharing control 710 and an editing control 720 can be displayed. Accordingly, by responding to the sharing command based on the sharing control 710, the first video can be shared to the associated content publishing platform; by responding to the editing command based on the editing control 710, the first video can be edited again to obtain the edited first video.

[0118] In this embodiment, when the first video has already been generated, it can be edited again by adjusting the template, or by inputting target adjustment prompts into the artificial intelligence model, thereby improving the flexibility of editing and generating the first video.

[0119] The first video described above in this embodiment can be automatically generated based on a terminal or server. Furthermore, in the process of generating the video to be gifted to the broadcaster's account, a corresponding second video can also be generated by combining information customized by the viewer user; please refer to Figure 8 It illustrates a video customization method that may include: S810. Display custom guidance information; the custom guidance information is used to guide the creation of a video to be gifted to the streamer's account.

[0120] The custom guidance information in this embodiment may include at least one form of information such as images and text. Optionally, the custom guidance information may be displayed in any form such as guidance bubbles, guidance controls, or guidance cards. The custom guidance information may be displayed in the virtual resource panel corresponding to the first viewer's account, or it may be displayed in any area of ​​the live broadcast page.

[0121] S820. In response to the video customization instruction triggered by the first viewer account based on the customized guidance information, display a customized page; the customized page includes at least one story element configuration item.

[0122] Custom guide messages can have a trigger attribute, allowing the generation of a custom video instruction by triggering the custom guide message. Upon responding to the custom video instruction, a custom page including at least one story element configuration item can be displayed. Custom guide messages may also lack a trigger attribute, allowing the generation of a custom video instruction by triggering the trigger information indicated by the custom guide message. Upon responding to the custom video instruction, a custom page including at least one story element configuration item can be displayed. For example, the custom guide message can instruct the triggering of a custom control to generate a custom video instruction.

[0123] Story elements can include scenes, characters, actions, time, etc. The corresponding custom page can include configuration items for scene elements, character elements, action elements, time elements, etc.

[0124] S830. In response to the first viewer account's information configuration operation on the target configuration item, a second video is obtained; the target configuration item is at least one of the at least one story element configuration items, and the second video is generated based on the first historical interaction information and the target story element, the target story element being determined based on the information configuration operation on the target configuration item.

[0125] During the process of video customization by viewers, at least one of the following configuration items can be configured: those corresponding to scene elements, character elements, action elements, and time elements. This configuration information allows for the generation of a second video. In this embodiment, the second video can be generated based on the terminal. Optionally, the terminal can perform video generation processing on the first historical interaction information and the target story element to obtain the second video. Alternatively, the second video can be generated based on the server. Optionally, the server can perform video generation processing on the first historical interaction information and the target story element to obtain the second video. When the second video is generated by the server, the terminal can obtain the second video from the server.

[0126] In this embodiment, during the process of customizing a video, the user can trigger a video customization command to display a customization page for configuring story elements. Then, based on the information configuration operation on the customization page, the user can determine the target story element, thereby obtaining a second video generated based on the first historical interaction information and the target story element. That is, the user can configure the target story element so that the generated second video contains a story plot related to the target story element, thereby further enriching the story content of the second video and realizing personalized video generation.

[0127] In an optional embodiment, after obtaining the second video in response to the information configuration operation on the target configuration item, the method further includes: In response to the resource donation instruction triggered by the first viewer account based on the second video, the second video is displayed; the first historical interaction information in the second video is presented according to the storyline corresponding to the target story element.

[0128] Once the second video has been generated, its video identifier will be displayed in the virtual resource panel corresponding to the first viewer's account. When the second video identifier is selected, triggering the resource gifting control will gift the second video to the broadcaster's account. Alternatively, a gifting prompt will be displayed, including an indication that the second video has been generated and the resource gifting control. Triggering the resource gifting control will gift the second video to the broadcaster's account. When the second video is gifted to the broadcaster's account, it will be displayed, and the first historical interaction information within the second video will be presented according to the storyline corresponding to the target story element.

[0129] Please see Figure 9 The document illustrates a video customization operation, using the display of custom guidance information 920 in the virtual resource panel 910 as an example. Custom guidance information 920 may display text messages such as "Customize Exclusive Video" or "Customize Video Gift." Triggering custom guidance information 920 displays a custom page 930, which may include configuration items for scene elements, character elements, action elements, and time elements. Configuring at least one of these items generates a second video. Once the second video is generated, a gifting prompt 940 is displayed, containing text messages such as "Second Video Generated" or "Give the Second Video Now." The prompt may also include a resource gifting control, which allows gifting the second video to the streamer's account. Finally, once the second video is generated, a video identifier 950 corresponding to the second video is displayed in the virtual resource panel corresponding to the first viewer's account. When video identifier 950 is selected and the resource gifting control in the virtual resource panel is triggered, the second video is gifted to the streamer's account. The second video can be displayed when a second video is gifted to the streamer's account.

[0130] In this embodiment, a video containing exclusive memories can be generated based on the first historical interaction information between the viewer's account and the live broadcast account, as well as the target story elements configured in the viewer's account. The historical interaction information in the video can be presented based on the storyline corresponding to the target story elements, thereby enabling the personalized generation of gift videos. By gifting personalized videos to the broadcaster's account, personalized interaction between the live broadcast audience and the broadcaster is achieved.

[0131] In one alternative embodiment, the second video is obtained by performing information fusion processing on the first historical interaction information and the target story elements through an artificial intelligence model.

[0132] The AI ​​model can be a pre-trained model with processing capabilities such as text-to-video and image-to-video generation. By inputting the first historical interaction information and the target story elements into the AI ​​model, the model can process the information to generate a video, presenting the first historical interaction information according to the storyline corresponding to the target story elements, thus obtaining the second video. Therefore, leveraging the powerful and outstanding processing capabilities of the AI ​​model, the quality and efficiency of the generated second video can be improved.

[0133] In one exemplary embodiment, the target story element includes a first character and a second character, wherein the first character is the character corresponding to the first viewer account, and the second character is the character corresponding to the broadcaster account; The display of the second video includes: The second video displays the first historical interaction information performed by the first character and the second character, as well as the target story obtained by fusing the target story elements.

[0134] The first audience account can configure the configuration items corresponding to the character elements on the custom page. It can configure the first character corresponding to the first audience account and the second character corresponding to the anchor account. The corresponding second video can display the target story obtained by the first task and the second character jointly performing the first historical interactive information and target story elements.

[0135] When configuring the configuration items corresponding to the character elements, you can configure the number of characters, character appearance, character type, etc. The character appearance can be the character's appearance, character style, etc., and the character type can be the character's occupation type, character's gender type, etc.

[0136] In this embodiment, by configuring target story elements including a first character and a second character, the second video displays a target story obtained by integrating the first historical interaction information and the target story elements, which is then presented by the first character and the second character. This makes the storyline of the target story more complete and enriches the presented video content.

[0137] In one alternative embodiment, the second video is generated based on the first historical interaction information, the target story element, and the real-time live streaming information of the live streaming room.

[0138] The real-time live information in the live room can refer to the collection of various data, content, interactions, and scene-related information that are generated and dynamically updated in real time during the live broadcast and are directly related to the live broadcast activities; and the second video generated based on the first historical interaction information, the target story elements, and the real-time live information in the live room. In addition to presenting the target story obtained by fusing the first historical interaction information and the target story elements, which are jointly performed by the first character and the second character, the second video may also include video elements associated with the real-time live information.

[0139] In this embodiment, a second video is generated by combining the first historical interaction information, the target story element, and the real-time live broadcast information of the live broadcast room. This allows the second video to not only present the target story obtained by fusing the first historical interaction information and the target story element, which is jointly performed by the first character and the second character, but also to include video elements associated with the real-time live broadcast information. In other words, the second video is closely linked to the real-time live broadcast information, avoiding the problem of the generated second video being detached from the live broadcast scene, and also improving the richness of the video content of the second video.

[0140] In one exemplary embodiment, the real-time live streaming information includes real-time audience information for the live streaming room; the real-time audience information for the live streaming room can refer to a collection of various data, behaviors, and interactive feedback information that are generated in real time and dynamically updated during the live streaming process and are directly related to the audience currently watching the live stream; correspondingly, displaying the second video includes: The second video displays the first historical interaction information performed by the first character, the second character, and the third character, as well as the target story obtained by fusing the target story elements; the third character is generated based on the real-time audience information of the live broadcast room, and the third character is used to assist the first character and the second character in performing the story.

[0141] The third character can correspond to the audience in the live broadcast room. The third character can act as an extra for the first and second characters, in order to cooperate with the first and second characters to perform the target story obtained by integrating the first historical interactive information and target story elements.

[0142] In this embodiment, a third character is determined from the real-time audience information in the live broadcast room to assist the first and second characters in the story performance. That is, the first, second, and third characters work together to tell the target story. On the one hand, by adding a third character to the target story, the character information in the target story can be enriched, thereby improving the richness of the video content of the second video. On the other hand, the third character is generated based on the real-time audience information in the live broadcast room, that is, the second video is closely related to the real-time live broadcast information, avoiding the problem of the generated second video being detached from the live broadcast scene.

[0143] In one optional embodiment, the real-time audience information of the live stream includes the number of viewers in the live stream and the live stream comments; The number of third-person characters in the first video is related to the number of viewers, and the status of the third-person characters is obtained by performing sentiment analysis on the live stream comments.

[0144] The number of viewers in a live stream can be the number of online viewers watching the live stream. By performing sentiment analysis on the live stream comments, the current comment atmosphere and viewer emotions in the live stream can be determined. Then, based on the actual comment atmosphere and viewer emotions in the live stream, the character state of the third person can be determined, that is, to make the character state of the virtual third person in the target story match the actual comment atmosphere and viewer emotions in the live stream.

[0145] In this embodiment, the number of third-person characters in the target story is determined by the actual number of viewers in the live broadcast room, and the character status of the third-person characters is determined by the sentiment analysis of the live broadcast comments. This achieves the effect of matching the real live broadcast scene with the virtual story scene items, that is, generating a scene that combines the virtual and real.

[0146] In one optional embodiment, the real-time live streaming information further includes the live stream footage from the live streaming room; In the second video, the second person is presented as the target person; the target person is the image of the anchor obtained from the live broadcast.

[0147] The live stream footage can include the real-time image of the host. By obtaining the host's image from the live stream footage and presenting it as the target image of a second persona in the video, the virtual second persona in the target story is combined with the actual host image in the live stream scene, which enhances the presentation of the host's image and enriches the video content.

[0148] In yet another alternative embodiment, the target story element further includes at least one of a first action corresponding to the first character and a second action corresponding to the second character; The second video presents at least one of the following: The first character performs the first action while performing the target story; The second character performs the second action while performing the target story.

[0149] In addition to configuring the actions corresponding to the first and second characters, the relationship between the first and second actions can be further configured. The first action corresponding to the first character and the second action corresponding to the second character can be related or unrelated. For example, if the first action is walking and the second action is walking, the first action and the second action can be considered unrelated. If the first action is hugging and the second action is hugging, the first action and the second action can be considered related, and the generated video can show the video content of the first character and the second character hugging.

[0150] In this embodiment, in addition to configuring the target story elements including a first character and a second character, the corresponding actions of the first character and the second character can be further configured. Accordingly, in the second video, the first character and the second character can perform corresponding actions while performing the target story. By configuring the characters' actions, the video content can be further enriched, and personalized video generation can be achieved by configuring actions according to user configuration preferences.

[0151] In an optional embodiment, the method further includes: If the story elements of the target story match the second recommended object, the second recommended object is displayed during the presentation of the second video.

[0152] In one optional embodiment, the second video may include, in addition to the first historical interaction information, extended story elements. These story elements may include characters, scenes, actions, etc., and may be added to the second video during the generation process based on the first historical interaction information. They may or may not be associated with the first historical interaction information. Correspondingly, there may be recommended objects associated with characters, scenes, actions, etc.

[0153] For example, the second video could show the first person corresponding to the first viewer's account and the second person corresponding to the streamer's account meeting at a coffee shop during the viewing time; here, the coffee shop can be a scene element in the story elements, and correspondingly, recommended objects associated with the coffee shop can be obtained, such as coffee cups or coffee.

[0154] The second recommended object can be displayed during the display of the second video. It can be directly included in the second video, that is, the second recommended object is displayed as a content element of the second video; or it can be displayed in a display area independent of the second video display screen, such as through object cards or pop-up windows.

[0155] In this embodiment, if there are story elements in the preset story that match the second recommended object, the second recommended object is displayed during the display of the second video. This enables the combination of story presentation and object recommendation in the second video, improving the audience's acceptance of the recommended object and enriching the form of information display.

[0156] In another alternative embodiment, displaying the second recommended object during the display process in the second video includes: The second recommended object and its recommendation entry point are displayed during the presentation of the second video.

[0157] The second recommended object and its recommendation entry can be displayed together, meaning the recommendation entry of the second recommended object is attached to the second recommended object for display; alternatively, the second recommended object and its recommendation entry can be displayed independently, for example, the recommendation entry of the second recommended object can be an independent entry control. For a schematic diagram of the second recommended object display, please refer to this embodiment. Figure 6 The first recommended object is shown in the illustration.

[0158] In this embodiment, when a story element matching the second recommended object exists in the preset story, the second recommended object is displayed during the display of the second video. This combines the story presentation of the second video with object recommendation, increasing viewer acceptance of the recommended object and enriching the information display format. Furthermore, by displaying a recommendation entry point for the second recommended object, users can easily access the second recommended object through this entry point, improving the efficiency of obtaining the second recommended object.

[0159] In another alternative embodiment, the target story element includes a first character and a second character, wherein the first character is the character corresponding to the first viewer account and the second character is the character corresponding to the streamer account; The display of the second video includes: The second video displays the target story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0160] In one example, the actions and / or appearance of the second character in the process of performing the target story can be determined based on the associated interaction information; optionally, the first historical interaction information performed by the first character and the second character and the target story obtained by fusing the target story elements are displayed in the second video; the actions and / or appearance of the second character in the process of performing the target story are determined based on the associated interaction information, which is the interaction information of the first viewer account on the associated platform.

[0161] The associated platform can be a content publishing platform or e-commerce platform associated with the live streaming platform. The corresponding associated interaction information may include at least one of the following: the first viewer account's historical interaction information on content publishing platforms other than the live streaming platform and the first viewer account's historical purchase information on e-commerce platforms. Through the first viewer account's historical interaction information on social platforms other than the live streaming platform, at least one of the first viewer account's preferred characters, items, or scenes can be determined. Accordingly, at least one of the first viewer account's preferred characters, items, or scenes can be incorporated into the first video as a story element. Through the first viewer account's historical purchase information on e-commerce platforms, the first viewer account's purchase preferences can be determined. Accordingly, purchase preferences can be incorporated into the first video as a story element.

[0162] In this embodiment, during the generation of the second video, the first historical interaction information of the first viewer account on the live streaming platform and the interaction information of the first viewer account on the associated platform can be combined to generate the second video. This breaks through the data limitations of the live streaming platform, realizes data connectivity between the live streaming platform and external platforms, realizes cross-platform story generation, and further improves the richness of the storyline of the preset story.

[0163] The following example illustrates the implementation process of this document: (The process of sending gifts during a live stream is described below.) 1. Before gift-giving - short video playback triggered: 1) Multiple gift-giving by a single user: Each gift-giving session triggers only one segment, and multiple gift-giving sessions by a single user are linked together to form a complete short video. 1) Manually select desired story details (time, scene, characters, actions, plot) 2) Send a gift 1) Select the desired story details again (time, scene, characters, actions, plot) 2) Send the gift 2) Single-person, single-time gift giving: Each gift giving triggers a short memory video. 1) Manually select desired story details (time, scene, characters, actions, plot) 2) Send a gift 3) Multi-user single-time gift relay: Each gift-giving session triggers only one segment, and multiple users sending gifts multiple times create a complete short video. User A: Manually select desired story details (time, scene, characters, actions, plot) 2) Send a gift User B: Manually select desired story details (time, scene, characters, actions, plot) 2) Send a gift User C: Manually select desired story details (time, scene, characters, actions, plot) 2) Send a gift ... 2. Gift Giving - Model Generation Process 1) Model Information Input: Input existing information into the artificial intelligence model. Live stream information (from the streamer's perspective): number of viewers online, number of commenters, comment content, and the time the live stream started; Information about the streamer (streamer perspective): streamer's live stream footage, revenue generation capacity, number of followers, city, etc.; User information (user dimensions): user city, user level, willingness to pay, etc.; User-selected information (user dimension): Story details (time, scene, characters, actions, etc.) manually selected by the user before triggering the event; Streamer-fan interaction information (streamer-fan interaction dimensions): user's follow time, user's donation amount to the streamer, user's time of joining the fan club, user's fan club level; 2) Model Special Effects Output: Generate the desired effects based on existing information. Scene section: Location: Combining the current live stream setting with the user's chosen setting; Atmosphere: Based on the current mood and comments in the live stream (in real time); Time section: Time point: Combined with the current live broadcast time (afternoon / morning); Timeline: It consists of past memories / present scenes / traveling to the future; Main characters: User profile: A profile is generated by combining the user's city, occupation, level, etc. Character actions: Generate actions (dancing, hugging) based on the user-selected storyline; Supporting characters: Character profile: Directly capture the live streamer's footage, combined with the streamer's revenue-generating ability, number of followers, city, etc.; Character actions: Generate corresponding actions based on the user's selected storyline (dance with the protagonist, hug the protagonist); Extras: Number of extras: based on the current number of viewers in the live stream; Extra's status: Generated based on the current atmosphere and emotions in the live stream comments; 3. After gift giving - the link after the gift video plays It supports users in viewing, saving, sharing, and forwarding. It supports synchronizing the generated short videos with other short video platforms and adding challenge topics (such as #MyCrossDimensionalEncounterWithTheStreamer). Supports secondary modifications to short film details (location, character appearance, encounter scenes); Template-based editing: Provides a library of preset scenes / actions that users can drag and drop to adjust. AI-assisted redesign: Input a text description (such as "replace the beach with a snow-capped mountain"), and AI will automatically replace the background.

[0164] This embodiment generates personalized "memory fragments" short films by combining the user's historical interactions with the streamer (such as tipping records and follow duration) with the storyline (encounter scene, actions, etc.) manually selected by the user. This allows virtual gifts to carry personalized narratives and enhance the depth of emotional expression. Through multi-dimensional data intelligent fusion (streamer's live broadcast screen, user attributes, and real-time atmosphere of the live broadcast room), it automatically generates character actions, extras' status, and background atmosphere that match the scene. The "fragmented story linking" mechanism (single gifting generates fragments, and multiple / multiple gifting sessions piece together a complete story) promotes fan collaboration, enhances live broadcast room participation and retention, and provides a material library for secondary dissemination (saving, modifying, and sharing).

[0165] It should be noted that any of the methods described above in this embodiment can be combined based on the actual implementation situation and have corresponding beneficial effects, which will not be elaborated here.

[0166] Figure 10 This is a block diagram illustrating a live interactive device according to an exemplary embodiment. (Refer to...) Figure 10 The device includes: The first display unit 1010 is configured to display at least one candidate video identifier in the virtual resource panel corresponding to the first viewer account in the live broadcast room. The second display unit 1020 is configured to execute a resource gifting instruction triggered by the first viewer account based on a target video identifier and display a first video; the target video identifier is any one of the at least one candidate video identifiers, the first video is the gifted video corresponding to the target video identifier, the first video is generated based on the first historical interaction information between the first viewer account and the anchor account, and the anchor account is the live broadcast initiating account corresponding to the live broadcast room.

[0167] In one exemplary embodiment, the first video is obtained by performing video generation processing on the first historical interaction information using an artificial intelligence model.

[0168] In one exemplary embodiment, the apparatus further includes a fused video display unit configured to perform: When the streamer's account receives multiple gifted videos, a merged video is displayed; the merged video is obtained by merging the multiple gifted videos; the multiple gifted videos are videos gifted to the streamer's account within a preset time period, or a preset number of videos that are continuously gifted to the streamer's account.

[0169] In one exemplary embodiment, the plurality of gifted videos are videos gifted by the first viewer's account; The fused video display unit is configured to perform: When the first viewer account continuously sends the multiple gifted videos to the streamer account, the merged video is displayed.

[0170] In an exemplary embodiment, the plurality of gifted videos are videos gifted by the first viewer account and the second viewer account, wherein the second viewer account is at least one viewer account other than the first viewer account among the viewer accounts corresponding to the live broadcast room; The fused video display unit is configured to perform: When the first viewer account and the second viewer account continuously send the multiple gifted videos to the streamer account, the fused video is displayed; the gifted video sent by the second viewer account is generated based on the second historical interaction information between the second viewer account and the streamer account.

[0171] In one exemplary embodiment, the first video presents a preset story corresponding to the first historical interaction information; The device further includes a first recommended object display unit, configured to perform: If a story element matching the first recommended object exists in the preset story, the first recommended object will be displayed during the display of the first video.

[0172] In an exemplary embodiment, the first recommendation object display unit is configured to perform: The first recommended object and its recommendation entry point are displayed during the presentation of the first video.

[0173] In one exemplary embodiment, the second display unit is configured to perform: The first video displays a preset story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0174] In one exemplary embodiment, the apparatus further includes a video publishing unit configured to perform: When the first video is displayed, in response to a sharing instruction for the first video, the first video is published on the associated content publishing platform.

[0175] In one exemplary embodiment, the apparatus further includes a video editing unit configured to perform: When the first video is displayed, in response to the editing instruction on the first video, an edited first video is generated; the edited first video is generated by adjusting the first video using a preset template, and / or the edited first video is generated by processing the first video based on target adjustment prompts using an artificial intelligence model.

[0176] In one exemplary embodiment, the apparatus further includes: The guidance information display unit is configured to display custom guidance information; the custom guidance information is used to guide the creation of a video to be gifted to the streamer's account. The custom page display unit is configured to execute a video custom instruction triggered by the first viewer account based on the custom guidance information and display a custom page; the custom page includes at least one story element configuration item. The second video generation unit is configured to perform an information configuration operation in response to the first viewer account on a target configuration item to obtain a second video; the target configuration item is at least one of the at least one story element configuration items, and the second video is generated based on the first historical interaction information and the target story element, the target story element being determined based on the information configuration operation on the target configuration item.

[0177] In one exemplary embodiment, the apparatus further includes a third display unit configured to perform: In response to the resource donation instruction triggered by the first viewer account based on the second video, the second video is displayed; the first historical interaction information in the second video is presented according to the storyline corresponding to the target story element.

[0178] In one exemplary embodiment, the second video is obtained by performing information fusion processing on the first historical interaction information and the target story element through an artificial intelligence model.

[0179] In one exemplary embodiment, the target story element includes a first character and a second character, wherein the first character is the character corresponding to the first viewer account, and the second character is the character corresponding to the broadcaster account; The third display unit is configured to execute: The second video displays the first historical interaction information performed by the first character and the second character, as well as the target story obtained by fusing the target story elements.

[0180] In one exemplary embodiment, the second video is generated based on the first historical interaction information, the target story element, and the real-time live streaming information of the live streaming room.

[0181] In one exemplary embodiment, the real-time live streaming information includes real-time audience information for the live streaming room; The third display unit is configured to execute: The second video displays the first historical interaction information jointly performed by the first character, the second character, and the third character, as well as the target story obtained by fusing the target story elements; the third character is generated based on the real-time audience information of the live broadcast room, and the third character is used to assist the first character and the second character in performing the story.

[0182] In one exemplary embodiment, the real-time audience information of the live stream includes the number of viewers in the live stream and the live stream comments in the live stream; The number of third-person characters in the first video is related to the number of viewers, and the status of the third-person characters is obtained by performing sentiment analysis on the live stream comments.

[0183] In one exemplary embodiment, the real-time live streaming information further includes the live stream footage from the live streaming room; In the second video, the second person is presented as the target person; the target person is the image of the anchor obtained from the live broadcast.

[0184] In one exemplary embodiment, the target story element further includes at least one of a first action corresponding to the first character and a second action corresponding to the second character; The second video presents at least one of the following: The first character performs the first action while performing the target story; The second character performs the second action while performing the target story.

[0185] In one exemplary embodiment, the apparatus further includes a second recommended object display unit, configured to perform: If the story elements of the target story match the second recommended object, the second recommended object is displayed during the presentation of the second video.

[0186] In one exemplary embodiment, the second recommendation object display unit is configured to perform: The second recommended object and its recommendation entry point are displayed during the presentation of the second video.

[0187] In one exemplary embodiment, displaying the second video includes: The second video displays the target story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

[0188] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0189] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform any of the methods described above.

[0190] In an exemplary embodiment, a computer program product is also provided, the computer program product including a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from the readable storage medium and executes the computer program, causing the device to perform any of the methods described above.

[0191] Figure 11 This is a block diagram illustrating an electronic device for live interactive streaming according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 11 As shown, the electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a live interactive method. Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the electronic device to which the present disclosure is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0192] Figure 12 This is a block diagram illustrating an electronic device for live interactive broadcasting according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 12As shown, the device may include an RF (Radio Frequency) circuit 1210, a memory 1220 including one or more computer-readable storage media, an input unit 1230, a display unit 1240, a sensor 1250, an audio circuit 1260, a WiFi (Wireless Fidelity) module 1270, a processor 1280 including one or more processing cores, and a power supply 1290, among other components. Those skilled in the art will understand that... Figure 12 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: RF circuit 1210 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and hands it over to one or more processors 1280 for processing; additionally, it transmits uplink data to the base station. Typically, RF circuit 1210 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. Furthermore, RF circuit 1210 can also communicate wirelessly with networks and other terminals. Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0193] The memory 1220 can be used to store software programs and modules. The processor 1280 executes various functional applications and data processing by running the software programs and modules stored in the memory 1220. The memory 1220 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for the functions, etc.; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 1220 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1220 may also include a memory controller to provide access to the memory 1220 by the processor 1280 and the input unit 1230.

[0194] The input unit 1230 can be used to receive input numerical or character information, and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. Specifically, the input unit 1230 may include a touch-sensitive surface 1231 and other input devices 1232. The touch-sensitive surface 1231, also known as a touch display screen or touchpad, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch-sensitive surface 1231), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface 1231 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 1280, and can receive and execute commands from the processor 1280. In addition, the touch-sensitive surface 1231 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. Besides the touch-sensitive surface 1231, the input unit 1230 may also include other input devices 1232. Specifically, other input devices 1232 may include, but are not limited to, one or more of the following: a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick. The display unit 1240 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the terminal. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. The display unit 1240 may include a display panel 1241, which may optionally be configured as an LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or similar display panel 1241. Further, a touch-sensitive surface 1231 may cover the display panel 1241. When the touch-sensitive surface 1231 detects a touch operation on or near it, it transmits the information to the processor 1280 to determine the type of touch event. Subsequently, the processor 1280 provides corresponding visual output on the display panel 1241 according to the type of touch event. The touch-sensitive surface 1231 and the display panel 1241 can be two independent components to implement input and output functions. However, in some embodiments, the touch-sensitive surface 1231 and the display panel 1241 can be integrated to achieve both input and output functions.

[0195] The terminal may also include at least one sensor 1250, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 1241 according to the ambient light level, and the proximity sensor can turn off the display panel 1241 and / or the backlight when the terminal is moved to the ear. As a type of motion sensor, a gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that identify the terminal's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, tapping), etc. Other sensors that may be configured on the terminal, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0196] Audio circuitry 1260, speaker 1261, and microphone 1262 provide an audio interface between the user and the terminal. Audio circuitry 1260 converts received audio data into electrical signals, which are then transmitted to speaker 1261, where they are converted into sound signals for output. Conversely, microphone 1262 converts collected sound signals into electrical signals, which are received by audio circuitry 1260, converted back into audio data, and then processed by processor 1280 before being transmitted via RF circuitry 1210 to, for example, another terminal, or output to memory 1220 for further processing. Audio circuitry 1260 may also include an earphone jack to facilitate communication between a peripheral headset and the terminal.

[0197] WiFi is a short-range wireless transmission technology. This terminal, through the WiFi module 1270, can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 12 WiFi module 1270 is shown, but it is understood that it is not an essential component of the terminal and can be omitted as needed without changing the nature of the invention.

[0198] The processor 1280 is the control center of the terminal, connecting various parts of the terminal through various interfaces and lines. It executes software programs and / or modules stored in the memory 1220, and calls data stored in the memory 1220 to perform various functions and process data, thereby enabling overall monitoring of the terminal. Optionally, the processor 1280 may include one or more processing cores; preferably, the processor 1280 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1280.

[0199] The terminal also includes a power supply 1290 (such as a battery) to power various components. Preferably, the power supply can be logically connected to the processor 1280 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 1290 may also include one or more DC or AC power supplies, a recharging system, a power fault detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0200] Although not shown, the terminal may also include a camera, Bluetooth module, etc., which will not be described in detail here. Specifically, in this embodiment, the display unit of the terminal is a touch screen display, and the terminal also includes a memory and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors of the instructions in the method embodiment of the present invention.

[0201] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0202] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A live streaming interactive method, characterized in that, The method includes: At least one candidate video identifier is displayed in the virtual resource panel corresponding to the first viewer's account in the live broadcast room; In response to a resource donation instruction triggered by the first viewer account based on a target video identifier, a first video is displayed; the target video identifier is any one of the at least one candidate video identifiers, the first video is the donation video corresponding to the target video identifier, the first video is generated based on the first historical interaction information between the first viewer account and the broadcaster account, and the broadcaster account is the live broadcast initiating account corresponding to the live broadcast room.

2. The method according to claim 1, characterized in that, The first video is obtained by using an artificial intelligence model to process the first historical interaction information into a video.

3. The method according to claim 1, characterized in that, The method further includes: When the streamer's account receives multiple gifted videos, a merged video is displayed; the merged video is obtained by merging the multiple gifted videos; the multiple gifted videos are videos gifted to the streamer's account within a preset time period, or a preset number of videos that are continuously gifted to the streamer's account.

4. The method according to claim 3, characterized in that, The multiple gifted videos are videos gifted by the first viewer's account; When the streamer's account receives multiple gifted videos, the merged video is displayed, including: When the first viewer account continuously sends the multiple gifted videos to the streamer account, the merged video is displayed.

5. The method according to claim 3, characterized in that, The multiple gifted videos are videos gifted by the first viewer account and the second viewer account, where the second viewer account is at least one viewer account other than the first viewer account among the viewer accounts corresponding to the live broadcast room. When the streamer's account receives multiple gifted videos, the merged video is displayed, including: When the first viewer account and the second viewer account continuously send the multiple gifted videos to the streamer account, the merged video is displayed; The gifted video from the second viewer account is generated based on the second historical interaction information between the second viewer account and the streamer account.

6. The method according to claim 1, characterized in that, The first video presents a preset story corresponding to the first historical interaction information; The method further includes: If a story element matching the first recommended object exists in the preset story, the first recommended object will be displayed during the display of the first video.

7. The method according to claim 6, characterized in that, The step of displaying the first recommended object during the display of the first video includes: The first recommended object and its recommendation entry point are displayed during the presentation of the first video.

8. The method according to claim 1, characterized in that, The first video shown includes: The first video displays a preset story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

9. The method according to claim 1, characterized in that, The method further includes: When the first video is displayed, in response to a sharing instruction for the first video, the first video is published on the associated content publishing platform.

10. The method according to claim 1, characterized in that, The method further includes: When the first video is displayed, in response to the editing instruction on the first video, an edited first video is generated; the edited first video is generated by adjusting the first video using a preset template, and / or the edited first video is generated by processing the first video based on target adjustment prompts using an artificial intelligence model.

11. The method according to claim 1, characterized in that, The method further includes: Display custom guidance information; the custom guidance information is used to guide the creation of a video to be gifted to the streamer's account; In response to a video customization instruction triggered by the first viewer account based on the customized guidance information, a custom page is displayed; the custom page includes at least one story element configuration item. In response to the first viewer account's information configuration operation on the target configuration item, a second video is obtained; the target configuration item is at least one of the at least one story element configuration items, and the second video is generated based on the first historical interaction information and the target story element, which is determined based on the information configuration operation on the target configuration item.

12. The method according to claim 11, characterized in that, After obtaining the second video in response to the information configuration operation of the target configuration item, the method further includes: In response to the resource donation instruction triggered by the first viewer account based on the second video, the second video is displayed; the first historical interaction information in the second video is presented according to the storyline corresponding to the target story element.

13. The method according to claim 11, characterized in that, The second video is obtained by using an artificial intelligence model to fuse the first historical interaction information and the target story elements.

14. The method according to any one of claims 11-13, characterized in that, The target story elements include a first character and a second character, where the first character is the character corresponding to the first viewer account and the second character is the character corresponding to the streamer account. The display of the second video includes: The second video displays the first historical interaction information performed by the first character and the second character, as well as the target story obtained by fusing the target story elements.

15. The method according to claim 14, characterized in that, The second video is generated based on the first historical interaction information, the target story element, and the real-time live streaming information of the live streaming room.

16. The method according to claim 15, characterized in that, The real-time live streaming information includes real-time audience information in the live streaming room; The display of the second video includes: The second video displays the first historical interaction information performed by the first character, the second character, and the third character, as well as the target story obtained by fusing the target story elements; the third character is generated based on the real-time audience information of the live broadcast room, and the third character is used to assist the first character and the second character in performing the story.

17. The method according to claim 16, characterized in that, The real-time audience information in the live stream includes the number of viewers in the live stream and the live stream comments. The number of third-person characters in the first video is related to the number of viewers, and the status of the third-person characters is obtained by performing sentiment analysis on the live stream comments.

18. The method according to claim 15, characterized in that, The real-time live streaming information also includes the live stream footage from the live streaming room. In the second video, the second person is presented as the target person; the target person is the image of the anchor obtained from the live broadcast.

19. The method according to claim 14, characterized in that, The target story element also includes at least one of the first action corresponding to the first character and the second action corresponding to the second character; The second video presents at least one of the following: The first character performs the first action while performing the target story; The second character performs the second action while performing the target story.

20. The method according to claim 14, characterized in that, The method further includes: If the story elements of the target story match the second recommended object, the second recommended object is displayed during the presentation of the second video.

21. The method according to claim 20, characterized in that, The display of the second recommended object during the presentation of the second video includes: The second recommended object and its recommendation entry point are displayed during the presentation of the second video.

22. The method according to claim 12, characterized in that, The display of the second video includes: The second video displays the target story obtained by fusing the first historical interaction information and related interaction information; The associated interactive information refers to the interactive information of the first viewer account on the associated platform.

23. A live interactive device, characterized in that, include: The first display unit is configured to display at least one candidate video identifier in the virtual resource panel corresponding to the first viewer account in the live broadcast room. The second display unit is configured to execute a resource gifting instruction triggered by the first viewer account based on the target video identifier and display the first video; The target video identifier is any one of the at least one candidate video identifiers, the first video is the gift video corresponding to the target video identifier, the first video is generated based on the first historical interaction information between the first viewer account and the anchor account, and the anchor account is the live broadcast initiating account corresponding to the live broadcast room.

24. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the live interactive method as described in any one of claims 1 to 22.

25. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is enabled to perform the live interactive method as described in any one of claims 1 to 22.

26. A computer program product, characterized in that, The computer program product includes a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from and executes the computer program, causing the device to perform the live interactive method as described in any one of claims 1 to 22.

Images