Video generation method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a video generation method and device, electronic equipment and a medium, and relates to the technical field of artificial intelligence. Determining an interaction text generated when the first terminal and the second terminal play the first interaction video clip; based on the interaction key information of the interaction text, generating a second interaction video clip containing an interaction video transition special effect; and sending the second interactive video clip to the first terminal and the second terminal when it is determined that the playing of the first interactive video clip is completed, so that the first terminal and the second terminal play the second interactive video clip. When the first terminal and the second terminal establish the connection, the video clip is generated based on the real-time interaction content, and the video clip generated in real time can be smoothly joined and played, so that real-time content perception and dynamic video generation capabilities are realized, and the visual experience of a user is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, specifically to a video generation method, apparatus, electronic device, and medium. Background Technology

[0002] In current related technologies, when a user initiates a connection request (such as a call request) using a terminal, the video content displayed on the user terminal is mostly fixed video content that the user has preset or selected. Moreover, when the call connection is successfully established, the video being played will be interrupted immediately, and the terminal usually displays a standard call interface or static image during the call.

[0003] However, when establishing a call connection, the relevant technology terminals cannot dynamically adjust the video according to the specific context of the current call (such as the relationship between the caller and the called user, the call intent, etc.), lacking personalization and context relevance, resulting in a relatively monotonous visual experience for users during the call. Summary of the Invention

[0004] This application provides a video generation method, apparatus, electronic device, and medium to solve the problem in related technologies where video playback is interrupted when a terminal establishes a connection and video content related to the current context cannot be dynamically generated according to the specific scene.

[0005] In a first aspect, embodiments of this application provide a video generation method, the method comprising: determining interactive text generated by the first terminal and the second terminal when playing a first interactive video segment, given that a second terminal is determined and a connection is established with a first terminal; generating a second interactive video segment containing interactive video transition effects based on interactive key information of the interactive text; and sending the second interactive video segment to the first terminal and the second terminal when it is determined that the first interactive video segment has finished playing, so that the first terminal and the second terminal can play the second interactive video segment.

[0006] In some embodiments, when a second terminal is determined and a connection is established with the first terminal, determining the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment includes: when it is determined that the first terminal sends a connection request to the second terminal, generating an initial video segment based on the relationship characteristics between the first terminal and the second terminal, and sending the initial video segment to the first terminal; when it is determined that the second terminal is determined and a connection is established with the first terminal, determining the first interactive video segment and the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment based on the initial video segment.

[0007] In some embodiments, when a second terminal is determined and a connection is established with the first terminal, determining a first interactive video segment and interactive text generated by the first and second terminals when playing the first interactive video segment based on an initial video segment includes: when a connection is determined between the first and second terminals, determining the video segments already played by the first terminal; determining unplayed video segments in the initial video segment based on the initial video segment and the played video segments; identifying the unplayed video segments as the first interactive video segment and sending the first interactive video segment to the second terminal so that the first and second terminals can play the first interactive video segment; acquiring interactive audio of the first and second terminals when playing the first interactive video segment; and recognizing the interactive audio to obtain the interactive text corresponding to the interactive audio.

[0008] In some embodiments, when it is determined that the first terminal sends a connection request to the second terminal, generating an initial video segment based on the relationship characteristics between the first terminal and the second terminal, and sending the initial video segment to the first terminal includes: determining the first terminal identifier of the first terminal and the second terminal identifier of the second terminal based on the first terminal identifier and the second terminal identifier; obtaining relationship data between the first terminal and the second terminal based on the first terminal identifier and the second terminal identifier; determining the relationship characteristics between the first terminal and the second terminal based on the relationship data; generating an initial video segment matching the relationship characteristics based on the relationship characteristics and a preset playback duration, and sending the initial video segment to the first terminal so that the first terminal can play the initial video segment.

[0009] In some embodiments, upon determining that the first interactive video segment has finished playing, a second interactive video segment is sent to a first terminal and a second terminal. The method then includes: determining subsequent interactive text generated by the first terminal and the second terminal while playing the second interactive video segment; determining whether interaction termination information exists in the subsequent interactive text based on subsequent interaction key information; if interaction termination information is determined to exist in the subsequent interactive text, generating a termination video segment containing a termination video transition effect based on the interaction key information, subsequent interaction key information, and the relationship features between the first terminal and the second terminal; upon determining that the second interactive video segment has finished playing, sending the termination video segment to the first terminal and the second terminal; and upon determining that the termination video segment has finished playing, sending a stop playback command to the first terminal and the second terminal.

[0010] In some embodiments, generating a second interactive video clip containing interactive video transition effects based on interactive key information from interactive text includes: extracting interactive key information from the interactive text; determining the video playback duration based on the semantic unit length or topic duration in the interactive key information; integrating the interactive key information, the video playback duration, and the first interactive video information of the first interactive video clip based on a preset generated prompt template to obtain first generated prompt information; and generating a second interactive video clip containing interactive video transition effects based on the first generated prompt information.

[0011] Secondly, embodiments of this application provide a video generation apparatus, the apparatus comprising: The determining unit is used to determine the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment, in the case of determining the second terminal and establishing a connection with the first terminal; The generation unit is used to generate a second interactive video clip containing interactive video transition effects based on the interactive key information of the interactive text. The playback unit is configured to send a second interactive video segment to a first terminal and a second terminal after determining that the first interactive video segment has finished playing, so that the first terminal and the second terminal can play the second interactive video segment.

[0012] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor, wherein, when the processor runs the computer program, it performs the method described in any embodiment of the first aspect.

[0013] Fourthly, embodiments of this application provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in any embodiment of the first aspect.

[0014] Fifthly, embodiments of this application provide a computer program product including a computer program that, when executed by a processor, performs the method described in any embodiment of the first aspect.

[0015] This application provides a video generation method that, upon determining a second terminal and establishing a connection with a first terminal, determines the interactive text generated by the first and second terminals during the playback of a first interactive video segment; based on the key interactive information in the interactive text, generates a second interactive video segment including interactive video transition effects; and upon determining that the first interactive video segment has finished playing, sends the second interactive video segment to both the first and second terminals, enabling them to play the second interactive video segment. This method achieves real-time content perception and dynamic video generation capabilities, enhancing the user's visual experience, by determining that the first and second terminals, when connected, can generate video segments based on their real-time interactive information, and by allowing a smooth transition between the first and second terminals when the current video segment finishes playing.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are merely embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort, and this application can be applied to other similar scenarios based on the provided drawings.

[0018] Figure 1 A flowchart illustrating a video generation method provided in this application embodiment; Figure 2 A flowchart illustrating the second video generation method provided in this application embodiment; Figure 3 An exemplary overall flowchart for video generation is provided for embodiments of this application; Figure 4 A flowchart illustrating an exemplary connection request initiation and initial video generation is provided for embodiments of this application. Figure 5 A flowchart illustrating an exemplary connection establishment and synchronized video playback is provided for embodiments of this application. Figure 6 A flowchart illustrating real-time content processing and subsequent video generation in an exemplary connection provided in this application embodiment; Figure 7 A flowchart illustrating an exemplary connection termination preprocessing procedure provided in this application embodiment; Figure 8 This is a schematic diagram of the structure of a video generation device provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. The described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] It should be noted that the terms "system," "device," "unit," and / or "module" used in this application are methods of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they can be replaced by other expressions.

[0021] Hereinafter, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include one or more of that feature.

[0022] Currently, in related technologies, when a user initiates a connection request (such as a call request) using a terminal, the video content displayed on the user terminal is mostly based on fixed static video materials that the user has pre-set or selected. Moreover, once the connection between the two terminals is successfully established, the video being played is immediately interrupted, and the terminal interface usually switches to a standard call interface or static image during the connection establishment process.

[0023] However, when establishing a call connection on the terminal, the relevant technologies cannot dynamically adjust the video according to the specific scenario of the current call (such as the relationship between the caller and the called user, the real-time call context, etc.), lacking personalization and context relevance, resulting in a relatively monotonous visual experience for users during the call.

[0024] To address the problems in existing technologies, this application proposes a video generation method. When a connection is established between a second terminal and a first terminal, a second interactive video segment, including interactive video transition effects, is generated based on the interactive text generated when the first and second terminals play a first interactive video segment. This second interactive video segment is then played back on both terminals after the first interactive video segment has finished playing. This ensures that when the first and second terminals are connected, the video playing on the first terminal is not interrupted and is pushed to the second terminal for synchronous playback, thus achieving a continuous visual experience with cross-stage video playback and synchronous sharing between the terminals. Furthermore, when the current video finishes playing, the first and second terminals can smoothly transition to playing subsequent video segments generated based on real-time interactive content between the terminals, thereby achieving real-time content perception and dynamic video generation capabilities and enhancing the user's visual experience.

[0025] The following section provides a detailed description of a video generation method provided in this application, with reference to the accompanying drawings.

[0026] Figure 1 A flowchart of a video generation method provided in an embodiment of this application is shown. Figure 1 As shown, the video generation method includes steps 101-103.

[0027] Step 101: If the second terminal is determined and a connection is established with the first terminal, determine the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment.

[0028] In the embodiments of this application, the video may specifically be a video ringback tone; the first terminal may be the calling terminal; the second terminal may be the called terminal; the establishment of a connection between the second terminal and the first terminal means that after the calling terminal (first terminal) initiates a call request, the called terminal (second terminal) completes the response operation, and the call link is formally established (i.e., switching from "call waiting state" to "call state").

[0029] The first interactive video segment is a video segment that the calling terminal has not yet finished playing before the called terminal successfully establishes a connection with the called terminal. After the called terminal and the calling terminal successfully establish a call connection, the first interactive video segment can continue to be displayed on the interfaces of the calling terminal and the called terminal (such as as a call interface background or a specific window). Users can turn the display on / off or switch the display style through the terminal settings.

[0030] Interactive text is structured text data generated by voice interaction between the users of the first terminal and the second terminal during the playback of the first interactive video segment (i.e., during the period when the first terminal and the second terminal establish a connection), and formed after technical processing.

[0031] In some examples, during a call between the calling and called users, with the user's authorization, the video ringback tone platform can capture the user's interactive voice in real time. The platform then sends this voice to a real-time voice processing module, which processes and analyzes it in real time, converting it into interactive text and extracting key information. The real-time voice processing module then feeds this key information back to the video ringback tone platform.

[0032] Step 102: Based on the key interactive information in the interactive text, generate a second interactive video clip containing interactive video transition effects.

[0033] In the embodiments of this application, interactive video transition effects refer to brief transition effects (such as fade, blur deformation, theme element evolution, etc.) that are related to the logic of changes in interactive video content, in order to smooth the visual connection. Interactive video transition effects can be generated by AIGC (Artificial Intelligence Generated Content) video generation models.

[0034] Key interactive information, including user intent and topic keywords, determines the theme, style, and visual elements of the second interactive video.

[0035] In some examples, after receiving key interactive information from the real-time voice processing module, the video ringback tone playback platform uses this information as core input to drive the AIGC video generation model to create a second interactive video clip highly relevant to the current conversation. For instance, when the user's conversation topic is mountain climbing, the video content generated by the AIGC video generation model might be a dynamic scene of mountains, forests, or outdoor activities. Furthermore, the generated second interactive video clip incorporates matching interactive video transition effects.

[0036] Step 103: After determining that the first interactive video segment has finished playing, the second interactive video segment is sent to the first terminal and the second terminal so that the first terminal and the second terminal can play the second interactive video segment.

[0037] In the embodiments of this application, the video ringback tone platform continuously monitors the playback progress of interactive video segments on both terminals. When it predicts or detects that the current interactive video segment is about to finish playing, it initiates the process of pushing the next interactive video segment.

[0038] In some examples, the video ringback tone platform simultaneously sends a pre-generated second interactive video clip (including its built-in transition effects) to both the first and second terminals. The terminal player seamlessly begins playing the second interactive video clip the instant the first interactive video clip ends. The embedded transition effects further ensure the smoothness and naturalness of the visual transition, providing users with a continuous and uninterrupted dynamic visual experience.

[0039] In summary, according to the video generation method proposed in this application, after determining the second terminal and establishing a connection with the first terminal, the interactive text generated by the first and second terminals when playing a first interactive video segment is determined; based on the key interactive information of the interactive text, a second interactive video segment including interactive video transition effects is generated; after determining that the first interactive video segment has finished playing, the second interactive video segment is sent to the first and second terminals so that the first and second terminals can play the second interactive video segment. This enables real-time playback of video segments generated based on inter-terminal interactive content when a user establishes a connection using a terminal, and allows for smooth transitions between video segments, thereby achieving real-time content perception and dynamic video generation capabilities, and improving the user's visual experience.

[0040] based on Figure 1 The embodiment shown, Figure 2 A flowchart of the second video generation method is further shown. Figure 2 based on Figure 1 The illustrated embodiment further defines steps 101, 102, and 103. Figure 2 In the illustrated embodiment, step 101 includes steps 201 and 202, step 102 includes steps 203, 204, 205, and 206, and step 103 includes step 207. For example... Figure 2 As shown, the method includes the following steps: Step 201: If it is determined that the first terminal sends a connection request to the second terminal, an initial video segment is generated based on the relationship characteristics between the first terminal and the second terminal, and the initial video segment is sent to the first terminal.

[0041] In the embodiments of this application, the relationship characteristics between the first terminal and the second terminal refer to the relationship type between the calling user and the called user (e.g., "close friends", "family", "ordinary colleagues", "first contact" etc.) or the degree of intimacy (e.g., "extremely high", "high", "medium", "low" etc.). The first terminal sending a connection request to the second terminal refers to the calling user terminal initiating a call request to the called user terminal. When the call request is initiated, the user relationship analysis module performs relationship analysis on the user based on the user terminal's identification information, generates the user's relationship characteristics, and then the AIGC video generation model generates an initial video clip content that conforms to the atmosphere, style, and theme of the relationship based on the relationship characteristics, and sends it to the video ringback tone platform. The video ringback tone platform pushes the initial video clip to the calling terminal, and the calling terminal starts playing the initial video clip during the call waiting period.

[0042] In some examples, when it is determined that the first terminal sends a connection request to the second terminal, the video ringback tone platform first obtains the first terminal identifier of the first terminal and the second terminal identifier of the second terminal (such as phone number, terminal device number, or in-app account, etc.) through the communication operator's network interface; then, based on the above terminal identifiers, it queries the relationship data between the caller and the called party from multi-dimensional data sources (data collection must meet privacy compliance requirements, and only data within the scope authorized by the user is obtained), specifically including: 1) System data from telecommunications operators / service providers (core source), including: User-defined group labels: Groups set by users for others in their contact management functions, such as "Family," "Friends," "Colleagues," "VIP Customers," "Blacklist," etc. These are the most direct indicators of relationship. Related information in user profiles: for example, family package members, corporate group network members, etc., which directly indicate specific relationships; Communication behavior data: The number of calls, total call duration, and average call duration between A and B within a specific time period (e.g., the past month or the past three months). Frequent and long-duration calls usually indicate a closer relationship; SMS / MMS interaction frequency: The number of SMS / MMS messages sent and received between A and B; Call patterns: For example, whether there are more one-way calls or a more balanced two-way call pattern, and the distribution of call times (working hours, non-working hours), etc. Service subscription data: Subscription status for shared services, such as shared data packages and family numbers. Specific relationship products, such as communication products offered by operators targeting couples or families.

[0043] 2) User-authorized data from third-party applications / social platforms (optional, enhanced sources, requiring explicit user authorization and privacy compliance), including: Social network association: If a user authorizes the connection to their social network account (such as WeChat, QQ, Weibo, etc.), information such as whether the two parties in the call are friends, their following relationship, the number of mutual friends, and the frequency of interaction (likes, comments) can be obtained; Grouping information within social media platforms: such as tags for WeChat friends, groups for QQ friends, etc. Collaboration platform data: For enterprise users, refer to the enterprise address book, project team member list, and organizational structure information (such as superiors and subordinates, and colleagues in the same department). 3) Data on user terminal devices (optional, requiring explicit user authorization and privacy compliance), including: Local contact information: The contact's nickname, group, associated social accounts, etc. in the terminal's Contacts app; Calendar / Schedule Sharing Information: Whether you have shared meetings, appointments, etc.; 4) User profiling and interest tagging systems (usually built by operators or large platforms), including: Individual user profile: Based on data such as user communication behavior, business usage, geographical location (authorized), and application usage (authorized), tags are generated for each user, such as age group, gender, occupational orientation, consumption level, and interests. Relationship inference: By comparing the profile tags of the caller and the called user, the similarity, complementarity, or specific associations are analyzed to help determine the relationship. For example, highly overlapping interest tags may indicate a friendship, and frequently overlapping geographical locations with regular timing may indicate family or colleagues.

[0044] 5) Real-time context information (available when the call occurs), including: Call time: weekday daytime, weekday evening, weekend, etc. Calls at different times may correspond to different relationship dominance; Approximate geographical location (if available and authorized): For example, whether the two parties in the call are in the same city or the same office area.

[0045] Next, the aforementioned relationship data is sent to the user relationship analysis module to determine the relationship characteristics between the first terminal and the second terminal. Specifically, the user relationship analysis module first cleans, formats, and performs necessary preprocessing on the received relationship data (e.g., converting call duration into standardized units, quantifying social interaction frequency, etc.); then, it extracts key features from the preprocessed data and quantifies or classifies these features, for example, into the following categories: Communication behavior characteristics: total number of recent calls, total duration, average duration per call, call direction ratio, number of text messages, and common call times (working / non-working). User-defined features: group tags set by the called user for the calling user (such as "family" or "colleague"), and keywords in the nickname (such as "boss" or "wife"). Social network characteristics: whether they are direct friends, number of mutual friends, interaction index (calculated by combining likes, comments, etc.), and group information on the social platform; Profile and Interest Characteristics: The overlap of profile tags between the two parties and the commonality score in specific interest areas; Contextual characteristics: whether the current call time is a holiday, whether the two parties are geographically close (if available), etc.

[0046] Finally, the user relationship analysis module uses one or more of the following methods to comprehensively determine relationship characteristics: 1) The rule-based inference engine defines a set of predefined rules. For example, IF (User A labels B as "family member" OR Family Package Member) THEN Relationship Feature = "Family Member". Rules can have priorities; for example, user-defined tags have higher priority than inferences based on behavioral data.

[0047] 2) Machine Learning-Based Classification Models (More Advanced Methods): A classification model (such as decision trees, neural networks, gradient boosting trees, etc.) is pre-trained using a large amount of labeled relationship data (e.g., relationships manually confirmed by users or verified through other means). The model's input is the aforementioned multi-dimensional key feature vectors. The goal of model training is to learn the mapping from the key feature vectors to specific relationship categories (e.g., "family," "friends," "colleagues," "business partners," "strangers," "potential harassment," etc.). During real-time analysis, the feature vectors of the calling and called users are input into the trained model, and the model outputs one or more most probable relationship categories and their confidence levels.

[0048] 3) Intimacy Calculation Based on Ratings and Thresholds: Different features are assigned different weights to calculate a comprehensive "intimacy score" or "relationship strength score." For example, call duration weight > SMS quantity weight. The score is compared with a preset threshold to classify different intimacy levels (e.g., extremely close, close, average, distant, stranger). These intimacy levels can be directly used as relationship features, or combined with other information to map to specific relationship categories.

[0049] The user relationship analysis module sends the analyzed relationship features to the video ringback tone platform. Finally, after receiving the relationship characteristics, the video ringback tone platform generates relationship prompts (including relationship category tags such as "family member" and "close friend", intimacy level such as "extremely high" and "medium", auxiliary relationship context information such as common interest tags or keywords, relationship establishment duration / stage, positive / negative relationship tendency, user profile and preference information, contextual information, target style such as "warm" and "lively"), and sets the video playback duration (a standard length can be preset (e.g., 10-15 seconds), or dynamically adjusted according to the depth of relationship analysis (e.g., the closer or more important the relationship, the longer the duration can be), ensuring that it can be played completely or mostly within the normal call connection waiting time). Then, it calls the preset AIGC video generation model (e.g., a text / concept to video model based on Transformer or diffusion model) to generate an initial video segment that matches the relationship characteristics (e.g., "close friend", "family member", "first contact", "important colleague"), and sends the initial video segment to the first terminal so that the first terminal can play the initial video segment during the call waiting period.

[0050] Step 202: After determining the second terminal and establishing a connection with the first terminal, based on the initial video segment, determine the first interactive video segment and the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment.

[0051] In the embodiments of this application, the first interactive video segment refers to the remaining unplayed segment of the initial video segment played by the first terminal during the connection request waiting period. In the event that the second terminal and the first terminal successfully establish a connection, the video segment played by the terminal not only remains uninterrupted but continues to play synchronously and continuously on both terminal screens.

[0052] In some examples, when the second terminal responds to the connection request, the call is established, the video ringback tone platform detects the change in call status, determines the played video segment of the initial video segment of the first terminal, and sends the unplayed video segment as the first interactive video segment to both the first and second terminals for synchronous playback.

[0053] During the interaction between the first terminal and the second terminal, the video ringback tone platform, after authorization by the user, collects the interactive audio between the first terminal and the second terminal in real time, and sends it to the real-time voice processing module to perform voice recognition on the interactive audio and convert the interactive audio into interactive text.

[0054] Step 203: Extract key interactive information from the interactive text.

[0055] In this embodiment, the application utilizes a real-time speech processing module to perform in-depth analysis of the interactive text, extracting key interactive information, including: keywords, topics, mentioned entities, emotional inclination (e.g., positive, negative, neutral), dialogue intent (e.g., asking, confirming, discussing, saying goodbye), dialogue rhythm, changes in speech rate, and important semantic unit boundaries or topic transition points. This information constitutes the real-time context for the generation of subsequent interactive video clips.

[0056] Step 204: Determine the video playback duration based on the semantic unit length or topic duration in the key interactive information.

[0057] In the embodiments of this application, the length of a semantic unit is quantified by the number of characters or the duration of the corresponding speech (for example, the text length of a semantic unit is 10-20 characters, and the corresponding speech duration is about 1-3 seconds), and the video playback duration is determined based on the length of the semantic unit. If there are multiple semantic units continuously surrounding the same topic in the interactive text (i.e., the topic duration is relatively long), the video playback duration is adjusted based on the total duration of the topic.

[0058] Specifically, this application can use a video ringback tone platform to intelligently control the video playback duration. To ensure the continuity of interactive video segment playback, the determination of the video playback duration will consider the following aspects: 1) The playback duration of each generated interactive video segment is dynamically determined based on the length of the semantic unit or the duration of the topic obtained from natural language analysis, so as to synchronize the rhythm of the interactive video segment with the rhythm of the dialogue between the two parties on the terminal. For example, if a semantic unit lasts for 5 seconds, the duration of the corresponding generated interactive video segment can be in the range of 4-6 seconds; 2) To ensure visual continuity and user acceptance, a user-friendly duration range is set (e.g., a minimum of 3 seconds and a maximum of 12 seconds). Even if the semantic unit is very short or very long, the generated segment length will be constrained within this range. This duration constraint can be adapted through content repetition, slow motion or speed-up (without affecting visual effects), or by adding or deleting content elements. 3) The video playback duration must also take into account the generation speed of the AIGC video generation model to ensure that generation and transmission are completed before the previous interactive video segment finishes playing. If the expected generation time is long, the duration can be appropriately shortened or a faster generation strategy can be adopted.

[0059] 4) Allows users to set their preferred average video clip duration and duration range.

[0060] Step 205: Based on the preset generated prompt template, integrate the key interactive information, video playback duration, and the first interactive video information of the first interactive video segment to obtain the first generated prompt information.

[0061] In the embodiments of this application, the preset generation prompt template is a structured and precise generation prompt template pre-built by the AIGC video generation model, used to organize and format the information input to the AIGC video generation model. The first interactive video information is the information of the currently playing video segment, including video style (such as "lively", "simple", "bright", which can be used to guide the style of generating the next video segment), visual continuity (such as feature vectors or low-resolution images of the last few frames of the video, which can be used to guide the starting state of the video generation model), and motion trend (if the first interactive video has an obvious motion trend, such as upward or expanding, it will be used as the starting motion reference for generating the next video).

[0062] Specifically, the AIGC video generation model integrates various input information from the video ringback tone platform, including key interactive information (such as keywords, themes, emotional tendencies, dialogue intentions, etc.), video playback duration (e.g., 8 seconds), and the first interactive video information, into a preset generation prompt template. After integration, it generates a rich and clear first generation prompt message, such as: "Generate a video of [video playback duration] seconds, with a style that continues the previous video clip, a theme about [core theme], an atmosphere of [emotional tendency], and elements such as [keywords]." Step 206: Based on the first generated prompt information, generate a second interactive video clip containing interactive video transition effects.

[0063] In the embodiments of this application, a transition effect that is highly relevant to the current dialogue and includes a smooth connection to the end of the first interactive video segment is generated based on the generated prompt information.

[0064] Specifically, the AIGC video generation model first processes the initial generated prompt information as follows: 1) First, the interactive text descriptions and semantic tags are parsed and converted into internal numerical representations (e.g., by mapping the text to a multimodal embedding space using a text encoder). Style instructions, visual continuity references, etc., are also encoded and incorporated into the model's conditional input; 2) For diffusion models, it typically starts with a sequence of randomly noisy images. At multiple time steps, the model iteratively removes noise, guided by encoded cues (core content, style, context). The challenge is to make the current image sequence resemble a scene like "friends hiking on a sunny weekend," while maintaining a "lively and simple" style and visually connecting it to the end of the previous segment.

[0065] For example, the model might prioritize generating visual primitives related to "mountain," "outdoors," and "sunshine," then combine them and give them dynamic effects and colors that evoke "excitement and positivity."

[0066] 3) The AIGC video generation model has the ability to process time series data, ensuring that the generated video frames have logical coherence and smooth dynamic changes, rather than a bunch of unrelated images; 4) Throughout the generation process, the style instructions of "lively, simple, and bright colors" will be continuously applied. Based on the training data and generation capabilities, specific visual elements will be rendered, such as stylized characters (representing friends), abstract or figurative mountains, dynamic clouds, and shining sunlight. 5) A video of a specified duration can be generated by controlling the number of time steps generated or the internal frame generation mechanism.

[0067] After completing the above processing, the AIGC video generation module can generate a second interactive video clip of a specified duration that includes interactive video transition effects, and then send the interactive video clip to the video ringback tone platform.

[0068] Step 207: After determining that the first interactive video segment has finished playing, the second interactive video segment is sent to the first terminal and the second terminal so that the first terminal and the second terminal can play the second interactive video segment.

[0069] In the embodiments of this application, the video ringback tone platform pushes the received second interactive video segment to the first terminal and the second terminal in real time, adds it to the playlist, and forms a visually coherent video stream driven by the AIGC video generation model that dynamically evolves with the call content, ensuring that the first terminal and the second terminal can seamlessly connect and continuously play the next interactive video segment after the current interactive video segment is played.

[0070] In some embodiments, after determining that the first interactive video segment has finished playing and sending the second interactive video segment to the first terminal and the second terminal, this application further includes: determining subsequent interactive text generated by the first terminal and the second terminal while playing the second interactive video segment; determining whether there is interaction termination information in the subsequent interactive text based on the subsequent interaction key information of the subsequent interactive text; if it is determined that there is interaction termination information in the subsequent interactive text, generating a termination video segment containing a termination video transition effect based on the interaction key information, the subsequent interaction key information, and the relationship features between the first terminal and the second terminal; sending the termination video segment to the first terminal and the second terminal when the second interactive video segment has finished playing; and sending a stop playback command to the first terminal and the second terminal when the termination video segment has finished playing.

[0071] In embodiments of this application, the interaction termination information may include termination keywords (such as words indicating the beginning and end of a call, such as "goodbye," "bye-bye," or "let's talk next time"), termination intent (such as the semantics of the interaction text being "agre to a time for subsequent communication" or "clearly end the current conversation"), and tone features (such as a slowed-down speech rate or a calm ending in the speech recognition result). If the subsequent interaction text contains at least one termination keyword or a clear termination intent, it is determined that interaction termination information exists, and the termination video clip generation process is triggered.

[0072] Specifically, the video ringback tone platform collects the interactive audio of the first and second terminals in real time and monitors the call status in real time. When it detects that either party intends to terminate the call, it sends a termination video segment generation request to the AIGC video generation model based on the last semantics before the end of the call, the overall emotional tone of the call, or the initial relationship. This generates a short, visually comfortable final video segment with video transition effects that has a summary, farewell, or relationship-related meaning. The duration of the termination video segment is usually set to a short, fixed, and visually acceptable length for the user (e.g., 3-5 seconds).

[0073] After the currently playing interactive video segment ends, a termination video segment will be sent to the first terminal and the second terminal for seamless playback. Once the termination video segment has finished playing, the first terminal and the second terminal will end the video playback process.

[0074] Optionally, if the subsequent interactive text contains an interaction termination message, the remaining interactive video segments will continue playing without generating a termination video segment. The video ringback tone platform first sends a stop playback command to the first and second terminals, and then stops the video playback process after the first and second terminals have finished playing the current interactive video segment.

[0075] To further explain the entire process of video generation in this application, please refer to [further details]. Figure 3 , Figure 3 This document provides an exemplary flowchart for video generation in accordance with embodiments of this application. It includes the following four stages: Phase One: Call initiation (corresponding to the connection request in this application) and initial ringback tone generation (corresponding to the initial video segment in this application). See [reference needed]. Figure 4 The flowchart shown below, illustrating an exemplary connection request initiation and initial video generation, includes the following four steps: Step 1, Initiate a call (call B): The calling terminal A (corresponding to the first terminal in this application) initiates a call request to the called terminal B (corresponding to the second terminal in this application); Step 2, request the generation of the initial ringback tone: refer to Figure 4In steps 2.1-2.6, the video ringback tone platform obtains the identification information of the calling terminal A and the called terminal B, and requests the user relationship analysis module to analyze the user relationship. The user relationship analysis module sends the analyzed relationship features to the video ringback tone platform. After receiving the relationship features, the video ringback tone platform prepares relationship prompt words and sets the initial video segment duration, inputs it into the AIGC video generation model to request the generation of the initial video segment, and the AIGC video generation model returns the generated initial video segment to the video ringback tone platform. Step 3: Push the initial ringback tone and start playing: Refer to... Figure 4 In steps 3.1-3.2, the video ringback tone platform pushes the initial video clip to the calling terminal A's terminal device, and the calling terminal A plays the initial video clip during the call waiting period.

[0076] Phase Two: Call Connection (corresponding to Connection Establishment in this application) and Synchronous Playback. (See also...) Figure 5 The flowchart shown is an example of a call connection and synchronous playback. The specific process is as follows: Step 4: Answer the call, establish the call, and continue playing the initial video clip without interruption: Refer to... Figure 5 In steps 4.1-4.4, when the called terminal B answers the call, the call is established. The video ringback tone platform detects the change in call status and immediately sends instructions to the calling terminal A and the called terminal B to continue playing the remaining segments of the initial video segment (i.e., the first interactive video segment).

[0077] Phase three involves real-time content processing during the call and a subsequent cycle for generating custom ringback tones. (Refer to...) Figure 6 The flowchart shown here illustrates an exemplary real-time content processing and subsequent video generation process during a call, comprising the following four steps: Step 5: The video ringback tone platform collects the voice stream between the calling terminal A and the called terminal B in real time: (Refer to...) Figure 6 In steps 5.1-5.2, the video ringback tone platform collects the mixed voice stream or the separated one-way voice stream (i.e., interactive audio) between the calling terminal A and the called terminal B in real time. Step 6: Process the speech stream and return content features: (Refer to...) Figure 6 In steps 6.1-6.3, the video ringback tone platform sends the collected voice stream to the real-time voice processing module. The real-time voice processing module performs real-time processing and analysis (including converting the voice into text in real time and performing in-depth analysis of the text to extract key information), and outputs content features (i.e. key interactive information) to the video ringback tone platform. Step 7, generate subsequent video ringback tone clips: refer to Figure 6In steps 7.1-7.4, after the video ringback tone platform determines the video playback duration, it inputs the duration and content features into the AIGC video generation model to request the generation of subsequent interactive video segments. The AIGC video generation model then sends the generated subsequent interactive video segments to the video ringback tone platform. Step 8, push subsequent video ringback tone clips: refer to Figure 6 In steps 8.1-8.2, the video ringback tone platform will continuously push subsequent interactive video clips to the calling terminal A and the called terminal B for continuous playback.

[0078] Phase Four: Processing before the call ends. (Refer to...) Figure 7 The flowchart shown is an exemplary pre-call termination process, which includes the following four steps: Step 9, detect the call end intention signal: refer to Figure 7 In steps 9.1-9.2, the video ringback tone platform monitors the call status in real time. When it detects that either party intends to hang up, it sends a request to the AIGC video generation module to generate a termination video segment and stops triggering requests to generate new interactive video segments. Step 10, generate the termination video segment: refer to Figure 7 In steps 10.1-10.4, the AIGC generation module generates a termination video segment based on the request from the video ringback tone platform and returns it to the video ringback tone platform. Step 11: Push the termination video clip and end the process: Refer to... Figure 7 In steps 11.1-11.3, the video ringback tone platform will push the termination video segment to the calling terminal A and the called terminal B for playback. Once the termination video segment has finished playing, the process ends. Step 12: Once the current interactive video segment has finished playing, the process ends. (Refer to...) Figure 7 In steps 12.1-12.2, if no termination video segment is generated, the video ringback tone platform sends a stop playback command to the calling terminal A and the called terminal B. The process ends when the calling terminal A and the called terminal B finish playing the current interactive video segment.

[0079] In summary, this application, by capturing and analyzing the interactive audio between users in real time when a connection is established between the first terminal and the second terminal, and dynamically generating interactive video clips highly related to the themes, emotions, keywords, and other information contained in the current interactive audio, achieves real-time content perception and dynamic video generation capabilities. Furthermore, the initial video clip playing on the first terminal before the connection is established will not be interrupted after the connection is established, allowing for a seamless transition to the connection establishment stage and synchronous playback on both the first and second terminals, achieving a continuous visual experience with cross-stage video playback and synchronous sharing between both terminals. Additionally, before the connection is established, this application analyzes the relationship characteristics between the first and second terminals to generate a personalized initial video clip related to these relationship characteristics, breaking away from the model of pre-setting or selecting fixed video content in related technologies, effectively improving the user's visual experience.

[0080] To implement the above embodiments, this application also provides a video generation apparatus. Figure 8 This is a schematic diagram of the structure of a video generation device 800 provided in an embodiment of this application. Figure 8 As shown, the device includes: The determining unit 810 is used to determine the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment, in the case of determining the second terminal and establishing a connection with the first terminal; The generation unit 820 is used to generate a second interactive video clip containing interactive video transition effects based on the interactive key information of the interactive text. The playback unit 830 is used to send the second interactive video segment to the first terminal and the second terminal after determining that the first interactive video segment has finished playing, so that the first terminal and the second terminal can play the second interactive video segment.

[0081] In some embodiments, the determining unit 810 is configured to: when it is determined that the first terminal sends a connection request to the second terminal, generate an initial video segment based on the relationship characteristics between the first terminal and the second terminal, and send the initial video segment to the first terminal; when it is determined that the second terminal has established a connection with the first terminal, determine a first interactive video segment and interactive text generated by the first terminal and the second terminal when playing the first interactive video segment based on the initial video segment.

[0082] In some embodiments, the determining unit 810 is configured to: determine a played video segment on the first terminal when a connection is established between the first terminal and the second terminal; determine an unplayed video segment in the initial video segment based on the initial video segment and the played video segment; identify the unplayed video segment as a first interactive video segment and send the first interactive video segment to the second terminal so that the first terminal and the second terminal can play the first interactive video segment; acquire interactive audio between the first terminal and the second terminal when playing the first interactive video segment; and identify the interactive audio to obtain interactive text corresponding to the interactive audio.

[0083] In some embodiments, the determining unit 810 is configured to: when it is determined that the first terminal sends a connection request to the second terminal, generate an initial video segment based on the relationship characteristics between the first terminal and the second terminal, and send the initial video segment to the first terminal, including: when it is determined that the first terminal sends a connection request to the second terminal, determining the first terminal identifier of the first terminal and the second terminal identifier of the second terminal; obtaining relationship data between the first terminal and the second terminal based on the first terminal identifier and the second terminal identifier; determining the relationship characteristics between the first terminal and the second terminal based on the relationship data; generating an initial video segment matching the relationship characteristics based on the relationship characteristics and a preset playback duration, and sending the initial video segment to the first terminal so that the first terminal plays the initial video segment.

[0084] In some embodiments, the generation unit 820 is configured to: extract key interactive information from the interactive text; determine the video playback duration based on the semantic unit length or topic duration in the key interactive information; integrate the key interactive information, the video playback duration, and the first interactive video information of the first interactive video segment based on a preset generation prompt template to obtain first generation prompt information; and generate a second interactive video segment containing interactive video transition effects based on the first generation prompt information.

[0085] In some embodiments, the playback unit 830 is configured to: determine subsequent interactive text generated by the first terminal and the second terminal when playing the second interactive video segment; determine whether there is interaction termination information in the subsequent interactive text based on the subsequent interaction key information of the subsequent interactive text; if it is determined that there is interaction termination information in the subsequent interactive text, generate a termination video segment containing a termination video transition effect based on the interaction key information, the subsequent interaction key information, and the relationship features between the first terminal and the second terminal; when the second interactive video segment finishes playing, send the termination video segment to the first terminal and the second terminal; and when the termination video segment finishes playing, send a stop playback command to the first terminal and the second terminal.

[0086] The methods and apparatus provided in the embodiments of this application have been described above. To implement the functions of the methods provided in the embodiments of this application, the electronic device may include a hardware structure and software modules, and may implement the above functions in the form of a hardware structure, software modules, or a hardware structure plus software modules. One of the above functions may be executed in the form of a hardware structure, software modules, or a hardware structure plus software modules.

[0087] Figure 9 This is a block diagram illustrating an electronic device 900 for implementing the above-described video generation method, according to an exemplary embodiment. For example, the electronic device 900 may be a mobile phone, computer, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0088] Reference Figure 9 The electronic device 900 may include a communication interface 901, capable of interacting with other devices; a processor 902, connected to the communication interface 901 to interact with other devices, used to execute the methods provided by one or more of the above-described technical solutions when running a computer program; and a memory 903, on which the computer program is stored. Specifically, the specific processing procedure of the processor 902 can refer to the video generation method described in the above embodiments of this application.

[0089] Of course, in practical applications, the various components in electronic device 900 are coupled together through bus system 904. It can be understood that bus system 904 is used to realize the connection and communication between these components. In addition to a data bus, bus system 904 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 9 The general labeled all buses as Bus System 904.

[0090] The memory 903 in this embodiment is used to store various types of data to support the operation of the electronic device 900. Examples of such data include any computer program used to operate on the electronic device 900.

[0091] The methods disclosed in the embodiments of this application can be applied to, or implemented by, processor 902. Processor 902 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the hardware of processor 902 or by instructions in software form. Processor 902 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 902 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, specifically memory 903. Processor 902 reads information from memory 903 and, in conjunction with its hardware, completes the steps of the aforementioned method.

[0092] In an exemplary embodiment, the electronic device 900 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0093] Embodiments of this application also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the video generation method described in the above embodiments of this application.

[0094] Embodiments of this application also propose a computer program product, including a computer program that is executed by a processor using the video generation method described in the above embodiments of this application.

[0095] Embodiments of this application also propose a chip including one or more interface circuits and one or more processors; the interface circuits are used to receive signals from the memory of an electronic device and send signals to the processors, the signals including computer instructions stored in the memory, and when the processor executes the computer instructions, it causes the electronic device to perform the video generation method described in the above embodiments of this application.

[0096] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application 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 application 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 application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0097] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0098] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0100] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0101] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0102] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0103] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A video generation method, characterized in that, The method includes: In the case of determining the second terminal and establishing a connection with the first terminal, determine the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment; Based on the key interactive information of the interactive text, a second interactive video clip containing interactive video transition effects is generated; Upon determining that the first interactive video segment has finished playing, the second interactive video segment is sent to the first terminal and the second terminal, so that the first terminal and the second terminal can play the second interactive video segment.

2. The method according to claim 1, characterized in that, The step of determining the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment, in the case of determining the second terminal and establishing a connection with the first terminal, includes: If it is determined that the first terminal sends a connection request to the second terminal, an initial video segment is generated based on the relationship characteristics between the first terminal and the second terminal, and the initial video segment is sent to the first terminal; In the case of determining the second terminal and establishing a connection with the first terminal, based on the initial video segment, the first interactive video segment and the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment are determined.

3. The method according to claim 2, characterized in that, In the case of determining the second terminal and establishing a connection with the first terminal, determining the first interactive video segment and the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment based on the initial video segment includes: If it is determined that the first terminal and the second terminal have established a connection, the video segment that has been played on the first terminal is determined; Based on the initial video segment and the already played video segment, determine the unplayed video segment in the initial video segment; The unplayed video segment is identified as the first interactive video segment, and the first interactive video segment is sent to the second terminal so that the first terminal and the second terminal can play the first interactive video segment. Acquire the interactive audio between the first terminal and the second terminal when playing the first interactive video segment; The interactive audio is identified to obtain the corresponding interactive text.

4. The method according to claim 2, characterized in that, The step of generating an initial video segment based on the relationship characteristics between the first terminal and the second terminal, and sending the initial video segment to the first terminal, when it is determined that the first terminal sends a connection request to the second terminal, includes: If it is determined that the first terminal sends a connection request to the second terminal, the first terminal identifier of the first terminal and the second terminal identifier of the second terminal are determined. Based on the first terminal identifier and the second terminal identifier, obtain the relationship data between the first terminal and the second terminal; Based on the relationship data, the relationship characteristics between the first terminal and the second terminal are determined; Based on the relationship features and the preset playback duration, an initial video segment matching the relationship features is generated, and the initial video segment is sent to the first terminal so that the first terminal can play the initial video segment.

5. The method according to claim 1, characterized in that, Upon determining that the first interactive video segment has finished playing, the second interactive video segment is sent to both the first terminal and the second terminal. The method then includes: Determine the subsequent interactive text generated by the first terminal and the second terminal while playing the second interactive video segment; Based on the key information of the subsequent interaction in the subsequent interaction text, determine whether there is interaction termination information in the subsequent interaction text. If it is determined that there is interaction termination information in the subsequent interaction text, an termination video segment containing termination video transition effects is generated based on the interaction key information, the subsequent interaction key information, and the relationship features between the first terminal and the second terminal. Upon completion of the second interactive video segment playback, the termination video segment is sent to both the first terminal and the second terminal. Upon completion of the playback of the terminated video segment, a stop playback command is sent to the first terminal and the second terminal.

6. The method according to claim 1, characterized in that, The generation of a second interactive video clip containing interactive video transition effects based on the interactive key information of the interactive text includes: Extract key interactive information from the interactive text; The video playback duration is determined based on the semantic unit length or topic duration in the key interactive information. Based on a preset generated prompt template, the key interactive information, the video playback duration, and the first interactive video information of the first interactive video segment are integrated to obtain the first generated prompt information; Based on the first generated prompt information, a second interactive video clip containing interactive video transition effects is generated.

7. A video generation apparatus, characterized in that, The device includes: The determining unit is configured to determine the interactive text generated by the first terminal and the second terminal when playing the first interactive video segment, in the case of determining the second terminal and establishing a connection with the first terminal; The generation unit is used to generate a second interactive video clip containing interactive video transition effects based on the interactive key information of the interactive text. The playback unit is configured to send the second interactive video segment to the first terminal and the second terminal when it is determined that the first interactive video segment has finished playing, so that the first terminal and the second terminal can play the second interactive video segment.

8. An electronic device, characterized in that, include: The processor and the memory used to store computer programs that can run on the processor. When the processor is used to run the computer program, it performs the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images