Video generation method, device, equipment, storage medium and program product

Abstract

The present disclosure provides a video generation method and device, equipment, storage medium and program product, and belongs to the technical field of network. The technical scheme provided by the present disclosure includes multiple arrangement elements in the target style template, realizes the structuring of the configuration information, and then the user can generate the video based on at least one target arrangement element in the multiple arrangement elements included in the target style template, instead of generating the video based on all the arrangement elements in the target style template, realizes the personalized application of the required arrangement elements in the video generation, reduces the workload of setting the configuration information of the video, and improves the human-computer interaction efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of network technology, and in particular to a method, apparatus, device, storage medium, and program product for generating video. Background Technology

[0002] In the field of video creation, one of the core competencies of creators is the consistency of video style, which makes the creator and the video recognizable.

[0003] In related technologies, in order to maintain a consistent style in videos, creators need to manually set a lot of configuration information for each video when editing videos using relevant video editing tools, such as filter parameters, effects combinations, transitions, etc.

[0004] The above configuration information is highly dependent on the creator's memory of the configuration information and the accuracy of the operation when manually setting it. Moreover, each video needs to be set once, and the workload of repeatedly setting the configuration information increases exponentially, resulting in low efficiency of human-computer interaction. Summary of the Invention

[0005] This disclosure provides a method, apparatus, device, storage medium, and program product for generating video, which improves the efficiency of human-computer interaction.

[0006] According to one aspect of the present disclosure, a method for generating a video is provided, the method comprising: in response to a video creation operation, displaying a target style template in a style library, the style template in the style library being used to generate a video; and, in response to a video generation operation, displaying a video generated by an agent based on the at least one target choreography element among a plurality of choreography elements included in the target style template, wherein the plurality of choreography elements respectively indicate configuration information for different choreography angles of the video.

[0007] According to another aspect of the present disclosure, a video generation apparatus is provided, the apparatus comprising: The first display module is configured to display a target style template in the style library in response to a video creation operation, the style template in the style library being used to generate the video; The second display module is configured to, in response to a video generation operation, display a video generated by an agent based on the at least one target choreography element when at least one of the multiple choreography elements included in the target style template is selected, wherein the multiple choreography elements respectively indicate configuration information for different choreography angles of the video.

[0008] In some embodiments, the first display module is configured to display at least one style template set in the style library, display a recommended style template from the recommended style template set in the at least one style template set as a target style template, the style template set including style templates with the same name; and in response to a confirmation operation of the target style template, display the name of the target style template and a plurality of arrangement elements included in the target style template.

[0009] In some embodiments, the arrangement elements in the style template are arrangement elements after removing at least one of the character-specific configuration content and scene-specific configuration content.

[0010] In some embodiments, the device further includes a third display module and a fourth display module; The third display module is configured to display multiple arrangement elements in the video in response to a template saving operation of the video; The fourth display module is configured to display, in response to a save operation on at least one first arrangement element among the plurality of arrangement elements, that a sedimentation style template has been saved to the style library, the sedimentation style template including the at least one first arrangement element.

[0011] In some embodiments, the third display module is configured to display multiple entries in response to a template saving operation of the video; the multiple entries respectively display the arrangement angle names of the multiple arrangement elements and the configuration information corresponding to the multiple arrangement elements.

[0012] In some embodiments, the device further includes a fifth display module, a sixth display module, and a seventh display module; The fifth display module is configured to display multiple plot stages in the dramatic structure on the generated page, which is used to generate chat logs through an intelligent agent; The sixth display module is configured to display the configured content of the at least one plot stage in response to a configuration operation on the generation page for at least one plot stage. The seventh display module is configured to display chat logs generated by the agent based on the multiple plot stages and the configured content of each plot stage in response to a generation operation on the generation page. The second display module is configured to, in response to a video generation operation, display a video generated by the agent based on the at least one target choreography element and the chat history when at least one target choreography element among the plurality of choreography elements included in the target style template is selected.

[0013] In some embodiments, the sixth display module is configured to include at least one of a first display unit and a second display unit; The first display unit is configured to display descriptive text of the at least one plot stage in response to a configuration operation of the content of at least one plot stage on the generation page; The second display unit is configured to display the semantic strength of the at least one plot stage in response to a configuration operation of the semantic strength of at least one plot stage on the generated page, the semantic strength indicating the semantic strength of the content in the plot stage.

[0014] In some embodiments, the first display unit is configured to display the filled content in the at least one plot stage as descriptive text of the at least one plot stage in response to a fill-in operation on the generation page; or, in response to an upload operation of existing chat records on the generation page, display descriptive text of the at least one plot stage generated by the agent based on the existing chat records.

[0015] In some embodiments, the apparatus further includes an eighth display module; the eighth display module is configured to display, on a generated page, arrangement elements adapted to each chat message in the chat history based on the at least one target arrangement element, wherein the arrangement element of each chat message is used to indicate how the chat message is presented in the video, and the arrangement element of each chat message matches the chat characteristics of the character who sent the chat message; the step of displaying a video generated by an agent based on the at least one target arrangement element in response to a video generation operation when at least one target arrangement element in the multiple arrangement elements included in the target style template is selected includes: displaying a video generated by an agent based on the arrangement elements of the chat history and each chat message in response to a video generation operation when at least one target arrangement element in the multiple arrangement elements included in the target style template is selected.

[0016] In some embodiments, the arrangement elements have multiple arrangement angles, and arrangement elements with different arrangement angles are used to provide different presentation effect dimensions in the video; the eighth display module is configured to, on the generated page, arrange and display each chat message in the chat history and its corresponding role along a first direction according to the order of each chat message in the chat history; on the generated page, arrange and display the multiple types along a second direction, and the display areas of the multiple types intersect with the display areas of each chat message to form multiple grids, and each grid displays the arrangement elements used by a corresponding chat message in a corresponding type.

[0017] In some embodiments, the device further includes a ninth display module; the ninth display module is configured to, on the generated page, prioritize displaying a target chat message in the chat history that is in an automatically selected state and the arrangement elements of the target chat message; wherein the target chat message is a chat message in the chat history whose semantic inversion intensity and emotional intensity exceed a preset value, the semantic inversion intensity is used to indicate the difference between the semantics of the current chat message and the semantics of the previous chat message, and the impact intensity of the arrangement elements of the target chat message is higher than the impact intensity of the arrangement elements of other chat messages in the chat history.

[0018] In some embodiments, the device further includes a tenth display module and an eleventh display module; The tenth display module is configured to display multiple rhyming schemes adapted to the selected background music and chat history on the generated page. The eleventh display module is configured to, in response to a rewriting operation, display the target text obtained by rewriting the chat record based on the target rhyming scheme when a target rhyming scheme is selected among the plurality of rhyming schemes, wherein the rhyming at the end of each sentence in the target text conforms to the target rhyming scheme. The second display module is configured to, in response to a video generation operation, display a video generated by an agent based on the at least one target choreography element and the target text, when at least one target choreography element among the plurality of choreography elements included in the target style template is selected.

[0019] In some embodiments, the apparatus further includes a twelfth display module; the twelfth display module is configured to display a plurality of rewriting constraints in the generated page, each rewriting constraint indicating the relative importance of semantic preservation, rhyme matching, and beat alignment when performing a rewrite; wherein, in response to a rewrite operation, the target text obtained by rewriting the chat record is displayed based on the target rhyme scheme when the target rhyme scheme among the plurality of rhyme schemes is selected, including: in response to a rewrite operation, the target text obtained by rewriting the chat record is displayed based on the target rhyme scheme and the target rewrite constraint when the target rhyme scheme among the plurality of rhyme schemes is selected and the target rewrite constraint among the plurality of rewriting constraints is selected.

[0020] According to another aspect of the present disclosure, an electronic device is provided, the electronic device comprising: one or more processors; a memory for storing processor-executable program code; wherein the processor is configured to execute the program code to implement the video generation method as described above.

[0021] According to another aspect of the present disclosure, a computer-readable storage medium is provided that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the video generation method described above.

[0022] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the video generation method described above.

[0023] In the technical solution provided by the embodiments of this disclosure, by including multiple arrangement elements in the target style template, the configuration information is structured. As a result, users can generate videos based on at least one target arrangement element among the multiple arrangement elements included in the target style template, instead of having to generate videos based on all arrangement elements in the target style template. This realizes the personalized application of the required arrangement elements in video generation, while reducing the workload of setting configuration information for videos and improving the efficiency of human-computer interaction.

[0024] 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

[0025] 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.

[0026] Figure 1 This is a schematic diagram illustrating an implementation environment according to an exemplary embodiment.

[0027] Figure 2 This is a flowchart illustrating a video generation method according to an exemplary embodiment.

[0028] Figure 3 This is a flowchart illustrating another method for generating video according to an exemplary embodiment.

[0029] Figure 4 This is a schematic diagram illustrating a page generation method according to an exemplary embodiment.

[0030] Figure 5 This is a schematic diagram illustrating the display of style templates in a style library according to an exemplary embodiment.

[0031] Figure 6 This is a schematic diagram illustrating a style template operation in the style library based on a new video operation, according to an exemplary embodiment.

[0032] Figure 7This is a flowchart illustrating another method for generating video according to an exemplary embodiment.

[0033] Figure 8 This is a schematic diagram illustrating a page generation method according to an exemplary embodiment.

[0034] Figure 9 This is a schematic diagram illustrating a page generation method according to an exemplary embodiment.

[0035] Figure 10 This is a flowchart illustrating another method for generating video according to an exemplary embodiment.

[0036] Figure 11 This is a schematic diagram illustrating a page generation method according to an exemplary embodiment.

[0037] Figure 12 This is a flowchart illustrating another method for generating video according to an exemplary embodiment.

[0038] Figure 13 This is a schematic diagram illustrating a page generation method according to an exemplary embodiment.

[0039] Figure 14 This is a schematic diagram illustrating a page generation method according to an exemplary embodiment.

[0040] Figure 15 This is a block diagram illustrating a video generation apparatus according to an exemplary embodiment.

[0041] Figure 16 This is a block diagram illustrating a terminal according to an exemplary embodiment. Detailed Implementation

[0042] 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.

[0043] 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.

[0044] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0045] Figure 1 This is a schematic diagram illustrating an implementation environment according to an exemplary embodiment. See also... Figure 1 The implementation environment specifically includes: terminal 101 and server 102. Terminal 101 and server 102 can be connected directly or indirectly through wired or wireless communication, which is not limited herein.

[0046] Terminal 101 is at least one of the following devices: smartphone, smartwatch, desktop computer, laptop, and mobile computer. Terminal 101 runs an application that supports video generation methods; for example, the application is a video editing tool that can be used for video editing and other similar scenarios. Users can log in to the application through Terminal 101 to access the services provided by the application. For example, users can use the application on Terminal 101 to perform video editing and generate videos based on the edited videos.

[0047] Terminal 101 generally refers to one of a plurality of terminals; this embodiment uses terminal 101 as an example. Those skilled in the art will understand that the number of terminals can be more or less. For example, there may be several terminals, or dozens or hundreds of terminals, or even more. This disclosure does not limit the number of terminals or the type of device.

[0048] Server 102 can be at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. Server 102 provides backend services for applications supporting video generation methods. Server 102 can connect to terminal 101 via a wireless or wired network. Server 102 can provide the terminal with database services related to video generation methods, and of course, other types of services. In some embodiments, the number of servers may be more or fewer, and this disclosure does not limit this. Of course, server 102 may also include other functional servers to provide more comprehensive and diversified services.

[0049] In the video creation ecosystem, one of the successful paths for serial creators is to create a highly recognizable series style: stable character appearance, consistent visual style, and a set of familiar music styles and special effects. Viewers' perception of a creator's intellectual property (IP) is built upon this consistency in visual style. Therefore, to maintain stylistic consistency, creators (i.e., users) need to manually set a large amount of configuration information for each video when using relevant video editing tools. This workload is enormous, and it's particularly pronounced in creative scenarios where video configuration information is more complex. For example, in the creation of chat rap videos, which are rap videos generated from chat logs, in addition to standard filter and transition configurations, chat rap videos involve a large amount of proprietary configuration content, such as character style (voice, speech bubble effects, color tone, etc.), rap beat alignment parameters, rhyme preferences, and climax frame effects.

[0050] Among related technologies, video editing tools mainly include the following categories: In the first category, all configuration information for the video arrangement is discarded after the user exports the video. That is, filter parameters, effect combinations, transition configurations, etc., that were adjusted in the Nth video are all reset to zero in the N+1th video, where N is a positive integer. Users can only manually configure these items one by one from memory, making it difficult to ensure complete stylistic consistency between video series. In creative scenarios with richer configuration dimensions, such as chat rap, additional configurations such as character voices, speech bubble effects, rap beat alignment, and rhyme preferences need to be reconfigured, multiplying the amount of repetitive work.

[0051] The second category includes some video editing tools that provide pre-made templates for users to choose from. However, these templates are uniformly produced by the platform, with fixed styles and limited quantities. The platform's templates are usually not the styles that users need, and users still need to manually set a lot of configuration information.

[0052] In summary, in related technologies, users need to manually and repeatedly set a large amount of configuration information to maintain a consistent video style when arranging videos. To solve the above problems, this disclosure provides a video generation method, apparatus, device, storage medium, and program product.

[0053] Figure 2 This is a flowchart illustrating a video generation method according to an exemplary embodiment, see [link to flowchart]. Figure 2 In this embodiment, the method is executed by an electronic device. The following description uses an electronic device provided as a terminal as an example. The method includes the following steps: In step 201, in response to the video creation operation, the terminal displays the target style template in the style library, which is used to generate the video.

[0054] In this step, the video creation operation refers to either creating a new video or creating a new video based on any style template in the style library. For example, it could respond to a video creation operation based on source material (chat logs). Alternatively, during video editing, it could respond to a reuse operation of any style template in the style library, applying the reused style template to the video being edited. This process is equivalent to creating a new video based on the reused style template. The style library includes at least one style template used to generate videos. The style template can be a template extracted from an already generated video.

[0055] In step 202, when at least one target choreography element among the multiple choreography elements included in the target style template is selected, the terminal responds to the video generation operation by displaying a video generated by the agent based on at least one target choreography element, wherein the multiple choreography elements respectively indicate configuration information for different choreography angles of the video.

[0056] In this step, the arrangement element refers to the configuration information for a particular arrangement angle of the video. The arrangement angle refers to the angle from which the video is arranged. For example, the arrangement angle may include character style, rap timbre, effect combinations, speech bubble visuals, music style, intro and outro, plot structure, rhyme preferences, etc. Of course, this is just an example of an arrangement angle; other classifications are also possible. Configuration information refers to the configuration content for each arrangement item in the video, such as filter parameters, transition types and durations, speech bubble styles and transparency settings, etc. The configuration information for each arrangement angle is different and may include multiple configuration items. Therefore, the arrangement element typically includes multiple configuration items belonging to a single arrangement angle. For example, when the arrangement angle is character style, the configuration information included in the arrangement element for that angle refers to the configuration content for the character in the video, such as the character's filter parameters (skin smoothing 60%, eye distance -5), the character's hairstyle, etc. At least one target orchestration element is an orchestration element selected by the user from multiple orchestration elements. The user can select any number of orchestration elements according to their needs to generate a video.

[0057] This step allows users to select the desired choreography elements from the target style template, enabling personalized application of the required choreography elements in video generation. It also improves the flexibility of reusing choreography elements in the style template. At the same time, users no longer need to manually configure at least one target choreography element; they only need to manually configure choreography elements other than at least one target choreography element. This reduces the workload of users in setting video configuration information and improves human-computer interaction efficiency.

[0058] In some embodiments, the orchestration element indicates the configuration content in the video; or, the orchestration element indicates the difference between the configuration content in the video and the default configuration content in the system. Here, "system" refers to the video orchestration tool. By saving only the difference information from the system default configuration content, the storage overhead required to save the style template is reduced, resulting in higher storage efficiency; by saving the complete configuration content in the video (i.e., full storage), updates to the video orchestration tool will not affect the configuration information in the style template, thus improving the stability of the style template.

[0059] In the technical solution provided by the embodiments of this disclosure, by including multiple arrangement elements in the target style template, the configuration information is structured. As a result, users can generate videos based on at least one target arrangement element among the multiple arrangement elements included in the target style template, instead of having to generate videos based on all arrangement elements in the target style template. This realizes the personalized application of the required arrangement elements in video generation, while reducing the workload of setting configuration information for videos and improving the efficiency of human-computer interaction.

[0060] Figure 3 This is a flowchart illustrating another method for generating video according to an exemplary embodiment, see [link to flowchart]. Figure 3 In this embodiment, the method is executed by an electronic device. The following description uses an electronic device provided as a terminal as an example. The method includes the following steps: In step 301, in response to the video creation operation, the terminal displays the target style template in the style library, which is used to generate the video.

[0061] To improve user decision-making efficiency regarding style templates, a target style template is displayed. When the target style template is not the user's desired style template, a style template switch can be performed. In some embodiments, step 301 includes displaying the name of the target style template and the multiple arrangement elements included in the target style template. In this step, the target style template can be the system default style template, the style template corresponding to the user's recommended settings, or the style template determined by the intelligent agent based on the user's input video theme. That is, the style template most likely to be needed by the user is displayed, reducing the efficiency of user switching and eliminating the need to select from a large number of style templates at the beginning, reducing the selection time and improving interaction efficiency. Furthermore, by directly displaying the target style template and the configuration information of multiple arrangement angles within the target style template, if the target style template is the user's desired style template, the user can simply select the required arrangement elements within the target style template, reducing operation steps. If the target style template is not the user's desired style template, the user can switch to another style template through a change operation. When the target style template set is a set of style templates determined by the agent based on the video theme entered by the user, the video theme entered by the user refers to the video name or other content of the video entered by the user when creating a new video. The agent automatically recommends the most suitable style template based on the video theme entered by the user and pre-fills it, so that the user can reuse it directly, reducing the number of operation steps.

[0062] When displaying style templates in the style library, to more intuitively showcase style templates with the same name and allow users to quickly switch between them, style templates with the same name can be displayed as a set of style templates. In some embodiments, the method further includes: in response to a style template switching operation, displaying at least one set of style templates in the style library, the style template set including style templates with the same name; and in response to a selection operation on a style template in the at least one set of style templates, displaying the selected style template as the target style template. In this step, the recommended style template set refers to the set of style templates that are preferentially recommended when a user creates a new video or selects a style template. Only one recommended style template set exists in the style library for the same user at any given time. The recommended style template set refers to the system's default style template set, the style template set corresponding to the user's recommendation settings, or the style template set determined by the agent based on the video theme input by the user. Furthermore, the name indicates the style of the style template. For example, if the name is "Friends Series • XX Edition", by displaying style templates with the same name as a style template set, the same style template set can include style templates of different versions but the same style. Based on this style template set, it is beneficial to clearly display the number of styles in the style library, so as to quickly select the corresponding style template set without having to search through a large number of style templates, thus improving the interaction efficiency.

[0063] When displaying a collection of style templates, to more clearly showcase the recommended style templates in the template library, recommended style templates can be displayed above other style template collections. In some embodiments, displaying at least one style template collection in the style library includes at least one of the following: displaying the recommended style template collection within the at least one style template collection; and displaying the recommended style template collection in the style library above each style template collection in the style library. In this step, by displaying the recommended style templates above other style template collections, the recommended style templates are presented more clearly.

[0064] When displaying a set of recommended style templates, in order to visually distinguish the set of recommended style templates from other style template sets, the set of recommended style templates can be displayed as selected, and a recommendation label can be displayed at the corresponding position of the set of recommended style templates. In some embodiments, displaying a set of recommended style templates from at least one style template set includes at least one of the following: displaying a set of recommended style templates from at least one style template set as selected; and displaying a recommendation label at the corresponding position of the set of recommended style templates from at least one style template set. In this step, by displaying the recommended style template set as selected and showing at least one of the recommended tags in its corresponding position, the display of the recommended style template set in the style library is distinguished from other style template sets. This achieves a more intuitive display of the recommended style template sets in the style library, making them easier to notice. Furthermore, displaying the recommended style template set as selected means that the terminal prioritizes recommending the recommended style template set. If the recommended style template set is not the style template the user needs, the user can reselect the desired style template set or a style template from a certain style template set. If the recommended style template set is the style template the user needs, the user can confirm without having to search for it again, thereby improving the user's interaction efficiency.

[0065] To clearly demonstrate the save time of the style templates included in the style template collection, the style templates are displayed in order of save time. In some embodiments, the method further includes: displaying the style templates included in the selected style template collection in the style library in order of save time. In this step, by displaying the selected style templates in order of save time, the display order of the style templates intuitively shows the version order of different style templates without viewing the style templates. This helps users quickly determine which version is newly saved and which version is older, thus quickly identifying the required version and improving the efficiency of users in determining the required version.

[0066] To clearly display recommended style templates in the style template set, a recommendation label is displayed at the corresponding position of the recommended style template. In some embodiments, the method further includes: displaying a recommendation label at the corresponding position of the recommended style template in the selected style template set. In this step, the recommendation label distinguishes the display of recommended style templates in the same style template set from other style templates, achieving a more intuitive display of recommended style templates in the style template set. Therefore, if the recommended style template is the style template the user needs, the user does not need to search for it separately, thereby improving the user's interaction efficiency.

[0067] To quickly find the desired set of style templates in the style library, filtering can be performed using at least one of the style template set's name and tags. Accordingly, in some embodiments, the method further includes: displaying the filtered set of style templates in the style library in response to the filtering operation based on the style template set's tags or name. In this step, the filtering operation based on the style template set's tags or name enables quick viewing of the desired set of style templates, improving user interaction efficiency.

[0068] If the target style template is not the style template the user needs, the user can select other style template sets or style templates. Accordingly, in some embodiments, in response to a selection operation on a style template in at least one style template set, the selected style template is displayed as the target style template, including: in response to a selection operation on a first style template set in the style library, a recommended style template in the first style template set is displayed as the target style template; or, in response to a selection operation on a second style template set in the style library, multiple style templates included in the second style template set are displayed, and in response to a selection operation on a first style template among the multiple style templates included in the second style template set, the first style template is displayed as the target style template. Through this step, the user is supported in selecting a style template set, and also in selecting a style template from a style template set, allowing the user to select a style template according to their needs.

[0069] When displaying the target style template, style templates from the style library can also be displayed. Based on the user's selection of a style template, the selected style template is displayed as the target style template. Accordingly, in some embodiments, step 301 includes: displaying at least one set of style templates from the style library, displaying recommended style templates from the recommended style template set within the at least one set of style templates as the target style template, the style template set including style templates with the same name; and, in response to a confirmation operation on the target style template, displaying the name of the target style template and the multiple arrangement elements included in the target style template. In this step, the terminal, in response to a video creation operation, displays at least one set of style templates from the style library. This only supports selection of style templates from the style library and reuse of the selected style template in the video, but does not support management operations (such as recommendation settings and comparison of configuration information between different recommended style templates) on the recommended style templates or recommended style template sets in the style library.

[0070] Videos typically include different characters or specific scenes, and some choreography elements are character-specific configurations or scene-specific configurations. To make the style template saved based on this video applicable to other videos with different characters or scenes, multiple choreography elements in the video can be elements after removing at least one of the character-specific and scene-specific configurations. Accordingly, in some embodiments, the choreography elements in the style template are elements after removing at least one of the character-specific and scene-specific configurations. In this step, it is equivalent to extracting general choreography elements from the specific character configuration, allowing the style template to be generalized and reused across characters or scenes, rather than being bound to a specific character or scene, thus improving the applicability of the style template.

[0071] In step 302, when at least one target choreography element among the multiple choreography elements included in the target style template is selected, the terminal, in response to the video generation operation, displays the video generated by the agent based on at least one target choreography element, wherein the multiple choreography elements respectively indicate configuration information for different choreography angles of the video.

[0072] The principle of this step is the same as that in the above embodiments, and will not be described in detail here.

[0073] In step 303, in response to the video template saving operation, the terminal displays multiple arrangement elements in the video.

[0074] This step displays multiple arrangement elements in the video, which means that the configuration information is displayed from different arrangement angles, rather than displaying all the configuration information in a chaotic manner. This improves the cleanliness and neatness of the page, and also makes it easier to select and save the configuration information according to the arrangement elements.

[0075] In response to the video template saving operation, to make the configuration information in the video clearer, it can be displayed as multiple arrangement elements according to the arrangement angle. Accordingly, in some embodiments, step 303 includes: in response to the video template saving operation, displaying multiple entries; and displaying the arrangement angle names of multiple arrangement elements and the configuration information corresponding to each arrangement element in the multiple entries. In this step, each entry displays the arrangement angle name of one arrangement element and the configuration information corresponding to that arrangement element, making the page cleaner and clearer, and facilitating users to select and save the required arrangement elements.

[0076] To facilitate differentiation between different style templates, at least one of the target name and target tags of the style template is displayed. In some embodiments, the method further includes: in response to a template saving operation on a video, displaying at least one of the target name and target tags of the style template, where the target tags indicate the characteristics of the style template. In this step, the target name can be a name generated by the agent based on the video, or it can be a preset default name. The target name indicates the style of the style template. The target name makes it easier to distinguish between different style templates; for example, the target name could be "Friends Series • XX Version," "Family Style," etc. The target tags are at least one of the tags generated by the agent based on the video and tags added by the user. For example, target tags include "Rap Series" and "Strong Reversal." The target tags further mark the characteristics of the style template, allowing direct differentiation of style templates without needing to examine the specific arrangement elements of the style template, making it easier to distinguish and select style templates and improving the convenience of reusing style templates.

[0077] The target name of the style template can also be the updated name. In some embodiments, the method further includes: in response to an update operation on the name of the sedimentation style template, displaying the updated name as the target name of the sedimentation style template. In this step, the update operation can be a modification operation on the name of the sedimentation style template, allowing the user to modify the name so that the displayed target name better suits the user's habits; the update operation can also be a regeneration operation on the name of the sedimentation style template through an intelligent agent, which enables rapid name updates, improves update speed, and lowers the operational threshold for users to update names.

[0078] The target tag can also be a modified tag. Accordingly, in some embodiments, the terminal displays the target tag in response to a video template saving operation, including at least one of the following: in response to a video template saving operation, displaying at least one first tag and a tag adding control; in response to a tag adding operation based on the tag adding control, displaying an added second tag; displaying at least one first tag and the second tag as the target tag, wherein the first tag is a tag generated by an agent based on the video; and in response to a deletion operation of a third tag among the at least one first tag, displaying the remaining first tags as the target tag. In this step, displaying at least one first tag and a tag adding control supports the deletion and addition of tags, making the final displayed target tag more in line with user habits.

[0079] In some embodiments, saving a video template includes either exporting the video or saving the arrangement elements within the video. Exporting refers to exporting the video after arrangement is complete. Saving the arrangement elements refers to saving the configuration information (i.e., the arrangement elements) of the current video state during the arrangement process. If the saving of the style template is automatically triggered during the video arrangement process, it would interrupt the user's video arrangement process. However, the method in this embodiment triggers the saving of the style template through the export operation. At this point, the user's satisfaction with the video arrangement is highest, and correspondingly, the user's willingness to save the style template is also highest. Therefore, a corresponding display is provided, and the user can save directly based on the display, eliminating the need for the user to manually save the style template to trigger the saving step, thus improving operational efficiency and human-computer interaction efficiency. Of course, users can also actively save the style template during the video arrangement process.

[0080] In step 304, in response to a save operation on at least one first arrangement element among a plurality of arrangement elements, the terminal displays that the sedimentation style template has been saved to the style library, the sedimentation style template including at least one first arrangement element.

[0081] In this step, at least one first arrangement element can be any number of arrangement elements from multiple arrangement elements. That is, the configuration information is displayed as independent modules according to arrangement elements, allowing users to select and save modules of any arrangement element from multiple arrangement elements, improving the flexibility and convenience of saving. The "settled style template" refers to a style template that includes at least one saved first arrangement element. The style library includes all saved style templates. The style templates in the style library are used to generate videos. That is, when creating a new video, the desired style template is selected from the style library. Then, when generating the video, the intelligent agent generates the video based on the style template, other content arranged during the video arrangement process, and related materials.

[0082] To enable quick viewing of saved style templates, in response to a save operation on at least one first arrangement element among multiple arrangement elements, a style library access control is displayed. Accordingly, in some embodiments, the method further includes: the terminal displaying a style library viewing control in response to a save operation on at least one first arrangement element among multiple arrangement elements; and displaying style templates in the style library in response to a trigger operation on the style library viewing control. In this step, by using the style library viewing control, users can directly access the style library from the current page, achieving the goal of quickly viewing saved style templates. Users do not need to access the style library through style library entry points on other pages, thus improving user interaction efficiency.

[0083] In the style library, to facilitate the management of style templates with the same name, style templates with the same name are displayed as a style template collection. In some embodiments, the method further includes: in response to a viewing operation of the style library, displaying at least one style template collection, the style template collection including style templates with the same name. In this step, the viewing operation of the style library can be: a trigger operation of the style library viewing control, or a trigger operation of the style library entry on other pages in the video editing tool. The style library entry on other pages in the video editing tool can be an independent entry in the video editing tool, such as the style library entry being located in the fixed navigation bar or sidebar at the bottom of the main page of the video editing tool. In response to the viewing operation of the style library, the displayed page is the style library management page. Based on this page, management operations can be performed on the style templates in the style library, such as recommending settings for style templates or style template collections, comparing different style templates, etc. By using the name of the style template to represent its style, and displaying style templates with the same name as a style template set, this allows a single style template set to include different versions of style templates with the same style. Based on this style template set, it is beneficial to clearly display the number of styles in the style library, facilitating quick selection of the appropriate style template set without having to search through a large number of style templates. This embodiment of the present disclosure solves the problem in related technologies where a newer version of a style template with the same name overwrites an older version, enabling the simultaneous storage of multiple style templates with the same name, i.e., multiple versions of style templates with the same style, facilitating comparison and selection between versions.

[0084] To clearly display the styles and number of style templates in a style template set, when displaying the style template set, the number of style templates included in the style template set and the set name are shown. Accordingly, in some embodiments, in response to a viewing operation of the style library, at least one style template set is displayed, including: in response to a viewing operation of the style library, displaying the number of style templates included in each style template set and the set name, where the set name is the name of the style templates included in the style template set. In this step, by displaying the set name, the style of the style template set is shown, making it easier for users to quickly locate the desired style template set. By displaying the number of style templates included in the style template set, a prompt is provided to the user, preventing the user from mistakenly believing that the style template set contains only one style template set, thus improving the speed at which the user determines the desired style template and thereby improving interaction efficiency.

[0085] To facilitate comparison of different style templates within the same style template set, in response to a comparison operation on a second style template included in the style template set, the method displays the difference configuration information between the second style template and the recommended style template. In some embodiments, the method further includes: in response to a comparison operation on a style template set included in the style library based on a selected state, displaying the difference configuration information, which consists of the arrangement elements that differ between the second style template and the recommended style template in the selected style template set. This step only displays the difference configuration information between different style templates, while the configuration information for indistinguishable arrangement angles can be collapsed, such as displaying "no change in 4 arrangement angles," or not displaying the configuration information for indistinguishable arrangement angles, reducing the amount of information displayed on the page and avoiding information overload. For style templates with the same name, multiple versions can be saved to form a style template set; and visual comparison of configuration information between different versions of style templates is supported, allowing for historical tracking of configuration information changes across different versions of style templates.

[0086] In some embodiments, displaying differentiated configuration information includes: displaying some layout elements from the second style template in the first area, and displaying some layout elements from the recommended style templates in the selected style template set in the second area, wherein the first and second areas do not overlap. In this step, the first and second areas are either horizontally or vertically positioned, with one area displaying some layout elements from the second style template and the other displaying some layout elements from the recommended style templates in the selected style template set. The differentiated configuration information can also be highlighted for a more prominent display, and the information is also displayed modularly according to the layout angle, rather than individually, ensuring users can quickly understand the differences.

[0087] To ensure that the recommended style templates in the style template set are what the user needs, or to ensure that the recommended style template set in the template library meets the user's dynamic needs for style templates (e.g., the user's style needs change at different times), the recommended style templates in the style template set can be configured with recommendations. It also supports setting other style template sets as recommended style template sets. In some embodiments, the method further includes at least one of the following: in response to a recommendation setting operation on a third style template included in a selected style template set in the style library, displaying the third style template as a recommended style template; in response to a recommendation setting operation on a third style template set in a non-recommended style template set in the style library, displaying the third style template set as a recommended style template set. Through this step, based on the user's recommendation setting operation on the third style template, the third style template is displayed as a recommended style template, aligning the recommended style templates with the user's needs and facilitating user management of the style library. This step enables the implementation of recommended settings based on user preferences for the third style template set. The third style template set is then displayed as a recommended style template set, aligning the recommended style template set with user needs and facilitating user management of the style library.

[0088] In step 305, in response to the target object's operation of sharing the sedimentation style template to the community, the terminal displays the sedimentation style template on the community's display page.

[0089] This step is optional. In this step, the target user refers to the user who saved the second target style template. The target user can choose to publish their own style template to the community for other users to browse and reuse (similar to a "template marketplace"). Of course, the target user can also browse and reuse style templates published by other users through the community's display page, greatly increasing the sources of style templates.

[0090] The method of this disclosure solves the problem that the configuration information set in video arrangement cannot be converted into reusable assets, and solves the problem that the methods of related technologies do not support the selective application of configuration information by module (such as arrangement angle).

[0091] The method of this disclosure automatically triggers the saving process after each video export, which means displaying the configuration information of multiple arrangement angles in the video. In response to the user's save operation on the configuration information, the user's settings (configuration information) can be systematically saved as a style template instead of being forgotten directly, thus changing the style template from "use and discard" to "accumulation and sedimentation".

[0092] By reusing style templates, the method of this disclosure ensures that videos in the same series (i.e., videos using the same style template) are highly consistent in multiple arrangement aspects such as character appearance, effect style, and speech bubble visuals, thereby enhancing the IP's recognizability and significantly improving the style consistency of the series of videos.

[0093] By using the method of this disclosure, style templates with the same name are stored in the same style template set, allowing users to boldly adjust the configuration information in the video and save it as a new version of the style template. That is, there are style templates with the same name but different configuration information. If you are not satisfied, you can roll back (referring to the operation of restoring the configuration information to a previous correct state, which can be done by reusing a style template). The psychological burden of users to explore styles is significantly reduced, and the cost of trial and error is reduced.

[0094] By using the method of this disclosure embodiment, when reusing the same configuration information across videos, one can select the corresponding style template and selectively apply the configuration information of the required arrangement angle. This is modular reuse, which reduces the workload of configuring the configuration information required for creating a new video by more than 70%, greatly reduces the amount of labor involved in repeatedly setting configuration information, significantly improves human-computer interaction efficiency, and significantly enhances the efficiency of video creation.

[0095] The following example, using the chat rap creator "@RapDiary", will introduce the video generation method.

[0096] like Figure 4 As shown, Figure 4 This is a schematic diagram of a page that triggers the saving of a style template in response to an export operation of a video, according to an exemplary embodiment. Figure 4 Figure (a) shows a schematic diagram of the video generation page. The video is the Nth "Rap Series" video. The video generation page displays an export control 401. In response to the triggering operation of the export control 401, the save page is displayed. The save page displays the configuration information of multiple editing angles in the video, that is, it displays... Figure 4Figure (b) shows multiple editing angles, including character style, rap timbre, effect combination, speech bubble visuals, music style, and opening / closing sequences. Below each editing element's name, the corresponding editing angle's configuration information is displayed. The save page also displays the target name and target tag of the first target style template. The target name is "Friends Series • XX Version," and the target tag is "Rap Series" and "Strong Reversal." Both the name and tag of the first target style template can be modified by the user. The save page also displays save control 402 and skip control 403. Save control 402 means "Save to Style Library," and skip control 403 means "Skip, Do Not Save." In response to triggering the skip control 403, the style template is not saved. In response to triggering the save control 402, save control 402 immediately becomes a loading state (spinning animation), indicating that the system is writing configuration information to the style library. After saving, the following is displayed: Figure 4 Figure (c) shows that the first target style template has been saved to the style library, the arrangement elements in the first target style template, and the style library viewing control 404. The style library viewing control 404 is used to view the style templates in the style library. The save page closes automatically after a preset time (e.g., about 2 seconds) to show the normal state of video export completion, without blocking the user's subsequent operations.

[0097] In response to Figure 4 The triggering operation of the style library control 404 shown in Figure (c) or the triggering operation of the style library entry on other pages in the video editing tool will display... Figure 5 Figure (a) shows the style library page displayed in response to a view operation. This page displays at least one style template set, showing the name and number of style templates included in each set. The name of each style template set is the same as the name of the included style templates. A recommendation label (i.e., "Activating") is displayed at the corresponding position of the recommended style template set, indicating that the recommended style template set is selected. For the selected style template set (i.e., the recommended style template set), the style templates included in it are displayed sequentially according to their save time, i.e., "v1•XX version", "v2•XX version", and "v3•XX version" are displayed according to their save time. Activation controls 501 are displayed at the corresponding positions of the non-recommended style template sets. In response to a trigger operation on any activation control 501, the non-recommended style template set corresponding to that activation control 501 is displayed as a recommended style template set.

[0098] like Figure 5As shown in Figure (a), on the style library page, a recommendation label (i.e., "current") is displayed at the corresponding position of the recommended style template (i.e., "v3•XX version") in the recommended style template set. Recommendation setting control 502 and comparison control 503 are displayed at the corresponding positions of the non-recommended style templates in the recommended style template set. In response to the triggering operation of the recommendation setting control 502 corresponding to "v2•XX version", "v2•XX version" is displayed as the recommended style template. In response to the triggering operation of the comparison control 503 of "v2•XX version", the comparison page is displayed, as shown below. Figure 5 Figure (b) shows the configuration information that differs between "v2•XX version" and "v3•XX version" on the comparison page, and displays the close comparison control 504 and the recommended settings control 505. In response to the trigger operation of the close comparison control 504, the comparison page is closed. In response to the trigger operation of the recommended settings control 505, "v2•XX version" is displayed as the recommended style template, that is, the recommended label will be displayed in the corresponding position of "v2•XX version", while the recommended label in the corresponding position of "v3•XX version" will disappear.

[0099] The terminal responds to new video creation operations on the generation page or style template viewing operations during video editing by displaying style templates from the style library, such as... Figure 6 Figure (a) shows the style library page, which displays at least one set of style templates. The recommended style template set is selected, and the recommended style template within that set is also selected. A confirmation control 601 is also displayed on the style library page. If the recommended style template is the user's desired style template, in response to the user's action on the confirmation control 601, the multiple arrangement elements included in the selected recommended style template (i.e., "Friends Series • XX Version v3") are displayed, such as... Figure 6 As shown in Figure (b), in response to the reuse operation of the selected arrangement elements in "Friends Series • XX Version v3" (that is, the trigger operation of "Apply Selected Module • Start Creating"), the configuration information included in the selected arrangement elements in "Friends Series • XX Version v3" is displayed as the video's configuration information; of course, it can also directly enter the video generation page in response to the trigger operation of not using the style template control 602. If the recommended style template is not the style template the user needs, the style library page also displays a filter control 603, which allows the user to filter based on the style template's name or tag.

[0100] The terminal responds to new video creation operations on the generation page or style template viewing operations during video arrangement. It can also directly display recommended style templates and multiple arrangement elements within the recommended style templates, such as displaying... Figure 6In Figure (b), if the recommended style template is the one the user needs, the user can reuse the necessary layout elements from the recommended style template, reducing the number of steps. If the recommended style template is not the one the user needs, the user can change to another style template by replacing the controls. In response to the triggering of the control replacement operation, the following is displayed: Figure 6 The style library page shown in Figure (a) allows users to select from a collection of style templates and style templates.

[0101] The above embodiments describe a video generation method based on a selected style template. However, in the process of generating a video based on dramatic chat messages, it is also necessary to obtain chat logs. The following describes the steps for obtaining chat logs and provides an overall description of the method for generating video based on chat logs and a target style template.

[0102] Figure 7 This is a flowchart illustrating a video generation method according to an exemplary embodiment, see [link to flowchart]. Figure 7 In this embodiment, the method is executed by an electronic device. The following description uses an electronic device provided as a terminal as an example. The method includes the following steps: In step 701, the terminal displays a generation page, which shows multiple plot stages in the dramatic structure. The generation page is used to generate chat logs through the intelligent agent.

[0103] In this step, the generation page is the page in the chat rap video generation tool used to generate chat logs through an intelligent agent. For example, it is displayed in response to a trigger operation on the chat rap video generation tool. Dramatic structure is a narrative organization framework that, through the orderly scheduling of the release order and rhythm of information from different content within a narrative event, achieves different emotional impacts on the audience. Consequently, chat logs with a dramatic structure typically have better dramatic appeal. Plot stages refer to the components of a dramatic structure. A dramatic structure includes multiple plot stages, such as setup, conflict, twist, climax, and conclusion, etc. A dramatic structure can also include more or fewer plot stages, which is not specifically limited in this embodiment. When the dramatic structure includes fewer plot stages, the configuration threshold for plot stages can be lowered, making it suitable for generating shorter chat logs (i.e., generating shorter videos), and also suitable as a dramatic structure for guiding new users. When the dramatic structure includes more plot stages, for more complex narrative events, higher-quality chat logs can be generated based on this dramatic structure.

[0104] When displaying multiple plot stages in a dramatic structure, these stages are presented in the order of the dramatic structure. Accordingly, in some embodiments, step 701 includes displaying the multiple plot stages in the order of the dramatic structure on the generated page. In this step, the orderly display of the plot stages indirectly demonstrates the narrative logic of the dramatic structure, serving as a prompt to the user. This helps the user break down the narrative events based on the plot stages, reducing the user's learning curve and improving operational efficiency.

[0105] In step 702, in response to a configuration operation for at least one episode stage on the generation page, the terminal displays the configured content for at least one episode stage.

[0106] In this step, the configuration operation refers to configuring the content or intensity of a plot phase. Configured content refers to the content that has been configured for a plot phase through the above configuration operations, such as the descriptive text within the plot phase or the intensity of the plot phase.

[0107] The configuration operation may configure at least one of the content and semantic strength of a plot stage. In some embodiments, step 702 includes at least one of the following: in response to a configuration operation on the content of at least one plot stage on the generation page, displaying descriptive text for at least one plot stage; and in response to a configuration operation on the semantic strength of at least one plot stage on the generation page, displaying the semantic strength of at least one plot stage, wherein the semantic strength indicates the semantic strength of the content in the plot stage. In this step, the descriptive text is used to describe a portion of the events corresponding to the plot stage, and the semantic strength refers to the semantic strength of the content generated by the agent in the plot stage. This step allows for the configuration of at least one of the descriptive text and semantic intensity for each plot stage. This is equivalent to binding at least one of these elements to the corresponding plot stage. When the descriptive text is bound to the corresponding plot stage, the core event carried in each plot stage is the event indicated by the descriptive text. The plot stage and descriptive text work together to define the narrative skeleton. Therefore, when an agent generates chat logs based on the plot stage and descriptive text, it is equivalent to generating chat logs under the constraints of the narrative skeleton. This generation process will not deviate from its intended path, ensuring that the generated chat logs have a dramatic structure. When semantic intensity is bound to the corresponding plot stage, the semantic intensity of the corresponding part in the chat logs generated by the agent can be controlled, achieving more precise control over the chat logs.

[0108] In some embodiments, when the plot stage is a setup, the semantic intensity of the setup indicates the suspense concentration, which in turn indicates the degree of anticipation the audience feels for the corresponding part of the chat log in the plot stage; when the plot stage is a conflict, the semantic intensity of the conflict indicates the intensity of the confrontation, which in turn indicates the intensity of the contradictions and conflicts within the plot stage; when the plot stage is a twist, the semantic intensity of the twist indicates the degree of surprise, which in turn indicates the degree to which the corresponding part of the chat log exceeds the audience's expectations; when the plot stage is a climax, the semantic intensity of the climax indicates the intensity of the emotional impact, which in turn indicates the intensity of the emotional fluctuations the corresponding part of the chat log in the plot stage causes in the audience; and when the plot stage is a conclusion, the semantic intensity of the conclusion indicates the length of the aftertaste, which in turn indicates the duration for which the content of the plot stage evokes lingering thoughts in the audience. In this step, the semantic intensity corresponding to different plot stages is illustrated. Through each semantic intensity, different parts of the generated chat log can have different semantic intensity, and thus different characteristics. For example, by configuring the degree of surprise to multiple intensities from low to high, the chat logs generated by the agent based on the reversal, degree of surprise and corresponding descriptive text are multiple intensity versions from "lighthearted and humorous" to "super funny".

[0109] When configuring the content of a plot stage, users can fill in the information in the plot stage, or existing chat logs can be uploaded, and the agent can generate and display the content of the plot stage based on the existing chat logs. Accordingly, in some embodiments, in response to the configuration operation of at least one plot stage on the generation page, displaying the descriptive text of at least one plot stage includes: in response to the filling operation of at least one plot stage on the generation page, displaying the filled content in at least one plot stage as the descriptive text of at least one plot stage; or, in response to the upload operation of existing chat logs on the generation page, displaying the descriptive text of at least one plot stage generated by the agent based on the existing chat logs. This step provides two ways to configure descriptive text in plot stages. The first is through user input during the plot stage, and the second is through analysis of uploaded existing chat logs by an agent. These two methods can have different generation modes. For example, the first is a completely new generation mode, where the agent generates text based on the configured content of the plot stage. The second is a rewriting mode, where the agent generates descriptive text for at least one plot stage based on existing chat logs. The generated chat logs differ from the existing chat logs, effectively rewriting them. This method eliminates the need for users to manually input descriptive text in the beat slots, improving the efficiency of beat slot configuration. Furthermore, this method supports uploading existing chat logs, expanding the sources of material for generating chat logs.

[0110] In step 703, the terminal responds to the generation operation on the generation page by displaying chat logs generated by the agent based on multiple plot stages and the configured content of each plot stage.

[0111] In this step, the "generate" operation refers to the operation used to generate the chat script. For example, after configuring the plot stage, it triggers the generation control on the generation page. The generation control can be displayed in various forms such as a "Next" button or a "Generate Chat History" button. The chat history includes a record of chat messages between at least two people. For example, chat logs can also be generated in segments by an agent based on each plot stage and at least one of the configured content of that plot stage. This method includes the following steps: generating a first segment by an agent based on the first plot stage and at least one of the configured content of that plot stage; generating a second segment by an agent based on the first segment, the second plot stage, and at least two of the configured content of that plot stage; generating a third segment by an agent based on the first segment, the second segment, the third plot stage, and at least two of the configured content of that plot stage; and generating segments corresponding to each plot stage sequentially according to the order of the dramatic structure. Each time a segment is generated, the agent generates the segment based on the segments corresponding to the plot stages preceding the current plot stage, the current plot stage, and the configured content of the current plot stage. In this method, each generation is generated under the constraints of the current plot stage and the configured content of the current plot stage, ensuring that the plot stage and the configured content of the plot stage are not lost. At the same time, each generation is also based on the segments corresponding to the plot stages preceding the current plot stage, enabling the agent to perceive the aforementioned generated chat messages and ensuring the semantic coherence between the generated segments. For example, when chat logs are generated by an agent segmenting them based on each plot stage and its configured content, this method can also include the following steps: The agent generates the chat logs segmented separately based on each plot stage and its configured content. In this method, the plot stages are highly constrained. To ensure the coherence between chat logs corresponding to different plot stages, the agent can further refine the chat content corresponding to each plot stage. This step gives the generated chat logs a dramatic structure, improving the generation quality.

[0112] In step 704, in response to the video creation operation based on the chat history, the terminal displays the target style template in the style library, which is used to generate the video.

[0113] To improve the efficiency of users' decision-making regarding style templates, a target style template is displayed. When the target style template is not the one the user desires, a style template switch can be performed. In some embodiments, step 704 includes displaying the name of the target style template and the multiple arrangement elements included in the target style template. At this time, the user can select at least one target arrangement element from the multiple arrangement elements included in the target style template.

[0114] In step 705, when at least one target choreography element among the multiple choreography elements included in the target style template is selected, the terminal, in response to the video generation operation, displays a video generated by the agent based on at least one target choreography element and chat history, wherein the multiple choreography elements respectively indicate configuration information for different choreography angles of the video.

[0115] This step allows for the selection of desired choreography elements from the target style template, enabling personalized application of these elements in video generation and improving the flexibility of reusing choreography elements within the style template.

[0116] After the user is satisfied with every sentence in the chat history, the terminal can further generate a video file based on the chat history and at least one target arrangement element, transforming the chat history and at least one target arrangement element into a visual chat rap video. Specifically, the terminal obtains the sender identifier and chat bubble style attributes (including bubble color, rounded corners, font style, avatar information, etc.) of each chat message in the chat history, associates the corresponding sender identifier and bubble style with each sentence, and configures the corresponding arrangement element for each sentence based on at least one target arrangement element. During the video rendering stage, when the background music plays to the moment corresponding to a certain sentence, the terminal presents the content of that sentence line by line on the video screen with the chat bubble style and arrangement element associated with that sentence. Finally, the terminal generates and outputs a chat rap video file, realizing the coordinated presentation of sound, words, and images.

[0117] The above mainly describes the principle of chat log generation. The following explains the chat log generation method from the perspective of page display, and takes the example of a user wanting to create a chat rap video to introduce the chat log generation method.

[0118] The method of this disclosure mainly includes two paths. The first path is a new generation mode, which requires the user to manually configure the description text of the plot stage. The second path is a rewriting mode, which automatically configures the description text of the plot stage based on the uploaded existing chat history. The page display of these two paths will be described below.

[0119] like Figure 8 The diagram shown is a schematic representation of a generation page according to an exemplary embodiment. In response to a trigger operation on the chat rap video generation tool, a generation page is displayed. The generation page displays a first mode control 801 and a second mode control 802. The first mode control is set to "Generate New," and the second mode control is set to "Rewrite Real Chat." The first mode control is selected, meaning the generation page is in the "Generate New" mode. Figure 8As shown in Figure (a), the generated page displays multiple plot stages of the dramatic structure. The five plot stages are: setup (initial situation and character relationships), conflict (establishing suspense), twist (unexpected revelation), climax (emotional outburst, user-set "semantic intensity" slider 0-100), and resolution (emotional resolution). These plot stages are displayed in the order of the dramatic structure. Pre-filled descriptive text is displayed for each plot stage as an example, which the user can directly use or modify. In response to a fill-in operation on at least one plot stage on the generated page, the filled-in content for at least one plot stage is displayed as the descriptive text for that plot stage, such as "My friend said he had something to say, and the atmosphere was a bit strange" in the setup. The generated page also displays adjustment controls 803 for each plot stage. In response to triggering any adjustment control, the corresponding track and slider on the track can be displayed, such as... Figure 8 As shown in Figure (b), in response to the operation of adjusting the position of the slider in the track, the slider is shown to change from the first position to the second position on the track, thereby adjusting the semantic intensity corresponding to the plot stage.

[0120] like Figure 8 As shown in Figure (a), the generation page also displays the target style and target visual elements. The target style refers to the chat platform style, including Style 1, Style 2, Style 3, etc. The target style "Style 1" is selected and is the system default style. Users can select other styles to modify the target style. The target visual elements refer to character settings, including the character's name and avatar. More can be included, such as bubble styles and chat backgrounds. The target visual elements are generated by the agent based on the system default style and the character's identity as described in the pre-filled system description text. The generation page also displays an "AI Regenerate" control. Responding to the trigger operation of the "AI Regenerate" control, the regenerated visual elements are displayed as the target visual elements. Each visual element in the target visual elements can also be modified individually. The generation page also displays generation control 804, used to generate chat logs. The generation controls are "Next" and "Generate Script" in the figure.

[0121] Once the plot stages are configured on the generated page, and the target style and visual elements are modified, in response to the "Next" or "Generate Script" trigger, the chat log generated by the agent based on multiple plot stages, the configured content of each plot stage, the target style, and the target visual elements is displayed, such as... Figure 8As shown in Figure (c), the chat messages in the chat log are displayed sequentially according to their plot stages within the dramatic structure. Plot stage labels are displayed at the corresponding positions of the chat messages in different segments of the chat log, indicating the plot stage to which each segment belongs. When the chat log matches the user's desired chat log, clicking "Confirm and Enter MV Arrangement" initiates the process of generating a video based on the chat log. The chat log is exported in standard message format, and the intelligent agent generates the video based on the exported chat log and other input content. A regeneration control 805 is also displayed at the corresponding position of each different segment of the chat message, i.e., "..." "Regenerate this segment" means that when the chat history is not the one the user wants, clicking the corresponding regenerate control 805 will only regenerate the chat messages for that segment, while the chat messages for the remaining segments will remain unchanged. The regenerated chat history will then be displayed. The generation page also displays controls for adjusting the semantic strength of different segments of the chat messages. In response to triggering these controls, the following can be displayed: Figure 8 The track and slider shown in Figure (b) respond to adjustments in the slider's position, displaying the regenerated chat history as the chat history. Similarly, responding to modifications to chat messages within the chat history also results in the regenerated chat history being displayed as the chat history. The chat history illustrated here is located on a different generation page than multiple plot stages. In this case, the target visual elements are still displayed on the generation page, and their regeneration and modification are supported. That is, when the chat history is not the user's desired chat history, the chat messages or semantic strength of the entire chat history can be regenerated for that segment.

[0122] In the new generation mode, the above Figure 8 Figures (a), (b), and (c) illustrate the page layout using the example of multiple plot stages and generated chat logs located on different generated pages. However, multiple plot stages and generated chat logs can also be located on the same generated page.

[0123] like Figure 8 As shown in Figure (a), in response to the selection of the second mode control on the generation page, the generation page in rewrite mode is displayed, as follows: Figure 9As shown in Figure (a), an upload control is displayed on the generated page. In response to the upload operation of existing chat records via the upload control, the event segment information of the agent's target core event is displayed, with each event segment corresponding to a plot stage. The target core event is identified by the agent based on existing chat records. The page also displays the target style identified by the agent based on existing chat records, and the target visual elements generated by the agent based on at least one of the target style and role identity. Figure 8 The new generation mode is the same as in the previous version, and the semantic intensity can also be configured in the plot stage. The target style and target visual elements can also be modified, which will not be elaborated here.

[0124] Once the plot stages are configured on the generated page, and the target style and visual elements are modified, in response to the "Next" or "Generate Script / Rewrite" trigger, the chat log generated by the agent based on multiple plot stages and the configured content of each plot stage is displayed, such as... Figure 9 As shown in Figure (b), the chat messages in the chat history are displayed sequentially according to their plot stage within the dramatic structure, and a comparison of existing chat history with the generated chat history is also displayed. On this generation page, editing controls are displayed at corresponding positions in the chat history. In response to triggering the editing controls, at least one of the following can be performed: regenerating chat messages from different segments of the chat history, adjusting the semantic strength of chat messages from different segments, or modifying chat messages from different segments.

[0125] In rewrite mode, Figure 9 Figures (a) and (b) illustrate the page layout using the example of multiple plot stages and generated chat logs located on different generation pages. However, multiple plot stages and generated chat logs can also reside on the same generation page. The above... Figures 8 to 9 This example illustrates how to display the first and second mode controls on the generation page. However, it's also possible to display the first and second mode controls on the generation page instead of the generation page itself. Instead, the upload control can be displayed permanently on the generation page. When you need to upload existing chat history, you can use the upload control. When you don't need to upload existing chat history, you can manually configure the plot stage.

[0126] In response to Figure 8 The "Confirm and Enter MV Arrangement" trigger operation in Figure (c) can display the target style template, that is, as shown below. Figure 6 In Figure (a) or Figure (b), taking Figure (b) as an example, multiple arrangement elements included in the target style template can be selected. In response to the trigger operation of "Apply selected module • Start creation" in the figure, a video generated by the agent based on the chat history and at least one target arrangement element selected in the target style template is displayed.

[0127] The above embodiments describe a video generation method based on chat logs and target style templates. However, in the process of generating videos based on dramatic chat messages, the chat logs can also be rewritten in a lyric-like manner (that is, rewritten into target text). The following describes the steps of rewriting chat logs and provides an overall description of the video generation method based on target text and target style templates.

[0128] Figure 10 This is a flowchart illustrating a video generation method according to an exemplary embodiment, see [link to flowchart]. Figure 10 In this embodiment, the method is executed by an electronic device. The following description uses an electronic device provided as a terminal as an example. The method includes the following steps: In step 1001, the terminal displays multiple rhyming schemes on the generated page based on the selected background music and chat history.

[0129] In this embodiment, the rhyming scheme refers to the rhyme constraint rules used when rewriting text into lyrics. Each rhyming scheme corresponds to a specific rhyme group (such as "a rhyme", "an rhyme", "ai rhyme", etc.), which specifies the rhyme to be used at the end of each sentence after rewriting. After obtaining the background music selected by the user and the initial text to be rewritten, the terminal analyzes both: on the one hand, it identifies the rhythmic features of the background music, and on the other hand, it extracts the corpus information of the initial text. Based on this, it generates multiple rhyming schemes that are suitable for the current music atmosphere and text content, and displays these multiple rhyming schemes to the user on the generation page for the user to browse and select.

[0130] For example, if a user uploads a piece of upbeat background music and a daily chat log between friends, the terminal can recommend several alternative rhyme schemes such as "a rhyme", "ai rhyme", and "an rhyme" based on the music's BPM (Beats Per Minute) and emotional tone, combined with the high-frequency ending words in the chat log.

[0131] In step 1002, when the target rhyming scheme is selected among multiple rhyming schemes, the terminal responds to the rewriting operation by displaying the target text obtained by rewriting the chat history based on the target rhyming scheme, wherein the end rhymes of each sentence in the target text conform to the target rhyming scheme.

[0132] In this embodiment of the disclosure, the target rhyming scheme refers to the scheme actually selected by the user among the multiple rhyming schemes displayed in step 1001. After detecting the user's selection of the target rhyming scheme, the terminal further responds to the user-triggered rewriting operation, using the rhyme specified by the target rhyming scheme as a unified constraint, and rewrites each sentence in the initial text one by one, displaying the rewritten target text on the generated page. Throughout the rewriting process, the terminal ensures that the target text and the initial text remain semantically similar, while also ensuring that the end of each sentence in the target text rhymes with the rhyme specified by the target rhyming scheme.

[0133] Continuing with the example in step 1001, if the user selects "a rhyme" from "a rhyme", "ai rhyme" and "an rhyme", the terminal will rewrite all messages in the chat history with "a rhyme" as the unified rhyme. After the rewriting is completed, the user can see that the end of each message ends with "a rhyme" and the overall semantics are consistent with the original chat history.

[0134] In the method of this disclosure, a rhyming scheme is recommended based on two dimensions of information: background music and initial text. This allows users to select a target rhyme from multiple suitable rhyming schemes on a visual page without needing professional rhyming knowledge, thus lowering the creative threshold. Simultaneously, the initial text is rewritten in batches using the user-selected rhyming scheme as a constraint, ensuring that the end of each sentence in the output target text consistently rhymes with the target rhyme. Compared to the traditional method of manually refining rhyming words sentence by sentence, this significantly improves the efficiency of human-computer interaction and the efficiency of rewriting text into lyrics. Furthermore, this method establishes a connection between music and text during the rewriting stage, making the rewritten result naturally rhymed with the background music. This avoids the problem of misaligned sound caused by rewriting lyrics first and then adding music, or vice versa, improving the usability and matching accuracy of the rewritten result in practical applications.

[0135] After the user selects a rhyming scheme but before triggering the rewriting operation, the terminal can also provide the user with constraint options to control the rewriting strategy, allowing the user to specify the priority of the rewriting according to current needs. Through this configuration, the user can not only determine the rhyme direction of the target text but also decide the trade-off strategy when the rewriting algorithm encounters conflicts between semantics, rhyme, and rhythm during execution, thereby obtaining a more satisfactory rewriting result. Accordingly, in some embodiments, the method further includes: displaying multiple rewriting constraints on the generation page, each constraint indicating the relative importance of semantic preservation, rhyme matching, and rhythm alignment during rewriting; and, in response to the rewriting operation, displaying the target text rewritten from the chat history based on the target rhyming scheme when the target rhyming scheme is selected among multiple rhyming schemes and the target rewriting constraint is selected, displaying the target text rewritten from the chat history based on the target rhyming scheme and the target rewriting constraint. In other words, when all three cannot be satisfied simultaneously, which dimension takes priority and which dimension can be appropriately compromised? For example, for narrative chat content, users may be more concerned about whether the original semantics are preserved after rewriting, in which case "semantic preservation priority" can be chosen as the constraint; for chorus sections that pursue rhythmic impact, users may be more concerned about whether the end of the sentence rhymes, in which case "rhyme matching priority" can be chosen as the constraint; for fast-paced music with a tight rhythm, users may be more concerned about whether the number of syllables in each sentence strictly matches the beat capacity, in which case "beat alignment priority" can be chosen as the constraint.

[0136] In this step, by displaying multiple rewriting constraints (ranking the importance of semantic preservation, rhyme matching, and beat alignment) on the generation page, users can flexibly specify their rewriting priority strategy based on their current creative needs. For example, semantic preservation is prioritized in narrative-heavy paragraphs to ensure story clarity, while rhyme matching is prioritized in high-energy paragraphs such as the chorus to ensure rhythmic impact. After the user selects the target constraint, the system executes the rewriting according to that constraint. This ensures that the rewriting result meets the rhyme scheme requirements while also satisfying the user's expectations in terms of semantic preservation and beat alignment accuracy. This avoids the limitations of a single rewriting strategy that cannot cater to the creative needs of different paragraphs, improving the controllability of the rewriting process and the adaptability of the rewriting result to the user's personalized needs.

[0137] To more accurately demonstrate the correspondence between background music and target text, the background music can be divided into multiple beat squares according to the smallest rhythmic unit. The corresponding sentences from the target text are displayed in each beat square. Accordingly, in some embodiments, the target text obtained by rewriting the chat log is displayed, including: displaying multiple beat squares of the background music on the generation page, each beat square indicating a smallest rhythmic unit of the background music; and displaying the corresponding sentences from the target text in each beat square, where the sentences in each beat square are the lyrics of the beat square. After selecting one or more target schemes from multiple rhyming schemes, the user triggers a rewriting instruction by clicking the rewrite button. Upon receiving the instruction, the terminal uses the rhyme specified by the user-selected target scheme as a rewriting constraint, rewriting each sentence in the initial text one by one into lyrics that uniformly rhyme at the end of each sentence, and presenting the result on the generation page after the rewriting is complete. Unlike conventional plain text display, the terminal simultaneously visualizes and breaks down the background music's timeline when presenting the rewritten results. It divides the music into multiple beat squares (each beat square corresponds to 1 beat) according to the smallest rhythmic unit, and then fills each rewritten lyric into its corresponding beat square for display. The lyric in each beat square represents the content that beat square should carry at that rhythmic position, allowing users to directly see "which rhythm point corresponds to which lyric."

[0138] By visually representing the beat grid of the background music on the generated page and filling the corresponding beat grids with the phrases from the rewritten target text, users can intuitively see the specific position of each lyric on the music timeline—which rhythm corresponds to which phrase, making it immediately clear. This visual mapping method of "lyrics filling into beat grids" establishes a spatial correspondence between abstract musical rhythms and specific lyric content. Users can check whether each lyric is aligned with the correct rhythmic position without needing music theory knowledge, improving the efficiency and accuracy of checking the alignment between lyrics and beats, and reducing the debugging costs during subsequent audio synthesis.

[0139] When displaying corresponding sentences from the target text in multiple beat frames, the terminal can adopt differentiated layout methods for the climax of the background music. Accordingly, in some embodiments, displaying corresponding sentences from the target text in multiple beat frames includes: determining the sentences in the target text corresponding to the climax of the background music as climax sentences; and displaying at least two climax sentences in each beat frame corresponding to the climax sentences. That is, in ordinary paragraphs, each beat frame displays one lyric (1 line per frame); while in climax paragraphs, each beat frame displays two lines of lyrics simultaneously (2 lines per frame), and the number of words in these two lines of lyrics is shortened to about half a line, forming a dense and compact visual rhythm. This, combined with the high-energy atmosphere of the chorus, creates a visual explosion, achieving an audiovisual synergy effect where the higher the musical energy, the greater the visual information density.

[0140] By identifying the climax of the background music, the target text phrases at corresponding positions are designated as climax phrases. At least two climax phrases are then displayed in a densely packed layout within the corresponding beat grid of the climax phrase. This creates a visually compact and intense rhythm for high-energy sections like the chorus, achieving audiovisual synergy with the climax atmosphere of the background music. Compared to using the same layout density (one phrase per grid) for climax and regular sections, this burst-grid layout concentrates more lyric information within a limited screen space, enhancing the visual impact and information density of the climax. Visually, it strengthens the perception of energy changes in the music, improving the integrated audiovisual effect of the chat rap video.

[0141] In step 1003, in response to the video creation operation based on the target text, the terminal displays the target style template in the style library, which is used to generate the video.

[0142] To improve the efficiency of users' decision-making regarding style templates, a target style template is displayed. When the target style template is not the one the user desires, a style template switch can be performed. In some embodiments, step 1003 includes: displaying the name of the target style template and the multiple arrangement elements included in the target style template. At this time, in response to the user's selection operation of at least one target arrangement element among the multiple arrangement elements included in the target style template, at least one target arrangement element is displayed as selected.

[0143] In step 1004, when at least one target choreography element among the multiple choreography elements included in the target style template is selected, the terminal, in response to the video generation operation, displays a video generated by the agent based on at least one target choreography element and target text, wherein the multiple choreography elements respectively indicate configuration information for different choreography angles of the video.

[0144] Through this step, it is supported to select the desired arrangement elements from the target style template, which realizes the personalized application of the required arrangement elements in video generation, and also improves the flexibility of reusing the arrangement elements in the style template.

[0145] After the user is satisfied with each sentence of the rewritten target text, the terminal may further generate a video file based on the rewriting result, and convert the text content and at least one target arrangement element into a visualized chat rap video. Specifically, the terminal binds each sentence in the target text to the corresponding beat grid position in the background music, and establishes a mapping relationship of the starting playback moment of each sentence on the music timeline. The terminal acquires the sender identifier and chat bubble style attributes of each chat message in the initial chat record (including bubble color, fillet radian, font style, avatar information, etc.), associates each sentence with the corresponding sender identifier and bubble style, and configures the corresponding arrangement element for each sentence based on at least one target arrangement element. In the video rendering stage, when the background music plays to the moment corresponding to a certain sentence, the terminal presents the content of the sentence on the video frame one by one with the chat bubble style and arrangement element associated with the sentence. Finally, the terminal generates and outputs a chat rap video file, which realizes the collaborative presentation of sound, words and images.

[0146] The foregoing mainly describes the principle of generating a video based on at least one target arrangement element and the target text, and the foregoing method will be described below from the perspective of page display.

[0147] As Figure 11 shown, in response to a confirmation operation on the generated chat record, it is possible to display Figure 11 the diagram (a) in, in Figure 11 the diagram (a) in, the rhyme schemes recommended based on the currently selected background music and initial text include 3 rhyme schemes of "a rhyme", "e rhyme" and "ao rhyme", and each rhyme scheme displays representative word examples and sound sense descriptions. Taking the "a rhyme" as an example, the representative word examples of the "a rhyme" include a plurality of words such as "lai · bai · wai · kai · dai · huai · ai"; the sound sense description of the "a rhyme" is "open and clear". The "a rhyme" is the currently selected rhyme scheme. Two rewriting constraints of "semantic preservation" and "rhythm preservation" are displayed on this page. "Semantic preservation" means that the priority of semantic similarity between the target text and the initial text during rewriting is higher than the priority of end-of-sentence rhyme matching; "rhythm preservation" means that the priority of end-of-sentence rhyme matching during rewriting is higher than the priority of semantic similarity between the target text and the initial text.

[0148] In response to the Figure 11 trigger operation of "Start Rewriting" in the diagram (a), it is possible to display Figure 11Figure (b), in this figure, the initial text is the chat history between Character A and Character B, which contains a total of 8 chat messages. The chat history is rewritten using the "a rhyme" to obtain the target text, in which all characters at the end are of the "a rhyme", such as "zai", "wai", "bai", "lai", "kai", "ha", etc. Each statement in the target text (i.e., each rewritten chat message) is displayed in the corresponding beat cell 1101, to reflect the rhythm of the rewritten chat history. In this figure, the number of syllables of the 3rd statement is 12, which exceeds the recommended maximum syllable capacity (11). At this time, the maximum syllable capacity of the 3rd statement will be highlighted, and a prompt message will be displayed — "Syllables in line 3 exceed the limit (11 syllables, recommended boundary ≤11 syllables); it is recommended to cut it short as: XXXXXXXX (8 syllables) for partial rewriting", to remind the user to make adjustments. The user can make adjustments according to this suggestion, make custom adjustments, or ignore this issue and proceed directly with subsequent operations. In this figure, the "semantics preservation" constraint condition 1102 and the "rhythm preservation" constraint condition 1103 are displayed in each beat cell. When any rewriting constraint condition is selected, in response to the trigger operation on the rewriting control 1104 in the beat cell, the terminal displays a new statement obtained by rewriting the statement again based on the selected rewriting constraint condition.

[0149] As shown Figure 11 In Figure (c), under the condition that the user confirms that the syllables in each statement in the target text are correct, for example, in response to the user's operation on Figure 11 The trigger operation of "Continue" in Figure (b), display Figure 11 Figure (c) in, in this process, the terminal obtains the climax position marker of the background music, determines that the 7th statement and the 8th statement in the target text are at the climax position and belong to climax statements, then the terminal places the 7th statement and the 8th statement in one beat cell to form a dense and compact visual rhythm, which cooperates with the high-energy atmosphere of the chorus section to create a visual sense of burst.

[0150] In response to the Figure 11 Trigger operation of "Export Lyrics" in Figure (c), the target style template can be displayed, that is, as shown in Figure 6 Figure (a) or Figure (b), taking Figure (b) as an example, at this time, multiple arrangement elements included in the target style template can be selected. In response to the trigger operation of "Apply Selected Modules • Start Creation" in the figure, a video generated by the agent based on the target text and at least one target arrangement element selected in the target style template is displayed.

[0151] The above embodiments describe a video generation method based on target text and target style template. However, in the process of generating videos based on dramatic chat messages, videos can be generated based on chat logs (or target text) and target arrangement elements in the target style template. The following is an overall description of the method for generating videos based on chat logs and target style template.

[0152] Figure 12 This is a flowchart illustrating a video generation method according to an exemplary embodiment, see [link to flowchart]. Figure 12 In this embodiment, the method is executed by an electronic device. The following description uses an electronic device provided as a terminal as an example. The method includes the following steps: In step 1201, the terminal displays on the generation page, based on at least one target orchestration element, orchestration elements that are adapted to each chat message in the chat history. The orchestration elements of each chat message are used to indicate how the chat message is presented in the video, and the orchestration elements of each chat message are matched with the chat characteristics of the character who sent the chat message.

[0153] In this embodiment of the disclosure, the chat log is a user-uploaded dialogue containing at least two characters, such as conversations between friends or interaction records in a group chat. Arrangement elements refer to control information used to define the presentation of chat messages in the video, determining "what the chat message looks like" and "how it appears" in the video. Chat characteristics refer to the perceptible attributes exhibited by characters in the dialogue, such as the character's emotional state, consistent expression style, and the direction of their statements.

[0154] After the terminal obtains the chat history and at least one target embellishment element from the target style template, it automatically identifies the role associated with each chat message through an intelligent agent. Based on the chat characteristics of the role that sent the message, the intelligent agent adapts the corresponding embellishment element to the chat message based on at least one target embellishment element. This ensures that the embellishment elements for the same role remain consistent across different chat messages, while the embellishment elements for different roles are distinguishable. The terminal then associates the adapted embellishment elements with the corresponding chat messages and displays them on the generated page, allowing users to view the presentation effects configured for each chat message.

[0155] The above example illustrates the situation where the user selects at least one target arranging element from the target style template. If the user does not use a style template, the terminal can also automatically identify the role of each chat message after obtaining the chat history, and adapt the corresponding arranging element for the chat message based on the chat characteristics of the role that sent the message. This ensures that the arranging elements of the same role remain consistent across different chat messages, while the arranging elements of different roles are distinguishable.

[0156] For example, in a chat log of a friend's conversation, the chat messages of character A are adapted with a lively character icon and light-hearted animation, while the chat messages of character B are adapted with a calm and composed character icon and a slow-in animation. Users can clearly see on the generated page that each chat message is assigned different layout elements according to the chat characteristics of each character.

[0157] When a user generates a video using a style library, they can finely select which types of choreography elements to reuse. Accordingly, in some embodiments, choreography elements have multiple choreography angles, and choreography elements with different angles are used to provide different presentation dimensions in the video. The generation page displays choreography elements adapted to each chat message in the chat history, including: on the generation page, arranging and displaying each chat message and its corresponding role in the chat history along a first direction according to the order of the chat messages; and on the generation page, arranging and displaying multiple types along a second direction, with the display areas of the multiple types intersecting with the display areas of each chat message to form multiple grids, each grid displaying the choreography elements used for a corresponding chat message in a corresponding type. When any type among the multiple types is selected, in response to the user operation, the terminal displays a video generated based on the choreography elements of the selected type and the chat history. In other words, when users call the style library, they can choose to apply only some types of styles (for example, only apply motion effect configurations and music segment configurations, while retaining the current scheme for character identifiers and emoticon image configurations), instead of applying all types of layout elements in the style library. This refined reuse method allows users to flexibly combine different types of layout elements according to the characteristics of different chat records, improving the flexibility and accuracy of style library reuse.

[0158] By dividing orchestration elements into multiple dimensions and arranging message sequences along the first direction and effect types along the second direction on the generated page, a two-dimensional grid structure is formed. The orchestration configuration of each message in each type is centrally displayed in the corresponding grid, allowing users to view the orchestration configuration of all messages in multiple effect dimensions on the same page simultaneously without having to switch repeatedly between multiple pages or levels. This improves the efficiency of users in reviewing and checking the completeness of the orchestration scheme. At the same time, the grid-based display method makes the distribution of orchestration configurations clear at a glance, reducing the time cost for users to find specific messages or specific type configurations and improving human-computer interaction efficiency.

[0159] After a user selects a style template from the application style library, the terminal can display a preview of the configuration of each arrangement element under that style template before it is applied to the current chat history. The user can confirm their satisfaction with the preview before performing the final application, preventing unsuitable arrangement elements from being mistakenly applied to the current chat history. After the user selects some style templates, the terminal also displays which chat messages in the current chat history lack corresponding configurations for that style template (i.e., the arrangement elements for that type of chat message are empty or using default values), and prompts the user whether to add configurations for these chat messages, improving the completeness of the arrangement scheme. The terminal also supports displaying an overall compatibility score for each style template with the current chat history on the style template selection page in the style library. For example, the compatibility score for animation types is 92%, and for music segment types it is 78%. Users can use the compatibility score to determine which style templates are suitable for reuse and which style templates need to retain the original configuration scheme of the current chat history, improving the accuracy of the user's reuse decisions. The terminal can also support users to select and combine different style templates from multiple style libraries in a single call. For example, select motion effect configuration from style library A, music segment configuration from style library B, and character identifier configuration from style library C, thereby forming a hybrid arrangement scheme across multiple style libraries.

[0160] As an advanced form of style library reuse, the terminal also supports users saving the current chat history's layout scheme to different style libraries according to different types. For example, saving animation configurations to style library A and music segment configurations to style library B enables the categorized storage and flexible scheduling of layout schemes across different style libraries. The terminal also supports real-time editing of layout elements within the style library during use. After selecting a style template, users can fine-tune the specific layout element configuration values ​​for that type before application. The terminal records the user's adjustments and asks whether to save the adjusted configuration to the style library as a new version, achieving a closed-loop optimization process of "use-adjustment-update" for layout schemes. The style library also supports batch import and export functions. Users can import multiple layout schemes into the style library in batches via files, or export multiple layout schemes from the style library in batches as backup files, enabling efficient migration and backup of layout schemes across different devices or users.

[0161] During the user's viewing of arrangement elements, some key messages may need to be prioritized. Accordingly, in some embodiments, the method further includes: in the generated page, prioritizing the display of target chat messages in the chat history in an automatically selected state and the arrangement elements of the target chat messages; wherein, the target chat message is a chat message in the chat history whose semantic reversal intensity and emotional intensity exceed a preset value. The semantic reversal intensity is used to indicate the difference between the semantics of the current chat message and the semantics of the previous chat message, and the impact intensity of the arrangement elements of the target chat message is higher than that of the arrangement elements of other chat messages in the chat history. That is, when the terminal displays the arrangement page, it automatically detects messages in the chat history where the semantics suddenly shifts or the emotional intensity suddenly increases (e.g., messages that suddenly change from calm to anger, or from build-up to reversal), and automatically selects these messages as target chat messages on the page and highlights their arrangement elements. At the same time, the arrangement elements of these messages have a higher impact intensity than ordinary messages to match their high-intensity emotional expression. This automatic positioning and priority display method helps users quickly locate key turning points in the conversation without having to manually browse and search, improving the efficiency of the arrangement scheme review.

[0162] By automatically identifying chat messages whose semantic reversal intensity and emotional intensity exceed preset values ​​as target chat messages, and prioritizing their automatic selection and their arrangement elements on the generated page, key messages with significant emotional fluctuations or sudden semantic shifts in the dialogue can be automatically located and highlighted without manual searching by the user, improving the efficiency of users in identifying the climax of the dialogue. At the same time, the impact intensity of the arrangement elements of the target chat message is higher than that of other messages, giving key messages a differentiated intensity at the arrangement configuration level, avoiding confusion between key content and ordinary content in terms of presentation effect, and improving the recognizability and accuracy of the climax of the video.

[0163] In some embodiments, the method further includes: in response to a modification operation on the arrangement elements of any chat message, the terminal updates and displays the arrangement elements of the chat message. In this embodiment, if a user is not satisfied with the arrangement element configuration of a message while viewing the arrangement scheme, they can modify it. In response to the user's modification operation, the terminal updates the arrangement elements of the message to the modified configuration and refreshes and displays the updated arrangement elements in real time on the video generation interface, allowing the user to see the modification result immediately. Modification of arrangement elements can be achieved through various interactive methods.

[0164] In step 1202, the terminal responds to the video generation operation by displaying a video generated by the agent based on the arrangement elements of the chat history and each chat message.

[0165] After the user completes the review and modification of the arrangement scheme, the video generation operation is triggered. The terminal responds to this operation by rendering and compositing the text content of each chat message in the chat history and the currently determined arrangement elements of each chat message, generating the final video file and displaying it on the terminal. In this video, each chat message appears sequentially in the original chat history, and the presentation of each chat message is consistent with the currently configured arrangement elements. The user has already completed all adjustments to the arrangement elements before video generation; once satisfied, a single click triggers the compositing to obtain the video, eliminating the need for further modifications after generation. During the video compositing process, the terminal also aligns the timing of each chat message with the corresponding beat of the background music, ensuring precise synchronization between the appearance of each chat message and the music beat.

[0166] After the video is generated, if the video is the one the user needs, in response to the export operation of the video or the save operation of the style template of the video, multiple arrangement elements in the video can be displayed. In response to the save operation of at least one first arrangement element among the multiple arrangement elements, it can be displayed that the sedimented style template has been saved to the style library. The sedimented style template includes at least one first arrangement element.

[0167] The above mainly describes the principle of video generation based on at least one target orchestration element and chat history. The following explains the above method from the perspective of page display.

[0168] like Figure 13 As shown in Figures (a) and (b), the generation page displays a first generation option 1301 and a second generation option 1302. When the first generation option 1301 is selected, the terminal displays the principle of video generation through an intelligent agent. Specifically, during video generation, the intelligent agent can identify the uploaded chat history screenshots, segment each chat message, identify the sending role, text content, and sending time of each chat message, and filter non-text messages such as transfer records and system prompts. Then, the intelligent agent can perform steps such as topic recognition, sentiment analysis, role style recognition, and rhythm alignment on the identified text content to determine the arrangement elements suitable for the chat history. Then, when the generation control 1303 is triggered, the intelligent agent can determine the arrangement elements suitable for the chat history according to the above principle. When the second generation option 1302 is selected, the terminal can display multiple style templates. The style of the arrangement elements in different style templates is different. Each style template includes the arrangement elements used for video generation. For example, in response to the user's confirmation operation of the selected style template, it can display... Figure 6 Figure (b) shows multiple arrangement elements of the selected style template, allowing users to choose the appropriate style template and arrangement elements within it to generate a video according to their needs. Then, when the generation control 1303 is triggered, the terminal can directly generate a video based on the selected style template.

[0169] In response to Figure 13 The "Start Generation" trigger operation in Figure (b) shows... Figure 13 In Figure (c), the chat timeline is horizontal, and the terminal displays chat messages between the "I" and "Friend" roles horizontally. Multiple layout elements are included, comprising four types: "voice / part," "emoticons," "bubble animations," and "musical segments." These four layout elements are arranged vertically, forming a two-dimensional layout board page structure with the chat messages. Figure 13 As shown in Figure (c), the display area of ​​the third chat message intersects with the display areas of various arrangement elements to form multiple grids. Each grid displays the arrangement element used by the third chat message in a corresponding type, namely, "Friend's Regular Voice" for "Voice / Part"; "Emoji" for "Emoji 1"; "Bubble Animation" for "Beat Slide In"; and "Music Segment" for "Segment 1".

[0170] When a user selects a certain message, the terminal also synchronously highlights the corresponding column of the message in the two-dimensional grid on the page, as well as the corresponding positions of the message in the card list and the timeline view, so that when the user selects a message in any view mode, the corresponding position of the message can be quickly located in other view modes, realizing linked highlighting between multiple views. As Figure 13 shown in figure (c) in the above, when the third chat message is selected, the terminal displays the layout element of the third chat message in the generated page.

[0171] The terminal can preferentially display the target chat message in the chat history in an automatically selected state and the layout element of the target chat message in the generated page, as Figure 13 shown in figure (d) in the above, the 6th chat message is the target chat message in the chat history, the semantic inversion intensity and emotion intensity of this chat message are both higher than preset values, and it belongs to the climax in the chat history. "Timbre / Voice Part" adopts "dual voice part"; "Emoticon pack" adopts the combined sending of "emoticon pack 2 and emoticon pack 3"; "Bubble animation effect" adopts an animation effect with strong visual impact, that is, "bubble animation effect 1 + bubble animation effect 2"; "Music segment" adopts "segment 2". Compared with Figure 5 the layout element of the third chat message shown in the above, the layout element of the 6th chat message has stronger impact intensity.

[0172] The terminal can also display the emotion intensity corresponding to each chat message in the generated page. That is, the emotion intensity of each chat message is displayed on the page in a visualized form, for example, presented in the form of a numerical label, color block shade, icon level, etc., so that the user can intuitively know the emotion intensity value of each message while viewing the layout elements, which is convenient for understanding why the agent configures high-intensity layout effects for certain messages, and evaluating whether the overall emotion trend is reasonable. For example, as Figure 13 shown in figure (d) in the above, the "emotion arc" block in the generated page uses a bar chart form to display the emotion intensities of all chat messages in the chat history. Among them, the emotion intensity of the first chat message is 20, the emotion intensity of the second chat message is 26, the emotion intensity of the third chat message is 48, the emotion intensity of the fourth chat message is 60, the emotion intensity of the fifth chat message is 70, the emotion intensity of the sixth chat message is 96, the emotion intensity of the seventh chat message is 80, and the emotion intensity of the eighth chat message is 38. The 6th chat message has the strongest emotion intensity and belongs to the climax part of the chat history.

[0173] The confirmation generation control is an operation entry in the generated page for the user to finally confirm and trigger video synthesis, for example Figure 13The "Confirm Arrangement and Generate Video" button in diagram (c) is shown. After reviewing the arrangement scheme determined by the agent, the user can trigger this control if satisfied with the arrangement result. In response to this trigger, the terminal renders and synthesizes the text content of each chat message in the chat history with the corresponding arrangement elements, generating the final video file and displaying it on the terminal.

[0174] In response to any modification operation to the arrangement elements of a chat message, the terminal updates and displays the arrangement elements of that chat message. Modification of arrangement elements can be achieved through various interactive methods. For example, for any chat message in the chat history, in response to a trigger operation on the arrangement elements of the chat message, the terminal displays a list of alternative elements; in response to the selection of any alternative element in the list, the terminal updates the arrangement elements of the chat message to the selected alternative element. That is, after a user clicks on the arrangement element of a message, the terminal pops up a list containing multiple alternative options, from which the user can select one to complete the replacement. Each alternative option in the list is presented in preview form, allowing the user to preview the effect of the option before selection, reducing the cost of trial and error. Figure 14 As shown in Figures (a) and (b), the generated page displays an arrangement element containing the 6th chat message. When the "bubble animation" selection control 1401 within this element is triggered, the terminal displays a candidate element list 1402, which includes the currently used bubble animation and other selectable bubble animations. When the selection control for any other bubble animation is triggered, the terminal can update the bubble animation to the selected bubble animation.

[0175] For the target chat message (i.e., the automatically identified climax message), in addition to modifying its arrangement element configuration, the user can also change which chat message is marked as the target chat message. Specifically, the terminal displays a modification control for the target chat message on the generated page. Then, in response to the triggering operation of the modification control, the terminal displays each chat message in the chat history, with the first chat message in the chat history being the current target chat message. In response to the selection operation of the second chat message in the chat history, the terminal changes the target chat message from the first chat message to the second chat message and updates the arrangement elements of the first and second chat messages respectively. That is, after the user triggers the modification control, the page displays a complete list of messages for the user to reselect the climax message. When the user selects a new message as the target chat message, the terminal automatically reduces the impact intensity of the arrangement elements of the original target chat message to a normal level, while increasing the impact intensity of the arrangement elements of the new target chat message to a climax level, realizing one-click migration of the climax mark and adaptive updating of the arrangement elements. Figure 14As shown in Figures (c) and (d), the 6th chat message is the automatically identified target chat message. When the modification control 1403 is triggered, the terminal displays a message list 1404, which contains all the chat messages in the chat history. In response to a click on the 7th chat message, the terminal updates the target chat message display from the 6th to the 7th chat message, and the arrangement elements of these two chat messages are also adjusted accordingly.

[0176] Figure 15 This is a block diagram illustrating a video generation apparatus according to an exemplary embodiment. See also Figure 15 The device includes: The first display module 1501 is configured to display a target style template in a style library in response to a video creation operation, the style template in the style library being used to generate the video; The second display module 1502 is configured to, in response to a video generation operation, display a video generated by an agent based on the at least one target choreography element when at least one of the plurality of choreography elements included in the target style template is selected, wherein the plurality of choreography elements respectively indicate configuration information for different choreography angles of the video.

[0177] In some embodiments, the first display module is configured to display at least one style template set in the style library, display a recommended style template from the recommended style template set in the at least one style template set as a target style template, the style template set including style templates with the same name; and in response to a confirmation operation of the target style template, display the name of the target style template and a plurality of arrangement elements included in the target style template.

[0178] In some embodiments, the arrangement elements in the style template are arrangement elements after removing at least one of the character-specific configuration content and scene-specific configuration content.

[0179] In some embodiments, the device further includes a third display module and a fourth display module; The third display module is configured to display multiple arrangement elements in the video in response to a template saving operation of the video; The fourth display module is configured to display, in response to a save operation on at least one first arrangement element among the plurality of arrangement elements, that a sedimentation style template has been saved to the style library, the sedimentation style template including the at least one first arrangement element.

[0180] In some embodiments, the third display module is configured to display multiple entries in response to a template saving operation of the video; the multiple entries respectively display the arrangement angle names of the multiple arrangement elements and the configuration information corresponding to the multiple arrangement elements.

[0181] In some embodiments, the device further includes a fifth display module, a sixth display module, and a seventh display module; The fifth display module is configured to display multiple plot stages in the dramatic structure on the generated page, which is used to generate chat logs through an intelligent agent; The sixth display module is configured to display the configured content of the at least one plot stage in response to a configuration operation on the generation page for at least one plot stage. The seventh display module is configured to display chat logs generated by the agent based on the multiple plot stages and the configured content of each plot stage in response to a generation operation on the generation page. The second display module is configured to, in response to a video generation operation, display a video generated by the agent based on the at least one target choreography element and the chat history when at least one target choreography element among the plurality of choreography elements included in the target style template is selected.

[0182] In some embodiments, the sixth display module is configured to include at least one of a first display unit and a second display unit; The first display unit is configured to display descriptive text of the at least one plot stage in response to a configuration operation of the content of at least one plot stage on the generation page; The second display unit is configured to display the semantic strength of the at least one plot stage in response to a configuration operation of the semantic strength of at least one plot stage on the generated page, the semantic strength indicating the semantic strength of the content in the plot stage.

[0183] In some embodiments, the first display unit is configured to display the filled content in the at least one plot stage as descriptive text of the at least one plot stage in response to a fill-in operation on the generation page; or, in response to an upload operation of existing chat records on the generation page, display descriptive text of the at least one plot stage generated by the agent based on the existing chat records.

[0184] In some embodiments, the apparatus further includes an eighth display module; the eighth display module is configured to display, on a generated page, arrangement elements adapted to each chat message in the chat history based on the at least one target arrangement element, wherein the arrangement element of each chat message is used to indicate how the chat message is presented in the video, and the arrangement element of each chat message matches the chat characteristics of the character who sent the chat message; the step of displaying a video generated by an agent based on the at least one target arrangement element in response to a video generation operation when at least one target arrangement element in the multiple arrangement elements included in the target style template is selected includes: displaying a video generated by an agent based on the arrangement elements of the chat history and each chat message in response to a video generation operation when at least one target arrangement element in the multiple arrangement elements included in the target style template is selected.

[0185] In some embodiments, the arrangement elements have multiple arrangement angles, and arrangement elements with different arrangement angles are used to provide different presentation effect dimensions in the video; the eighth display module is configured to, on the generated page, arrange and display each chat message in the chat history and its corresponding role along a first direction according to the order of each chat message in the chat history; on the generated page, arrange and display the multiple types along a second direction, and the display areas of the multiple types intersect with the display areas of each chat message to form multiple grids, and each grid displays the arrangement elements used by a corresponding chat message in a corresponding type.

[0186] In some embodiments, the device further includes a ninth display module; the ninth display module is configured to, on the generated page, prioritize displaying a target chat message in the chat history that is in an automatically selected state and the arrangement elements of the target chat message; wherein the target chat message is a chat message in the chat history whose semantic inversion intensity and emotional intensity exceed a preset value, the semantic inversion intensity is used to indicate the difference between the semantics of the current chat message and the semantics of the previous chat message, and the impact intensity of the arrangement elements of the target chat message is higher than the impact intensity of the arrangement elements of other chat messages in the chat history.

[0187] In some embodiments, the device further includes a tenth display module and an eleventh display module; The tenth display module is configured to display multiple rhyming schemes adapted to the selected background music and chat history on the generated page. The eleventh display module is configured to, in response to a rewriting operation, display the target text obtained by rewriting the chat record based on the target rhyming scheme when a target rhyming scheme is selected among the plurality of rhyming schemes, wherein the rhyming at the end of each sentence in the target text conforms to the target rhyming scheme. The second display module is configured to, in response to a video generation operation, display a video generated by an agent based on the at least one target choreography element and the target text, when at least one target choreography element among the plurality of choreography elements included in the target style template is selected.

[0188] In some embodiments, the apparatus further includes a twelfth display module; the twelfth display module is configured to display a plurality of rewriting constraints in the generated page, each rewriting constraint indicating the relative importance of semantic preservation, rhyme matching, and beat alignment when performing a rewrite; wherein, in response to a rewrite operation, the target text obtained by rewriting the chat record is displayed based on the target rhyme scheme when the target rhyme scheme among the plurality of rhyme schemes is selected, including: in response to a rewrite operation, the target text obtained by rewriting the chat record is displayed based on the target rhyme scheme and the target rewrite constraint when the target rhyme scheme among the plurality of rhyme schemes is selected and the target rewrite constraint among the plurality of rewriting constraints is selected.

[0189] It should be noted that the video generation apparatus provided in the above embodiments is only illustrated by the division of the above functional units. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the electronic device can be divided into different functional units to complete all or part of the functions described above. In addition, the video generation apparatus and the video generation method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0190] 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.

[0191] When an electronic device is provided as a terminal, Figure 16This is a block diagram illustrating a terminal according to an exemplary embodiment. The diagram shows a structural block diagram of a terminal 1600 provided in an exemplary embodiment of this disclosure. The terminal 1600 may be a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal 1600 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0192] Typically, terminal 1600 includes a processor 1601 and a memory 1602.

[0193] Processor 1601 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1601 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1601 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1601 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, processor 1601 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0194] The memory 1602 may include one or more computer-readable storage media, which may be non-transitory. The memory 1602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1602 are used to store at least one computer program, which is executed by the processor 1601 to implement the method provided in the method embodiments of this application.

[0195] In some embodiments, the terminal 1600 may also optionally include a peripheral device interface 1603 and at least one peripheral device. The processor 1601, memory 1602, and peripheral device interface 1603 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1603 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 1604, a display screen 1605, a camera assembly 1606, an audio circuit 1607, and a power supply 1608.

[0196] Peripheral interface 1603 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1601 and memory 1602. In some embodiments, processor 1601, memory 1602 and peripheral interface 1603 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1601, memory 1602 and peripheral interface 1603 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0197] The radio frequency (RF) circuit 1604 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1604 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1604 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. In some embodiments, the RF circuit 1604 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1604 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1604 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0198] Display screen 1605 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1605 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1601 for processing. In this case, display screen 1605 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1605, disposed on the front panel of terminal 1600; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1600 or in a folded design; in still other embodiments, display screen 1605 may be a flexible display screen, disposed on a curved or folded surface of terminal 1600. Furthermore, display screen 1605 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1605 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0199] The camera assembly 1606 is used to acquire images or videos. In some embodiments, the camera assembly 1606 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1606 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash is a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0200] The audio circuit 1607 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting them into electrical signals that are input to the processor 1601 for processing, or to the radio frequency circuit 1604 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1600. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1601 or the radio frequency circuit 1604 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1607 may also include a headphone jack.

[0201] Power supply 1608 is used to power the various components in terminal 1600. Power supply 1608 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1608 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0202] Those skilled in the art will understand that Figure 16 The structure shown does not constitute a limitation on terminal 1600 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0203] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program that can be executed by a processor to perform the methods in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0204] In an exemplary embodiment, a computer program product or computer program is also provided, which includes program code stored in a computer-readable storage medium. A processor of an electronic device reads the program code from the computer-readable storage medium and executes the program code, causing the electronic device to perform the method described above.

[0205] 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 disclosure 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.

[0206] 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 method for generating video, characterized in that, The method includes: In response to a video creation operation, the target style template in the style library is displayed, and the style template in the style library is used to generate the video; When at least one of the multiple choreography elements included in the target style template is selected, in response to the video generation operation, a video generated by the agent based on the at least one target choreography element is displayed, wherein the multiple choreography elements respectively indicate configuration information for different choreography angles of the video.

2. The video generation method according to claim 1, characterized in that, The target style templates in the display style library include: Display at least one style template set in the style library, and display the recommended style template in the recommended style template set in the at least one style template set as the target style template, wherein the style template set includes style templates with the same name; In response to the confirmation operation of the target style template, the name of the target style template and the multiple layout elements included in the target style template are displayed.

3. The video generation method according to claim 1, characterized in that, The arrangement elements in the style template are those after removing at least one of the character-specific configuration content and scene-specific configuration content.

4. The video generation method according to claim 1, characterized in that, The method further includes: In response to a template saving operation on the video, multiple arrangement elements in the video are displayed; In response to a save operation on at least one first arrangement element among the plurality of arrangement elements, it is displayed that a sedimentation style template has been saved to the style library, the sedimentation style template including the at least one first arrangement element.

5. The video generation method according to claim 4, characterized in that, The response to the template saving operation of the video, displaying multiple arrangement elements in the video, includes: In response to the template saving operation of the video, multiple entries are displayed; The arrangement angle names of the arrangement elements and the configuration information corresponding to the arrangement elements are displayed in the multiple entries respectively.

6. The video generation method according to claim 1, characterized in that, The method further includes: The generated page displays multiple plot stages in the dramatic structure and is used to generate chat logs via an intelligent agent. In response to a configuration operation on at least one episode stage on the generation page, the configured content of the at least one episode stage is displayed; In response to a generation operation on the generation page, the chat log generated by the agent based on the plurality of plot stages and the configured content of each plot stage is displayed. When at least one target choreography element is selected among the multiple choreography elements included in the target style template, in response to the video generation operation, displaying a video generated by the agent based on the at least one target choreography element includes: If at least one target choreography element is selected among the multiple choreography elements included in the target style template, in response to the video generation operation, a video generated by the agent based on the at least one target choreography element and the chat history is displayed.

7. The video generation method according to claim 6, characterized in that, The response to a configuration operation on the generation page for at least one episode stage, displaying the configured content for the at least one episode stage, includes at least one of the following: In response to a configuration operation on the generation page for the content of at least one plot stage, descriptive text for the at least one plot stage is displayed; In response to a configuration operation on the generated page for the semantic strength of at least one plot stage, the semantic strength of the at least one plot stage is displayed, the semantic strength indicating the semantic strength of the content in the plot stage.

8. The video generation method according to claim 7, characterized in that, The response to a configuration operation for at least one episode stage on the generation page, displaying descriptive text for the at least one episode stage, includes: In response to the filling operation of the at least one plot stage on the generation page, the filled content in the at least one plot stage is displayed as descriptive text of the at least one plot stage; or, In response to the upload operation of existing chat records on the generation page, the agent displays descriptive text for the at least one plot stage generated based on the existing chat records.

9. The video generation method according to claim 1, characterized in that, The method further includes: Based on the at least one target arrangement element, the generated page displays arrangement elements that are adapted to each chat message in the chat history. The arrangement element of each chat message is used to indicate how the chat message is presented in the video. The arrangement element of each chat message is matched with the chat characteristics of the character who sent the chat message. The response to the video generation operation, displaying the video generated by the agent based on the at least one target orchestration element, includes: In response to the video generation operation, a video generated by the agent based on the arrangement elements of the chat history and each chat message is displayed.

10. The video generation method according to claim 9, characterized in that, The arrangement elements have multiple arrangement angles, and arrangement elements with different arrangement angles are used to provide different presentation effect dimensions in the video; The arrangement elements displayed on the generated page that adapt to each chat message in the chat history include: In the generated page, each chat message in the chat history and its corresponding character are arranged and displayed in the first direction according to the order of each chat message in the chat history; In the generated page, the various types are arranged and displayed along the second direction. The display areas of the various types intersect with the display areas of each chat message to form multiple grids. Each grid displays the arrangement elements used by a corresponding chat message in a corresponding type.

11. The video generation method according to claim 9, characterized in that, The method further includes: In the generated page, the target chat message in the chat history is displayed in an automatically selected state, and the arrangement elements of the target chat message are displayed first. The target chat message is a chat message in the chat history where at least one of the semantic inversion strength and the emotional strength exceeds a preset value. The semantic inversion strength is used to indicate the difference between the semantics of the current chat message and the semantics of the previous chat message. The impact strength of the arrangement elements of the target chat message is higher than the impact strength of the arrangement elements of other chat messages in the chat history.

12. The video generation method according to claim 1, characterized in that, The method further includes: The generated page displays multiple rhyming schemes based on the selected background music and chat history. When a target rhyming scheme is selected among the multiple rhyming schemes, in response to the rewriting operation, the target text obtained by rewriting the chat record is displayed based on the target rhyming scheme, wherein the final rhyme of each sentence in the target text conforms to the target rhyming scheme; When at least one target choreography element is selected among the multiple choreography elements included in the target style template, in response to the video generation operation, displaying a video generated by the agent based on the at least one target choreography element includes: When at least one target choreography element is selected among the multiple choreography elements included in the target style template, in response to the video generation operation, a video generated by the agent based on the at least one target choreography element and the target text is displayed.

13. The video generation method according to claim 12, characterized in that, The method further includes: The generated page displays multiple rewriting constraints, each of which indicates the relative importance of semantic preservation, rhyme matching, and beat alignment when performing a rewrite. When a target rhyming scheme is selected among the multiple rhyming schemes, in response to the rewrite operation, the target text obtained by rewriting the chat history is displayed based on the target rhyming scheme, including: When a target rhyming scheme is selected among the multiple rhyming schemes and a target rewrite constraint is selected among the multiple rewrite constraints, in response to the rewrite operation, the target text obtained by rewriting the chat record is displayed based on the target rhyming scheme and the target rewrite constraint.

14. A video generation apparatus, characterized in that, The device includes: The first display module is configured to display a target style template in the style library in response to a video creation operation, the style template in the style library being used to generate the video; The second display module is configured to, in response to a video generation operation, display a video generated by an agent based on the at least one target choreography element when at least one of the multiple choreography elements included in the target style template is selected, wherein the multiple choreography elements respectively indicate configuration information for different choreography angles of the video.

15. An electronic device, characterized in that, The electronic device includes: One or more processors; Memory used to store the executable program code of the processor; The processor is configured to execute the program code to implement the video generation method as described in any one of claims 1 to 13.

16. 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 able to perform the video generation method as described in any one of claims 1 to 13.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the video generation method according to any one of claims 1 to 13.

Images