Content generation method and device, computer readable storage medium and program product

Abstract

The invention relates to the technical field of computers, in particular to a content generation method and device, a computer readable storage medium and a program product. The content generation method comprises the steps that a plurality of scripts are generated according to the creation dimension of a story text, and each script corresponds to a part of the story text; creating at least one content generation task based on each script; a plurality of content generation tasks corresponding to the plurality of scripts are distributed to a plurality of matched users, and historical contents created by the users are matched with at least one of the styles and styles of the content generation tasks and the categories of the story texts; and according to the attribute information of the creation dimension, integrating at least a part of contents in the plurality of contents generated by the plurality of users to generate multimedia contents.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a content generation method and device, a computer readable storage medium and a program product. BACKGROUND

[0002] With the popularity of multimedia technologies such as video platforms and audio media, the demand of users for secondary creation such as editing and adaptation, creative expression, etc. of original content such as novels and films is increasing.

[0003] However, in the related art, text segments are usually manually intercepted, and secondary creation content is synthesized by manually selecting video templates, music and special effects. Such a way is low in efficiency, and requires a creator to have multiple production capabilities, so that users cannot efficiently generate derivative works with coherent plots and unified styles. SUMMARY

[0004] In view of this, the embodiments of the present disclosure provide a content generation method and device, a computer readable storage medium and a program product, which can split multiple scripts and content generation tasks corresponding to each script according to the creation dimensions of a story text, distribute the content generation tasks to users with matched capabilities, and finally integrate the content generated by multiple users to generate multimedia content, so as to realize the joint creation of multiple users and improve the generation efficiency and quality of multimedia content.

[0005] According to some embodiments of the present disclosure, a content generation method is provided, including: generating multiple scripts according to the creation dimensions of a story text, wherein each script corresponds to a part of the story text; creating at least one content generation task based on each script; distributing multiple content generation tasks corresponding to multiple scripts to multiple matched users, wherein the historical content created by the users matches at least one of the genre, style, and category of the story text of the content generation task; and integrating at least part of multiple contents generated by multiple users according to the attribute information of the creation dimensions to generate multimedia content.

[0006] According to some embodiments of the present disclosure, a content generation apparatus is provided, comprising: a script generation module configured to generate a plurality of scripts according to a creative dimension of a story text, wherein each of the scripts corresponds to a part of the story text; a task creation module configured to create at least one content generation task based on each of the scripts; a task distribution module configured to distribute a plurality of content generation tasks corresponding to the plurality of scripts to a plurality of matched users, wherein the users' historical content matches at least one of a genre, a style, and a category of the story text of the content generation tasks; and a content generation module configured to integrate at least part of a plurality of contents generated by the plurality of users according to attribute information of the creative dimension to generate a multimedia content.

[0007] According to some embodiments of the present disclosure, a content generation apparatus is provided, comprising: at least one memory; and at least one processor coupled to the at least one memory, the at least one processor being configured to execute a content generation method according to any of the embodiments of the present disclosure based on instructions stored in the at least one memory.

[0008] According to some embodiments of the present disclosure, a computer readable storage medium is provided, having stored thereon computer instructions which, when executed by a processor, implement a content generation method according to any of the embodiments of the present disclosure.

[0009] According to some embodiments of the present disclosure, a computer program product is provided, which, when running on a computer, causes the computer to implement a content generation method according to any of the embodiments of the present disclosure.

[0010] Other features, aspects, and advantages of the present disclosure will become apparent from the following detailed description of the exemplary embodiments with reference to the following drawings. BRIEF DESCRIPTION OF DRAWINGS

[0011] Embodiments of the present disclosure will be described below with reference to the accompanying drawings. It should be understood that the accompanying drawings relate only to some embodiments of the present disclosure and are not intended to limit the present disclosure. In the drawings:

[0012] Figure 1 A flowchart of a content generation method according to some embodiments of the present disclosure is shown;

[0013] Figure 2 A flowchart of generating a script according to some embodiments of the present disclosure is shown;

[0014] Figure 3 A flowchart of distributing a content generation task according to some embodiments of the present disclosure is shown;

[0015] Figure 4A flowchart illustrating distribution of content generation tasks according to some embodiments of the present disclosure is shown;

[0016] Figure 5 A flowchart illustrating content integration according to some embodiments of the present disclosure is shown;

[0017] Figures 6A to 6C A schematic diagram illustrating performing a content generation method in some embodiments of the present disclosure is shown;

[0018] Figure 7 A block diagram illustrating a content generation apparatus according to some embodiments of the present disclosure is shown;

[0019] Figure 8 A block diagram illustrating a content generation apparatus according to some embodiments of the present disclosure is shown;

[0020] Figure 9 A block diagram illustrating an electronic device according to some embodiments of the present disclosure is shown.

[0021] It should be understood that the dimensions of the various portions shown in the drawings are shown for purposes of convenience and do not necessarily bear an accurate relationship to each other. Identical or similar reference numerals are used throughout the drawings to refer to identical or similar components. Thus, once a component is defined in one drawing, it can not be further discussed in subsequent drawings. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. It should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein.

[0023] It should be understood that the various steps recited in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit performing the steps shown. The scope of the present disclosure is not limited in this respect. Unless specifically stated otherwise, the relative arrangement of components and steps set forth in these embodiments, numerical expressions, and numerical values should be interpreted as being merely exemplary, and not limiting the scope of the present disclosure.

[0024] The term “comprising” and variations thereof as used in the present disclosure mean an open-ended term that includes at least the recited elements / features, but does not exclude other elements / features, i.e., “including but not limited to”. The term “based on” means “based at least in part on”.

[0025] It should be noted that the terms "first", "second", and the like in the present disclosure are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, the terms "first", "second", and the like are not intended to imply a given order or any other way of a given order.

[0026] It should be noted that the terms "one", "multiple" in the present disclosure are illustrative and not restrictive, and those skilled in the art should understand that unless otherwise specified in the context, it should be understood as "one or more".

[0027] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0028] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present disclosure are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0029] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined by any suitable means from the present disclosure that is clear to those skilled in the art.

[0030] In the related art, the efficiency of secondary creation of specific content is low, the quality is poor, and high-quality multimedia content cannot be generated. The embodiments of the present disclosure provide a content generation method, which can split multiple scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute these content generation tasks to users with matching capabilities, and finally integrate the content generated by multiple users to generate multimedia content, to realize the joint creation of multiple users and improve the generation efficiency and generation quality of multimedia content.

[0031] Figure 1 A flowchart of a content generation method according to some embodiments of the present disclosure is shown.

[0032] As Figure 1As shown, the content generation method can include: step S1, generating a plurality of scripts according to the creation dimension of the story text, wherein each script corresponds to a part of the story text; step S2, creating at least one content generation task based on each script; step S3, distributing a plurality of content generation tasks corresponding to a plurality of scripts to a plurality of matched users, wherein the historical content created by the users matches at least one of the genre, style, and category of the story text of the content generation task; and step S4, integrating at least part of the content generated by a plurality of users according to the attribute information of the creation dimension, to generate multimedia content.

[0033] A story text refers to narrative content presented in the form of text, which tells a complete or fragmented story by describing events, characters, scenes, and plot development. Story texts can cover various forms, such as novels, short stories, folk tales, game narratives, etc. The creation dimension of a story text, for example, includes elements such as characters and plot, refers to the components of the complete system of a story.

[0034] The creation dimension refers to the constitutive direction that supports content creation. The creation dimension of a story text can be used as the basis for splitting scripts. Based on the creation dimension, a plurality of different scripts can be split and generated from the story text, for example, for the character dimension, a plurality of scripts adapted to perform can be generated based on different characters of the story text.

[0035] For each generated script, at least one content generation task can be further generated as needed. The form and content of the content generation task are diverse, which can be a task of generating some components of multimedia content, such as a task of generating the image of a specific character or a task of generating specific music, or a task of generating complete multimedia content, such as a task of generating a video segment in a specific scene.

[0036] The generated content generation task can be distributed to users matched with each content generation task, so that the users generate the content required by the task. The users matched with the content generation task refer to, for example, users whose abilities meet the requirements of the task. For example, the abilities of users can be determined by using historical content obtained after authorization by each user, and compared with the genre, style, or category of the story text required by the content generation task, so as to find users matched with each content generation task for distribution of the task.

[0037] Genre refers to the specific presentation form of content, which can be used to define the category of content form. The genre of the content generation task is the genre of the content to be generated, which includes, for example, video dramas, dynamic comics, animations, etc.

[0038] Style refers to the overall temperament and emotional tone presented by the content in the expression level, which can be used to determine the sensory experience of the content. Similar to genre, the style of a content generation task is the style of the content to be generated, for example, including cheerful, passionate, healing, suspense, dark, and other styles.

[0039] Category refers to the classification of story texts in core settings, theme directions, and element compositions, which can be used to define the content attributes of story texts, such as science fiction, fantasy, ancient style, urban, suspense, and campus categories.

[0040] Subsequently, the content generated by each user according to the matched content generation task can be received, and the content can be integrated and spliced. For example, in the case of a target multimedia content being a video, a part of the users can generate character images in the video, a part of the users can generate video clips, and a part of the users can generate transition effects in the video. After receiving the above-mentioned content, the content can be integrated and a complete video can be generated for subsequent content publishing and other purposes.

[0041] The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content.

[0042] The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content. Figure 1 The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content. Figure 2 The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content. Figure 2 The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content. The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content.

[0043] The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content. Figure 2 The above-mentioned content generation method can split a plurality of scripts and content generation tasks corresponding to each script according to the creation dimension of the story text, distribute the content generation tasks to users with matching capabilities, and finally integrate the content generated by a plurality of users to generate multimedia content. Through the above-mentioned method, the capabilities of a plurality of users can be utilized to realize the common creation of a plurality of users for a specific multimedia content, without the need for one user to generate a complete multimedia content, thereby improving the generation efficiency and generation quality of the multimedia content.

[0044] As mentioned above, the creation dimension refers to a constituting direction supporting the content creation. In the above embodiment, the creation dimension can include at least one of a plot dimension, an event dimension, and a character dimension. The plot dimension refers to the plot development of the story text, which can be determined according to the chapter structure of the story text or the semantic understanding of the plot in the story text, for example. The event dimension refers to the key events or famous scenes in the story text, which can be determined according to the various plot nodes in the story text, for example. The character dimension refers to the characters in the story text, including the main characters, supporting characters, and various other characters.

[0045] The process of generating a script based on the text paragraphs can include scene building, dialogue design, action design, and the like. Scene building can be the conversion of narrative language of the text paragraphs into scene descriptions that conform to scene logic, such as time, location, and environmental atmosphere. Dialogue design can be the combination of dialogue text, psychological activity, and behavior motivation of the characters to design dialogue that can both advance the plot and highlight the characteristics of the characters. Action design can be the combination of the behavior of the characters and the designed scene to supplement the interaction details of the characters and the scene and enhance the visual effect of the script.

[0046] In the following, based on the above three dimensions, how to generate a script based on a story text will be introduced respectively under each dimension. Figure 2

[0047] In some embodiments, in the case where the creation dimension includes the plot dimension, the generating a plurality of scripts based on the creation dimension of the story text includes: determining a plurality of text paragraphs with continuous plots in the story text; and generating a plurality of scripts with continuous plots based on the plurality of text paragraphs.

[0048] In the case of splitting based on the plot development of the story text, each chapter can be determined as a text paragraph according to the chapter structure of the story text, thereby determining a plurality of text paragraphs with continuous plots. Based on the text paragraphs, a plurality of scripts can also be generated according to the text paragraphs with the continuous plot as the standard, for example, the text paragraphs of the first chapter to the fifth chapter can be used to generate one script, and the text paragraphs of the sixth chapter to the tenth chapter can be used to generate another script.

[0049] Through the above splitting method based on the plot dimension, the plot in each script and between the scripts is continuous. On the one hand, the continuity of the content production can be achieved, avoiding the large-scale transition of characters and scenes, and improving the production efficiency. On the other hand, by maintaining the plot order between the contents, the subsequent integration and splicing of the contents can be facilitated.

[0050] ​In some embodiments, in a case where the creation dimension includes an event dimension, the generating a plurality of scripts according to the creation dimension of the story text includes: determining a plurality of events in the story text according to plot nodes of the story text; for each of the events, determining a corresponding text passage in the story text according to the plot nodes; and generating at least one script according to the determined text passages.

[0051] In a case of splitting based on events of the story text, semantic understanding of the story text can be performed to determine plot nodes at which the story turns, and based on the plot nodes, a plurality of events can be determined.

[0052] For example, a plot node at which the story turns can be a node at which a conflict breaks out, such as a confrontation between a main character and an opponent, a choice between good and evil in the heart of a character, and the like. For another example, a plot node can also be a node at which a relationship between characters changes, such as a meeting between a male and a female lead, an argument between the male and the female lead, and the like. For these plot nodes, an event corresponding to the plot node itself, i.e., a famous scene that causes the plot to turn, can be determined.

[0053] It should be understood that the above plot nodes are exemplary and non-limiting, and other ways of determining plot nodes in a story text can also be used in the content generation method proposed in the disclosure.

[0054] After determining a plurality of events in the story text, a text passage corresponding to each event can be determined, and at least one script can be generated based on each event. Through the above splitting method based on the event dimension, famous scenes in the story text can be extracted, transitions between contents are reduced, compactness of the generated contents is improved, and efficiency and quality of content production are improved.

[0055] In some embodiments, in a case where the story text includes a plurality of characters, the creation dimension includes a character dimension, and the generating a plurality of scripts according to the creation dimension of the story text includes: for each of the characters, determining a text passage in the story text corresponding to the character; and generating at least one script according to the determined text passages.

[0056] In a case of splitting based on characters of the story text, a main character corresponding to each text passage in the story text can also be determined according to semantic understanding of the text passage. The main character is only a main character in the text passage, and can be a main character in the story text or another character in the story text.

[0057] Subsequently, a corresponding script can be generated according to the set of text passages corresponding to each role. For example, a corresponding script can be generated for each role, i.e., at least one script is generated according to all the text passages corresponding to a role, thereby describing the state change process of the role in the development of the plot, which can be understood as the role subplot script of the role.

[0058] For example, for roles that are associated with each other, a unified script can be generated by integrating their text passages. For example, for the male and female leads, the psychological state changes of the male and female leads can be described from their respective perspectives before they meet, and then their common experiences can be described after they meet, thereby reflecting the association between the male and female leads.

[0059] Through the above splitting method based on the role dimension, the role subplots of each role in the story can be extracted, and corresponding scripts can be generated, thereby making the theme of each script more prominent and improving the quality of content generation.

[0060] The above describes different processes of generating scripts according to different creative dimensions of the story text, and further describes how to generate multiple scripts in step S1. Next, how to create at least one content generation task in step S2 will be further described. Figure 2 The scripts generated above can correspond to the entire multimedia content, e.g., for generating a complete video or video segment. The content generation task corresponds to each user and is used to instruct each user to generate content, and does not necessarily correspond to the complete multimedia content. After the script is generated, each script can further generate at least one content generation task, so as to subsequently distribute the tasks to the matching users.

[0061] In some embodiments, the creating at least one content generation task based on the script includes creating multiple content generation tasks of different scenes based on the script including multiple scenes, and the multiple content generation tasks have the same or different genres.

[0062] In the case where the script includes multiple scenes, e.g., the script corresponds to the story text of the first chapter to the fifth chapter, which includes multiple scenes of the male lead in the hospital, at home, in the mall, etc., content generation tasks corresponding to the scenes of the hospital, home, and mall can be further split out. In addition, the scenes can also be determined according to the scenes in the script, e.g., dialogue scenes, fighting scenes, etc.

[0063]

[0064] ​As described above, the genre of the content generation task refers to the genre of the content to be generated, such as an animation genre, a dynamic comic genre, a live-action genre, and the like. For multiple content generation tasks of different scenes, the genres of the tasks can be the same, such as all requiring the generation of content of a video drama genre. They can also be different, such as determining a suitable genre as the genre of the content generation task according to the scene.

[0065] By splitting the content generation tasks from the scenes of the script, on the one hand, the complexity of each content generation task can be reduced, allowing reuse of scene materials in the generation process, thereby improving the efficiency of content generation. On the other hand, each refined content generation task can be distributed to users with matching capabilities for content generation, such as distributing content generation tasks for dialogue scenes to users skilled in making dialogue scenes, and distributing content generation tasks for fighting scenes to users skilled in making fighting scenes, thereby generating higher quality content.

[0066] In some embodiments, the script includes a script corresponding to a key event in the story text, and creating at least one content generation task based on the script includes: based on the script corresponding to the key event, creating multiple content generation tasks of the same genre and the same scene.

[0067] Corresponding to the above splitting of the script based on the event dimension, after splitting multiple scripts based on each event of the story text, for the script corresponding to the key event, multiple content generation tasks of the same scene and the same genre can be created for distribution to different users.

[0068] For example, based on semantic understanding of the story text, the importance of each event in the story text can be determined, and events with importance higher than a certain threshold, such as events that are important turning points in the plot of the story text, such as the love between the male and female leads, are determined as key events. For scripts including key events, multiple content generation tasks of the same or similar genre can be generated, which can correspond to the entire script or a part of the script.

[0069] By creating and distributing content generation tasks in the above manner, multiple users can subsequently generate multiple different versions of content, so as to select the optimal version for promotion when, for example, distributing content, thereby improving the quality of the content.

[0070] In some embodiments, the script includes a script corresponding to a character in the story text, and creating at least one content generation task based on the script includes: creating the at least one content generation task according to the attributes of the character corresponding to each of the scripts, the genre of the at least one content generation task matching the attributes of the character.

[0071] Corresponding to the above splitting the script based on the role dimension, after splitting the multiple scripts based on the role branch, for each script, the genre of the content to be generated can be determined according to the attributes of the role. For example, in the case where the role image is close to the real person ratio, it can be determined that the content of the real person shooting genre needs to be generated. In the case where the role personality is prominent, it can be determined that the content of the animation theme needs to be generated in order to highlight the personality of the role. In the case where the theme of the role is biased towards the narrative theme, it can be determined that the content of the dynamic comic genre needs to be generated in order to simplify the image of the role and highlight the description of the plot narration.

[0072] As can be seen, in response to the role meeting a certain attribute, it can be determined that the content of the corresponding genre needs to be generated, therefore, the genre determined according to the attributes of the role can be one or multiple. According to the determined genre, at least one content generation task can be correspondingly generated in order for the user to create.

[0073] By creating the content generation task in the above manner, the genre of the generated content can be more diversified, the attributes of the role can be described from multiple perspectives, and the quality of the generated content can be improved.

[0074] It should be understood that the embodiments described above are not mutually exclusive, but can be executed in combination. For example, for a certain script, based on different scene splitting, multiple content generation tasks of different scenes can be generated, and for important scenes in multiple scenes, multiple content generation tasks of the same scene and the same theme can also be generated.

[0075] The above describes how to create the content generation task in step S2, by generating more refined content generation tasks, each task can have a prominent theme in order to distribute each task to the user with matching ability for creation, thereby improving the quality of the generated content.

[0076] In the following, the Figure 3 How to distribute the content generation task to the matching user in step S3 will be introduced. Figure 3 A flowchart of distributing the content generation task according to some embodiments of the present disclosure is shown.

[0077] As Figure 3As shown, the step S3 of distributing the plurality of content generation tasks corresponding to the plurality of scripts to the plurality of matched users comprises: a step S31 of determining a plurality of candidate users from the users of the community according to the attribute data of the story text and the interaction data of the community corresponding to the story text, wherein the interaction data is obtained based on the authorization of the users in the community; a step S32 of determining the users matched with each of the content generation tasks from the plurality of candidate users according to at least one of the genre, style and category of the historical content created by the plurality of candidate users after authorization; and a step S33 of distributing the plurality of content generation tasks to the plurality of matched users.

[0078] The users in the community corresponding to the story text can be understood as a collection of all users related to the story text, for example, including all users who have read the story text or other texts of the same category. The range of users in the community is the widest.

[0079] The candidate users for matching with the content generation tasks can be determined according to the interaction data of the users in the community. The candidate users can be understood as a collection of users capable of creating content, for example, users who have historically created content. It can be seen that the range of candidate users is a smaller range included in the range of users in the community.

[0080] Subsequently, the matched users can be determined by matching the genre and style of the content generation tasks and the category of the story text with the genre, style or category of the content created by the candidate users. The matched users can be understood as users whose historical content matches the content generation tasks and the story text. The execution of the plurality of content generation tasks generated above by these users can improve the quality of content generation. The range of matched users is a smaller range further included in the range of candidate users.

[0081] After determining the matched users, the distribution of the content generation tasks can be performed so that the users generate corresponding content according to the tasks. The distribution of the content generation tasks can be performed in units of individual users, i.e., each content generation task is distributed to an independent individual user, thereby improving the diversity of the generated content.

[0082] The distribution of the content generation tasks can also be performed in units of user groups, for example, a plurality of content generation tasks split according to the same script are distributed to a user group, which may, for example, include a plurality of users with similar historical content genres or styles. The users in the user group can jointly create multimedia content after receiving the content generation tasks, thereby improving the efficiency and quality of content generation.

[0083] Furthermore, in some embodiments, the plurality of content generation tasks include a first generation task and a second generation task, and the distribution of the plurality of content generation tasks corresponding to the plurality of scripts to the plurality of matching users includes: in response to the first generation task depending on the second generation task, distributing the first generation task to a first user matching the first content generation task, and distributing the content generated by the first user and the second content generation task to a second user matching the second content generation task.

[0084] In other words, for content generation tasks that have dependencies, the content generation tasks can be distributed to the matching users in a serial manner. That is, after one task is completed, the results of the other task and the previous task are distributed to the matching users.

[0085] For example, the first generation task mentioned above could be a scene generation task, while the second generation task could be a character action generation task. To improve the quality of the generated content, the character's actions need to be depicted based on the scene; therefore, the second generation task depends on the first generation task. During content distribution, the first generation task can be distributed to the first user first, and after the first user completes the task, the second generation task and the content generated by the first user can be distributed to the second user, thus achieving sequential content generation.

[0086] In other embodiments, in response to the absence of a dependency between the first generation task and the second generation task, the first generation task and the second generation task are distributed to the first user and the second user, respectively.

[0087] In other words, for content generation tasks that do not have dependencies, they can be distributed to matching users in parallel. For example, the first generation task could be for one role, while the second generation task could be for another role. Since there is no dependency between the first and second generation tasks, they can be distributed to both users simultaneously, thus improving content generation efficiency.

[0088] The above text combines Figure 3 This paper describes the process of identifying and distributing content generation tasks to matched users. In addition to distributing content generation tasks, the content generation method proposed in this disclosure can also simultaneously distribute corresponding reference materials to the matched users. The following section will combine... Figure 4 This section introduces how to distribute content generation tasks and provides reference materials.

[0089] Figure 4 A flowchart illustrating a content generation task according to other embodiments of this disclosure is shown. Figure 4As shown, step S3, which distributes multiple content generation tasks corresponding to multiple scripts to multiple matched users, includes: step S301, determining historical materials corresponding to the story text, wherein the historical materials include at least one of character materials, scene materials, special effects materials, and sound materials; step S302, based on feedback on the historical materials, determining reference materials from the historical materials that correspond to at least one of the genre and style of each content generation task; and step S303, distributing the multiple content generation tasks and their corresponding reference materials to the multiple matched users.

[0090] In step S301, the historical material corresponding to the story text can be historical content created by users in the community for the story text as mentioned above, or it can be material corresponding to other story texts or general material.

[0091] Character assets include images of various characters from the story text. Scene assets include elements of the scene or scene composition. Special effects assets include video transition effects and animation effects. Sound assets include dialogue audio, music, and sound effects.

[0092] The aforementioned historical materials can be obtained, for example, from a resource library corresponding to the story text. By collecting and storing historical content created by various users, this content can be used to create subsequent multimedia content of various genres, thereby enriching the community content and improving the user experience.

[0093] In step S302, materials corresponding to the content generation task can be selected from the historical materials as reference materials for the task. For example, if the content generation task includes generating dynamic comic content of the male protagonist in a hospital scene, the image material of the male protagonist in the dynamic comic can be determined from the historical materials as reference material for the content generation task, so that the user can refer to it when generating content according to the task.

[0094] In addition, feedback from other users regarding historical materials can be used to select materials with high user approval as reference materials for tasks.

[0095] In some embodiments, the reference material includes a content template applied to each of the content generation tasks. The content template is used to specify a particular part during content generation. Referring to the example above of generating motion comic content of the male protagonist in a hospital scene, a motion comic male protagonist image can also be determined as the content template for the content generation task to ensure that the male protagonist's image in the generated content conforms to the requirements of the content template.

[0096] Content templates allow you to define specific parts of the generated content, ensuring that key elements are consistent across different user-generated content, such as maintaining a consistent image for the male protagonist.

[0097] In step S303, each content generation task and the corresponding reference materials can be distributed to the user matching the task so that content can be generated.

[0098] The above process improves content generation efficiency by identifying and distributing reference materials relevant to the task. It also ensures consistency in the generated content, thus improving its quality.

[0099] The above text combines Figure 3 and Figure 4 This paper introduces an embodiment of step S3 in the content generation method, which involves distributing content generation tasks. The following section will combine... Figure 5 This section describes how to integrate multiple user-generated contents to generate multimedia content in step S4.

[0100] Figure 5 A flowchart illustrating the integration of content according to some embodiments of this disclosure is shown. For example... Figure 5 As shown, step S4, which integrates at least a portion of the multiple user-generated content according to the attribute information of the creation dimension to generate multimedia content, includes: step S41, determining multiple related content among the multiple content according to the attribute information of the creation dimension corresponding to the multiple content; step S42, integrating the multiple related content to generate the multimedia content.

[0101] In step S41, the attribute information of the creation dimension refers to the specific content corresponding to the creation dimension described above. For example, when the creation dimension is a character dimension, the attribute information of the creation dimension refers to the specific character in the content. As another example, when the creation dimension is an event dimension, the attribute information of the creation dimension refers to the specific event in the content.

[0102] The aforementioned attribute information allows us to determine the relevance between multiple pieces of content created by multiple users. For example, content focusing on the same character can be identified as related content, or multiple pieces of content that continue a storyline can be identified as related content. Identifying related content can be understood as aggregating and organizing user-generated content. Furthermore, when content is distributed according to user groups, multiple pieces of content generated by multiple users within the same user group can also be directly identified as related content.

[0103] In some embodiments, determining multiple related contents among the multiple contents based on the attribute information of the creation dimension corresponding to the multiple contents includes: determining multiple contents corresponding to the same script as the multiple related contents.

[0104] As mentioned earlier, the script is broken down based on the creative dimension of the story text. In other words, if multiple content generation tasks are created for the same script, the attribute information of the creative dimension of the multiple pieces of content generated by the user based on these tasks will naturally be the same. Therefore, multiple pieces of content corresponding to the same script can be identified as related content.

[0105] In other embodiments, determining multiple related contents among the multiple contents based on the attribute information of the creative dimension corresponding to the multiple contents includes: determining multiple contents corresponding to multiple scripts belonging to the same creative dimension as the multiple related contents.

[0106] For multiple scripts belonging to the same creative dimension, the attribute information of the generated content in that creative dimension usually corresponds to each other. For example, for multiple scripts belonging to the plot dimension, the plots of these scripts are continuous, and the plots of the content generated from these scripts are also continuous. Therefore, multiple pieces of content corresponding to multiple scripts belonging to the same creative dimension can also be identified as related content.

[0107] In step S42, after obtaining authorization from each user, the relevant content can be integrated to generate the final multimedia content, such as a complete video.

[0108] Since user-generated content takes many forms, the method of integrating such content is not limited herein. Taking video as an example of multimedia content, user-generated content can be video clips, and the integration of video clips may include, for example, editing and splicing. User-generated content can also be video elements such as character images and scenes, and the integration of video elements may include, for example, processing the video elements to generate corresponding videos or video clips.

[0109] In some embodiments, integrating the plurality of related content to generate the multimedia content includes: determining at least one of the genre similarity and style similarity among the plurality of related content based on at least one of the genre and style of the content generation task corresponding to the plurality of related content; and integrating the plurality of related content based on at least one of the genre similarity and style similarity among the plurality of related content to generate the multimedia content.

[0110] In the above embodiments, the similarity between related content can be determined based on the genre and style of the content generation task on which the generated content is based, and content with high similarity can be selected for integration to generate multimedia content.

[0111] For example, when multiple pieces of content targeting the same character are identified as related, to improve the quality of the integrated multimedia content, content with the same genre and similar style can be selected for integration. For instance, content in the motion comic genre can be selected for integration, thus ensuring consistency in the generated multimedia content.

[0112] In some embodiments, integrating the plurality of related content to generate the multimedia content includes: selecting at least a portion of the plurality of related content for integration based on feedback regarding the plurality of related content, and generating the multimedia content.

[0113] In addition to using the genre and style of the content as a basis for integration, feedback from other users on each piece of content can also be used as a basis for integration.

[0114] For example, each user-generated content can be promoted independently, and then, based on feedback from other users in the community, the content with better feedback can be selected and integrated to improve the quality of the generated multimedia content.

[0115] The preceding text has detailed each step of the content generation method proposed in this disclosure. Below, we will combine... Figures 6A to 6C This section introduces the specific implementation of the content generation method. Figures 6A to 6C The diagram illustrates a content generation method performed in some embodiments of this disclosure.

[0116] like Figure 6A As shown, after receiving story text 61 as input, text segments 621 to 623 can be determined based on the creative dimension of story text 61, which are used to generate multiple scripts 631 to 633. Scripts 631 and 632 are split based on the character dimension, with script 631 corresponding to character A and script 632 corresponding to character B. Script 633 is split based on the plot dimension, corresponding to chapters one through ten of the story text.

[0117] Subsequently, as Figure 6B As shown, at least one content generation task can be created for each script. For example, content generation task 641 corresponds to script 631, content generation tasks 642 and 643 correspond to script 632, and content generation tasks 644 and 645 correspond to script 633.

[0118] The genres of content generation task 642 and content generation task 643 can be different. For example, the genre of content generation task 642 is motion comics, while the genre of content generation task 643 is video dramas.

[0119] The scenarios for content generation task 644 and content generation task 645 can be different. For example, the scenario for content generation task 644 is a dialogue scenario, while the scenario for content generation task 645 is a fighting scenario.

[0120] After creating the above content generation tasks, users 651 to 655 can be identified based on the user's historical content creation, and each task can be distributed to the matched users so that they can generate content according to the tasks.

[0121] While distributing content generation tasks, you can also distribute reference materials corresponding to the content generation tasks to users to improve the efficiency and quality of content generation.

[0122] Finally, as Figure 6C As shown, based on the content 661 to 665 created by each user, and after obtaining user authorization, the content can be integrated to generate multimedia content 671 and 672.

[0123] For example, relevant content can be identified and integrated based on the attribute information of the creative dimension. Contents 662 and 663 both correspond to script 632, and therefore can be identified as relevant content. Similarly, content 664 and 665 can also be identified as relevant content. When there is a relationship between character A and character B, for example, character A is the male protagonist and character B is the female protagonist, content 661, content 662, and content 663 can also be identified as relevant content.

[0124] As can be seen, related content can be understood as grouping of content. The same content may exist in multiple groups, thus integrating to generate different multimedia content.

[0125] Once the relevant content is determined, it can be integrated. Figure 6C In the example shown, content items 661, 662, and 663 are integrated to generate video multimedia content 671. Content items 664 and 665 are integrated to generate video multimedia content 672. The final generated multimedia content can be used for subsequent purposes such as content promotion.

[0126] It should be understood that the above process and interface are merely exemplary and not restrictive. The content generation method proposed in this disclosure can also be displayed in the interface in other ways or generated in other ways, such as the above script, content generation task, and multimedia content.

[0127] The above describes the content generation method provided in this disclosure. The video generation method disclosed above can break down multiple scripts and corresponding content generation tasks based on the creative dimension of the story text, distribute these content generation tasks to users with matching abilities, and finally integrate the content generated by multiple users to generate multimedia content, thereby achieving collaborative creation by multiple users and improving the generation efficiency and quality of multimedia content.

[0128] The following is for reference. Figure 7 and Figure 8 The present disclosure describes a content generation apparatus according to embodiments thereof, used to perform any of the embodiments of the above-described content generation method. Figure 7 A block diagram of a content generation apparatus according to some embodiments of the present disclosure is shown.

[0129] like Figure 7 As shown, the content generation device 7 includes: a script generation module 71, configured to generate multiple scripts based on the creative dimension of the story text, wherein each script corresponds to a part of the story text; a task creation module 72, configured to create at least one content generation task based on each script; a task distribution module 73, configured to distribute multiple content generation tasks corresponding to the multiple scripts to multiple matching users, wherein the user's historical content matches at least one of the genre, style, and category of the content generation task; and a content generation module 74, configured to integrate at least a portion of the multiple contents generated by the multiple users based on the attribute information of the creative dimension to generate multimedia content.

[0130] The script generation module 71 of the content generation device 7 can, for example, be used to execute... Figure 1 Step S1. The task creation module 72 of the content generation device 7 can, for example, be used to perform... Figure 1 Step S2. The task distribution module 73 of the content generation device 7 can, for example, be used to perform... Figure 1 Step S3. The content generation module 74 of the content generation device 7 can, for example, be used to perform... Figure 1 Step S4.

[0131] The content generation device disclosed herein can break down multiple scripts and corresponding content generation tasks based on the creative dimension of the story text, distribute these content generation tasks to users with matching abilities, and finally integrate the content generated by multiple users to generate multimedia content, so as to realize the collaborative creation of multiple users and improve the generation efficiency and quality of multimedia content.

[0132] Figure 8 A block diagram of a content generation apparatus according to other embodiments of the present disclosure is shown.

[0133] like Figure 8 As shown, the content generation apparatus 8 includes: at least one memory 81; and at least one processor 82 coupled to the at least one memory 81, the at least one processor 82 being configured to execute the content generation method as described in any of the foregoing embodiments based on instructions stored in the at least one memory 81.

[0134] Memory 81 is used to store one or more computer-readable instructions. Memory 81 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 111 may, for example, store operating systems, application programs, bootloaders, databases, and other programs, as well as various application programs and various data.

[0135] Processor 82 is configured to execute computer-readable instructions to implement the content generation method described in any of the foregoing embodiments. Specific implementations of each step of the method can be found in the above embodiments, for example... Figures 1 to 5 The steps involved are repeated here, so the details will not be repeated.

[0136] The content generation device disclosed herein can break down multiple scripts and corresponding content generation tasks based on the creative dimension of the story text, distribute these content generation tasks to users with matching abilities, and finally integrate the content generated by multiple users to generate multimedia content, so as to realize the collaborative creation of multiple users and improve the generation efficiency and quality of multimedia content.

[0137] The processor 82 can be various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The central processing unit (CPU) can be based on x86 or ARM architectures, etc.

[0138] The processor 82 and the memory 81 can communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. The processor 82 and the memory 81 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0139] It should be noted that Figure 8The components of the content generation apparatus 8 shown are merely exemplary and not limiting. The content generation apparatus 8 may also have other components depending on the specific application requirements. The processor 82 can control other components in the content generation apparatus 8 to perform desired functions.

[0140] The content generation device 8 can be implemented by software, firmware and / or hardware, and can be integrated into a device with the relevant application installed.

[0141] Figure 9 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0142] Figure 9 The electronic device 9 shown can be a computer system with a dedicated hardware structure, which can perform corresponding functions when the relevant application is installed.

[0143] Electronic devices include, but are not limited to, mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet PCs, portable multimedia players (PMPs), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.

[0144] like Figure 9 As shown, the Central Processing Unit (CPU) 91 performs various processes based on a program stored in the Read-Only Memory (ROM) 92 or a program loaded from the storage section 98 into the Random Access Memory (RAM) 93. The RAM 93 stores data required as needed when the CPU 91 performs various processes, etc. The CPU is merely exemplary; it could also be other types of processors, such as the various processors described above. The ROM 92, RAM 93, and storage section 98 can be various forms of computer-readable storage media. It should be noted that although... Figure 9 The diagram shows ROM 92, RAM 93 and storage section 98, but one or more of them may be combined or located in the same or different memory or storage modules.

[0145] CPU 91, ROM 92 and RAM 93 are interconnected via bus 94. Input / output interface 95 is also connected to bus 94.

[0146] The following components are connected to the input / output interface 95: input section 96, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 97, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 98, including hard disk, magnetic tape, etc.; and communication section 99, including network interface cards such as LAN cards, modems, etc. The communication section 99 allows communication processing via a network such as the Internet. It is easy to understand that, although... Figure 9 The portion of the electronic device 9 shown communicates via bus 94, but it may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0147] As needed, drive 910 is also connected to input / output interface 95. Removable media 911, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 910 as needed, so that computer programs read from them can be installed into storage section 98 as needed.

[0148] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as a removable medium 911.

[0149] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to implement the content generation method described in any of the foregoing embodiments. The computer program product includes computer instructions carried on a computer-readable medium, containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer instructions can be downloaded and installed from a network via communication section 99, or installed from storage section 98, or installed from ROM 92. When the computer program is executed by CPU 91, the methods of embodiments of this disclosure are performed.

[0150] The above content generation method can break down the story text into multiple scripts and corresponding content generation tasks based on the creative dimension of the story text, and distribute these content generation tasks to users with matching abilities. Finally, the content generated by multiple users is integrated to generate multimedia content, so as to realize the collaborative creation of multiple users and improve the generation efficiency and quality of multimedia content.

[0151] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0152] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0153] Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the content generation method described in any of the foregoing embodiments.

[0154] The content generation method disclosed herein can break down multiple scripts and corresponding content generation tasks based on the creative dimension of the story text, distribute these content generation tasks to users with matching abilities, and finally integrate the content generated by multiple users to generate multimedia content, thereby realizing the collaborative creation of multiple users and improving the generation efficiency and quality of multimedia content.

[0155] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0156] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0157] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the methods described in any of the foregoing embodiments. For example, the instructions may be embodied in computer program code.

[0158] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0159] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0160] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0161] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A content generation method, comprising: Based on the creative dimensions of the story text, multiple scripts are generated, each script corresponding to a part of the story text; Based on each of the aforementioned scripts, create at least one content generation task; Multiple content generation tasks corresponding to multiple scripts are distributed to multiple matching users, wherein the user's historical content matches at least one of the genre, style, and category of the story text in the content generation task. Based on the attribute information of the creation dimension, at least a portion of the multiple user-generated content is integrated to generate multimedia content.

2. The content generation method according to claim 1, wherein, The creative dimensions include at least one of plot dimension, event dimension, and character dimension, and generating multiple scripts based on the creative dimensions of the story text includes: Identify multiple text segments in the story text that are related to the creative dimension; The multiple scripts are generated based on the multiple text paragraphs.

3. The content generation method according to claim 2, wherein, The creative dimension includes the plot dimension, and generating multiple scripts based on the creative dimension of the story text includes: Identify multiple text segments with continuous plots in the story text; Based on the multiple text paragraphs, generate multiple scripts with consecutive plots.

4. The content generation method according to claim 2, wherein, The creative dimension includes the event dimension, and generating multiple scripts based on the creative dimension of the story text includes: Based on the plot nodes of the story text, determine multiple events in the story text; For each of the events, the corresponding text paragraph is determined in the story text; Based on the determined text paragraphs, at least one script is generated.

5. The content generation method according to claim 2, wherein, The story text includes multiple characters, the creative dimension includes a character dimension, and generating multiple scripts based on the creative dimension of the story text includes: For each of the aforementioned characters, determine the text paragraphs in the story text that correspond to the character; Based on the determined text paragraphs, at least one script is generated.

6. The content generation method according to claim 1, wherein, The creation of at least one content generation task based on each of the aforementioned scripts includes: Based on the script, which includes multiple scenarios, multiple content generation tasks are created for different scenarios, and the multiple content generation tasks may be of the same or different genres.

7. The content generation method according to claim 1, wherein, The script includes scripts corresponding to key events in the story text, and the creation of at least one content generation task based on the script includes: Based on the scripts corresponding to the key events, create multiple content generation tasks with the same genre and the same scene.

8. The content generation method according to claim 1, wherein, The script includes scripts corresponding to the characters in the story text, and the creation of at least one content generation task based on the script includes: Based on the attributes of the characters corresponding to each script, at least one content generation task is created, wherein the genre of the at least one content generation task matches the attributes of the characters.

9. The content generation method according to claim 1, wherein, The step of generating multiple content tasks corresponding to multiple scripts and distributing them to multiple matched users includes: Based on the attribute data of the story text and the interaction data of the community corresponding to the story text, multiple candidate users are determined from the users of the community, wherein the interaction data is obtained based on user authorization in the community; Based on at least one of the genre, style, and category of the historical content created by the plurality of candidate users after authorization, determine the user that matches each of the content generation tasks from the plurality of candidate users; The multiple content generation tasks are then distributed to the matched multiple users.

10. The content generation method according to claim 1, wherein, The step of generating multiple content tasks corresponding to multiple scripts and distributing them to multiple matched users includes: Identify historical materials corresponding to the story text, wherein the historical materials include at least one of character materials, scene materials, special effects materials, and sound materials; Based on the feedback from the historical materials, reference materials corresponding to at least one of the genre and style of each of the content generation tasks are determined from the historical materials. The multiple content generation tasks and their corresponding reference materials are distributed to the multiple matched users.

11. The content generation method according to claim 10, wherein, The reference materials include content templates applied to each of the content generation tasks.

12. The content generation method according to claim 1, wherein, The multiple content generation tasks include a first generation task and a second generation task, and the distribution of the multiple content generation tasks corresponding to the multiple scripts to the multiple matching users includes: In response to the first generation task depending on the second generation task, the first generation task is distributed to a first user matching the first content generation task, and the content generated by the first user and the second content generation task are distributed to a second user matching the second content generation task; or Since there is no dependency between the first generation task and the second generation task, the first generation task and the second generation task are distributed to the first user and the second user, respectively.

13. The content generation method according to claim 1, wherein, The step of integrating at least a portion of the multiple user-generated content items based on the attribute information of the creation dimension to generate multimedia content includes: Based on the attribute information of the creation dimension corresponding to the multiple contents, determine multiple related contents among the multiple contents; The multiple related contents are integrated to generate the multimedia content.

14. The content generation method according to claim 13, wherein, The step of determining multiple related contents among the multiple contents based on the attribute information of the creation dimension corresponding to the multiple contents includes: Multiple pieces of content corresponding to the same script are identified as the multiple related pieces of content; or Multiple pieces of content corresponding to multiple scripts belonging to the same creative dimension are identified as the multiple related contents.

15. The content generation method according to claim 13, wherein, The process of integrating the multiple related contents to generate the multimedia content includes: Based on at least one of the genre and style of the content generation task corresponding to the plurality of related content, determine at least one of the genre similarity and style similarity among the plurality of related content; The multimedia content is generated by integrating the multiple related content based on at least one of the genre similarity and style similarity among the multiple related content.

16. The content generation method according to claim 13, wherein, The process of integrating the multiple related contents to generate the multimedia content includes: Based on feedback regarding the multiple related content items, at least a portion of the content items are selected and integrated to generate the multimedia content.

17. A content generation apparatus, comprising: The script generation module is configured to generate multiple scripts based on the creative dimensions of the story text, wherein each script corresponds to a part of the story text; The task creation module is configured to create at least one content generation task based on each of the aforementioned scripts; The task distribution module is configured to distribute multiple content generation tasks corresponding to multiple scripts to multiple matching users, wherein the user's historical content matches at least one of the genre, style, and category of the story text of the content generation task. The content generation module is configured to integrate at least a portion of the multiple user-generated content items based on the attribute information of the creation dimension to generate multimedia content.

18. A content generation apparatus, comprising: At least one memory; as well as At least one processor coupled to the at least one memory, the at least one processor being configured to perform the content generation method as described in any one of claims 1 to 16 based on instructions stored in the at least one memory.

19. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the content generation method as described in any one of claims 1 to 16.

20. A computer program product, when run on a computer, causes the computer to implement the content generation method as described in any one of claims 1 to 16.

Images