Video script generation method and device, computer device and storage medium

Abstract

Embodiments of the present application provide a video script generation method and device, computer equipment and a storage medium, relating to the technical field of artificial intelligence. The method comprises: obtaining script requirement description information; obtaining script framework information according to the script requirement description information; using a large language model and a first prompt word, generating multiple script segments based on a pre-constructed video script knowledge base and the script framework information, and generating an initial video script according to the multiple script segments; the first prompt word comprises a script segment prompt word for each script segment in the multiple script segments; using the large language model and a second prompt word, generating a target video script based on the initial video script; the second prompt word is used to guide the large language model to adjust the script data format of the initial video script. The method improves the efficiency and accuracy of video script generation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a video script generation method and device, computer equipment, storage medium and computer program product. BACKGROUND

[0002] In the field of video shooting, it is usually necessary to generate a corresponding video script in advance. In view of the drawbacks of the traditional method relying on artificial creation, such as low efficiency and being easily limited by the personal experience and style of the creator, in general, in the video script creation technology, a large language model can be introduced to generate a video script using the large language model, which can improve the efficiency of video script generation.

[0003] However, in the current video script generation technology, the video information obtained in the information processing process is relatively single and insufficient, for example, basic information such as dialogues and pictures is extracted from the video, while potential cultural connotations and emotional expressions are ignored, resulting in a significant lack of logical coherence, cultural adaptability and emotional resonance in the generated video script, and the problems of low accuracy and low practicability. SUMMARY

[0004] Therefore, it is necessary to provide a video script generation method, device, computer equipment, storage medium and computer program product to solve the above technical problems.

[0005] In a first aspect, the present application provides a video script generation method. The method comprises:

[0006] obtaining script requirement description information;

[0007] obtaining script framework information according to the script requirement description information;

[0008] segmenting and generating a plurality of script segments based on a pre-constructed video script knowledge base and the script framework information using a large language model and a first prompt word, and generating an initial video script according to the plurality of script segments; the first prompt word comprises a script segment prompt word for each of the plurality of script segments;

[0009] generating a target video script based on the initial video script using the large language model and a second prompt word; the second prompt word is used to guide the large language model to adjust the script data format of the initial video script.

[0010] In one of the embodiments, before the segment generation of the plurality of script segments based on the pre-constructed video script knowledge base and the script framework information using the large language model and the first prompt word, the method further comprises: obtaining a plurality of historical video scripts in a historical time period corresponding to a current time period; obtaining a plurality of script elements according to historical video script information of each of the plurality of historical video scripts; obtaining element attribute information of each of the plurality of script elements, and obtaining element relationships between each of the plurality of script elements according to the element attribute information; and constructing the video script knowledge base according to the plurality of script elements and the element relationships between each of the plurality of script elements.

[0011] In one of the embodiments, the segment generation of the plurality of script segments based on the pre-constructed video script knowledge base and the script framework information using the large language model and the first prompt word comprises: determining a script structure according to the script framework information; screening a matching video script matching the script framework information from the plurality of historical video scripts according to the script framework information and a plurality of script elements of each of the plurality of historical video scripts and element relationships between each of the plurality of script elements included in the video script knowledge base; and segment generating the plurality of script segments according to the script structure and the matching video script using the large language model and the first prompt word.

[0012] In one of the embodiments, the screening of the matching video script matching the script framework information from the plurality of historical video scripts according to the script framework information and a plurality of script elements of each of the plurality of historical video scripts and element relationships between each of the plurality of script elements included in the video script knowledge base comprises: obtaining a similarity between the script framework information and each of the plurality of historical video scripts according to the script framework information and the plurality of script elements of each of the plurality of historical video scripts and the element relationships between each of the plurality of script elements included in the video script knowledge base; and determining the historical video script with a similarity greater than a preset similarity threshold as the matching video script.

[0013] In one of the embodiments, the obtaining of the script framework information according to the script requirement description information comprises: obtaining an associated script keyword according to the script requirement description information; obtaining a target associated video in an associated video data source according to the associated script keyword; obtaining a multi-dimensional feature of the target associated video according to video information of the target associated video; the video information comprises at least two of text information, audio information, and video image information of the target associated video; the multi-dimensional feature at least comprises an emotional expression feature; and obtaining the script framework information according to the multi-dimensional feature.

[0014] In one of the embodiments, the obtaining the target associated video according to the associated script keyword in the associated video data source comprises: obtaining a plurality of candidate associated videos according to the associated script keyword in the associated video data source; obtaining script requirement features according to the script requirement description information; and screening the target associated video from the plurality of candidate associated videos according to the script requirement features.

[0015] In one of the embodiments, before the generating the target video script based on the initial video script by using the large language model and the second prompt word, the method further comprises: determining initial data format information of the initial video script; determining target data format information of the target video script; and generating the second prompt word according to the initial data format information and the target data format information.

[0016] In a second aspect, the present application provides a video script generation device. The device comprises:

[0017] an information obtaining module configured to obtain script requirement description information;

[0018] a framework obtaining module configured to obtain script framework information according to the script requirement description information;

[0019] a first script generation module configured to generate an initial video script by using a large language model and a first prompt word based on a pre-constructed video script knowledge base and the script framework information, and segmenting a plurality of script segments, wherein the first prompt word comprises a script segment prompt word for each of the plurality of script segments;

[0020] a second script generation module configured to generate a target video script by using the large language model and a second prompt word based on the initial video script, wherein the second prompt word is used to guide the large language model to adjust a script data format of the initial video script.

[0021] In a third aspect, the present application further provides a computer device. The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0022] obtaining script requirement description information;

[0023] obtaining script framework information according to the script requirement description information;

[0024] The large language model and the first prompt word are used to generate a plurality of script segments based on a pre-constructed video script knowledge base and the script framework information, and an initial video script is generated according to the plurality of script segments; the first prompt word includes a script segment prompt word for each of the plurality of script segments.

[0025] The large language model and the second prompt word are used to generate a target video script based on the initial video script; the second prompt word is used to guide the large language model to adjust the script data format of the initial video script.

[0026] In a fourth aspect, the present application also provides a computer readable storage medium. The computer readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to implement the following steps:

[0027] Obtaining script requirement description information;

[0028] Obtaining script framework information according to the script requirement description information;

[0029] The large language model and the first prompt word are used to generate a plurality of script segments based on a pre-constructed video script knowledge base and the script framework information, and an initial video script is generated according to the plurality of script segments; the first prompt word includes a script segment prompt word for each of the plurality of script segments.

[0030] The large language model and the second prompt word are used to generate a target video script based on the initial video script; the second prompt word is used to guide the large language model to adjust the script data format of the initial video script.

[0031] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and the computer program is executed by a processor to implement the following steps:

[0032] Obtaining script requirement description information;

[0033] Obtaining script framework information according to the script requirement description information;

[0034] The large language model and the first prompt word are used to generate a plurality of script segments based on a pre-constructed video script knowledge base and the script framework information, and an initial video script is generated according to the plurality of script segments; the first prompt word includes a script segment prompt word for each of the plurality of script segments.

[0035] The large language model and the second prompt word are used to generate a target video script based on the initial video script; the second prompt word is used to guide the large language model to adjust a script data format of the initial video script.

[0036] In the video script generation method, device, computer equipment, storage medium and computer program product, first, script requirement description information can be obtained; next, script framework information can be obtained according to the script requirement description information; further, a large language model and a first prompt word can be used to generate a plurality of script segments based on a pre-constructed video script knowledge base and the script framework information, and an initial video script can be generated according to the plurality of script segments; the first prompt word includes a script segment prompt word for each script segment in the plurality of script segments; finally, a large language model and a second prompt word can be used to generate a target video script based on the initial video script; the second prompt word is used to guide the large language model to adjust a script data format of the initial video script. In the method provided by the embodiment of the application, the script framework information can be obtained according to the script requirement description information combined with the hot information, and the plurality of script segments can be generated based on the script framework information by using the large language model and the pre-constructed video script knowledge base, and then the initial video script is generated, which can improve the efficiency and accuracy of video script generation. Subsequently, the initial video script can be optimized to obtain the target video script, which can further improve the accuracy of video script generation. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the application or the related art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the application or the related art. Obviously, the drawings in the following description only some embodiments of the application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0038] Figure 1 A flowchart of a video script generation method provided by an embodiment of the application;

[0039] Figure 2 A flowchart of obtaining script framework information provided by an embodiment of the application;

[0040] Figure 3 A flowchart of constructing a video script knowledge base provided by an embodiment of the application;

[0041] Figure 4 A flowchart of generating a plurality of script segments provided by an embodiment of the application;

[0042] Figure 5A flowchart of a process for obtaining multi-dimensional features of a target associated video is provided for an embodiment of the present application.

[0043] Figure 6 A flowchart of a process for obtaining a target associated video is provided for an embodiment of the present application.

[0044] Figure 7 A flowchart of a process for generating a second prompt word is provided for an embodiment of the present application.

[0045] Figure 8 A structural block diagram of a video script generation device is provided for an embodiment of the present application.

[0046] Figure 9 An internal structural diagram of a computer device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0048] In one exemplary embodiment, as shown in Figure 1 A video script generation method is provided, and the present embodiment is exemplarily described by taking the method applied to a server. It should be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is realized through the interaction of the terminal and the server. In the present embodiment, the method includes the following steps:

[0049] In step 102, script requirement description information is obtained.

[0050] In the video script generation method, the video script generation system can include a video script generation terminal and a system server. The video script generation terminal can be a personal computer, a notebook computer, a smart phone, a tablet computer, an Internet of Things device, and a portable wearable device, but is not limited thereto. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The system server can be a server for generating a video script in the video script generation system, and can be implemented by an independent server or a server cluster composed of multiple servers. The video script generation terminal can communicate with the system server through a network. A video script generation personnel can register and log in the video script generation system on the video script generation terminal. The video script generation terminal displays a video script demand input page in response to a login operation triggered by the video script generation personnel. The video script generation personnel can input script demand description information on the video script demand input page, and trigger a video script generation request for a to-be-generated video script. The video script generation request includes the script demand description information. In a possible implementation, the to-be-generated video script can be a video promotion script for a promotion video of a target object, such as a target product. The script demand description information can be a promotion demand for a promotion video of a target object, such as a target product. The script demand description information can include demand information for product promotion and demand information for video script creation, such as basic information, creative reference, product characteristics, picture and language style, role requirement, plot and scene design, format specification, audience orientation, and special requirement, etc. The script demand description information can serve as guidance information for generating the to-be-generated video script. The basic information can include a video subject, a video direction, or a core concept (for example, a technology product demonstration and a cultural activity promotion, etc.), a video use (for example, an advertisement, an education and teaching, and an entertainment program, etc.), and a target audience, etc. The characteristics of the target audience can include an age range (for example, children, teenagers, adults, and the elderly, etc.), an interest (for example, a technology enthusiast, an art pursuer, and a sports enthusiast, etc.), and a cultural background, etc. The creative reference source can include a specified reference video link or description, and a popular trend or popular element. The product or service characteristics can include product core advantages, brand image, and values, etc.The picture and visual style requirements can include color preferences (e.g., warm tones, cool tones, bright colors, and retro colors, etc.), scene setting preferences (e.g., natural scenery scenes (forests, beaches, mountains, etc.), urban environment scenes (streets, high-rise buildings, parks, etc.), indoor scenes (home, office, studio, etc.), and style characteristics of scenes (e.g., modern minimalist, classical elegance, science fiction future, etc.), and lens language requirements (e.g., lens movement (push, pull, shake, shift, follow, etc.), shooting angle (low angle, high angle, eye level, etc.), and preference or special requirements for shot size (long shot, wide shot, medium shot, close-up, close-up, etc.). The language style and dialogue requirements can include overall language style (e.g., humorous, serious, warm, passionate, etc.) and dialogue characteristics. The character and character image requirements can include main character characteristics (e.g., personality characteristics (outgoing, introverted, brave, wise, etc.), appearance characteristics (age, body type, appearance description, etc.), and role background (occupation, growth experience, etc.), and role relationship setting (e.g., friends, family, etc.). The plot and story structure requirements can include plot clues and development direction (e.g., setting of the beginning, development, climax and ending of the story, and turning points, suspense settings, etc.), and story structure preferences (e.g., linear narrative, nonlinear narrative (flashback, intercalation, and multi-line narrative, etc.), and circular structure, etc.). The script format and specification requirements can include script format examples and duration requirements. The audience interaction and guidance requirements can include emotional resonance and interaction points, etc., which can be emotional resonance points (e.g., moving, inspiring, and enlightening, etc.) with the audience in the video, and the need to set up interactive elements (e.g., asking questions, guiding comments, and likes, etc.).

[0051] Step 104, according to the script requirement description information, obtaining script framework information.

[0052] Among them, as Figure 2As shown, first, it can be judged according to the script requirement description information whether the script requirement description information contains video direction information; if the script requirement description information contains the video direction information, it can be judged whether the script requirement description information contains a reference video link; if the script requirement description information contains the reference video link, the reference video link is video parsed to obtain script framework information for generating a to-be-generated video script; if the script requirement description information does not contain the reference video link, the associated script keywords of the to-be-generated video script are extracted according to the script requirement description information, and next, the multiple candidate associated videos corresponding to the to-be-generated video script can be obtained according to the associated script keywords in the script requirement description information or the associated video data source of the to-be-generated video script, and further, the target associated video with the highest relevance to the to-be-generated video script can be screened out from the multiple candidate associated videos, and the target associated video is video parsed to obtain script framework information for generating a to-be-generated video script; if the script requirement description information does not contain the video direction information, it is judged whether the script requirement description information contains hot spot related information, if the script requirement description information contains hot spot related information, the associated real-time hot spot corresponding to the script requirement description information is obtained in the associated hot spot data source, and the associated hot spot word is screened out according to the associated real-time hot spot, and next, the multiple candidate associated videos corresponding to the to-be-generated video script can be obtained according to the associated hot spot word in the script requirement description information or the associated video data source of the to-be-generated video script, and further, the target associated video with the highest relevance to the to-be-generated video script can be screened out from the multiple candidate associated videos, and the target associated video is video parsed to obtain script framework information for generating a to-be-generated video script; if the script requirement description information does not contain hot spot related information, the corresponding script keywords are determined according to the script requirement description information, and next, the multiple candidate associated videos corresponding to the to-be-generated video script can be obtained according to the script keywords in the script requirement description information or the associated video data source of the to-be-generated video script, and further, the target associated video with the highest relevance to the to-be-generated video script can be screened out from the multiple candidate associated videos, and the target associated video is video parsed to obtain script framework information for generating a to-be-generated video script.

[0053] In step 106, a large language model and a first prompt word are used to generate multiple script segments based on a pre-constructed video script knowledge base and script framework information, and an initial video script is generated according to the multiple script segments.

[0054] In this step, a video script knowledge base can be pre-constructed, which contains a plurality of historical video scripts. The construction process of the video script knowledge base can include: obtaining a plurality of historical video scripts in a historical time period corresponding to a current time period from a plurality of video script sources (for example, corresponding business systems, or pre-written script sets, etc.); obtaining a plurality of script elements according to historical video script information of each historical video script in the plurality of historical video scripts; obtaining element attribute information of each script element, and obtaining element relationships between script elements according to the element attribute information; and constructing a video script knowledge base according to the plurality of script elements and the element relationships between the script elements. Further, a large language model and a first prompt word can be used to generate a plurality of script segments based on the pre-constructed video script knowledge base and script framework information, and an initial video script can be generated according to the plurality of script segments. The first prompt word of the large language model can be pre-set, and the first prompt word includes a script segment prompt word for each script segment in the plurality of script segments. For example, the first prompt word can be set as "You are an experienced information flow advertisement script copywriter, good at extracting valuable data from various sources and integrating it into an easily understandable form. You have a deep understanding of video content analysis and can accurately grasp the interests and behavior patterns of the audience. You will receive a piece of information: reference video creative content: for reference to the character lines / copy / creativity, etc. in it." Next, the matching video script of the script requirement description information can be screened in the video script knowledge base. Further, the script framework information can be analyzed by the large language model to obtain a script structure for generating the to-be-generated video script. The script structure can include video architecture and key elements of the to-be-generated video script, such as video direction, video subject or core concept, target audience, emotional tone, and visual elements. Finally, the matching video script can be divided into a plurality of matching script segments, such as an introduction matching script segment, a main body matching script segment, and an ending matching script segment. Further, a plurality of script segments can be generated by using the large language model in combination with the script structure and the plurality of matching script segments, and the initial video script can be generated according to the plurality of script segments.

[0055] Step 108, generating a target video script based on the initial video script by using a large language model and a second prompt word.

[0056] Among them, the second prompt word is used to guide the large language model to adjust the script data format of the initial video script. The script data format may include a script logical sequence and a data structure, and the script data format of the video script to be generated may be set in advance in the second prompt word. The initial video script is input into the large language model. Under the guidance of the second prompt word, the large language model can check and optimize the logical sequence of the initial video script. For example, the logical sequence of the initial video script may be to first determine the theme and core plot, and then gradually expand the role shaping, scene design, line writing and other links, and finally perform an overall logical check and optimization. In addition, the large language model can also convert the data structure of the initial video script from unstructured data to structured data, and then the converted structured data can be verified and cleaned to ensure the accuracy and integrity of the data. Furthermore, in this step, the organized structured data can be combined with visualization tools to visualize the script content. For example, graphical script editing software can be used to generate corresponding graphical representations, such as shot sequences on a timeline or scene layout diagrams, based on information such as scene descriptions and shot sizes in the structured data. This allows script creators and relevant personnel to intuitively understand the overall structure and visual effects of the script. Furthermore, visual elements can be colored or labeled based on attributes such as the emotional atmosphere in the data to enhance the visual experience. Human-computer interaction can also be implemented, allowing video script generators to modify the script directly on the video script generation terminal based on the visual presentation. Users can adjust the order of shots by dragging them on the timeline, click on scene elements to edit them (for example, to modify the screen content or lines), and select different shot sizes or emotional atmosphere options to make changes. As users make modifications, the system updates the modified information to the structured data in real time and feeds it back to the large language model. Based on the new input and modification intent, the model provides further optimization suggestions or automatically adjusts relevant content, enabling efficient human-computer collaboration and iterative optimization. For example, if a user shortens the duration of a scene, the system automatically updates the duration field in the structured data and asks the large language model whether the rhythm of the lines or the content of the picture need to be adjusted when the duration is shortened. The model provides corresponding answers based on its knowledge and experience, and the user can continue to make modifications based on the answers.

[0057] In the method of the embodiment, first, script requirement description information can be acquired; next, script framework information can be acquired according to the script requirement description information; further, a large language model and a first prompt word can be used to generate a plurality of script segments based on a pre-constructed video script knowledge base and the script framework information, and an initial video script can be generated according to the plurality of script segments; the first prompt word includes a script segment prompt word for each script segment in the plurality of script segments; finally, a large language model and a second prompt word can be used to generate a target video script based on the initial video script; the second prompt word is used to guide the large language model to adjust the script data format of the initial video script. In the method provided in the embodiment of the application, the script framework information can be obtained according to the script requirement description information in combination with hot information, and a plurality of script segments can be generated based on the script framework information by using a large language model and a pre-constructed video script knowledge base, and then an initial video script is generated, which can improve the efficiency and accuracy of video script generation. Subsequently, the initial video script can be optimized to obtain a target video script, which can further improve the accuracy of video script generation.

[0058] In one exemplary embodiment, as shown in FIG. 1, step 106 can include the following steps for providing a construction method of the video script knowledge base, and the steps specifically include steps 302 to 308. Wherein: Figure 3

[0059] Step 302, a plurality of historical video scripts in a historical time period corresponding to a current time period are acquired.

[0060] Step 304, a plurality of script elements are acquired according to historical video script information of each historical video script in the plurality of historical video scripts.

[0061] Step 306, element attribute information of each script element is acquired, and element relationships between the script elements are acquired according to the element attribute information.

[0062] Step 308, a video script knowledge base is constructed according to the plurality of script elements and the element relationships between the script elements.

[0063] ​Specifically, in the process of obtaining a plurality of historical video scripts, at least one screening indicator can be set, such as the number of plays, likes, comments, shares, creativity novelty, and structural integrity, and the plurality of historical video scripts can be obtained from a large number of video scripts using the at least one screening indicator. Next, script disassembly and annotation can be performed on each historical video script in the plurality of historical video scripts. Each historical video script can be divided into three parts, the introduction part, the main content, and the ending part, according to the historical video script information of each historical video script. Each part is disassembled and annotated, a plurality of script elements of each historical script video are obtained, and the element relationship between the plurality of script elements is obtained. For the introduction part, (1) the function and role of the introduction part are analyzed in depth, such as whether it can quickly attract the attention of the audience (by creating suspense, asking thought-provoking questions, showing shocking scenes, etc.), effectively introducing the theme (closely related to the theme and naturally transitioned), and successfully creating a specific atmosphere (such as tension, warmth, mystery, etc.). (2) The key elements of the introduction part, i.e., script elements, are extracted, including scene setting (detailed recording of the location, time, and environmental characteristics of the scene), role presentation (the first appearance of the role, the shaping of the appearance image, the characteristics of the behavior and action, etc.), the style of the dialogue (humorous and witty, serious and solemn, poetic, etc. Style characteristics and use of specific language skills), and the use of music or sound effects (type, rhythm, and melody of music, and uniqueness of sound effects and their role in creating atmosphere). (3) The extracted key elements are classified and annotated using labels with clear semantics, such as “attention-grabber” (attention-grabbing element), “theme-introduction” (theme introduction element), “mysterious-atmosphere-builder” (mysterious atmosphere-building element), etc. for subsequent query and analysis. For the main content, (1) the plot development context of the main content is carefully combed, and the main plot nodes, i.e., script elements, and their roles in story development are clarified, such as turning points in the story (moments when the plot changes significantly, changing the direction of the story), and division of development stages (dividing the main content into different development stages according to the ups and downs of the plot and the rhythm). (2) The behavior of the characters in each plot node and the content of the dialogue are analyzed in detail, and core plot information is extracted, including the goals, actions, and decision-making processes of the characters in the plot, as well as the key information, emotional attitudes, and changes in character relationships conveyed by the dialogue. (3) The emotional change curve in the main content is accurately identified, and the emotional climax and trough parts are annotated (determined by analyzing the emotional expression of the characters, the tension of the plot, and the highlighting of music and sound effects), as well as the corresponding plot and dialogue, recording the type of emotion (such as joy, sadness, anger, excitement, etc.) and the change in intensity.(4) Comprehensively extract the visual elements in the main content, including scene transitions (the method, timing, and purpose of transitions), picture composition characteristics (the use and effects of symmetrical composition, asymmetrical composition, and the rule of thirds), camera movement methods (the use and effects of push shots, pull shots, pan shots, dolly shots, and follow shots), and color use (main color, color contrast, and color symbolic meaning), and make detailed classification and annotation. For the ending, (1) clarify the purpose of the ending, such as sublimating the theme (elevating the theme to a higher level and triggering deeper thinking among the audience) and leaving a deep impression (making the audience unforgettable through unique pictures, touching plots, and powerful lines). (2) Extract the key information of the ending, namely the script elements, including emotional ending methods (for example, a heartwarming and touching ending, humorous replays, and a shocking climax ending), and picture presentation (how the brand logo is displayed, how the product is handled in close-up, and how the scene is frozen). (3) Label the script elements at the end, for example, label the emotional ending as "touching-ending", "humorous-ending", "powerful-climax-ending", etc. according to the emotional type. Next, a video script knowledge base can be constructed based on multiple script elements and the element relationship between each script element. Specifically, first, each of the multiple script elements of each historical video script can be determined as a node, and multiple nodes of the video script knowledge base can be created, such as the scene node and character node of the introduction part, the plot node and emotional node in the main content, the recommendation node and picture node of the ending part, etc., and edges are defined to represent the node relationship between the nodes, that is, the element relationship; next, the nodes can be labeled, and the corresponding nodes can be labeled according to the element attribute information of the script element corresponding to each node, such as the name, type and function of the element, etc., and a unique identifier can be given to each node; further, a node can be established For example, a "lead to" edge is established between the scene node of the introduction part and the starting plot node of the main content to indicate the transition of the plot; a "participate in" edge is established between the character node and the plot node in which it participates to reflect the character's action trajectory in the story; finally, a graph database is used to store the constructed video script knowledge base, and a complete data management mechanism can be established for the video script knowledge base, including a regular data backup strategy to prevent data loss; an update strategy is formulated to clarify how to update the nodes and edges in the knowledge base when new high-quality scripts are added or the information of existing scripts changes; a convenient data query interface is designed to facilitate the rapid query and use of information in the knowledge base in the subsequent script creation process.

[0064] In the method of the embodiment, a pre-constructed video script knowledge base can be introduced, and a matching video script of the script requirement description information is obtained in the video script knowledge base, and the large language model is used to generate a plurality of script segments based on the script framework information and the matching video script, and then generate an initial video script, which can improve the efficiency and accuracy of video script generation.

[0065] In one exemplary embodiment, as shown in FIG. 4, step 106 can include steps 402 to 406. Among them: Figure 4

[0066] Step 402, determining the script structure according to the script framework information.

[0067] Among them, the script framework information can be parsed by the large language model to obtain the script structure for generating the to-be-generated video script. The script structure can include the video architecture and key elements of the to-be-generated video script, such as video direction, video subject or core concept, target audience, emotional tone, and visual elements.

[0068] Step 404, according to the script framework information and the plurality of script elements and the element relationship between each script element of each historical video script in the plurality of historical video scripts contained in the video script knowledge base, filtering out a matching video script matched with the script framework information from the plurality of historical video scripts.

[0069] Among them, the video script knowledge base contains a plurality of historical video scripts. Each of the plurality of historical video scripts corresponds to a plurality of nodes and a plurality of edges, wherein the node is used to represent the constituent elements of each historical video script, and each node corresponds to a script element; the edge is used to represent the relationship between the nodes, that is, to represent the relationship between the script elements. Each of the plurality of historical video scripts contains a plurality of script elements and the element relationship between each of the plurality of script elements, and each script element is labeled with corresponding element attribute information. Therefore, the similarity between each historical video script and the to-be-generated video script can be obtained according to the plurality of script elements of each historical video script, the element attribute information of each script element, and the element relationship between each script element and the script framework information, and then the matching video script matched with the to-be-generated video script can be filtered out from the plurality of historical video scripts according to the similarity. In one possible implementation, the historical video script with a similarity greater than a preset similarity threshold can be determined as the matching video script of the to-be-generated video script.

[0070] Step 406, using the large language model and the first prompt word, generating a plurality of script segments based on the script structure and the matching video script. ​

[0071] Among them, the first prompt word of the large language model can be set in advance. The first prompt word includes a script segment prompt word for each script segment in multiple script segments. For example, the first prompt word can be set to "You are an experienced information flow advertising script copywriting expert who is good at extracting valuable data from various sources and integrating it into an easy-to-understand form. You have a deep understanding of video content analysis and can accurately grasp the audience's interests and behavior patterns. You will receive a message: reference video creative content: for reference to the character lines / copywriting / creativity, etc." Next, the matching video script can be divided into multiple matching script segments, for example, it can be divided into an introduction matching script segment, a main body matching script segment and an ending matching script segment. Then, a large language model can be used, under the guidance of the first prompt word, combined with the script structure and the multiple matching script segments, to generate multiple corresponding script segments by segmented imitation, and generate the initial video script based on the multiple script segments, wherein the introduction matching script segment of the matching video script can be imitated according to the script structure to obtain the introduction script segment of the initial video script; the main body matching script segment of the matching video script can be imitated according to the script structure to obtain the main body script segment of the initial video script; and the ending matching script segment of the matching video script can be imitated according to the script structure to obtain the ending script segment of the initial video script.

[0072] In the method of this embodiment, a large language model and a pre-built video script knowledge base can be used to generate multiple script segments based on the script framework information, and then generate an initial video script, which can improve the efficiency and accuracy of video script generation.

[0073] In an exemplary embodiment, step 404 may include:

[0074] Based on the script framework information and the multiple script elements of each historical video script in the multiple historical video scripts contained in the video script knowledge base and the element relationship between each script element, the similarity between the script framework information and each historical video script in the multiple historical video scripts is obtained; the historical video scripts whose similarity is greater than the preset similarity threshold are determined as matching video scripts.

[0075] The script framework information can be subjected to feature extraction to obtain a plurality of script feature information of the script framework information, which can be a plurality of script feature information of the video script to be generated. The historical script feature information of the corresponding historical video script can also be obtained according to the plurality of script elements of each historical video script, the element attribute information of each script element, and the element relationship between each script element. The similarity between the script framework information and each historical video script in the plurality of historical video scripts can be obtained according to the plurality of script feature information of the video script to be generated and the historical script feature information of each historical video script. The similarity can be used to represent the degree of association between each historical video script and the video script to be generated, and further, the reference value for generating the video script to be generated. In a possible implementation manner, in the process of generating a plurality of script segments based on the pre-constructed video script knowledge base and the script framework information by using a large language model and a first prompt word, the matching script segment of each script segment in the plurality of script segments can be screened in the video script knowledge base by using this method, and then each script segment can be generated based on the script segment feature information of each script segment in the script framework information and the corresponding matching script segment. For example, the plurality of script segments can include an introduction script segment, a main script segment, and an ending script segment. Each historical video script in the plurality of historical video scripts in the video script knowledge base can include a historical introduction script segment, a historical main script segment, and a historical ending script segment. In this way, the introduction feature information of the introduction script segment, the main feature information of the main script segment, and the ending feature information of the ending script segment of the video script to be generated can be obtained according to the script framework information, and the historical introduction feature information, the historical main feature information, and the historical ending feature information of each historical video script can be obtained. Next, the matching historical introduction script segment of the introduction script segment of the video script to be generated can be screened from the plurality of historical introduction script segments contained in the video script knowledge base according to the similarity between the introduction feature information of the video script to be generated and the historical introduction feature information of the historical introduction script segment of each historical video script in the plurality of historical video scripts in the video script knowledge base. The matching historical main script segment of the main script segment of the video script to be generated can also be screened from the plurality of historical main script segments contained in the video script knowledge base by using the same method, and the matching historical ending script segment of the ending script segment of the video script to be generated can be screened from the plurality of historical ending script segments contained in the video script knowledge base.

[0076] In the method of the embodiment, the matching video script of the video script to be generated can be obtained in the video script knowledge base, and then the video script to be generated can be obtained by segment-by-segment imitation according to the matching video script, thereby improving the efficiency and accuracy of video script generation.

[0077] In an exemplary embodiment, Figure 5 As shown, step 102 may include steps 502 to 508. Among them:

[0078] Step 502: Obtain associated script keywords based on the script requirement description information.

[0079] Step 504: Obtain the target associated video from the associated video data source according to the associated script keywords.

[0080] First, based on the script requirement description information, it can be determined whether the script requirement description information contains video direction information; if the script requirement description information contains the video direction information, it can be determined whether the script requirement description information contains a reference video link; if the script requirement description information contains the reference video link, the reference video link is subjected to video parsing to obtain script framework information for generating the video script to be generated; if the script requirement description information does not contain the reference video link, the associated script keywords of the video script to be generated are extracted based on the script requirement description information. Next, based on the associated script keywords, multiple candidate associated videos corresponding to the video script to be generated can be obtained from the script requirement description information or the associated video data source of the video script to be generated. Furthermore, the target associated video with the highest relevance to the video script to be generated can be screened out from the multiple candidate associated videos, and the target associated video is subjected to video parsing to obtain script framework information for generating the video script to be generated. If the script requirement description information does not contain the video direction information, it is determined whether the script requirement description information contains hotspot related information. If the script requirement description information does not contain the video direction information, it is determined whether the script requirement description information contains hotspot related information. If the information contains hotspot related information, then the associated real-time hotspot corresponding to the script requirement description information is obtained from the associated hotspot data source, and the associated hotspot words are filtered out based on the associated real-time hotspot. Next, based on the associated hotspot words, multiple candidate associated videos corresponding to the video script to be generated can be obtained from the script requirement description information or the associated video data source of the video script to be generated. Further, the target associated video with the highest relevance to the video script to be generated can be filtered out from the multiple candidate associated videos, and the video analysis is performed on the target associated video to obtain the script framework information for generating the video script to be generated. If the script requirement description information does not contain hotspot related information, then the corresponding script keywords are determined based on the script requirement description information. Next, based on the script keywords, multiple candidate associated videos corresponding to the video script to be generated can be obtained from the script requirement description information or the associated video data source of the video script to be generated. Further, the target associated video with the highest relevance to the video script to be generated can be filtered out from the multiple candidate associated videos, and the video analysis is performed on the target associated video to obtain the script framework information for generating the video script to be generated.

[0081] Step 506: Acquire multi-dimensional features of the target-related video based on the video information of the target-related video.

[0082] The video information includes at least two types of text information, audio information and video image information of the target associated video; and the multidimensional features include at least emotional expression features.

[0083] Specifically, multimodal video analysis can be performed on the target-related video. First, computer vision technology is used to capture dynamic shots (e.g., zooming, panning, and other camera movements and speed changes), character expressions (recognition and analysis of emotions such as joy, anger, sadness, and happiness), and background elements (scene type, environmental atmosphere, key objects, etc.). Next, automatic speech recognition (ASR) technology can be used to extract the dialogue from the video, and natural language processing (NLP) technology can be used to perform text analysis on the dialogue, such as vocabulary usage (industry jargon, buzzwords, colloquial expressions, etc.), sentence structure (pairing of long and short sentences, use of complex sentence structures, etc.), rhetorical techniques (metaphor, personification, parallelism, etc.), and overall language style (humorous, serious, lyrical, etc.). Furthermore, we can combine image information, audio information and text information to conduct sentiment analysis, determine the emotional tone conveyed by the video (such as joy, sadness, tension, warmth, etc.) and the emotional change curve (emotional ups and downs, turning points and trends); identify popular cultural memes in the video (such as Internet buzzwords, popular film and television animation elements, social hot topics, etc.) and unique visual elements (such as special color matching, unique picture composition, iconic visual symbols, etc.); summarize the theme content of the video (such as story theme, propaganda theme, core events, etc.), sort out the plot development context (the plot's beginnings, developments, key plot nodes, story development rhythm, etc.), and clarify character characteristics (character personality, character relationships, the character's role in the story, etc.). Next, you can integrate product information for the target products involved, clarifying their core selling points (e.g., app downloads, e-commerce merchandise), including their unique advantages, user pain points they address, and differentiation from competing products; their target users (e.g., age range, interests, and other characteristics); their desired actions (e.g., downloading the app, following the brand); and common video characteristics (e.g., common styles, techniques, and elements used in successful videos). Finally, based on the target product information and video analysis results, you can determine the thematic direction of the creative framework and plan its overall structure. This includes how to attract viewers' attention at the beginning (e.g., by raising fitness questions relevant to the target users and demonstrating fitness achievement comparisons); how to showcase the product's advantages and user experience in the middle (e.g., using user scenarios to illustrate the process of developing and executing a personalized plan); how to guide user action at the end (e.g., offering incentives for app downloads and showcasing user testimonials); and how to set the emotional tone (e.g., creating a vibrant and positive atmosphere to inspire a healthy lifestyle).

[0084] Step 508: Acquire script framework information based on the multi-dimensional features.

[0085] According to the above method, the multi-dimensional characteristics of the target associated video can be obtained according to the multi-form information of the target associated video, and the multi-form information can include text information, audio information and image information, and the multi-dimensional characteristics can include but are not limited to product characteristics, video framework characteristics and emotional expression characteristics, etc. Furthermore, the multi-dimensional characteristic information of the multi-dimensional characteristics can be input into the large language model as input information, and the large language model can obtain script framework information according to the multi-dimensional characteristic information of the multi-dimensional characteristics under the guidance of the pre-set prompt word, and the script framework information can be used to describe the video framework of the to-be-generated video script.

[0086] In the method of the embodiment, the associated video script of the to-be-generated video script can be screened out from the plurality of video sources, and then the script framework information of the to-be-generated video script can be generated according to the associated video script in combination with the large language model, so as to facilitate subsequent determination of the script structure of the to-be-generated video script, and improve the efficiency and accuracy of video script generation.

[0087] In one exemplary embodiment, as shown in Figure 6 Step 504 can include steps 602 to 606. Wherein:

[0088] Step 602: According to the associated script keywords, a plurality of candidate associated videos are obtained from the associated video data source.

[0089] The associated script keywords can be used to represent the video direction and video theme of the to-be-generated video script, and according to the associated script keywords, a plurality of candidate associated videos associated with the video direction and video theme of the to-be-generated video script can be screened out from the associated video data source.

[0090] Step 604: According to the script requirement description information, script requirement characteristics are obtained.

[0091] Step 606: According to the script requirement characteristics, a target associated video is screened out from the plurality of candidate associated videos.

[0092] According to the script requirement characteristics and the script characteristics of the associated video script of each candidate associated video in the plurality of candidate associated videos, the similarity between each candidate associated video and the to-be-generated video script can be obtained, and the candidate associated video with a similarity greater than a pre-set similarity threshold is determined as the target associated video of the to-be-generated video script. In one possible implementation, the candidate associated video with the greatest similarity can be determined as the target associated video of the to-be-generated video script.

[0093] In one exemplary embodiment, as shown in Figure 7 Before step 108, steps 702 to 706 can be included. Wherein:

[0094] Step 702, determining initial data format information of the initial video script.

[0095] Step 704, determining target data format information of the target video script.

[0096] Step 706, generating a second prompt word according to the initial data format information and the target data format information.

[0097] The second prompt word is used to guide the large language model to adjust the script data format of the initial video script. The script data format can include a script logical order and a data structure, and the script data format of the to-be-generated video script can be set in the second prompt word in advance. The initial data format information can represent the script logical order and the data structure of the initial video script, and the data structure of the initial video script can be unstructured data. The target data format information can represent the script logical order and the data structure of the target video script, and the data structure of the target video script can be structured data.

[0098] In the method of the embodiment, the initial video script can be optimized by using the large language model to obtain the target video script, and the accuracy of video script generation can be further improved.

[0099] It should be understood that, although each step in the flowchart involved in each of the above-described embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each of the above-described embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0100] Based on the same inventive concept, the embodiments of the present application also provide a video script generation device for implementing the above-mentioned video script generation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more video script generation device embodiments provided below can refer to the limitations of the video script generation method described above, which will not be repeated here.

[0101] In one embodiment, as Figure 8As shown, a video script generation apparatus is provided, comprising: an information acquisition module 802, a framework acquisition module 804, a first script generation module 806, and a second script generation module 808, wherein:

[0102] The information acquisition module 802 is configured to acquire script requirement description information.

[0103] The framework acquisition module 804 is configured to acquire script framework information according to the script requirement description information.

[0104] The first script generation module 806 is configured to utilize a large language model and a first prompt word, based on a pre-constructed video script knowledge base and the script framework information, to segment multiple script segments, and according to the multiple script segments, to generate an initial video script; the first prompt word comprises a script segment prompt word for each of the multiple script segments.

[0105] The second script generation module 808 is configured to utilize the large language model and a second prompt word, based on the initial video script, to generate a target video script; the second prompt word is used to guide the large language model to adjust the script data format of the initial video script.

[0106] In one embodiment, the first script generation module 806 is further configured to: acquire multiple historical video scripts in a historical time period corresponding to a current time period; acquire multiple script elements according to historical video script information of each of the multiple historical video scripts; acquire element attribute information of each of the script elements, and acquire element relationships between the script elements according to the element attribute information; and construct the video script knowledge base according to the multiple script elements and the element relationships between the script elements.

[0107] In one embodiment, the first script generation module 806 is further configured to: determine a script structure according to the script framework information; filter out matching video scripts matching the script framework information from multiple historical video scripts according to the script framework information and multiple script elements of each of the multiple historical video scripts and element relationships between the script elements; and utilize the large language model and the first prompt word to segment and generate the multiple script segments according to the script structure and the matching video scripts.

[0108] In an embodiment, the first script generation module 806 is further configured to: obtain similarity between the script framework information and each of the historical video scripts in the video script knowledge base according to the script framework information and the script elements and the element relationships between the script elements of each of the historical video scripts in the video script knowledge base; and determine the historical video scripts with similarity greater than a preset similarity threshold as the matching video scripts.

[0109] In an embodiment, the framework obtaining module 804 is further configured to: obtain associated script keywords according to the script requirement description information; obtain a target associated video from an associated video data source according to the associated script keywords; obtain multi-dimensional features of the target associated video according to video information of the target associated video; the video information includes at least two of text information, audio information and video image information of the target associated video; the multi-dimensional features at least include emotional expression features; and obtain the script framework information according to the multi-dimensional features.

[0110] In an embodiment, the framework obtaining module 804 is further configured to: obtain a plurality of candidate associated videos from the associated video data source according to the associated script keywords; obtain script requirement features according to the script requirement description information; and select the target associated video from the plurality of candidate associated videos according to the script requirement features.

[0111] In an embodiment, the second script generation module 808 is further configured to: determine initial data format information of the initial video script; determine target data format information of the target video script; and generate the second prompt word according to the initial data format information and the target data format information.

[0112] The above-mentioned modules in the video script generation apparatus can be all or partially implemented by software, hardware and combinations thereof. The above-mentioned modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to the above-mentioned modules.

[0113] In an embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in FIG. 8. Figure 9As shown in the figure. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video script generation related data. The network interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a video script generation method.

[0114] Those skilled in the art can understand that, Figure 9 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0115] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the method embodiments.

[0116] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments.

[0117] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments.

[0118] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0120] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0121] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A video script generation method, characterized in that: The method comprises: Get script requirement description information; Obtaining script framework information according to the script requirement description information; Acquire multiple historical video scripts within a historical time period corresponding to a current time period; acquire multiple script elements based on historical video script information of each of the multiple historical video scripts; acquire element attribute information of each of the script elements, and acquire element relationships between the script elements based on the element attribute information; construct a video script knowledge base based on the multiple script elements and the element relationships between the script elements; Determine the script structure based on the script framework information; select a matching video script that matches the script framework information from the multiple historical video scripts based on the script framework information and multiple script elements of each of the multiple historical video scripts contained in the video script knowledge base and the element relationship between the script elements; utilize a large language model and a first prompt word to segmentally generate multiple script segments based on the script structure and the matching video script, and generate an initial video script based on the multiple script segments; the first prompt word includes a script segment prompt word for each of the multiple script segments; The target video script is generated based on the initial video script using the large language model and the second prompt word; the second prompt word is used to guide the large language model to adjust the script data format of the initial video script.

2. The method according to claim 1, characterized in that The method further comprises screening out a matching video script that matches the script framework information from the plurality of historical video scripts based on the script framework information and the plurality of script elements of each of the plurality of historical video scripts contained in the video script knowledge base and the element relationships between the script elements, including: Obtaining a similarity between the script framework information and each of the plurality of historical video scripts according to the script framework information and the plurality of script elements of each of the plurality of historical video scripts contained in the video script knowledge base and the element relationships between the script elements; The historical video scripts whose similarity is greater than a preset similarity threshold are determined as the matching video scripts.

3. The method according to claim 1, characterized in that The step of obtaining script framework information according to the script requirement description information includes: According to the script requirement description information, obtain related script keywords; According to the associated script keywords, obtaining a target associated video from an associated video data source; Acquire multidimensional features of the target-associated video based on video information of the target-associated video; the video information includes at least two types of text information, audio information, and video image information of the target-associated video; and the multidimensional features include at least an emotional expression feature; The script framework information is obtained according to the multi-dimensional features.

4. The method according to claim 3, characterized in that The step of obtaining a target associated video from an associated video data source according to the associated script keyword includes: According to the associated script keywords, a plurality of candidate associated videos are obtained from an associated video data source; Obtaining script requirement characteristics according to the script requirement description information; According to the script requirement characteristics, the target associated video is screened out from the plurality of candidate associated videos.

5. The method according to any one of claims 1 to 4, characterized in that Before generating a target video script based on the initial video script using the large language model and the second prompt word, the method further includes: Determining initial data format information of the initial video script; Determining target data format information of the target video script; The second prompt word is generated according to the initial data format information and the target data format information.

6. A video script generating device, characterized in that: The device comprises: Information acquisition module, used to obtain script requirement description information; A framework acquisition module is used to acquire script framework information according to the script requirement description information; A first script generation module is configured to determine a script structure based on the script framework information; screen out a matching video script that matches the script framework information from the plurality of historical video scripts based on the script framework information and a plurality of script elements of each of the plurality of historical video scripts contained in a video script knowledge base and the element relationships between the script elements; generate a plurality of script segments based on the script structure and the matching video script using a large language model and a first prompt word, and generate an initial video script based on the plurality of script segments; the first prompt word includes a script segment prompt word for each of the plurality of script segments; A second script generation module is configured to generate a target video script based on the initial video script using the large language model and a second prompt word; the second prompt word is configured to guide the large language model to adjust the script data format of the initial video script; The first script generation module is also used to obtain multiple historical video scripts within the historical time period corresponding to the current time period; obtain multiple script elements based on the historical video script information of each of the multiple historical video scripts; obtain element attribute information of each of the script elements, and obtain element relationships between each of the script elements based on the element attribute information; and construct the video script knowledge base based on the multiple script elements and the element relationships between each of the script elements.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images