Video script generation method, computing device, computer storage medium and computer program product
Generating video scripts through artificial intelligence large-scale models solves the problems of low efficiency in video script generation and difficulty in meeting specific needs in the existing technology, and realizes automated and accurate video script generation, which improves the effect of promoting videos.
Patent Information
- Application Number
- CN202411253366.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-19
AI Technical Summary
In the prior art, the generation of video scripts requires professional screenwriters to spend a lot of time and energy. It is difficult for non-professionals to obtain video scripts that meet their own needs, and ready-made scripts are difficult to fully meet specific needs, and require a lot of modifications.
The artificial intelligence model is used to automatically generate video scripts based on the description information and script structure of the target object, including oral copywriting and storyboard description information, and a complete script is formed through the storyboard, responding to the client's video script generation instructions.
It improves the efficiency and accuracy of video script generation, so that the generated script meets the promotion needs of the target object, and reduces the workload and number of modifications of the screenwriter.
Smart Images

Figure CN118984413A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of video processing technology, and in particular to a video script generation method, a computing device, a computer storage medium, and a computer program product. Background Art
[0002] In today's era of booming digital marketing, promotional videos have become an important means for companies and individuals to showcase their products and services. Promotional videos often need to be produced based on video scripts.
[0003] The video script is the blueprint for the creation of the entire promotional video, which determines the narrative logic, picture presentation and emotional communication of the video. In the process of realizing the conception of this application, the inventor found that in the relevant technology, professional screenwriters usually need to spend a lot of time and energy to conceive and create to complete the video script. For screenwriters, it is necessary to fully understand the characteristics, needs and expected effects of the target object, and then gradually build the framework and content of the script. For some non-professionals, it is even more difficult to obtain a suitable video script. Usually, they need to search the Internet or buy ready-made scripts, but these scripts are often difficult to fully meet their specific needs, and they still need a lot of modifications and adjustments. Summary of the invention
[0004] Embodiments of the present application provide a video script generation method, computing device, computer storage medium, and computer program product.
[0005] In a first aspect, an embodiment of the present application provides a method for generating a video script, which is applied to a server, and the method includes:
[0006] In response to the video script generation instruction for the target object sent by the client, determine the object description information and the video script type of the target object;
[0007] Determine a target script structure corresponding to the video script type; the target script structure includes a plurality of storyboards;
[0008] Generate the script content of each storyboard based on the object description information and the target script structure using the artificial intelligence big model; the script content includes the spoken copy and the storyboard description information; the storyboard description information is used to describe the screen content of the storyboard;
[0009] The script contents corresponding to the multiple storyboards respectively constitute a video script according to the target script structure.
[0010] In a second aspect, an embodiment of the present application provides a video script generation device, comprising:
[0011] An instruction response module, used to respond to a video script generation instruction for a target object sent by a client, and determine object description information and a video script type of the target object;
[0012] A structure determination module, used to determine a target script structure corresponding to the video script type; the target script structure includes a plurality of storyboards;
[0013] A content generation module, used to generate the script content of each storyboard based on the object description information and the target script structure by using the artificial intelligence big model; the script content includes the oral copy and the storyboard description information; the storyboard description information is used to describe the screen content of the storyboard;
[0014] The script generation module is used to construct a video script according to the target script structure using the script contents corresponding to the multiple storyboards.
[0015] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component;
[0016] The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the video script generation method provided in the embodiment of the present application.
[0017] In a fourth aspect, a computer-readable storage medium is provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processing component, the video script generation method provided in an embodiment of the present application is implemented.
[0018] In a fifth aspect, a computer program product is provided in an embodiment of the present application, including a computer program / instruction, which, when executed by a processing component, implements the video script generation method provided in an embodiment of the present application.
[0019] The embodiment of the present application provides a method for generating a video script, by adopting the following methods: responding to a video script generation instruction for a target object sent by a client, determining the object description information and the video script type of the target object; determining a target script structure corresponding to the video script type; the target script structure comprising a plurality of storyboards; utilizing an artificial intelligence big model to generate script content for each storyboard based on the object description information and the target script structure; the script content comprising spoken text and storyboard description information; the storyboard description information being used to describe the screen content of the storyboard; and a technical solution of forming a video script from the script contents corresponding to the plurality of storyboards according to the target script structure. The method can respond to a video script generation instruction, automatically generate a video script based on the description information of the target object, and on the basis of providing the generation efficiency of the video script, can also make the script meet the promotion needs of the target object.
[0020] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0022] Figure 1 A system architecture diagram provided by an embodiment of the present application is shown;
[0023] Figure 2 A flowchart of a method for generating a video script provided by an embodiment of the present application is shown;
[0024] Figure 3 A schematic diagram schematically illustrates a video script provided by an embodiment of the present application;
[0025] Figure 4 A framework diagram of a video script generation method provided by the present application is shown;
[0026] Figure 5 A block diagram of a video script generating device provided by an embodiment of the present application is shown;
[0027] Figure 6 A block diagram of a computing device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION
[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.
[0029] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.
[0030] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).
[0031] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0032] It should be noted that the technical solution of the embodiment of the present application is applicable to a network virtual environment. The users described generally refer to "virtual users". Real users can register user accounts in the server through registration to obtain user identities in the network environment. In the embodiment of the present application, the same user account can be used to log in to the server through different types of clients, so that the server can identify the same user. Of course, different user accounts can also be used to log in to the server through different types of clients. The server stores binding relationships between different user accounts, so that different user accounts with binding relationships can be considered to be the same user.
[0033] In today's era of booming digital marketing, promotional videos have become an important means for companies and individuals to showcase their products and services. Promotional videos often need to be produced based on video scripts.
[0034] The video script is the blueprint for the creation of the entire promotional video, which determines the narrative logic, picture presentation and emotional communication of the video. In the process of realizing the conception of this application, the inventor found that in the relevant technology, professional screenwriters usually need to spend a lot of time and energy to conceive and create to complete the video script. For screenwriters, it is necessary to fully understand the characteristics, needs and expected effects of the target object, and then gradually build the framework and content of the script. For some non-professionals, it is even more difficult to obtain a suitable video script. Usually, they need to search the Internet or buy ready-made scripts, but these scripts are often difficult to fully meet their specific needs, and they still need a lot of modifications and adjustments.
[0035] In order to solve the technical problems existing in the related technology, the embodiment of the present application provides a video script generation method, by adopting: responding to the video script generation instruction for the target object sent by the client, determining the object description information and the video script type of the target object; determining the target script structure corresponding to the video script type; the target script structure includes multiple storyboards; using an artificial intelligence big model based on the object description information and the target script structure, generating the script content of each storyboard; the script content includes oral copy and storyboard description information; the storyboard description information is used to describe the picture content of the storyboard; the technical solution of forming a video script by the script contents corresponding to multiple storyboards according to the target script structure can respond to the video script generation instruction, automatically generate a video script based on the description information of the target object, and on the basis of providing the generation efficiency of the video script, can also make the script meet the promotion needs of the target object.
[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0037] Figure 1 A system architecture diagram of a technical solution of an embodiment of the present application that can be applied to extraction is shown, and the system architecture may include a user terminal 101 and a server terminal 102. (Or: it may include a server terminal and multiple user terminals; or it may include a server terminal, a first user terminal and a second user terminal, etc.)
[0038] Among them, a connection is established between the user terminal 101 and the server terminal 102 through a network. The network provides a medium for the communication link between the user terminal 101 and the server terminal 102. The network may include various connection types, such as wired, wireless communication links or optical fiber cables, etc. Optionally, the server can be connected to the user terminal through a mobile network. Accordingly, the network standard of the mobile network can be any one of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), 5G, WiMax, etc. Optionally, the user terminal can also establish a communication connection with the server through Bluetooth, WiFi, infrared, etc.
[0039] The client 101 can interact with the server 102 through the network to receive or send messages, etc.
[0040] Among them, the user terminal 101 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, Hypertext Markup Language Version 5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The user terminal 101 can be deployed in an electronic device and needs to rely on the device to run or some apps in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc. For ease of understanding, Figure 1 The user end is mainly represented by a device image. Various other types of applications can usually be configured in electronic devices, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. Electronic devices can refer to devices used by users, which have the functions of computing, surfing the Internet, communicating, etc. required by users, such as mobile phones, tablet computers, personal computers, wearable devices, etc. Electronic devices can usually include at least one processing component and at least one storage component. Electronic devices may also include basic configurations such as network card chips, IO buses, audio and video components, which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices may also be included, such as keyboards, mice, input pens, printers, etc., which are not limited in this application.
[0041] The server 102 may include servers that provide various services, such as a server for background training that provides support for the model used on the user terminal 101, or a server that processes interactive information sent by the user terminal.
[0042] It should be noted that the server 102 can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.
[0043] It should be noted that the video script generation method provided in the embodiment of the present application is generally executed by the server 102, and the corresponding video script generation device is generally set in the server 102. However, in other embodiments of the present application, the user end 101 can also have similar functions as the server 102, so as to execute the video script generation method provided in the embodiment of the present application. In other embodiments, the video script generation method provided in the embodiment of the present application can also be jointly executed by the user end 101 and the server 102.
[0044] It should be understood that Figure 1 The number of the user terminals and the server terminals in the figure is only for illustration. Any number of the user terminals and the server terminals may be provided according to the implementation requirements.
[0045] The implementation details of the technical solution of the embodiment of the present application are elaborated in detail below.
[0046] Figure 2 A flowchart of a video script generation method provided by an embodiment of the present application is shown. The video script generation method can be applied to a server, such as Figure 2 As shown, the video script generation method may specifically include the following steps:
[0047] 201, responding to the video script generation instruction for the target object sent by the client, and determining the object description information and the video script type of the target object;
[0048] 202, determining a target script structure corresponding to the video script type; the target script structure includes a plurality of storyboards;
[0049] 203, using the artificial intelligence big model based on the object description information and the target script structure, generating the script content of each storyboard; the script content includes the spoken copy and the storyboard description information; the storyboard description information is used to describe the screen content of the storyboard;
[0050] 204, the script contents corresponding to the plurality of storyboards are used to form a video script according to the target script structure.
[0051] The target object may include a commodity, and the video script generated by the video script generation instruction may be used to introduce and promote the commodity represented by the target object. The above-mentioned commodity may include tangible products or intangible services; tangible products may refer to commodities that can be touched and physically owned, such as electronic products, clothing or daily necessities; intangible services may include services provided by merchants, such as nanny services, cleaning services, maintenance services or any products and services that do not have a physical form.
[0052] The object description information may include the name, characteristics, purpose, advantages, etc. of the target object, and may serve as the basis for the video content. For example, the following is the object description information for a cleaning service: "Professional home cleaning service, covering whole house cleaning, including kitchens, bathrooms, bedrooms and other areas, meticulous service, and the use of environmentally friendly cleaning agents." Through the object description information, the name of the target object may be introduced, such as "home cleaning service", where the service content of "home cleaning service" includes "whole house cleaning, including kitchens, bathrooms, bedrooms and other areas", and the service advantages and characteristics are "meticulous service, the use of environmentally friendly cleaning agents".
[0053] The video script can be used to guide the elements and links in the video generation process, and different types of video scripts can be used to generate different types of promotional videos. The video script can include multiple storyboards, each of which can be used to guide the generation of a video segment of the promotional video, and the video segment can be a link in the process of generating the promotional video.
[0054] After receiving the video script generation instruction, the video script type can be determined based on the target object, promotion purpose, etc.; alternatively, the user can specify the desired video script type in the video generation instruction.
[0055] Video script types may include, for example, narrative type, explanatory type, etc., wherein each video script type corresponds to a different script structure.
[0056] After determining the type of video script, you can determine the script structure corresponding to the type of video script. The script structure can refer to the number of storyboards, and each storyboard can be used to display specific content. Take the three-part script structure as an example. This structure divides the video content into three main parts or storyboards. First, storyboard 1 can focus on emotional marketing, with the goal of establishing a connection with the audience through emotional resonance, stimulating the audience's interest and emotional response; storyboard 2 is dedicated to service introduction, where the characteristics and advantages of the service provided can be introduced in detail to ensure that the audience has a clear understanding of the service itself. Finally, storyboard 3 shows the applicable population of the service and shares the feedback and evaluation of the experiencers, which helps the audience understand the actual application effect of the service and enhances the sense of trust.
[0057] Through this structured approach, the video script can be developed in an orderly manner, with each storyboard designed for specific goals and content, thus forming a coherent and persuasive video narrative. This clear script structure not only helps guide video shooting and production, but also helps ensure that the final video content can effectively convey information, attract target audiences, and achieve established marketing goals.
[0058] Among them, the spoken copy may include the narration or dialogue text in the current storyboard, and the storyboard description information may be used to illustrate the visual content of each storyboard, for example, it may include scene layout, character actions, camera angles, lens movement, etc.
[0059] The artificial intelligence large model can understand the overall framework of the video and the order of each storyboard based on the script structure, and understand the basis of the script content based on the object description information of the target object, so that the script content of each storyboard can be intelligently generated.
[0060] The storyboard description information can ensure that the generated promotional video images can accurately convey the intended information and emotions, and can also maintain consistency with the spoken copy.
[0061] After using the artificial intelligence big model to generate the script content for each storyboard, the script content can be filled into the corresponding storyboard of the target script structure to generate a video script.
[0062] In some embodiments, using the artificial intelligence big model based on the object description information and the target script structure to generate the script content of each storyboard can be specifically implemented as follows:
[0063] Generate the spoken copy for each storyboard based on the object description information and the target script structure using the artificial intelligence big model;
[0064] The artificial intelligence model is used to generate storyboard description information for each storyboard based on the spoken text of each storyboard.
[0065] Among them, the artificial intelligence large model can integrate the object description information into the script based on the provided object description information and the target script structure, through understanding the object description information, and generate spoken text for each storyboard that conforms to the script structure and the target object.
[0066] The artificial intelligence big model can generate storyboard description information for describing the visual content corresponding to the spoken text by understanding the spoken text, so that the visual effects presented in the generated promotional video match the spoken content.
[0067] In some embodiments, the generation of the spoken copy for each storyboard based on the object description information and the target script structure using the artificial intelligence big model can be specifically implemented as follows:
[0068] Obtain the target script template and target script requirements corresponding to the target script structure;
[0069] Generate a first prompt word according to the first prompt template by using the object description information, the target script template and the target script requirements;
[0070] The first prompt word is input into the artificial intelligence big model, so as to utilize the artificial intelligence big model to generate the spoken text for each storyboard based on the object description information, refer to the target script template and follow the script requirements.
[0071] The target script template may refer to a script pre-generated under the target script structure, which includes the same number of storyboards as the target script structure, and each storyboard includes corresponding script content. For example, the target script template may be generated by reverse parsing other popular promotional videos that have been generated. Thus, by generating script content according to the target script template generated by reverse parsing other popular promotional videos, its script structure, script style, etc. may be imitated, thereby improving the maturity and popularity of the generated script content.
[0072] The target script requirements may be used to indicate the length, style, target audience, content requirements, format requirements, etc. of the script that is expected to be generated based on the target script structure.
[0073] The first prompt template can be a predefined framework or structure for guiding and standardizing the content input into the artificial intelligence model. In an embodiment of the present application, the first prompt template can include elements such as script structure, target audience, copy length, format requirements, language and tone, and specific requirements.
[0074] The first prompt word can be generated by filling the object description letter, the target script template and the target script requirements into the corresponding elements of the first prompt template.
[0075] By inputting the first prompt word into the artificial intelligence big model, the artificial intelligence big model can generate the spoken text for each storyboard based on the object description information, refer to the target script template and follow the script requirements.
[0076] The following may be a possible implementation of a first prompt word provided in an embodiment of the present application. It should be noted that the first prompt word is only an example.
[0077] #Setting a Purpose#
[0078] 1. I want to make a short video content of "product and service promotion.
[0079] 2. Please generate the narration material for this promotional short video by analyzing and extracting the core content of #post information#.
[0080] #Script structure#
[0081] Generate narration corpus according to the following structure:
[0082] Part 1: Based on the characteristics of your product or service and the industry classification information, create a fictional experience from a first-person perspective (close to the experiences of ordinary people and ordinary companies) to trigger everyone's emotional resonance.
[0083] Part 2: From a third-person perspective, recommend this product or service to your friends and talk about what kind of people this product or service is suitable for.
[0084] Part 3: From a third-person perspective, talk about the impact this product has on your daily life and work.
[0085] #Content Requirements#
[0086] 1. The number of words in the generated narration is within 240 words;
[0087] 2. Part 1 should not exceed 60 words;
[0088] 3. Part 2 should not exceed 140 words;
[0089] 4. Part 3 should not exceed 40 words;
[0090] 5. Descriptions such as "our products", "our services", "contact us", etc. are prohibited.
[0091] #Format requirements#
[0092] 1. Please use "part1:", "part2:", "part3:" to distinguish each paragraph. The text must be divided into 3 paragraphs, with the second paragraph being the longest.
[0093] 2. Each paragraph must not be empty.
[0094] #Sample copy#
[0095] Oh, my pile of shoes is a disaster! A pile of dirty shoes is a headache. I really don't want to wash them by myself, it feels too difficult!
[0096] So, I suddenly had an idea and decided to hand over these troublesome things to a shoe cleaning company. Do you know that a shoe cleaning company is an "old shoe doctor" with many years of experience, specializing in cleaning all kinds of shoes and is well-known.
[0097] I heard that they use advanced equipment and environmentally friendly materials, and the door-to-door pickup and delivery service is also convenient and efficient. It's great to think that my shoes will be brand new under their "magic hands". Moreover, if you have any questions during the cleaning process, there are specialists to answer them immediately!
[0098] What makes me even more excited is that XXXX shoe cleaning also offers low prices and guaranteed quality. When I think of the limited-time discounts and generous gifts waiting for me, I feel that this choice is simply a "treasure"!
[0099] Letting my shoes be washed by XYZ makes me feel confident in every step. Choosing XYZ to wash my shoes makes my life easier and more comfortable!
[0100] In the above-mentioned first prompt word, #sample copy# can be the target script template, #content requirements# and #format requirements# can be the target script requirements, and #post information# can be the object description information (the specific content of the post information is not provided in the above-mentioned first prompt word).
[0101] In some embodiments, the video script generation method may further include:
[0102] Get the target video;
[0103] Analyze the target video to obtain multiple storyboard videos and the spoken texts corresponding to the multiple storyboard videos;
[0104] Generate storyboard description information and text description information of each storyboard video based on multiple storyboard videos and the corresponding oral texts of the storyboard videos by using the artificial intelligence big model; wherein the storyboard description information is used to describe the screen content of the storyboard video; and the text description information is used to describe the text type of the storyboard video;
[0105] Generate a script template according to the script structure composed of multiple storyboard videos and the storyboard description information and copy description information of each storyboard video;
[0106] Save the script template;
[0107] In some embodiments, obtaining the target script template and target script requirements corresponding to the target script structure may be specifically implemented as follows:
[0108] From the saved script templates, search for the target script template corresponding to the target script structure;
[0109] Get the target script requirements corresponding to the target script structure.
[0110] The user may provide the target video through the client, but is not limited thereto. The user may also provide an access link to the target video through the client, so that the server obtains the target video based on the access link. In addition, the target video may not be provided by the client, but may be actively obtained by the server. For example, the server may obtain the target video from the Internet using crawler technology. The target video may include, for example, a video that is used to display content related to the target object and has a high popularity, i.e., a relatively popular video.
[0111] By reverse parsing the target video, the video script of the target video can be obtained, and a promotional video with a style and structure similar to the target video can be generated based on the video script.
[0112] After parsing the target video and obtaining the spoken copy of the target video, the artificial intelligence model can be used to generate the storyboard description information and copy description information corresponding to each storyboard. Then, based on the script structure composed of multiple storyboard videos and the storyboard description information and copy description information of each storyboard video, a script template can be generated.
[0113] Among them, the copy description information can be used to describe the copy type of the storyboard video. In one embodiment of the present application, as in the example of the first prompt word above, "Part 1: Based on the product service characteristics and the industry classification information, a fictional experience (close to the experience of ordinary people and ordinary companies) is created from the first person perspective to trigger everyone's emotional resonance", "Part 2: From the third person perspective, promote this product service to friends and talk about what kind of people this product service is suitable for", "Part 3: From the third person perspective, talk about the impact of this product on daily life and work" can respectively represent a type of copy description information.
[0114] In some embodiments, parsing the target video to obtain multiple storyboard videos may be specifically implemented as follows:
[0115] The target video is segmented according to content similarity to obtain multiple storyboard videos.
[0116] In some embodiments, segmenting the target video according to content similarity to obtain multiple storyboard videos may be specifically implemented as follows:
[0117] Segment the target video according to content similarity to obtain multiple segmented videos;
[0118] At least one segmented video whose content similarity meets a preset condition is merged in sequence to generate a plurality of storyboard videos.
[0119] The target video may be a video associated with the target object, shot by the user, generated by specific software, or downloaded from the Internet. The target video may be long, and may display multiple different themes. Therefore, in order to increase the number and richness of material videos when generating promotional videos, the target video provided by the user may be split. By splitting the target video, a longer target video can be divided into multiple shorter material videos according to different themes or contents.
[0120] The server can determine the splitting position of the target video by identifying key frames, scene changes or other important content points in the target video, and split the target video at each splitting position to obtain multiple segmented videos.
[0121] In some embodiments, segmenting the target video according to content similarity to obtain multiple storyboard videos may be specifically implemented as follows:
[0122] Perform frame extraction on the target video to obtain multiple video frames;
[0123] Use a large AI model to convert multiple video frames into video features;
[0124] The content similarity between video frames is calculated based on video features, and video frames whose content similarity meets preset conditions are merged into a storyboard video.
[0125] In a possible implementation, the server can perform frame extraction processing on the target video to extract a series of separate video frames from the target video. The server can perform similarity calculation between consecutive video frames, and calculate the similarity between consecutive video frames by comparing the visual content between consecutive frames, such as color, texture, shape, and motion features. The similarity calculation can be calculated, for example, by pixel comparison, feature vector matching, or the output of a deep learning model. Based on the calculated similarity results, the server can determine the splitting points of the target video, i.e., key frames. The splitting points can be located at positions where the similarity drops significantly, which can indicate that the video content is changing or switching to a new scene. Thus, the server can split the target video into multiple segmented videos on these key frames, and each segmented video can contain a series of visually similar continuous frames, so that the consistency of the content of each segmented video can be guaranteed. In addition, when performing segmentation processing, the server can also consider the contextual information and semantic information of the video to improve the accuracy and relevance of the segmentation; for example, if the dialogue or narrative in the video logically belongs to the same subject, it may not be split into different segments even if there are slight visual changes.
[0126] In some embodiments, the video script generation method may further include:
[0127] The video script is published to the object providing system of the target object or the video script and / or the download address of the video script is sent to the client so that the client can save the video script.
[0128] In some embodiments, the video script generation method may further include:
[0129] Send the video script to the client;
[0130] Receive a video generation instruction generated by the client based on the video script;
[0131] In response to the video generation instruction, convert the spoken text corresponding to each storyboard into spoken audio;
[0132] Searching for a target material video that matches the storyboard description information of each storyboard and the target object from the material library;
[0133] The spoken audio of each storyboard is combined with the corresponding target material video into a target storyboard video;
[0134] According to the target script structure, target storyboard videos corresponding to multiple storyboards are synthesized to obtain a promotional video for the target object.
[0135] After the spoken copy is generated, the spoken copy of each storyboard can be converted into spoken audio using text-to-speech conversion technology. Next, according to the storyboard description information of the storyboard and the screen content described in the storyboard description information, the material content that matches the screen content described in the storyboard description information and matches the target object can be searched from the material library. Among them, matching the target object can refer to the material content that matches the product corresponding to the target object.
[0136] By searching for source videos based on the storyboard description information and the target object, it is possible to ensure that the visual content of the generated promotional video matches the target object and the usage scenario of the target object.
[0137] For the material video and spoken audio corresponding to each storyboard, the corresponding material video and spoken audio can be synthesized and synchronized to generate a target storyboard video.
[0138] Then, according to the script structure, multiple target storyboard videos can be synthesized in an orderly manner to generate a promotional video for the target object.
[0139] In an embodiment of the present application, by adopting a video generation instruction for a target object sent by a response client, the object description information and the video script type of the target object are determined; the script structure corresponding to the video script type is determined; the script structure includes multiple storyboards; the script content of each storyboard is generated based on the object description information and the script structure using an artificial intelligence big model; the script content includes spoken copy and storyboard description information; the storyboard description information is used to describe the picture content of the storyboard; the spoken copy corresponding to each storyboard is converted into spoken audio; the material video that matches the storyboard description information of each storyboard and the target object is searched from the material library; the spoken audio of each storyboard is synthesized with the corresponding material video into a storyboard video; according to the script structure, the storyboard videos of multiple storyboards are synthesized to obtain a technical solution for a promotional video for the target object, which can automatically generate a promotional video based on the object description information of the target object and according to the video script type, and the spoken copy and video material used in the promotional video are matched with the target object and the object description information, thereby improving the accuracy of the promotional video content while improving the generation efficiency of the promotional video.
[0140] In some embodiments, the video script generation method may further include:
[0141] Based on the spoken audio of each storyboard, a digital human image of the digital human broadcasting the spoken audio is generated.
[0142] Among them, Digital Human or Virtual Human can be a computer-generated character with human-like appearance, behavior and communication ability. Digital Human can be two-dimensional or three-dimensional and can be created through computer graphics (CGI) and artificial intelligence technology.
[0143] The digital human screen can be used to display the facial movements of the digital human that match the spoken audio, such as facial expressions and lip movements.
[0144] In some embodiments, synthesizing the spoken audio of each storyboard with the corresponding target material video into a target storyboard video may be specifically implemented as follows:
[0145] Combine the spoken audio of each storyboard with the digital human image to form a digital human video;
[0146] In the case that a target material video exists in any storyboard, the digital human video and the target material video are combined into a target storyboard video;
[0147] When there is no target material video for any storyboard, the digital human video is used as the target storyboard video.
[0148] After synthesizing the spoken audio and the digital human image into a digital human video, the digital human can broadcast the spoken audio according to facial movements that match the spoken audio and use corresponding timbre, intonation and emotional expression, so that the visual and auditory elements of the digital human video are coordinated.
[0149] When there is a target material video in any storyboard, the digital human video can be added to the layer above the target material video layer, so that the digital human image is integrated into the target material video, and the target material video is used as the background for the digital human image to perform voice broadcasting, thereby improving the display effect.
[0150] In the case that there is no target material video in any storyboard, the digital human video can be used independently as the video content of the storyboard. In this case, appropriate background elements can be added to the digital human video to ensure the richness and visual appeal of the picture.
[0151] In some embodiments, the video script generation method may further include:
[0152] Sending digital human selection prompt information of multiple digital humans to the client;
[0153] According to the digital human selection request sent by the client, the target digital human selected by the user is determined.
[0154] The digital human selection prompt information may include a brief introduction, characteristics, appearance, etc. of each digital human among the multiple digital humans. After the client receives the digital human selection prompt information, the user may send a digital human selection request through the client according to preferences or specific purposes. The digital human selection request may include identification information of the digital human selected by the user.
[0155] In response to the digital human selection request, the server can determine the target digital human selected by the user based on the information in the digital human selection request.
[0156] In some embodiments, based on the spoken audio of each storyboard, generating a digital human screen in which the digital human broadcasts the spoken audio may be specifically implemented as follows:
[0157] Generate the lip shape features of the target digital human based on the spoken audio;
[0158] The lip shape features are synthesized into the digital human model corresponding to the target digital human to generate a digital human image.
[0159] The server can analyze the spoken audio to determine the rhythm, intonation, and pronunciation of the speech, thereby generating lip features synchronized with the audio. Lip features may include, for example, the opening and closing of the lips, the position of the tongue, and possible accompanying facial expressions.
[0160] In a possible implementation of the present application, speech recognition and analysis technology can be used to decompose the audio signal of the oral audio into individual factors and syllables. Then, an artificial intelligence model can be used to map the decomposed factors and syllables to specific lip movements. Among them, the artificial intelligence model can, for example, be based on a machine learning algorithm and have the ability to identify the lip shape, tongue position and facial expression corresponding to different factors. After the artificial intelligence model identifies the lip shape corresponding to each factor, these lip movements can be synthesized using technologies such as facial animation to create a coherent lip animation sequence. In this process, it is necessary to accurately synchronize the lip shape of the digital person with the pronunciation in the oral audio to achieve a natural and smooth visual effect. In addition, in order to enhance the expressive ability of the digital person, the server can also analyze the emotions and intonation in the audio, and integrate these emotional factors into the lip shape and facial expressions, so that the digital person can convey information more vividly. Finally, the generated lip shape features and facial animations can be integrated into the target digital human model, and the digital human screen can be generated through real-time rendering technology to ensure that the lip shape, facial expression and overall performance of the digital person match the audio content when the voice is broadcast.
[0161] In some embodiments, synthesizing the digital human video and the target material video into the target storyboard video may be specifically implemented as follows:
[0162] The background image in the digital human video is replaced with the material image of the target material video to generate a target storyboard video.
[0163] In some embodiments, searching the material library for the material video that matches the storyboard description information of each storyboard and the target object may be specifically implemented as follows:
[0164] Performing feature extraction processing on the storyboard description information to generate storyboard description features;
[0165] Based on the matching degree between the storyboard description information of each storyboard and the video features, a target material video matching each storyboard is searched from a plurality of material videos in the material library that match the object type of the target object.
[0166] The server can analyze the storyboard description information of each storyboard, extract the visual and content features of the storyboard description information, and convert these features into a storyboard description feature vector. The storyboard description feature vector can contain the core elements of the storyboard, such as scene, role, action, color and emotion, to provide a basis for searching and matching video materials.
[0167] After generating the storyboard description feature vector, the server can match the storyboard description feature vector with the video feature vector in the material library. The video materials in the material library can be pre-analyzed and converted into their own video feature vectors, which can be used to describe the visual content of the video. By calculating the similarity between the storyboard description feature vector and the video feature vector, the server can quantify the degree of match between each video material and a specific storyboard.
[0168] When matching video materials, the server not only considers the matching degree of feature vectors, but also searches for video materials that are consistent with the type of the target object in the classified material videos, and selects matching material videos from the material library in combination with the object type of the target object.
[0169] The following describes the video script generation method provided in the embodiment of the present application in conjunction with specific application scenarios.
[0170] The following is an example of a practical application scenario where cleaning service is the target object:
[0171] Let’s say a cleaning service company wants to create a promotional video to showcase its professional cleaning services. Therefore, cleaning services can be identified as the target audience.
[0172] First, the client can send a video script generation instruction for the cleaning service to the server, and the server determines the object description information of the cleaning service, such as the service scope covers homes and offices, the service features include meticulousness, efficiency, and the use of environmentally friendly cleaning products, and the selected video script type is the type that highlights the service effect.
[0173] The server determines the target script structure corresponding to this type of video script, including multiple storyboards, such as a messy scene before cleaning, a detailed display during the cleaning process, and a neat picture after cleaning.
[0174] The server can then use the AI big model to first obtain the target script template and requirements corresponding to the target script structure, such as requiring the language to be vivid and attractive. Then, the first prompt word is generated according to the first prompt template, and it is input into the big model to generate the spoken copy for each storyboard, such as "In this messy office, dust is everywhere and debris is piled up. Let our professional cleaning team perform a magical cleaning!". Then, based on the spoken copy of each storyboard, the storyboard description information is generated, such as "The camera focuses on the desk full of documents and garbage."
[0175] The server can also obtain the previously saved target video about the cleaning service and parse it into multiple storyboard videos and corresponding oral texts. The AI big model is used to generate the storyboard description information and text description information for each storyboard video, and a script template is generated and saved.
[0176] After generating the video script, the server can publish it to the system of the cleaning service company, or send the video script and download address to the client for saving. Alternatively, the video script is sent to the client, and after receiving the video generation instruction generated by the client based on the video script, the server responds to the instruction to convert the spoken copy of each storyboard into spoken audio, and searches the material library for the target material video that matches the storyboard description information, such as close-ups of cleaning supplies, pictures of cleaning staff working hard, etc., and synthesizes the spoken audio and the target material video into a target storyboard video, and finally synthesizes the promotion video according to the target script structure.
[0177] Figure 3 A schematic diagram of a video script provided by an embodiment of the present application is schematically shown.
[0178] As mentioned above, the video script may include three shots, among which the spoken text of shot 1 is "Hello, we are a professional cleaning team, and today we bring you thoughtful home cleaning services", and the shot description information is "A cleaning staff in a neat uniform, with a smile on his face, carrying a professional cleaning tool kit, standing at the customer's door"; the spoken text of shot 2 is "Now our cleaning staff is carefully cleaning the kitchen, not letting go of any corner", and the shot description information is "The cleaning staff is in the kitchen, using professional tools to wipe the stove, clean the sink, etc."; the spoken text of shot 3 is "After our careful cleaning, the room is brand new, making your home more comfortable and tidy", and the shot description information is "neat and bright bedrooms, bathrooms and kitchens, with neatly arranged items."
[0179] Figure 4 A framework diagram of the video script generation method provided by the present application is shown.
[0180] like Figure 4 As shown, the video script generation method provided in the embodiment of the present application includes a script service 401, a director service 402, and a material service 403.
[0181] Among them, the script service 401 is used to generate a video script. In one embodiment of the present application, the script service 401 can be specifically used to extract and generate a target script from the target video by reverse parsing the target video. Among them, the video tracking module 4011 can be used to track popular hot videos from the Internet, and then the target video is segmented by the video storyboard parsing module 4012 to obtain multiple storyboard videos. The first prompt word generation module 4013 can be used to generate a copy prompt word, which can be used to instruct the artificial intelligence large model to generate a spoken copy. The second prompt word generation module 4014 can be used to generate a storyboard prompt word, which can be used to instruct the artificial intelligence large model to generate a storyboard description information. The framework generation module 4015 can be used to generate a script template, wherein there can be multiple storyboards in the script template. After the script template is generated, it can be submitted to the review module 4016 for review. The review module 4016 can be used to review whether the logic of the script template is smooth, whether the theme is clear, etc. If the script template passes the review, the script template can be saved. If the script template does not pass the review, it can return to the regeneration step, such as regenerating the storyboard, regenerating the prompt words, etc.
[0182] In the editing and directing service 402, the video frame matching module 4021 can be used to determine the corresponding video script for the user's video generation instruction. The oral content generation module 4022 can be used to generate oral copy based on the copy prompt words generated by the first prompt word generation module 4013; the storyboard description generation module 4023 can be used to generate storyboard description information based on the storyboard prompt words generated by the second prompt word generation module 4014. The oral copy generated by the oral content generation module 4021 can generate corresponding oral audio through the oral audio generation module 4024. The storyboard video generation / matching module 4025 can be used to match the corresponding video material for the storyboard description information from the material library, or generate corresponding synthetic content for the storyboard description information. The background music matching module 4026 can be used to match the background music of the corresponding style for the storyboard. The video material time piling module 4027 can be used to pile the oral copy and the video material in the storyboard video, so that when the storyboard video broadcasts the oral copy, the matching video material is played accordingly. The video synthesis module 4028 can be used to synthesize multiple storyboard videos into a promotional video.
[0183] In the material service 403, the material capture module 4031 can capture videos that can be used as video materials from the Internet and classify the video materials. The material generation module 4032 can be used to provide picture generation and video generation capabilities for the storyboard video generation / matching module 4025. The material management module 4033 can be used for material cleaning and material review to improve the quality of video materials and filter out material videos that do not meet the requirements. The material preprocessing module 4034 can be used to segment the video captured by the material capture module 4031 or the video provided by the user according to the video content, and vectorize each segmented video, and store the video features in the material storage module 4035.
[0184] Figure 5 FIG. 1 is a block diagram of a video script generation device provided by an embodiment of the present application. Figure 5 As shown, the video script generating device may include:
[0185] The instruction response module 501 is used to respond to the video script generation instruction for the target object sent by the client, and determine the object description information and video script type of the target object;
[0186] A structure determination module 502 is used to determine a target script structure corresponding to the video script type; the target script structure includes a plurality of storyboards;
[0187] The content generation module 503 is used to generate the script content of each storyboard based on the object description information and the target script structure by using the artificial intelligence big model; the script content includes the oral copy and the storyboard description information; the storyboard description information is used to describe the screen content of the storyboard;
[0188] The script generation module 504 is used to construct a video script according to the target script structure using the script contents corresponding to the multiple storyboards.
[0189] In some embodiments, the content generation module 503 may be specifically used to:
[0190] Generate a spoken copy for each storyboard based on the object description information and the target script structure using an artificial intelligence big model;
[0191] The artificial intelligence big model is used to generate the storyboard description information of each storyboard based on the spoken text of each storyboard.
[0192] In some embodiments, the content generation module 503 may be specifically used to:
[0193] Obtain a target script template and target script requirements corresponding to the target script structure;
[0194] Generate a first prompt word according to the first prompt template by using the object description information, the target script template and the target script requirement;
[0195] The first prompt word is input into the artificial intelligence big model, so as to utilize the artificial intelligence big model to generate the spoken text of each storyboard based on the object description information, with reference to the target script template and in accordance with the script requirements.
[0196] In some embodiments, the video script generating apparatus may further include:
[0197] A video acquisition module is used to acquire a target video;
[0198] A video parsing module, used for parsing the target video to obtain a plurality of storyboard videos and spoken texts corresponding to the plurality of storyboard videos;
[0199] A copywriting generation module, used to generate storyboard description information and copywriting description information of each storyboard video based on the multiple storyboard videos and the oral copywriting corresponding to the storyboard videos by using an artificial intelligence big model; wherein the storyboard description information is used to describe the screen content of the storyboard video; and the copywriting description information is used to describe the copywriting type of the storyboard video;
[0200] A template generation module, used to generate a script template according to the script structure composed of the multiple storyboard videos and the storyboard description information and copy description information of each storyboard video;
[0201] A template saving module, used to save the script template;
[0202] In some embodiments, the content generation module 503 may be specifically used to:
[0203] Searching for a target script template corresponding to the target script structure from the saved script templates;
[0204] Obtain the target script requirement corresponding to the target script structure.
[0205] In some embodiments, the video parsing module is specifically used to:
[0206] The target video is segmented according to content similarity to obtain the multiple storyboard videos.
[0207] In some embodiments, the video parsing module is specifically used to:
[0208] Segmenting the target video according to content similarity to obtain multiple segmented videos;
[0209] At least one segmented video whose content similarity meets a preset condition is merged in sequence to generate the multiple storyboard videos.
[0210] In some embodiments, the video parsing module is specifically used to:
[0211] Performing frame extraction processing on the target video to obtain multiple video frames;
[0212] Using an artificial intelligence big model to convert the multiple video frames into video features respectively;
[0213] The content similarity between the video frames is calculated based on the video features, and the video frames whose content similarity meets a preset condition are merged into a storyboard video.
[0214] In some embodiments, the video script generating apparatus may further include:
[0215] A script publishing module is used to publish the video script to the object providing system of the target object or send the video script and / or the download address of the video script to the client so that the client can save the video script.
[0216] In some embodiments, the video script generating apparatus may further include:
[0217] A script sending module, used for sending the video script to the client;
[0218] An instruction receiving module, used for receiving a video generation instruction generated by the client based on the video script;
[0219] A text conversion module, configured to convert the spoken text corresponding to each storyboard into spoken audio in response to the video generation instruction;
[0220] A material search module, used for searching a target material video that matches the storyboard description information of each storyboard and the target object from a material library;
[0221] The first synthesis module is used to synthesize the spoken audio of each storyboard with the corresponding target material video into a target storyboard video;
[0222] The second synthesis module is used to synthesize the target storyboard videos corresponding to the multiple storyboards according to the target script structure to obtain a promotional video for the target object.
[0223] Figure 5 The video script generating device can execute Figure 2 The implementation principle and technical effects of the video script generation method described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the video script generation device in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.
[0224] The present application also provides a computing device, such as Figure 6 As shown, the device may include a storage component and a processing component;
[0225] The storage component stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component to implement the video script generation method provided in the embodiment of the present application.
[0226] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.
[0227] The processing components in the computing device are used to implement the following Figure 2 In the case of the video script generation method shown, the computing device may also include a display component to perform corresponding display operations.
[0228] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices.
[0229] The processing component may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.
[0230] The storage component is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0231] The display component may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.
[0232] It should be noted that the above computing device implements Figure 2In the case of the video script generation method shown, it can be a physical device or an elastic computing host provided by a cloud computing platform, etc. It can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device.
[0233] It should be noted that the above computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. It can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device.
[0234] The present application also provides a computer-readable storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 2 The video script generation method shown. The computer readable medium may be included in the electronic device described in the above embodiment; or it may exist independently without being assembled into the electronic device.
[0235] The present application also provides a computer program product, which includes a computer program carried on a computer-readable storage medium. When the computer program is executed by a computer, the computer program can achieve the above-mentioned Figure 2 The video script generation method shown. In such an embodiment, the computer program can be downloaded and installed from the network, and / or installed from a removable medium. When the computer program is executed by the processor, various functions defined in the system of the present application are executed.
[0236] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).
[0237] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0238] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0239] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0240] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for generating a video script, characterized in that: Applied to the server, the method includes: In response to the video script generation instruction for the target object sent by the client, determine the object description information and the video script type of the target object; Determine a target script structure corresponding to the video script type; the target script structure includes a plurality of storyboards; Generate the script content of each storyboard based on the object description information and the target script structure using the artificial intelligence big model; the script content includes the spoken copy and the storyboard description information; the storyboard description information is used to describe the screen content of the storyboard; The script contents corresponding to the multiple storyboards respectively constitute a video script according to the target script structure.
2. The method according to claim 1, characterized in that The method of using the artificial intelligence big model to generate the script content of each storyboard based on the object description information and the target script structure includes: Generate a spoken copy for each storyboard based on the object description information and the target script structure using an artificial intelligence big model; The artificial intelligence big model is used to generate the storyboard description information of each storyboard based on the spoken text of each storyboard.
3. The method according to claim 2, characterized in that The method of using the artificial intelligence big model to generate the oral copy for each storyboard based on the object description information and the target script structure includes: Obtain a target script template and target script requirements corresponding to the target script structure; Generate a first prompt word according to the first prompt template by using the object description information, the target script template and the target script requirement; The first prompt word is input into the artificial intelligence big model, so as to utilize the artificial intelligence big model to generate the spoken text of each storyboard based on the object description information, with reference to the target script template and in accordance with the script requirements.
4. The method according to claim 3, characterized in that Also includes: Get the target video; Parsing the target video to obtain a plurality of storyboard videos and spoken texts corresponding to the plurality of storyboard videos; Generate storyboard description information and text description information of each storyboard video based on the multiple storyboard videos and the oral texts corresponding to the storyboard videos by using an artificial intelligence big model; wherein the storyboard description information is used to describe the screen content of the storyboard video; and the text description information is used to describe the text type of the storyboard video; Generate a script template according to the script structure composed of the multiple storyboard videos and the storyboard description information and copy description information of each storyboard video; Saving the script template; The step of obtaining the target script template and target script requirements corresponding to the target script structure includes: Searching for a target script template corresponding to the target script structure from the saved script templates; Obtain the target script requirement corresponding to the target script structure.
5. The method according to claim 4, characterized in that The step of parsing the target video to obtain a plurality of storyboard videos comprises: The target video is segmented according to content similarity to obtain the multiple storyboard videos.
6. The method according to claim 5, characterized in that The segmenting of the target video according to content similarity to obtain the plurality of storyboard videos comprises: Segmenting the target video according to content similarity to obtain multiple segmented videos; At least one segmented video whose content similarity meets a preset condition is merged in sequence to generate the multiple storyboard videos.
7. The method according to claim 5, characterized in that The segmenting of the target video according to content similarity to obtain the plurality of storyboard videos comprises: Performing frame extraction processing on the target video to obtain multiple video frames; Using an artificial intelligence big model to convert the multiple video frames into video features respectively; The content similarity between the video frames is calculated based on the video features, and the video frames whose content similarity meets a preset condition are merged into a storyboard video.
8. The method according to claim 1, characterized in that: The method further comprises: The video script is published to the object providing system of the target object or the video script and / or the download address of the video script is sent to the client so that the client can save the video script.
9. The method according to claim 1, characterized in that: The method further comprises: Sending the video script to the client; Receiving a video generation instruction generated by the client based on the video script; In response to the video generation instruction, converting the spoken text corresponding to each storyboard into spoken audio; Searching for a target material video that matches the storyboard description information of each storyboard and the target object from a material library; The spoken audio of each storyboard is combined with the corresponding target material video into a target storyboard video; According to the target script structure, the target storyboard videos corresponding to the multiple storyboards are synthesized to obtain a promotional video for the target object.
10. A computing device, characterized in that including a processing component and a storage component; The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the video script generation method as described in any one of claims 1 to 9.
11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by the processing component, the video script generation method as described in any one of claims 1 to 9 is implemented.
12. A computer program product, characterized in that It includes computer programs / instructions, which, when executed by a processing component, implement the video script generation method as described in any one of claims 1 to 9.
Citation Information
Patent Citations
Video splitting method and device, equipment and computer readable storage medium
CN113408332A
Video generation method and device, electronic equipment and storage medium
CN113727039A
SOAR script model, script construction method, electronic equipment and storage medium
CN114338178A
Video processing method and electronic equipment
CN116668768A
Propaganda video generation method and device, and storage medium
CN117241087A
Cited By
Role view angle video generation method, related device and medium
CN119545119A
Video generation method, computing device, storage medium and program product
CN119815142A
Intelligent script generation method, system and equipment based on large model
CN119990078A
Scenario generation method and related device
CN120032374A
A script generation method and related apparatus
CN120032374B
