Video release method and device, storage medium and program product

Abstract

The embodiment of the invention provides a video publishing method and device, a storage medium and a program product. In the method, a video processing application can generate a promotion video of a target object according to object description information and a video script type; selecting a target playing platform and a target capital applet template from the plurality of candidate playing platforms and the plurality of candidate capital applet templates; the target playing platform can integrate the applet code corresponding to the applet identifier into the applet shell to obtain the target applet, so that the target applet is mounted on the promotion video. And the target applet is bound with the device identifier of the terminal device to collect the capital information of the second user watching the promotion video and feed back the capital information to the terminal device. Through the mode, the playing platform and the applet template can be accurately determined, and the target applet is mounted on the playing platform based on the applet template so as to more accurately collect the capital information, so that generation and release of the promotion video can be efficiently performed.

Description

Technical Field

[0001] The present application relates to the technical field of video publishing, and in particular to a video publishing method, device, storage medium and program product. Background Art

[0002] With the popularization of mobile terminals and the acceleration of the Internet, short, fast and high-traffic content has gradually gained the favor of major platforms and capital, and people are more willing to use short videos to record and share their lives, or sell goods. Short videos are short videos that integrate topics such as skill sharing, humor, fashion trends, social hot spots, street interviews, public welfare education, advertising creativity, and commercial customization. They are suitable for watching on the move and in a short leisure state. Short videos are widely loved by people for their short, concise and easy-to-spread characteristics.

[0003] Based on this, when merchants have a need to promote their products, they would like to use short video platforms to generate promotional videos and publish them accordingly to promote their products. However, in the prior art, it is usually impossible to promote products for merchants more efficiently based on short video platforms. Summary of the invention

[0004] Multiple aspects of the present application provide a video publishing method, device, storage medium and program product for more efficiently generating and publishing promotional videos.

[0005] An embodiment of the present application provides a video publishing method, which is applied to a video processing application on a terminal device of a first user; the method includes: obtaining object description information and a video script type of a target object; generating a promotional video for the target object according to the object description information and the video script type; selecting a target playback platform and a target information retention mini-program template from multiple candidate playback platforms and multiple candidate information retention mini-program templates respectively; different information retention mini-program templates correspond to different business types and mini-program identifiers; sending the device identifier of the terminal device, the promotion video, and the mini-program identifier corresponding to the target information retention mini-program template to the target playback platform, so that the target playback platform can publish the promotional video; wherein the released promotional video is mounted with a target mini-program, and the target mini-program is obtained by the target playback platform integrating the mini-program code corresponding to the mini-program identifier into a preset mini-program shell, and the target mini-program is bound to the device identifier of the terminal device, and is used to collect the information retention information of a second user who watches the promotional video, and feed it back to the terminal device.

[0006] Optionally, obtaining object description information and video script type of the target object includes: displaying an information collection interface provided by the video processing application, responding to information input operations on the information collection interface, and obtaining object description information and video script type of the target object.

[0007] Optionally, an information collection interface provided by the video processing application is displayed, and in response to an information input operation on the information collection interface, object description information of the target object and a video script type are obtained, including: displaying a term selection interface to the first user, the term selection interface including: a term selection control and a term confirmation control; in response to a trigger operation of the first user on the term selection control, selecting at least one keyword from a plurality of keywords; in response to a trigger operation of the first user on the term confirmation control, generating the object description information according to the at least one keyword, and jumping from the term selection interface to a script selection interface, the script selection interface including: a plurality of candidate script types and a type confirmation control; in response to a trigger operation of the first user on the type confirmation control, determining the video script type from the plurality of candidate script types; or, displaying a picture upload interface provided by the video processing application, in response to an image upload operation on the picture upload interface, obtaining a multi-view image of the target object; extracting semantic information from the multi-view image of the target object using an artificial intelligence-based image understanding module, and generating the object description information and the video script type according to the semantic information.

[0008] Optionally, a promotional video for the target object is generated according to the object description information and the video script type, including: determining a script structure corresponding to the video script type; the script structure includes multiple storyboards; using an artificial intelligence-based video generation module to generate script content for each storyboard based on the object description information and the script structure; the script content includes spoken text and storyboard description information; the storyboard description information is used to describe the screen content of the storyboard; converting the spoken text corresponding to each storyboard into spoken audio, and obtaining a material video matching the target object according to the storyboard description information of each storyboard; generating a storyboard video for each storyboard according to the spoken audio and material video of each storyboard; and synthesizing the storyboard videos of multiple storyboards according to the script structure to obtain a promotional video for the target object.

[0009] Optionally, a target playback platform and a target information retention mini-program template are respectively selected from multiple candidate playback platforms and multiple candidate information retention mini-program templates, including: displaying an information configuration interface to the first user, displaying multiple candidate playback platforms and multiple candidate information retention mini-program templates on the information configuration interface; responding to a first selection operation, determining a candidate playback platform selected from the multiple candidate playback platforms as the target playback platform; responding to a second selection operation, determining a candidate information retention mini-program template selected from the multiple candidate information retention mini-program templates as the target information retention mini-program template.

[0010] Optionally, a target playback platform and a target information retention mini-program template are respectively selected from multiple candidate playback platforms and multiple candidate information retention mini-program templates, including: determining the target playback platform from the multiple candidate playback platforms based on performance indicator information of the multiple candidate playback platforms; the performance indicator information includes: network delay information, server load information, traffic information used to promote the target object in a historical period and / or historical popularity information of the target object; determining a target business type corresponding to the target object based on the object description information; and selecting a target information retention mini-program template corresponding to the target business type from the multiple candidate information retention mini-program templates.

[0011] Optionally, it also includes: generating an initial descriptive text of the promotional video based on the object description information, the initial descriptive text is used to summarize the content of the promotional video, including: copy and / or title; displaying a video editing interface to the first user, the first setting area in the video editing interface is used for the first user to preview the initial descriptive text of the promotional video, and the second setting area displays a descriptive text editing control; in response to the first user's editing operation on the descriptive text editing control, updating the initial descriptive text to a target descriptive text, and sending it to the target playback platform to be displayed together with the promotional video on the video playback page.

[0012] Optionally, the target playback platform provides a video transmission interface for the video processing application; the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target mini-program template are sent to the target playback platform, including: displaying a preview interface to the first user, the preview interface including: a video preview window, a video editing control, and a sharing control; in response to the first user's editing operation on the video editing control, editing the video parameters of the promotional video; the video preview window is used for the first user to preview the result of the editing operation; the sharing control is bound to a call event to the video transmission interface; the call event includes: detecting that the sharing control is manually triggered, receiving a target voice command, or the arrival of a preset call cycle; in response to the triggering of the call event, calling the video transmission interface, and sending the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target mini-program template to the target playback platform.

[0013] An embodiment of the present application also provides a video publishing method, which is applied to a target playback platform, and the target playback platform is pre-installed with a mini-program shell; the method includes: receiving a promotional video of a target object and an identifier of the terminal device sent by a terminal device of a first user; the promotional video is generated according to the object description information of the target object and the video script type; determining the mini-program identifier that is compatible with the promotional video, and integrating the mini-program code corresponding to the mini-program identifier into the mini-program shell to obtain a target mini-program; binding the target mini-program to the promotional video for publishing, and binding the target mini-program to the device identifier of the terminal device, so as to collect the retention information of a second user who watches the promotional video and feed it back to the terminal device.

[0014] Optionally, determining a mini-program identifier that is compatible with the promotional video, and integrating the mini-program code corresponding to the mini-program identifier into the mini-program shell to obtain a target mini-program, includes: receiving a mini-program identifier corresponding to a target mini-program template sent by the terminal device; determining a mini-program shell corresponding to the identifier of the terminal device from multiple mini-programs; integrating the mini-program code corresponding to the mini-program identifier in a local code resource library into the mini-program shell to obtain the target mini-program; or, displaying a configuration interface to a third user, the configuration interface including: multiple mini-program templates and a code editing control; determining a mini-program shell corresponding to the identifier of the terminal device from the multiple mini-programs; determining a mini-program identifier that is compatible with the promotional video in response to the third user's selection operation on the multiple mini-program templates; displaying the mini-program code corresponding to the mini-program identifier in the code resource library; and integrating the edited mini-program code into the mini-program shell in response to the third user's editing operation on the code editing control to obtain the target mini-program.

[0015] An embodiment of the present application also provides an electronic device, comprising: a memory and a processor; the memory is used to store one or more computer instructions; the processor is used to execute the one or more computer instructions to: execute the steps in the video publishing method.

[0016] An embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor is enabled to implement the steps in the video publishing method.

[0017] An embodiment of the present application also provides a computer program product, including a computer program / instruction. When the computer program / instruction is executed by a processor, the steps in the video publishing method are executed.

[0018] In this embodiment, the video processing application can generate a promotional video for the target object based on the object description information and the video script type; select a target playback platform and a target retention information mini-program template from multiple candidate playback platforms and multiple candidate retention information mini-program templates; the target playback platform can integrate the mini-program code corresponding to the mini-program identifier into the mini-program shell to obtain the target mini-program, thereby mounting the target mini-program on the promotional video. The target mini-program is bound to the device identifier of the terminal device to collect the retention information of the second user who watches the promotional video and feed it back to the terminal device. In this way, the playback platform and mini-program template can be determined more accurately, and the target mini-program can be mounted on the playback platform based on the mini-program template to more accurately collect the retention information, thereby more efficiently generating and publishing promotional videos. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1a A flowchart of the entire process of a video promotion service provided by an exemplary embodiment of the present application;

[0021] Figure 1b A schematic diagram of a video publishing method provided as a flow chart of an exemplary embodiment of the present application;

[0022] Figure 2a-2b A schematic diagram of a small program template for leaving funds provided for an exemplary embodiment of the present application;

[0023] Figure 3 A schematic diagram of an entry selection interface and a script selection interface provided for an exemplary embodiment of the present application;

[0024] Figure 4a-4b A schematic diagram of an information configuration interface provided for an exemplary embodiment of the present application;

[0025] Figure 5 A schematic diagram of a video editing interface provided by an exemplary embodiment of the present application;

[0026] Figure 6 A schematic diagram of a preview interface provided for an exemplary embodiment of the present application;

[0027] Figure 7 A flowchart of another video publishing method provided as an exemplary embodiment of the present application;

[0028] Figure 8 A schematic diagram of a configuration interface provided for an exemplary embodiment of the present application;

[0029] Fig. 9 A schematic diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. 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 ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[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 portals for users to choose to authorize or refuse. In addition, the various models involved in this application (including but not limited to language models or large models) are in compliance with relevant laws and standards.

[0032] In the field of product promotion, when merchants have a need to promote their products, they hope to use short video platforms to generate promotional videos and publish them accordingly to promote their products. However, merchants are usually unable to promote their products more efficiently based on short video platforms.

[0033] In view of the technical problems existing in the above-mentioned prior art, in some embodiments of the present application, a solution is provided: a video processing application provides a full process of video promotion service to a first user, and each service link in the full process is sequentially executed to provide video promotion service to the first user, such as Figure 1a As shown, the whole process may include the video service activation phase, promotional video production phase, promotional video release phase, lead collection phase, lead follow-up phase and video sharing phase. Figure 1a As shown, the video service activation link refers to the process of providing the first user with video service rights and interests based on the first user's video service needs. The promotional video production link refers to the process of generating a promotional video with one click based on the first user's video production needs. The promotional video publishing link refers to the process of publishing the promotional video to the video playback platform for playback based on the first user's publishing needs. The lead collection link refers to the process of obtaining potential user information from user information that initiates interactive operations to the video playback platform during the playback of the promotional video. The lead follow-up link refers to the process of driving the conversion of potential user information into order information and monitoring the conversion details. In the video sharing link, the first user can share the promotional video generated for itself by the service platform with other merchants, and can obtain corresponding sharing rewards after successful sharing. In addition Figure 1a The various links shown in the whole process may also include a live video link. In this live video link, the service platform can create a live broadcast based on the promotional video generated for the first user, and broadcast it live on the video playback platform.

[0034] The embodiments of the present application are mainly applied to the promotional video production and promotional video publishing stages of the entire process. The technical solutions provided by the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings.

[0035] Figure 1bThe following is a flow chart of a video publishing method provided by an exemplary embodiment of the present application. Figure 1b As shown, the method includes:

[0036] Step 11: Obtain object description information of the target object and the video script type.

[0037] Step 12: Generate a promotional video for the target object based on the object description information and the video script type.

[0038] Step 13: Select a target playback platform and a target information retention mini-program template from multiple candidate playback platforms and multiple candidate information retention mini-program templates respectively; different information retention mini-program templates correspond to different business types and mini-program identifiers.

[0039] Step 14: Send the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target information retention mini-program template to the target playback platform, so that the target playback platform can publish the promotional video; wherein, the published promotional video is mounted with the target mini-program, and the target mini-program is obtained by the target playback platform integrating the mini-program code corresponding to the mini-program identification into a preset mini-program shell. The target mini-program is bound to the device identification of the terminal device, and is used to collect the information retention information of the second user who watches the promotional video and feed it back to the terminal device.

[0040] The execution subject of this embodiment may be a video processing application on the terminal device of the first user. The first user refers to a merchant with promotion needs. The terminal device may be a mobile phone, a tablet computer, a smart wearable device or a computer, etc., which is not limited in this embodiment. The video processing application can be used to provide video processing services such as video generation and video publishing.

[0041] In this embodiment, the target object can be any object, such as an animal, plant, building, person, etc., or various commodities, such as services, vehicles, mobile phones, tables, etc., and this embodiment does not limit it. Taking the target object as a service as an example, the target object can be housekeeping service, laundry service, cleaning service, etc.

[0042] In this embodiment, object description information of the target object and the type of video script can be obtained. Among them, the object description information can be used to describe the target object, and may include the name, characteristics, uses, advantages and other contents of the target object, which can be used as the basis of the video content. The type of 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. Among them, the object description information can be generated based on the keywords input by the first user, or can be directly input by the first user, or can be obtained from a cloud server connected to the terminal device in communication, which is not limited in this embodiment. The type of video script can be selected by the first user, or can be selected from the video script types used at historical moments, or can be obtained from a cloud server, which is not limited in this embodiment.

[0043] Afterwards, a promotional video for the target object can be generated based on the object description information and the video script type. Among them, the promotional video for the target object can be understood as a video used to promote the target object, which can be a marketing video or a live video, etc., which is not limited in this embodiment. Among them, a video generation module based on artificial intelligence (AI) can be used to generate a promotional video based on the object description information and the video script type; a preset video template can also be used to generate a promotional video based on the object description information and the video script type; the object description information and the video script type can also be provided to the first user for manual video editing by the first user to obtain a promotional video, which is not limited in this embodiment. In this way, a promotional video can be generated for the target object more accurately.

[0044] After the promotional video is generated, a target playback platform and a target retention mini program template are selected from multiple candidate playback platforms and multiple candidate retention mini program templates. Among them, the playback platform can be used to play the promotional video to promote the target object to the second user, which can be a short video platform, a long video platform, a live broadcast platform, etc., wherein the second user refers to a user who uses the playback platform to watch the video. Among them, the retention mini program template refers to a template of the retention mini program that can be mounted on the playback platform, which can be used to display the interface style of the retention mini program.

[0045] Different information retention mini program templates may correspond to different mini program identifiers and different business types. Among them, the mini program identifier corresponding to the information retention mini program template is used to identify the identity of the information retention mini program template. Different information retention mini program templates may correspond to different business types. Among them, different target objects may belong to different or the same business types respectively. For example, down jacket cleaning services and snow suit dry cleaning services both belong to the business type of laundry services; for another example, designated driver services and car rental services may respectively belong to the business type of transportation services; the above is only an exemplary description, and the specific type classification rules can be customized according to actual needs, and this embodiment does not limit it.

[0046] In this embodiment, different information-reservation mini-program templates may be set for different business types, so that the information-reservation mini-program is more adaptable to the business type of the target object. Figure 2a-2b The following are three examples of the template for the leave a capital app: Figure 2a As shown, the information leaving applet template L1 corresponding to the laundry service business type may include a submit control of "Submit information and wait for contact" and the following configuration items: relevant pictures of the target object, contact information, required services, clothing types, laundry styles, and door-to-door service addresses. Figure 2b As shown, the information retention applet template L2 corresponding to the business type of transportation services may include a submission control of "Submit information and wait for contact" and the following configuration items: relevant pictures of the target object, contact information, required services, vehicle type, ideal price range, and door-to-door service address. It should be noted that Figure 2a-2b It is only used to provide an illustrative description of the template for the Mini Program for Retaining Information, and does not limit the specific style of the template for the Mini Program for Retaining Information.

[0047] Among them, when selecting the target playback platform from multiple candidate playback platforms, it can be manually selected by the first user, or it can be automatically selected by the video processing application, and this embodiment does not limit it. When selecting the target information retention applet template from multiple candidate information retention applet templates, it can be manually selected by the first user, or it can be automatically selected by the video processing application, and this embodiment does not limit it.

[0048] After selecting the target playback platform and the target information retention mini-program template, the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target information retention mini-program template can be sent to the target playback platform. Correspondingly, different mini-program codes and the correspondence between the mini-program code and the mini-program identification can be stored on the target playback platform, and then based on the correspondence, the mini-program code corresponding to the mini-program identification can be determined, and the mini-program code can be integrated into the preset mini-program shell to obtain the target mini-program, thereby mounting the target mini-program on the released promotional video. Among them, the mini-program shell configured on the target playback platform can be understood as a lightweight application container, which can be used as a basic framework to provide a running environment for the mini-program code. The mini-program codes running in the mini-program shell are different, and the resulting mini-programs are also different.

[0049] Mounting the target mini program on the released promotional video can be understood as mounting the target mini program on the video playback page of the released promotional video. For example, a mini program launch control is added to the video playback page of the promotional video, and the second user can click the mini program launch control to open the target mini program.

[0050] Among them, the target mini program can be bound to the device identifier of the terminal device, so that it can be used to collect the information left by the second user who watches the promotional video and feed it back to the terminal device; in other words, the target mini program needs to determine the return of the information left to the terminal device corresponding to the device identifier based on the device identifier.

[0051] The information left by the second user watching the promotional video refers to the personal information provided by the second user through the target mini program during the process of watching the promotional video. For example, assuming that the target mini program is obtained based on the mini program identifier corresponding to the information left by the mini program template L1, the second user can see the following information after opening the target mini program: Figure 2a The mini program interface is displayed, where you can fill in your contact information, required services, clothing type, desired laundry style, and door-to-door service address as your information.

[0052] It should be emphasized that since the mini-program code integrated into the mini-program shell by the target playback platform is determined based on the target information-retention mini-program template selected by the terminal device, and different information-retention mini-program templates correspond to different business types, the integrated target mini-program is not only more in line with the first user's mini-program mounting needs, but also more adaptable to the business type to which the target object belongs, thereby more accurately collecting information retention information.

[0053] In this embodiment, the video processing application can generate a promotional video for the target object based on the object description information and the video script type; select a target playback platform and a target retention information mini-program template from multiple candidate playback platforms and multiple candidate retention information mini-program templates; the target playback platform can integrate the mini-program code corresponding to the mini-program identifier into the mini-program shell to obtain the target mini-program, thereby mounting the target mini-program on the promotional video. The target mini-program is bound to the device identifier of the terminal device to collect the retention information of the second user who watches the promotional video and feed it back to the terminal device. In this way, the playback platform and mini-program template can be determined more accurately, and the target mini-program can be mounted on the playback platform based on the mini-program template to more accurately collect the retention information, thereby more efficiently generating and publishing promotional videos.

[0054] In some optional embodiments, when obtaining the object description information of the target object and the type of the video script, an information collection interface provided by the video processing application may be displayed to the first user, and the user may perform corresponding information input operations on the information collection interface. Correspondingly, the object description information of the target object and the type of the video script may be obtained in response to the information input operation of the first user on the information collection interface. Specifically, the process of obtaining the object description information of the target object and the type of the video script may be implemented based on the following two implementations:

[0055] Implementation method 1: Displaying a term selection interface, the term selection interface may include: a term selection control and a term confirmation control. For example, Figure 3 The illustrated entry selection interface exemplarily displays six entry selection controls and an entry confirmation control. The first user can click on any entry selection control to view multiple keywords and select a keyword from them. Correspondingly, in response to the first user's triggering operation on the entry selection control, at least one keyword can be selected from the multiple keywords.

[0056] Optionally, multiple keywords may be divided into multiple groups according to multiple levels, and the first user may select keywords in order from top to bottom according to the levels. Figure 3 As shown, keywords such as housekeeping, cleaning, laundry and shoe washing can be selected in sequence from multiple keywords, wherein the levels of housekeeping, cleaning, and laundry and shoe washing decrease in sequence, that is, housekeeping includes cleaning, and cleaning includes laundry and shoe washing.

[0057] Afterwards, after the user selects a keyword, the entry confirmation control may be triggered. Correspondingly, in response to the triggering operation of the first user on the entry confirmation control, object description information may be generated according to at least one keyword. Optionally, the association relationship between at least one keyword may be analyzed to understand the subject corresponding to at least one keyword; a sentence structure adapted to at least one keyword may be used to generate object description information according to at least one keyword and the association relationship between at least one keyword.

[0058] See Figure 3 After generating the object description information, you can jump from the entry selection interface to the script selection interface, which includes: multiple candidate script types and a type confirmation control. In response to the first user's triggering operation on the type confirmation control, the video script type is determined from multiple candidate script types. For example, the first user clicks on the candidate script type U1 and then clicks on the type confirmation control, then the determined video script type is the candidate script type U1.

[0059] It should be emphasized that Figure 3 The interface shown in the figure is only an optional method for selecting a term and a script, and does not limit the specific implementation of the interface. Figure 3 Take the entry selection interface shown in as an example, except Figure 3 In the manner shown, the entry selection controls can be arranged from top to bottom, from left to right, or in other arrangements; the entry confirmation control can also be located on the left, right, or top of the entry selection interface, which is not limited in this embodiment. Figure 3 Take the script selection interface shown in as an example, except Figure 3 In the manner shown, multiple candidate script types can be arranged from left to right, or arranged in other arrangements, or displayed in sequence in the type list, which is not limited in this embodiment; the type confirmation control can also be located on the left, right or top side of the script selection interface, which is not limited in this embodiment.

[0060] Implementation method 2: Display the image upload interface provided by the video processing application, and the first user can upload the multi-view image of the target object through the image upload interface. In response to the image upload operation on the image upload interface, the multi-view image of the target object is obtained; the image understanding module based on artificial intelligence is used to extract semantic information from the multi-view image of the target object, and the object description information and the video script type are generated according to the semantic information. Among them, the image understanding module based on artificial intelligence can have the ability to determine the object description information and the video script type based on the multi-view image of the target object through a pre-model training process. Specifically, the image understanding module of artificial intelligence can set corresponding semantic labels or feature vectors for different image areas of the multi-view image according to the extracted semantic information, and determine the object description information according to the respective semantic labels or feature vectors of different image areas of the multi-view image. The image understanding module of artificial intelligence can perform image recognition analysis on the multi-view image, thereby determining the scene in which the target object is located, and select the candidate script type corresponding to the scene in which the target object is located from multiple candidate script types as the video script type.

[0061] Through the above-mentioned implementation mode 1 or implementation mode 2, the object description information and the video script type of the target object can be determined more accurately. Afterwards, based on the following steps 21 to 24, a promotional video of the target object can be generated according to the object description information and the video script type.

[0062] Step 21, determine the script structure corresponding to the video script type; the script structure includes multiple storyboards.

[0063] Among them, the object description information may include the name, characteristics, uses, advantages, etc. of the target object, which can be used as the basis of the video content. For example, the following is the object description information of the cleaning service: "Professional home cleaning service, covering whole house cleaning, including kitchen, bathroom, bedroom and other areas, meticulous service, and use of environmentally friendly detergents". Through the object description information, the name of the target object can be introduced, such as "home cleaning service", where the service content of "home cleaning service" includes "whole house cleaning, including kitchen, bathroom, bedroom and other areas", and the service advantages and characteristics are "meticulous service, use of environmentally friendly detergents". Among them, 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 may include multiple storyboards, each of which may be used to guide the generation of one of the video segments of the promotional video, and the video segment may be a link in the process of generating the promotional video. After receiving the video generation instruction, the video script type may be determined according to the target object, the purpose of promotion, etc.; or, the user may specify the desired video script type in the video generation instruction.

[0064] Video script types may include, for example, narrative type, explanatory type, etc., wherein each video script type corresponds to a different script structure.

[0065] 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.

[0066] 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.

[0067] Step 22: Generate the script content of each storyboard based on the object description information and the script structure using an artificial intelligence-based video generation module; the script content includes spoken text and storyboard description information; the storyboard description information is used to describe the picture content of the storyboard.

[0068] 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.

[0069] The artificial intelligence video generation module 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.

[0070] 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.

[0071] Step 23, convert the oral text corresponding to each storyboard into oral audio, and obtain the material video matching the target object according to the storyboard description information of each storyboard; generate the storyboard video of each storyboard according to the oral audio and material video of each storyboard. Specifically, the oral text corresponding to each storyboard can be converted into oral audio; search the material library for the target material video that matches the storyboard description information of each storyboard and the target object; and synthesize the oral audio of each storyboard with the corresponding target material video into the target storyboard video.

[0072] Step 24: According to the script structure, the storyboard videos of the plurality of storyboards are synthesized to obtain a promotional video for the target object. Specifically, according to the script structure, the target storyboard videos corresponding to the plurality of storyboards are synthesized to obtain a promotional video for the target object.

[0073] After the oral copy is generated, the oral copy of each storyboard can be converted into oral audio using text-to-speech conversion technology. Next, according to the picture content described by the storyboard description information of the storyboard, the material content that matches the picture content described by 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 commodity corresponding to the target object. By searching for material videos based on the storyboard description information and the target object, it can be ensured that the visual content of the generated promotional video matches the target object and the usage scenario of the target object. For the material video and oral audio corresponding to each storyboard, the corresponding material video and oral audio can be synthesized and synchronized to generate a target storyboard video. 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.

[0074] In some embodiments, the video generation module using artificial intelligence generates the script content of each storyboard based on the object description information and the target script structure, which can be specifically implemented as follows: the video generation module using artificial intelligence generates the oral copy of each storyboard based on the object description information and the target script structure; the video generation module using artificial intelligence generates the storyboard description information of each storyboard based on the oral copy of each storyboard. Among them, the video generation module of artificial intelligence can integrate the object description information into the script based on the provided object description information and the target script structure, and generate the oral copy of each storyboard that conforms to the script structure and the target object.

[0075] The video generation module of artificial intelligence 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.

[0076] In this way, high-quality script content can be generated efficiently, and the copywriting and visual effects in the script content can be closely integrated.

[0077] In some embodiments, the video generation module using artificial intelligence generates the oral copy of each storyboard based on the object description information and the target script structure, which can be specifically implemented as follows: obtaining the target script template and the target script requirements corresponding to the target script structure; generating the first prompt word according to the first prompt template based on the object description information, the target script template and the target script requirements; inputting the first prompt word into the video generation module of artificial intelligence, so as to generate the oral copy of each storyboard based on the object description information, the target script template and the script requirements by using the video generation module of artificial intelligence. Among them, the target script template can 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 the corresponding script content. For example, the target script template can be generated by reverse parsing other popular promotional videos that have been generated. Thus, by generating the script content according to the target script template generated by reverse parsing other popular promotional videos, the script structure, script style, etc. can be imitated to improve the maturity and popularity of the generated script content. The target script requirements can be used to indicate the length, style, target audience, content requirements, format requirements, etc. of the script expected to be generated based on the target script structure. The first prompt template can be a predefined framework or structure for guiding and standardizing the content input into the video generation module of the artificial intelligence. In an embodiment of the present application, the first prompt template may include, for example, elements such as script structure, target audience, copy length, format requirements, language and tone, and specific requirements. The first prompt word can be generated by filling the object description information, the target script template, and the target script requirements into the corresponding elements of the first prompt template.

[0078] By inputting the first prompt word into the video generation module of artificial intelligence, the video generation module of artificial intelligence can generate the spoken text for each storyboard based on the object description information, with reference to the target script template and in accordance with the script requirements.

[0079] In some embodiments, a digital human screen in which a digital human broadcasts the spoken audio can also be generated based on the spoken audio of each storyboard. Wherein, a digital human (Digital Human or Virtual Human) can be a computer-generated character with a human-like appearance, behavior and communication ability. The digital human can be two-dimensional or three-dimensional and can be created through computer graphics (CGI) and artificial intelligence technology. The digital human screen can be used to show the facial movements of the digital human that match the spoken audio, such as facial expressions and lip shape.

[0080] In some embodiments, the spoken audio of each storyboard and the corresponding target material video are synthesized into the target storyboard video, which can be specifically realized as follows: the spoken audio of each storyboard is synthesized into a digital human video with the digital human screen; when the target material video exists in any storyboard, the digital human video and the target material video are synthesized into the target storyboard video; when the target material video does not exist in any storyboard, the digital human video is used as the target storyboard video. After the spoken audio and the digital human screen are synthesized into the digital human video, the digital human can broadcast the spoken audio according to the facial movements that match the spoken audio, and use the corresponding timbre, intonation and emotional expression, so that the visual and auditory elements of the digital human video are coordinated. When the target material video exists in any storyboard, the digital human video can be added to the upper layer of 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. 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.

[0081] In some embodiments, digital person selection prompt information of multiple digital persons may also be obtained; according to the digital person selection request sent by the first user, the target digital person selected by the user is determined. The digital person selection prompt information may include a brief introduction, characteristics, appearance and other information of each digital person among the multiple digital persons. Thus, after receiving the digital person selection prompt information, the first user may send a digital person selection request according to preference or specific purpose. The digital person selection request may include identification information of the digital person selected by the first user. The video processing application may respond to the digital person selection request, and may determine the target digital person selected by the first user according to the information in the digital person selection request.

[0082] In some embodiments, based on the spoken audio of each storyboard, generating a digital human screen of a digital human broadcasting the spoken audio can be specifically implemented as follows: based on the spoken audio, generating the lip shape features of the target digital human; synthesizing the lip shape features into the digital human model corresponding to the target digital human, and generating the digital human screen. The video processing application can analyze the spoken audio to determine the rhythm, intonation and pronunciation of the speech, thereby generating lip shape features synchronized with the audio. The lip shape features can include, for example, the opening and closing of the lips, the position of the tongue, and possible accompanying facial expressions.

[0083] 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 (i.e., the artificial intelligence-based video generation module mentioned in this embodiment) 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 video processing application 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 by 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.

[0084] In some embodiments, synthesizing the digital human video and the target material video into the target storyboard video may be specifically implemented by replacing the background image in the digital human video with the material image of the target material video to generate the target storyboard video.

[0085] In some embodiments, at least one object video input by the first user can also be obtained; each object video is segmented according to the content similarity to obtain multiple segmented videos; the multiple segmented videos are converted into video features respectively using an artificial intelligence video generation module; the multiple segmented videos are respectively used as material videos, and are saved in the material library in correspondence with their respective video features and the object type corresponding to the object video. Among them, the object video can be a video associated with the target object shot by the user himself, generated by specific software, or downloaded from the Internet. The object video may be long in length, and multiple different themes may be displayed in the object video. Therefore, in order to increase the number and richness of material videos when generating promotional videos, the object videos provided by the user can be split. By splitting the object video, a longer object video can be divided into multiple shorter material videos according to different themes or contents.

[0086] The video processing application can determine the splitting positions of the object video by identifying key frames, scene changes or other important content points in the object video, and split the object video at each splitting position to obtain multiple segmented videos.

[0087] In one possible implementation, the video processing application may perform frame extraction processing on the object video to extract a series of individual video frames from the object video. The video processing application may 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 may be performed, for example, by pixel comparison, feature vector matching, or the output of a deep learning model. Based on the similarity result calculated, the video processing application may determine the splitting point of the object video, i.e., the key frame. The splitting point may be located at a position where the similarity drops significantly, which may indicate that the video content is changing or transitioning to a new scene, so that the video processing application may split the object video into multiple segmented videos on these key frames, each of which may contain a series of visually similar continuous frames, so that the consistency of the content of each segmented video may be ensured. In addition, when performing segmentation processing, the video processing application may 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 is a slight visual change.

[0088] 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:

[0089] Performing feature extraction processing on the storyboard description information to generate storyboard description features;

[0090] 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.

[0091] The video processing application 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.

[0092] After generating the storyboard description feature vector, the video processing application 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 video processing application can quantify the degree of match between each video material and a specific storyboard.

[0093] When matching video materials, the video processing application 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.

[0094] The specific selection method of the target playback platform and the target information retention mini program template is not limited in the embodiments of the present application. In some exemplary embodiments, the target playback platform and the target information retention mini program template can be selected from multiple candidate playback platforms and multiple candidate information retention mini program templates based on the following two implementation methods:

[0095] Implementation method 1: displaying an information configuration interface to the first user, displaying multiple candidate playback platforms and multiple candidate retention app templates on the information configuration interface, such as Figure 4a Among them, displaying each candidate retention mini program template can be understood as displaying the interface thumbnail of the retention mini program corresponding to each candidate retention mini program template.

[0096] In response to the first selection operation of the first user, a candidate playback platform selected from multiple candidate playback platforms is determined as the target playback platform; in response to the second selection operation of the first user, a candidate retention mini program template selected from multiple candidate retention mini program templates is determined as the target retention mini program template.

[0097] Implementation method 2: Figure 4b As shown, a first information configuration interface is displayed to a first user, and multiple candidate playback platforms are displayed on the first information configuration interface; in response to a first selection operation, a candidate playback platform selected from the multiple candidate playback platforms is determined as a target playback platform. A second information configuration interface is displayed to the first user; multiple candidate retention mini program templates are displayed on the second information configuration interface; in response to a second selection operation, a candidate retention mini program template selected from the multiple candidate retention mini program templates is determined as a target retention mini program template.

[0098] Implementation method three: determine the target playback platform from multiple candidate playback platforms based on the performance indicator information of multiple candidate playback platforms. Among them, the performance indicator information may include one of the following: network delay information, server load information, traffic information used to promote the target object in the historical period, and historical popularity information of the target object in the historical period. Among them, the traffic information used to promote the target object in the historical period refers to: the traffic indicator data related to the target object counted by the candidate playback platform in the historical period, which may include one of the following: number of views, number of interactions or user engagement, etc. Among them, the historical popularity information of the target object in the historical period refers to the popularity of the target object in the historical period, which can be obtained by comprehensive calculation based on the likes data, comment data, and forwarding data of the target object on the candidate playback platform.

[0099] Among them, based on the network delay information of multiple candidate playback platforms, the candidate playback platform whose network delay meets the preset delay condition can be selected as the target playback platform; based on the server load information of multiple candidate playback platforms, the candidate playback platform whose server load meets the preset load condition can be selected as the target playback platform; based on the traffic information of multiple candidate playback platforms used to promote target objects in a historical period, the candidate playback platform whose traffic used to promote target objects in a historical period meets the preset traffic condition can be selected as the target playback platform; based on the historical heat information of the target objects of multiple candidate playback platforms in a historical period, the candidate playback platform whose historical heat meets the preset heat condition can be selected as the target playback platform.

[0100] In this implementation, the target business type corresponding to the target object can be determined based on the object description information. Among them, the object description information can be semantically understood based on the semantic understanding module of artificial intelligence to obtain the target business type corresponding to the target object. Furthermore, the target retention applet template corresponding to the target business type can be selected from multiple candidate retention applet templates.

[0101] Through the above-mentioned implementation modes one to three, a method for manual selection by users and a method for automatic selection by video processing applications are provided, which can more accurately select a target playback platform and a target information retention mini-program template from multiple candidate playback platforms and multiple candidate information retention mini-program templates.

[0102] In some optional embodiments, the video processing application may also generate an initial descriptive text of the promotional video based on the object description information. The initial descriptive text may be used to summarize the content of the promotional video and may include at least one of a copy and a title. When generating the initial descriptive text of the promotional video based on the object description information, the semantic understanding module of artificial intelligence may be used to perform semantic understanding on the object description information, and a preset sentence template may be used to perform a corresponding summary description based on the result of the semantic understanding to obtain the initial descriptive text. The video editing interface is displayed to the first user, such as Figure 5 As shown, the first setting area in the video editing interface can be used for the first user to preview the initial descriptive text of the promotional video, and the second setting area can display the descriptive text editing control. The number of the descriptive text editing controls can be one or more, and the descriptive text editing controls include but are not limited to at least one of the following: a font editing control and a text modification control.

[0103] In response to the first user's editing operation on the descriptive text editing control, the initial descriptive text is updated to the target descriptive text, and sent to the target playback platform to be displayed together with the promotional video on the video playback page. The target descriptive text refers to the descriptive text edited by the first user.

[0104] In this way, the copy and title of the promotional video can be generated more accurately and displayed together with the promotional video, so that the second user can understand the general content of the promotional video more efficiently.

[0105] In some optional implementations, the target playback platform may provide a video transmission interface for the video processing application, and the video processing may perform corresponding data transmission based on the video transmission interface. Based on this, when the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target mini-program template are sent to the target playback platform, a preview interface may be displayed to the first user, and the preview interface includes: a video preview window, a video editing control, and a sharing control.

[0106] Figure 6 An optional implementation of the preview interface is shown, and the specific implementation of the preview interface is not limited. Specifically, the relative position relationship between the video preview window, the video editing control, and the sharing control is not limited. Among them, the number of video editing controls can be one or more, and different video editing controls can correspond to different video editing functions. For example, video editing control 1 can be used to change the resolution of the promotional video, video editing control 2 can be used to change the video size of the promotional video, video editing control 3 can be used to change the format of the promotional video, and so on. In response to the first user's editing operation on the video editing control, the video parameters of the promotional video can be edited, wherein the video parameters include but are not limited to format, size and resolution. Among them, the video preview window can be used for the first user to preview the results of the editing operation.

[0107] The sharing control can be bound to a call event for the video transmission interface, and the call event may include: detecting that the sharing control is manually triggered, receiving a target voice command, or the arrival of a preset call cycle. When the call event is triggered, the video transmission interface can be called in response to the triggering of the call event, and the device identifier of the terminal device, the promotional video, and the mini program identifier corresponding to the target mini program template can be sent to the target playback platform.

[0108] In this way, the preview interface can be used for the first user to perform rich video editing before publishing the promotional video, and the video can be quickly published based on the sharing control.

[0109] In addition to the above-mentioned video publishing method applied to video processing applications, the embodiment of the present application also provides a video publishing method, which is applied to a target playback platform, and the target playback platform is pre-installed with a mini-program shell. Figure 7 As shown, the method comprises the following steps:

[0110] Step 71: Receive a promotional video of a target object and an identifier of the terminal device sent by a terminal device of a first user; the promotional video is generated according to the object description information of the target object and the type of video script.

[0111] Step 72: Determine the mini program identifier that matches the promotional video, and integrate the mini program code corresponding to the mini program identifier into the mini program shell to obtain the target mini program.

[0112] Step 73: Bind the target mini program to the promotional video for publishing, and bind the target mini program to the device identifier of the terminal device to collect the information left by the second user who watches the promotional video and feed it back to the terminal device.

[0113] In some optional embodiments, when determining the mini program identifier that is compatible with the promotional video and integrating the mini program code corresponding to the mini program identifier into the mini program shell to obtain the target mini program, it can be implemented based on the following two implementation methods:

[0114] Implementation method one: receive the mini-program identifier corresponding to the target mini-program template sent by the terminal device. Considering that a target playback platform is usually configured with multiple mini-programs, there is a corresponding relationship between the mini-program shells in the multiple mini-programs and the terminal device; therefore, the mini-program shell corresponding to the identifier of the terminal device can be determined from the multiple mini-programs according to the identifier of the terminal device. The target playback platform can maintain a code resource library locally, which may include mini-program codes corresponding to different mini-programs. Therefore, the mini-program code corresponding to the mini-program identifier can be determined from the local code resource library, and the mini-program code corresponding to the mini-program identifier can be integrated into the mini-program shell to obtain the target mini-program. Among them, the mini-program code can be loaded into the corresponding position in the code storage space in the mini-program shell to complete the code integration. In other words, since the mini-program shell can provide an operating environment for the mini-program code, the mini-program code can be loaded into the operating environment in the mini-program shell to obtain the target mini-program.

[0115] Implementation method 2: determine the mini-program shell corresponding to the identifier of the terminal device from multiple mini-programs; display a configuration interface to a third user, the configuration interface including: multiple mini-program templates and code editing controls. The third user refers to a user with management authority on the target playback platform. In an actual scenario, after the first user logs in to the target playback platform and obtains the corresponding management authority, the first user with management authority can serve as the third user. In addition, the third user can also be an administrator on the target playback platform, which is not limited in this embodiment.

[0116] In response to a third user's selection operation on multiple mini-program templates, the mini-program code of the selected target mini-program template is displayed. Figure 8 An optional implementation method of the configuration interface is exemplarily shown, and multiple mini-program templates and code editing controls can be displayed on the configuration interface. When a third user selects a target mini-program template from multiple mini-program templates, the mini-program code corresponding to the target mini-program template can be determined as a mini-program identifier adapted to the promotional video in response to the selection operation. The mini-program code corresponding to the mini-program identifier in the code resource library is displayed in the display area. Afterwards, the third user can perform corresponding editing operations on the mini-program code by triggering the code editing control; correspondingly, in response to the third user's editing operation on the code editing control, the edited mini-program code can be integrated into the mini-program shell to obtain the target mini-program.

[0117] Through the above implementation, the mini program identifier that is compatible with the promotional video can be determined more accurately, and the mini program code corresponding to the mini program identifier can be integrated into the mini program shell to obtain the target mini program.

[0118] In this embodiment, the video processing application can generate a promotional video for the target object based on the object description information and the video script type; select a target playback platform and a target retention information mini-program template from multiple candidate playback platforms and multiple candidate retention information mini-program templates; the target playback platform can integrate the mini-program code corresponding to the mini-program identifier into the mini-program shell to obtain the target mini-program, thereby mounting the target mini-program on the promotional video. The target mini-program is bound to the device identifier of the terminal device to collect the retention information of the second user who watches the promotional video and feed it back to the terminal device. In this way, the playback platform and mini-program template can be determined more accurately, and the target mini-program can be mounted on the playback platform based on the mini-program template to more accurately collect the retention information, thereby more efficiently generating and publishing promotional videos.

[0119] In the above embodiments and the following embodiments, the video processing application can integrate multiple services together to provide a one-stop service for the first user, so that the first user can easily obtain various services required on the same video processing application. The one-stop service provided by the video processing application includes but is not limited to video generation service, video publishing service, video sharing service, video live broadcast service, user information collection service, information management service, video data management service and service refund service.

[0120] In this embodiment, the video processing application can provide the first user with a login / registration function, and in response to various preset login trigger operations, a login page can be displayed to the first user, and the login page can support the login operation in the form of "mobile phone number + verification code". The preset login trigger operation may include but is not limited to the rights viewing operation, rights purchase operation, and information viewing operation.

[0121] In the logged-in state, the video processing application can display a variety of rights introductions and rights purchase entrances on the homepage. The first user can purchase the corresponding rights through the rights purchase entrance, and after purchasing the rights, he can enjoy the services corresponding to the rights. Different rights can correspond to different services. For example, right one can correspond to video generation services and video publishing services, right two can correspond to live video services, and right three can correspond to user information collection services and information management services for potential users. Of course, these are only exemplary and not limited to this. In addition, if the merchant no longer needs the services corresponding to the purchased rights, he can submit a refund application for the purchased rights, and the video processing application will refund the merchant according to the refund rules corresponding to the rights.

[0122] The video generation service and the video publishing service have been described in detail in the previous embodiments and will not be repeated here.

[0123] For the video sharing service, the first user can share the promotional video generated for himself by the video processing application with other merchants, and can obtain corresponding sharing rewards after successful sharing.

[0124] For the live video service, the video processing application can create a live broadcast based on the promotional video generated for the first user and broadcast it live on the video playback platform.

[0125] For user information collection services and information management services, after the promotional video is posted on the video playback platform, or when the promotional video is broadcast live on the video playback platform, the comment area corresponding to the promotional video or the bullet screen area corresponding to the live broadcast can be monitored. If new comment content is detected in the comment area / bullet screen area, reply content is constructed for the comment content according to the preset guidance template to guide the first user who posted the comment content to initiate a private chat request for the first user. In the case where the first user is detected to initiate a private chat request for the first user, the private chat content of the first user is generated according to the preset information collection template, and the private chat content is sent to the video playback platform to display the private chat content in the private chat window corresponding to the first user in the form of a dialogue; if the user information input by the first user collected from the video playback platform contains a specified information field, the first user is determined to be a potential user, and the user information corresponding to the first user is added to the potential user information library for the first user to view.

[0126] For video data management services, the video processing application can provide a data display interface to the first user to display the playback data of the promoted video to the first user through the data display interface. The playback data includes but is not limited to: the number of likes and shares today, the number of comments on each video playback platform, the number of private messages on each video playback platform, the amount of user information collected, etc.

[0127] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 11 to 14 can be device A; for another example, the execution subject of steps 11 to 12 can be device A, and the execution subject of steps 13 to 14 can be device B; and so on.

[0128] In addition, in some of the processes described in the above embodiments and the accompanying drawings, multiple operations appearing 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 document or may be executed in parallel, and the sequence numbers of the operations, such as 11, 12, etc., are only used to distinguish between different operations, and the sequence 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.

[0129] It should be noted that the descriptions such as “first” and “second” in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit “first” and “second” to different types.

[0130] Fig. 9 is a schematic diagram of the structure of a terminal device provided by an exemplary embodiment of the present application. The terminal device is applicable to the video publishing method provided by the aforementioned embodiment. Fig. 9 As shown, the terminal device may include: a memory 901, a processor 902 and a communication component 903.

[0131] The memory 901 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phone book data, messages, pictures, videos, etc.

[0132] Processor 902 is coupled to memory 901 and is used to execute a computer program in memory 901, so as to: obtain object description information and a video script type of a target object; generate a promotional video for the target object according to the object description information and the video script type; select a target playback platform and a target information retention mini-program template from a plurality of candidate playback platforms and a plurality of candidate information retention mini-program templates respectively; different information retention mini-program templates correspond to different business types and mini-program identifiers; send the device identifier of the terminal device, the promotional video and the mini-program identifier corresponding to the target information retention mini-program template to the target playback platform, so that the target playback platform can publish the promotional video; wherein the published promotional video is mounted with a target mini-program, and the target mini-program is obtained by the target playback platform integrating the mini-program code corresponding to the mini-program identifier into a preset mini-program shell, and the target mini-program is bound to the device identifier of the terminal device, so as to collect the information retention information of a second user who watches the promotional video, and feed it back to the terminal device.

[0133] Optionally, when the processor 902 obtains the object description information and the video script type of the target object, it is specifically used to: display the information collection interface provided by the video processing application, respond to the information input operation on the information collection interface, and obtain the object description information and the video script type of the target object.

[0134] Optionally, the processor 902 displays the information collection interface provided by the video processing application, and responds to the information input operation on the information collection interface to obtain the object description information of the target object and the video script type, and is specifically used to: display the entry selection interface to the first user, the entry selection interface including: an entry selection control and an entry confirmation control; respond to the first user's trigger operation on the entry selection control, select at least one keyword from multiple keywords; respond to the first user's trigger operation on the entry confirmation control, generate the object description information according to the at least one keyword, and jump from the entry selection interface to the script selection interface, the script selection interface including: multiple candidate script types and a type confirmation control; respond to the first user's trigger operation on the type confirmation control, determine the video script type from the multiple candidate script types; or, display the picture upload interface provided by the video processing application, respond to the image upload operation on the picture upload interface, and obtain a multi-view image of the target object; use an artificial intelligence-based image understanding module to extract semantic information from the multi-view image of the target object, and generate the object description information and the video script type according to the semantic information.

[0135] Optionally, when the processor 902 generates a promotional video for the target object based on the object description information and the video script type, it is specifically used to: determine the script structure corresponding to the video script type; the script structure includes multiple storyboards; using an artificial intelligence-based video generation module to generate script content for each storyboard based on the object description information and the script structure; the script content includes spoken text and storyboard description information; the storyboard description information is used to describe the screen content of the storyboard; converting the spoken text corresponding to each storyboard into spoken audio, and obtaining a material video matching the target object according to the storyboard description information of each storyboard; generating a storyboard video for each storyboard according to the spoken audio and material video of each storyboard; and synthesizing the storyboard videos of multiple storyboards according to the script structure to obtain a promotional video for the target object.

[0136] Optionally, when the processor 902 selects a target playback platform and a target information retention mini-program template from multiple candidate playback platforms and multiple candidate information retention mini-program templates, it is specifically used to: display an information configuration interface to the first user, and display multiple candidate playback platforms and multiple candidate information retention mini-program templates on the information configuration interface; respond to a first selection operation, and determine the candidate playback platform selected from the multiple candidate playback platforms as the target playback platform; respond to a second selection operation, and determine the candidate information retention mini-program template selected from the multiple candidate information retention mini-program templates as the target information retention mini-program template.

[0137] Optionally, when the processor 902 selects a target playback platform and a target information retention mini-program template from multiple candidate playback platforms and multiple candidate information retention mini-program templates, it is specifically used to: determine the target playback platform from the multiple candidate playback platforms based on performance indicator information of the multiple candidate playback platforms; the performance indicator information includes: network delay information, server load information, traffic information used to promote the target object in a historical period and / or historical popularity information of the target object; determine the target business type corresponding to the target object based on the object description information; select the target information retention mini-program template corresponding to the target business type from the multiple candidate information retention mini-program templates.

[0138] Optionally, processor 902 is also used to: generate initial descriptive text of the promotional video based on the object description information, the initial descriptive text is used to summarize the content of the promotional video, including: copy and / or title; display a video editing interface to the first user, the first setting area in the video editing interface is used for the first user to preview the initial descriptive text of the promotional video, and the second setting area displays a descriptive text editing control; in response to the first user's editing operation on the descriptive text editing control, update the initial descriptive text to the target descriptive text, and send it to the target playback platform to be displayed together with the promotional video on the video playback page.

[0139] Optionally, the target playback platform provides a video transmission interface for the video processing application; when the processor 902 sends the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target mini-program template to the target playback platform, it is specifically used to: display a preview interface to the first user, the preview interface including: a video preview window, a video editing control, and a sharing control; in response to the first user's editing operation on the video editing control, edit the video parameters of the promotional video; the video preview window is used for the first user to preview the result of the editing operation; the sharing control is bound to a call event to the video transmission interface; the call event includes: detecting that the sharing control is manually triggered, receiving a target voice command, or the arrival of a preset call cycle; in response to the triggering of the call event, calling the video transmission interface, and sending the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target mini-program template to the target playback platform.

[0140] Optionally, the terminal device may further include: a display component 904 and a power supply component 905 . Fig. 9 Only some components are shown schematically, which does not mean that the terminal equipment only includes Fig. 9 Components shown.

[0141] The above-mentioned display component includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0142] The power supply assembly provides power to various components of the device where the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply assembly is located.

[0143] Accordingly, an embodiment of the present application also provides a computer-readable storage medium storing a computer program, which, when executed, can implement the steps that can be executed by the terminal device in the above method embodiment.

[0144] In this embodiment, the video processing application can generate a promotional video for the target object based on the object description information and the video script type; select a target playback platform and a target retention information mini-program template from multiple candidate playback platforms and multiple candidate retention information mini-program templates; the target playback platform can integrate the mini-program code corresponding to the mini-program identifier into the mini-program shell to obtain the target mini-program, thereby mounting the target mini-program on the promotional video. The target mini-program is bound to the device identifier of the terminal device to collect the retention information of the second user who watches the promotional video and feed it back to the terminal device. In this way, the playback platform and mini-program template can be determined more accurately, and the target mini-program can be mounted on the playback platform based on the mini-program template to more accurately collect the retention information, thereby more efficiently generating and publishing promotional videos.

[0145] Above Fig. 9 The memory 901 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 storage, flash memory, magnetic disk or optical disk.

[0146] Above Fig. 9The communication component 903 in is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component can be implemented based on near field communication (NFC) technology, radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0147] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0148] The present invention is described with reference to the flowchart and / or block diagram of the method, device (system), and computer program product according to the embodiment of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the process and / or box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0149] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0150] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0151] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0152] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0153] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0154] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0155] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A video publishing method, characterized in that: A video processing application applied to a terminal device of a first user; the method comprising: Obtain object description information of the target object and the video script type; Generate a promotional video for the target object according to the object description information and the video script type; Select a target broadcasting platform and a target retention mini program template from multiple candidate broadcasting platforms and multiple candidate retention mini program templates respectively; different retention mini program templates correspond to different business types and mini program identifiers; Sending the device identification of the terminal device, the promotional video, and the mini-program identification corresponding to the target information retention mini-program template to the target playback platform, so that the target playback platform can publish the promotional video; Among them, the released promotional video is mounted with a target mini-program, and the target mini-program is obtained by the target playback platform integrating the mini-program code corresponding to the mini-program identifier into a preset mini-program shell. The target mini-program is bound to the device identifier of the terminal device, and is used to collect the information left by the second user who watches the promotional video and feed it back to the terminal device.

2. The method according to claim 1, characterized in that Get the object description information and video script type of the target object, including: Display the information collection interface provided by the video processing application, respond to the information input operation on the information collection interface, and obtain the object description information and video script type of the target object.

3. The method according to claim 2, characterized in that Displaying the information collection interface provided by the video processing application, responding to the information input operation on the information collection interface, obtaining the object description information of the target object and the video script type, including: Displaying a term selection interface to the first user, the term selection interface comprising: a term selection control and a term confirmation control; In response to a triggering operation of the first user on the entry selection control, selecting at least one keyword from a plurality of keywords; In response to the triggering operation of the first user on the entry confirmation control, the object description information is generated according to the at least one keyword, and the script selection interface is jumped from the entry selection interface to the script selection interface, wherein the script selection interface includes: a plurality of candidate script types and a type confirmation control; In response to the triggering operation of the first user on the type confirmation control, determining the video script type from the multiple candidate script types; or, Display an image upload interface provided by the video processing application, respond to the image upload operation on the image upload interface, and obtain a multi-view image of the target object; use an artificial intelligence-based image understanding module to extract semantic information from the multi-view image of the target object, and generate the object description information and the video script type based on the semantic information.

4. The method according to claim 1, characterized in that: Generate a promotional video for the target object according to the object description information and the video script type, including: Determine a script structure corresponding to the video script type; the script structure includes a plurality of storyboards; Using an artificial intelligence-based video generation module, based on the object description information and the script structure, the script content of each storyboard is generated; the script content includes a spoken copy and storyboard description information; the storyboard description information is used to describe the screen content of the storyboard; Convert the spoken text corresponding to each storyboard into spoken audio, and obtain a material video matching the target object according to the storyboard description information of each storyboard; generate a storyboard video of each storyboard according to the spoken audio and material video of each storyboard; According to the script structure, the storyboard videos of multiple storyboards are synthesized to obtain a promotional video for the target object.

5. The method according to claim 1, characterized in that Select a target broadcasting platform and a target retention mini program template from multiple candidate broadcasting platforms and multiple candidate retention mini program templates, including: Displaying an information configuration interface to the first user, displaying multiple candidate playback platforms and multiple candidate retention mini-program templates on the information configuration interface; In response to a first selection operation, determining a selected candidate playback platform from the plurality of candidate playback platforms as the target playback platform; In response to the second selection operation, a candidate resource retention mini-program template selected from the plurality of candidate resource retention mini-program templates is determined as the target resource retention mini-program template.

6. The method according to claim 1, characterized in that Select a target broadcasting platform and a target retention mini program template from multiple candidate broadcasting platforms and multiple candidate retention mini program templates, including: Determine the target playback platform from the multiple candidate playback platforms according to performance indicator information of the multiple candidate playback platforms; the performance indicator information includes: network delay information, server load information, traffic information used to promote the target object in a historical period, and / or historical popularity information of the target object; Determine the target service type corresponding to the target object according to the object description information; A target information retention mini-program template corresponding to the target business type is selected from the multiple candidate information retention mini-program templates.

7. The method according to claim 1, characterized in that Also includes: Generating an initial descriptive text of the promotional video according to the object description information, wherein the initial descriptive text is used to summarize the content of the promotional video, including: copywriting and / or title; Displaying a video editing interface to the first user, wherein a first setting area in the video editing interface is used for the first user to preview an initial descriptive text of the promotional video, and a second setting area displays a descriptive text editing control; In response to the first user's editing operation on the descriptive text editing control, the initial descriptive text is updated to the target descriptive text and sent to the target playback platform to be displayed together with the promotional video on the video playback page.

8. The method according to any one of claims 1 to 7, characterized in that: The target playback platform provides a video transmission interface for the video processing application; sending the device identifier of the terminal device, the promotional video, and the mini-program identifier corresponding to the target mini-program template to the target playback platform, including: Displaying a preview interface to the first user, the preview interface comprising: a video preview window, a video editing control, and a sharing control; In response to the first user's editing operation on the video editing control, the video parameters of the promotional video are edited; the video preview window is used for the first user to preview the result of the editing operation; the sharing control is bound to a call event of the video transmission interface; the call event includes: detecting that the sharing control is manually triggered, receiving a target voice command, or a preset call cycle has arrived; In response to the triggering of the calling event, the video transmission interface is called to send the device identification of the terminal device, the promotional video and the mini-program identification corresponding to the target mini-program template to the target playback platform.

9. A video publishing method, characterized in that: Applied to a target playback platform, the target playback platform is pre-installed with a mini-program shell; the method comprises: Receiving a promotional video of a target object and an identifier of the terminal device sent by a terminal device of a first user; the promotional video is generated according to the object description information of the target object and the type of video script; Determine a mini program identifier that is compatible with the promotional video, and integrate the mini program code corresponding to the mini program identifier into the mini program shell to obtain a target mini program; The target applet is bound to the promotional video for publishing, and the target applet is bound to the device identifier of the terminal device to collect the information left by the second user who watches the promotional video and feed it back to the terminal device.

10. The method according to claim 9, characterized in that Determining a mini program identifier that is compatible with the promotional video, and integrating a mini program code corresponding to the mini program identifier into the mini program shell to obtain a target mini program, including: Receiving a mini-program identifier corresponding to a target mini-program template sent by the terminal device; determining a mini-program shell corresponding to the identifier of the terminal device from a plurality of mini-programs; integrating the mini-program code corresponding to the mini-program identifier in a local code resource library into the mini-program shell to obtain the target mini-program; or, A configuration interface is displayed to a third user, wherein the configuration interface includes: multiple mini-program templates and a code editing control; a mini-program shell corresponding to the identifier of the terminal device is determined from the multiple mini-programs; in response to the third user's selection operation on the multiple mini-program templates, a mini-program identifier adapted to the promotional video is determined; the mini-program code corresponding to the mini-program identifier in the code resource library is displayed; in response to the third user's editing operation on the code editing control, the edited mini-program code is integrated into the mini-program shell to obtain the target mini-program.

11. An electronic device, characterized in that: include: A memory and a processor; the memory is used to store one or more computer instructions; the processor is used to execute the one or more computer instructions to: execute the steps in the method described in any one of claims 1-8 or claims 9-10.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is enabled to implement the steps of the method according to any one of claims 1 to 8 or claims 9 to 10.

13. A computer program product, characterized in that The method comprises a computer program / instruction, and when the computer program / instruction is executed by a processor, the steps in the method according to any one of claims 1 to 8 or claims 9 to 10 are performed.

Images