Video processing method and device, equipment and medium

Abstract

The embodiment of the invention relates to a video processing method and device, equipment and a medium, and the method comprises the steps: obtaining a target video template and an original material prompt word of the target video template in response to the selection operation of the target video template in a target scene, and enabling the target video template to be a video production format frame for the target scene; obtaining character features input for the target role; generating a target material cue word based on the original material cue word; generating at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material cue word; and filling the at least one character material and the at least one scene material into the target video template to generate a target video. According to the embodiment of the invention, the user can generate the video only by selecting the video template and inputting the character features which want to play the role, and the video generation efficiency is effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a video processing method, device, equipment and medium. Background Art

[0002] With the development of video technology, video shooting has become an increasingly important part of people's lives. When shooting a video that includes a specific person, it is necessary to manually write the script, organize the offline shooting materials, and edit them into a film in the later stage. In related technologies, the efficiency can be improved by automating the shooting, editing and synthesis of video materials, but users are required to shoot offline in front of designated equipment, resulting in high costs and thresholds for video material shooting, and the script story production still needs to be done manually, which is inefficient. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a video processing method, device, equipment and medium.

[0004] The present disclosure provides a video processing method, the method comprising:

[0005] In response to a selection operation of a target video template under a target scene, the target video template and an original material prompt word of the target video template are acquired, wherein the target video template is a video production format framework for the target scene;

[0006] Obtaining character features input for the target character;

[0007] Generate target material prompt words based on the original material prompt words;

[0008] Based on the character features and the target material prompt words, generating at least one character material of the target role and at least one scene material of the target scene;

[0009] The at least one character material and the at least one scene material are filled into the target video template to generate a target video.

[0010] The present disclosure also provides a video processing device, the device comprising:

[0011] A first acquisition module is used to acquire the target video template and the original material prompt words of the target video template in response to the selection operation of the target video template under the target scene, wherein the target video template is a video production format framework for the target scene;

[0012] The second acquisition module is used to acquire the character features inputted for the target character;

[0013] A prompt word module, used for generating a target material prompt word based on the original material prompt word;

[0014] A material module, used for generating at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words;

[0015] The video module is used to fill the at least one character material and the at least one scene material into the target video template to generate a target video.

[0016] An embodiment of the present disclosure also provides an electronic device, which includes: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the video processing method provided by the embodiment of the present disclosure.

[0017] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the video processing method provided by the embodiment of the present disclosure.

[0018] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art: the video processing solution provided by the embodiments of the present disclosure, in response to a selection operation of a target video template under a target scene, obtains a target video template and original material prompt words of the target video template, wherein the target video template is a video production format framework for the target scene; obtains character features input for a target role; generates target material prompt words based on the original material prompt words; generates at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words; fills the at least one character material and the at least one scene material into the target video template to generate a target video. By adopting the above technical scheme, for the video template of the scene selected by the user, the video template and the corresponding original material prompt words can be obtained, and new target material prompt words can be generated and the character features input for the role selected by the user can be obtained. Based on the character features and the target material prompt words, the character material of the role and the scene material of the scene are generated. By filling the materials into the video template, a video of the user playing the role in the scene can be generated, thereby realizing the automatic generation of personalized material prompt words and corresponding character materials and scene materials for the current user. The material prompt words can include the script story, which reduces the cost and threshold of generating the script story and video material. The user can realize video generation by only selecting the video template and inputting the character features of the role he wants to play, thereby effectively improving the efficiency of video generation, and enriching the diversity, flexibility and playability of the video, and effectively improving the user's video generation experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 A schematic diagram of a flow chart of a video processing method provided by an embodiment of the present disclosure;

[0021] Figure 2 A schematic diagram of a first video generation page provided in an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of a second video generation page provided in an embodiment of the present disclosure;

[0023] Figure 4 A schematic diagram of a third video generation page provided in an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of a fourth video generation page provided in an embodiment of the present disclosure;

[0025] Figure 6 A schematic diagram of a fifth video generation page provided in an embodiment of the present disclosure;

[0026] Figure 7 A schematic diagram of a sixth video generation page provided in an embodiment of the present disclosure;

[0027] Figure 8 A schematic diagram of a seventh video generation page provided in an embodiment of the present disclosure;

[0028] Fig. 9 A schematic diagram of a video processing process provided by an embodiment of the present disclosure;

[0029] Fig.10 A schematic diagram of another video processing process provided by an embodiment of the present disclosure;

[0030] Fig.11 A schematic diagram of another video processing process provided by an embodiment of the present disclosure;

[0031] Fig.12 A schematic diagram of the structure of a video processing device provided by an embodiment of the present disclosure;

[0032] Fig.13 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0034] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0035] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0036] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0037] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0038] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0039] In order to solve the cost and efficiency problems of video processing in the related art, the embodiments of the present disclosure provide a video processing method, which is introduced below in conjunction with specific embodiments.

[0040] Figure 1 The flowchart of a video processing method provided by an embodiment of the present disclosure is shown in FIG. 1 , which can be executed by a video processing device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:

[0041] Step 101: In response to a selection operation of a target video template under a target scene, a target video template and original material prompt words of the target video template are obtained, wherein the target video template is a video production format framework for the target scene.

[0042] Among them, the video template can be a fixed video production format framework, which is used to quickly produce videos or generate videos. The video template may include at least one of the following: a cover image, background audio, multiple slots for filling materials, special effect materials corresponding to each slot, and transition materials between different slots, etc. The target video template can be the video template selected by the user for the current selection operation of one or more video templates in the target scene. The selection operation can be a gesture control operation such as clicking, long pressing, and double-clicking the target video template in the current page. The embodiment of the present disclosure does not limit this. The target scene can be a scene currently selected by the user. For example, the scene can include a tourist attraction, an exhibition venue, a sports venue, etc. The target scene can be, for example, a scenic spot in a tourist attraction.

[0043] The original material prompt words can be texts pre-generated by the target video template during the initial film production process, including script content such as story lines, character dialogues, action descriptions, scene settings, background descriptions, and instructions for interaction between characters. Each video template has a corresponding original material prompt word, and different video templates may include different numbers of characters, story lines, and other script content. The original material prompt words are used as the basis for the prompt words of the model to generate video materials for subsequent videos to be produced. In the disclosed embodiment, the video materials can include two types of character materials and scene materials. Character materials can be video clips related only to characters, and can include various characteristics of characters, such as head, limbs, voice, etc.; scene materials can be video clips related only to scenes, and scene materials are irrelevant to characters but strongly related to story lines.

[0044] Specifically, after receiving the user's selection operation on the target video template in the video generation page under the target scene, the video processing device can determine that the user wants to shoot related videos based on the target scene, and obtain the template data of the target video template and the original material prompt words of the target video template, which can be obtained from the server or locally, without limitation.

[0045] For example, Figure 2 A schematic diagram of a first video generation page provided in an embodiment of the present disclosure, such as Figure 2 As shown in the figure, an exemplary video generation page 200 for a target scene being a scenic spot A is shown. After a user triggers a control 201 for starting video generation in the video generation page 200, a video generation control 201 can be displayed. Figure 3Optionally, the video generation page 200 can also display the filming records of the A scenic spot, including the video being generated and the video that has been generated, so that the user can quickly view the historically generated videos.

[0046] For example, Figure 3 A schematic diagram of a second video generation page provided in an embodiment of the present disclosure, such as Figure 3 As shown in the figure, a video generation page 300 is shown, and the video generation page 300 displays multiple video templates for the target scene being scenic spot A, such as Figure 3 Five video templates are displayed. Different video templates have different names and the number of characters they include. When the user selects control 301 where template 2 is located in the figure, the video template corresponding to template 2 is the target video template, and the target video template and the corresponding original material prompt word can be obtained. Then the user triggers control 302 to start making the video corresponding to template 2. Control 302 includes a prompt word to start your story. When the user does not select a video template on this page, control 302 is set to be unselectable.

[0047] Step 102: Obtain character features input for the target character.

[0048] The target role may be a role currently selected by the user from the role indicated in the target video template, which may be regarded as the user wanting to play the target role. The number of target roles may be one or more, and is not limited to one or more. When there are multiple target roles, the user may input multiple character features to play multiple target roles. Character features may be features that can characterize the personalized characteristics of the user, and the character features may be the characteristic features of the character playing the target role. In the embodiment of the present disclosure, character features may include features such as head, limbs, voice, and clothing, which are only examples.

[0049] Specifically, the video processing device can determine the target role selected by the user based on the user's operation, and obtain the character features input by the user for the target role. For example, the image, audio, and character feature text input by the user can be determined as the character features. The character feature text describes the relevant features through text. When there are multiple target roles, the corresponding character features can be obtained for each target role.

[0050] In some embodiments, obtaining character features input for a target character may include: displaying an input control in response to a selection operation on the target character, wherein the number of target characters is at least one; obtaining an input target image and target audio in response to a trigger operation on the input control; and performing feature recognition on the target image and target audio to obtain visual features and voice features as character features for the target character.

[0051] Among them, the input control can be used as a functional control to support the user to input corresponding image, video, audio and other data for the target character. The target image is the image input for the target character, which can be the image of the current user or the image of other users, without specific limitation; the visual feature can be the feature of the visual dimension obtained by performing character-related feature recognition on the target image, for example, the visual feature can include the head, limbs, clothing, etc. of the character in the target image. The target audio can be the audio data input for the target character, which can be the audio data of the current user or the audio data of other users, without specific limitation; the voice feature can be the feature obtained by performing voice recognition on the target audio, for example, it can include voice, intonation, timbre, etc.

[0052] Specifically, the video processing device can display at least one role included in the target video template, and when receiving a user's selection operation on one of the target roles, it can display an input control, and after receiving a trigger operation on the input control, it can obtain the target image and target audio input by the user, and use a feature extraction model to perform feature recognition on the target image to obtain visual features, specifically, it can extract key point information to generate corresponding feature values, and use a speech recognition model to recognize the target audio to obtain speech features; the visual features and speech features are used as the characteristics of the character selected by the user to play the target role.

[0053] In the above scheme, for the role selected by the user in the video template, the input character-related image, audio and other information can be used as character features, or the character features can be obtained through feature recognition and extraction based on the input information to participate in the production of subsequent videos.

[0054] For example, Figure 4 A schematic diagram of a third video generation page provided in an embodiment of the present disclosure, such as Figure 4 As shown in the figure, Figure 3 In the video generation page 300, when the user triggers the control 302, the video generation page 400 is displayed. The three characters included in the A scenic spot template 2 (that is, the target video template) can be displayed in the video generation page 400, such as the characters A, B and C in the figure. After the user selects the character A, the initial avatar of the character A is represented as the target character by a rectangular frame selection, and the input control 401 for the character A is displayed. The input control 401 includes the prompt text "Click to upload". The user can input images and audios for the character A through the input control 401, and determine the characteristics of the person playing the character A through the input images and audios.

[0055] For example, Figure 5 A schematic diagram of a fourth video generation page provided in an embodiment of the present disclosure, such as Figure 5As shown, the figure shows a video generation page 500, in which the avatar of character A is switched from the initial avatar to an updated avatar representing the replacement of user uploaded data. The user can continue to select character C, and the initial avatar of character C is also represented as the target character by a rectangular selection. An input control 501 for character C is displayed, and the input control 501 includes a prompt text "Click to upload more character data". The user can upload image, audio and other data for character C by triggering the input control 502. In addition Figure 5 A control 502 may also be displayed, the control 502 including a prompt text “Okay! Just use these”, and when the user triggers the control 502, data uploading of the target character may be stopped.

[0056] For example, Figure 6 A schematic diagram of a fifth video generation page provided in an embodiment of the present disclosure, such as Figure 6 As shown, the figure shows a video generation page 600, in which the avatars of character A and character C are switched from initial avatars to updated avatars replaced by user uploaded data, indicating that the user wants to play these two characters, and the character features can be obtained based on the data input by the user.

[0057] Step 103: Generate target material prompt words based on the original material prompt words.

[0058] The target material prompt words may be new material prompt words generated by rewriting, optimizing, etc. the original material prompt words of the target video template, and the target material prompt words have the same story line as the original material prompt words, and at least part of other information is changed. The target material prompt words are used as prompt words of the model to generate video materials corresponding to the video currently being produced by the current user, and the video materials may include character materials and scene materials.

[0059] In some embodiments, generating target material prompt words based on original material prompt words may include: extracting rewriting prompt words from a prompt word library; inputting the rewriting prompt words and the original material prompt words into a text rewriting model to generate target material prompt words.

[0060] The prompt word library may include multiple rewriting prompt words, and the rewriting prompt words may be prompt words used to rewrite the original material prompt words of the video template in a certain dimension and direction. The rewriting dimensions and directions of different rewriting prompt words may be different. The embodiment of the present disclosure does not limit the number of rewriting prompt words. The text rewriting model may be a model used to rewrite the input text with the same meaning, and the specific model type is not limited.

[0061] Specifically, after obtaining the original material prompt word of the target video template, the video processing device can extract a rewritten prompt word from the prompt word library, for example, any one can be extracted or extracted in a preset order; then the rewritten prompt word and the original material prompt word can be input into the text rewriting model for calculation, and the target material prompt word can be output. In the above scheme, through the setting of the prompt word library and the rewriting operation of the original material prompt word each time a request is made, an original material prompt word can be rewritten into a corresponding new target material prompt word for different users, so as to achieve the effect of different prompt words for different users, avoid the high cost and low efficiency caused by manual rewriting, improve the efficiency of prompt word generation, and help improve the efficiency of subsequent video material generation.

[0062] The target material prompt words include at least one prompt word, each prompt word is used to generate character material or scene material, and each prompt word includes at least one of the following: picture description text, color style text, element detail text, dynamic effect text, and dubbing line text.

[0063] The target material prompt words may include script content. A script may include multiple scenes. A scene may be regarded as a large chapter of a story. The plot in the scene will have a relatively complete development. The target material prompt words may have corresponding prompt words for each scene. One prompt word may generate character material or scene material for one scene. Each scene may include character material and / or scene material. And each prompt word may include at least one of a picture description text, a color style text, an element detail text, a dynamic effect text, a dubbing line text, etc. The picture description text may be a text describing the main body of the picture, the color style text may be a text describing the hue, color, visual style, etc., the element detail text may be a text describing the details of the multiple elements included, the dynamic effect text may be a text describing the effects of the dynamic level of the included elements, and the dubbing line text may be a text describing the lines, mouth shape, time, etc. of the multiple characters included.

[0064] For example, a prompt word may be expressed as "Picture description text: A brave hero wearing shining armor, holding a sword, standing on a vast grassland. Color style text: The overall color tone is mainly red and gold, creating a brave and exciting atmosphere. The hero's armor and sword are shining with golden light, representing justice and strength. Element detail text: Behind the hero follows a loyal warhorse, which is clad in armor and looks majestic. There are some wild flowers growing on the grassland, and the flowers are swaying gently in the breeze. In the distant sky, a red sun is slowly rising. Dynamic effect text: The hero walks forward with firm steps, and the warhorse follows behind him. The breeze blows the hero's cloak, and the wild flowers dance in the wind. The light of the red sun becomes stronger and stronger, illuminating the entire grassland. Dubbing lines text: Character mouth shape: The character is telling a line: "Glory and mission!"; duration: 2 seconds", which is only an example and not a limitation.

[0065] Step 104: Generate at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words.

[0066] Among them, both character materials and scene materials are short video clips, for example, the duration is controlled within a few seconds. Character materials can be video clips related only to characters, and can include various features of characters, such as head, limbs, voice, etc. Scene materials can be video clips related only to scenes, which are irrelevant to characters but strongly related to the story line.

[0067] In the disclosed embodiment, after acquiring character features and generating target material prompt words, the video processing device can input the character features and the target material prompt words into the Wensheng video model, and output at least one character material of the target role that meets the character features and at least one scene material of the target scene.

[0068] The Vincent video model may be a model for generating a video that conforms to the text description according to the text description, and the prompt word may be context information generated by accurately converting the user demand into a form that the model can effectively understand and process, and the Vincent video model may generate a corresponding video for the prompt word of the target material. The video processing device inputs the character features and at least one prompt word in the prompt words of the target material into the Vincent video model, and for at least one character prompt word in the at least one prompt word, the model inference may be performed together with the character features to generate at least one character material that conforms to the character features, where the character prompt word refers to a prompt word that includes character information for generating character materials, for example, the generated character material has the same hair length and clothing style as the character features, and the target character's line audio in the generated character material is generated using the voice features in the character features; for at least one scene prompt word in the at least one prompt word, the corresponding scene material may be generated through model inference, where the scene prompt word refers to a prompt word that does not include character information for generating scene materials, and each scene material is related to the above-mentioned target scene, for example, a scene material is related to an area of ​​the target scene.

[0069] In some embodiments, the video processing method may further include: acquiring at least one prefabricated material of the target scene, and generating at least one scene material of the target scene based on the at least one prefabricated material and the scene prompt words in the target material prompt words.

[0070] The prefabricated material may be a scene material pre-shot for the target scene, and the number of prefabricated materials may include one or more. When the video processing device obtains at least one prefabricated material of the target scene, the scene prompt word in the prompt word of the target material may be input into the Wensheng video model, and the prefabricated material may be adjusted based on the scene prompt word to make it more consistent with the latest prompt word, and the corresponding at least one scene material may be generated, so that the generation of video materials is more diversified and flexible.

[0071] Optionally, the at least one character material and the at least one scene material may be reviewed through an audit model, and materials that fail the review may be deleted to ensure the accuracy and completeness of the materials.

[0072] Step 105: Fill at least one character material and at least one scene material into the target video template to generate a target video.

[0073] The target video template includes multiple slots, cover images, and background audio. The number of slots in the target video template has been determined, and each slot is used to fill in character materials or scene materials; the cover image can be an image pre-generated in the target video template and located at the front and most prominent position in the target video to be generated, and the background audio can be music played in the background of the target video to be generated, which is used to set off the atmosphere of the picture and create or strengthen specific emotions. The target video can be a video in which a virtual character that meets the character characteristics plays the target role in the target scene. When the target role includes multiple characters, the target video includes multiple virtual characters that meet the multiple character characteristics playing multiple target roles. The virtual character can be a digital character image close to the human image generated by the text video model based on the character characteristics.

[0074] After generating at least one character material of the target role and at least one scene material of the target scene, the video processing device can fill the at least one character material and the at least one scene material according to the slots set for each prompt word in the target material prompt words in the target video template to generate a target video, in which a virtual character that meets the character characteristics plays the target role, and during the playing process, the image of the virtual character is similar to the visual characteristics in the character characteristics and the voice of the virtual character is similar to the voice characteristics in the character characteristics.

[0075] For example, Figure 7 A schematic diagram of a sixth video generation page provided in an embodiment of the present disclosure, such as Figure 7 As shown in the figure, Figure 5 or Figure 6 Then, the video generation page 700 is performed during the process of generating the target video. In the video generation page 700, at least one character material and at least one scene material are filled in for the target video template of the A scenic spot template 2, and prompt texts of "generating" and "estimated to 2 minutes" are displayed to prompt the user.

[0076] For example, Figure 8 A schematic diagram of a seventh video generation page provided in an embodiment of the present disclosure, such as Figure 8 As shown, the figure shows a video generation page 800 after the target video is generated for the target video template of the A scenic spot template 2. The video generation page 800 displays a cover image 801 of the target video to indicate that the target video has been generated, and also displays function controls for sharing and downloading. The user can share and / or download the generated target video by triggering the corresponding function controls.

[0077] It is understandable that the above Figure 2-Figure 8 The video generation page is only an example of the page displayed to the user during the video generation process, and is not a limitation.

[0078] The video processing solution provided by the embodiment of the present disclosure obtains the target video template and the original material prompt words of the target video template in response to the selection operation of the target scene, wherein the target video template is a video production format framework for the target scene; obtains the character features input for the target role; generates the target material prompt words based on the original material prompt words; generates at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words; fills the at least one character material and the at least one scene material into the target video template to generate the target video. By adopting the above technical scheme, for the video template of the scene selected by the user, the video template and the corresponding original material prompt words can be obtained, and new target material prompt words can be generated and the character features input for the role selected by the user can be obtained. Based on the character features and the target material prompt words, the character material of the role and the scene material of the scene are generated. By filling the materials into the video template, a video of the user playing the role in the scene can be generated, thereby realizing the automatic generation of personalized material prompt words and corresponding character materials and scene materials for the current user. The material prompt words can include the script story, which reduces the cost and threshold of generating the script story and video material. The user can realize video generation by only selecting the video template and inputting the character features of the role he wants to play, thereby effectively improving the efficiency of video generation, and enriching the diversity, flexibility and playability of the video, and effectively improving the user's video generation experience.

[0079] Next, the video processing process of the embodiment of the present disclosure is further described by a specific example. Fig. 9 A schematic diagram of a video processing process provided by an embodiment of the present disclosure is shown in FIG. Fig. 9As shown, the figure shows the video processing process, which may specifically include: the user selects a target video template, selects a target role, uploads an image, and records audio on the client; the video processing device may call model 1, model 2, and an audio interface, and extracts visual features from the image through model 1 and model 2. Model 1 and model 2 may be two different models for extracting image features, and are not limited to specific ones; the audio interface calls the sound replication technology to extract voice features from the audio, and the extracted visual features and voice features are combined to obtain character features; the target material prompt words are generated based on the original material prompt words of the target video template and a rewritten prompt word extracted from the prompt word library; the target material prompt words and the character features are input into the Wensheng video model to generate a video material including at least one character material and at least one scene material; when generating the character material, the voice features extracted by the sound replication technology and the lines in the character prompt words in the target material prompt words can be used to generate the corresponding audio and picture to obtain a video clip, which is the character material; when generating the scene material, it can be obtained by adjusting the local prefabricated material or directly generated based on the scene prompt words in the target material prompt words; the video material is filled into the target video template to generate the target video; the client obtains the generated target video for display. The above-mentioned voice reproduction technology is a technology that can analyze and simulate the voice characteristics of a specific person, thereby generating new voice content so that it sounds like the original voice.

[0080] The video processing method of the embodiment of the present disclosure may be executed by the client, or by the client and the server together, depending on the actual situation.

[0081] For example, Fig.10 A schematic diagram of another video processing process provided by an embodiment of the present disclosure is shown as follows: Fig.10 As shown, the figure shows the video processing process based on multiple slots of the target video template, specifically including: generating target material prompt words based on the original material prompt words of the target video template; the visual features of the target image extracted by the feature extraction model and the speech features of the target audio extracted by the sound reproduction technology are input into the Wensheng video model together with the target material prompt words as character features, and the three character materials and four scene materials in the figure are output, which are filled into the 7 slots corresponding to the target video template to obtain the target video. The number of slots, arrangement method, and number of character materials and scene materials of the target video template in the figure are only examples, not limitations; the characters in the character materials in the figure meet the visual features of the target image, and the lines audio in the character materials meet the speech features of the target audio, so as to achieve the effect of imitating the voice and intonation of the target audio, and the scene materials are consistent with the description of the target scene in the target material prompt words.

[0082] For example, Fig.11A schematic diagram of another video processing process provided by an embodiment of the present disclosure is shown as follows: Fig.11 As shown in the figure, the original material prompt word of a video template is material prompt word 1, corresponding to video material 1, and video 1 is generated; after the current user's request, a new material prompt word 2 is generated based on material prompt word 1 for the same video template, and video material 2 is generated, and video 2 is obtained. The story line of material prompt word 1 and material prompt word 2 is the same but the details are different. The story line of video 1 and video 2 is the same but the details such as the picture and audio are different. It is realized that an original material prompt word is rewritten into a corresponding new target material prompt word for different users, so as to achieve the effect of different prompt words for different users.

[0083] In the above solution, a video processing solution is provided to automatically generate personalized material prompts and corresponding video materials for different users and then generate videos, reducing the script production cost of the video and the shooting cost and threshold of the video material, greatly improving the efficiency of script and video material generation. Users can generate videos by simply selecting a video template and entering the characteristics of the character they want to play, making the production of user videos more efficient, reducing production costs, and enriching video diversity and playability.

[0084] Fig.12 FIG. 1 is a schematic diagram of the structure of a video processing device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. Fig.12 As shown, the device comprises:

[0085] The first acquisition module 1201 is used to acquire the target video template and the original material prompt words of the target video template in response to the selection operation of the target video template in the target scene, wherein the target video template is a video production format framework for the target scene;

[0086] The second acquisition module 1202 is used to acquire the character features inputted for the target character;

[0087] A prompt word module 1203, configured to generate a target material prompt word based on the original material prompt word;

[0088] A material module 1204, configured to generate at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words;

[0089] The video module 1205 is used to fill the at least one character material and the at least one scene material into the target video template to generate a target video.

[0090] Optionally, the second obtaining module 1202 is used to:

[0091] In response to a selection operation on a target role, an input control is displayed, wherein the number of the target role is at least one;

[0092] In response to a trigger operation on the input control, acquiring an input target image and a target audio;

[0093] Feature recognition is performed on the target image and the target audio to obtain visual features and voice features as character features for the target character.

[0094] Optionally, the prompt word module 1203 is used to:

[0095] Extract rewriting prompt words from the prompt word library;

[0096] The rewriting prompt word and the original material prompt word are input into a text rewriting model to generate the target material prompt word.

[0097] Optionally, the material module 1204 is used to:

[0098] The character features and the target material prompt words are input into the Wensheng video model, and at least one character material of the target role and at least one scene material of the target scene that meet the character features are output.

[0099] Optionally, the device further includes a scene material module, which is used to:

[0100] At least one prefabricated material of the target scene is acquired, and at least one scene material of the target scene is generated based on the at least one prefabricated material and the scene prompt words in the target material prompt words.

[0101] Optionally, the target material prompt word includes at least one prompt word, each of the prompt word is used to generate the character material or the scene material, and each of the prompt word includes at least one of the following: picture description text, color style text, element detail text, dynamic effect text, and dubbing line text.

[0102] Optionally, the target video template includes multiple slots, a cover image, and background audio, and each slot is used to fill the character material or the scene material.

[0103] The video processing device provided in the embodiments of the present disclosure can execute the video processing method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0104] The embodiments of the present disclosure further provide a computer program product, including a computer program / instruction, which implements the video processing method provided by any embodiment of the present disclosure when executed by a processor.

[0105] Fig.13 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0106] The following specific reference Fig.13 , which shows a schematic diagram of the structure of an electronic device 1300 suitable for implementing the embodiment of the present disclosure. The electronic device 1300 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.13 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0107] like Fig.13 As shown, the electronic device 1300 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 1301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1302 or a program loaded from a storage device 1308 to a random access memory (RAM) 1303. In the RAM 1303, various programs and data required for the operation of the electronic device 1300 are also stored. The processing device 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0108] Typically, the following devices may be connected to the I / O interface 1305: an input device 1306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1309. The communication device 1309 may allow the electronic device 1300 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.13 The electronic device 1300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0109] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 1309, or installed from a storage device 1308, or installed from a ROM 1302. When the computer program is executed by the processing device 1301, the above-mentioned functions defined in the video processing method of the embodiment of the present disclosure are executed.

[0110] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0111] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0112] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0113] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: in response to a selection operation of a target video template under a target scene, obtains the target video template and the original material prompt words of the target video template, wherein the target video template is a video production format framework for the target scene; obtains character features input for a target role; generates target material prompt words based on the original material prompt words; generates at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words; fills the at least one character material and the at least one scene material into the target video template to generate a target video.

[0114] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0115] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0116] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0117] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0118] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0120] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0121] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0122] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A video processing method, characterized in that: include: In response to a selection operation of a target video template under a target scene, the target video template and an original material prompt word of the target video template are acquired, wherein the target video template is a video production format framework for the target scene; Obtaining character features input for the target character; Generate target material prompt words based on the original material prompt words; Based on the character features and the target material prompt words, generating at least one character material of the target role and at least one scene material of the target scene; The at least one character material and the at least one scene material are filled into the target video template to generate a target video.

2. The method according to claim 1, characterized in that The step of obtaining the character features inputted for the target character includes: In response to a selection operation on a target role, an input control is displayed, wherein the number of the target role is at least one; In response to a trigger operation on the input control, acquiring an input target image and a target audio; Feature recognition is performed on the target image and the target audio to obtain visual features and voice features as character features for the target character.

3. The method according to claim 1, characterized in that Generating a target material prompt word based on the original material prompt word includes: Extract rewriting prompt words from the prompt word library; The rewriting prompt word and the original material prompt word are input into a text rewriting model to generate the target material prompt word.

4. The method according to claim 1, characterized in that Generating at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words, including: The character features and the target material prompt words are input into the Wensheng video model, and at least one character material of the target role and at least one scene material of the target scene that meet the character features are output.

5. The method according to claim 1, characterized in that The method further comprises: At least one prefabricated material of the target scene is acquired, and at least one scene material of the target scene is generated based on the at least one prefabricated material and the scene prompt words in the target material prompt words.

6. The method according to any one of claims 1 to 5, characterized in that: The target material prompt word includes at least one prompt word, each of which is used to generate the character material or the scene material, and each of which includes at least one of the following: picture description text, color style text, element detail text, dynamic effect text, and dubbing line text.

7. The method according to claim 1, characterized in that The target video template includes a plurality of slots, a cover image, and background audio, and each of the slots is used to fill the character material or the scene material.

8. A video processing device, characterized in that: include: A first acquisition module is used to acquire the target video template and the original material prompt words of the target video template in response to the selection operation of the target video template under the target scene, wherein the target video template is a video production format framework for the target scene; The second acquisition module is used to acquire the character features inputted for the target character; A prompt word module, used for generating a target material prompt word based on the original material prompt word; A material module, used for generating at least one character material of the target role and at least one scene material of the target scene based on the character features and the target material prompt words; The video module is used to fill the at least one character material and the at least one scene material into the target video template to generate a target video.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the video processing method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the video processing method described in any one of claims 1 to 7.

Images