Video generation method, device and equipment based on music

Abstract

The present disclosure provides a method, device and equipment for video generation based on music, which relates to the field of image processing technology, and in particular to the field of video generation technology. The specific implementation scheme is: obtain a multimedia text to be accompanied by music, and parse and process the multimedia text to be accompanied by music, and obtain the image parsing result of each picture in the multimedia text to be accompanied by music; wherein the image parsing result represents the characteristics of the picture itself and the characteristics of adjacent pictures, the characteristics of the picture itself represent the characteristic information in the picture, and the characteristics of adjacent pictures represent the characteristic relationship between the picture and the adjacent pictures; according to the image parsing result of the picture, determine the video information of the picture; wherein the video information represents the information of the picture in the video with music to be generated; according to the picture, the image parsing result of the picture and the video information of the picture, generate a video with music.

Description

Technical Field

[0001] The present disclosure relates to the field of video generation technology in the field of image processing technology, and in particular to a method, device and equipment for video generation based on music. Background Art

[0002] With the development of media technology, it is often necessary to add music to multimedia texts, that is, to configure music for multimedia texts. Among them, multimedia texts include multiple pictures. This often involves the copyright issues of music.

[0003] Therefore, how to automatically configure appropriate music for multimedia texts and avoid music copyright issues is a problem that needs to be solved urgently. Summary of the invention

[0004] The present disclosure provides a method, device and apparatus for generating a video based on music.

[0005] According to a first aspect of the present disclosure, a method for generating a video based on soundtrack is provided, comprising:

[0006] Acquire a multimedia text to be matched with music, and parse the multimedia text to be matched with music to obtain a picture parsing result of each picture in the multimedia text to be matched with music; wherein the picture parsing result represents the characteristics of the picture itself and the characteristics of adjacent pictures, the characteristics of the picture itself represent the characteristic information in the picture, and the characteristics of adjacent pictures represent the characteristic relationship between the picture and the adjacent pictures;

[0007] Determine video information of the picture according to the picture analysis result of the picture; wherein the video information represents information of the picture in the video with music to be generated;

[0008] A video with music is generated according to the picture, the picture analysis result of the picture and the video information of the picture.

[0009] According to a second aspect of the present disclosure, there is provided a video generation device based on soundtrack, comprising:

[0010] An acquisition unit is used to acquire a multimedia text to be matched with music, and parse the multimedia text to be matched with music to obtain a picture analysis result of each picture in the multimedia text to be matched with music; wherein the picture analysis result represents the characteristics of the picture itself and the characteristics of adjacent pictures, the characteristics of the picture itself represent the characteristic information in the picture, and the characteristics of adjacent pictures represent the characteristic relationship between the picture and the adjacent pictures;

[0011] A determination unit, configured to determine video information of the picture according to a picture analysis result of the picture; wherein the video information represents information of the picture in a video with music to be generated;

[0012] A generating unit is used to generate a video with music according to the picture, the picture analysis result of the picture and the video information of the picture.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the soundtrack-based video generation method described in the first aspect.

[0014] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the video generation method based on soundtrack according to the first aspect.

[0015] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising: a computer program, wherein the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect.

[0016] According to the video generation method, device and equipment based on music arrangement disclosed in the present invention, by acquiring a multimedia text to be accompanied by music, and parsing the multimedia text to be accompanied by music, a picture parsing result of each picture in the multimedia text to be accompanied by music is obtained, and according to the picture parsing result of the picture, the video information of the picture is determined, and according to the picture, the picture parsing result of the picture and the video information of the picture, a video with music arrangement is generated, wherein the multimedia text to be accompanied by music is parsed to obtain the picture parsing result of each picture in the multimedia text to be accompanied by music, and the acquired multimedia file to be accompanied by music can be parsed in detail, thereby improving the accuracy of the video generation method based on music arrangement, wherein according to the picture parsing result of the picture, the video information of the picture is determined, and according to the picture, the picture parsing result of the picture and the video information of the picture, a video with music arrangement is generated, thereby avoiding the problem of music copyright disputes in the video generation method based on music arrangement.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0019] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0020] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure;

[0021] Figure 3 is a block diagram of a device for generating a video based on music for implementing an embodiment of the present disclosure;

[0022] Figure 4 The block diagram of an electronic device used to implement the video generation method based on soundtrack according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0024] The present invention discloses a method, device and equipment for generating a video based on music, which are applied to the field of video generation technology in the field of image processing technology, so as to improve the accuracy of the method for generating a video based on music and avoid music copyright disputes.

[0025] Figure 1 Schematic diagram of the first embodiment of the present disclosure. Figure 1 As shown, the video generation method based on soundtrack provided by the first embodiment of the present disclosure includes:

[0026] Step S101: Acquire a multimedia text to be matched with music, and parse the multimedia text to be matched with music to obtain a picture parsing result of each picture in the multimedia text to be matched with music.

[0027] Specifically, a multimedia text to be matched with music may be obtained, and the multimedia text to be matched with music may be parsed to obtain a picture parsing result of each picture in the multimedia text to be matched with music.

[0028] Wherein, the multimedia text includes but is not limited to one or more pictures / videos, for example: the multimedia text to be accompanied by music is a picture, or multiple pictures, or a video, or multiple videos. Wherein, the present disclosure does not limit the process of obtaining the multimedia text to be accompanied by music. Optionally, multimedia text uploaded by a user can be obtained. Optionally, in response to a video generation request sent by a user, one or more recommended multimedia texts can be obtained, and in response to a user's selection instruction, the multimedia text to be accompanied by music can be determined from the recommended multimedia texts, wherein the video generation request is used to indicate the generation of a video based on music, specifically, the video generation request first indicates the acquisition of one or more recommended multimedia texts, wherein the recommended multimedia text can be a multimedia text obtained from a local database and / or a network according to the video generation request and selected by the user, wherein the selection instruction is used to indicate the selection of the multimedia text to be accompanied by music from one or more recommended multimedia texts.

[0029] Among them, the present disclosure does not limit the process of parsing the multimedia text to be accompanied by music and obtaining the image parsing result of each picture in the multimedia text to be accompanied by music. Optionally, based on a preset artificial intelligence model, the multimedia text to be accompanied by music can be extracted to obtain the picture in the multimedia text to be accompanied by music, and then the extracted picture is parsed to obtain the picture parsing result of the picture. Among them, the picture parsing result represents the characteristics of the picture itself and the characteristics of adjacent pictures, the characteristics of the picture itself represent the characteristic information in the picture, and the characteristics of adjacent pictures represent the characteristic relationship between the picture and the adjacent pictures. Among them, the present disclosure does not limit the characteristic information in the picture, and any feature that can be obtained by parsing the multimedia text to be accompanied by music and represents the picture in the multimedia text can be used as the characteristic information in the picture provided in the present disclosure, such as: the color feature, texture feature, shape feature and spatial relationship feature of the picture, among them, the present disclosure does not limit the characteristic relationship between the picture and the adjacent pictures, and any feature relationship that can be obtained by parsing the multimedia text to be accompanied by music and represents the relationship between the characteristics of the picture and the adjacent pictures in the multimedia text can be used as the characteristic relationship between the picture and the adjacent pictures provided in the present disclosure.

[0030] Step S102: Determine the video information of the picture according to the picture analysis result of the picture.

[0031] Specifically, the video information of each picture can be determined according to the picture analysis result of each picture in the multimedia text to be accompanied with music obtained in step S101. The video information represents the information of the picture in the video with music to be generated. The video with music to be generated refers to the video generated based on the video generation method based on music proposed in the present disclosure and the multimedia text to be accompanied with music obtained in step S101. Specifically, the generated video is obtained by sorting, filtering, switching or maintaining the pictures in the multimedia text to be accompanied with music.

[0032] Among them, the present disclosure does not limit the process of determining the video information of a picture based on the picture analysis results of the picture. Optionally, the picture analysis results of the picture can be input into a preset artificial intelligence model for processing to obtain the video information of the picture.

[0033] Step S103: Generate a video with music according to the picture, the picture analysis result of the picture and the video information of the picture.

[0034] Specifically, a video with music is generated based on each picture in the obtained multimedia text to be accompanied by music, the analysis result of each picture, and the video information of each picture determined in step S102. The present disclosure does not limit the process of generating a video with music based on pictures, picture analysis results of pictures, and video information of pictures. Optionally, music prompt words can be generated based on the picture analysis results of pictures and the video information of pictures; and then the video with music is generated based on the pictures, the video information of the pictures, and the music prompt words.

[0035] The music content in the video with music is original music generated based on the picture, the picture analysis result of the picture and the video information of the picture.

[0036] In the disclosed embodiment, a multimedia text to be accompanied with music is obtained and the multimedia text to be accompanied with music is parsed to obtain image parsing results of each picture in the multimedia text to be accompanied with music, and video information of the picture is determined based on the image parsing results of the picture. A video with music is generated based on the picture, the image parsing results of the picture and the video information of the picture. The multimedia text to be accompanied with music is parsed to obtain image parsing results of each picture in the multimedia text to be accompanied with music, and the obtained multimedia file to be accompanied with music can be analyzed in detail, thereby improving the accuracy of the video generation method based on music. The video information of the picture is determined based on the image parsing results of the picture, and the video with music is generated based on the picture, the image parsing results of the picture and the video information of the picture. This can avoid music copyright disputes in the video generation method based on music.

[0037] In a possible embodiment, the features of the image itself represented by the image analysis result include: object features of each object in the image, and / or, overall features of the image. Each image includes at least one object, and each object includes at least one object feature, wherein an object refers to an image unit constituting the image, for example: if the image is a photo of a single person, the object is each body part of the person, for example: if the image is a group photo of people, the object is each person in the image, wherein the object feature is used to represent the features of the object, specifically, the object features representing different objects are different, and the present disclosure does not limit the features represented by each object, for example: if the object is a body part of a person, such as an eye, its object features may include state features, direction features, color features, size features, regional features, ethnic features, emotional features and other features, wherein the overall features of the image represent the overall features of each object in the image, and optionally, the overall features include but are not limited to: scene features, style features and other features, for example: the overall representation scene constituted by each object in the image is a snowy scene, a rainy scene, an indoor scene, an outdoor scene and other scenes. Among them, further limiting the characteristics of the image itself can achieve more detailed image analysis of each image obtained in the multimedia file, so as to make the video generation method based on music more accurate.Optionally, based on the features of the image itself described above, the adjacent image features first include the association relationship between each object in the image and each object in the adjacent image, wherein the association relationship includes an identical relationship, a related relationship, and an unrelated relationship. If there are objects with identical relationships, the adjacent image features include the object features of the objects with identical relationships in the adjacent images, and the change features of the object features of the objects with identical relationships in the current image. For example, if the objects with identical relationships are eyes in a photo of a single person, in the current image, the state features of the eyes are open, and in the adjacent image, the state features of the eyes are closed. Then the adjacent image features include the associated object eyes, and the state features in the adjacent image are changed from open to closed. For example, if the objects with identical relationships are eyes in a photo of a single person, in the current image, the state features of the eyes are open, in the adjacent picture, the state feature of the eyes is also open, then the adjacent picture features include the eyes of the associated object, and the state feature in the adjacent picture is keep open; wherein, if there is a related object, the adjacent picture features include the features of the related object in the adjacent picture, for example: if the object related to the eyes in the current picture is glasses in the adjacent picture, then the adjacent picture features include the features of the glasses in the adjacent picture, such as color features, shape features, style features, etc.; wherein, if there is an unrelated object, the adjacent picture features include the features of the unrelated object in the adjacent picture, for example: if the unrelated object is the sun appearing in the background of a photo of a single person, then the adjacent picture features include the features of the sun in the adjacent picture, such as color features, position features, time features, etc. In a possible embodiment, the adjacent picture features represented by the picture analysis result include one or more of the following: position change features of each object in the picture, emotional change features of each object in the picture, and the association relationship between each object in the picture and each object in the adjacent image. Among them, the description of the association relationship between each object in the picture and each object in the adjacent image can refer to the description above and will not be repeated here. Among them, the position change characteristics and emotion change characteristics of each object in the picture are the adjacent picture characteristics of objects with the same association relationship. Among them, on the basis of further limiting the characteristics of the picture itself as described above, the further limitation of the characteristics of adjacent pictures can achieve more detailed picture analysis of each picture obtained in the multimedia file, so as to make the video generation method based on music more accurate.

[0038] In order to enable readers to more deeply understand the implementation principle of the present disclosure, the following Figure 2-Figure 4 right Figure 1 The illustrated embodiment is further refined.

[0039] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure. Figure 2 As shown, the video generation method based on soundtrack provided by the second embodiment of the present disclosure includes:

[0040] Step S201: Obtain the multimedia text to be matched with music.

[0041] Specifically, a multimedia file to be matched with music may be obtained, wherein the specific description of this step may refer to the description in step S101, and this step will not be described in detail.

[0042] Step S202: Based on a preset artificial intelligence model, extract images from the multimedia text to be accompanied by music to obtain images in the multimedia text to be accompanied by music.

[0043] Specifically, after obtaining the multimedia text to be accompanied by music, image extraction can be performed on the multimedia text to be accompanied by music based on a preset artificial intelligence model to obtain images in the multimedia text to be accompanied by music, wherein, based on the description in step S101, if the multimedia text includes one image, the image in the multimedia text to be accompanied by music obtained by extraction is one image; if the multimedia text includes multiple images, the images in the multimedia text to be accompanied by music obtained by extraction are multiple images; if the multimedia text includes a video, the images in the multimedia text to be accompanied by music obtained by extraction are images constituted by each frame of the video; if the multimedia text includes multiple videos, the images in the multimedia text to be accompanied by music obtained by extraction are images constituted by each frame of each video.

[0044] In this step, the preset artificial intelligence model for image extraction of multimedia text to be accompanied by music is an artificial intelligence model generated by pre-training based on historical multimedia text and corresponding historical image extraction results, wherein the present disclosure does not limit the pre-training process of the artificial intelligence model. In this case, image extraction of multimedia text to be accompanied by music based on the preset artificial intelligence model can improve the accuracy of extraction and further improve the accuracy of the video generation method based on music.

[0045] Step S203: Based on a preset artificial intelligence model, the extracted image is analyzed and processed to obtain an image analysis result of the image.

[0046] Specifically, after obtaining the pictures in the multimedia text to be matched with music, each picture in the extracted multimedia text to be matched with music can be analyzed based on a preset artificial intelligence model to obtain a picture analysis result of each picture, wherein the description of the picture analysis result can refer to the description in step S101, and this step will not be repeated.

[0047] In this step, the artificial intelligence model for parsing the extracted images is an artificial intelligence model generated by pre-training based on historical images and corresponding image parsing results, wherein the present disclosure does not limit the pre-training process of the artificial intelligence model. Parsing the extracted images based on the preset artificial intelligence model can improve the detail of the analysis and further improve the accuracy of the video generation method based on music.

[0048] Step S204: input the image analysis result of the image into a preset artificial intelligence model for processing to obtain video information of the image.

[0049] Specifically, after obtaining the analysis result of each picture, the picture analysis result of the picture can be input into a preset artificial intelligence model for processing to obtain the video information of the picture, wherein the description of the video information of the picture can refer to the description in step S102, and this step will not be repeated. Optionally, the video information includes one or more of the following: picture sorting information, picture filtering information, switching effect information, and retention time information. Among them, the picture sorting information represents the position of the picture in the video with music to be generated. The picture filtering information represents whether the picture is retained in the video with music to be generated. The switching effect information represents the switching effect of the picture in the video with music to be generated. The retention time information represents the length of time the picture remains displayed in the video with music to be generated. Among them, the further limitation of the video information can more specifically limit the video with music generated according to the video information, further improving the accuracy of the video generation method based on music.

[0050] In this step, the artificial intelligence model that processes the analysis results of each image is an artificial intelligence model generated by pre-training based on historical image analysis results and corresponding video information, and the present disclosure does not limit the pre-training process of the artificial intelligence model. Processing the analysis results of each image based on a preset artificial intelligence model can improve the accuracy of the obtained video information and further improve the accuracy of the video generation method based on music.

[0051] The present disclosure does not limit the process of inputting the image analysis result of the image into a preset artificial intelligence model for processing to obtain the video information of the image. Optionally, the prompt words for generating the video information of the image can be obtained according to the image analysis result of the image, and then the prompt words for generating the video information of the image can be input into the preset artificial intelligence model for processing to obtain the video information of the image. Inputting the image analysis result of the image into the preset artificial intelligence model for processing to obtain the video information of the image can effectively improve the efficiency of video information generation and further improve the efficiency of the video generation method based on soundtrack.

[0052] Optionally, after obtaining the video information of the picture, the picture can be filtered according to the picture filtering information in the video information of the picture. The picture filtering information indicates whether the picture is retained in the video with music to be generated. Specifically, if the picture filtering information indicates that the picture is retained in the video with music to be generated, the picture is retained when the picture is filtered; if the picture filtering information indicates that the picture is not retained in the video with music to be generated, the picture is not retained when the picture is filtered. Optionally, all pictures in the multimedia text to be accompanied by music can be filtered, and a video with specific music can be generated based on the filtered pictures, so that the pictures included in the finally generated video with music are the filtered pictures, thereby optimizing the finally generated video with music and improving the user experience of the video generation method based on music.

[0053] Step S205: Generate music prompt words according to the picture analysis result and the video information of the picture.

[0054] Specifically, the music prompt word may be generated according to the image analysis result of the image obtained in step S203 and the video information of the image obtained in step S204, wherein the music prompt word represents the music information of the video.

[0055] Among them, the present disclosure does not limit the process of generating music prompt words according to the picture analysis results of the pictures and the video information of the pictures. Optionally, the picture analysis results of each picture can be sorted according to the picture sorting information in the video information of each picture to obtain the picture analysis results of each sorted picture. Then, according to the picture analysis results of each sorted picture, the switching effect information in the video information of each picture, and the retention time information, the music prompt words are generated. Among them, the picture sorting information represents the position of the picture in the video with music to be generated. The generated music prompt words are generated based on the picture analysis results of each sorted picture, the switching effect information in the video information of each picture, and the retention time information, which optimizes the finally generated music prompt words and further improves the user experience of the video generation method based on music.

[0056] Optionally, the above-mentioned process of generating music prompt words according to the image analysis results of the picture and the video information of the picture can be implemented based on a preset artificial intelligence model, that is, the image analysis results of the picture and the video information of the picture are input into the preset artificial intelligence model to obtain music prompt words, wherein, in this step, the preset artificial intelligence model is an artificial intelligence model generated by pre-training based on the image analysis results of historical pictures and the video information of the picture, and the corresponding historical music prompt words, wherein the present disclosure does not limit the pre-training process of the artificial intelligence model.

[0057] Among them, the present disclosure does not limit the process of generating the music prompt word according to the picture analysis results of each picture after sorting, the switching effect information in the video information of each picture, and the retention time information. Optionally, the self-attention calculation processing can be performed based on the preset artificial intelligence model according to the picture characteristics of each picture after sorting, the adjacent picture characteristics and the switching effect information of each picture, to obtain the picture fusion feature of each picture. Among them, the description of the adjacent picture characteristics and the switching effect information can refer to the description in the above embodiment, and this step is not repeated. Among them, self-attention calculation is a technology commonly used in the fields of natural language processing (NLP) and computer vision (CV), which is used to find more critical information for the current task in the input sequence. The core idea of ​​self-attention calculation is to "select a small amount of important information from a large amount of information" and "focus on these important information and ignore most of the unimportant information". Among them, the fusion feature representation is the self-attention calculation processing based on the preset artificial intelligence model, which is obtained from the picture characteristics of the picture characteristics of each picture after sorting, the adjacent picture characteristics and the switching effect information of each picture, and is used to generate the fusion feature of each picture for the music prompt word. Then, based on the preset artificial intelligence model, the image fusion features of each image, the switching effect information of each image, and the retention time information of each image are weighted and processed to obtain the fusion features of the video. In addition to the image fusion features of each image obtained above, the switching effect information of each image and the retention time information of each image are also included. Therefore, the image fusion features of each image, the switching effect information of each image, and the retention time information of each image can be weighted and processed to obtain the fusion features of the video, wherein the fusion features of the video represent the features of the fusion video obtained after weighting the image fusion features of each image, the switching effect information of each image, and the retention time information of each image based on the preset artificial intelligence model. The music prompt words are then generated based on the fusion features of the video. Among them, the fusion features of the video generated based on the above process are generated based on a preset artificial intelligence model, according to the image characteristics of the image itself, the adjacent image characteristics and the switching effect information of each image in the image analysis results of each sorted image, as well as the switching effect information of each image and the retention time information of each image. It can more comprehensively characterize the characteristics of the fused video. Therefore, the music prompt words generated based on the fusion features of the video are more in line with the music requirements, further improving the accuracy of the video generation method based on music.

[0058] Optionally, the process of generating music prompt words according to the fusion features of the video may include: determining the music features of the video according to the fusion features of the video. And generating the music prompt words according to the music features of the video. The music features of the video represent the features used to generate the music prompt words determined according to the fusion features of the video. The process of determining the music features of the video and generating the music prompt words according to the music features of the video can improve the accuracy of the generation of the music prompt words, and further improve the accuracy of the video generation method based on the music.

[0059] Step S206: Generate a video with music according to the picture, the video information of the picture and the music prompt word.

[0060] Specifically, after generating the music prompt words according to the image parsing result of the image and the video information of the image, a video with music can be generated according to the image in the multimedia text to be matched with music extracted in step S202, the video information of the image obtained in step S204, and the music prompt words generated in step S205. According to the characteristics of the music prompt words that better meet the music requirements as described above, the video with music generated according to the music prompt words can also better meet the music requirements, further improving the accuracy and user experience of the video generation method based on music.

[0061] The present disclosure does not limit the process of generating a video with music according to the picture, the video information of the picture and the music prompt word. Optionally, the music prompt word can be first input into a preset artificial intelligence model to obtain the music content. Then, a video without music is generated according to the picture and the video information of the picture. The music content and the video without music are fused to obtain a video with music. In this step, the artificial intelligence model input with the music prompt word to obtain the music content is an artificial intelligence model generated by pre-training based on historical music prompt words and historical music content, and the present disclosure does not limit the pre-training process of the artificial intelligence model. The present disclosure does not limit the process of generating a video without music according to the picture and the video information of the picture. Optionally, the picture can be screened according to the picture screening information in the video information of the picture; the picture is then sorted according to the picture sorting information in the video information of each screened picture, and the video without music is generated according to the switching effect information and the holding time information in the video information of each sorted picture. The soundtrack content refers to content that can be integrated with a video without a soundtrack to obtain a video with a soundtrack, wherein the soundtrack content includes at least one soundtrack music of the video, wherein the soundtrack music refers to music included in the soundtrack content that is directly integrated with the video without a soundtrack, wherein each soundtrack music can be directly integrated with the video without a soundtrack to obtain a video with a soundtrack, and different soundtrack music in the same soundtrack content has different styles. Based on the above description, the generated video without a soundtrack matches the soundtrack content, and the final video with a soundtrack will be more accurate, further improving the user experience of the video generation method based on the soundtrack.

[0062] Optionally, when the soundtrack content includes multiple soundtrack music, the soundtrack content and the video without soundtrack are fused to obtain the video with soundtrack, and the process may include: generating and displaying characteristic prompt words of the soundtrack music according to the soundtrack music in the soundtrack content. The characteristic prompt words represent the style of the soundtrack music. In response to the user's confirmation instruction, the soundtrack music indicated by the confirmation instruction and the video without soundtrack are fused to obtain the video with soundtrack. The confirmation instruction indicates the soundtrack music selected by the user. In the case where the soundtrack content includes multiple soundtrack music, the characteristic prompt words of the soundtrack music are used to enable the user to select the soundtrack music, and further combined with the user's confirmation instruction, the obtained video with soundtrack better meets the user's needs, thereby improving the user experience of the video generation method based on soundtrack.

[0063] Step S207: display the video with the soundtrack to the user, or, in response to the export instruction, export the video with the soundtrack to the video storage location indicated by the export instruction for storage.

[0064] Specifically, after generating a video with music, the video with music can be displayed to the user, or, in response to an export instruction, the video with music is exported to a video storage location indicated by the export instruction for storage. The export instruction is used to instruct the export of the video with music, and the export instruction indicates the video storage location. The video with music can be applied in the form of direct display and / or export, which also improves the user experience.

[0065] In the disclosed embodiment, a multimedia text to be accompanied with music is obtained, and based on a preset artificial intelligence model, image extraction is performed on the multimedia text to be accompanied with music to obtain images in the multimedia text to be accompanied with music; based on the preset artificial intelligence model, the extracted images are parsed and processed to obtain image parsing results of the images; the image parsing results of the images are input into the preset artificial intelligence model for processing to obtain video information of the images; music prompt words are generated according to the image parsing results of the images and the video information of the images; a video with music is generated according to the images, the video information of the images and the music prompt words; the video with music is displayed to a user, or, in response to an export instruction, the video with music is exported to a video storage location indicated by the export instruction for storage; wherein, based on the preset artificial intelligence model, image extraction is performed on the multimedia text to be accompanied with music, the accuracy of extraction can be improved, and the accuracy of the video based on music can be further improved. The accuracy of the video generation method based on music is improved, wherein the extracted images are parsed based on a preset artificial intelligence model, which can improve the detail of the analysis and further improve the accuracy of the video generation method based on music, wherein the analysis results of each image are processed based on a preset artificial intelligence model, which can improve the accuracy of the obtained video information and further improve the accuracy of the video generation method based on music, wherein the music prompt words generated according to the image parsing results and the video information of the image are more in line with the music requirements, and the video with music generated according to the music prompt words is also more in line with the music requirements, further improving the accuracy and user experience of the video generation method based on music, wherein the video with music can be applied in the form of direct display and / or export, which also improves the user experience. Based on the above description, the accuracy and user experience of the video generation method based on music can be improved.

[0066] Figure 3 is a block diagram of a video generation device based on music for implementing an embodiment of the present disclosure, such as Figure 3 As shown, the music-based video generation device 300 provided in the third embodiment of the present disclosure includes:

[0067] The acquisition unit 301 is used to acquire the multimedia text to be matched with music, and parse the multimedia text to be matched with music to obtain the image parsing result of each picture in the multimedia text to be matched with music; wherein the image parsing result represents the characteristics of the picture itself and the characteristics of adjacent pictures, the characteristics of the picture itself represent the characteristic information in the picture, and the characteristics of adjacent pictures represent the characteristic relationship between the pictures;

[0068] The determination unit 302 is used to determine the video information of the picture according to the picture analysis result of the picture; wherein the video information represents the information of the picture in the video with music to be generated;

[0069] The generating unit 303 is used to generate a video with music according to the picture, the picture analysis result of the picture and the video information of the picture.

[0070] In the disclosed embodiment, the device for generating a video based on music includes an acquisition unit 301 for acquiring a multimedia text to be accompanied by music, and parsing the multimedia text to be accompanied by music to obtain a picture parsing result of each picture in the multimedia text to be accompanied by music, a determination unit 302 for determining the video information of the picture according to the picture parsing result of the picture, and a generation unit 303 for generating a video with music according to the picture, the picture parsing result of the picture and the video information of the picture, wherein the acquisition unit 301 can perform a detailed analysis on the acquired multimedia file to be accompanied by music, thereby improving the accuracy of the video generation method based on music, wherein the determination unit 302 and the generation unit 303 can avoid the problem of music copyright disputes in the video generation method based on music.

[0071] In some embodiments, the features of the image itself include: object features of each object in the image, and / or, overall features of the image; features of adjacent images include one or more of the following: position change features of each object in the image, emotion change features of each object in the image, and the association relationship between each object in the image and each object in adjacent images.

[0072] In some embodiments, the acquisition unit 301 includes: an extraction module 3011 (not shown in the figure), which is used to extract images of the multimedia text to be accompanied by music based on a preset artificial intelligence model, and obtain images in the multimedia text to be accompanied by music; a parsing module 3012 (not shown in the figure), which is used to parse the extracted images based on a preset artificial intelligence model, and obtain image parsing results of the images.

[0073] In some embodiments, the video information includes one or more of the following: picture sorting information, picture filtering information, switching effect information, and retention time information; wherein the picture sorting information represents the position of the picture in the video with music to be generated; the picture filtering information represents whether the picture is retained in the video with music to be generated; the switching effect information represents the switching effect of the picture in the video with music to be generated; and the retention time information represents the length of time the picture remains displayed in the video with music to be generated.

[0074] In some embodiments, the determination unit 302 includes: a processing module 3021 (not shown in the figure), which is used to input the image analysis result of the image into a preset artificial intelligence model for processing to obtain video information of the image; a screening module 3022 (not shown in the figure), which is used to screen the image according to the image screening information in the video information of the image; wherein the image screening information represents whether the image is retained in the video with music to be generated.

[0075] In some embodiments, the generation module includes: a first generation module 3023 (not shown in the figure), which is used to generate music prompt words based on the picture analysis results of the picture and the video information of the picture; wherein the music prompt words represent the music information of the video; a second generation module 3024 (not shown in the figure), which is used to generate a video with music based on the picture, the video information of the picture and the music prompt words.

[0076] In some embodiments, the first generation module 3023 (not shown in the figure) includes: a sorting submodule 3025 (not shown in the figure), which is used to sort the image analysis results of each picture according to the image sorting information in the video information of each picture, and obtain the image analysis results of each sorted picture; wherein the image sorting information represents the position of the picture in the video with music to be generated; the first generation submodule 3026 (not shown in the figure) is used to generate music prompt words according to the image analysis results of each sorted picture, the switching effect information in the video information of each picture, and the retention time information.

[0077] In some embodiments, the first generation submodule 3026 (not shown in the figure) is specifically used to: perform self-attention calculation processing based on a preset artificial intelligence model according to the image characteristics of the image itself, the characteristics of adjacent images and the switching effect information of each image in the image analysis results of each sorted image, to obtain the image fusion characteristics of each image; perform weight calculation processing on the image fusion characteristics of each image, the switching effect information of each image and the holding time information of each image based on the preset artificial intelligence model to obtain the fusion characteristics of the video; generate music prompt words according to the fusion characteristics of the video.

[0078] In some embodiments, the first generating submodule 3026 (not shown in the figure) is further specifically used to: determine the music features of the video according to the fusion features of the video; and generate music prompt words according to the music features of the video.

[0079] In some embodiments, the second generation module 3024 (not shown in the figure) includes: an acquisition sub-module 3027 (not shown in the figure), which is used to input the music prompt word into a preset artificial intelligence model to obtain the music content; wherein the music content includes at least one piece of music for the video; a second generation sub-module 3028 (not shown in the figure), which is used to generate a video without music based on the picture and the video information of the picture; a fusion sub-module 3029 (not shown in the figure), which is used to fuse the music content and the video without music to obtain a video with music.

[0080] In some embodiments, when the soundtrack content includes multiple soundtrack music, the fusion sub-module 3029 (not shown in the figure) is specifically used to: generate and display characteristic prompt words of the soundtrack music based on the soundtrack music in the soundtrack content; wherein the characteristic prompt words represent the style of the soundtrack music; in response to the user's confirmation instruction, fuse the soundtrack music indicated by the confirmation instruction and the video without the soundtrack to obtain a video with the soundtrack; wherein the confirmation instruction indicates the soundtrack music selected by the user.

[0081] In some embodiments, the soundtrack-based video generation device 300 also includes: a display unit 304 (not shown in the figure), which is used to display the video with the soundtrack to the user; or, an export unit 305 (not shown in the figure), which is used to export the video with the soundtrack to the video storage location indicated by the export instruction in response to the export instruction for storage; wherein the export instruction is used to instruct the export of the video with the soundtrack, and the export instruction indicates the video storage location.

[0082] Figure 3 The provided music-based video generation device can execute the steps involved in the terminal in the above-mentioned corresponding method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0083] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the solution provided by any of the above embodiments.

[0084] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute a solution provided by any of the above embodiments.

[0085] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0086] Figure 4 is a block diagram of an electronic device for implementing the video generation method based on soundtrack according to an embodiment of the present disclosure, Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0087] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0088] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0089] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as a video generation method based on a soundtrack. For example, in some embodiments, the video generation method based on a soundtrack may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the video generation method based on the soundtrack described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform a video generation method based on a soundtrack in any other appropriate manner (e.g., by means of firmware).

[0090] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0092] 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.

[0093] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0094] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by 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), and the Internet.

[0095] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0096] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0097] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A video generation method based on music, comprising: Acquire a multimedia text to be matched with music, and parse the multimedia text to be matched with music to obtain a picture parsing result of each picture in the multimedia text to be matched with music; wherein the picture parsing result represents the characteristics of the picture itself and the characteristics of adjacent pictures, the characteristics of the picture itself represent the characteristic information in the picture, and the characteristics of adjacent pictures represent the characteristic relationship between the picture and the adjacent pictures; Determine video information of the picture according to the picture analysis result of the picture; wherein the video information represents information of the picture in the video with music to be generated; Generate a video with music according to the picture, the picture analysis result of the picture and the video information of the picture; The step of generating a video with music according to the picture, the picture analysis result of the picture and the video information of the picture comprises: Generate a music prompt word according to the image analysis result of the image and the video information of the image; wherein the music prompt word represents the music information of the video; Generate a video with music according to the picture, the video information of the picture and the music prompt word; The step of generating a music prompt word according to the image analysis result of the image and the video information of the image includes: Sorting the image analysis results of each of the images according to the image sorting information in the video information of each of the images to obtain sorted image analysis results of each of the images; wherein the image sorting information represents the position of the image in the video with music to be generated; The music prompt words are generated according to the image analysis results of the sorted images, the switching effect information and the holding time information in the video information of each image.

2. The method according to claim 1, wherein: The image features include: object features of each object in the image, and / or overall features of the image; The adjacent picture features include one or more of the following: position change features of each object in the picture, emotion change features of each object in the picture, and association relationship between each object in the picture and each object in an adjacent image.

3. The method according to claim 1 or 2, wherein: The step of parsing the multimedia text to be matched with music to obtain a picture parsing result of each picture in the multimedia text to be matched with music includes: Based on a preset artificial intelligence model, extracting images from the multimedia text to be matched with music, and obtaining images in the multimedia text to be matched with music; Based on the preset artificial intelligence model, the extracted image is analyzed and processed to obtain an image analysis result of the image.

4. The method according to claim 1 or 2, wherein: The video information includes one or more of the following: picture sorting information, picture filtering information, switching effect information, and holding time information; Among them, the picture sorting information represents the position of the picture in the video with music to be generated; the picture filtering information represents whether the picture is retained in the video with music to be generated; the switching effect information represents the switching effect of the picture in the video with music to be generated; and the retention time information represents the length of time the picture remains displayed in the video with music to be generated.

5. The method according to claim 1 or 2, wherein: The determining the video information of the picture according to the picture analysis result of the picture includes: Inputting the image analysis result of the image into a preset artificial intelligence model for processing to obtain video information of the image; The picture is filtered according to the picture filtering information in the video information of the picture; wherein the picture filtering information indicates whether the picture is retained in the video with music to be generated.

6. The method according to claim 1 or 2, wherein: The generating the music prompt word according to the image analysis results of the sorted images, the switching effect information and the holding time information in the video information of each image, comprises: According to the features of the image itself, the features of the adjacent images and the switching effect information of each image in the image analysis results of each image after sorting, self-attention calculation processing is performed based on a preset artificial intelligence model to obtain the image fusion features of each image; Based on the preset artificial intelligence model, the image fusion features of each image, the switching effect information of each image, and the retention time information of each image are weighted and processed to obtain the fusion features of the video; The music prompt words are generated according to the fusion features of the video.

7. The method according to claim 6, wherein: The step of generating the music prompt word according to the fusion feature of the video includes: The music features of the video are determined according to the fusion features of the video; and the music prompt words are generated according to the music features of the video.

8. The method according to any one of claims 1 to 2 and 7, wherein: The step of generating a video with music according to the picture, the video information of the picture and the music prompt word comprises: Inputting the music prompt words into a preset artificial intelligence model to obtain music content; wherein the music content includes at least one piece of music for the video; Generate a video without music according to the picture and the video information of the picture; The music content and the video without music are fused to obtain the video with music.

9. The method according to claim 8, wherein: When the soundtrack content includes multiple soundtrack music, the soundtrack content and the video without the soundtrack are fused to obtain the video with the soundtrack, including: Generate and display characteristic prompt words of the soundtrack music according to the soundtrack music in the soundtrack content; wherein the characteristic prompt words represent the style of the soundtrack music; In response to a confirmation instruction from the user, the background music indicated by the confirmation instruction and the video without background music are fused to obtain a video with background music; wherein the confirmation instruction indicates the background music selected by the user.

10. The method according to any one of claims 1-2, 7, and 9, further comprising: Displaying the video with the soundtrack to the user; Alternatively, in response to an export instruction, the video with music is exported to a video storage location indicated by the export instruction for storage; wherein the export instruction is used to instruct the export of the video with music, and the export instruction indicates the video storage location.

11. A video generation device based on music, comprising: An acquisition unit is used to acquire a multimedia text to be matched with music, and parse the multimedia text to be matched with music to obtain a picture analysis result of each picture in the multimedia text to be matched with music; wherein the picture analysis result represents the characteristics of the picture itself and the characteristics of adjacent pictures, the characteristics of the picture itself represent the characteristic information in the picture, and the characteristics of adjacent pictures represent the characteristic relationship between the picture and the adjacent pictures; A determination unit, configured to determine video information of the picture according to a picture analysis result of the picture; wherein the video information represents information of the picture in a video with music to be generated; A generating unit, configured to generate a video with music according to the picture, the picture analysis result of the picture and the video information of the picture; The generating unit comprises: A first generating module is used to generate a music prompt word according to the image analysis result of the image and the video information of the image; wherein the music prompt word represents the music information of the video; A second generating module, configured to generate a video with music according to the picture, the video information of the picture and the music prompt word; The first generating module comprises: A sorting submodule, used to sort the image analysis results of each of the images according to the image sorting information in the video information of each of the images, to obtain the sorted image analysis results of each of the images; wherein the image sorting information represents the position of the image in the video with music to be generated; The first generating submodule is used to generate the music prompt word according to the image analysis results of the sorted images, the switching effect information and the holding time information in the video information of each image.

12. The device according to claim 11, wherein The image features include: object features of each object in the image, and / or overall features of the image; The adjacent picture features include one or more of the following: position change features of each object in the picture, emotion change features of each object in the picture, and association relationship between each object in the picture and each object in an adjacent image.

13. The device according to claim 11 or 12, wherein: The acquisition unit comprises: An extraction module, used for extracting images from the multimedia text to be matched with music based on a preset artificial intelligence model, to obtain images in the multimedia text to be matched with music; The analysis module is used to analyze the extracted image based on the preset artificial intelligence model to obtain the image analysis result of the image.

14. The device according to claim 11 or 12, wherein: The video information includes one or more of the following: picture sorting information, picture filtering information, switching effect information, and holding time information; Among them, the picture sorting information represents the position of the picture in the video with music to be generated; the picture filtering information represents whether the picture is retained in the video with music to be generated; the switching effect information represents the switching effect of the picture in the video with music to be generated; and the retention time information represents the length of time the picture remains displayed in the video with music to be generated.

15. The device according to claim 11 or 12, wherein: The determining unit comprises: A processing module, used for inputting the image analysis result of the image into a preset artificial intelligence model for processing to obtain video information of the image; A screening module is used to screen the picture according to the picture screening information in the video information of the picture; wherein the picture screening information represents whether the picture is retained in the video with music to be generated.

16. The device according to claim 11 or 12, wherein: The first generating submodule is specifically used for: According to the features of the image itself, the features of the adjacent images and the switching effect information of each image in the image analysis results of each image after sorting, self-attention calculation processing is performed based on a preset artificial intelligence model to obtain the image fusion features of each image; Based on the preset artificial intelligence model, the image fusion features of each image, the switching effect information of each image, and the retention time information of each image are weighted and processed to obtain the fusion features of the video; The music prompt words are generated according to the fusion features of the video.

17. The device according to claim 16, wherein: The first generating submodule is further specifically used for: The music features of the video are determined according to the fusion features of the video; and the music prompt words are generated according to the music features of the video.

18. The device according to any one of claims 11-12 and 17, wherein: The second generating module comprises: An acquisition submodule is used to input the music prompt word into a preset artificial intelligence model to obtain music content; wherein the music content includes at least one piece of music for the video; A second generating submodule, configured to generate a video without music according to the picture and the video information of the picture; The fusion submodule is used to fuse the music content with the video without music to obtain the video with music.

19. The device according to claim 18, wherein: When the soundtrack content includes multiple soundtrack music, the fusion submodule is specifically used to: Generate and display characteristic prompt words of the soundtrack music according to the soundtrack music in the soundtrack content; wherein the characteristic prompt words represent the style of the soundtrack music; In response to a confirmation instruction from the user, the background music indicated by the confirmation instruction and the video without background music are fused to obtain a video with background music; wherein the confirmation instruction indicates the background music selected by the user.

20. The device according to any one of claims 11-12, 17, and 19, further comprising: A display unit, used for displaying the video with music to a user; Alternatively, the export unit is used to export the video with music in response to an export instruction to store it in a video storage location indicated by the export instruction; wherein the export instruction is used to instruct the export of the video with music, and the export instruction indicates the video storage location.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 10.

Images