Video processing method, device, equipment and medium

Abstract

An embodiment of the present disclosure relates to a video processing method, apparatus, device, and medium, where the method includes extracting video content features based on an analysis of an original video, obtaining at least one recommended material matching the video content features, and performing video processing on the original video based on the recommended material to generate a target video, which is a video generated after adding the recommended material to the original video.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to a Chinese patent application bearing application number 202210178794.5, filed on February 25, 2022, the entire disclosure of which is incorporated herein by reference.

[0002] The present disclosure relates to the technical field of computer applications, and in particular to a video processing method, device, apparatus and medium. [Background technology]

[0003] In order to perform effects processing such as beautification on the shot video, users can use video clip software to select appropriate materials and add them to decorate the video, but the process of selecting and adding them one by one increases time costs and reduces processing efficiency.

[0004] Currently, the related video clip software provides video template or video decoration scheme for one-click video generation, incorporates the shot video or picture into the selected video template, and automatically clips the beautified video with template effects. Summary of the Invention

[0005] According to some embodiments of the present disclosure, a video processing method is provided, the method including: extracting video content features based on an analysis of an original video; obtaining at least one recommended material matching the video content features; performing processing on the original video based on the recommended material; and generating a target video, the target video being a video generated after adding the recommended material to the original video.

[0006] According to some other embodiments of the present disclosure, a video processing device is further provided, the device including: an extraction module for extracting video content features based on an analysis of an original video; an acquisition module for obtaining at least one recommended material matching the video content features; and a processing module for performing processing on the original video based on the recommended material and generating a target video, which is a video generated after adding the recommended material to the original video.

[0007] According to still further some embodiments of the present disclosure, there is further provided an electronic device, the electronic device including a processor and a memory for storing instructions executable by the processor, the processor being adapted to read the executable instructions from the memory and execute the instructions to realize a video processing method according to any embodiment of the present disclosure.

[0008] According to some further embodiments of the present disclosure, there is further provided a computer-readable storage medium having a computer program stored therein, the computer program being adapted to perform a video processing method according to any embodiment of the present disclosure.

[0009] According to still further embodiments of the present disclosure, a computer program is further provided, the computer program including instructions which, when executed by a processor, cause the processor to implement a video processing method according to any embodiment of the present disclosure. [Brief description of the drawings]

[0010] The features, advantages and aspects of the above-mentioned embodiments as well as other embodiments of the present disclosure will become more apparent when referring to the following detailed description in conjunction with the drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0011] [Figure 1]1 is a flowchart of a video processing method according to an embodiment of the present disclosure. [Diagram 2] 4 is a flowchart of another video processing method according to an embodiment of the present disclosure. [Diagram 3] FIG. 2 is a schematic diagram of a video processing scenario according to an embodiment of the present disclosure. [Figure 4] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Diagram 5] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 7] 4 is a flowchart of another video processing method according to an embodiment of the present disclosure. [Figure 8] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 9] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 10] 4 is a flowchart of another video processing method according to an embodiment of the present disclosure. [Figure 11] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 12] 4 is a flowchart of another video processing method according to an embodiment of the present disclosure. [Figure 13] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 14] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 15] 4 is a flowchart of another video processing method according to an embodiment of the present disclosure. [Figure 16] FIG. 2 is a schematic diagram of another video processing scenario according to an embodiment of the present disclosure. [Figure 17] FIG. 2 is a structural schematic diagram of a video processing device according to an embodiment of the present disclosure. [Figure 18] FIG. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, the embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the drawings show some embodiments of the present disclosure, it should be understood that the present disclosure may be realized in many forms and should not be construed as being limited to the embodiments described herein, but rather, these embodiments are provided for a more transparent and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are used for illustrative purposes only and are not intended to limit the protection scope of the present disclosure.

[0013] It should be understood that steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel, and that method embodiments may include additional steps and / or omit performance of steps that are shown, and the scope of the present disclosure is not limited in this respect.

[0014] The term "including" and variations thereof as used herein are open inclusions 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 other embodiment", and the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms are given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in this 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. It should be noted by those skilled in the art that the modifications of "one" and "multiple" mentioned in this disclosure are general rather than limiting, and should be understood as "one or more" unless otherwise clearly indicated in the context. The names of messages or information transmitted between multiple devices in the embodiments of the present disclosure are used for explanatory purposes only, and are not used to limit the scope of these messages or information.

[0015] The inventor found that the pre-made video template is fixed, so the template selected by the user over time may not be intelligently adapted to the original video introduced by the user and cannot be used directly, and the number of effects of the video template is limited, so that multiple videos may frequently use the same video template, and it is not possible to perform effect processing such as adaptive beautification based on the specific video content.

[0016] In order to solve the problem mentioned above that when beautifying a video in the conventional technology, the beautifying effect does not match the video content to a high degree, an embodiment of the present disclosure provides a video processing method, in which materials for effect processing are recommended based on the content of the video, so that after processing based on the recommended materials, the video has a relatively high matching degree between the processing effect and the video content, and the processing effects of videos with different contents are obviously different, resulting in a processing effect of "different effects for different videos", thereby meeting the individual needs of video processing effects.

[0017] The method of the present disclosure will now be described with specific examples.

[0018] 1 is a flowchart of a video processing method according to an embodiment of the present disclosure, which may be performed by a video processing device, which may be realized in software and / or hardware, and may generally be implemented in an electronic device. As shown in FIG. 1, the method includes steps 101-103.

[0019] In step 101, video content features are extracted based on the analysis of the original video.

[0020] In some embodiments, in order to perform video effect processing in accordance with the individual characteristics of the video content, video content features are extracted based on the analysis of the original video, where the original video is the uploaded video to be effect processed, and the video content features include, but are not limited to, one or more of video audio features, video text features, video image features, video filter features, subject features contained in the video, etc.

[0021] In step 102, at least one recommended material that matches the video content characteristics is obtained.

[0022] In some embodiments, at least one recommended material that matches the video content characteristics is obtained, including but not limited to one or more of audio material, sticker material, video material, filter material, etc. In practical applications, the manner of obtaining at least one recommended material that matches the video content characteristics may vary according to different scenarios, and the specific obtaining manner may be illustratively described in subsequent embodiments, and will not be further described here.

[0023] In step 103, the original video is processed based on the recommended material to generate a target video, where the target video is a video generated after adding the recommended material to the original video.

[0024] In this embodiment, the original video is subjected to video processing based on the recommended material to generate a target video, that is, the target video is generated after adding the corresponding recommended material to the original video. In the actual execution process, each material has a corresponding additional track, so that the corresponding material can be added based on the track of the corresponding material. For example, as shown in Table 1 below, the track of each material is defined by its corresponding field name, type, and description information, and Table 1 is an example of a track of a material.

[0025] [Table 1]

[0026] Also, by including parameters corresponding to each recommended material, it becomes easier to make some individual adjustments to the display effect when adding materials, for example, to adjust the size of the material after determining the material area in the following embodiment. For example, the parameters of the text_template material shown in Table 2 below may include a scaling factor, a rotation angle, etc.

[0027] [Table 2]

[0028] Here, in the actual process of adding material, different adding methods can be implemented according to different material types, and different adding methods can be distinguished by adding time, adding position, adding frequency, etc., so as to better respond to the corresponding recommended material and video content, and to show a strong association between the recommended material and the presented video content. Specific adding methods are illustratively described in the following examples, and will not be further described here.

[0029] To sum up, in the video processing method of the embodiment of the present disclosure, after extracting the video content features of the original video, at least one recommended material matching the video content features is obtained, and the recommended material is added to the original video to obtain a target video, so that the video material is added according to the video content of the video, the matching degree between the video content and the video material is improved, and personalized effect processing for the video is realized.

[0030] As mentioned above, in the actual implementation process, the video content features are different in different application scenarios, which is illustratively described as follows.

[0031] In one embodiment of the present disclosure, video content features are extracted based on the text content of the original video to enhance the atmosphere of the video.

[0032] In this embodiment, as shown in FIG. 2, extracting video content features based on analyzing the original video includes steps 201-202.

[0033] In step 201, a voice recognition process is performed on the target audio data of the original video to obtain the corresponding text content.

[0034] After obtaining the target audio data of the original video, in some embodiments, the preset video clip application can identify the video track of the original video, and can also identify each audio track included in the original video, where each audio track corresponds to a sound source. For example, in the case of an original video A, the voices of user a and user b speaking are included, and in this embodiment, the audio track corresponding to the voice of a and the audio track corresponding to the voice of b can be identified.

[0035] In some embodiments, to facilitate processing of each audio track, a video file of the original video retrieves all audio tracks to be displayed in a video clip application. As can be easily understood, the sound source corresponding to each audio track has a generation time, so in some embodiments, the audio tracks are displayed based on a time axis.

[0036] For example, as shown in FIG. 3, when the audio file of the original video is divided into a video track video and two audio tracks audio1 and audio2, the corresponding audio tracks can be displayed in the video clip application.

[0037] In some embodiments, still referring to Figure 3, a merge process is performed on all audio tracks based on a time axis to generate total audio data, for example, audio1 and audio2 are merged based on a time axis to generate total audio data complex-audio, where the total audio data includes all audio data in the original video.

[0038] Of course, as mentioned above, the total audio data is also related to time, so when the first time length of the total audio data is greater than the second time length of the second video of the original video, in order to ensure the consistency of the process length and avoid some audio data having no corresponding video content, the first time length of the total audio data is trimmed to obtain the target audio data, where the time length of the target audio data is consistent with the second time length.

[0039] For example, still referring to FIG. 3, if the duration of complex-audio is longer than the duration of video, the portion of complex-audio that is longer than the duration of video on the time axis is trimmed to obtain target-audio, and the target-audio is aligned with the video on the time axis to facilitate subsequent video processing.

[0040] Of course, in the actual execution process, the audio file corresponding to the original video may include audio data of interaction between the subjects, and may also include background sound, such as music voice played in the environment, or the voice of cars passing on the road in the environment. Such background voice is generally unrelated to the video content, so that it is easy to improve the accuracy of extracting subsequent video content features, and to avoid the interference of background voice with the extraction of video content features (for example, when extracting video text features, the text content in background voice may be identified), in some embodiments, the background voice in the original video can be removed.

[0041] In some embodiments, an audio identifier for each audio track is detected, i.e., based on identifying voice features such as a voice spectrum of the audio corresponding to each audio track, the voice features of the audio corresponding to each audio track are matched with voice features corresponding to each predetermined audio identifier, an audio identifier for each audio track is determined based on the matching result, and a target audio track representing a background music identifier is detected, and then an integration process is performed on all audio tracks other than the target audio track based on a time axis to generate total audio data.

[0042] For example, as shown in FIG. 4, continuing to take the scenario shown in FIG. 3 as an example, if it is determined that the audio identifiers of the audio tracks of the original video are audio1, audio2, and bg-audio respectively, then since bg-audio matches the background music identifier, when generating the total audio data, only the audio tracks corresponding to audio1 and audio2 are integrated.

[0043] Of course, in the actual execution process, the target audio data may be obtained by integrating all audio tracks corresponding to the original video, or may be obtained by integrating only audio tracks that satisfy a certain type of voice characteristic that is preset, etc., and can be specifically set according to the needs of the scenario, and is not limited here.

[0044] In some embodiments, after obtaining the original video, a voice recognition process is performed on the target audio data of the original video, and the corresponding text content is further obtained, and the text content may be obtained by identifying it through voice recognition technology.

[0045] In step 202, a semantic analysis process is performed on the text content to obtain a first keyword.

[0046] Here, the first keyword can match the recommended materials for the video on the content dimension. For example, the first keyword can be an emotion keyword such as "haha, funny", and therefore, based on the first keyword, emotion-rendering materials can be recommended for the video, such as some laughing sticker materials, or some fireworks video materials, etc. Also, for example, the first keyword can be a professional field word such as "basin", and based on the first keyword, professional sticker materials introducing the corresponding field can be recommended for the video, making the corresponding professional field word more understandable, etc.

[0047] In some embodiments, a semantic analysis is performed on the text content, and the analyzed semantic result is matched with a predefined keyword meaning to determine a first successfully matched keyword.

[0048] In some embodiments, in order to improve the efficiency and accuracy of identifying the first keyword, as shown in FIG. 5 , an Automatic Speech Recognition (ASR) technology can be used to identify the text content of the target audio data to obtain phrases, and a Natural Language Processing (NLP) technology can be used to understand the meaning of the corresponding text phrases to obtain the corresponding first keyword.

[0049] In some embodiments, the material recommended based on the first keyword can ensure the relevance of the recommended material and the video content on the content dimension, so as to better render the corresponding video content. For example, as shown in Figure 6 (in the figure, the corresponding first keyword is displayed in the form of subtitles, so that the person skilled in the art can more intuitively understand the solution), after performing semantic analysis based on the text content of the original video, if the first keyword obtained is "haha", the material can be recommended sticker material of "applause", so that in the processed video, the sticker of "applause" is displayed for the audio of "haha", which renders a more joyful atmosphere, and the matching degree between the added recommended material and the video content is higher, so that the addition of the recommended material does not seem abrupt.

[0050] In some embodiments of the present disclosure, as shown in FIG. 7, extracting video content features based on analyzing an original video includes steps 701-702.

[0051] In step 701, a voice detection process is performed on the target audio data of the original video to obtain the corresponding spectrum data.

[0052] In some embodiments, it is considered that in some scenarios, the target audio data can embody the content features of the original video even if the target audio data cannot be converted into the corresponding text content, for example, when the target audio data includes sounds such as "applause" or "explosion", adding recommended material based on such target audio data can further enhance the atmosphere of the original video according to the corresponding audio.

[0053] Therefore, it is obvious that by performing voice detection processing on the target audio data mentioned in the above embodiment, and extracting corresponding spectrum data, some information that cannot be converted into text content but embodies the content characteristics of the video can be extracted from the spectrum data.

[0054] In step 702, an analysis process is performed on the spectrum data to obtain a second keyword.

[0055] In some embodiments, an analysis process can be performed on the spectral data to obtain a second keyword, and then a recommended material corresponding to the corresponding spectral data can be obtained based on the second keyword.

[0056] In some embodiments, the spectral data can be input into a deep learning model that has been previously trained based on a large amount of sample data, and a second keyword can be obtained that is output by the deep learning model.

[0057] In some other embodiments, the acquired spectrum data can be matched with the spectrum data of each preset keyword, and a second keyword corresponding to the spectrum data can be determined based on the matching degree, for example, if the matching degree between the acquired spectrum data and the spectrum data corresponding to the keyword "explosion" is greater than a preset threshold, the second keyword corresponding to the target audio data can be determined to be "explosion".

[0058] Here, referring to FIG. 8 , when determining recommended materials, the first keyword and the second keyword can be jointly recommended together, where the second keyword can be a corresponding second keyword identified based on an audio event detection (AED) technology, and the corresponding recommended materials are further determined based on the first keyword and the second keyword.

[0059] For example, as shown in FIG. 9 , after performing a voice detection process on the target audio data of the original video and obtaining corresponding spectrum data, if the corresponding second keyword obtained based on the spectrum data is “explosion”, the matching recommended material is an “explosion” sticker, and therefore, the corresponding “explosion” sticker is displayed on the corresponding video frame, and the video content including the explosion audio is further rendered.

[0060] To summarize, the video processing method of the embodiment of the present disclosure takes any feature reflecting the video content as a video content feature, the extracted video content feature has a strong correlation with the video content, ensures the correlation between the material recommended based on the video content feature and the video content, and provides technical support for the personalized processing effect of the video.

[0061] According to the above embodiment, after the video content feature is obtained, the recommended material that matches the video content feature is further recommended, and the processing effect for the video is determined according to the recommended material. The following describes the determination of the recommended material in combination with a specific example.

[0062] In some embodiments of the present disclosure, as shown in FIG. 10, obtaining at least one recommended material matching a video content characteristic includes steps 1001-1002.

[0063] In step 1001, a video style feature is determined based on the video images of the original video.

[0064] It can be easily understood that, even if the video content features are similar, the corresponding video styles are different, so adding similar recommended materials will affect the matching degree with the video content. For example, the first keyword obtained by performing semantic analysis based on the target audio data of the original video S1 is "haha", and the first keyword obtained by performing semantic analysis based on the target audio data of the original video S2 is also "haha". However, the person who utters "haha" in S1 is a cartoon character, and the person who utters "haha" in S2 is a real person, so if the recommended materials are adapted to these two styles, it will obviously affect the video processing effect.

[0065] In the embodiment of the present disclosure, in order to ensure the processing effect of the video, a video style feature is determined based on the video image of the original video, where the video style feature includes, but is not limited to, the image feature of the video content, the theme style feature of the video content, the shooting object feature contained in the video, etc.

[0066] It should be explained that in different application scenarios, the manners of determining video style features based on the video images of the original video are different, and an exemplary description is given as follows.

[0067] In some embodiments, as shown in FIG. 11 , a convolutional network model is trained in advance based on a large amount of sample data, a video image is input into the corresponding convolutional network model, and the video style features output by the convolutional network model are obtained.

[0068] In some embodiments, as shown in FIG. 12, determining a video style characteristic based on a video image of an original video includes steps 1201-1202.

[0069] In step 1201, an image identification process is performed on the video images of the original video, and at least one shooting target is determined based on the identification result.

[0070] Here, the subject to be photographed may be the main body included in the video image, and includes, but is not limited to, people, animals, furniture, tableware, etc.

[0071] In step 1202, a weighting calculation is performed for at least one shooting object according to a preset object weight, and a video style feature corresponding to the original video is determined by matching the calculation result with a preset style classification.

[0072] In this embodiment, to determine the video style, an object type of each shooting object can be identified, a preset database can be queried, and an object weight of each shooting object can be obtained, where the database includes each shooting type and corresponding object weight obtained by training based on a large amount of sample data, and a weighting calculation can be performed for at least one shooting object based on the preset object weight, and a predetermined style classification can be matched based on the calculation result, and a video style feature corresponding to the style classification that is successfully matched can be determined.

[0073] Here, as shown in Fig. 13, multi-frame video frames are extracted from the original video, and the multi-frame video frames are used as video images of the original video, so that the style identification efficiency can be further improved. In some embodiments, multi-frame video frames may be extracted from the original video based on a preset time interval (e.g., 1 second), or a corresponding video segment may be extracted at regular intervals based on a preset time length, and the multi-frame video frames included in the video segment may be used as video images of the original video.

[0074] In some embodiments, after obtaining the corresponding video image, the video image can be input into a pre-trained image smart identification model, and at least one shooting object can be determined based on the identification result. In the figure, the shooting objects include human faces, objects, environments, etc., and further, classification features t1, t2, t3 corresponding to each shooting object are identified, and when the corresponding object weights are z1, z2, z3 respectively, the value of t1×z1+t2×z2+t3×z3 is calculated as the calculation result, and based on this calculation result, it is matched with a pre-set style classification to determine the video style feature corresponding to the original video.

[0075] In step 1002, at least one recommended material matching the video style characteristics and the video content characteristics is obtained.

[0076] In some embodiments, after obtaining the video style features, at least one recommended material matching the video style features and the video content features is obtained, so that the recommended material matches the video content based on the video style features and the video content features, and further enhances the video processing effect.

[0077] In some embodiments, as shown in FIG. 14 , a material library that matches the video style characteristics may be first obtained, and at least one recommended material that matches the video content characteristics is obtained in the material library, thereby ensuring that the obtained recommended material not only matches the video content but also is consistent with the style of the video.

[0078] For example, when the video style characteristic is "girl animation", a material library consisting of various materials in girl style matching "girl animation" is obtained, and further, by matching video materials in the material library consisting of various materials in girl style based on the video content characteristic, it is ensured that all the obtained recommended materials are in girl style.

[0079] In some embodiments of the present disclosure, as shown in FIG. 15, obtaining at least one recommended material matching a video content characteristic includes steps 1501-1504.

[0080] In step 1501, a play duration of a video frame corresponding to a video content feature in an original video is determined, where the video content feature is generated based on the video content of the video frame.

[0081] In some embodiments, since not all video images of each frame contain similar video content features, and the video content features are generated based on the video content of the video frames, determining the playback time of the video frames in the original video that correspond to the video content features facilitates recommending and adding corresponding material based on this playback time only for video frames that contain corresponding video content features.

[0082] In step 1502, a time identifier is marked for a video content feature based on the play time of the video frame.

[0083] In some embodiments, marking temporal identifiers for video content features based on the play duration of video frames facilitates matching of recommended material over time.

[0084] In step 1503, if it is determined that there are a plurality of video content features corresponding to the time identifier, the plurality of video content features are combined into a video feature set, and at least one recommended material matching the video feature set is obtained, where the plurality of video content features includes the video content feature.

[0085] In some embodiments, once it is determined that there are multiple corresponding video content features for a single time identifier, i.e., a single video frame corresponding to a single time, the multiple video content features are combined into a video feature set to obtain at least one recommended material that matches the video feature set.

[0086] In some embodiments, multiple video content features are combined to generate multiple video content feature combinations (video feature sets), a pre-defined correspondence is consulted to determine whether there is any enhancement material corresponding to each video content feature combination, and if there is no match with the enhancement material, the video content feature combination is split into individual content features to match the recommended material; if there is a match with the enhancement material, the enhancement material is the corresponding recommended material.

[0087] It should be understood that the enhanced material herein does not necessarily include a simple combination of recommended materials corresponding to a plurality of video content features, but may be different recommended materials with a stronger sense of atmosphere that are generated to further enhance the video atmosphere when there is an association between a plurality of video content features.

[0088] For example, in multiple video content features, if a first keyword corresponding to video content feature 1 is “haha” and a second keyword corresponding to video content feature 2 is “applause”, the recommended material jointly determined based on the first keyword and the second keyword is a transition effect material, rather than the sticker material corresponding to “haha” and “applause” respectively mentioned above.

[0089] If, in step 1504, it is determined that a corresponding video content feature exists for a time identifier, at least one recommended material that matches the video content feature is obtained.

[0090] In some embodiments, if it is determined that a corresponding video content feature exists for a time identifier, then at least one recommended material that matches the video content feature is obtained, i.e., in the case of a single video content feature, at least one recommended material that matches alone is obtained.

[0091] Furthermore, after obtaining the corresponding recommended material, when performing video processing on the original video based on the recommended material to generate a target video, a material addition time of the recommended material matching the video content feature is set based on the time identifier of the video content feature, and this addition time is consistent with the display time of the video frame of the corresponding video content feature.

[0092] Furthermore, a clip process is performed on the original video according to the material addition time of the recommended material to generate a target video, so that the corresponding recommended material is added only when the video frame of the video content feature corresponding to the material is played, and the addition of the material is avoided to be inconsistent with the video content.

[0093] In addition, in the actual execution process, some materials, such as music effect materials, transition effect materials, etc., do not have size information, and some materials, such as sticker materials and text materials, etc., have size information. When adding some materials with size information, it is necessary to determine the adding area of ​​these materials with size information, so as to avoid occluding important display contents in the video, such as avoid occluding a person's face in the video frame.

[0094] In some embodiments, if the material type of the recommended material satisfies a predetermined target type, i.e., if the recommended material has an additional size information attribute, the corresponding material is deemed to satisfy the predetermined target type, and a target video frame corresponding to the material addition time of the recommended material is obtained from the original video, and image recognition is performed on the target video fragment frame to obtain a body area of ​​the subject to be shot, where the body area may be displayed as any position information of the position where the subject is located, for example, a central coordinate point, or for example, a position range, etc.

[0095] For example, when the material to be added is added based on the first keyword "haha", the subject to be filmed is the vocalization subject corresponding to the "haha" audio, and after determining the main body region of the subject to be filmed, a material region for adding the recommended material to the target video frame is determined based on the main body region of the subject to be filmed.

[0096] Here, in some embodiments, a material type label of the recommended material is determined, and based on this material type label, a pre-defined correspondence is consulted to determine region features of the material region (e.g., a background region on an image), and a region in the target video frame that matches this region feature is determined as the material region.

[0097] In some other embodiments, an object type label of the object to be shot is determined, and based on this object type label, a pre-established correspondence is queried to determine area features of the material area (for example, if the object to be shot is a human face type, the corresponding area feature corresponds to above the head, etc.), and an area in the target video frame that matches this area feature is determined as the material area.

[0098] After the material area is determined, a clip process is performed on the original video based on the material addition time and material area of ​​the recommended material to generate a target video, and the corresponding material is added to the material area in the video frame corresponding to the material addition time. Here, the material area may be displayed as a center point coordinate where the material is added to the corresponding video frame, or may be displayed as a coordinate range of the material where the material is added to the corresponding video frame. Here, the server that determines the body area, etc., may not be the same server as the server that performs the style feature identification. In order to improve the identification efficiency, the server that performs the style feature identification may be a local server, and in order to reduce the pressure of the calculation power of the material addition time and material area analysis, the server that is identified based on the material addition time and material area of ​​the recommended material may be a remote server.

[0099] In some embodiments, as shown in Fig. 16, when the recommended material includes F1 and F2 with size attributes, the material addition time of the recommended material matching the video content feature is set as t1 and t2 according to the time identifier of the video content feature, and the original video is clipped according to the material addition time of the recommended material to obtain a video segment clip1 corresponding to F1 and a video segment clip2 corresponding to F2. After sending clip1 and clip2 to the corresponding server, the corresponding server optimizes the material to be added, performs image identification on the target video piece frame to obtain the main area of ​​the shooting object, and further determines the material area to add the recommended material to the target video frame according to the main area of ​​the shooting object, obtains the target video segment sticker1 corresponding to clip1 and the target video segment sticker2 corresponding to clip2 according to the material addition time and material area of ​​the recommended material, and edits the original video according to sticker1 and sticker2 to obtain the corresponding target video.

[0100] To summarize, the video processing method of the embodiment of the present disclosure determines video content features, and then determines at least one recommended material that matches the multi-dimensional video content features, ensures the positional and temporal correspondence between the material and the video frames, and further ensures that the video processing effect meets the unique characteristics of the video content.

[0101] In order to realize the above embodiment, the present disclosure further proposes a video processing device. Figure 17 is a structural schematic diagram of a video processing device according to an embodiment of the present disclosure, which may be realized by software and / or hardware, and may be generally implemented in electronic equipment. As shown in Figure 17, the device includes an extraction module 1710, an acquisition module 1720, and a processing module 1730.

[0102] The extraction module 1710 is used to extract video content features based on the analysis of the original video.

[0103] The acquisition module 1720 is used to acquire at least one recommended material that matches the video content characteristics.

[0104] The processing module 1730 is used to process the original video based on the recommended material, and generate a target video, which is a video generated after adding the recommended material to the original video.

[0105] The video processing device according to the embodiments of the present disclosure can execute the video processing method according to any embodiment of the present disclosure, and has corresponding functional modules for executing the method and beneficial effects, which will not be further described herein.

[0106] To realize the above embodiments, the present disclosure further proposes a computer program product, which includes a computer program / instruction, which, when executed by a processor, realizes the video processing method in any of the above embodiments.

[0107] FIG. 18 is a structural schematic diagram of an electronic device according to an embodiment of the present disclosure.

[0108] Hereinafter, referring specifically to FIG. 18, a structural schematic diagram for realizing an electronic device 1800 in an embodiment of the present disclosure is shown. The electronic device 1800 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 personal computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop personal computers. The electronic device shown in FIG. 18 is merely an example, and does not impose any limitations on the functions and scope of use of the embodiment of the present disclosure.

[0109] As shown in Fig. 18, the electronic device 1800 may include a processor (e.g., a central processor, a graphics processor, etc.) 1801, and may execute various appropriate operations and processes based on a program stored in a read-only memory (ROM) 1802 or a program loaded from a memory 1808 into a random access memory (RAM) 1803. The RAM 1803 stores various programs and data necessary for the operation of the electronic device 1800. The processor 1801, the ROM 1802, and the RAM 1803 are connected to each other via a bus 1804. An input / output (I / O) interface 1805 is also connected to the bus 1804.

[0110] Typically, input devices 1806 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyro, etc., output devices 1807 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc., memory 1808 including, for example, a magnetic tape, hard disk, etc., and communication devices 1809 can be connected to the I / O interface 1805. The communication devices 1809 can allow the electronic device 1800 to exchange data with other devices by wireless or wired communication. Although FIG. 18 shows the electronic device 1800 having various devices, it should be understood that it is not necessary to implement or include all of the devices shown. More or fewer devices can be implemented or included.

[0111] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowcharts can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, including a computer program carried on a non-transitory computer-readable medium, the computer program including a program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device 1809, or may be installed from the memory 1808, or may be installed from the ROM 1802. When the computer program is executed by the processor 1801, it performs the above-mentioned functions defined in the video processing method of the embodiment of the present disclosure.

[0112] It should be explained that the computer-readable medium of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of both. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of more than one. More specific examples of the computer-readable storage medium may include, but are not limited to, an electrical connection having one or more conductors, a portable computer magnetic 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 memory device, a magnetic memory device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in combination with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include, but is not limited to, a propagated data signal having computer-readable program code carried thereon, either in baseband or as part of a carrier. Such a 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. A computer-readable signal medium may be any computer-readable medium other than a computer-readable storage medium, which may transmit, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained in the computer-readable medium may be transmitted by any suitable medium, including but not limited to, an electrical wire, an optical cable, RF (radio frequency), or the like, or any suitable combination of the above.

[0113] In some embodiments, the clients and servers may communicate using any network protocol now known or later developed, such as HyperText Transfer Protocol (HTTP), and may be communicatively connected (e.g., via a communications network) with digital data in any form or medium. Examples of communications networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet, and an end-to-end network (e.g., an ad hoc end-to-end network), and any network now known or later developed.

[0114] The computer readable medium may be included in the electronic device or may exist separately and not integrated into the electronic device.

[0115] The computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device executes the following steps: extracting video content features of an original video, obtaining at least one recommended material matching the video content features, and adding the recommended material to the original video to obtain a target video, thereby adding video material according to the video content of the video, improving the matching degree between the video content and the video material, and realizing personalized effect processing for the video.

[0116] Computer program code for carrying out the operations of the present disclosure can be written in one or more program design languages ​​or combinations thereof, including, but not limited to, object-oriented program design languages ​​such as Java, Smalltalk, C++, and may further include general procedural program design languages ​​such as "C" or similar program design 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. When referring to a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (e.g., connected via the Internet using an Internet Service Provider).

[0117] The flowcharts and block diagrams in the drawings illustrate possible system architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, program segment or part of code, which includes one or more executable instructions for implementing the specified logical function. It should be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than the order marked in the drawings. For example, two blocks shown in succession may actually be executed essentially in parallel or in the reverse order, depending on the functionality involved. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented in a dedicated hardware-based system that performs the specified functions or operations, or may be implemented in a combination of dedicated hardware and computer instructions.

[0118] The units described in the embodiments of the present disclosure may be implemented in a software manner or a hardware manner, and the names of the units do not constitute limitations on the units themselves in some cases.

[0119] The functionality described herein may be performed, at least in part, by one or more hardware logic components. For example, and 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 general purpose products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), etc.

[0120] In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain or store a program used by or in combination with an instruction execution system, device, or apparatus. 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 apparatus, or any suitable combination of the above. More specific examples of machine-readable storage media include one or more wire-based electrical connections, portable computer disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), optical fibers, compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0121] According to some embodiments of the present disclosure, the present disclosure provides a video processing method, the video processing method comprising: Extracting video content features based on an analysis of the original video; obtaining at least one recommended material matching the video content characteristics; and processing the original video based on the recommended material to generate a target video, the target video being a video generated after adding the recommended material to the original video.

[0122] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, the extracting of video content features based on the analysis of the original video includes: Performing a voice recognition process on the target audio data of the original video to obtain corresponding text content; and performing a semantic analysis process on the text content to obtain a first keyword.

[0123] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, the extracting of video content features based on the analysis of the original video includes: Performing a voice detection process on the target audio data of the original video to obtain corresponding spectrum data; and performing an analysis process on the spectrum data to obtain a second keyword.

[0124] According to some embodiments of the present disclosure, in a video processing method according to the present disclosure, the method of obtaining target audio data includes: obtaining all audio tracks of the video file of the original video to be displayed in a video clip application; performing an integration process on all of the audio tracks based on a time axis to generate total audio data; comparing a first time length of the total audio data with a second time length of the original video, and if the first time length is greater than the second time length, trimming the first time length of the total audio data to obtain the target audio data whose time length matches the second time length.

[0125] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, the step of performing integration processing on all the audio tracks based on a time axis to generate total audio data includes: detecting an audio identifier for each audio track; and when a target audio track representing a background music identifier is detected, performing an integration process on all audio tracks other than the target audio track based on a time axis to generate total audio data.

[0126] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, obtaining at least one recommended material matching the video content characteristics includes: determining a video style characteristic based on video images of the original video; and obtaining at least one recommended material that matches the video style characteristics and the video content characteristics.

[0127] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, the determining of the video style feature based on the video image of the original video includes: performing an image identification process on the video images of the original video and determining at least one shooting target based on the identification result; The method includes performing a weighting calculation for the at least one shooting object based on a preset object weight, and matching the calculation result with a preset style classification to determine a video style feature corresponding to the original video.

[0128] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, obtaining at least one recommended material matching the video content characteristics includes: determining, in the original video, a play duration of a video frame corresponding to the video content feature generated based on a video content of the video frame; marking a time identifier for the video content feature based on a play time of the video frame; if determining that there are a plurality of video content features corresponding to the time identifier, combining the plurality of video content features into a video feature set and obtaining at least one recommended material matching the video feature set, where the plurality of video content features includes the video content feature; If it is determined that only the video content characteristics correspond to the time identifier, obtaining at least one recommended material that matches the video content characteristics.

[0129] According to some embodiments of the present disclosure, in the video processing method of the present disclosure, the step of performing video processing on the original video based on the recommended material to generate a target video includes: setting a material addition time of the recommended material matching the video content characteristics based on the time identifier of the video content characteristics; and performing clip processing on the original video based on the material addition time of the recommended material to generate a target video.

[0130] According to some embodiments of the present disclosure, in the video processing method of the present disclosure, the step of performing clip processing on the original video based on the material addition time of the recommended material to generate a target video includes: When a material type of the recommended material satisfies a preset target type, acquiring a target video frame corresponding to a material addition time of the recommended material from the original video; performing image identification on the target video frame to obtain a body region of a subject; determining a material area onto which the recommended material is to be added on the target video frame based on a body area of ​​the subject; and generating a target video by performing clip processing on the original video based on the material addition time of the recommended material and the material area.

[0131] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, the detecting of the audio identifier for each of the audio tracks comprises: identifying a voice characteristic of the audio corresponding to each audio track; Matching voice characteristics of audio corresponding to each audio track with voice characteristics corresponding to each predetermined audio identifier; and determining an audio identifier for each audio track based on the matching results.

[0132] According to some embodiments of the present disclosure, in the video processing method according to the present disclosure, obtaining at least one recommended material matching the set of video features includes: Querying a predefined correspondence relationship based on the video feature set to determine whether the video feature set is an enhancement material; partitioning the set of video features into recommended material that matches a single content feature if no enhancement material is matched; When matching with the reinforcement material, setting the reinforcement material as the corresponding recommended material.

[0133] According to some embodiments of the present disclosure, the present disclosure provides a video processing device, the video processing device comprising: an extraction module for extracting video content features based on an analysis of the original video; an acquisition module for acquiring at least one recommended material matching the video content characteristics; and a processing module for performing video processing on the original video based on the recommended material to generate a target video, the target video being a video generated after adding the recommended material to the original video.

[0134] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the extraction module comprises: Perform voice recognition processing on the target audio data of the original video to obtain corresponding text content; The text content is subjected to a semantic analysis process to obtain a first keyword.

[0135] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the extraction module comprises: Perform a voice detection process on the target audio data of the original video to obtain corresponding spectrum data; The spectrum data is subjected to an analysis process to obtain a second keyword.

[0136] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the extraction module obtains all audio tracks of the video file of the original video that are displayed in a video clip application; performing an integration process on all of the audio tracks based on a time axis to generate total audio data; A first time length of the total audio data is compared with a second time length of the original video, and if the first time length is greater than the second time length, the first time length of the total audio data is trimmed to obtain the target audio data whose time length matches the second time length.

[0137] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the extraction module comprises: Detect the audio identifier for each audio track, When a target audio track representing a background music identifier is detected, a merging process is performed on all audio tracks other than the target audio track based on a time axis to generate total audio data.

[0138] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the acquisition module specifically includes: determining a video style characteristic based on video images of the original video; A method for obtaining at least one recommended material that matches the video style characteristics and the video content characteristics.

[0139] According to some embodiments of the present disclosure, in the video processing device of the present disclosure, the acquisition module specifically performs an image identification process on the video image of the original video, and determines at least one shooting object according to the identification result; A weighting calculation is performed on the at least one shooting object based on a preset object weight, and a result of the weighting calculation is matched with a preset style classification to determine a video style feature corresponding to the original video.

[0140] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the acquisition module includes: determining, in the original video, a playing time of a video frame corresponding to the video content feature generated based on a video content of the video frame; marking a time identifier for the video content feature based on the play time of the video frame; When it is determined that there are a plurality of video content features corresponding to the same time identifier, combining the plurality of video content features into a video feature set, and obtaining at least one recommended material matching the video feature set; If it is determined that a corresponding video content feature exists for the same time identifier, the video content feature is used to obtain at least one recommended material that matches the corresponding video content feature.

[0141] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the acquisition module includes: determining a material addition time of the recommended material matching the video content characteristics based on the time identifier of the video content characteristics; The clip processing is used to generate a target video by performing clip processing on the original video based on the material addition time of the recommended material.

[0142] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the acquisition module includes: If the material type of the recommended material satisfies a preset target type, a target video frame corresponding to a material addition time of the recommended material is obtained from the original video; Perform image identification on the target video fragment frame to obtain a main body area of ​​the shooting target; determining a material area for adding the recommended material onto the target video frame based on a body area of ​​the subject; The clip processing is used to generate a target video by performing clip processing on the original video based on the material addition time of the recommended material and the material area.

[0143] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the extraction module comprises: Identifying the voice characteristics of the audio corresponding to each audio track; Matching voice characteristics of audio corresponding to each audio track with voice characteristics corresponding to each predetermined audio identifier; It is used to determine an audio identifier for each audio track based on the matching results.

[0144] According to some embodiments of the present disclosure, in the video processing device according to the present disclosure, the acquisition module includes: Querying a predefined correspondence relationship based on the video feature set to determine whether the video feature set is an enhancement material; If no match is found with the reinforcement material, the set of video features is divided into recommended material that matches the single content feature; When matching to an improvement material, it is used to make the improvement material the corresponding recommended material.

[0145] According to some embodiments of the present disclosure, the present disclosure provides an electronic device, the electronic device comprising: A processor; a memory for storing instructions executable by the processor; The processor is adapted to read the executable instructions from the memory and execute the instructions to implement any one of the video processing methods according to the present disclosure.

[0146] According to some embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium having a computer program stored therein, the computer program being used to execute any one of the video processing methods described herein.

[0147] The above description is merely a description of the preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the disclosure scope of the present disclosure is not limited to the technical solution of the specific combination of the above technical features, and also includes other technical solutions formed by any combination of the above technical features or features equivalent thereto, such as the above features and the technical features having similar functions disclosed in the present disclosure (but not limited thereto) substituted with each other, without departing from the concept of the disclosure.

[0148] It should be noted that although operations are illustrated using a particular sequence, this should not be understood as requiring that these operations be performed in the particular sequence or order shown. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although the above discussion includes some specific implementation details, these should not be construed as limitations on the scope of the disclosure. Some features that are described in the context of a single embodiment may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may be implemented in multiple embodiments alone or in any suitable subcombination.

[0149] Although the present subject matter has been described using language specific to structural features and / or methodological logical operations, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or operations described above. Rather, the specific features and operations described above are merely example forms for implementing the claims.

Claims

1. 1. A video processing method comprising the steps of: Extracting video content features based on an analysis of the original video; obtaining at least one recommended material that matches the video content characteristics; performing processing on the original video based on the recommended material to generate a target video, the target video being a video generated after adding the recommended material to the original video.

2. The step of extracting video content features based on an analysis of the original video includes: performing a voice recognition process on the target audio data of the original video to obtain corresponding text content; The video processing method according to claim 1 , further comprising: performing a semantic analysis process on the text content to obtain a first keyword.

3. The step of extracting video content features based on an analysis of the original video includes: performing a voice detection process on the target audio data of the original video to obtain corresponding spectrum data; The video processing method according to claim 1 or 2, further comprising the step of: performing an analysis process on the spectrum data to obtain a second keyword.

4. The method for obtaining target audio data includes: obtaining all audio tracks of the video file of the original video to be displayed in a video clip application; performing an integration process on all the audio tracks based on a time axis to generate total audio data; and comparing a first time length of the total audio data with a second time length of the original video, and if the first time length is greater than the second time length, trimming the first time length of the total audio data to obtain the target audio data whose time length matches the second time length.

5. The step of performing an integration process on all the audio tracks based on a time axis to generate total audio data includes: detecting an audio identifier for each audio track; The video processing method according to claim 4, further comprising the step of: when a target audio track representing a background music identifier is detected, performing integration processing on all audio tracks other than the target audio track based on a time axis to generate total audio data.

6. The step of obtaining at least one recommended material that matches the video content characteristics includes: determining a video style characteristic based on video images of the original video; The method of claim 1 , further comprising the step of: obtaining at least one recommended material that matches said video style characteristics and said video content characteristics.

7. The step of determining a video style feature based on a video image of the original video further comprises: performing an image identification process on the video image of the original video, and determining at least one shooting object based on the identification result; The video processing method of claim 6, further comprising: performing a weighting calculation for the at least one shooting object based on a preset object weight; and matching the calculation result with a preset style classification to determine a video style feature corresponding to the original video.

8. The step of obtaining at least one recommended material that matches the video content characteristics includes: determining, in the original video, a playing time of a video frame corresponding to the video content feature generated based on a video content of the video frame; marking a time identifier for the video content feature based on the play time of the video frame; if it is determined that there are a plurality of video content features corresponding to the time identifier, combining the plurality of video content features into a video feature set and obtaining at least one recommended material matching the video feature set, the plurality of video content features including the video content feature; The video processing method of claim 1 , further comprising the step of: if it is determined that only a video content feature corresponds to the time identifier, obtaining at least one recommended material that matches the video content feature.

9. The step of processing the original video based on the recommended material and generating a target video, the target video being a video generated after adding the recommended material to the original video, includes: setting a material addition time of the recommended material matching the video content characteristics based on the time identifier of the video content characteristics; 9. The video processing method according to claim 8, further comprising the step of: performing clip processing on the original video based on a material addition time of the recommended material to generate a target video.

10. The step of generating a target video by performing clip processing on the original video based on the material addition time of the recommended material includes: When a material type of the recommended material satisfies a preset target type, acquiring a target video frame corresponding to a material addition time of the recommended material from the original video; performing image identification on the target video frame to obtain a body region of a subject; determining a material area on the target video frame for adding the recommended material based on a body area of ​​the subject; 10. The video processing method according to claim 9, further comprising: performing clip processing on the original video based on the material addition time of the recommended material and the material area to generate a target video.

11. said step of detecting an audio identifier for each audio track comprising: identifying voice characteristics of the audio corresponding to each audio track; matching voice characteristics of audio corresponding to each audio track with voice characteristics corresponding to each predetermined audio identifier; A method according to any one of claims 5 to 10, further comprising the step of: determining an audio identifier for each audio track based on the matching results.

12. The step of obtaining at least one recommended material that matches the video feature set includes: Querying a predefined correspondence relationship based on the video feature set to determine whether the video feature set is a corresponding enhancement material; if no match is found for the reinforcement material, splitting the set of video features into recommended material that matches a single content feature; A method according to any one of claims 8 to 10, further comprising the step of: if the enhanced material matches the enhanced material, setting the enhanced material as the corresponding recommended material.

13. 1. A video processing device comprising: an extraction module for extracting video content features based on an analysis of the original video; an acquisition module for acquiring at least one recommended material matching the video content characteristics; a processing module for performing processing on the original video based on the recommended material to generate a target video, the target video being a video generated after adding the recommended material to the original video.

14. An electronic device, A processor; a memory for storing instructions executable by the processor; An electronic device, the processor reading the executable instructions from the memory and executing the executable instructions to implement the video processing method of any one of claims 1 to 12.

15. 13. A computer readable storage medium having a computer program stored thereon, the computer program being used to perform a video processing method according to any one of claims 1 to 12.

16. A computer program comprising instructions which, when executed by a processor, implements the video processing method of any one of claims 1 to 12.

Images