CN111970565A - Video data processing method and device, electronic equipment and storage medium - Google Patents

Abstract

The present application discloses a video data processing method, device, electronic device and storage medium, and relates to the technical field of data processing. The method includes: acquiring a video to be processed and a target bit rate corresponding to the video to be processed, where the target bit rate is lower than an initial bit rate of the video to be processed; Perform transcoding processing; obtain the quality index value corresponding to the video to be processed after the transcoding process; if the difference between the quality index value and the quality threshold value is greater than the first threshold, adjust the target bit rate, and The transcoding process is performed on the video to be processed based on the adjusted target bit rate until the difference is less than or equal to the first threshold. The method realizes that the target bit rate of the video to be processed is adjusted on the premise of ensuring the video quality of the video to be processed, thereby saving the bit rate and the network bandwidth.

Description

Video data processing method, device, electronic device and storage medium

technical field

The present application relates to the technical field of video processing, and more particularly, to a video data processing method, apparatus, electronic device and storage medium.

Background technique

With the development of network technology, video services have developed rapidly, and users have higher and higher requirements for the quality of the videos they watch. In a related manner of improving video quality, video data may be transcoded. However, with the increase of types of video data and the increase of video service traffic, in order to ensure video quality, when transcoding video data, there is still a problem of wasted bit rate, which in turn results in wasted network bandwidth.

SUMMARY OF THE INVENTION

The present application proposes a video data processing method, device, electronic device and storage medium to improve the above problems.

In a first aspect, an embodiment of the present application provides a video data processing method, the method includes: acquiring a video to be processed and a target bit rate corresponding to the video to be processed, where the target bit rate is lower than the to-be-processed video The initial bit rate of the video; the video to be processed is transcoded based on the target bit rate; the quality indicator value corresponding to the video to be processed after the transcoding process is obtained; if the quality indicator value and the quality threshold The difference is greater than the first threshold, adjust the target bit rate, and perform the transcoding process on the video to be processed based on the adjusted target bit rate, until the difference is less than or equal to the first threshold.

In a second aspect, an embodiment of the present application provides a video data processing apparatus, the apparatus includes: a first acquisition module, configured to acquire a video to be processed and a target bit rate corresponding to the video to be processed, the target code The rate is lower than the initial bit rate of the video to be processed; the first processing module is used to transcode the video to be processed based on the target bit rate; the second acquisition module is used to acquire and transcode after processing The quality index value corresponding to the video to be processed; the second processing module is used to adjust the target bit rate if the difference between the quality index value and the quality threshold is greater than the first threshold, and based on the adjusted The target bit rate performs the transcoding process on the video to be processed until the difference is less than or equal to the first threshold.

In a third aspect, embodiments of the present application provide an electronic device, comprising: one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and Configured to be executed by the one or more processors, the one or more application programs are configured to execute the video data processing method provided by the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a program code is stored in the computer-readable storage medium, and the program code can be invoked by a processor to execute the video provided in the first aspect above data processing method.

A video data processing method, device, electronic device and storage medium provided by the present application, by acquiring the video to be processed and the target bit rate corresponding to the video to be processed, and then performing transcoding processing on the video to be processed based on the target bit rate, and then acquiring The quality index value corresponding to the video to be processed after the transcoding process, and then if the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate, and based on the adjusted target bit rate The video to be processed is processed. The transcoding process is performed until the difference is less than or equal to the first threshold. Thus, the above-mentioned method realizes that the video to be processed is transcoded based on a target bit rate lower than the initial bit rate of the video to be processed, and the quality index value corresponding to the video to be processed after the transcoding process is different from the quality threshold value. When the difference is greater than the first threshold, the target code rate is adjusted again, and the video to be processed is transcoded again based on the adjusted target code rate until the difference is less than or equal to the first threshold, so that it can be The target bit rate of the video is adjusted on the premise of the video quality, so as to save the bit rate and network bandwidth.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

FIG. 1 shows a schematic diagram of an application environment provided by an embodiment of the present application.

FIG. 2 shows a flowchart of a video data processing method provided by an embodiment of the present application.

FIG. 3 shows a flowchart of a video data processing method provided by another embodiment of the present application.

FIG. 4 shows a schematic diagram of a splitting manner for splitting a video to be transcoded according to this embodiment.

FIG. 5 shows a flowchart of a method corresponding to a manner of determining a quality threshold corresponding to a plurality of video clips according to an embodiment of the present application.

FIG. 6 shows a schematic diagram of a manner for determining a quality threshold corresponding to a plurality of video clips according to the content complexity corresponding to each of the plurality of video clips according to an embodiment of the present application.

FIG. 7 shows a flow chart of a method corresponding to another manner of determining quality thresholds corresponding to multiple video clips according to an embodiment of the present application.

FIG. 8 shows a schematic diagram of a manner for determining a quality threshold corresponding to a plurality of video clips according to respective clip positions corresponding to the plurality of video clips according to an embodiment of the present application.

FIG. 9 shows a flowchart of a method corresponding to yet another manner of determining quality thresholds corresponding to multiple video clips according to an embodiment of the present application.

FIG. 10 shows a flowchart of a video data processing method provided by another embodiment of the present application.

FIG. 11 shows a flowchart of a video data processing method provided by still another embodiment of the present application.

FIG. 12 shows a structural block diagram of a video data processing apparatus provided by an embodiment of the present application.

FIG. 13 shows a structural block diagram of an electronic device provided by an embodiment of the present application.

FIG. 14 shows a storage unit for storing or carrying a program code for implementing the video data processing method according to the embodiment of the present application according to the embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application.

With the improvement of people's living standards, the penetration rate of smart terminals in daily use has almost reached universal coverage, resulting in an extremely high growth trend in the number and frequency of viewing users of video services such as short videos or webcasts. At the same time, users have higher and higher demands on the quality of the videos they watch.

As a way to improve the video quality, the video quality can be improved by transcoding the video data. Specifically, the video quality can be improved by optimizing the transcoding model and using the optimized transcoding model. However, training the transcoding model requires a large amount of data sources, and different training models have different training speeds and accuracy for different scales of data or different types of data. Simply relying on optimizing the transcoding model can improve video quality. , the optimal transcoding result may not be obtained; and in order to ensure the transcoding efficiency, the video data needs to be transcoded according to a unified transcoding format, and as the video data increases, the server will increase the storage of the video data. In this way, for some video data with relatively simple video content, if it is still transcoded in a unified transcoding format, it may lead to a waste of bit rate, and thus a waste of network bandwidth resources.

After long-term research, the inventor found that the video to be processed and the target bit rate corresponding to the video to be processed can be obtained, and then the video to be processed can be transcoded based on the target bit rate, and then the video corresponding to the video to be processed after the transcoding process can be obtained. and then if the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate, and perform the transcoding process on the video to be processed based on the adjusted target bit rate until the difference is less than or equal to the first threshold. Thus, the above-mentioned method realizes that the video to be processed is transcoded based on a target bit rate lower than the initial bit rate of the video to be processed, and the quality index value corresponding to the video to be processed after the transcoding process is different from the quality threshold value. When the difference is greater than the first threshold, the target code rate is adjusted again, and the video to be processed is transcoded again based on the adjusted target code rate until the difference is less than or equal to the first threshold, so that it can be The target bit rate of the video is adjusted on the premise of the video quality, so as to save the bit rate and network bandwidth.

Therefore, in order to improve the above-mentioned problems, the inventor proposes a video data processing method provided by the present application that can adjust the target bit rate of the video to be processed under the premise of ensuring the video quality of the video to be processed, thereby saving the bit rate and network bandwidth, Apparatus, electronic equipment, and storage medium.

The application environment involved in the embodiments of the present application is first introduced below.

Please refer to FIG. 1 , which is a schematic diagram of an application environment of a video data processing method provided by an embodiment of the present application. As shown in FIG. 1 , the application environment can be understood as a network system 10 provided by an embodiment of the present application. The network system 10 includes: a mobile terminal 11 and a server 12. Optionally, the mobile terminal 11 can be any device with communication and storage functions, including but not limited to PC (Personal Computer, personal computer), PDA (tablet computer), smart TV, Smart phones, smart wearable devices or other smart communication devices with network connection function, the server 12 can be a server (network access server), or a server cluster (cloud server) composed of several servers, or it can be It is a cloud computing center (database server).

In the embodiment of the present application, the video shot by the user through the mobile terminal 11 can be sent to the server 12 through the network for storage. As the number of videos increases, the server 12 can perform segmentation processing on the video to be stored to obtain multiple video segments. segment, and then adjust the bit rate of some video segments in the multiple video segments, or adjust the bit rate of each video segment in the multiple video segments, so as to achieve the premise of maintaining the video quality. , reduce its bit rate as much as possible to save the bit rate and save network bandwidth resources.

It should be noted that, as a way to improve the transcoding efficiency, in the embodiment of the present application, when the video to be stored is segmented, some servers may be responsible for segmenting the video, while other different servers are responsible for segmenting the video. The divided video is transcoded, so that the video segmentation and video transcoding can be processed in parallel, thereby improving the transcoding efficiency. The specific numbers of some servers and other servers may not be limited.

The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Please refer to FIG. 2 , which shows a flowchart of a video data processing method provided by an embodiment of the present application. This embodiment provides a video data processing method, which can be applied to a server. The method includes:

Step S110: Obtain the video to be processed and a target bit rate corresponding to the video to be processed.

In this embodiment, the video to be processed may be a video to be stored whose file size is greater than or equal to the target threshold. For example, the video to be processed may be a video with a file size greater than or equal to 10M, wherein the specific value of the target threshold may not be limited. In addition to the 10M, other values, such as 20M or 30M, may also be used.

As a way to reduce the storage space occupied by the video to be processed, a target bit rate corresponding to the video to be processed can be obtained, and then the video to be processed can be transcoded based on the target bit rate to save the bit rate.

In this embodiment, the target bit rate corresponding to the video to be processed can be set lower than the initial bit rate of the video to be processed. For example, if the initial bit rate of the video to be processed is 2048kbps, the target bit rate can be set to 1024kbps ( This is only an example, and the specific value may not be limited).

Optionally, in order to maintain the quality of the video to be processed as much as possible, when setting the target bit rate, as an implementation method, it may be determined whether the video to be processed belongs to a video file of an important level. The naming distinguishes whether the video to be processed belongs to the importance level. Optionally, a video file belonging to an important level may carry a special identifier, for example, the special identifier may be "imp".

In one embodiment, if the video to be processed is a video file belonging to an important level, the maximum value of the difference between the target bit rate and the initial bit rate can be set to be no greater than a third threshold, so that the target bit rate is lower than the initial bit rate. On the basis of the rate, it can be as close to the initial bit rate as possible, so as to achieve the highest fidelity video quality. In another embodiment, if the video to be processed is a video file that does not belong to the important level, the maximum value of the difference between the target bit rate and the initial bit rate can be set to be no greater than the fourth threshold, so that the to-be-processed video file can be reduced as much as possible. The bit rate of the video can be reduced as much as possible to reduce the storage space of the video to be processed, thereby saving network bandwidth resources in the process of transmitting the video to be processed. The fourth threshold is greater than the third threshold, and the specific values of the fourth threshold and the third threshold may not be limited. It should be noted that the target code rate set by the above two methods is lower than the initial code rate.

For example, in a specific application scenario, assuming that the initial bit rate is 2048kbps, the third threshold is 200kbps, and the fourth threshold is 500kbps, if the video to be processed is a video file belonging to an important level, then the target bit rate can be set to 1900kbps; if the video to be processed is a video file that does not belong to the important level, the target bit rate can be set to 1600kbps. It should be noted that the above numerical values are only described as examples, and do not constitute a limitation to this solution, and can be set according to technical requirements during actual implementation.

Step S120: Transcode the to-be-processed video based on the target bit rate.

Optionally, after obtaining the target bit rate, you can also obtain transcoding parameters corresponding to the video to be processed, so that the video to be processed can be transcoded based on the target bit rate and the transcoding parameters, so that the transcoded video can be transcoded. The bitrate of the video to be processed is the target bitrate. For example, assuming that the initial bit rate corresponding to the video to be processed is 2048kbps, and the target bit rate corresponding to the video to be processed is 1024kbps, then the bit rate of the transcoded video to be processed is 1024kbps. The transcoding parameters may include parameters such as the image width and height of the video to be processed, the transcoding type, and the transcoding frame rate.

Step S130: Obtain a quality index value corresponding to the video to be processed after the transcoding process.

As a method, the transcoded video to be processed may be compared with the video to be processed before transcoding to obtain a quality index value (ie a VMAF value) corresponding to the transcoded video to be processed. Among them, VMAF (Video Multimethod Assessment Fusion, video quality multi-method assessment fusion) is a video quality evaluation index that combines human vision model and machine learning. The VMAF index can be used to compare the quality and efficiency of various transcoding technologies. Optionally, in the calculation process, the quality index value may be calculated by comparing the value of each pixel of the video image to be processed after transcoding and the video image to be processed before transcoding.

Step S140: if the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate, and perform the transcoding process on the video to be processed based on the adjusted target bit rate, until the difference is less than or equal to the first threshold.

Wherein, the quality threshold (may be the VMAF quality threshold in this embodiment) may be preset. Optionally, the quality threshold may be set according to the initial bit rate of the video to be processed, and the quality threshold corresponding to the video to be processed with a higher initial bit rate may be greater than the quality threshold corresponding to the video to be processed with a lower initial bit rate. In this embodiment, the video picture quality corresponding to the quality threshold is close to the picture quality of the video to be processed.

As a method, when the quality index value corresponding to the video to be processed after the transcoding process is obtained, the difference between the quality index value and the quality threshold value can be obtained, and then it is determined whether the difference value is less than or equal to the first threshold value , so that the target bit rate can be flexibly adjusted according to the judgment result. Optionally, the first threshold may be understood as a threshold. Wherein, in some embodiments, the first threshold may be 0. In this case, if the quality index value is not equal to the quality threshold, the target bit rate needs to be adjusted. In other embodiments, the first threshold value may be in a relatively small range, for example, may be 0 to 5 (the specific value may be adjusted according to actual needs) and the like.

As an embodiment, if the difference between the quality index value and the quality threshold value is greater than the first threshold, and the quality index value is greater than the quality threshold value, the picture quality of the video to be processed in this case is relative to the picture corresponding to the quality threshold value The quality is closer to the picture quality of the video to be processed, and the code rate of the current video to be processed (that is, the aforementioned transcoded video) is the target code rate. In order to reduce the occupation of the storage space of the video to be processed, the target code can be reduced. rate, thereby reducing the file size of the video to be processed, thereby saving network transmission bandwidth. Wherein, the reduction range of the target code rate can be set according to actual needs, which is not limited here. In this way, in order to reduce the size of the video file as much as possible while ensuring the video quality of the video to be processed, the above-mentioned transcoding process can be performed again on the video to be processed based on the reduced target bit rate. Until the difference between the quality index value and the quality threshold is less than or equal to the first threshold.

As another implementation, if the difference between the quality index value and the quality threshold value is greater than the first threshold, and the quality index value is less than the quality threshold value, it means that the file size of the video to be processed in this case is small, that is, the file size of the video to be processed is small. In this case, the picture quality of the video to be processed is weaker than the picture quality corresponding to the quality threshold. Optionally, in order to ensure the picture quality of the video to be processed, the target bit rate can be increased to improve (or maintain) the to-be-processed The picture quality of the video. The specific range of increasing the target code rate may not be limited. In this way, in order to improve (or maintain) the picture quality of the to-be-processed video while ensuring the file size of the to-be-processed video is as small as possible, it is possible to continue to perform the aforesaid steps on the to-be-processed video again based on the increased target bit rate. The transcoding process is performed until the difference between the quality index value and the quality threshold is less than or equal to the first threshold.

Optionally, after the target bit rate is adjusted by the above two implementations, the quality index value corresponding to the video to be processed can be equal to the aforementioned quality threshold, or the quality index value corresponding to the video to be processed can be infinitely approached (or approximated). ) quality threshold, that is, the difference between the quality index value and the quality threshold is less than or equal to the first threshold.

In the video data processing method provided in this embodiment, the video to be processed and the target bit rate corresponding to the video to be processed are acquired, then the video to be processed is transcoded based on the target bit rate, and then the video to be processed after the transcoding process is acquired and processed Corresponding quality index value, and then if the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate, and perform the transcoding process on the video to be processed based on the adjusted target bit rate, until the difference less than or equal to the first threshold. Thus, the above-mentioned method realizes that the video to be processed is transcoded based on a target bit rate lower than the initial bit rate of the video to be processed, and the quality index value corresponding to the video to be processed after the transcoding process is different from the quality threshold value. When the difference is greater than the first threshold, the target code rate is adjusted again, and the video to be processed is transcoded again based on the adjusted target code rate until the difference is less than or equal to the first threshold, so that it can be The target bit rate of the video is adjusted on the premise of the video quality, and the file size of the video to be processed after adjustment is reduced compared to before the adjustment, which saves the bit rate and thus saves network bandwidth resources.

Please refer to FIG. 3 , which shows a flowchart of a video data processing method provided by another embodiment of the present application. This embodiment provides a video data processing method, which can be applied to a server. The method includes:

Step S210: Acquire the video to be processed and the target bit rate corresponding to each of the plurality of video segments.

In this embodiment, the video to be processed may include multiple video clips, and the multiple video clips are obtained by dividing the video to be transcoded. Optionally, the server may be configured with an automatic compression function. When the automatic compression function is enabled, the video that needs to be stored (that is, corresponding to the video to be stored when a storage instruction is received) may be the video to be transcoded by default. In this manner, in order to improve the transcoding efficiency of the video to be processed, the video to be transcoded may be segmented. Exemplarily, the server may divide the video to be transcoded in units of GOP (Group of Pictures, group of pictures) or a multiple of GOP to obtain multiple video segments, and use the video segments as the video to be processed. One GOP may be a group of continuous pictures, and the number of picture frames included in one GOP may not be limited in this embodiment.

Optionally, in the actual segmentation process, there may be multiple segmentation methods for a video to be transcoded. Exemplarily, please refer to FIG. 4 , which shows a schematic diagram of a segmentation manner for segmentation of the video to be transcoded provided in this embodiment. As shown in FIG. 4 , the video to be transcoded may be segmented by a single GOP as a unit, and each video segment segmented by this segmentation method includes the same number of picture frames. The number of picture frames included in a single GOP can be set according to actual needs. For example, if the picture content of the video to be transcoded is small, the video to be transcoded can be segmented in units of GOPs including a smaller number of picture frames. Obtain a plurality of video clips in "Mode 1" as shown in FIG. 4 (that is, video clip 1, video clip 2, video clip 3, video clip 4, video clip 5, video clip 6 corresponding to mode one in FIG. 4 ) , video clip 7, video clip 8). Similarly, if the content of the video to be transcoded is large, the video to be transcoded can be divided in units of GOPs that include a larger number of picture frames, or to be transcoded in units of multiples of GOPs that include a smaller number of picture frames. The coded video is segmented to obtain multiple video clips in "Mode 2" as shown in Figure 4 (ie, video clip 1, video clip 2, video clip 3, and video clip 4 corresponding to mode 2 in Figure 4). It is not difficult to see that the number of picture frames included in a single video clip in “Mode 2” shown in FIG. 4 is more than the number of picture frames included in a single video clip in “Mode 1”.

Optionally, the video to be transcoded can also be divided alternately in units of GOPs that include a smaller number of picture frames and GOPs that include a larger number of picture frames. As shown in FIG. 4 , there are multiple video clips in “mode 3” (video clip 1 , video clip 2 , video clip 3 , video clip 4 , video clip 5 , and video clip 6 corresponding to mode three in FIG. 4 ). Optionally, the segmentation method can be determined according to the performance of the server and the number of cores. For example, a server supporting single core corresponds to segmentation method 1, a server supporting dual-core corresponds to segmentation method 2, and a server supporting multi-core corresponds to segmentation method 3, etc. , the selection of the specific segmentation method can be adjusted according to the actual situation, and the above is only an example.

In the manner of this embodiment, target bit rates corresponding to each of the multiple video clips may be set respectively. Optionally, the target bit rates corresponding to each of the multiple video clips may be the same or different. In some embodiments, the target bit rate corresponding to each video clip may be lower than the initial bit rate of the video clip; in other embodiments, the target bit rate corresponding to each video clip may be lower than the entire video to be processed The initial code rate (optionally, the overall initial code rate may be the average value of the corresponding initial code rates of multiple video segments).

Step S220: Perform transcoding processing on the plurality of video segments based on the respective corresponding target bit rates.

As a method, if the target bit rates corresponding to the multiple video clips are different, the multiple video clips can be transcoded based on the target bit rates corresponding to each of the multiple video clips. The corresponding bit rate of each video clip is its corresponding target bit rate. For the specific flow of transcoding processing for multiple video clips respectively, reference may be made to the descriptions in the foregoing embodiments, which will not be repeated here.

Step S230: Acquire quality index values corresponding to the plurality of video clips after the transcoding process.

The quality index value corresponding to each video clip can be calculated by combining the transcoded video clip and the pre-transcoded video clip, and the specific calculation principle can be referred to the description in the foregoing embodiment, which will not be repeated here.

Optionally, the quality index value corresponding to the video clip with a higher target bit rate can be higher, and the quality index value corresponding to the video clip with a lower target bit rate can be lower. In this way, in order to ensure the video quality On the premise of reducing the storage size of the video file as much as possible, the target bit rate corresponding to the video clip needs to be adjusted. As a method, a quality threshold may be set, the quality index value and the quality threshold may be compared, and the target bit rate may be adjusted according to the comparison result. However, if a uniform quality threshold is used to compare the quality index values corresponding to multiple video clips, the target bit rate corresponding to a certain video clip may be incorrectly adjusted when the target bit rate corresponding to a certain video clip is increased. The rate is also increased, resulting in a waste of code rate.

As a way to improve the above problem, the quality thresholds corresponding to the multiple video clips can be determined based on the quality characteristics corresponding to each of them. That is, if the quality characteristics corresponding to the multiple video clips are different, the quality thresholds corresponding to the multiple video clips can be Different, the specific description is as follows.

As an implementation manner, please refer to FIG. 5 , which shows a flowchart of a method corresponding to a manner of determining quality thresholds corresponding to multiple video clips according to an embodiment of the present application. As shown in FIG. 5 , a method for determining quality thresholds corresponding to multiple video clips may include the following steps:

Step S231: Obtain the content complexity of each of the video clips.

In this embodiment, the quality feature corresponding to the video clip may be the content complexity of the video clip. The content complexity is used to characterize how fast or slow the content of the picture scene of the video clip changes, the type of picture color, and/or how much or how fast the picture color changes. For example, the higher the content complexity of the video clip, the faster the content of the picture scene between adjacent picture frames in the video clip changes; the lower the content complexity of the video clip, the faster the content between adjacent picture frames in the video clip The screen scene content changes more slowly. For another example, the higher the content complexity of the video clip, the more/faster the picture color types between adjacent picture frames in the video clip change; the lower the content complexity of the video clip, the more adjacent pictures in the video clip change. The less/slower the variety of picture color changes between frames. Specifically, the content complexity of the video clip can be obtained according to the degree of difference between adjacent picture frames in the video clip. Optionally, the difference degree can be obtained based on the similarity of picture contents between adjacent picture frames in the video clip, or the difference degree can be obtained based on the speed of change of the motion vector of the pixels of the adjacent picture frames in the video clip.

Wherein, as an implementation manner, the similarity of the picture content between adjacent picture frames can be obtained, and the change speed of the content of the picture scene can be determined according to the value of the similarity, so as to obtain the content complexity of the video clip. Optionally, the smaller the similarity of the picture content between the adjacent picture frames, the faster the change of the picture scene content between the adjacent picture frames; the greater the similarity of the picture content between the adjacent picture frames, the greater the The content of the picture scene between the adjacent picture frames changes more slowly. In this implementation, the similarity of the picture content between adjacent picture frames can be scored, and then the target score (the specific value may not be limited, for example, it can be 100) minus the similarity score to obtain the difference degree score. Optionally, a larger difference degree score indicates a larger difference degree, and a smaller difference degree score indicates a smaller difference degree.

Optionally, in the case where the similarity of the picture content between adjacent picture frames is obtained, the variation range of the similarity of the picture content corresponding to the plurality of adjacent picture frames of the video clip may be obtained. Optionally, The larger the change range is, the faster the screen scene content of the corresponding video clip changes, and the smaller the change range is, the slower the screen scene content of the corresponding video clip changes. Exemplarily, it is assumed that the video clip A includes 5 picture frames, namely picture frame 1, picture frame 2, picture frame 3, picture frame 4 and picture frame 5, if the picture content between picture frame 1 and picture frame 2 is similar The degree of similarity is 8, the similarity of the picture content between the picture frame 2 and the picture frame 3 is 15, the similarity of the picture content between the picture frame 3 and the picture frame 4 is 23, and the similarity of the picture content between the picture frame 4 and the picture frame 5 is 23. If the similarity is 40, it can be determined that the content of the picture scene of the corresponding video clip changes rapidly. And if the similarity of the picture content between the picture frame 1 and the picture frame 2 is 8, the similarity of the picture content between the picture frame 2 and the picture frame 3 is 9, and the similarity of the picture content between the picture frame 3 and the picture frame 4 is 9. is 11, and the similarity of the picture content between the picture frame 4 and the picture frame 5 is 15, it can be determined that the picture scene content of the corresponding video clip changes slowly.

As another implementation manner, the change speed of the motion vector of the pixels of adjacent picture frames can be obtained, and then the change speed of the picture scene content can be determined according to the change speed of the motion vector. Optionally, if the change of the motion vector of the pixels of the adjacent picture frames is faster, it can be determined that the degree of difference between the adjacent picture frames is greater, indicating that the content of the picture scene between the adjacent picture frames changes faster; However, if the change of the motion vector of the pixels of the adjacent picture frames is slower, it can be determined that the degree of difference between the adjacent picture frames is smaller, indicating that the content of the picture scene between the adjacent picture frames changes more slowly.

Optionally, or it may be that the more color types of picture frames in the video clip, the higher the content complexity of the corresponding video clip; the fewer the color types of the picture frames in the video clip, the higher the content complexity of the corresponding video clip. lower. Or the more the picture color changes between adjacent picture frames in the video clip, the higher the content complexity of the corresponding video clip; the less the picture color changes between adjacent picture frames in the video clip, the corresponding The less complex the content of the video clip.

Step S232: Determine a quality threshold corresponding to each of the video segments based on the content complexity of each of the video segments.

In this embodiment, a video clip with higher content complexity corresponds to a higher quality threshold. In one way, the quality threshold corresponding to each video clip may be determined based on the content complexity of each video clip in the plurality of video clips.

For example, in a specific application scenario, please refer to FIG. 6 , which shows a schematic diagram of a manner for determining a quality threshold corresponding to each video clip according to the content complexity of each video clip provided by an embodiment of the present application. As shown in FIG. 6 , it is assumed that the video to be processed includes 4 video clips, namely video clip 1, video clip 2, video clip 3 and video clip 4 as shown in FIG. 6 . If the content corresponding to the four video clips is complex The relationship between the degrees is: "video clip 3 > video clip 2 > video clip 1 > video clip 4", then it can be determined that the quality threshold corresponding to video clip 3 is 90, the quality threshold corresponding to video clip 2 is 85, and the quality threshold corresponding to video clip 1 is 85. The corresponding quality threshold is 80, and the corresponding quality threshold of video segment 4 is 75.

By determining the quality threshold corresponding to the video clip according to the content complexity, when the difference between the quality index value of the transcoded video clip and the quality threshold is less than or equal to the first threshold, the video clip with more complex content can be The video quality of the video clips with less complex content can be maintained at a relatively high level to improve the user’s viewing experience, while the video quality of video clips with less complex content can be maintained at a relatively lower level than that of video clips with more complex content, which can achieve The bit rate of the video clip is reduced, thereby reducing the storage space occupied by the video clip.

As another implementation manner, please refer to FIG. 7 , which shows a flowchart of a method corresponding to another manner of determining quality thresholds corresponding to multiple video clips according to an embodiment of the present application. As shown in FIG. 7 , another manner of determining the quality thresholds corresponding to the multiple video clips may include the following steps:

Step S233: Obtain the segment positions of each of the video segments in the to-be-transcoded video.

In this embodiment, the quality feature corresponding to the video clip may be the clip position of the video clip. The segment position may be understood as the relative arrangement position of the video segments among the multiple video segments. Optionally, the multiple video segments may be arranged from front to back in the order of the playback time of the video to be processed. It can be understood that each video clip includes multiple frames of video images. Optionally, the location of the video clip (that is, the clip) may be determined by the time of the first video frame of each video clip (for example, the shooting time). position), or the position of each video clip (ie, the clip position) can be determined by the time of the last video image of the video clip, or the two adjacent video clips can be used to determine the clip position of the video clip. The interval between adjacent start frames may be equal.

Step S234: Determine a quality threshold corresponding to each of the video segments based on the segment position of each of the video segments in the to-be-transcoded video.

In this embodiment, the more centered the video segment is, the higher the corresponding quality threshold may be. It should be noted that the center position in this embodiment is the middle position of the playback sequence of the video to be processed. For example, assuming that the playback duration of the video to be processed is 12 minutes, the position of the video clip corresponding to the playback duration of the video to be processed from the 4th minute to the 8th minute can be used as the center position of the video to be processed. As a method, the quality threshold corresponding to each video segment may be determined based on the segment position of each video segment in the video to be transcoded. Optionally, in order to quickly confirm the segment positions of the video clips, multiple video clips can be divided into segment regions, so that the segment positions of the video clips can be quickly confirmed according to the location of the segment region to which the video clips belong.

Wherein, each segment area may include at least one video segment. For example, suppose the video to be processed includes 10 video clips, namely video clip 1, video clip 2, video clip 3, video clip 4, video clip 5, video clip 6, video clip 7, video clip 8, video clip 9 and For video segment 10, if the segment area of the video to be processed is divided into three segments, namely segment area 1, segment area 2 and segment area 3, then segment area 1 may include video segment 1, video segment 2, video segment 3 and Video segment 4, segment area 2 may include video segment 5, video segment 6, video segment 7, and video segment 8, and segment area 3 may include video segment 9 and video segment 10. Optionally, the above division is only described as an example. In actual implementation, the number of video segment regions included in each to-be-processed video and the number of video segments included in each video segment region can be set according to the actual situation, which is not made here. limited.

For example, in a specific application scenario, please refer to FIG. 8 , which shows a schematic diagram of a manner for determining quality thresholds corresponding to multiple video clips according to respective clip positions of multiple video clips according to an embodiment of the present application. As shown in FIG. 8 , it is assumed that the video to be processed includes three video segment areas, namely segment area 13, segment area 14 (the segment position is relatively centered), and segment area 15. Suppose that segment area 13 includes two video segments, segment area 14 Including several video clips, the clip area 15 includes two video clips. Optionally, the server may divide the video segment area according to the video content of the video to be processed. For example, for some movies with long preambles or titles and relatively short titles, the video segments included in the first segment area can be Contains more video clips than its last clip area.

Optionally, a quality threshold corresponding to a video clip whose clip position is relatively centered may be set higher than the quality threshold corresponding to other video clips (that is, a video clip whose position is relatively non-centered). As shown in FIG. 8 , the quality thresholds corresponding to the video segments included in the segment area 14 are all greater than the quality thresholds corresponding to the video segments included in the segment area 13 and the segment area 15 respectively. Optionally, the quality thresholds corresponding to different video clips belonging to the centered clip area may be the same or different. For example, in the clip area 14 shown in FIG. 8 , the quality thresholds corresponding to the two rightmost video clips are both 90 (that is, the same), while the quality thresholds corresponding to the two leftmost video clips are 85 and 90 (that is, not the same). Similarly, the quality thresholds corresponding to different video clips belonging to the non-centered clip area may be the same or different. For example, the quality thresholds corresponding to the two video clips in the clip area 13 shown in FIG. 8 are both 80 (that is, the same). ), and the respective quality thresholds corresponding to the two video clips in the clip area 15 are 80 and 75 (ie, different).

As another implementation manner, please refer to FIG. 9 , which shows a flowchart of a method corresponding to another manner of determining quality thresholds corresponding to multiple video clips according to an embodiment of the present application. As shown in FIG. 9 , another method for determining the quality thresholds corresponding to the multiple video clips may include the following steps:

Step S235: Input the multiple video clips into the machine learning model.

In order to improve the accuracy of video transcoding, as a method, deep learning can be combined to input multiple video clips into a machine learning model. Optionally, the machine learning model can be used to predict the quality threshold corresponding to the video clips. Machine learning models can be pre-trained with a large number of video clips.

Step S236: Obtain the quality thresholds output by the machine learning model and corresponding to the multiple video clips respectively.

In this implementation manner, the quality thresholds output by the machine learning model and corresponding to the multiple video clips can be acquired. By using the machine learning model to obtain the quality threshold corresponding to the video segmentation, the computing pressure on the server can be reduced, thereby improving the transcoding efficiency. At the same time, it can improve the accuracy of video transcoding.

It should be noted that, in the actual operation process of determining the quality thresholds corresponding to the multiple video clips, it can be confirmed in combination with at least two of the above-mentioned embodiments. The quality thresholds corresponding to the clips can also be combined with machine learning and clip positions to confirm the quality thresholds corresponding to multiple video clips, or can be combined with content complexity and clip positions (the order of judgment between the two can be unrestricted). The quality thresholds corresponding to multiple video clips, or the quality thresholds corresponding to multiple video clips can also be confirmed in combination with machine learning, content complexity, and clip location. The specific implementation process will not be repeated here, all including the above implementation. The quality threshold determination scheme of the method is all within the protection scope of the present application.

Step S240: If the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate corresponding to the video segment with the difference greater than the first threshold, and adjust the video based on the adjusted target bit rate. The segment undergoes the transcoding process until the difference is less than or equal to the first threshold.

In this embodiment, if there are still video clips in which the difference between the quality index value and the quality threshold value is greater than the first threshold value among the multiple video clips, the target bit rate corresponding to the video clips whose difference value is greater than the first threshold value can be adjusted, And based on the adjusted target bit rate, the foregoing transcoding process may be performed again on the corresponding video segment until the difference between the quality index value and the quality threshold value is less than or equal to the first threshold value. For the specific code rate adjustment principle and the transcoding process, reference may be made to the descriptions in the foregoing embodiments, which will not be repeated here.

The video data processing method provided in this embodiment realizes that, based on a target bit rate that is lower than the initial bit rate of each video clip of the video to be processed, transcoding processing is performed on multiple video clips of the video to be processed respectively, and When the difference between the quality index values corresponding to the multiple video clips after the transcoding process and the corresponding quality threshold is greater than the first threshold, the target bit rate corresponding to the video clips whose difference is greater than the first threshold is adjusted, and Based on the adjusted target bit rate, the corresponding video clip is transcoded again until the difference is less than or equal to the first threshold, so that the corresponding target bit rate of the video clip can be adjusted on the premise of ensuring the video quality of the video clip , so as to save the bit rate and save the network bandwidth. At the same time, the corresponding quality thresholds of multiple video clips are determined based on their respective quality characteristics such as content complexity and clip location, which improves the reliability and accuracy of the quality thresholds.

Please refer to FIG. 10 , which shows a flowchart of a video data processing method provided by another embodiment of the present application. This embodiment provides a video data processing method, which can be applied to a server. The method includes:

Step S310: Acquire the video to be processed and the target bit rate corresponding to each of the plurality of video segments.

Step S320: Invoke multiple threads to perform transcoding processing on the multiple video clips based on their corresponding target bit rates.

Optionally, in order to facilitate the improvement of transcoding efficiency, in this embodiment, multiple threads may be invoked to perform transcoding processing on the multiple video segments based on respective target bit rates corresponding to the multiple video segments. The multiple threads may be pre-created threads or threads created in real time. Optionally, the server can automatically determine the number of calling threads according to its processing performance or running performance.

It can be understood that, if the processing performance or running performance of the server is weak, the number of threads it calls may be less than the number of video clips, that is, the threads and video clips in this case may not be supported in a one-to-one correspondence. As an implementation method, if the number of multiple threads is less than the number of video clips, the video clips that meet the specified conditions among the multiple video clips can be obtained as the target video clips (which can be multiple video clips); then multiple threads are called first. The corresponding video clips are transcoded based on their corresponding target bit rates in the target video clips; after each video clip in the target video clips is transcoded, multiple threads are called based on the multiple video clips. Transcoding is performed on the other video clips except the target video clip in the multiple video clips with the corresponding target bit rates of the other video clips except the target video clip.

The specified conditions may include: the content complexity of the video clip is higher than the second threshold (optionally, the second threshold in this embodiment can be understood as the complexity threshold); or the video clip is the center position of the video to be processed , the center position is the middle position of the playback sequence of the video to be processed. Optionally, the specific value of the second threshold may not be limited, for example, the second threshold may be 80, 85, or 90.

It should be noted that, when the target video clip is selected in the transcoding processing stage, if the specified condition is that the content complexity of the video clip is higher than the second threshold, in this case, when the quality threshold corresponding to the video clip is subsequently determined, As an embodiment, the quality threshold corresponding to the video clip can be quickly determined according to the judgment result of whether the content complexity of the video clip is higher than the second threshold. For example, if it is determined that the content complexity of the video clip is higher than the second threshold If the content complexity of the video clip is determined to be lower than the second threshold, the quality threshold corresponding to the video clip can be set to be smaller. The quality threshold corresponding to the video clip with higher content complexity may be larger.

As another implementation manner, when it is determined that the content complexity of the video clip is higher than the second threshold, the clip position of the video clip may be further obtained, if the content complexity of the video clip is higher than the second threshold and the video clip For the segment in the center of the video to be processed, the quality threshold corresponding to the video segment can be set to be larger; if the content complexity of the video segment is higher than the second threshold, and the video segment is not in the center of the video to be processed. clips, then the quality threshold corresponding to the video clips can be set to be relatively small.

When it is determined that the content complexity of the video clip is higher than the second threshold, the method of further obtaining whether the video clip is a clip in the center of the video to be processed, and then determining the quality threshold corresponding to the video clip according to the obtaining result, can ensure that the video clip is to be processed. Processing the core image content of the video can maintain a high video playback quality and improve the accuracy of the quality threshold setting, thereby improving the user's viewing experience.

Similarly, if the specified condition is that the video segment is the segment in the center of the video to be processed, in this case, when the quality threshold corresponding to the video segment is subsequently determined, as an implementation, it can be directly determined according to whether the video segment is a The judgment result of the segment in the center of the video to be processed can quickly determine the quality threshold corresponding to the video segment. For example, if it is determined that the video segment is the segment in the center of the video to be processed, the quality threshold corresponding to the video segment can be set to be larger. ; and if it is determined that the video clip is not a clip in the center of the video to be processed, the quality threshold corresponding to the video clip can be set to be smaller.

As another implementation, when it is determined that the video segment is a segment in the center of the video to be processed, the content complexity of the video segment can be further obtained. If the video segment is a segment in the center of the video to be processed and the video If the content complexity of the clip is higher than the second threshold, the quality threshold corresponding to the video clip can be set to be larger; if the video clip is a clip in the center of the video to be processed, and the content complexity of the video clip is lower than the second threshold, then the quality threshold corresponding to the video clip can be set to be relatively small.

By further acquiring the content complexity of the video clip when it is determined that the video clip is the clip in the middle position of the video to be processed, it can be ensured that the video clip with higher content complexity in the middle position of the playback sequence of the video to be processed can be Play at a higher bit rate to improve the video playback quality and user viewing experience, while the video clips with relatively low content complexity in the middle of the playback timing of the video to be processed are played at a relatively low bit rate , the bit rate can be saved, thereby reducing the waste of bandwidth resources.

Step S330: Obtain quality index values corresponding to the plurality of video clips after the transcoding process.

Step S340: If the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate corresponding to the video segment with the difference greater than the first threshold, and adjust the video based on the adjusted target bit rate. The segment undergoes the transcoding process until the difference is less than or equal to the first threshold.

The video data processing method provided in this embodiment realizes that, based on a target bit rate that is lower than the initial bit rate of each video clip of the video to be processed, transcoding processing is performed on multiple video clips of the video to be processed respectively, and When the difference between the quality index values corresponding to the multiple video clips after the transcoding process and the corresponding quality threshold is greater than the first threshold, the target bit rate corresponding to the video clips whose difference is greater than the first threshold is adjusted, and Based on the adjusted target bit rate, the corresponding video clip is transcoded again until the difference is less than or equal to the first threshold, so that the corresponding target bit rate of the video clip can be adjusted on the premise of ensuring the video quality of the video clip , so as to save the bit rate and save the network bandwidth. The transcoding efficiency is improved by invoking multiple threads to perform transcoding processing on the multiple video segments based on their respective target bit rates corresponding to the multiple video segments.

Please refer to FIG. 11 , which shows a flowchart of a video data processing method provided by another embodiment of the present application. This embodiment provides a video data processing method, which can be applied to a server. The method includes:

Step S410: Acquire the video to be processed and the target bit rate corresponding to each of the plurality of video segments.

Step S420: Perform transcoding processing on the plurality of video clips based on their corresponding target bit rates.

Step S430: Acquire quality index values corresponding to the plurality of video clips after the transcoding process.

Step S440: If the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate corresponding to the video clip whose difference is greater than the first threshold, and adjust the video based on the adjusted target bit rate. The segment undergoes the transcoding process until the difference is less than or equal to the first threshold.

Step S450: Determine whether the difference between the quality index value corresponding to each video clip and the corresponding quality threshold value of each of the plurality of video clips is both less than or equal to the first threshold value.

Optionally, in order to ensure that the video to be processed after the transcoding process can be played normally, it can be determined whether the difference between the quality index value corresponding to each video clip in the multiple video clips and the corresponding quality threshold value is both less than or equal to the first A threshold value, so that whether to start video splicing can be determined according to the judgment result.

Optionally, in order to facilitate the content of adaptive media stream based on adaptive resolution protocols such as DASH (Dynamic Adaptive Streaming over HTTP, HTTP-based dynamic adaptive streaming), HLS (HTTP Live Streaming, dynamic bit rate adaptive technology) Generate, can store the video clip whose difference between the quality index value after transcoding and the quality threshold value is greater than the first threshold value; Storage to reduce the secondary development process and improve development efficiency.

Optionally, in some implementation manners, the quality threshold in this embodiment may also be a threshold determined based on other video quality evaluation standards. Wherein, other video quality evaluation criteria may include a PSNR (Peak Signal to Noise Ratio, peak signal-to-noise ratio) method, an SSIM (Structural SIMilarity, structural similarity) method, and the like. Alternatively, at least two methods among VMAF, PSNR and SSIM may be used in combination to jointly confirm the quality threshold corresponding to the video segment. For example, when the quality threshold corresponding to the video clip is determined by the VMAF method, the PSNR value and/or the SSIM value of the video clip can be calculated at the same time, and then the quality threshold corresponding to the video clip can be determined according to the calculation result.

Step S460: Splicing the multiple video clips to obtain a target video.

As a method, if the difference between the quality index value corresponding to each of the multiple video clips and the corresponding quality threshold is less than or equal to the first threshold, the multiple video clips can be spliced to obtain the target video. In this embodiment, the bit rate of the target video is lower than the initial bit rate of the video to be processed. Visually, the video quality of the target video is comparable to that of the video to be processed.

As another way, if there are video clips in which the difference between the quality index value and the corresponding quality threshold value is greater than the first threshold in the multiple video clips, you can continue to wait for the difference between the quality index value of all the video clips and the corresponding quality threshold value. When both are less than or equal to the first threshold, start splicing.

Optionally, in this embodiment, if the difference between the quality index value corresponding to the transcoded video clip and the corresponding quality threshold value is less than or equal to the first threshold value, the corresponding thread may be terminated, or the corresponding thread may be instructed to start pairing Other video segments whose difference is not less than or equal to the first threshold are transcoded.

Optionally, in some embodiments, if the difference between the quality index value corresponding to the video clip and the quality threshold value corresponding to the video clip is greater than the first threshold after multiple transcoding processing, the quality threshold value corresponding to the video clip can be adjusted. , and the specific adjustment value can be selected according to the actual situation, which is not listed here.

The video data processing method provided in this embodiment realizes that, based on a target bit rate that is lower than the initial bit rate of each video clip of the video to be processed, transcoding processing is performed on multiple video clips of the video to be processed respectively, and When the difference between the quality index values corresponding to the multiple video clips after the transcoding process and the corresponding quality threshold is greater than the first threshold, the target bit rate corresponding to the video clips whose difference is greater than the first threshold is adjusted, and Based on the adjusted target bit rate, the corresponding video clip is transcoded again until the difference is less than or equal to the first threshold, so that the corresponding target bit rate of the video clip can be adjusted on the premise of ensuring the video quality of the video clip , so as to save the bit rate and save the network bandwidth. By splicing multiple video segments whose difference between the quality index value and the quality threshold is less than or equal to the first threshold, it is possible to reduce the overall storage space of the video to be processed, thereby reducing the storage cost.

Please refer to FIG. 12 , which is a structural block diagram of a video data processing apparatus provided by an embodiment of the present application. This embodiment provides a video data processing apparatus 500 that can run on a server. The apparatus 500 includes: a first acquisition module 510 , the first processing module 520, the second acquisition module 530 and the second processing module 540:

The first acquiring module 510 is configured to acquire the video to be processed and a target bit rate corresponding to the video to be processed, where the target bit rate is lower than the initial bit rate of the video to be processed.

The first processing module 520 is configured to perform transcoding processing on the video to be processed based on the target bit rate.

The second obtaining module 530 is configured to obtain a quality index value corresponding to the video to be processed after the transcoding process.

The second processing module 540 is configured to adjust the target bit rate if the difference between the quality index value and the quality threshold value is greater than the first threshold, and perform an analysis on the video to be processed based on the adjusted target bit rate. The transcoding process is performed until the difference is less than or equal to the first threshold.

In one embodiment, the second processing module 540 may be configured to reduce the bit rate if the difference is greater than the first threshold and the quality indicator value is greater than the quality threshold. In this manner, the transcoding process may be performed on the video to be processed based on the reduced target bit rate until the difference is less than or equal to the first threshold.

In another implementation manner, the second processing module 540 may be configured to increase the code rate if the difference is greater than the first threshold and the quality indicator value is less than the quality threshold. In this manner, the transcoding process may be performed on the video to be processed based on the increased target bit rate until the difference is less than or equal to the first threshold.

Optionally, the apparatus 500 may further include a video segmentation module, and the video segmentation module may be configured to segment the to-be-transcoded video to obtain the to-be-processed video including multiple video segments. In this case, the first obtaining module 510 may be configured to obtain target bit rates corresponding to the plurality of video clips; the first processing module 520 may be configured to obtain target bit rates for the plurality of videos based on the corresponding target bit rates The clips are respectively transcoded; the second obtaining module 530 can be used to obtain the quality index values corresponding to the plurality of video clips after the transcoding process; the second processing module 540 can be used to obtain the quality index value if the The difference between the quality thresholds is greater than the first threshold, adjust the target bit rate corresponding to the video clip whose difference is greater than the first threshold, and perform the transcoding process on the video clip based on the adjusted target bit rate until all the The difference is less than or equal to the first threshold.

Optionally, the apparatus 500 may further include a threshold setting module, in the case where the video to be processed includes multiple video clips, if the difference between the quality index value and the quality threshold is greater than the first threshold, the target code Before adjusting the rate, as an implementation manner, the threshold setting module can be used to obtain the content complexity of each of the video clips; based on the content complexity of each of the video clips, determine the corresponding , wherein the video clip with higher content complexity corresponds to a higher quality threshold.

As another implementation manner, the threshold setting module can be used to obtain the segment position of each of the video segments in the to-be-transcoded video; based on the segment position of each of the video segments in the to-be-transcoded video , and determine the quality threshold corresponding to each of the video segments.

As another implementation manner, the threshold setting module can be used to input the multiple video clips into a machine learning model, and the machine learning model is used to predict the quality threshold corresponding to the video clips; obtain the output of the machine learning model The quality thresholds corresponding to the plurality of video segments respectively.

As an implementation manner, the first processing module 520 may be configured to invoke multiple threads to perform transcoding processing on the multiple video segments based on the respective corresponding target bit rates. Wherein, if the number of the multiple threads is less than the number of the video clips, a video clip that satisfies the specified condition among the multiple video clips can be obtained as the target video clip; then the multiple threads are called based on the corresponding Perform transcoding processing on the target video clip at the target bit rate; and then call the multiple threads to perform transcoding processing on the video clips other than the target video clip in the multiple video clips based on their corresponding transcoding parameters . Optionally, the specified conditions in this embodiment may include: the content complexity of the video clip is higher than the second threshold; or the video clip is a clip in the center of the video to be processed, and the center position is the to-be-processed clip. The middle position of the video's playback timing.

Optionally, the apparatus 500 may further include a splicing module, configured to adjust the target bit rate corresponding to the video clip whose difference is greater than the first threshold if the difference between the quality index value and the quality threshold is greater than the first threshold, and perform the transcoding process on the video clips based on the adjusted target bit rate until the difference value is less than or equal to the first threshold, if each video clip in the plurality of video clips corresponds to The difference between the quality index value and the corresponding quality threshold is less than or equal to the first threshold, and the target video is obtained by splicing the plurality of video segments. Optionally, in this embodiment, the bit rate of the target video is lower than the initial bit rate of the video to be processed.

Optionally, the apparatus 500 may further include a storage module for storing the video clips whose difference between the quality index value and the quality threshold value after transcoding is greater than the first threshold; The video segments whose difference between the quality thresholds is less than or equal to the first threshold are stored.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the above-described devices and modules, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In several embodiments provided in this application, the coupling between the modules may be electrical, mechanical or other forms of coupling.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically alone, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules.

Referring to FIG. 13 , based on the foregoing video data processing method and apparatus, an embodiment of the present application further provides an electronic device 100 that can execute the foregoing video data processing method. The electronic device 100 may be the server 12 described in FIG. 1 . The electronic device 100 includes a memory 102 and one or more (only one shown in the figure) processors 104 coupled with each other, and a communication line between the memory 102 and the processors 104 is connected. The memory 102 stores programs that can execute the contents of the foregoing embodiments, and the processor 104 can execute the programs stored in the memory 102 .

The processor 104 may include one or more processing cores. The processor 104 uses various interfaces and lines to connect various parts of the entire electronic device 100, and executes by running or executing the instructions, programs, code sets or instruction sets stored in the memory 102, and calling the data stored in the memory 102. Various functions of the electronic device 100 and processing data. Optionally, the processor 104 may adopt at least one of digital signal processing (Digital Signal Processing, DSP), field-programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). implemented in hardware. The processor 104 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), a modem, and the like. Among them, the CPU mainly handles the operating system, user interface and application programs, etc.; the GPU is used for rendering and drawing of the display content; the modem is used to handle wireless communication. It can be understood that, the above-mentioned modem may not be integrated into the processor 104, and is implemented by a communication chip alone.

The memory 102 may include random access memory (Random Access Memory, RAM), or may include read-only memory (Read-Only Memory). Memory 102 may be used to store instructions, programs, codes, sets of codes, or sets of instructions. The memory 102 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.) , instructions for implementing the foregoing embodiments, and the like. The storage data area may also store data (such as phone book, audio and video data, chat record data) created by the electronic device 100 during use.

Please refer to FIG. 14 , which shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application. The computer-readable medium 600 stores program codes, and the program codes can be invoked by the processor to execute the methods described in the above method embodiments.

The computer-readable storage medium 600 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 600 includes a non-transitory computer-readable storage medium. Computer readable storage medium 600 has storage space for program code 610 to perform any of the method steps in the above-described methods. These program codes can be read from or written to one or more computer program products. Program code 610 may be compressed, for example, in a suitable form.

To sum up, a video data processing method, device, electronic device, and storage medium provided by the embodiments of the present application obtain the video to be processed and the target bit rate corresponding to the video to be processed, and then the video to be processed is based on the target bit rate. Perform transcoding processing, and then obtain the quality index value corresponding to the video to be processed after the transcoding process, and then if the difference between the quality index value and the quality threshold value is greater than the first threshold, adjust the target bit rate, and based on the adjusted The target bit rate is to perform the transcoding process on the video to be processed until the difference is less than or equal to the first threshold. Thus, the above-mentioned method realizes that the video to be processed is transcoded based on a target bit rate lower than the initial bit rate of the video to be processed, and the quality index value corresponding to the video to be processed after the transcoding process is different from the quality threshold value. When the difference is greater than the first threshold, the target bit rate is adjusted again, and based on the adjusted target bit rate, the video to be processed is transcoded again until the difference is less than or equal to the first threshold, so that it can be ensured The target bit rate of the video to be processed is adjusted under the premise of the video quality of the video to be processed, so as to save the bit rate and network bandwidth.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not drive the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions in the embodiments of the present application.

Claims (15)

1. a video data processing method, is characterized in that, described method comprises: Obtain the video to be processed and a target bit rate corresponding to the video to be processed, where the target bit rate is lower than the initial bit rate of the video to be processed; Transcoding the to-be-processed video based on the target bit rate; obtaining a quality index value corresponding to the video to be processed after the transcoding process; If the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate, and perform the transcoding process on the video to be processed based on the adjusted target bit rate until the The difference is less than or equal to the first threshold. 2. The method according to claim 1, wherein, if the difference between the quality index value and the quality threshold is greater than a first threshold, adjusting the target bit rate, comprising: If the difference is greater than a first threshold, and the quality index value is greater than the quality threshold, reducing the target bit rate; Performing the transcoding process on the video to be processed based on the adjusted target bit rate until the difference is less than or equal to the first threshold, including: The transcoding process is performed on the video to be processed based on the reduced target bit rate until the difference is less than or equal to the first threshold. 3. The method according to claim 1, wherein if the difference between the quality index value and the quality threshold is greater than a first threshold, adjusting the target bit rate, comprising: If the difference is greater than a first threshold and the quality index value is less than the quality threshold, increasing the target bit rate; Performing the transcoding process on the video to be processed based on the adjusted target bit rate until the difference is less than or equal to the first threshold, including: The transcoding process is performed on the video to be processed based on the increased target bit rate until the difference is less than or equal to the first threshold. 4 . The method according to claim 1 , wherein the video to be processed comprises multiple video clips, and the multiple video clips are obtained by segmenting the video to be transcoded, and the acquisition is the same as the to-be-processed video. 5 . The target bit rate corresponding to the video, perform transcoding processing on the video to be processed based on the target bit rate, and obtain a quality index value corresponding to the video to be processed after the transcoding process, if the quality index value is the same as the quality The difference between the thresholds is greater than the first threshold, the target bit rate is adjusted, and the transcoding process is performed on the video to be processed based on the adjusted target bit rate, until the difference is less than or equal to the first a threshold, including: obtaining target bit rates corresponding to the plurality of video clips; Perform transcoding processing on the plurality of video clips based on the respective corresponding target bit rates; obtaining quality index values corresponding to the plurality of video clips after the transcoding process; If the difference between the quality index value and the quality threshold is greater than the first threshold, adjust the target bit rate corresponding to the video clips whose difference is greater than the first threshold, and perform all the adjustments on the video clips based on the adjusted target bit rate. The transcoding process is performed until the difference is less than or equal to the first threshold. 5. The method according to claim 4, wherein if the difference between the quality index value and the quality threshold is greater than a first threshold, before adjusting the target bit rate, the method further comprises: obtaining the content complexity of each of the video clips; Based on the content complexity of each of the video clips, a quality threshold corresponding to each of the video clips is determined, wherein the video clip with higher content complexity has a larger quality threshold. 6. The method according to claim 4, wherein if the difference between the quality index value and the quality threshold is greater than a first threshold, before adjusting the target bit rate, the method further comprises: Obtain the segment position of each of the video segments in the to-be-transcoded video; Based on the segment position of each of the video segments in the video to be transcoded, a quality threshold corresponding to each of the video segments is determined. 7. The method according to claim 4, wherein if the difference between the quality index value and the quality threshold is greater than a first threshold, before adjusting the target bit rate, the method further comprises: inputting the plurality of video clips into a machine learning model for predicting a quality threshold corresponding to the video clips; Acquiring quality thresholds output by the machine learning model and corresponding to the multiple video clips respectively. 8. The method according to claim 4, wherein the transcoding processing is performed on the plurality of video clips based on the respective corresponding target bit rates, comprising: Multiple threads are called to perform transcoding processing on the multiple video clips based on their corresponding target bit rates. 9 . The method according to claim 8 , wherein the invoking multiple threads to perform transcoding processing on the multiple video clips based on their respective corresponding target bit rates, comprising: 10 . If the number of the multiple threads is less than the number of the video clips, acquiring a video clip that satisfies the specified condition among the multiple video clips as the target video clip; invoking the multiple threads to perform transcoding processing on the target video segment based on the respective corresponding target bit rates; Invoke the multiple threads to perform the processing on the video segments other than the target video segment in the multiple video segments based on the respective target bit rates of the video segments other than the target video segment in the multiple video segments. Transcoding processing. 10 . The method according to claim 9 , wherein the specified condition comprises: the content complexity of the video segment is higher than a second threshold; or the video segment is a segment in the center of the video to be processed, and the The center position is the middle position of the playback sequence of the video to be processed. 11. The method according to claim 4, wherein, if the difference between the quality index value and the quality threshold is greater than a first threshold, the target bit rate corresponding to the video clip whose difference is greater than the first threshold is performed. adjusting, and performing the transcoding process on the video segment based on the adjusted target bit rate until the difference is less than or equal to the first threshold, further comprising: If the difference between the quality index value corresponding to each of the plurality of video clips and the corresponding quality threshold value is less than or equal to the first threshold, splicing the plurality of video clips to obtain the target video . 12. The method of claim 4, wherein the method further comprises: storing the video clips whose difference between the quality index value and the quality threshold value after transcoding is greater than the first threshold value; and storing the video segments whose difference between the quality index value and the quality threshold after transcoding is less than or equal to the first threshold. 13. A video data processing device, characterized in that, running on a server, the device comprising: a first acquisition module, configured to acquire a video to be processed and a target bit rate corresponding to the video to be processed, where the target bit rate is lower than the initial bit rate of the video to be processed; a first processing module, configured to perform transcoding processing on the to-be-processed video based on the target bit rate; a second obtaining module, configured to obtain a quality index value corresponding to the transcoded video to be processed; A second processing module, configured to adjust the target bit rate if the difference between the quality index value and the quality threshold is greater than the first threshold, and perform the described processing on the video to be processed based on the adjusted target bit rate Transcoding is performed until the difference is less than or equal to the first threshold. 14. An electronic device, comprising one or more processors and a memory; One or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs being configured to perform the method of any of claims 1-12. 15. A computer-readable storage medium, wherein a program code is stored in the computer-readable storage medium, wherein, when the program code is executed by a processor, any one of claims 1-12 is executed method.

Images