Video decoding methods, devices, electronic equipment and storage media

Abstract

This invention provides a video decoding method, apparatus, electronic device, and storage medium. The method includes: determining multiple bitstreams corresponding to the video to be decoded, and hardware parameters for video decoding; grouping the bitstreams based on their basic information and hardware parameters to obtain multiple bitstream groups, wherein the difference in decoding time between the bitstreams within the same group is less than a threshold; and performing video decoding on the bitstreams within each bitstream group. This invention groups multiple bitstreams based on their basic information and hardware parameters, achieving optimal decoding performance by grouping bitstreams with similar specifications together, thus ensuring fast decoding speed. Furthermore, the small difference in decoding time between the bitstreams within the same group avoids the problem of long waiting times and wasted hardware decoding core resources caused by traditional methods that require waiting for longer-decoding bitstreams to complete decoding before processing the next batch of data.

Description

Technical Field

[0001] This invention relates to the field of video decoding technology, and in particular to a video decoding method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of video acceleration hardware, the concept of batch processing has been introduced to further improve hardware processing efficiency. Hardware decodes tens or even hundreds of frames of images as a batch of data, eliminating the need for CPU scheduling and allowing the hardware accelerator to handle the task directly. This reduces the overhead of CPU-hardware interaction and improves efficiency.

[0003] However, when decoding each bitstream in the current batch of data, after the bitstream with a shorter decoding time is completed, it is necessary to wait for the bitstream with a longer decoding time to complete its decoding before the next batch of data can be processed. This waiting time is long and wastes the resources of some hardware decoding cores. Summary of the Invention

[0004] This invention provides a video decoding method, apparatus, electronic device, and storage medium to solve the defects of the prior art, which requires waiting for a long bitstream to complete decoding before processing the next batch of data, resulting in long waiting times and wasted hardware decoding core resources.

[0005] This invention provides a video decoding method, comprising:

[0006] Determine the multiple bitstreams corresponding to the video to be decoded, as well as the hardware parameters used for video decoding;

[0007] Based on the basic information of each bitstream and the hardware parameters, each bitstream is grouped to obtain multiple bitstream groups, and the difference in decoding time between each bitstream in the same group is less than a threshold.

[0008] Video decoding is performed on the bitstreams in each bitstream group separately.

[0009] According to a video decoding method provided by the present invention, the step of grouping the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain multiple bitstream groups includes:

[0010] The basic information of each bitstream and the hardware parameters are input into the grouping model, and the grouping model groups the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain the bitstream grouping result;

[0011] The grouping model is trained based on sample information of the sample bitstream, sample hardware parameters, and sample bitstream grouping labels.

[0012] According to a video decoding method provided by the present invention, the bitstream grouping result is the probability of each bitstream group.

[0013] According to a video decoding method provided by the present invention, determining multiple bitstreams corresponding to the video to be decoded includes:

[0014] Identify the keyframes in the video to be decoded;

[0015] Extract the multiple bitstreams from the keyframes.

[0016] According to a video decoding method provided by the present invention, determining multiple bitstreams corresponding to the video to be decoded includes:

[0017] Decrypt the video to be decoded to obtain the decrypted video;

[0018] Extract the multiple bitstreams from the decrypted video.

[0019] According to a video decoding method provided by the present invention, the basic information of each bitstream includes at least one of the following: encoding type, bit depth, resolution, entropy encoding type, bit rate, number of reference frames, and frame interval.

[0020] According to a video decoding method provided by the present invention, the hardware parameters include at least one of memory read / write bandwidth, CPU frequency, and memory information.

[0021] The present invention also provides a video decoding device, comprising:

[0022] The determining unit is used to determine the multiple bitstreams corresponding to the video to be decoded, as well as the hardware parameters used for video decoding;

[0023] A grouping unit is used to group each bitstream based on its basic information and the hardware parameters to obtain multiple bitstream groups, wherein the difference in decoding time between each bitstream in the same group is less than a threshold.

[0024] The decoding unit is used to perform video decoding on the bitstreams in each bitstream group.

[0025] According to a video decoding apparatus provided by the present invention, the grouping unit is specifically used for:

[0026] The basic information of each bitstream and the hardware parameters are input into the grouping model, and the grouping model groups the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain the bitstream grouping result;

[0027] The grouping model is trained based on sample information of the sample bitstream, sample hardware parameters, and sample bitstream grouping labels.

[0028] According to a video decoding apparatus provided by the present invention, the bitstream grouping result is the probability of each bitstream group.

[0029] According to a video decoding apparatus provided by the present invention, the determining unit includes:

[0030] A keyframe determination unit is used to determine keyframes in the video to be decoded;

[0031] The first extraction unit is used to extract the multiple bitstreams from the keyframe.

[0032] According to a video decoding apparatus provided by the present invention, the determining unit includes:

[0033] The decryption unit is used to decrypt the video to be decoded, thereby obtaining the decrypted video.

[0034] The second extraction unit is used to extract the multiple bitstreams from the decrypted video.

[0035] According to a video decoding apparatus provided by the present invention, the basic information of each bitstream includes at least one of the following: encoding type, bit depth, resolution, entropy encoding type, bit rate, number of reference frames, and frame interval.

[0036] According to a video decoding device provided by the present invention, the hardware parameters include at least one of memory read / write bandwidth, CPU frequency, and memory information.

[0037] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the video decoding method described above.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the video decoding method as described above.

[0039] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the video decoding methods described above.

[0040] The video decoding method, apparatus, electronic device, and storage medium provided by this invention group multiple bitstreams based on their basic information and hardware parameters. This grouping of bitstreams with similar specifications ensures optimal decoding performance while maintaining decoding speed. Furthermore, the decoding time differences between bitstreams within the same group are small, avoiding the problems of long waiting times and wasted hardware decoding core resources inherent in traditional methods that require waiting for longer bitstreams to complete decoding before processing the next batch of data. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 This is one of the flowcharts illustrating the video decoding method provided by the present invention;

[0043] Figure 2 This is the second flowchart illustrating the video decoding method provided by the present invention;

[0044] Figure 3 This is the third flowchart illustrating the video decoding method provided by the present invention;

[0045] Figure 4 This is a flowchart illustrating the group model training method provided by the present invention;

[0046] Figure 5 This is a schematic diagram of the video decoding device provided by the present invention;

[0047] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0049] Currently, video decoding often employs a batch decoding approach, such as decoding in batches according to the bitstream sequence. However, when decoding frames within the current batch, after the frames with shorter decoding times are completed, it is necessary to wait for the frames with longer decoding times to finish before processing the next batch of data can begin. This waiting time is considerable and wastes the resources of some hardware decoding cores.

[0050] In response, this invention provides a video decoding method. Figure 1 This is one of the flowcharts illustrating the video decoding method provided by the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0051] Step 110: Determine the multiple bitstreams corresponding to the video to be decoded, as well as the hardware parameters used for video decoding.

[0052] Here, the video to be decoded is the video that needs to be decoded. The video to be decoded can be a pre-shot and stored video, or a video stream captured in real time; this embodiment of the invention does not specifically limit this. The bitstream refers to the data stream of the video to be decoded during transmission. It contains all the information of the video to be decoded, such as images, sound, and subtitles. The bitstream can be extracted from the video frames of the video to be decoded.

[0053] Hardware parameters for video decoding refer to the performance indicators and specifications of the computer hardware platform used for video decoding. These parameters can be used to evaluate a computer's performance and functionality. Hardware parameters can be obtained in the following ways: ① System information tools built into the operating system. For example, in Windows, you can view hardware parameters through "Control Panel" > "System and Security" > "System"; in Mac, you can view them through "About This Mac". ② Third-party system information tools, such as CPU-Z, GPU-Z, and Speccy, can provide detailed hardware parameter information. ③ BIOS / UEFI settings interface. For example, pressing the corresponding key during computer startup (usually F2, F10, Delete, etc.) will enter the BIOS / UEFI settings interface, where you can view hardware parameters. ④ The hardware platform itself: For example, graphics cards, motherboards, and memory modules usually have model numbers and parameter information labeled on them, which can be directly viewed.

[0054] Step 120: Based on the basic information and hardware parameters of each bitstream, group each bitstream into multiple bitstream groups, and the difference in decoding time between each bitstream in the same group is less than a threshold.

[0055] Step 130: Decode the video streams in each bitstream group separately.

[0056] Specifically, the basic information of the bitstream can characterize the information of the video to be decoded, including encoding type, bit depth, resolution, entropy encoding type, bit rate, number of reference frames, frame interval, etc. Hardware parameters can characterize the performance of the computer hardware platform. Therefore, when grouping based on the basic information and hardware parameters of each bitstream, both the information of the video to be decoded and the performance of the hardware platform itself are considered. This enables the grouping of bitstreams with similar specifications (such as grouping bitstreams with similar sizes) while ensuring optimal decoding performance, thereby guaranteeing the decoding speed of the bitstream.

[0057] In order to reduce the size of the data stream during video data transmission, compression algorithms are usually used to compress the data. However, the compressed data cannot be played or edited directly and needs to be decoded to restore it to the original video, which is video decoding.

[0058] Since the difference in decoding time between each bitstream in the same group is less than the threshold in the embodiments of the present invention, that is, the difference in decoding time between each bitstream in the same group is small, the problem of long waiting time and waste of hardware decoding core resources caused by waiting for the bitstream with longer decoding time to complete decoding before processing the next batch of data in the traditional method is avoided.

[0059] Therefore, the video decoding method provided in this embodiment of the invention groups multiple bitstreams based on their basic information and hardware parameters. This ensures optimal decoding performance by grouping bitstreams with similar specifications together, thus guaranteeing decoding speed. Furthermore, the decoding time differences between bitstreams within the same group are small in this embodiment, avoiding the problem of long waiting times and wasted hardware decoding core resources caused by traditional methods that require waiting for bitstreams with longer decoding times to complete before processing the next batch of data.

[0060] like Figure 2 As shown, in some specific implementations, multiple bitstreams corresponding to the video to be decoded and hardware parameters for video decoding are determined. Based on the basic information of each bitstream and the hardware parameters, the multiple bitstreams are grouped to obtain bitstream group 1 (size 1), bitstream group 2 (size 2) of size 2, ..., bitstream group n (size n) of size n.

[0061] Based on the above embodiments, the bitstreams are grouped according to their basic information and hardware parameters to obtain multiple bitstream groups, including:

[0062] The basic information and hardware parameters of each bitstream are input into the grouping model, which then groups the bitstreams based on the basic information and hardware parameters to obtain the bitstream grouping results.

[0063] The grouping model is trained based on sample information, sample hardware parameters, and sample code stream grouping labels.

[0064] Specifically, the grouping model is used to group each bitstream based on its basic information and hardware parameters to obtain the bitstream grouping result. The grouping model can be constructed based on a fully connected network.

[0065] like Figure 3As shown, in some specific implementations, multiple bitstreams corresponding to the video to be decoded and hardware parameters for video decoding are determined. The basic information feature vectors and hardware parameter feature vectors of each bitstream are extracted, and the basic information feature vectors and hardware parameter feature vectors of each bitstream are input into the grouping model. The grouping model groups each bitstream according to the basic information feature vectors and hardware parameter feature vectors of each bitstream, resulting in bitstream group 1 (size 1), bitstream group 2 (size 2) of size 2, ..., bitstream group n (size n) of size n.

[0066] The grouping model is trained based on sample information, sample hardware parameters, and sample code stream grouping labels. For example... Figure 4 As shown, the sample information of the sample bitstream can include encoding type, bit depth, resolution, etc., and the sample hardware parameters can include memory information, etc. The sample information and hardware parameters of the sample bitstream are input into the input layer of the initial model. After passing through the hidden layer and the output layer, the sample grouping result is obtained. Based on the sample grouping result and the sample bitstream grouping label, the parameters of the initial model are updated until the convergence condition is met, and the trained grouping model is obtained.

[0067] It is understandable that, given enough sample information, sample hardware parameters, and sample code stream grouping labels to train the initial model, the initial model can learn enough sample information and sample hardware parameters. This allows the resulting grouping model to accurately obtain grouping results that ensure both the fastest decoding speed and the best decoding performance, thereby maximizing the characteristics of the hardware platform and improving the overall decoding speed.

[0068] Therefore, it can be seen that the training parameters for training the grouping model in this embodiment of the invention include sample information of the sample bitstream, that is, detailed features of the sample bitstream. These detailed features almost entirely cover the parameters affecting decoding time. Based on these parameters, the input bitstreams can be classified, grouping bitstreams with similar decoding times into one category. This allows bitstreams of the same category to be decoded "in parallel," greatly increasing hardware efficiency. In addition, the sample hardware parameters of the sample hardware platform are also extracted as training parameters for training the grouping model. This allows for adaptive adjustment of bitstream grouping according to the characteristics of the hardware platform, thereby further improving the overall decoding performance under the current hardware platform scenario.

[0069] Based on any of the above embodiments, the result of the bitstream grouping is the probability of each bitstream group.

[0070] Specifically, the probability of each bitstream group can be the decoding performance probability corresponding to each bitstream group. The higher the probability, the better the corresponding hardware decoding performance, and the lower the probability, the worse the corresponding hardware decoding performance.

[0071] Therefore, the embodiments of the present invention obtain the basic information and hardware parameters of each bitstream as input parameters of the grouping model, perform performance analysis on each bitstream group, and thus obtain the decoding performance probability corresponding to each bitstream group. Thus, during decoding, the bitstream group with the highest probability can be selected for decoding, that is, the optimal bitstream group can be selected for decoding. The optimal bitstream group can be understood as one that can ensure both fast decoding and optimal decoding performance.

[0072] Based on any of the above embodiments, multiple bitstreams corresponding to the video to be decoded are determined, including:

[0073] Identify the keyframes in the video to be decoded;

[0074] Extract multiple bitstreams from keyframes.

[0075] Specifically, a keyframe is a video frame that contains important information about the video to be decoded. For example, if the important information in the video to be decoded is a person, then the video frame carrying the person's information is a keyframe, while the video frame that only contains background information is a non-keyframe.

[0076] Decoding non-keyframes in the video to be decoded not only fails to extract important information but also wastes decoding time and hardware resources used for video decoding. To address this, this invention, after acquiring the video to be decoded, first identifies the keyframes and then extracts multiple bitstreams from them. The resulting bitstreams contain important information from the video to be decoded, further improving decoding speed and saving hardware resources used for video decoding.

[0077] Based on any of the above embodiments, multiple bitstreams corresponding to the video to be decoded are determined, including:

[0078] Decrypt the video to be decoded to obtain the decrypted video;

[0079] Extract multiple bitstreams from the decrypted video.

[0080] Specifically, considering data privacy issues, the video to be decoded in this embodiment of the invention is a compressed encrypted video, meaning that unauthorized users cannot obtain the data information in the video to be decoded during the transmission process, and the video to be decoded is a compressed video, which improves the video transmission speed.

[0081] After obtaining the video to be decoded, the video can be decrypted based on the private key to obtain the decrypted video. Multiple bitstreams can then be extracted from the decrypted video, and the bitstreams can be grouped and the video decoded sequentially.

[0082] Therefore, the embodiments of the present invention can not only prevent unauthorized users from stealing data information in the video to be decoded during the transmission of the video to be decoded, but also further improve the video transmission speed.

[0083] Based on any of the above embodiments, the basic information of each bitstream includes at least one of the following: encoding type, bit depth, resolution, entropy encoding type, bit rate, number of reference frames, and frame interval (gop size).

[0084] Specifically, many factors affect the video decoding time of a bitstream. Assuming consistent hardware parameters, parameters related to video decoding time include encoding type, bit depth, resolution, entropy coding type, and the frame type of the current frame. In addition, there are more refined parameters such as the number of stripes per frame, whether 8×8 transform decoding is used, frame field mode, and whether video compression techniques (such as deblocking) are used. Besides these parameters, many other factors also affect the video decoding time, such as the current bitrate, the number of reference frames, and the GOP size.

[0085] Based on any of the above embodiments, the hardware parameters include at least one of memory read / write bandwidth, CPU frequency, and memory information.

[0086] Specifically, the hardware parameters of the hardware platform also have a significant impact on video decoding performance, such as the memory read / write bandwidth, CPU frequency, and memory information of the hardware platform. For example, the memory size in the memory information can affect the maximum number of bitstreams that can be decoded simultaneously.

[0087] Based on extensive experiments and analysis, the empirical values ​​for the corresponding hardware parameters are as follows to ensure video decoding speed and optimal decoding performance:

[0088] Video decoding requires different memory read / write bandwidths depending on the chip and the scenario. For example, for H.264@1080P@30fps, when the reference frame is less than 10 frames, the required memory read / write bandwidth is generally between 200 and 500 Mbps.

[0089] The impact of CPU frequency on decoding performance: For H264@1080P@30fps, on a Gen Intel(R) Core(TM) i5-12600K CPU platform, decoding 200 channels using a certain third-party software platform consumes approximately 500% of the CPU.

[0090] The impact of memory information on the number of decoding channels supported: In video decoding, the YUV buffer occupies the vast majority of the required memory. Generally speaking, the number of this buffer is the number of reference frames + the number of buffers. Different videos have different numbers of reference frames, and different software platforms have different numbers of buffers required, but the number of buffers is roughly between 10 and 20. The memory size in the hardware memory information determines the maximum number of decoding channels that this platform can support.

[0091] The video decoding apparatus provided by the present invention is described below. The video decoding apparatus described below and the video decoding method described above can be referred to in correspondence.

[0092] Based on any of the above embodiments, the present invention also provides a video decoding device, such as... Figure 5 As shown, the device includes:

[0093] The determining unit 510 is used to determine multiple bitstreams corresponding to the video to be decoded, as well as the hardware parameters used for video decoding.

[0094] Grouping unit 520 is used to group each bitstream based on the basic information of each bitstream and the hardware parameters to obtain multiple bitstream groups, wherein the difference in decoding time between each bitstream in the same group is less than a threshold.

[0095] Decoding unit 530 is used to perform video decoding on the bitstreams in each bitstream group respectively.

[0096] Based on any of the above embodiments, the grouping unit 520 is specifically used for:

[0097] The basic information of each bitstream and the hardware parameters are input into the grouping model, and the grouping model groups the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain the bitstream grouping result;

[0098] The grouping model is trained based on sample information of the sample bitstream, sample hardware parameters, and sample bitstream grouping labels.

[0099] Based on any of the above embodiments, the bitstream grouping result is the probability of each bitstream group.

[0100] Based on any of the above embodiments, the determining unit 510 includes:

[0101] A keyframe determination unit is used to determine keyframes in the video to be decoded;

[0102] The first extraction unit is used to extract the multiple bitstreams from the keyframe.

[0103] Based on any of the above embodiments, the determining unit 510 includes:

[0104] The decryption unit is used to decrypt the video to be decoded, thereby obtaining the decrypted video.

[0105] The second extraction unit is used to extract the multiple bitstreams from the decrypted video.

[0106] Based on any of the above embodiments, the basic information of each bitstream includes at least one of the following: encoding type, bit depth, resolution, entropy encoding type, bit rate, number of reference frames, and frame interval.

[0107] Based on any of the above embodiments, the hardware parameters include at least one of memory read / write bandwidth, CPU frequency, and memory information.

[0108] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 6 As shown, the electronic device may include a processor 610, a memory 620, a communication interface 630, and a communication bus 640, wherein the processor 610, memory 620, and communication interface 630 communicate with each other through the communication bus 640. The processor 610 can call logical instructions in the memory 620 to execute a video decoding method, which includes: determining multiple bitstreams corresponding to the video to be decoded, and hardware parameters for video decoding; grouping the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain multiple bitstream groups, wherein the difference in decoding time between the bitstreams in the same group is less than a threshold; and performing video decoding on the bitstreams in each bitstream group respectively.

[0109] Furthermore, the logical instructions in the aforementioned memory 620 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0110] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the video decoding method provided by the above methods, the method comprising: determining multiple bitstreams corresponding to the video to be decoded, and hardware parameters for video decoding; grouping the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain multiple bitstream groups, wherein the difference in decoding time between the bitstreams in the same group is less than a threshold; and performing video decoding on the bitstreams in each bitstream group respectively.

[0111] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program is implemented to perform the video decoding methods provided above. The method includes: determining multiple bitstreams corresponding to a video to be decoded, and hardware parameters for video decoding; grouping the bitstreams based on basic information of each bitstream and the hardware parameters to obtain multiple bitstream groups, wherein the difference in decoding time between the bitstreams in the same group is less than a threshold; and performing video decoding on the bitstreams in each bitstream group respectively.

[0112] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0113] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A video decoding method, characterized in that, include: The process involves determining multiple bitstreams corresponding to the video to be decoded, as well as the hardware parameters used for video decoding. The hardware parameters used for decoding refer to the performance indicators and specifications of the computer hardware platform used for video decoding, and these hardware parameters are used to evaluate the performance and functionality of the computer. Based on the basic information of each bitstream and the hardware parameters, each bitstream is grouped to obtain multiple bitstream groups, and the difference in decoding time between each bitstream in the same group is less than a threshold. Video decoding is performed on the bitstreams in each bitstream group separately; Based on the basic information of each bitstream and the hardware parameters, the bitstreams are grouped to obtain multiple bitstream groups, including: The basic information of each bitstream and the hardware parameters are input into the grouping model, and the grouping model groups the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain the bitstream grouping result; The grouping model is trained based on sample information of the sample bitstream, sample hardware parameters, and sample bitstream grouping labels.

2. The video decoding method according to claim 1, characterized in that, The bitstream grouping result is the probability of each bitstream group.

3. The video decoding method according to any one of claims 1 to 2, characterized in that, The determination of multiple bitstreams corresponding to the video to be decoded includes: Identify the keyframes in the video to be decoded; Extract the multiple bitstreams from the keyframes.

4. The video decoding method according to any one of claims 1 to 2, characterized in that, The determination of multiple bitstreams corresponding to the video to be decoded includes: Decrypt the video to be decoded to obtain the decrypted video; Extract the multiple bitstreams from the decrypted video.

5. The video decoding method according to any one of claims 1 to 2, characterized in that, The basic information of each bitstream includes at least one of the following: encoding type, bit depth, resolution, entropy encoding type, bit rate, number of reference frames, and frame interval.

6. The video decoding method according to any one of claims 1 to 2, characterized in that, The hardware parameters include at least one of memory read / write bandwidth, CPU frequency, and memory information.

7. A video decoding device, characterized in that, include: The determining unit is used to determine multiple bitstreams corresponding to the video to be decoded, as well as the hardware parameters for video decoding; the hardware parameters for decoding refer to the performance indicators and specifications of the computer hardware platform used for video decoding, and the hardware parameters are used to evaluate the performance and functions of the computer. A grouping unit is used to group each bitstream based on its basic information and the hardware parameters to obtain multiple bitstream groups, wherein the difference in decoding time between each bitstream in the same group is less than a threshold. The decoding unit is used to perform video decoding on the bitstreams in each bitstream group; Based on the basic information of each bitstream and the hardware parameters, the bitstreams are grouped to obtain multiple bitstream groups, including: The basic information of each bitstream and the hardware parameters are input into the grouping model, and the grouping model groups the bitstreams based on the basic information of each bitstream and the hardware parameters to obtain the bitstream grouping result; The grouping model is trained based on sample information of the sample bitstream, sample hardware parameters, and sample bitstream grouping labels.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the video decoding method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the video decoding method as described in any one of claims 1 to 6.

Images