A method and system for video decoding acceleration based on a decoding card

Abstract

The application provides a video decoding acceleration method and system based on a decoding card. The video decoding acceleration method comprises the following steps: receiving a video decoding request with a data amount corresponding to a to-be-decoded video, extracting the to-be-decoded video which needs to be divided, and decoding the to-be-decoded video which does not need to be divided; according to the size of the data amount corresponding to the to-be-decoded video in the video decoding request, dividing the to-be-decoded video which needs to be divided according to a preset data amount threshold, to obtain a plurality of to-be-decoded video groups; receiving the plurality of to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decoding the plurality of to-be-decoded video groups by using a decoding card. The system comprises modules corresponding to the method steps.

Description

TECHNICAL FIELD

[0001] The application provides a video decoding acceleration method and system based on a decoding card, and belongs to the technical field of video decoding. BACKGROUND

[0002] Current video decoding is mostly implemented by using CPU software decoding and video playing, for example, the decoding of videos by domestic computers such as Loongson. The video decoding and video playing by using CPU software decoding have high resource occupation and low efficiency, and thus the video decoding efficiency is low and the response time is long during video playing, especially in the case of multi-channel monitoring video scenes. SUMMARY

[0003] The application provides a video decoding acceleration method and system based on a decoding card, and belongs to the technical field of video decoding.

[0004] A video decoding acceleration method based on a decoding card, the video decoding acceleration method comprising:

[0005] receiving a video decoding request with a data amount corresponding to a to-be-decoded video, extracting the to-be-decoded video that needs to be divided, and decoding the to-be-decoded video that does not need to be divided;

[0006] dividing the to-be-decoded video that needs to be divided according to a preset data amount threshold according to the size of the data amount corresponding to the to-be-decoded video in the video decoding request, to obtain a plurality of to-be-decoded video groups;

[0007] receiving the plurality of to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decoding the plurality of to-be-decoded video groups by using a decoding card.

[0008] The decoding card can be a Hi3536 type chip.

[0009] Further, receiving a video decoding request with a data amount corresponding to a to-be-decoded video, extracting the to-be-decoded video that needs to be divided, and decoding the to-be-decoded video that does not need to be divided comprises:

[0010] receiving a video decoding request with a data amount corresponding to a to-be-decoded video, comparing the data amount corresponding to the to-be-decoded video with a first data amount threshold set in advance, and obtaining a comparison result;

[0011] when the data amount corresponding to the to-be-decoded video exceeds the first data amount threshold, regarding the to-be-decoded video exceeding the first data amount threshold as the to-be-decoded video that needs to be divided;

[0012] When the data amount corresponding to the to-be-decoded video does not exceed the first data amount threshold, the to-be-decoded video not exceeding the first data amount threshold is regarded as a to-be-decoded video which does not need to be divided.

[0013] The to-be-decoded video which does not need to be divided is directly received according to the video decoding request, and video decoding is directly performed on the received video data by using a decoding card.

[0014] Further, according to the data amount corresponding to the to-be-decoded video contained in the video decoding request, the to-be-decoded video which needs to be divided is divided according to a preset data amount threshold, to obtain a plurality of to-be-decoded video groups, including:

[0015] The data amount corresponding to the to-be-decoded video contained in the video decoding request is extracted, and the data amount corresponding to the to-be-decoded video is compared with a preset second data amount threshold and a third data amount threshold, to obtain a comparison result.

[0016] When the data amount corresponding to the to-be-decoded video does not exceed the second data amount threshold, the to-be-decoded video not exceeding the second data amount threshold is divided into a first group of to-be-decoded data.

[0017] When the data amount corresponding to the to-be-decoded video exceeds the second data amount threshold but does not exceed the third data amount threshold, the to-be-decoded video exceeding the second data amount threshold but not exceeding the third data amount threshold is divided into a second group of to-be-decoded data.

[0018] When the data amount corresponding to the to-be-decoded video exceeds the third data amount threshold, the to-be-decoded video exceeding the third data amount threshold is divided into a third group of to-be-decoded data.

[0019] Further, the to-be-decoded priority rule is:

[0020] The total data amount of the first group of to-be-decoded data, the second group of to-be-decoded data, and the third group of to-be-decoded data is determined.

[0021] The priority of the total data amount is set from high to low according to the data amount from large to small.

[0022] If there are a plurality of to-be-decoded video groups with equal total data amount in the first group of to-be-decoded data, the second group of to-be-decoded data, and the third group of to-be-decoded data, the number of video decoding requests in the plurality of to-be-decoded video groups with equal total data amount is determined, and the priority of the plurality of to-be-decoded video groups with equal total data amount is set from high to low according to the number of video decoding requests from more to less.

[0023] A video decoding acceleration system based on a decoding card, the video decoding acceleration system comprising:

[0024] receive a video decoding request with a data volume corresponding to a to-be-decoded video, extract the to-be-decoded video that needs to be divided, and decode the to-be-decoded video that does not need to be divided;

[0025] divide the to-be-decoded video that needs to be divided according to a preset data volume threshold, to obtain a plurality of to-be-decoded video groups;

[0026] decode the plurality of to-be-decoded video groups in sequence using a decoding card according to a to-be-decoded priority rule.

[0027] The decoding card can be a Hi3536 type chip.

[0028] Further, the receiving module comprises:

[0029] compare the data volume corresponding to the to-be-decoded video with a first data volume threshold set in advance to obtain a comparison result;

[0030] When the data volume corresponding to the to-be-decoded video exceeds the first data volume threshold, the to-be-decoded video exceeding the first data volume threshold is determined as the to-be-decoded video that needs to be divided.

[0031] When the data volume corresponding to the to-be-decoded video does not exceed the first data volume threshold, the to-be-decoded video not exceeding the first data volume threshold is determined as the to-be-decoded video that does not need to be divided.

[0032] The first video decoding module is configured to directly receive video data according to the video decoding request for the to-be-decoded video that does not need to be divided, and directly perform video decoding using the decoding card after receiving the video data.

[0033] Further, the dividing module comprises:

[0034] extract the data volume corresponding to the to-be-decoded video in the video decoding request, and compare the data volume corresponding to the to-be-decoded video with a second data volume threshold and a third data volume threshold set in advance to obtain a comparison result;

[0035] When the data volume corresponding to the to-be-decoded video does not exceed the second data volume threshold, the to-be-decoded video not exceeding the second data volume threshold is divided into a first group of to-be-decoded data.

[0036] a second dividing module, configured to divide the to-be-decoded videos corresponding to the data amount exceeding the second data amount threshold but not exceeding a third data amount threshold into a second group of to-be-decoded data when the to-be-decoded videos corresponding to the data amount exceeding the second data amount threshold but not exceeding the third data amount threshold;

[0037] a third dividing module, configured to divide the to-be-decoded videos exceeding the third data amount threshold into a third group of to-be-decoded data when the to-be-decoded videos corresponding to the data amount exceeding the third data amount threshold.

[0038] Further, the to-be-decoded priority rule is:

[0039] judging a total data amount of the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data;

[0040] setting the priority of the total data amount from high to low in a descending order;

[0041] if there are multiple groups of to-be-decoded videos with equal total data amount in the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data, determining the number of video decoding requests in the multiple groups of to-be-decoded videos with equal total data amount, and setting the priority of the multiple groups of to-be-decoded videos with equal total data amount from high to low in a descending order of the number of video decoding requests.

[0042] The present application has the following advantages:

[0043] The present application provides a video decoding acceleration method and system based on a decoding card, which can effectively improve the decoding speed of video decoding and further improve the decoding efficiency. Meanwhile, the video decoding acceleration method and system based on a decoding card provided by the present application does not occupy the CPU resources of the original computer system in the video decoding process, and does not affect the running efficiency of the original system; the power consumption is low, and the specific further use of the Hi3536 chip and the support of other similar chips can effectively reduce the system running power consumption in the decoding process, and does not cause resource waste by increasing power consumption. On the other hand, the video decoding acceleration method and system based on a decoding card can use the Hi3536-based decoding card to assist decoding, and play the video by hardware acceleration decoding to support more video channels for simultaneous decoding and playing, and does not increase additional power consumption while supporting more video channels for simultaneous decoding and playing. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 a flowchart of the method of the present application;

[0045] Figure 2 a system block diagram of the system of the present application. DETAILED DESCRIPTION

[0046] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings, it should be understood that the preferred embodiments described herein are only used to explain and illustrate the present application, and are not used to limit the present application.

[0047] The embodiment of the present application provides a video decoding acceleration method based on a decoding card, as shown in the figure, the video decoding acceleration method comprises: Figure 1

[0048] S1, receiving a video decoding request with a data amount corresponding to a to-be-decoded video, extracting a to-be-decoded video which needs to be divided, and decoding a to-be-decoded video which does not need to be divided;

[0049] S2, according to the size of the data amount corresponding to the to-be-decoded video contained in the video decoding request, dividing the to-be-decoded video which needs to be divided according to a preset data amount threshold, to obtain a plurality of to-be-decoded video groups;

[0050] S3, receiving the plurality of to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decoding the plurality of to-be-decoded video groups by using a decoding card.

[0051] Among them, the decoding card can adopt Hi3536 type chip.

[0052] The working principle of the above technical solution is as follows: first, receiving a video decoding request with a data amount corresponding to a to-be-decoded video, extracting a to-be-decoded video which needs to be divided, and decoding a to-be-decoded video which does not need to be divided; then, according to the size of the data amount corresponding to the to-be-decoded video contained in the video decoding request, dividing the to-be-decoded video which needs to be divided according to a preset data amount threshold, to obtain a plurality of to-be-decoded video groups; finally, receiving the plurality of to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decoding the plurality of to-be-decoded video groups by using a decoding card.

[0053] ​The technical scheme has the effects that the embodiment provides a video decoding acceleration method based on a decoding card, which can effectively improve the decoding speed of video decoding and further improve the decoding efficiency. Meanwhile, the video decoding acceleration method based on the decoding card provided by the embodiment does not occupy the CPU resources of the original computer system in the video decoding process and does not affect the running efficiency of the original system. The power consumption is low, and the specific further use of the Hi3536 chip and support for other similar chips can effectively reduce the system running power consumption in the decoding process, and the excessive increase of power consumption causes resource waste. On the other hand, the video decoding acceleration method based on the decoding card provided by the embodiment can use the Hi3536-based decoding card to assist decoding, play the video through hardware acceleration decoding to support more video channels to be decoded and played simultaneously, and does not increase additional power consumption while supporting more video channels to be decoded and played simultaneously.

[0054] In an embodiment of the present application, a video decoding request with a data amount corresponding to a to-be-decoded video is received, a to-be-decoded video that needs to be divided is extracted, and a to-be-decoded video that does not need to be divided is decoded, comprising:

[0055] S101, receiving a video decoding request with a data amount corresponding to a to-be-decoded video, comparing the data amount corresponding to the to-be-decoded video with a first data amount threshold set in advance, and obtaining a comparison result;

[0056] S102, when the data amount corresponding to the to-be-decoded video exceeds the first data amount threshold, the to-be-decoded video exceeding the first data amount threshold is taken as a to-be-decoded video that needs to be divided;

[0057] S103, when the data amount corresponding to the to-be-decoded video does not exceed the first data amount threshold, the to-be-decoded video not exceeding the first data amount threshold is taken as a to-be-decoded video that does not need to be divided;

[0058] S104, for the to-be-decoded video that does not need to be divided, video data is received directly according to the video decoding request, and after the video data is received, the video is decoded directly by using a decoding card.

[0059] The working principle of the technical solution is as follows: first, a video decoding request with a data amount corresponding to a to-be-decoded video is received, the data amount corresponding to the to-be-decoded video is compared with a first preset data amount threshold to obtain a comparison result; then, when the data amount corresponding to the to-be-decoded video exceeds the first data amount threshold, the to-be-decoded video exceeding the first data amount threshold is taken as a to-be-decoded video that needs to be divided; subsequently, when the data amount corresponding to the to-be-decoded video does not exceed the first data amount threshold, the to-be-decoded video not exceeding the first data amount threshold is taken as a to-be-decoded video that does not need to be divided; finally, the to-be-decoded video that does not need to be divided is directly subjected to video data reception according to the video decoding request, and video decoding is directly performed on the video data by using a decoding card after the video data is received.

[0060] The effect of the technical solution is as follows: by the above manner, the video screening efficiency and rationality can be effectively improved by screening and extracting a video with a large amount of video data. Meanwhile, the video decoding efficiency can be effectively improved by performing targeted decoding processing on to-be-decoded videos with different data orders of magnitude.

[0061] In an embodiment of the present application, according to the size of the data amount corresponding to the to-be-decoded video contained in the video decoding request, the to-be-decoded video that needs to be divided is divided according to a preset data amount threshold, and a plurality of to-be-decoded video groups are obtained, including:

[0062] S201, extracting the data amount corresponding to the to-be-decoded video contained in the video decoding request, and comparing the data amount corresponding to the to-be-decoded video with a second preset data amount threshold and a third data amount threshold to obtain a comparison result;

[0063] S202, when the data amount corresponding to the to-be-decoded video does not exceed the second data amount threshold, the to-be-decoded video not exceeding the second data amount threshold is divided into a first group of to-be-decoded data;

[0064] S203, when the data amount corresponding to the to-be-decoded video exceeds the second data amount threshold but does not exceed the third data amount threshold, the to-be-decoded video exceeding the second data amount threshold but not exceeding the third data amount threshold is divided into a second group of to-be-decoded data;

[0065] S204, when the data amount corresponding to the to-be-decoded video exceeds the third data amount threshold, the to-be-decoded video exceeding the third data amount threshold is divided into a third group of to-be-decoded data.

[0066] The working principle of the technical solution is as follows: first, the data amount corresponding to the to-be-decoded video included in the video decoding request is extracted, and the data amount corresponding to the to-be-decoded video is compared with a preset second data amount threshold and a third data amount threshold to obtain a comparison result; then, when the data amount corresponding to the to-be-decoded video does not exceed the second data amount threshold, the to-be-decoded video that does not exceed the second data amount threshold is divided into a first group of to-be-decoded data; subsequently, when the data amount corresponding to the to-be-decoded video exceeds the second data amount threshold but does not exceed the third data amount threshold, the to-be-decoded video that exceeds the second data amount threshold but does not exceed the third data amount threshold is divided into a second group of to-be-decoded data; finally, when the data amount corresponding to the to-be-decoded video exceeds the third data amount threshold, the to-be-decoded video that exceeds the third data amount threshold is divided into a third group of to-be-decoded data.

[0067] The effect of the technical solution is that the video screening efficiency and rationality can be effectively improved by screening and extracting the video with a large amount of video data in the above manner. Meanwhile, the efficiency of video decoding processing can be effectively improved by performing targeted decoding processing on the to-be-decoded video with different data orders of magnitude.

[0068] In an embodiment of the present application, the to-be-decoded priority rule is that:

[0069] The total data amount of the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data is determined.

[0070] The priority of the total data amount is set from high to low according to the data from large to small.

[0071] If multiple to-be-decoded video groups with equal total data amount appear in the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data, the number of video decoding requests in the multiple to-be-decoded video groups with equal total data amount is determined, and the priority of the multiple to-be-decoded video groups with equal total data amount is set from high to low according to the number of video decoding requests from more to less.

[0072] The effect of the technical solution is that the efficiency of video decoding processing can be effectively improved by setting the decoding priority rule without performing targeted decoding processing on the to-be-decoded video with different data orders of magnitude.

[0073] An embodiment of the present application proposes a video decoding acceleration system based on a decoding card, as shown in Figure 2 The video decoding acceleration system includes:

[0074] The receiving module is configured to receive a video decoding request with a data volume corresponding to a to-be-decoded video, extract the to-be-decoded video that needs to be divided, and decode the to-be-decoded video that does not need to be divided;

[0075] The dividing module is configured to divide the to-be-decoded video that needs to be divided according to a preset data volume threshold based on a size of the data volume corresponding to the to-be-decoded video included in the video decoding request, to obtain a plurality of to-be-decoded video groups.

[0076] The decoding module is configured to receive the plurality of to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decode the plurality of to-be-decoded video groups by using a decoding card.

[0077] The decoding card can be a Hi3536 chip.

[0078] The working principle of the above technical solution is as follows: first, the receiving module receives a video decoding request with a data volume corresponding to a to-be-decoded video, extracts the to-be-decoded video that needs to be divided, and decodes the to-be-decoded video that does not need to be divided; then, the dividing module divides the to-be-decoded video that needs to be divided according to a preset data volume threshold based on a size of the data volume corresponding to the to-be-decoded video included in the video decoding request, to obtain a plurality of to-be-decoded video groups; finally, the decoding module receives the plurality of to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decodes the plurality of to-be-decoded video groups by using a decoding card.

[0079] The above technical solution has the following effects: the embodiment proposes a video decoding acceleration system based on a decoding card, which can effectively improve the decoding speed of video decoding and thus effectively improve the decoding efficiency. At the same time, the video decoding acceleration system based on the decoding card proposed in the embodiment does not occupy the CPU resources of the original computer system during the video decoding process, and does not affect the running efficiency of the original system; the power consumption is low, and at the same time, the specific further use of the Hi3536 chip and the support of other similar chips can effectively reduce the system running power consumption in the decoding process, and does not cause resource waste due to excessive increase in power consumption. On the other hand, the video decoding acceleration system based on the decoding card proposed in the embodiment can use a decoding card based on the Hi3536 to assist decoding, play the video by using hardware acceleration decoding to support more video channels to be decoded and played at the same time, and does not increase additional power consumption while supporting more video channels to be decoded and played at the same time.

[0080] In an embodiment of the present application, the receiving module comprises:

[0081] a comparison module configured to receive a video decoding request with a data amount corresponding to a to-be-decoded video, compare the data amount corresponding to the to-be-decoded video with a preset first data amount threshold, and obtain a comparison result;

[0082] a first division determination module configured to, when the data amount corresponding to the to-be-decoded video exceeds the first data amount threshold, regard the to-be-decoded video exceeding the first data amount threshold as a to-be-decoded video that needs to be divided;

[0083] a second division determination module configured to, when the data amount corresponding to the to-be-decoded video does not exceed the first data amount threshold, regard the to-be-decoded video not exceeding the first data amount threshold as a to-be-decoded video that does not need to be divided;

[0084] a first video decoding module configured to, for the to-be-decoded video that does not need to be divided, directly receive video data according to the video decoding request, and directly perform video decoding using a decoding card after receiving the video data.

[0085] The working principle of the above technical solution is as follows: first, the comparison module receives a video decoding request with a data amount corresponding to a to-be-decoded video, compares the data amount corresponding to the to-be-decoded video with a preset first data amount threshold, and obtains a comparison result; then, the first division determination module regards the to-be-decoded video exceeding the first data amount threshold as a to-be-decoded video that needs to be divided when the data amount corresponding to the to-be-decoded video exceeds the first data amount threshold; subsequently, the second division determination module regards the to-be-decoded video not exceeding the first data amount threshold as a to-be-decoded video that does not need to be divided when the data amount corresponding to the to-be-decoded video does not exceed the first data amount threshold; finally, the first video decoding module directly receives video data according to the video decoding request for the to-be-decoded video that does not need to be divided, and directly performs video decoding using a decoding card after receiving the video data.

[0086] The effect of the above technical solution is that, by the above manner, the video screening efficiency and rationality can be effectively improved by screening and extracting a video with a large amount of video data. Meanwhile, the video decoding efficiency can be effectively improved by performing targeted decoding processing on to-be-decoded videos with different data orders of magnitude.

[0087] In an embodiment of the present application, the division module comprises:

[0088] an extraction module configured to extract the data amount corresponding to the to-be-decoded video included in the video decoding request, compare the data amount corresponding to the to-be-decoded video with a preset second data amount threshold and a third data amount threshold, and obtain a comparison result;

[0089] a first dividing module, configured to divide the to-be-decoded video corresponding to a data amount not exceeding the second data amount threshold to a first group of to-be-decoded data when the to-be-decoded video corresponding data amount does not exceed the second data amount threshold;

[0090] a second dividing module, configured to divide the to-be-decoded video corresponding to a data amount exceeding the second data amount threshold but not exceeding a third data amount threshold to a second group of to-be-decoded data when the to-be-decoded video corresponding data amount exceeds the second data amount threshold but not exceeding the third data amount threshold;

[0091] a third dividing module, configured to divide the to-be-decoded video corresponding to a data amount exceeding the third data amount threshold to a third group of to-be-decoded data when the to-be-decoded video corresponding data amount exceeds the third data amount threshold.

[0092] The working principle of the above technical solution is as follows: first, the to-be-decoded video corresponding data amount contained in the video decoding request is extracted by the extraction module, and the to-be-decoded video corresponding data amount is compared with the preset second data amount threshold and third data amount threshold to obtain a comparison result; then, the first dividing module is used to divide the to-be-decoded video corresponding to a data amount not exceeding the second data amount threshold to a first group of to-be-decoded data when the to-be-decoded video corresponding data amount does not exceed the second data amount threshold; subsequently, the second dividing module is used to divide the to-be-decoded video corresponding to a data amount exceeding the second data amount threshold but not exceeding the third data amount threshold to a second group of to-be-decoded data when the to-be-decoded video corresponding data amount exceeds the second data amount threshold but not exceeding the third data amount threshold; finally, the third dividing module is used to divide the to-be-decoded video corresponding to a data amount exceeding the third data amount threshold to a third group of to-be-decoded data when the to-be-decoded video corresponding data amount exceeds the third data amount threshold.

[0093] The effect of the above technical solution is that: by the above-mentioned manner, the video screening efficiency and rationality can be effectively improved by screening and extracting the video with large data amount. At the same time, the efficiency of video decoding processing can be effectively improved by targeted decoding processing for to-be-decoded videos of different data orders of magnitude.

[0094] In an embodiment of the present application, the to-be-decoded priority rule is:

[0095] judging the total data amount of the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data;

[0096] setting the priority from high to low according to the total data amount from large to small;

[0097] If there are multiple video groups with equal total data amount in the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data, the number of video decoding requests in the multiple video groups with equal total data amount is determined, and the multiple video groups with equal total data amount are set in priority from high to low according to the number of video decoding requests from more to less.

[0098] The effect of the above technical solution is that the above decoding priority principle can not be used for targeted decoding processing of to-be-decoded videos with different data orders of magnitude, and the efficiency of video decoding processing can be effectively improved.

[0099] Obviously, various modifications and variations of the present application can be made by those skilled in the art without departing from the spirit and scope of the application. Thus, it is intended that the present application include modifications and variations to the application made in light of the above disclosure.

Claims

1. A method for video decoding acceleration based on a decoding card, characterized in that, The video decoding acceleration method comprises: receiving a video decoding request with a corresponding data amount of a to-be-decoded video, extracting the to-be-decoded video that needs to be divided, and decoding the to-be-decoded video that does not need to be divided; according to the size of the corresponding data amount of the to-be-decoded video contained in the video decoding request, dividing the to-be-decoded video that needs to be divided according to a preset data amount threshold, to obtain a plurality of to-be-decoded video groups; receiving the plurality of to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decoding the plurality of to-be-decoded video groups by using a decoding card; wherein, according to the size of the corresponding data amount of the to-be-decoded video contained in the video decoding request, dividing the to-be-decoded video that needs to be divided according to a preset data amount threshold, to obtain a plurality of to-be-decoded video groups, comprises: extracting the corresponding data amount of the to-be-decoded video contained in the video decoding request, and comparing the corresponding data amount of the to-be-decoded video with a preset second data amount threshold and a third data amount threshold to obtain a comparison result; when the corresponding data amount of the to-be-decoded video does not exceed the second data amount threshold, dividing the to-be-decoded video that does not exceed the second data amount threshold into a first group of to-be-decoded data; when the corresponding data amount of the to-be-decoded video exceeds the second data amount threshold but does not exceed the third data amount threshold, dividing the to-be-decoded video that exceeds the second data amount threshold but does not exceed the third data amount threshold into a second group of to-be-decoded data; when the corresponding data amount of the to-be-decoded video exceeds the third data amount threshold, dividing the to-be-decoded video that exceeds the third data amount threshold into a third group of to-be-decoded data.

2. The method of claim 1, wherein, receiving a video decoding request with a corresponding data amount of a to-be-decoded video, extracting the to-be-decoded video that needs to be divided, and decoding the to-be-decoded video that does not need to be divided, comprises: receiving a video decoding request with a corresponding data amount of a to-be-decoded video, extracting the to-be-decoded video that needs to be divided, and decoding the to-be-decoded video that does not need to be divided, comprises: comparing the corresponding data amount of the to-be-decoded video with a preset first data amount threshold to obtain a comparison result; when the corresponding data amount of the to-be-decoded video exceeds the first data amount threshold, dividing the to-be-decoded video that exceeds the first data amount threshold as the to-be-decoded video that needs to be divided; when the corresponding data amount of the to-be-decoded video does not exceed the first data amount threshold, dividing the to-be-decoded video that does not exceed the first data amount threshold as the to-be-decoded video that does not need to be divided; 3. The method of claim 1, wherein the video decoding acceleration method is characterized by, directly receiving video data according to the video decoding request for the to-be-decoded video that does not need to be divided, and directly decoding the video by using a decoding card after receiving the video data. The to-be-decoded priority rule is: judging the total data amount of the first group of to-be-decoded data, the second group of to-be-decoded data, and the third group of to-be-decoded data; setting the priority from high to low according to the total data amount from large to small. If multiple video decoding request groups with equal total data amount appear in the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data, the number of video decoding requests in the multiple video decoding request groups with equal total data amount is determined, and the multiple video decoding request groups with equal total data amount are set in priority from high to low according to the number of video decoding requests from more to less.

4. A video decoding acceleration system based on a decoding card, characterized in that, The video decoding acceleration system comprises: A receiving module is configured to receive a video decoding request with a corresponding data amount of a to-be-decoded video, extract a to-be-decoded video that needs to be divided, and decode a to-be-decoded video that does not need to be divided; A dividing module is configured to divide the to-be-decoded video that needs to be divided according to a preset data amount threshold based on the size of the corresponding data amount of the to-be-decoded video in the video decoding request, and obtain multiple to-be-decoded video groups; A decoding module is configured to receive the multiple to-be-decoded video groups according to a to-be-decoded priority rule, and sequentially decode the multiple to-be-decoded video groups by using a decoding card. The dividing module comprises: An extracting module is configured to extract the corresponding data amount of the to-be-decoded video in the video decoding request, and compare the corresponding data amount of the to-be-decoded video with a preset second data amount threshold and a third data amount threshold to obtain a comparison result; A first dividing module is configured to divide the to-be-decoded video that does not exceed the second data amount threshold to a first group of to-be-decoded data when the corresponding data amount of the to-be-decoded video does not exceed the second data amount threshold; A second dividing module is configured to divide the to-be-decoded video that exceeds the second data amount threshold but does not exceed a third data amount threshold to a second group of to-be-decoded data when the corresponding data amount of the to-be-decoded video exceeds the second data amount threshold but does not exceed the third data amount threshold; A third dividing module is configured to divide the to-be-decoded video that exceeds the third data amount threshold to a third group of to-be-decoded data when the corresponding data amount of the to-be-decoded video exceeds the third data amount threshold.

5. The video decoding acceleration system of claim 4, wherein, The receiving module comprises: A comparison module is configured to receive a video decoding request with a corresponding data amount of a to-be-decoded video, compare the corresponding data amount of the to-be-decoded video with a preset first data amount threshold, and obtain a comparison result; A first dividing determining module is configured to divide the to-be-decoded video that exceeds the first data amount threshold as to-be-decoded video that needs to be divided when the corresponding data amount of the to-be-decoded video exceeds the first data amount threshold; A second dividing determining module is configured to divide the to-be-decoded video that does not exceed the first data amount threshold as to-be-decoded video that does not need to be divided when the corresponding data amount of the to-be-decoded video does not exceed the first data amount threshold; A first video decoding module is configured to directly receive video data according to a video decoding request for to-be-decoded video that does not need to be divided, and directly decode the video by using a decoding card after receiving the video data.

6. The video decoding acceleration system of claim 4, wherein, The to-be-decoded priority rule is: Determine the total data amount of the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data. The total data amount values are set in a high-to-low priority from large to small data; If there are multiple decoded video groups with equal total data amount values in the first group of to-be-decoded data, the second group of to-be-decoded data and the third group of to-be-decoded data, the number of video decoding requests in the multiple decoded video groups with equal total data amount values is determined, and the multiple decoded video groups with equal total data amount values are set in a high-to-low priority from more to less video decoding requests.

Images