CN103188521B - Transcoding distribution method and device, code-transferring method and equipment - Google Patents

Abstract

The invention discloses a transcoding distribution method based on a cloud platform, which is used for improving transcoding efficiency. The method includes: obtaining the transcoding complexity of each video segment to be transcoded and the transcoding performance value of each computing device constituting the cloud platform; according to the transcoding complexity of each video segment, each computing device's The transcoding performance value obtains the first average time required by each of the computing devices to transcode the allocated video clips; determine whether the transcoding time required for the first video clip on the first computing device is greater than The first average time; when the judgment result is no, assign the first video segment to the first computing device for transcoding. The invention also discloses a device for realizing the method, and discloses a transcoding method and device.

Description

Transcoding distribution method and device, transcoding method and device

technical field

The invention relates to the field of video coding and distributed computing, in particular to a transcoding distribution method and device, and a transcoding method and equipment.

Background technique

With the development of video coding technology, more and more coding methods and standards have emerged, such as H.264 (highly compressed digital video codec standard), MPEG-4 (fourth generation motion picture compression coding standard) and MPEG-2 (second-generation moving picture compression coding standard) and the like. Different environments often require different encoding technologies, which requires transcoding between different encoding methods. The encoding technology itself is very complicated, and it takes a long time to transcode on a single machine, so parallel technology may be required to achieve fast transcoding. In the prior art, parallel transcoding technologies are mainly divided into two types, one is multi-core-based parallel computing. One is cloud computing based on multiple machines.

Parallel computing based on multi-core is carried out in the same machine with multiple CPUs (central processing units). Multiple CPUs share resources such as memory and hard disk, but can perform calculations independently. The advantage of parallel encoding based on multi-core is that multiple CPUs share resources, communication between them is more convenient, and reference dependencies between data can be quickly processed to obtain a higher degree of parallelism, that is, the video that needs to be transcoded can be divided into smaller parts. Small video clips are transcoded. However, parallel computing based on multi-core requires the use of multi-core computers, and the multi-CPU structure requires corresponding hardware support, which is generally difficult to expand and expensive.

The cloud computing based on multi-machines (that is, cloud transcoding) just overcomes this shortcoming. Cloud transcoding is based on the cloud platform. The cloud platform consists of a group of thousands of computers, each of which can perform calculations independently. Through task scheduling and allocation, these computers can perform tasks in parallel to provide greater computing power. Because there is no hardware requirement for computers in the cloud platform, everything from servers to ordinary personal computers can be used as a part of the cloud platform. Therefore, the cloud platform is relatively scalable and inexpensive.

In the process of implementing the technical solutions of the embodiments of the present application, the inventors of the present application at least found the following technical problems in the prior art:

During the cloud transcoding process, video clips may be allocated randomly, without considering the characteristics of the video clips and the working machine itself, which may lead to low transcoding efficiency.

Contents of the invention

Embodiments of the present invention provide a transcoding allocation method and device, and a transcoding method and device, which are used to improve transcoding efficiency.

A transcoding distribution method applied to a user side in a cloud platform, comprising the following steps:

Obtain the transcoding complexity of each video segment to be transcoded and the transcoding performance value of each computing device forming the cloud platform;

According to the formula Obtaining the first average time required for each of the computing devices to transcode the allocated video clips; where f ^* is the first average time, and m is the total number of computing devices in the cloud platform , n is the total number of video segments that need to be transcoded, c _i is the transcoding complexity of the i-th video segment, p _j is the transcoding performance value of the j-th computing device, t _overhead Start time averaging for video clips;

Judging whether the transcoding time required for the first video segment on the first computing device is greater than the first average time;

When the judgment result is no, assign the first video segment to the first computing device for transcoding.

A transcoding method applied to a user side in a cloud platform, comprising the following steps:

Segment the video to be transcoded to obtain each video segment to be transcoded;

Allocating each of the video segments according to the transcoding allocation method;

After each computing device in the cloud platform completes the transcoding of the allocated video clips, the transcoded video clips are obtained and processed into transcoded videos.

A transcoding distribution device applied to a user side in a cloud platform, comprising:

The first acquisition module is used to obtain the transcoding complexity of each video segment to be transcoded and the transcoding performance value of each computing device forming the cloud platform;

The second acquisition module is used to obtain according to the formula Obtaining the first average time required for each of the computing devices to transcode the allocated video clips; where f ^* is the first average time, and m is the total number of computing devices in the cloud platform , n is the total number of video segments that need to be transcoded, c _i is the transcoding complexity of the i-th video segment, p _j is the transcoding performance value of the j-th computing device, t _overhead Starting a time average for the video segment; a judging module, configured to determine whether the transcoding time required for the first video segment on the first computing device is greater than the first average time;

An allocation module, configured to allocate the first video segment to the first computing device for transcoding when the judgment result is negative.

A transcoding device, applied to the user side in the cloud platform, including:

The segmentation module is used to segment the video to be transcoded to obtain each video segment to be transcoded;

a transcoding distribution device, configured to distribute each of the video clips;

A processing module, configured to obtain transcoded video clips after each computing device in the cloud platform transcodes the allocated video clips, and process them into transcoded videos.

The transcoding method in the embodiment of the present invention is to obtain the transcoding complexity of each video segment to be transcoded and the transcoding performance value of each computing device constituting the cloud platform; according to the transcoding complexity of each video segment 1. The transcoding performance value of each computing device obtains the first average time required for each computing device to transcode the assigned video segment; Whether the transcoding time is greater than the first average time; if the judgment result is no, assign the first video segment to the first computing device for transcoding. According to the obtained transcoding complexity of each video segment and the transcoding performance value of each computing device, the first average time required for each computing device to transcode the allocated video segment is obtained, when a video segment is in When the transcoding time on a computing device is not greater than the first average time, the video segment is allocated to the computing device, so that each video segment is allocated to a different computing device according to the characteristics of each video segment and each computing device , saving transcoding time and improving transcoding efficiency.

Description of drawings

FIG. 1 is a main structural diagram of a transcoding distribution device in an embodiment of the present invention;

FIG. 2 is a main structural diagram of a transcoding device in an embodiment of the present invention;

Fig. 3 is the main flow chart of the transcoding allocation method in the embodiment of the present invention;

FIG. 4 is a main flowchart of a transcoding method in an embodiment of the present invention.

Detailed ways

The transcoding allocation method in the embodiment of the present invention is to obtain the transcoding complexity of each video segment to be transcoded and the transcoding performance value of each computing device constituting the cloud platform; according to the transcoding complexity of each video segment According to the transcoding performance value of each computing device, obtain the first average time required by each computing device to transcode the assigned video clips respectively; Whether the transcoding time is greater than the first average time; if the judgment result is no, assign the first video segment to the first computing device for transcoding. According to the obtained transcoding complexity of each video segment and the transcoding performance value of each computing device, the first average time required for each computing device to transcode the allocated video segment is obtained, when a video segment is in When the transcoding time on a computing device is not greater than the first average time, the video segment is allocated to the computing device, so that each video segment is allocated to a different computing device according to the characteristics of each video segment and each computing device , saving transcoding time and improving transcoding efficiency.

Referring to FIG. 1 , the transcoding distribution device in the embodiment of the present invention includes a first obtaining module 101 , a second obtaining module 102 , a judging module 103 and a distribution module 104 . The apparatus described in the embodiments of the present invention can be applied to the user side in the cloud platform, that is, it can be located in any computing device that constitutes the cloud platform. The performance of each computing device among the computing devices constituting the cloud platform may be the same or different.

The first acquiring module 101 is configured to acquire the transcoding complexity of each video segment to be transcoded and the transcoding performance value of each computing device constituting the cloud platform.

Firstly, the first acquisition module 101 needs to acquire some parameters for calculation scheduling, the parameters at least include the transcoding complexity of each video clip and the transcoding performance value of each computing device constituting the cloud platform. When the performance of each computing device constituting the cloud platform is different, the first obtaining module 101 needs to obtain the transcoding performance value of each computing device constituting the cloud platform. The first obtaining module 101 can obtain the segmented video segments from the segmenting module 105, and then can estimate the transcoding complexity of each video segment. Assuming that there are n video clips after segmentation, which are respectively recorded as V=(1, 2, ..., n), where n is an integer not less than 2, and their obtained transcoding complexity can be respectively recorded as C= (c1, c2, ..., cn). At the same time, the first obtaining module 101 can request the server to obtain the transcoding history records of each computing device constituting the cloud platform. From the transcoding historical records of each computing device, the first obtaining module 101 can estimate the transcoding history of different computing devices. Code performance value. Wherein, the server may be a management device of the cloud platform, which may be served by any one of the computing devices constituting the cloud platform, or may be served by a dedicated computing device. Assuming that there are m computing devices, m is an integer greater than or equal to 1, and their transcoding performance values can be respectively recorded as P=(p1, p2, . . . , pn). At the same time, the startup time of each video clip as a task on different computing devices can be estimated, and the average startup time of the video clip can be obtained according to the startup time of each video clip on different computing devices, and the startup time of the video clip can be averaged The value is noted as t _overhead . Alternatively, the start-up time of each video clip on different computing devices is generally not much different, and the difference can even be ignored, so one of all start-up times can also be selected as t _overhead . Since the transcoding time required for a video segment is proportional to the transcoding complexity of the video segment itself, and inversely proportional to the transcoding performance value of the computing device, it can be obtained that the i-th segment is transcoded on the j working machine The required transcoding time can be called the first transcoding time, and can be represented by t _ij , where i and j are integers not less than 1:

${\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; ij</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; c</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; overhead</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

The second acquiring module 102 is configured to obtain the first transcoding required by each computing device for transcoding the allocated video clips according to the transcoding complexity of each video clip and the transcoding performance value of each computing device. an average time.

The average time required for all video clips to be transcoded on their assigned computing devices can be calculated according to the obtained t _ij , that is, the average time required for each computing device to transcode the assigned video clips respectively , which can be called the first average time:

${\mathrm{<span\; class="notranslate">\; f</span>}}^{<span\; class="notranslate">\; *</span>}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; c</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}}{{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}}<span\; class="notranslate">\; +</span>\frac{\mathrm{<span\; class="notranslate">\; no</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; t</span>}}_{\mathrm{<span\; class="notranslate">\; overhead</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; )</span>$

Then use this as a reference, so that the transcoding time required by each computing device should not exceed the first average time as much as possible. You can use f _j to represent the transcoding time required by the jth computing device, because each computing device transcodes video clips in a serial process, that is, a computing device can only transcode one video clip at a time , but cannot transcode multiple video clips at the same time, so f _j should be equal to the sum of the transcoding time required by all the video clips allocated to the computing device. Initially, the default transcoding time for all computing devices is zero, and then the distribution of video segments begins.

The judging module 103 is configured to judge whether the transcoding time required by the first video segment on the first computing device is greater than the first average time.

First, the judging module 103 needs to sort the video clips that need to be transcoded according to their transcoding complexity. In the embodiment of the present invention, sorting from large to small is taken as an example, and at the same time, each computing device can be sorted according to the size of its transcoding performance value Sort from largest to smallest. After sorting, two queues can be obtained, namely the queue of video clips to be allocated and the queue of computing devices to be selected. When allocating, the computing device with the best transcoding performance value may be selected from the queue of computing devices to be selected as the computing device to be processed currently, that is, the computing device at the front of the queue of computing devices to be selected. Then, from the video segment queue to be allocated, select the video segment with the largest transcoding complexity, that is, the video segment at the front of the video segment queue to be allocated, and allocate it. The judging module 103 can judge whether the transcoding time required by the currently pending computing device to transcode the video segment will not overflow, that is, whether the required transcoding completion time is not greater than the first average time.

The allocation module 104 is configured to allocate the first video segment to the first computing device for transcoding when the determination result is no.

That is, when it is assumed that the i-th video clip (or called the first video clip) is assigned to the j-th computing device (or called the first computing device), if:

f _j +t _ij ≤ f ^* (3)

Then the allocation module 104 determines to allocate the first video segment to the first computing device.

In the first round of allocation, the transcoding time required by each computing device may be as close as possible to the first average time (but not greater than the first average time). For example, there are 5 video clips in the queue of video clips to be allocated, and 3 computing devices in the queue of computing devices to be selected, and the first average time is 5 seconds. After the first video segment is assigned to the first computing device, the judging module 103 determines that the transcoding time required by the first computing device is 2 seconds, and the assigning module 104 determines to assign the first video segment to the first computing device. computing device, the judging module 103 judges whether the transcoding time required by the first computing device is equal to the first average time, because 2<5, then the judging module 103 can continue to determine that the second video segment is allocated to The transcoding time required by the first computing device after the first computing device, if the second video segment is assigned to the first computing device, the total transcoding time required by the first computing device is 4.5 seconds, then the allocation module 104 can determine that the second video segment is also allocated to the first computing device, because 4.5<5, then the judging module 103 can continue to determine that the third video segment is allocated to the first The transcoding time required by the first computing device after the computing device, if the transcoding time required by the first computing device after assigning the third video clip to the first computing device is 7 seconds, exceeds The first average time, then the allocation module 104 determines that the third video segment cannot be allocated to the first computing device, and can continue to judge whether the third video segment can be allocated to the second computing device with the same steps. equipment.

After the first round of distribution ends, if the judging module 103 determines that there are unallocated video clips in the queue of video clips to be distributed, the judging module 103 can obtain each computing device according to each different video clip. The required transcoding time after the video segment, that is, traverse each computing device for each remaining video segment, obtain the required transcoding time after adding the video segment to different computing devices, and select the required transcoding time from it A minimum computing device, the distribution module 104 is notified to distribute the video segment to the computing device. For example, there are 3 remaining video clips in the queue of video clips to be allocated, and there are 5 computing devices in the cloud platform (i.e., the queue of computing devices to be selected), then when the first remaining video clip is allocated, the judging module 103 can Obtain the transcoding time required by the last five computing devices allocated to the five computing devices respectively, if the judgment module 103 determines that the transcoding time required by the second computing device plus the first remaining video segment is the least , the allocation module 104 determines to allocate the first remaining video segment to the second computing device. Then follow the same steps to continue to allocate other remaining video segments until the queue of video segments to be allocated is empty.

In the first round of allocation process, if the judging module 103 determines that no matter which computing device a video segment is allocated to, the transcoding time required by the computing device is greater than the first average time, then the allocation module 104 may perform the first round of When allocating, allocate the video segment to the computing device that requires the least transcoding time after adding the video segment, or skip the video segment in the first round of allocation and leave it unprocessed until the first round After the allocation is complete, the allocation module 104 allocates it to the computing device that requires the least transcoding time after adding the video segment, so as to save transcoding time as much as possible.

As shown in FIG. 2 , an embodiment of the present invention also provides a transcoding device, which may further include a segmentation module 105 and a processing module 106 in addition to the transcoding distribution apparatus.

The segmentation module 105 is used to segment the video to be transcoded to obtain each video segment to be transcoded. The segmenting module 105 is responsible for obtaining the original video data to be transcoded from the local storage, and then segmenting it into at least two video segments that can be transcoded independently. In order to ensure data independence between video clips, it is necessary to ensure segmentation between Groups of pictures (GOP). For reference frame dependencies between GOPs, it is necessary to add a redundant GOP after the video clips, which ensures that the two video clips can be encoded independently, and the transcoded video clips can also be merged at the end. Make sure you get the full transcoded video.

The processing module 106 is configured to obtain transcoded video clips after each computing device in the cloud platform transcodes the allocated video clips, and process them into transcoded videos. The processing method may be merging. After each computing device completes the transcoding of all the video clips, the processing module 106 acquires the transcoded video clips from the server, and then merges them in order. Wherein, after segmenting the video to be transcoded, the segmenting module 105 can number each segmented video segment, so that the processing module 106 can merge the transcoded video segments according to the sequence of numbers. For a redundant segment with one GOP added, when two segments are merged, a GOP will be repeated, and the redundant GOP can be used as the output at this time.

Using the transcoding device to complete the transcoding task can save transcoding time and improve transcoding efficiency.

The embodiment of the present invention also provides a server, which can be located on the network side of the cloud platform. The allocation module 104 may notify the server of the allocation result, and the server is responsible for allocating the corresponding video segment to the corresponding computing device, and notifying the corresponding computing device to perform transcoding. Each computing device notifies the server after the transcoding is completed, and the server may send the transcoded video clips to the processing module 106 after the transcoding of each computing device is completed, and the processing module 106 performs merging processing. Wherein, the segmentation module 105 can store in the local virtual storage area after the video is segmented into video clips, and each computing device constituting the cloud platform can have a virtual storage area, which can constitute a cloud platform virtual storage area , which can be managed uniformly by the server. After the allocation module 104 allocates each video segment, the server allocates different video segments to the corresponding computing device according to the distribution result, and the computing device performs transcoding according to the video segment sent by the server, and after the transcoding is completed, the transcoded video segment is played. into the virtual storage area, and notify the server, and then the server sends the transcoded video clips to the transcoding distribution device.

The transcoding allocation method and the transcoding method in the embodiments of the present invention are introduced below through specific embodiments.

Referring to Fig. 3, the specific method flow of transcoding allocation in the embodiment of the present invention is as follows:

Step 301: Obtain the transcoding complexity of each video clip that needs to be transcoded and the transcoding performance value of each computing device that constitutes the cloud platform.

Step 302: According to the transcoding complexity of each video segment and the transcoding performance value of each computing device, obtain a first average time required for each computing device to transcode the assigned video segment.

Step 303: Determine whether the transcoding time required for the first video segment on the first computing device is greater than the first average time. When the judgment result is yes, because the video clips and computing devices have been sorted before, it can be determined that the transcoding time required for the computing device to execute the first video clip will also be greater than the first average time, then the first video segment can not be processed temporarily, and the first video segment can be skipped to process the next video segment first, and then the first video segment can be processed after the first round of distribution is completed, and it can be assigned to the added The computing device that requires the least transcoding time after uploading the transcoding time required for the first video segment, or can directly process the first video segment in the first round of allocation, and allocate it to the plus The computing device that requires the least transcoding time after the transcoding time required for the first video segment.

Step 304: When the judgment result is no, assign the first video segment to the first computing device for transcoding.

Referring to Figure 4, the specific implementation process of the transcoding method in the embodiment of the present invention is as follows:

Step 401: Segment the video to be transcoded to obtain video segments to be transcoded.

Step 402: Allocate each of the video clips according to the transcoding allocation method.

Step 403: After each computing device in the cloud platform completes the transcoding of the allocated video segment, obtain the transcoded video segment, and process it into a transcoded video.

The transcoding method in the embodiment of the present invention is to obtain the transcoding complexity of each video segment to be transcoded and the transcoding performance value of each computing device constituting the cloud platform; according to the transcoding complexity of each video segment 1. The transcoding performance value of each computing device obtains the first average time required for each computing device to transcode the assigned video segment; Whether the transcoding time is greater than the first average time; if the judgment result is no, assign the first video segment to the first computing device for transcoding. According to the obtained transcoding complexity of each video segment and the transcoding performance value of each computing device, the first average time required for each computing device to transcode the allocated video segment is obtained, when a video segment is in When the transcoding time on a computing device is not greater than the first average time, the video segment is allocated to the computing device, so that each video segment is allocated to a different computing device according to the characteristics of each video segment and each computing device , saving transcoding time and improving transcoding efficiency. Through the technical solutions of the embodiments of the present invention, relatively complex video clips can be scheduled to computing devices with better performance ratios, so that these computing devices can obtain a relatively small number of video clips, thereby reducing their task startup time.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims (10)

1. a transcoding distribution method, is applied to the user side in cloud platform, it is characterized in that, comprise the following steps:

Obtain the transcoding performance value of the transcoding complexity treating each video segment of transcoding and each computing equipment forming described cloud platform;

According to formula obtain each described computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Wherein f ^*for described first average time, m for the total quantity of computing equipment described in described cloud platform, n be the total quantity of the described video segment needing to carry out transcoding, c _ibe the described transcoding complexity of i-th video segment, p _jfor the described transcoding performance value of a jth computing equipment, t _overheadfor video segment mean value start-up time;

Judge whether the transcoding time needed for the first video segment is on the first computing equipment is greater than described first average time;

When judged result is no, described first video segment is assigned on described first computing equipment and carries out transcoding.

2. the method for claim 1, it is characterized in that, judging the first video segment transcoding time required on the first computing equipment also comprises step before whether being greater than described first average time: sorted according to the order that transcoding complexity described in it is descending by each described video segment, and each described computing equipment is worth descending order according to transcoding performance described in it is sorting;

Judge whether the first video segment transcoding time required on the first computing equipment is greater than the step of described first average time and comprises: judge whether the transcoding time needed for described first video segment is on described first computing equipment is greater than described first average time according to the sequence of each described video segment and the sequence of each described computing equipment.

3. the method for claim 1, is characterized in that, described first video segment is assigned to described first computing equipment carries out transcoding after also comprise step:

Judge whether the transcoding time needed for described first computing equipment equals described first average time;

When judged result is no, continue judge described first video segment and the second video segment on the first computing equipment needed for the transcoding time whether be greater than described first average time;

When judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is not more than described first average time, described second video segment being assigned on described first computing equipment and carrying out transcoding;

When judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is greater than described first average time, continue to judge whether the transcoding time needed for described second video segment is on the second computing equipment is greater than described first average time.

4. the method for claim 1, is characterized in that, described first video segment is assigned to described first computing equipment carries out transcoding after also comprise step:

Judge whether remaining video fragment;

When judged result is for being, according to each described computing equipment of described remaining video fragment traversal, select a described computing equipment adding the transcoding minimal time after the transcoding time needed for described remaining video fragment needed for it;

Described computing equipment is given by described remaining video fragment allocation.

5. a code-transferring method, is applied to the user side in cloud platform, it is characterized in that, comprise the following steps:

To treat that the video of transcoding carries out cutting, obtain each video segment treating transcoding;

According to the transcoding distribution method as described in any one of claim 1-4, video segment as described in each is distributed;

The described video segment distributed carries out after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding by each computing equipment in described cloud platform.

6. a transcoding distributor, is applied to the user side in cloud platform, it is characterized in that, comprising:

First acquisition module, for obtaining the transcoding complexity of each video segment treating transcoding and forming the transcoding performance value of each computing equipment of described cloud platform;

Second acquisition module, for according to formula obtain each described computing equipment and respectively carried out to the described video segment distributed the first average time needed for transcoding; Wherein f ^*for described first average time, m for the total quantity of computing equipment described in described cloud platform, n be the total quantity of the described video segment needing to carry out transcoding, c _ibe the described transcoding complexity of i-th video segment, p _jfor the described transcoding performance value of a jth computing equipment, t _overheadfor video segment mean value start-up time;

Judge module, for judging whether the first video segment transcoding time required on the first computing equipment is greater than described first average time;

Distribution module, during for being no when judged result, being assigned to described first video segment on described first computing equipment and carrying out transcoding.

7. device as claimed in claim 6, is characterized in that, described judge module also for:

Each described video segment is sorted according to the order that transcoding complexity described in it is descending, and each described computing equipment is worth descending order according to transcoding performance described in it sorts;

Judge whether described first video segment transcoding time required on described first computing equipment is greater than described first average time according to the sequence of each described video segment and the sequence of each described computing equipment.

8. device as claimed in claim 6, is characterized in that, described judge module also for: judge whether the transcoding time needed for described first computing equipment equals described first average time; When judged result is no, continue judge described first video segment and the second video segment on the first computing equipment needed for the transcoding time whether be greater than described first average time; And when judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is greater than described first average time, continue to judge whether the transcoding time needed for described second video segment is on the second computing equipment is greater than described first average time;

Described second video segment also for when judging to determine that described first video segment and the second video segment transcoding time required on the first computing equipment is not more than described first average time, being assigned on described first computing equipment and carrying out transcoding by described distribution module.

9. device as claimed in claim 6, it is characterized in that, described judge module is also for having judged whether remaining video fragment, when judged result is for being, according to each described computing equipment of described remaining video fragment traversal, select a described computing equipment adding the transcoding minimal time after the transcoding time needed for described remaining video fragment needed for it;

Described distribution module is also for giving described computing equipment by described remaining video fragment allocation.

10. a transcoding device, is applied to the user side in cloud platform, it is characterized in that, comprising:

Cutting module, for treating that the video of transcoding carries out cutting, obtains each video segment treating transcoding;

Transcoding distributor as described in any one of claim 6-9, for distributing each described video segment;

Processing module, to be undertaken the described video segment distributed after transcoding completes, obtaining the video segment after transcoding, being treated to the video after transcoding for each computing equipment in described cloud platform.