WO2022252083A1

WO2022252083A1 - Data transmission method and apparatus, and electronic device and storage medium

Info

Publication number: WO2022252083A1
Application number: PCT/CN2021/097487
Authority: WO
Inventors: 郭小东; 张海波; 唐飞龙; 郭铭潇
Original assignee: 华为技术有限公司
Priority date: 2021-05-31
Filing date: 2021-05-31
Publication date: 2022-12-08
Also published as: CN117441337A

Abstract

Disclosed in the present application are a data transmission method and apparatus, and an electronic device and a storage medium. The method comprises: sending a first sub-stream request to a first sending node, and sending a second sub-stream request to a second sending node, wherein the first sending node is a node that provides a first sub-stream, the second sending node is a node that provides a second sub-stream, and the first sub-stream and the second sub-stream are obtained by means of dividing an original stream; receiving the first sub-stream and the second sub-stream; and decoding the first sub-stream and the second sub-stream to obtain the original stream. By means of the present method, the whole mobile distributed stream transmission process is split into a plurality of sub-stream distribution tree model transmission processes, such that the data transmission pressure of a single node in a stream transmission network can be reduced to a great extent, and loads of data sending nodes are more balanced; and uplink bandwidths of the nodes in a mobile distributed stream transmission network environment are fully matched, such that the destruction-resistance and the transmission efficiency of the whole stream transmission network are higher.

Description

A data transmission method, device, electronic equipment and storage medium

technical field

The present application relates to the technical field of data processing, and in particular to a data transmission method, device, electronic equipment and storage medium.

Background technique

Data transmission is a communication process that transmits data from a data source to a data terminal through one or more data links according to certain procedures. A good data transmission method can improve the real-time and reliability of data transmission, making data transmission faster, safer and more efficient. With the continuous development of electronic computing and network communication, more and more application scenarios need to rely on efficient data transmission, and people's demand for efficient data transmission is increasing. For example, for a live broadcast of a product launch event, the number of users watching the live broadcast online is uncertain, and a large number of online users will far exceed the bandwidth load of the content delivery network (CDN), resulting in data transmission stuck Suddenly, there were problems such as crashes and disconnections in the live broadcast, which brought poor experience to users.

At present, the decentralized real-time streaming media transmission based on the distribution tree method is the most widely used data transmission method. In the data transmission method, each node participating in the data transmission is structured into a streaming media transmission tree, and the source node divides the streaming media file into several file blocks, and transmits the stream through corresponding child nodes on the transmission tree.

However, the above data transmission method is highly dependent on the uplink bandwidth of a single node, and disconnection of a certain node will cause data transmission failure of all child nodes under the node. Therefore, the data transmission method has low bandwidth utilization, poor invulnerability, and low data transmission efficiency.

Contents of the invention

The embodiment of the present application provides a data transmission method, device, electronic equipment, and storage medium. By splitting the entire mobile distributed stream transmission process into multiple sub-stream distribution tree model transmission processes, the convective transmission can be greatly reduced. The data transmission pressure of a single node in the network makes the load of the data sending node more balanced, fully matches the uplink bandwidth of each node in the mobile distributed streaming network environment, and makes the entire streaming network more robust and efficient.

In the first aspect, the embodiment of the present application provides a data transmission method, the method including:

sending a first request to a first sending node;

receiving the first substream sent by the first sending node in response to the first request;

sending a second request to a second sending node;

receiving the second substream sent by the second sending node in response to the second request; the first sending node is different from the second sending node; the first substream and the second substream are both Consisting of chunks of data in an original stream, said first substream is different from said second substream.

In the embodiment of the present application, by dividing the original stream into multiple sub-streams, and then splitting the entire mobile distributed stream transmission process into multiple sub-stream transmission processes, the transmission efficiency of the entire transmission network is higher. Specifically, the first requesting node sends a first request to the first sending node, where the first request is used to request the first sending node to send the first substream. A first requesting node sends a second request to a second sending node, where the second request is used to request the second sending node to send a second substream. Wherein, the first substream and the second substream are obtained by dividing the original stream, and the first substream and the second substream are not completely the same. The first requesting node receives the first sub-stream and the second sub-stream. So far, the embodiment of the present application divides the original stream into the first sub-stream and the second sub-stream, and further divides the transmission process of the original stream into the first sub-stream and the second sub-stream, thereby improving the efficiency of the entire transmission network. transmission efficiency.

The current data transmission method usually uses a distribution tree-based method for decentralized real-time streaming media transmission. Each node participating in data transmission is structured into a streaming media transmission tree, and the source node divides the streaming media file into several file blocks, and transmits the stream through the corresponding child nodes on the transmission tree. Therefore, the uplink bandwidth of a single node is highly dependent, and the disconnection of a certain node will cause data transmission failure of all child nodes under the node.

Compared with the current data transmission method, the data transmission method provided by the embodiment of the present application adopts the process of splitting the entire mobile distributed stream transmission process into multiple sub-stream distribution tree model transmissions, which can greatly reduce the number of convection transmission networks. The data transmission pressure of a single node in the network makes the load of the data sending node more balanced, fully matches the uplink bandwidth of each node in the mobile distributed streaming network environment, and makes the entire streaming network more robust and efficient.

In a possible implementation manner, the method also includes:

Decoding the first substream and the second substream to obtain the original stream.

In the embodiment of the present application, after receiving the first substream and the second substream, the first requesting node decodes the first substream and the second substream to obtain the original stream. In the embodiment of the present application, the transmission efficiency of the entire transmission network is improved by dividing the original stream into the first sub-stream and the second sub-stream, and then splitting the transmission process of the original stream into the first sub-stream and the second sub-stream. .

In a possible implementation manner, the original stream includes a first file block and a second file block, and both the first sub-stream and the second sub-stream include the first file block and the second file Data blocks in blocks.

In the embodiment of the present application, a possible implementation manner of dividing substreams is provided by describing data blocks included in the first substream and the second substream. Divide the original stream into two or more file blocks, each file block includes two or more data blocks. Indexes of all data blocks are numbered in time order, and the data blocks are divided into different sub-streams according to the data block indexes, so that each divided sub-stream includes at least one data block in each file block. Specifically, the original stream is divided into a first file block and a second file block, and the first file block and the second file block include two or more data blocks. The data block is divided into the first sub-stream or the second sub-stream according to the data block index, so as to realize the purpose of dividing the original stream into the first sub-stream and the second sub-stream. Wherein, the first substream includes at least one data block in the first file block and at least one data block in the second file block, and the second substream includes at least one data block in the first file block and the second file block At least one data block in the block.

The substream division method provided by the embodiment of the present application makes the divided first substream and second substream both include at least one data block in the first file block and at least one data block in the second file block, ensuring that the first After receiving the first sub-stream and the second sub-stream, a requesting node can restore the original stream by encoding the first sub-stream and the second sub-stream, thereby improving data transmission efficiency.

In a possible implementation manner, the first substream includes a data block obtained by performing redundant encoding on the first file block, or a data block obtained by performing redundant encoding on the second file block; The second substream includes a data block obtained by performing redundant encoding on the first file block, or a data block obtained by performing redundant encoding on the second file block.

In the embodiment of the present application, a possible implementation manner of substream redundancy coding is provided by describing the data blocks included in the first file block and the second file block. Divide the original stream into two or more file blocks, each file block contains two or more data blocks. Perform forward error correction code (Forward Error Correction, FEC) encoding on the data blocks in each file block to obtain new redundant data blocks, and add the redundant data blocks to the corresponding file blocks, so that each file block The data blocks in are the data blocks in the original stream, or the data blocks obtained by redundantly encoding the file blocks. Specifically, divide the original stream into a first file block and a second file block, perform FEC encoding on the data block in the first file block to obtain a new redundant data block, and add the redundant data block to the first file block In the same way, FEC encoding is performed on the data blocks in the second file block to obtain a new redundant data block, and the redundant data block is added to the second file block. Therefore, the data blocks in the first file block are data blocks in the original stream, or data blocks obtained by redundantly encoding the first file block, and the data blocks in the second file block are data blocks in the original stream, or is a data block obtained by redundantly encoding the second file block.

In the embodiment of the present application, redundant coding of the file block is performed, and redundant data blocks are added to the file block, so as to realize the purpose of redundant coding of the substream. The newly added redundant data blocks can get the corresponding redundant sub-streams, so that even if there are several sub-streams that are disconnected during the stream transmission process, as long as the dropped sub-streams do not exceed the redundant sub-streams, the The received sub-stream is decoded to obtain the original stream, which improves the reliability and stability of sub-stream transmission.

In a possible implementation manner, the size of the first file block is determined by the data block type and the data block size in the original stream, and the size of the second file block is determined by the data block in the original stream The type and block size are determined.

In the embodiment of the present application, a possible implementation manner of dividing the file block is provided, that is, the size of the divided file block is determined by the type and size of the data block included in the original stream. The original streams transmitted in different application scenarios are different, and the data types and sizes contained in them are different. Therefore, the size of divided file blocks should be adjusted adaptively according to the application scenarios, which can improve the efficiency of data transmission.

In a possible implementation manner, both the first request and the second request include remaining bandwidth information of the first requesting node; the first requesting node sends the first request and the second request the requesting node; the remaining bandwidth information of the first requesting node is used by the first sending node to determine whether to send the first sub-stream, and is used by the second sending node to determine whether to send the second sub-stream .

In this embodiment of the present application, the substream request sent by the first requesting node includes remaining bandwidth information of the first requesting node. The sending node may receive substream requests from multiple requesting nodes. At this time, the sending node needs to select one or more requesting nodes with higher remaining bandwidth to send the substream according to the remaining bandwidth information of the requesting node. The remaining bandwidth of the first requesting node The bandwidth information is used by the sending node to determine whether to send the corresponding subflow to the first requesting node, so that the load of the data sending node is more balanced, and the data transmission efficiency is improved.

In a possible implementation manner, before sending the first substream request to the first sending node, the method further includes:

obtaining metadata of the original stream;

determining the first substream based on the metadata;

Based on the metadata, the first sending node is determined.

In the embodiment of the present application, a possible implementation manner of determining the sending node is provided. Before sending the first request to the first sending node, it is necessary to determine a node capable of providing the first substream, that is, the first sending node. Similarly, before sending the second request to the second sending node, it is necessary to determine a node capable of providing the second substream, that is, the second sending node. The above-mentioned first sending node and second sending node may be determined according to metadata of the original stream. The metadata includes division information of the original stream, which can be used to determine the data blocks included in the first sub-stream and the data blocks included in the second sub-stream. After the original stream is divided into the first sub-stream and the second sub-stream, the metadata is published in the streaming network group. The first requesting node may respectively initiate a request for the substream to the first sending node and the second sending node according to the metadata.

The embodiment of the present application determines the sending node that can provide the sub-stream through the metadata, and initiates a request for the sub-stream to the sending node, which can maximize the accuracy and efficiency of sub-stream positioning, thereby improving the transmission of the overall stream transmission network efficiency.

In a possible implementation manner, the determining the first sending node based on the metadata includes:

Based on the metadata, determine a set of candidate sending nodes; the set of candidate sending nodes includes candidate sending nodes owning the first substream;

Determining a first candidate sending node in the set of candidate sending nodes as the first sending node; the first candidate sending node is a candidate sending node whose distribution tree height is smaller than a first threshold.

In the embodiment of the present application, a possible specific implementation manner of determining the sending node is provided. According to the metadata, a set of candidate sending nodes is determined, and the set of candidate sending nodes includes one or more candidate sending nodes and their distribution tree height information in the transmission network. Among them, the above-mentioned candidate sending node is a potential first sub-stream providing node, if the start data block index and the end data block index of a sub-stream owned by a certain node cover the first sub-stream, then the node is regarded as a candidate sending node Stored in the set of candidate sending nodes. Then, by comparing the distribution tree heights of the candidate sending nodes in the candidate sending node set, determine the first candidate sending node whose distribution tree height is smaller than the first threshold as the first sending node, and send the first substream request to it. The first threshold is not a fixed value, and may vary according to different application scenarios. The candidate sending node with the smallest distribution tree height in the candidate sending node set may be selected by adjusting the first threshold as the final first substream providing node. Similarly, the second sending node may be determined through the above manner of determining the first sending node.

In this embodiment of the present application, through the start data block index and the end data block index of the sub-stream owned by the node, it is judged that the node completely covers the first sub-stream, so as to determine that the node is a potential first sub-stream providing node, and then the node The candidate sending node is stored in the candidate sending node set, and then a candidate sending node is selected from the candidate sending node set according to the distribution tree height information of the node as the first sending node to which the first substream request is sent. Through the above method, the effect of the final selected substream provider node can be optimized, the data transmission pressure on the upstream nodes in the streaming transmission network can be reduced to the greatest extent, and the upstream bandwidth of each node in the mobile distributed streaming network environment can be fully matched. , so that the load of the data sending node is more balanced, and the efficiency of data transmission in the streaming network is greatly improved.

In a possible implementation manner, before sending the first request to the first sending node, the method further includes:

receiving distribution tree height information sent by the first sending node, where the distribution tree height information of the first sending node is used by the first requesting node to determine the first sending node.

In the embodiment of this application, before sending the first request to the first sending node, the first requesting node determines the first sending node through the received distribution tree height information of the first sending node, and sends the first request, which improves the efficiency of data transmission in streaming networks.

In a possible implementation manner, the method also includes:

If the distribution tree heights of two or more candidate sending nodes are the same and smaller than the first threshold, the candidate sending node with the highest remaining bandwidth is determined as the first sending node.

In the embodiment of this application, the possible specific implementation of determining the sending node is further explained, and the candidate sending node with the smallest distribution tree height in the candidate sending node set is screened out by adjusting the first threshold and provided as the final first substream node, if there are two or more candidate sending nodes whose distribution tree heights are the same and less than the first threshold, determine the candidate sending node with the highest remaining bandwidth as the first substream providing node, that is, the first sending node node.

In a possible implementation manner, the determining the set of candidate sending nodes based on the metadata includes:

Based on the metadata, query a neighbor node or a network node; the neighbor node is a node whose transmission frequency with the first requesting node exceeds a frequency threshold;

adding the neighbor node that owns the first subflow to the set of candidate sending nodes, and adding the network node that owns the first subflow to the set of candidate sending nodes.

In the embodiment of the present application, a possible specific implementation manner of determining a set of candidate sending nodes is further described. According to the metadata, the division of the original flow can be obtained, and the neighbor node or network node is queried for the node that owns the first sub-flow. A node whose transmission frequency exceeds a frequency threshold.

In a possible implementation manner, the method also includes:

In the case that the first substream sent by the first sending node in response to the first request is abnormal, sending a third request to a second candidate sending node in the set of candidate sending nodes; the second The candidate sending node is a candidate sending node whose distribution tree height is smaller than the second threshold and not smaller than the first threshold, and the third request is used to request the second candidate sending node to send the first substream.

In the embodiment of the present application, a possible implementation manner of adjusting a substream sending node is provided. In the case that the response of the first sending node to the first request does not meet the preset condition, the first requesting node will select the second-best candidate sending node from the above-mentioned set of candidate sending nodes as a new first substream providing node, Dynamically adjust the sending node of the first sub-flow in the flow distribution tree. Specifically, the first requesting node will select the second candidate sending node in the set of candidate sending nodes as the new first substream providing node, and send a first substream re-request to the second candidate sending node, the first substream The re-request is used to request the second candidate sending node to send the first sub-stream. Wherein, the second candidate sending node is a candidate sending node whose distribution tree height is smaller than the second threshold and not smaller than the above first threshold, and the second threshold is similar to the above first threshold, and is not a fixed value, which can be determined according to the application scenario It varies from person to person. Candidate sending nodes whose distribution tree height is suboptimal in the set of candidate sending nodes may be screened out by adjusting the second threshold and used as final first substream providing nodes again. Similarly, when the response to the second request does not meet the preset condition, the second substream sending node may be adjusted in the above manner of adjusting the first substream sending node.

In the embodiment of the present application, a suboptimal candidate sending node is selected from the set of candidate sending nodes as a new substream sending node through the distribution tree height information of the node, and a substream re-request is sent to it to continue to obtain substreams to be received. flow. Through the above method, the effect of the final selected substream provider node can be optimized, the data transmission pressure on the upstream nodes in the streaming transmission network can be reduced to the greatest extent, and the upstream bandwidth of each node in the mobile distributed streaming network environment can be fully matched. , so that the load of the data sending node is more balanced, and the efficiency of data transmission in the streaming network is greatly improved.

In a possible implementation manner, when receiving the first substream sent by the first sending node in response to the first request is abnormal, sending the second candidate in the set of candidate sending nodes The sending node sends a third request, including:

If the first sending node has not sent the first substream within a preset time, sending the third request to the second candidate sending node; or,

If the transmission of the first substream is interrupted during the process of receiving the first substream, sending the third request to the second candidate sending node; or,

In the process of receiving the first substream, if the first transmission speed of the first substream is less than a preset threshold, send the third request to the second candidate sending node; or,

During the process of receiving the first substream and the second substream, the difference between the first transmission speed of the first substream and the second transmission speed of the second substream is greater than a target threshold, and When the first transmission speed is lower than the second transmission speed, sending the third request to the second candidate sending node.

In the embodiment of the present application, a possible specific implementation manner of adjusting a substream sending node is provided. After determining that the sending node of the first substream is the first sending node, a first request is sent to the first sending node, for requesting the first sending node to send the first substream. In the case that the first sending node does not send the first substream within the preset time, the first requesting node will select the second candidate sending node from the set of candidate sending nodes as a new first substream providing node, and Sending a first substream re-request to request the second candidate sending node to send the first substream, the preset time is not a fixed value and may vary according to different application scenarios. Or, in the case that the transmission of the first sub-stream is interrupted during the process of receiving the first sub-stream by the first requesting node, the first requesting node will select the second candidate sending node from the above-mentioned set of candidate sending nodes as the new first sub-stream. The stream providing node sends a first sub-stream re-request to it, which is used to request the second candidate sending node to send the first sub-stream. Or, in the process of receiving the first sub-stream and the second sub-stream, if the first transmission speed of the first sub-stream is much lower than the second transmission speed of the second sub-stream, that is, the difference between the first transmission speed and the second transmission speed If the difference is greater than the target threshold, the first requesting node will actively interrupt the transmission of the first substream with the first sending node, and select the second candidate sending node from the above candidate sending node set as a new first substream providing node, And send a first substream re-request to it, for requesting the second candidate sending node to send the first substream. The above-mentioned target threshold is similar to the above-mentioned first threshold and second threshold, and is not a fixed value, and may be different according to different application scenarios.

In the embodiment of the present application, when the response to the first request does not meet the preset condition, a suboptimal candidate sending node is selected from the candidate sending node set as a new substream sending node through the distribution tree height information of the node, And send a sub-stream re-request to it, for continuing to obtain the sub-stream to be received. Through the above method, the effect of the final selected substream provider node can be optimized, the data transmission pressure on the upstream nodes in the streaming transmission network can be reduced to the greatest extent, and the upstream bandwidth of each node in the mobile distributed streaming network environment can be fully matched. , so that the load of the data sending node is more balanced, and the efficiency of data transmission in the streaming network is greatly improved.

In a possible implementation manner, the method also includes:

When the number of sub-stream interruptions is greater than the number of redundant sub-streams, pull the required data blocks in the first sub-stream to the nodes in the synchronization group; the nodes in the synchronization group are during transmission and The first requesting node is a node at the same starting position.

In the embodiment of the present application, a possible implementation manner of handling interruption of sub-stream transmission is also provided. In the case that the transmission of the first sub-stream is interrupted during the process of receiving the first sub-stream by the first requesting node, if the number of interrupted sub-streams is greater than the number of redundant sub-streams, the first requesting node actively pulls the sub-stream from the nodes in the synchronization group. The required data blocks in the first sub-stream until the first requesting node is relocated to a new first sub-stream providing node. Wherein, the nodes in the synchronization group are nodes at the same starting position as the first requesting node during the transmission process, that is, the nodes in the synchronization group and the data receiving process of the first requesting node are in a state of synchronization. Similarly, in the case that the transmission of the second sub-stream is interrupted during the process of receiving the second sub-stream by the first requesting node, if the number of interrupted sub-streams is greater than the number of redundant sub-streams, the first requesting node actively The required data blocks in the second sub-stream are pulled until the first requesting node is relocated to a new second sub-stream providing node.

The embodiment of the present application uses the above synchronization group mechanism to actively pull the data blocks required by the disconnected sub-stream when the sub-stream is interrupted too much, until the requesting node is relocated to a new sub-stream providing node, which can effectively improve the transmission of the sub-stream efficiency.

In a possible implementation manner, the first subflow re-request includes remaining bandwidth information of the first requesting node, and the remaining bandwidth information of the first requesting node is used by the second candidate sending node to determine whether Send the first sub-stream.

In this embodiment of the present application, the first substream re-request sent by the first requesting node includes remaining bandwidth information of the first requesting node. The sending node may receive substream re-requests from multiple requesting nodes. At this time, the sending node needs to select one or more requesting nodes to send the substream according to the remaining bandwidth information of the requesting node. The remaining bandwidth information of the first requesting node is used for The sending node determines whether to send the first subflow to the first requesting node, so as to improve data transmission efficiency.

In a possible implementation manner, the method also includes:

The set of candidate sending nodes no longer includes the first candidate sending node.

In the embodiment of the present application, a possible specific implementation manner of adjusting the set of candidate sending nodes is also provided. That is, the sending nodes whose response to the first request does not meet the preset condition are deleted from the set of candidate sending nodes. Specifically, the first sending node does not send the first sub-stream within the preset time, or the transmission of the first sub-stream is interrupted during the process of receiving the first sub-stream, or the first requesting node actively interrupts the communication with the first sending node In the case of transmission of the first substream, the first candidate sending node is deleted from the set of candidate sending nodes, so that the set of candidate sending nodes no longer includes the first candidate sending node. The embodiments of the present application can improve the accuracy and stream transmission efficiency of the first requesting node in locating the substream providing node in the subsequent stream transmission process.

In a second aspect, an embodiment of the present application provides a data transmission method, the method including:

Receive a first request sent by a first requesting node or a second request sent by a second requesting node; the first request is used to request sending the first substream to the first requesting node, and the second request is used to request sending a second substream to the second requesting node; the first requesting node is different from the second requesting node; both the first substream and the second substream are composed of data blocks in the original stream , the first substream is different from the second substream;

Sending the first subflow to the first requesting node or sending the second subflow to the second requesting node.

In the embodiment of the present application, the original stream is divided into multiple sub-streams, and then the entire mobile distributed stream transmission process is split into multiple sub-stream transmission processes, so that the transmission efficiency of the entire transmission network is higher. Specifically, the first sending node receives substream requests sent by multiple requesting nodes, such as receiving the first request sent by the first requesting node or receiving the second request sent by the second requesting node, the first request is used to request the first The sending node sends the first substream, and the second request is used to request the first sending node to send the second substream. Wherein, the first sending node is a node that provides the first sub-stream or the second sub-stream, the first sub-stream and the second sub-stream are obtained by dividing the original stream, and the first sub-stream and the second sub-stream are incomplete same. After receiving the substream request, the first sending node will send the first substream to the first requesting node or send the second substream to the second requesting node according to the substream transmission information and node transmission status.

In a possible implementation manner, the original stream includes a first file block and a second file block, and both the first sub-stream and the second sub-stream include the first file block and the second file block. Data blocks in file blocks.

The substream division method provided by the embodiment of the present application makes the divided first substream and the second substream both include at least one data block in the first file block and at least one data block in the second file block, ensuring that the request After receiving the first sub-stream and the second sub-stream, the node can restore the original stream by encoding the first sub-stream and the second sub-stream, thereby improving data transmission efficiency.

In the embodiment of the present application, a possible implementation manner of substream redundancy coding is provided by describing the data blocks included in the first file block and the second file block. Divide the original stream into two or more file blocks, and each file block contains two or more data blocks. Perform FEC encoding on the data blocks in each file block to obtain new redundant data blocks, and add the redundant data blocks to the corresponding file blocks, so that the data blocks in each file block are the data blocks in the original stream , or a data block obtained by redundantly encoding a file block. Specifically, divide the original stream into a first file block and a second file block, perform FEC encoding on the data block in the first file block to obtain a new redundant data block, and add the redundant data block to the first file block In the same way, FEC encoding is performed on the data blocks in the second file block to obtain a new redundant data block, and the redundant data block is added to the second file block. Therefore, the data blocks in the first file block are data blocks in the original stream, or data blocks obtained by redundantly encoding the first file block, and the data blocks in the second file block are data blocks in the original stream, or is a data block obtained by redundantly encoding the second file block.

In a possible implementation manner, the first request includes remaining bandwidth information of the first requesting node, the second request includes remaining bandwidth information of the second requesting node; The remaining bandwidth information and the remaining bandwidth information of the second requesting node are used by the first sending node to determine whether to send the first sub-flow or the second sub-flow, and the first sending node is the first sub-flow or the sending node corresponding to the second substream.

In this embodiment of the present application, the first request sent by the first requesting node includes remaining bandwidth information of the first requesting node, and the second request sent by the second requesting node includes remaining bandwidth information of the second requesting node. The first sending node may receive sub-stream requests from multiple requesting nodes. At this time, the first sending node needs to select one or more requesting nodes with higher remaining bandwidth to send the sub-stream according to the remaining bandwidth information of the requesting nodes. Therefore, the above The remaining bandwidth information of the first requesting node and the remaining bandwidth information of the second requesting node are used by the first sending node to determine whether to send the first sub-flow to the first requesting node or to send the second sub-flow to the second requesting node, so that the data can be sent The load of the nodes is more balanced, which improves the efficiency of data transmission.

In a possible implementation manner, before receiving the first request sent by the first requesting node, the method further includes:

sending the distribution tree height information of the first sending node to the first requesting node, where the distribution tree height information of the first sending node is used by the first requesting node to determine whether to send the first sending node to the first sending node On request, the first sending node is a sending node sending the first sub-stream or the second sub-stream.

In this embodiment of the application, the first sending node will send the distribution tree height information of the first sending node to the first requesting node. There may be multiple potential sending nodes owning the first substream in the streaming network. The first requesting node The node needs to select a sending node according to the distribution tree height information of the potential sending node, and send the first request to it for the first substream transmission. Therefore, the distribution tree height information of the first sending node is used for the first requesting node to determine Whether to send the first request to the first sending node makes the load of the data sending node more balanced and improves the data transmission efficiency.

In a possible implementation manner, the sending the first subflow to the first requesting node or sending the second subflow to the second requesting node includes:

When the first sending node provides the first sub-stream and the remaining bandwidth of the first sending node is higher than the bit rate of the first sub-stream, sending the first sub-stream to the first requesting node flow; or,

When the first sending node provides the second substream and the remaining bandwidth of the first sending node is higher than the bit rate of the second substream, sending the second substream to the second requesting node Erziliu; or,

The first sub-stream and the second sub-stream are provided at the first sending node, and the remaining bandwidth of the first sending node is higher than the bit rate of the first sub-stream and the second sub-stream In the case of the sum of bit rates, the first substream is sent to the first requesting node, and the second substream is sent to the second requesting node.

In this embodiment of the present application, a possible implementation manner in which the first sending node sends the substream is provided. The first sending node will send the first substream to the first requesting node or send the second substream to the second requesting node according to the substream transmission information and the node transmission status. Specifically, when the first sending node provides the first sub-stream and the remaining bandwidth is higher than the bit rate of the first sub-stream, the first sub-stream is sent to the first requesting node; the second sub-stream is provided at the first sending node And when the remaining bandwidth is higher than the bit rate of the second sub-stream, send the second sub-stream to the second request node; provide the first sub-stream and the second sub-stream at the first sending node, and the remaining bandwidth is higher than the first sub-stream In the case of the sum of the bit rates of the sub-stream and the second sub-stream, the first sub-stream is sent to the first requesting node, and the second sub-stream is sent to the second requesting node.

In this embodiment of the present application, combined with the remaining bandwidth information of the first sending node and the sub-stream data it owns, the preferred sub-stream is sent to the requesting node, which can maximize bandwidth utilization and fully match the mobile distributed streaming network The uplink bandwidth of each node in the environment makes the load of the data sending node more balanced, and makes the transmission efficiency of the entire stream transmission network higher.

In a possible implementation manner, the sending the first substream to the first requesting node, and sending the second substream to the second requesting node include:

If the remaining bandwidth of the first requesting node is greater than the remaining bandwidth of the second requesting node, sending the first substream to the first requesting node;

updating the remaining bandwidth of the first sending node;

When the updated remaining bandwidth of the first sending node is higher than the bit rate of the second sub-stream, sending the second sub-stream to the second requesting node.

In the embodiment of the present application, a possible implementation manner in which the first requesting node sends the substream is further described. When the first sending node provides the first sub-stream and the second sub-stream, and the remaining bandwidth is higher than the bit rate of the first sub-stream and the second sub-stream, compare the remaining bandwidth of the first requesting node and the second requesting node , if the remaining bandwidth of the first requesting node is greater than the remaining bandwidth of the second requesting node, send the first substream to the first requesting node; then update the remaining bandwidth of the first sending node; the remaining bandwidth after the update of the first sending node is high In the case of the bit rate of the second sub-stream, the second sub-stream is sent to the second requesting node.

According to the remaining bandwidth information of each requesting node, the embodiment of the present application selects the requesting node with higher remaining bandwidth to send the requested substream, which can maximize the bandwidth utilization rate and fully match the mobile distributed streaming network environment. The uplink bandwidth of each node makes the load of the data sending node more balanced, making the transmission efficiency of the entire streaming transmission network higher.

In a third aspect, the embodiment of the present application provides a data transmission device, which includes:

a sending unit, configured to send a first request to a first sending node;

a receiving unit, configured to receive the first substream sent by the first sending node in response to the first request;

The sending unit is further configured to send a second request to a second sending node;

The receiving unit is further configured to receive a second substream sent by the second sending node in response to the second request; the first sending node is different from the second sending node; the first substream Both of the second substreams are composed of data blocks in the original stream, and the first substream is different from the second substream.

In a possible implementation manner, the device also includes:

A decoding unit, configured to decode the first substream and the second substream to obtain the original stream.

In a possible implementation manner, the first request includes remaining bandwidth information of the data transmission device, and the second request includes remaining bandwidth information of the data transmission device; the remaining bandwidth information of the data transmission device Used by the first sending node to determine whether to send the first sub-stream, or used by the second sending node to determine whether to send the second sub-stream.

In a possible implementation manner, the device also includes:

The receiving unit is further configured to obtain metadata of the original stream;

a determining unit, configured to determine the first sub-stream based on the metadata;

The determining unit is further configured to determine the first sending node based on the metadata.

In a possible implementation manner, the determining unit is specifically configured to determine a set of candidate sending nodes based on the metadata, where the set of candidate sending nodes includes a candidate sending node that owns the first substream;

The determining unit is specifically further configured to determine a first candidate sending node in the set of candidate sending nodes as the first sending node, and the first candidate sending node is a sending candidate whose distribution tree height is smaller than a first threshold node.

In a possible implementation manner, the receiving unit is further configured to receive the distribution tree height information sent by the first sending node, and the distribution tree height information of the first sending node is used by the data transmission device to determine The first sending node.

In a possible implementation manner, the determining unit is specifically further configured to, when the distribution tree heights of two or more candidate sending nodes are the same and less than the first threshold, select The sending node is determined as the first sending node.

In a possible implementation manner, the device also includes:

A query unit, configured to query a neighbor node or a network node based on the metadata; the neighbor node is a node whose transmission frequency with the first requesting node exceeds a frequency threshold;

The determining unit is specifically further configured to add the neighbor node owning the first subflow to the set of candidate sending nodes, and add the network node owning the first subflow to the set of candidate sending nodes .

In a possible implementation manner, the sending unit is further configured to send the candidate sending node A second candidate sending node in the set sends a third request; the second candidate sending node is a candidate sending node whose distribution tree height is less than a second threshold and not less than the first threshold, and the third request is used to request the The second candidate sending node sends the first substream.

In a possible implementation manner, the sending unit is further configured to, in the case that the first sending node does not send the first substream within a preset time, send sending said third request; or,

The sending unit is specifically further configured to send the third request to the second candidate sending node when the transmission of the first substream is interrupted during the process of receiving the first substream; or,

The sending unit is further configured to send the second candidate sending node to the second candidate sending node when the first transmission speed of the first substream is lower than a preset threshold during the process of receiving the first substream. the third request; or,

The sending unit is further configured to, during the process of receiving the first substream and the second substream, the first transmission speed of the first substream and the second transmission speed of the second substream When the speed difference is greater than the target threshold and the first transmission speed is smaller than the second transmission speed, sending the third request to the second candidate sending node.

In a possible implementation manner, the device also includes:

A pulling unit, configured to pull data blocks required in the first sub-stream from nodes in the synchronization group when the number of sub-stream interruptions is greater than the number of redundant sub-flows; the nodes in the synchronization group is the node at the same starting position as the first requesting node during the transmission process.

In a possible implementation manner, the first substream re-request includes remaining bandwidth information of the first requesting node, and the remaining bandwidth information of the first requesting node is used by the second candidate sending node to determine the The first request node.

In a possible implementation manner, the device also includes:

A deleting unit, configured to delete the first candidate sending node from the set of candidate sending nodes.

Regarding the technical effect brought about by the third aspect and any possible implementation manner, reference may be made to the introduction corresponding to the technical effect of the first aspect and the corresponding implementation manner.

In a fourth aspect, the embodiment of the present application provides a data transmission device, which includes:

A receiving unit, configured to receive a first request sent by a first requesting node or a second request sent by a second requesting node; the first request is used to request to send a first substream to the first requesting node, and the first requesting node The second request is used to request to send a second substream to the second requesting node; the first requesting node is different from the second requesting node; both the first substream and the second substream are composed of the original stream Composed of data blocks in , the first sub-stream is different from the second sub-stream;

A sending unit, configured to send the first substream to the first requesting node or send the second substream to the second requesting node.

In a possible implementation manner, the first request includes remaining bandwidth information of the first requesting node, the second request includes remaining bandwidth information of the second requesting node; The remaining bandwidth information and the remaining bandwidth information of the second requesting node are used by the data transmission device to determine whether to send the first sub-flow or the second sub-flow.

In a possible implementation manner, the sending unit is further configured to send the distribution tree height information of the data transmission device to the first request node, and the distribution tree height information of the data transmission device is used for the A first requesting node determines whether to send the first request to the data transmission device.

In a possible implementation manner, the sending unit is specifically configured to provide the first substream at the data transmission device and the remaining bandwidth of the data transmission device is higher than the bit rate of the first substream In the case of , sending the first sub-flow to the first requesting node; or,

The sending unit is further configured to send the second substream to the second substream when the data transmission device provides the second substream and the remaining bandwidth of the data transmission device is higher than the bit rate of the second substream. two requesting nodes to send the second sub-stream; or,

The sending unit is further configured to provide the first substream and the second substream at the data transmission device, and the remaining bandwidth of the data transmission device is higher than the bit rate of the first substream and the bit rate of the second substream, sending the first substream to the first requesting node, and sending the second substream to the second requesting node.

In a possible implementation manner, the device also includes:

The sending unit is specifically further configured to send the first substream to the first requesting node when the remaining bandwidth of the first requesting node is greater than the remaining bandwidth of the second requesting node;

an updating unit, configured to update the remaining bandwidth of the data transmission device;

The sending unit is further configured to send the second sub-stream to the second requesting node when the updated remaining bandwidth of the data transmission device is higher than the bit rate of the second sub-stream.

Regarding the technical effect brought by the fourth aspect and any possible implementation manner, reference may be made to the introduction corresponding to the technical effect of the second aspect and the corresponding implementation manner.

In the fifth aspect, the embodiment of the present application provides a data transmission device, the data transmission device includes a processor and a memory; the memory is used to store computer-executable instructions; the processor is used to execute the computer-executable instructions stored in the memory. instructions, so that the data transmission device executes the method according to the above first aspect and any possible implementation manner, or executes the method according to the above second aspect and any possible implementation manner. Optionally, the data transmission device further includes a transceiver, configured to receive signals or send signals.

In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, which is used to store instructions or computer programs; when the instructions or the computer programs are executed, the first aspect and the The method described in any possible implementation manner is implemented, or the second aspect and the method described in any possible implementation manner are implemented.

In the seventh aspect, the embodiment of the present application provides a computer program product, the computer program product includes instructions or computer programs; when the instructions or the computer programs are executed, the first aspect and any possible implementation The method described in the manner is realized, or the method described in the second aspect and any possible implementation manner is realized.

In an eighth aspect, an embodiment of the present application provides a chip, the chip includes a processor, and the processor is configured to execute instructions. When the processor executes the instructions, the chip performs the first aspect and any possible The method described in the implementation manner, or perform the method described in the second aspect and any possible implementation manner. Optionally, the chip further includes a communication interface, and the communication interface is used for receiving signals or sending signals.

In the ninth aspect, the embodiment of the present application provides a data transmission system, the system includes at least one data transmission device as described in the third aspect, or the data transmission device as described in the fourth aspect, or the data transmission device as described in the fifth aspect A data transmission device, or the chip described in the eighth aspect.

In addition, during the process of executing the method described in the above-mentioned first aspect and any possible implementation manner, or the method described in the above-mentioned second aspect and any possible implementation manner, in the above-mentioned method, the relevant sending information (such as The first sub-stream, the second sub-stream) and/or the process of receiving information can be understood as the process of outputting information by the processor, and/or the process of receiving input information by the processor. When outputting information, the processor may output information to a transceiver (or a communication interface, or a sending module) for transmission by the transceiver. After the information is output by the processor, additional processing may be required before reaching the transceiver. Similarly, when the processor receives input information, the transceiver (or communication interface, or sending module) receives the information and inputs it to the processor. Furthermore, after the transceiver receives the information, the information may require other processing before being input to the processor.

Based on the above principles, for example, the sending information mentioned in the foregoing method can be understood as the processor outputting information. For another example, receiving information may be understood as the processor receiving input information.

Optionally, for operations such as transmitting, sending, and receiving involved in the processor, if there is no special description, or if it does not conflict with its actual function or internal logic in the relevant description, it can be understood more generally as Processor output and receive, input and other operations.

Optionally, in the implementation process, the above-mentioned processor may be a processor dedicated to performing these methods, or a processor that executes these methods by executing computer instructions in a memory, such as a general-purpose processor. The above-mentioned memory can be a non-transitory (non-transitory) memory, such as a read-only memory (Read Only Memory, ROM), which can be integrated with the processor on the same chip, or can be respectively arranged on different chips. The embodiment does not limit the type of the memory and the arrangement of the memory and the processor.

In a possible implementation manner, the at least one memory is located outside the communication device.

In yet another possible implementation manner, the above at least one memory is located in the communication device.

In yet another possible implementation manner, part of the memory of the at least one memory is located inside the communication device, and another part of the memory is located outside the communication device.

In this application, the processor and the memory may also be integrated into one device, that is, the processor and the memory may also be integrated together.

In the embodiment of the present application, by splitting the entire mobile distributed stream transmission process into multiple sub-stream distribution tree model transmission processes, the data transmission pressure on a single node in the stream transmission network can be greatly reduced, making the data sending node The load is more balanced, fully matching the uplink bandwidth of each node in the mobile distributed streaming network environment, making the entire streaming network more robust and efficient.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings that need to be used in the embodiments of the present application. Obviously, the accompanying drawings described below are only some embodiments of the present application. Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

Figure 1a is a schematic diagram of the architecture of a distribution tree-based streaming network;

FIG. 1b is a schematic structural diagram of a distribution tree-based streaming network provided by an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a stream transmission node provided in an embodiment of the present application;

FIG. 3 is a schematic flow diagram of a data transmission method provided by an embodiment of the present application;

Fig. 4 is a schematic diagram of the effect of substream distribution provided by the embodiment of the present application;

Fig. 5 is a schematic diagram of the effect of redundant coding of a sub-stream provided by the embodiment of the present application;

FIG. 6 is a schematic diagram of the effect of a synchronization group mechanism provided by the embodiment of the present application;

FIG. 7 is a schematic diagram of an effect of adjusting a streaming transmission node provided by an embodiment of the present application;

FIG. 8 is a schematic flowchart of another data transmission method provided by the embodiment of the present application;

FIG. 9 is an interactive schematic diagram of a streaming network provided by an embodiment of the present application;

FIG. 10 is a schematic structural diagram of a data transmission device provided in an embodiment of the present application;

FIG. 11 is a schematic structural diagram of another data transmission device provided by an embodiment of the present application;

FIG. 12 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the following will describe the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application.

The terms "first" and "second" in the specification, claims and drawings of the present application are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally It also includes other steps or units inherent to these processes, methods, products, or devices.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

It should be understood that in this application, "at least one (item)" means one or more, "multiple" means two or more, and "at least two (items)" means two or three And three or more, "and/or", is used to describe the association relationship of associated objects, indicating that there can be three types of relationships, for example, "A and/or B" can mean: only A exists, only B exists, and A exists at the same time and B, where A and B can be singular or plural. The character "/" generally indicates that the contextual objects are an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one item (piece) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c ", where a, b, c can be single or multiple.

This application provides a data transmission method. In order to describe the solution of this application more clearly, some knowledge related to data transmission will be introduced below.

Redundant coding: A redundant code is a code that uses more symbols, or signal elements, than necessary to represent the information. Redundant encryption technology is applied, that is, the encoding principle of error-correcting codes is used, and a large amount of redundant information is added to encrypted files, so as to achieve the purpose of encryption. Currently, the redundant encryption technique studied by most researchers is public key cryptography. At present, commonly used redundant codes include Hamming codes, cyclic codes, algebraic geometry codes, etc., which are very rich in content and involve a wide range of fields.

Peer-to-peer (P2P): Also known as peer-to-peer technology, it is an Internet system that has no central server and relies on user groups (peers) to exchange information. Its role is to reduce the number of nodes in the previous network transmission to reduce the risk of data loss. Different from the central network system with a central server, each client of the peer-to-peer network is not only a node, but also has the function of a server. Any node cannot directly find other nodes, and must rely on its user group for information exchange.

Content Delivery Network (CDN): CDN is an intelligent virtual network built on the basis of the existing network, relying on the edge servers deployed in various places, through the load balancing, content distribution, scheduling and other functional modules of the central platform, so that Users can obtain the required content nearby, reduce network congestion, and improve user access response speed and hit rate. The key technology of CDN mainly includes content storage and distribution technology.

Human Oriented Network (HON): The main goal is to improve user experience and build a network around experience. The network involves three major capabilities: device-pipe-cloud collaboration, innovation/reconfiguration of system architecture, and promotion of network and terminal technology innovation.

Embodiments of the present application are described below with reference to the drawings in the embodiments of the present application.

With the continuous development of electronic computing and network communication, more and more application scenarios need to rely on efficient data transmission, and people's demand for efficient data transmission is increasing. Taking streaming media transmission as an example, the pusher uses streaming media transmission technology to compress a series of media data, and then sends them in segments through the network to provide users with real-time audio and video for viewing. As the core infrastructure of cloud networks, CDN has been continuously developed in recent years. Especially with the continuous development of video services, CDN has received great attention, and it is the key bearer and bridge to improve user experience. Especially for high-concurrency services such as live broadcasts, every large-scale live broadcast is a re-insurance event. For example, for a live broadcast of a product launch event, the number of users watching the live broadcast online is uncertain. A large number of online users will far exceed the bandwidth load of the CDN, resulting in data transmission freezes, live broadcast crashes, and disconnections. problems and bring poor user experience.

The p2p mode has the characteristics of potential scalability and easy deployment. This mode is that the users who participate in the live broadcast can also directly share data with the users who need it. This can effectively reduce the bottleneck of the centralized server. Therefore, in this mode, the The real-time transmission design of streaming media becomes very important. Existing p2p streaming media transmission methods can be divided into two categories according to the organizational structure of the overlay network: push streaming based on the distribution tree method and pull streaming using the mesh-pull method. Stream push refers to the process in which the sending node pushes stream data to the requesting node, and streaming refers to the process in which the requesting node actively pulls data from the data owner. Among them, the decentralized real-time streaming media transmission based on the distribution tree method is currently the most widely used data transmission method. In the data transmission method, each node participating in the data transmission is structured into a streaming media transmission tree, and the source node divides the streaming media file into several file blocks, and transmits the stream through corresponding child nodes on the transmission tree.

Please refer to FIG. 1a, which is a schematic diagram of a distribution tree-based streaming network architecture.

As shown in Figure 1a, the transmission system organizes the nodes participating in the transmission (source node, first node, second node, third node, fourth node, fifth node, sixth node, etc.) into a streaming media transmission tree, and the source The node divides the original stream into several file blocks (the first file block, the second file block, the nth file block, etc.), and the streaming media file blocks are streamed through the corresponding streaming media transmission tree.

Compared with using the mesh-pull method to pull streams, the above data transmission method solves the problem of redundant transmission, and ideally has higher transmission efficiency and network bandwidth utilization. However, the above data transmission method is highly dependent on the uplink bandwidth of a single node, and the disconnection of a certain node will cause the data transmission of all child nodes under the node to fail. If the connection is disconnected due to other reasons, all child nodes (fifth node, sixth node) connected to the node will not receive data, and the child nodes will not be able to quickly resume data transmission at this time. Therefore, the data transmission method has low bandwidth utilization, poor invulnerability, and low data transmission efficiency.

In addition, different devices generally have different transmission capabilities. In a distributed environment, the transmission system also needs to evaluate the data transmission capabilities of different nodes to reasonably regulate the structure of the distributed network for more effective streaming. For example, the number of users of mobile terminals such as mobile phones and tablets is getting higher and higher, which is a very important application scenario in business scenarios. Moreover, in mobile distributed network scenarios, users may be in different environments, and at the same time, users may frequently switch networks, open/close applications, etc., and put forward higher requirements for the reliability of distributed streaming technology. Requirements, the streaming system needs to build a data distribution system reasonably to ensure the most efficient data transmission.

To solve the problems of poor invulnerability and low data transmission efficiency in the above data transmission method, the embodiment of the present application provides a new stream transmission network architecture.

Please refer to FIG. 1b. FIG. 1b is a schematic structural diagram of a distribution tree-based streaming network provided by an embodiment of the present application.

As shown in Figure 1b, the transmission system organizes the nodes participating in the transmission (source node, first node, second node, third node, fourth node, fifth node, sixth node, etc.) into a streaming media transmission tree, and the source The node divides the original stream into several file blocks (the first file block, the second file block, the nth file block, etc.), and the streaming media file blocks are streamed through the corresponding streaming media transmission tree. The data transmission method based on this architecture can solve the problem of redundant transmission, and in an ideal state, the transmission efficiency and network bandwidth utilization are higher. Moreover, different from the transmission tree in Figure 1a, the transmission tree in the embodiment of the present application is a distributed topology architecture, and the data transmission between nodes does not depend on the uplink bandwidth of a single node. Fails the data transfer of all child nodes under this node. For example, the second node in Figure 1b is disconnected due to reasons such as changes in the mobile network bandwidth, which will cause the sub-nodes (such as the fifth node and the sixth node) connected to the node to fail to receive data. At this time, the fifth node The node and the sixth node will turn to request data transmission from the first node. Therefore, the stream transmission network architecture in the embodiment of the present application has higher bandwidth utilization, better invulnerability, and higher data transmission efficiency.

In addition, based on the new stream transmission network architecture, this application also provides a new data transmission method, which can be greatly expanded by splitting the entire mobile distributed stream transmission process into multiple sub-stream distribution tree model transmission processes. Reduce the data transmission pressure on a single node in the stream transmission network to a certain extent, make the load of the data sending node more balanced, fully match the uplink bandwidth of each node in the mobile distributed stream transmission network environment, and make the entire stream transmission network indestructible and The transmission efficiency is higher. Correspondingly, combined with the new data transmission method, the embodiment of the present application also designs a system composed of a whole set of sub-stream publishing, subscribing, sending, analyzing, corresponding distribution tree construction, adjustment and other modules.

Please refer to FIG. 2 . FIG. 2 is a schematic diagram of an architecture of a stream transmission node provided by an embodiment of the present application.

As shown in Figure 2, the system architecture of the streaming node includes a file processing module, a streaming file publishing module, a streaming file subscription module, a streaming data sending module, a distribution tree construction module, a distribution tree adjustment module, and a node capability analysis module.

Among them, the file processing module is mainly used for processing the original streaming media file, including dividing sub-streams, redundant encoding, and the like. By dividing the original stream into multiple sub-streams, and then splitting the entire mobile distributed stream transmission process into multiple sub-stream transmission processes, the transmission efficiency of the entire transmission network can be improved. Moreover, by redundantly encoding the file blocks, redundant data blocks are added to the file blocks, thereby achieving the purpose of substream redundant encoding. The newly added redundant data blocks can get the corresponding redundant sub-streams, so that even if there are several sub-streams that are disconnected during the stream transmission process, as long as the dropped sub-streams do not exceed the redundant sub-streams, the The received sub-stream is decoded to obtain the original stream, which can improve the reliability and stability of sub-stream transmission.

The stream file publishing module is mainly used to publish metadata about the original stream to the stream transmission network. The metadata includes the division of sub-streams, but does not include specific stream data.

The flow file subscription module is mainly used to decide whether to subscribe to the flow after receiving the metadata sent by the source node. By determining the sending node that can provide the sub-stream through the metadata, and initiating a request for the sub-stream to the sending node, the accuracy and efficiency of sub-stream positioning can be improved to the greatest extent, thereby improving the transmission efficiency of the overall stream transmission network.

The stream data sending module is mainly used to continuously push data to the data requester after the node establishes a connection.

The node capability analysis module is mainly used to analyze the data transmission capability of the node, and record the node transmission capability, so as to provide relevant information when building the flow distribution tree. By modeling the data transmission capabilities of nodes, the selection of child nodes and parent nodes is optimized, the height of the stream distribution tree is reduced, and the efficiency of stream transmission is improved.

The distribution tree construction module is mainly used to construct the distribution tree according to the data provided by the above-mentioned node capability analysis module modeling, and is used to determine the data sender and receiver. By building a mobile distributed sub-stream distribution tree, the entire streaming network can be structured and standardized, and the streaming distribution tree can be quickly built in the scenario of no central scheduler. By modeling the streaming network and node capabilities to optimize the selection of child nodes and parent nodes, the height of the sub-stream distribution tree can be minimized and the efficiency of stream transmission can be maximized.

The distribution tree adjustment module is mainly used to deal with the problem of node exit during the streaming process, quickly obtain urgently needed data blocks for streaming, and adjust the streaming distribution tree. For the problem of frequent exit and join of nodes in mobile distributed network, the stream transmission distribution tree is repaired by dynamically adjusting the stream transmission distribution tree. In the case of a lot of substream loss, if the received data blocks are not enough to restore the file blocks, you can actively pull the data blocks that are urgently needed for streaming until a connection is established with a new parent node to improve streaming efficiency.

Correspondingly, based on the foregoing stream transmission node system architecture, embodiments of the present application provide a new data transmission method.

Please refer to Figure 3, Figure 3 is a schematic flow chart of a data transmission method provided by the embodiment of the present application, the method includes but is not limited to the following steps:

Step 301: Send a first substream request to a first sending node, and send a second substream request to a second sending node.

A node in this embodiment of the present application is a connection point, which means a redistribution point or a communication endpoint, specifically an active electronic device connected to a network. The electronic device is equipped with a processor that can be used to execute computer-executable instructions, and can send, receive or forward information through a communication channel. Specifically, in data communication, the electronic device can be a data circuit termination device, such as a modulator, hub or switch, etc.; it can also be a data terminal device, such as a computer, mobile phone or host (such as a router, workstation or server) Wait. In addition, "first" and "second" in the embodiments of the present application are used to distinguish different objects, rather than to describe a specific order.

In this embodiment of the present application, the first requesting node sends the first substream request to the first sending node, and sends the second substream request to the second sending node. The first sending node is different from the second sending node, the first sending node is a node providing the first substream, and the second sending node is a node providing the second substream. The first substream request is used to request the first sending node to send the first substream, and the second substream request is used to request the second sending node to send the second substream. Wherein, the first sub-flow request and the second sub-flow request sent by the first requesting node both include remaining bandwidth information of the first requesting node. Because the sending node may receive sub-stream requests from multiple requesting nodes at the same time, the sending node needs to select one or more requesting nodes to send sub-streams according to the remaining bandwidth information of the requesting node, so the remaining bandwidth information of the first requesting node The sending node is used to determine the first requesting node, so that the load of the data sending node is more balanced, and the data transmission efficiency is improved.

In a possible implementation manner, the first substream and the second substream are obtained by dividing the original stream, and the first substream and the second substream are not completely the same. A possible implementation manner of dividing sub-streams will be provided below.

Divide the original stream into two or more file blocks, and each file block contains two or more data blocks. Indexes of all data blocks are numbered in time order, and the data blocks are divided into different sub-streams according to the data block indexes, so that each divided sub-stream includes at least one data block in each file block. Specifically, the original stream may be divided into a first file block and a second file block, and the first file block and the second file block include two or more data blocks. The data block is divided into the first sub-stream or the second sub-stream according to the data block index, so as to realize the purpose of dividing the original stream into the first sub-stream and the second sub-stream. The first substream includes at least one data block in the first file block and at least one data block in the second file block, and the second substream includes at least one data block in the first file block and at least one data block in the second file block at least one block of data. Wherein, the size of the above-mentioned divided file blocks may be determined by the data block type and data block size contained in the original stream. The original streams transmitted in different application scenarios are different, and the data types and sizes contained in them are different. Therefore, the size of divided file blocks should be adjusted adaptively according to the application scenarios, which can improve the efficiency of data transmission.

Please refer to FIG. 4 . FIG. 4 is a schematic diagram of an effect of substream distribution provided by an embodiment of the present application. The foregoing implementation manner of dividing substreams may be further described in conjunction with FIG. 4 . As shown in FIG. 4 , the original stream s is divided into more than two file blocks (first file block, second file block, third file block, etc.), and each file block includes five data blocks. Sort and number all data blocks (bilock _n , n=1,2,3,…) in chronological order starting from 1, and divide the data blocks into different sub-streams according to the data block index

, so that each sub-flow obtained by division

Contains at least one data block in each file block. Wherein, N _s and R _s are used to represent the number of sub-streams and the bit rate of the divided sub-streams respectively, and the index numbers of the data blocks contained in the i-th sub-stream include: k*N _s +i, k=0,1,2, … for substream

In terms of bitrates:

In the sub-stream distribution shown in Figure 4, the indexes of all data blocks are numbered, wherein the first file block includes data block 1, data block 2, data block 3, data block 4, data block 5, and the second file block Including data block 6, data block 7, data block 8, data block 9, and data block 10, the third file block includes data block 11, data block 12, data block 13, data block 14, and data block 15. According to the above data block index, the data block is divided into different sub-streams (first sub-stream A, second sub-stream B, third sub-stream C, fourth sub-stream D, fifth sub-stream E), so as to achieve The purpose of dividing the original stream into multiple sub-streams. Wherein, the first substream A includes at least one data block (data block 1) in the first file block, at least one data block (data block 6) in the second file block and at least one data block in the third file block (data block 11), the second substream B contains at least one data block (data block 2) in the first file block, at least one data block (data block 7) in the second file block, and at least one data block (data block 7) in the third file block At least one data block (data block 12), the third substream C contains at least one data block in the first file block (data block 3), at least one data block in the second file block (data block 8) and the third At least one data block (data block 13) in the file block, the fourth substream D contains at least one data block (data block 4) in the first file block, at least one data block (data block 9) in the second file block ) and at least one data block (data block 14) in the third file block, the fifth substream E includes at least one data block (data block 5) in the first file block, at least one data block in the second file block (data block 10) and at least one data block (data block 15) in the third file block.

The sub-stream division method provided by the embodiment of the present application makes each divided sub-stream contain at least one data block in each file block, thus ensuring that after the first requesting node receives each sub-stream, it can Sub-stream decoding restores to obtain the original stream, improving data transmission efficiency.

In a possible implementation manner, on the premise that the original stream is divided to obtain the first sub-stream and the second sub-stream, redundant coding may also be performed on the first sub-stream and the second sub-stream, so as to improve the efficiency of sub-stream transmission. reliability and stability. A possible implementation manner of substream redundant coding will be provided below.

Divide the original stream into two or more file blocks, each file block includes two or more data blocks. Perform FEC encoding on the data blocks in each file block to obtain new redundant data blocks, and add the redundant data blocks to the corresponding file blocks, so that the data blocks in each file block are the data obtained by dividing the original stream block, or a data block obtained by redundantly encoding a file block. Specifically, divide the original stream into a first file block and a second file block, perform FEC encoding on the data block in the first file block to obtain a new redundant data block, and add the redundant data block to the first file block In the same way, FEC encoding is performed on the data blocks in the second file block to obtain a new redundant data block, and the redundant data block is added to the second file block. Therefore, the data blocks in the first file block are the data blocks obtained by dividing the original stream, or the data blocks obtained by redundantly encoding the first file block, and the data blocks in the second file block are the data blocks obtained by dividing the original stream , or a data block obtained by redundantly encoding the second file block. The above-mentioned FEC is an error control method, which means that the signal is encoded according to a certain algorithm before being sent to the transmission channel, and the redundant code with the characteristics of the signal itself is added, and the received signal is processed according to the corresponding algorithm at the receiving end. The technology of decoding the signal to find out the error code generated during the transmission and correct it can greatly increase the reliability and stability of data communication.

Please refer to FIG. 5 . FIG. 5 is a schematic diagram of an effect of substream redundancy coding provided by an embodiment of the present application. The implementation manner of the above substream redundant coding can be further described in conjunction with FIG. 5 . As shown in FIG. 5, the original stream is divided into several file blocks including the first file block and the second file block. Wherein, the first file block includes four data blocks (data block 1, data block 2, data block 3, data block 4), and the second file block also includes four data blocks (data block 5, data block 6, data block 7. Data block 8). Perform FEC encoding on the data block in the first file block to obtain a new redundant data block, and add the redundant data block to the first file block. Similarly, perform FEC encoding on the data block in the second file block A new redundant data block is obtained, and the redundant data block is added to the second file block. Renumber all data block indexes from 1 in time order, and it can be obtained that the first file block after redundant encoding processing includes five data blocks (data block 1, data block 2, data block 3, data block 4, Data block 5), the second file block after redundant encoding processing also includes five data blocks (data block 6, data block 7, data block 8, data block 9, data block 10). Therefore, the data blocks in the above-mentioned first file block are data blocks obtained by dividing the original stream, or the data blocks obtained by redundantly encoding the first file block, and the data blocks in the above-mentioned second file block are obtained by dividing the original stream A data block, or a data block obtained by redundantly encoding the second file block. In addition, performing redundant encoding on the file block including four data blocks to obtain a new redundant data block, it can be obtained that the redundancy γ of the redundant encoding is: 1/4=0.25.

The sub-stream redundant coding method provided in the embodiment of the present application implements redundant coding of the sub-stream by adding redundant data blocks to the file block through redundant coding of the file block. The newly added redundant data blocks can get the corresponding redundant sub-streams, so that even if there are several sub-streams that are disconnected during the stream transmission process, as long as the dropped sub-streams do not exceed the redundant sub-streams, the The received substream is decoded to obtain the original stream. For example, assuming that each file block originally contains n data blocks, each file block contains n+γn data blocks after redundancy encoding, for n+γn substreams, even if there are several substreams that are disconnected, but As long as at least n substreams are received, the original stream can still be decoded. In the above-mentioned FIG. 4, a new redundant data block is obtained by redundant encoding of the first file block, and its index is renumbered as data block 5, and the first file block is added. Similarly, a new redundant data block is obtained by redundantly encoding the second file block, its index is renumbered as data block 10, and the second file block is added. A new redundant data block is obtained by redundantly encoding the third file block, its index is renumbered as data block 15, and the third file block is added. In this way, the newly added redundant data block can obtain the corresponding redundant sub-stream fifth sub-stream E. Originally, the original stream was divided into four sub-streams to obtain five sub-streams, so that in the process of stream transmission, even if there is a certain In the case of sub-stream transmission disconnection, as long as the dropped sub-stream does not exceed the number of newly added redundant sub-streams, the original stream can still be decoded according to the received sub-stream, which improves the reliability and stability of sub-stream transmission .

In a possible implementation manner, before the first requesting node sends the first sub-stream request to the first sending node and sends the second sub-stream request to the second sending node, the first requesting node needs to determine to provide the first A first sending node for the substream and a second sending node for providing the second substream. A possible implementation manner of determining the sending node will be provided below by taking the first requesting node determining the first sending node as an example.

After the source node divides the original flow and publishes the metadata of the original flow in the group of the transmission network, the first requesting node can determine the first sending node according to the metadata of the original flow, and initiate a request to the first sending node Request for the first substream. Specifically, the first requesting node first determines a set of candidate sending nodes according to the metadata

The candidate sending node set includes one or more candidate sending nodes and their distribution tree height information in the transmission network

Wherein, the above-mentioned candidate sending node is a potential provider node of the first substream _si , and whether the node is a potential provider node of the first substream _si can be judged through the data block index of the substream owned by the node, that is, if The starting data block index of the substream owned by a certain node

and last block index

completely covered the above-mentioned first sub-stream s _i , save this node as a candidate sending node to the set of candidate sending nodes

middle. The set of candidate sending nodes is determined by the above method

Afterwards, the first requesting node compares the set of candidate sending nodes

The distribution tree height of the candidate sending node in

will distribute the tree height

The first candidate sending node smaller than the first threshold is determined as the first sending node, and sends the first substream request to it, for requesting to send the first substream s _i . Wherein, the above-mentioned first threshold is not a fixed value, and may be different according to different application scenarios. Therefore, the set of candidate sending nodes can be screened out by adjusting the first threshold

middle distribution tree height

The smallest candidate sending node is used as the final first substream providing node. Similarly, the second sending node may also be determined through the above implementation manner of determining the first sending node. In summary, from the set of candidate sending nodes

The first sending node selected in must meet the following conditions:

Further, by adjusting the first threshold above, the candidate sending node with the smallest distribution tree height in the candidate sending node set is selected as the final first substream providing node, if there are two or more candidate sending nodes with the same distribution tree height and is less than the first threshold, the candidate sending node with the highest remaining bandwidth RB is determined as the final first substream providing node, that is, the first substream providing node must meet the conditions:

Further, the above-mentioned first requesting node first determines a set of candidate sending nodes according to the metadata. Specifically, it may first obtain the division of the original flow according to the metadata, and then query the neighbor nodes or network nodes for nodes that own the first sub-flow . Among them, the neighbor node is a node that periodically exchanges flow data with the first requesting node, that is, a node whose transmission frequency with the first requesting node exceeds a frequency threshold, and the frequency threshold is similar to the above-mentioned first threshold, and is not a fixed value , can vary according to different application scenarios.

Step 302: Receive the first substream and the second substream.

After the first request node sends the first sub-stream request to the first sending node and the second sub-stream request to the second sending node, if the first sending node accepts the first sub-stream request and sends the first sub-stream, the second The second sending node accepts the second substream request and sends the second substream, and the first requesting node receives the first substream and the second substream.

If the first sending node rejects the first sub-flow request or fails to send the first sub-flow, and the second sending node rejects the second sub-flow request or fails to send the second sub-flow, the first requesting node needs to The transmission state, the transmission state of the second sub-stream, the sending state of the first sending node, and the sending state of the second sending node dynamically adjust the sending nodes of the sub-stream in the stream distribution tree. The following will take the first request node dynamically adjusting the sending node of the first substream in the stream distribution tree as an example to provide a possible implementation manner of adjusting the sending node of the substream.

In a possible implementation manner, after determining that the sending node of the first substream is the first sending node, a first substream request is sent to the first sending node, for requesting the first sending node to send the first substream. In the case that the first sending node refuses to send the first substream, the first requesting node will select a suboptimal candidate sending node from the above candidate sending node set as a new first substream providing node.

Specifically, the first request node will select the second candidate sending node in the set of candidate sending nodes as the new first substream providing node, and send a first substream re-request to the second candidate sending node, the first substream The flow re-request is used to request the second candidate sending node to send the first sub-flow, and the first sub-flow re-request includes the remaining bandwidth information of the first requesting node, because the second candidate sending node may receive multiple requesting nodes at the same time The substream re-requests. At this time, the second candidate sending node needs to select one or more requesting nodes to send the substream according to the remaining bandwidth information of the requesting node, so the remaining bandwidth information of the first requesting node is used for the second candidate sending node to determine The first requesting node. Wherein, the above-mentioned second candidate sending node is a candidate sending node whose distribution tree height is smaller than the second threshold and not smaller than the above-mentioned first threshold, and the second threshold is similar to the above-mentioned first threshold, and is not a fixed value. It varies from person to person. Candidate sending nodes whose distribution tree height is suboptimal in the candidate sending node set may be selected by adjusting the second threshold as the final first substream providing node. Similarly, when the first request node sends a second sub-flow request to the second sending node, and the second sending node refuses to send the second sub-flow, the sending of the first sub-flow in the flow distribution tree can be adjusted through the above-mentioned node to adjust the sending node of the second sub-flow in the flow distribution tree.

In a possible implementation manner, after determining that the sending node of the first substream is the first sending node, a first substream request is sent to the first sending node, for requesting the first sending node to send the first substream, The first sending node accepts the first substream request and sends the first substream to the first requesting node. In the case that the transmission of the first sub-stream is interrupted during the process of the first requesting node receiving the first sub-stream, the first requesting node will select the second-best candidate sending node from the above-mentioned set of candidate sending nodes as the new first sub-stream Provide a node.

Specifically, the first request node will select the second candidate sending node in the set of candidate sending nodes as the new first substream providing node, and send a first substream re-request to the second candidate sending node, the first substream The flow re-request is used to request the second candidate sending node to send the first sub-flow, and the first sub-flow re-request includes the remaining bandwidth information of the first requesting node, because the second candidate sending node may receive multiple requesting nodes at the same time The substream re-requests. At this time, the second candidate sending node needs to select one or more requesting nodes to send the substream according to the remaining bandwidth information of the requesting node, so the remaining bandwidth information of the first requesting node is used for the second candidate sending node to determine The first requesting node. Wherein, the above-mentioned second candidate sending node is a candidate sending node whose distribution tree height is less than the second threshold and not less than the above-mentioned first threshold, and the second threshold is similar to the above-mentioned first threshold, and is not a fixed value. It varies from person to person. Candidate sending nodes whose distribution tree height is suboptimal in the set of candidate sending nodes may be screened out by adjusting the second threshold as the final first substream providing node. Similarly, when the transmission of the second sub-stream is interrupted while the first requesting node is receiving the second sub-stream, the stream distribution tree can be adjusted by adjusting the sending node of the first sub-stream in the stream distribution tree as described above The sending node of the second substream in .

In this embodiment of the present application, a suboptimal candidate sending node is selected from the set of candidate sending nodes as a substream sending node through the node's distribution tree height information, and a substream re-request is sent to it to continue to obtain the interrupted substream. Through the above method, the effect of the final selected substream provider node can be optimized, the data transmission pressure on the upstream nodes in the streaming transmission network can be reduced to the greatest extent, and the upstream bandwidth of each node in the mobile distributed streaming network environment can be fully matched. , so that the load of the data sending node is more balanced, and the efficiency of data transmission in the streaming network is greatly improved.

Further, in the above-mentioned case where the transmission of the first sub-stream is interrupted during the process of receiving the first sub-stream by the first requesting node, the first requesting node selects the second-best candidate sending node from the above-mentioned set of candidate sending nodes as the new second sub-stream In addition to a sub-stream providing node, the synchronization group mechanism will also be used to actively pull sub-stream data. The following will take the first sub-stream transmission interruption as an example to provide a possible implementation manner in which the synchronization group mechanism pulls stream data.

Specifically, if the number of interrupted sub-flows is greater than the number of redundant sub-flows, the first requesting node will actively pull the required data blocks in the first sub-flow from the nodes in the synchronization group until the first requesting node relocates to the new The first substream of provides nodes. Wherein, the nodes in the synchronization group are nodes at the same starting position as the first requesting node during the transmission process, that is, the nodes in the synchronization group and the data receiving process of the first requesting node are in a state of synchronization. Similarly, in the case that the transmission of the second sub-stream is interrupted during the process of receiving the second sub-stream by the first requesting node, if the number of interrupted sub-streams is greater than the number of redundant sub-streams, the first requesting node will send a request to the nodes in the synchronization group The required data blocks in the second sub-stream are actively pulled until the first requesting node is relocated to a new second sub-stream providing node.

Please refer to FIG. 6 . FIG. 6 is a schematic diagram of an effect of a synchronization group mechanism provided by an embodiment of the present application. The above-mentioned implementation manner of pulling streaming data by the synchronization group mechanism can be further described in conjunction with FIG. 6 . As shown in Figure 6, take the node m representing the above-mentioned first requesting node as an example for illustration, the synchronization group node set SY _s,m can be used to represent the node at the same initial position as node m in the transmission process of streaming media s , the nodes in the synchronization group node set SY _s,m are in a state of synchronizing with the data receiving process of node m, which means that in the emergency state where the data transmission of node m is interrupted, the nodes in the synchronization group node set SY _s,m can send The node sends a request to actively pull the data blocks required by node m. Specifically, the synchronization group node set SY _s,m may be determined through the synchronization group mechanism, that is, the synchronization block set K _m is used to determine whether other nodes are in a synchronization state with node m. For a node m that newly joins the streaming distribution network, the node m adds all the data blocks in the two consecutive file blocks after the checkpoint in the streaming media s to the synchronization block set K _m , as shown in Figure 6, The checkpoint is data block 5, and all data blocks (data block 6 to data block 15) in the subsequent two consecutive file blocks (second file block and third file block) are added to the synchronization block set K _m . if

Indicates that node n and node m start to receive data almost at the same time, that is, node n and node m are nodes at the same starting position during the transmission of streaming media s, and node n is added to the above synchronization group node set SY _s,m . When node m loses a certain substream, it will select the node x which has the most intersection with its own synchronization block from the above synchronization group node set SY _s,m to send an emergency request. Among them, node x needs to satisfy {x|max{K _m ∩K _x }}, and the emergency request is used to request σ data blocks after the disconnection sub-flow breakpoint. σ is a system parameter, which is not a fixed value, and can be determined according to Different application scenarios vary. While using the synchronization group mechanism to pull stream data, the first requesting node (node m) also needs to find a new provider node of the disconnected sub-stream. After receiving σ data blocks, if the first request node (node m) has not successfully found a new provider node, it will continue to send emergency requests until it is connected to a new sub-stream provider node. After finding a new sub-stream provider After the node, stop the sync group from pulling streaming data. In addition, in order to ensure the real-time and reliability of the synchronization group, each node will periodically detect the nodes in the synchronization group node set SY _s,m , if

Then delete node n from the synchronization group node set SY _s,m ; otherwise, if

Then add node n to the above-mentioned synchronization group node set SY _s,m .

The synchronization group mechanism in the embodiment of this application ensures that disconnected nodes can actively pull urgently needed data blocks from the synchronization group nodes quickly, so that disconnected nodes can spend the time of finding new substream providing nodes more smoothly. The process improves the smoothness of streaming media file transmission.

In a possible implementation manner, after determining that the sending node of the first substream is the first sending node and that the sending node of the second substream is the second sending node, the first substream request is sent to the first sending node, It is used to request the first sending node to send the first substream, and to send the second substream request to the second sending node, and is used to request the second sending node to send the second substream. The first sending node accepts the first substream request and sends the first substream to the first requesting node, and the second sending node accepts the second substream request and sends the second substream to the first requesting node. During the process of receiving the first substream and the second substream at the first requesting node, if the first transmission speed of the first substream is much lower than the second transmission speed of the second substream, that is, the first transmission speed and the second transmission speed If the speed difference is greater than the target threshold, the first requesting node will actively interrupt the transmission of the first sub-flow with the first sending node, and select the suboptimal candidate sending node from the above-mentioned set of candidate sending nodes as the new first sub-flow Provide a node.

Specifically, the difference in sending time of different sub-streams is caused by different performances of devices providing the sub-streams or different network states, and the difference means the difference between the above-mentioned first transmission speed and the second transmission speed. The difference between the above-mentioned first transmission speed and the second transmission speed can be judged by comparing the difference between the data block indexes received by any two sub-flows, that is, the difference between the latest received data block indexes of any two sub-flows receiving a certain flow is too large. When it is large, it means that the transmission progress of the two sub-streams is different, and the entire stream transmission process must be limited to the slowest sub-stream. The specific implementation is that, when the first requesting node receives data blocks of multiple sub-streams within τ time, the first requesting node will compare the data block index values of these sub-streams to obtain the maximum difference α between the index values. If the difference α>ρ*N _s , it means that the transmission speed of the substream that provides data blocks with smaller index values is much slower than other substreams, this substream will affect the performance of the entire stream transmission, and the substream needs to be replaced Provide a node. Among them, τ and ρ are system parameters, which are not fixed values and may vary according to different application scenarios. To sum up, it can be seen that the following conditions must be met to judge that the transmission speed gap between two sub-streams is too large:

This condition indicates that the transmission speed of the i-th sub-flow of the original flow s is much faster than that of the j-th sub-flow, the entire flow transmission process will be limited by the transmission of sub-flow j, and a strategy of adjusting the provider node of sub-flow j is required. Since the transmission of sub-stream j is in the form of streaming, firstly, the first requesting node needs to send an interrupt signal to the providing node of sub-stream j to stop the transmission of sub-stream j, and transfer the providing node of sub-stream j from the candidate sending node set

delete, and re-find the providing node of substream j. Taking the above-mentioned sub-flow j as the above-mentioned first sub-flow as an example for description, the specific implementation method is that the first requesting node will select a set of candidate sending nodes

The second candidate sending node in the network serves as a new first substream providing node, and sends a first substream re-request to the second candidate sending node, and the first substream re-request is used to request the second candidate sending node to send the first substream re-request. A sub-flow, the first sub-flow re-request contains the remaining bandwidth information of the first requesting node, because the second candidate sending node may receive sub-flow re-requests from multiple requesting nodes at the same time, at this time the second candidate sending node needs According to the remaining bandwidth information of the requesting node, one or more requesting nodes are preferentially selected to send the substream, so the remaining bandwidth information of the first requesting node is used by the second candidate sending node to determine the first requesting node. Wherein, the second candidate sending node is a candidate sending node whose distribution tree height is smaller than the second threshold and not smaller than the first threshold. The above-mentioned target threshold and the second threshold are similar to the above-mentioned first threshold, and are not a fixed value, and may be different according to different application scenarios. Candidate sending nodes whose distribution tree height is suboptimal in the set of candidate sending nodes may be screened out by adjusting the second threshold as the final first substream providing node. Similarly, when the first requesting node receives the first sub-stream and the second sub-stream, if the second transmission rate of the second sub-stream is much lower than the first transmission rate of the first sub-stream, the stream distribution can be adjusted through the above The sending node of the first sub-stream in the tree is used to adjust the sending node of the second sub-stream in the stream distribution tree.

Please refer to FIG. 7 . FIG. 7 is a schematic diagram of an effect of adjusting a streaming transmission node provided by an embodiment of the present application. A possible implementation manner of the foregoing adjustment substream sending node may be further described with reference to FIG. 7 . As shown in Figure 7, the first requesting node receives five sub-flows (the first sub-flow A, the second sub-flow B, the third sub-flow C, the fourth sub-flow D, and the fifth sub-flow E) within τ time By comparing these data block index values, it can be obtained that the difference between the data block index of the fifth sub-stream E and the data block indexes of the other four sub-streams is large, and the data block index of the fifth sub-stream E is more Small. It means that the transmission speed of the fifth sub-stream E is much slower than that of the other four sub-streams, the fifth sub-stream E will affect the transmission performance of the entire stream, and the providing node of the fifth sub-stream E needs to be replaced. According to the foregoing manner of adjusting the sending node of the first substream in the stream distribution tree, the sending node of the fifth substream E in the stream distribution tree is adjusted. After the adjustment, it can be seen that the first requesting node receives five sub-flows (the first sub-flow A, the second sub-flow B, the third sub-flow C, the fourth sub-flow D, and the sixth sub-flow F) within τ time The difference between the index values of the data blocks is small, and the difference in transmission speed is also small. Here, in order to indicate that the provision node of the fifth sub-stream E has been adjusted, the original fifth sub-stream E is represented by the sixth sub-stream F.

In the embodiment of the present application, the requesting node actively interrupts the transmission of the substream whose transmission speed is too slow, and selects a suboptimal candidate sending node from the candidate sending node set as the new substream sending node through the distribution tree height information of the node, and Send a substream re-request to it to continue to obtain substreams to be received. Through the above method, the effect of the finally selected sub-stream providing node can be optimized, the transmission speed of the sub-stream in the streaming transmission network can be improved to the greatest extent, and the transmission efficiency can be greatly improved.

Further, when the above-mentioned first sending node refuses to send the first sub-stream, or the transmission of the first sub-stream is interrupted during the process of receiving the first sub-stream, or the first requesting node actively interrupts the first sub-stream with the first sending node In the case of stream transmission, deleting the first candidate sending node from the set of candidate sending nodes can improve the accuracy and stream transmission efficiency of the first requesting node in locating the sub-stream providing node during subsequent stream transmission.

After step 302, the first requesting node decodes the first substream and the second substream to obtain the original stream.

After receiving the first substream and the second substream through the above step 302, the first requesting node decodes the first substream and the second substream to obtain the original stream. In this embodiment of the present application, by dividing the original stream into the first sub-stream and the second sub-stream, and then splitting the entire mobile distributed stream transmission process into the first sub-stream and the second sub-stream transmission process, the entire transmission network is improved. transmission efficiency.

Please refer to FIG. 8. FIG. 8 is a schematic flowchart of another data transmission method provided by the embodiment of the present application. The method includes but is not limited to the following steps:

Step 801: Receive a first substream request sent by a first requesting node or a second substream request sent by a second requesting node.

In this embodiment of the present application, the first sending node receives the first substream request sent by the first request node and the second substream request sent by the second request node. The first sending node is a node that provides the first substream or the second substream, and the first requesting node is different from the second requesting node. The first substream request is used to request the first sending node to send the first substream, and the second request node is used to request the first sending node to send the second substream. Wherein, the first subflow request sent by the first requesting node includes remaining bandwidth information of the first requesting node, and the second subflow request sent by the second requesting node includes remaining bandwidth information of the second requesting node. Because the sending node may receive sub-stream requests from multiple requesting nodes at the same time, the sending node needs to select one or more requesting nodes to send sub-streams according to the remaining bandwidth information of the requesting node, so the remaining bandwidth information of the first requesting node and the remaining bandwidth information of the second requesting node are used by the first sending node to determine the first requesting node or the second requesting node, so that the load of the data sending node is more balanced, and the data transmission efficiency is improved.

In a possible implementation manner, the first substream and the second substream are obtained by dividing the original stream, and the first substream and the second substream are not completely the same. The embodiment of the present application will provide a possible implementation manner of dividing sub-streams, and its specific implementation process has been specifically described in the above step 301, and will not be repeated here.

In a possible implementation manner, on the premise that the original stream is divided to obtain the first sub-stream and the second sub-stream, redundant coding may also be performed on the first sub-stream and the second sub-stream, so as to improve the efficiency of sub-stream transmission. reliability and stability. The embodiment of the present application will provide a possible implementation manner of substream redundancy coding, and its specific implementation process has been described in the above step 301, and will not be repeated here.

In a possible implementation manner, before the first requesting node sends the first substream request to the first sending node and before the second requesting node sends the second substream request to the first sending node, the first sending node The distribution tree height information of the first sending node will be sent to the first requesting node and the second requesting node. There may be multiple potential sending nodes owning the first substream in the streaming network. The first requesting node and the second requesting node need to select a sending node according to the distribution tree height information of the potential sending nodes, and send the first The substream requests the transmission of the first substream, and sends the second substream request thereto for the transmission of the second substream. Therefore, the distribution tree height information of the first sending node is used by the first requesting node to determine to send the first sub-stream request to the first sending node, and is used by the second requesting node to send the second sub-stream request to the first sending node, The load of the data sending node is more balanced, and the efficiency of data transmission is improved.

Step 802: Send the first subflow to the first requesting node or send the second subflow to the second requesting node.

This step provides a possible implementation manner in which the first sending node sends the substream. The first sending node will send the first substream to the first requesting node or send the second substream to the second requesting node according to the substream transmission information and the node transmission status.

Specifically, when the first sending node provides the first sub-stream and the remaining bandwidth is higher than the bit rate of the first sub-stream, the first sub-stream is sent to the first requesting node; the second sub-stream is provided at the first sending node And when the remaining bandwidth is higher than the bit rate of the second sub-stream, send the second sub-stream to the second request node; provide the first sub-stream and the second sub-stream at the first sending node, and the remaining bandwidth is higher than the first sub-stream In the case of bit rates of the sub-stream and the second sub-stream, the first sub-stream is sent to the first requesting node, and the second sub-stream is sent to the second requesting node.

Further, when the first sending node provides the first sub-stream and the second sub-stream, and the remaining bandwidth is higher than the bit rate of the first sub-stream and the second sub-stream, the first sending node will compare the first requesting node The remaining bandwidth with the second requesting node. If the remaining bandwidth of the first requesting node is greater than the remaining bandwidth of the second requesting node, first send the first substream to the first requesting node; then update the remaining bandwidth of the first sending node; the remaining bandwidth after the update of the first sending node is high In the case of the bit rate of the second sub-stream, the second sub-stream is then sent to the second requesting node. Similarly, if the remaining bandwidth of the second requesting node is greater than the remaining bandwidth of the first requesting node, first send the second substream to the second requesting node; then update the remaining bandwidth of the first sending node; after the update of the first sending node When the remaining bandwidth is higher than the bit rate of the first sub-stream, the first sub-stream is sent to the first requesting node.

In this embodiment of the present application, combined with the remaining bandwidth information of the first sending node and the sub-stream data it owns, the preferred sub-stream is sent to the requesting node, and, combined with the remaining bandwidth information of each requesting node, the preferred option has a higher residual bandwidth The request node sends its requested sub-stream, which can maximize the bandwidth utilization, fully match the uplink bandwidth of each node in the mobile distributed stream transmission network environment, make the load of the data sending node more balanced, and make the entire stream transmission The transmission efficiency of the network is higher.

Please refer to FIG. 9 . FIG. 9 is an interactive schematic diagram of a stream transmission network provided by an embodiment of the present application, and can also be understood as a supplement to the flow charts of the data transmission methods in FIGS. 3 and 8 above.

As shown in FIG. 9 , taking the stream transmission network composed of the first requesting node, the first sending node, the second sending node, and the second requesting node as an example, the data transmission methods in the above-mentioned FIG. 3 and FIG. 8 are supplemented.

In the embodiment of the present application, firstly, the source node processes the original streaming media file, including dividing sub-streams, redundant encoding, and the like. By dividing the original stream into multiple sub-streams, and then splitting the entire mobile distributed stream transmission process into multiple sub-stream transmission processes, the transmission efficiency of the entire transmission network can be improved. Moreover, by redundantly encoding the file blocks, redundant data blocks are added to the file blocks, thereby achieving the purpose of substream redundant encoding. The newly added redundant data blocks can get the corresponding redundant sub-streams, so that even if there are several sub-streams that are disconnected during the stream transmission process, as long as the dropped sub-streams do not exceed the redundant sub-streams, the The received sub-stream is decoded to obtain the original stream, which can improve the reliability and stability of sub-stream transmission. Afterwards, the source node publishes metadata about the original flow to the streaming network, the metadata includes the division of sub-streams, but does not include specific flow data.

Each requesting node in the streaming network (such as the first requesting node and the second requesting node in the embodiment of the present application) decides whether to subscribe to the stream after receiving the metadata published by the source node in the streaming network. Determine the sending node that can provide the sub-stream through the metadata, and initiate a request for the sub-stream to the sending node. For example, the first requesting node sends substream positioning to the first sending node, the second sending node, and the second requesting node respectively in the stream transmission network, and determines the sending node that can provide the first substream and the second substream. The sending node of the stream; the second requesting node sends substream positioning to the first sending node, the second sending node, and the first requesting node respectively in the streaming network, and determines the sending node that can provide the first substream and the The sending node of the second substream. In this way, the accuracy and efficiency of sub-stream positioning can be improved to the greatest extent, thereby improving the transmission efficiency of the overall stream transmission network.

After substream positioning, the first requesting node and the second requesting node determine that the first sending node can provide the first substream, and the second sending node can provide the second substream. The first request node sends a first substream request to the first sending node, requests the first sending node to send the first substream, and sends a second substream request to the second sending node, requests the second sending node to send the second substream . Similarly, the second requesting node sends a first sub-stream request to the first sending node, requests the first sending node to send the first sub-stream, and sends a second sub-stream request to the second sending node, requests the second sending node to send the first sub-stream Two sons flow.

After the first sending node receives the first sub-stream request sent by the first requesting node and the first sub-stream request sent by the second requesting node, in response to the request, it sends the first sub-stream to the first requesting node and the second sub-stream to the second requesting node respectively. The requesting node sends the first sub-flow. Specifically, here the first sending node will compare the remaining bandwidth of the first requesting node and the second requesting node, if the remaining bandwidth of the first requesting node is greater than the remaining bandwidth of the second requesting node, the first sending node will give priority to the first requesting node The requesting node sends the first sub-stream; then updates the remaining bandwidth of the first sending node; when the updated remaining bandwidth of the first sending node is higher than the bit rate of the first sub-stream, then sends the first sub-stream to the second requesting node Substream. Similarly, after the second sending node receives the second substream request sent by the first requesting node and the second substreaming request sent by the second requesting node, it responds to the request by comparing the The remaining bandwidth is selected to send the second sub-flow to the first requesting node and send the second sub-flow to the second requesting node respectively. In this way, the bandwidth utilization rate can be improved to the greatest extent, and the uplink bandwidth of each node in the mobile distributed streaming network environment can be fully matched, so that the load of the data sending node is more balanced, and the transmission efficiency of the entire streaming transmission network is higher.

It should be noted that in the process of streaming, the problem of frequently exiting or joining nodes occurs from time to time. In the embodiment of this application, when the first sending node goes offline due to node performance or network status, etc., it and The transmission of the first substream between the first requesting node and the second requesting node is interrupted. At this time, the first requesting node and the second requesting node can use the synchronization group mechanism to actively pull the data blocks required by the first substream from the synchronization group node until the first requesting node and the second requesting node relocate to the new A substream provides nodes. The synchronization group mechanism in the embodiment of this application ensures that disconnected nodes can actively pull urgently needed data blocks from the synchronization group nodes quickly, so that disconnected nodes can spend the time of finding new substream providing nodes more smoothly. The process improves the smoothness and efficiency of streaming media file transmission.

After receiving the first substream and the second substream, the first requesting node and the second requesting node decode the first substream and the second substream to obtain the original stream. In this embodiment of the present application, by dividing the original stream into the first sub-stream and the second sub-stream, and then splitting the entire mobile distributed stream transmission process into the first sub-stream and the second sub-stream transmission process, it can largely Reduce the data transmission pressure on a single node in the stream transmission network, make the load of the data sending node more balanced, fully match the uplink bandwidth of each node in the mobile distributed stream transmission network environment, and make the entire stream transmission network indestructible and transmission efficient higher.

The method of the embodiment of the present application has been described in detail above, and the device of the embodiment of the present application is provided below.

Please refer to Figure 10, Figure 10 is a schematic structural diagram of a data transmission device provided in the embodiment of the present application, the data transmission device 100 may include a sending unit 1001 and a receiving unit 1002, wherein the description of each unit is as follows:

a sending unit 1001, configured to send a first request to a first sending node;

a receiving unit 1002, configured to receive the first substream sent by the first sending node in response to the first request;

The sending unit 1001 is further configured to send a second request to a second sending node;

The receiving unit 1002 is further configured to receive a second substream sent by the second sending node in response to the second request; the first sending node is different from the second sending node; the first substream Both the stream and the second sub-stream are composed of data blocks in the original stream, and the first sub-stream is different from the second sub-stream.

In a possible implementation manner, the device also includes:

The decoding unit 1003 is configured to decode the first substream and the second substream to obtain the original stream.

In a possible implementation manner, the original stream includes a first file block and a second file block, and the first sub-stream includes at least one data block in the first file block and the second file block At least one data block in the second substream includes at least one data block in the first file block and at least one data block in the second file block.

In a possible implementation manner, the data blocks in the first file block are data blocks in the original stream, or data blocks obtained by redundantly encoding the first file block; the second file The data blocks in the blocks are the data blocks in the original stream, or the data blocks obtained by redundantly encoding the second file blocks.

In a possible implementation manner, the device also includes:

The receiving unit 1002 is configured to acquire metadata of the original stream, where the metadata is used to determine the data blocks included in the first sub-stream;

The determining unit 1004 is configured to determine the first sending node based on the metadata.

In a possible implementation manner, the determining unit 1004 is specifically configured to determine a set of candidate sending nodes based on the metadata; the set of candidate sending nodes includes candidate sending nodes owning the first substream;

The determining unit 1004 is further configured to determine a first candidate sending node in the set of candidate sending nodes as the first sending node; the first candidate sending node is a candidate whose distribution tree height is smaller than a first threshold sending node.

In a possible implementation manner, the receiving unit 1002 is further configured to receive the distribution tree height information sent by the first sending node, and the distribution tree height information of the first sending node is used by the data transmission device Determine the first sending node.

In a possible implementation manner, the determining unit 1004 is further configured to, in the case that the heights of the distribution trees of two or more candidate sending nodes are the same and less than the first threshold, select the one with the highest remaining bandwidth The candidate sending node is determined as the first sending node.

In a possible implementation manner, the device also includes:

A query unit 1005, configured to query a neighbor node or a network node based on the metadata; the neighbor node is a node whose transmission frequency with the first requesting node exceeds a frequency threshold;

The determining unit 1004 is further configured to add the neighbor node owning the first subflow to the candidate sending node set, and add the network node owning the first subflow to the candidate sending node gather.

In a possible implementation manner, the sending unit 1001 is further configured to, when the response of the first sending node to the first request does not meet the preset condition, send The second candidate sending node sends a third request; the second candidate sending node is a candidate sending node whose distribution tree height is less than the second threshold and not less than the first threshold, and the third request is used to request the first The second candidate sending node sends the first substream.

In a possible implementation manner, the sending unit 1001 is specifically configured to, when the first sending node does not send the first substream within a preset time, send the second candidate sending node sending said third request; or,

The sending unit 1001 is specifically further configured to send the third request to the second candidate sending node when the transmission of the first substream is interrupted during the process of receiving the first substream; or,

The sending unit 1001 is further configured to, in the process of receiving the first sub-stream, if the first transmission speed of the first sub-stream is lower than a preset threshold, send to the second candidate sending node said third request; or,

The sending unit 1001 is specifically further configured to, during the process of receiving the first substream and the second substream, the first transmission speed of the first substream and the second transmission speed of the second substream When the difference in transmission speed is greater than the target threshold and the first transmission speed is lower than the second transmission speed, sending the third request to the second candidate sending node.

In a possible implementation manner, the device also includes:

Pulling unit 1006, configured to pull the required data blocks in the first sub-stream from the nodes in the synchronization group when the number of sub-stream interruptions is greater than the number of redundant sub-streams; The node is a node at the same starting position as the first requesting node during the transmission process.

In a possible implementation manner, the third request includes remaining bandwidth information of the first requesting node, and the remaining bandwidth information of the first requesting node is used by the second candidate sending node to determine the first request node.

In a possible implementation manner, the device also includes:

A deleting unit 1007, configured to delete the first candidate sending node from the set of candidate sending nodes.

According to the embodiment of the present application, each unit in the device shown in Fig. 10 can be respectively or all combined into one or several other units to form, or one (some) units can be further divided into functionally more It is composed of multiple small units, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of one unit may also be realized by multiple units, or the functions of multiple units may be realized by one unit. In other embodiments of the present application, the network-based device may also include other units. In practical applications, these functions may also be assisted by other units, and may be implemented cooperatively by multiple units.

It should be noted that, for the implementation of each unit, reference may also be made to the corresponding description of the method embodiment shown in FIG. 3 above.

Regarding the technical effect brought about by any possible implementation in the embodiments of the present application, reference may be made to the introduction corresponding to the first aspect in the summary of the invention and the technical effect of the corresponding implementation.

In the data transmission device 100 described in FIG. 10, the process of splitting the entire mobile distributed streaming transmission process into multiple sub-stream distribution tree model transmissions can greatly reduce the data transmission pressure on a single node in the streaming transmission network. , so that the load of the data sending node is more balanced, and fully matches the uplink bandwidth of each node in the mobile distributed streaming network environment, so that the indestructibility and transmission efficiency of the entire streaming network are higher.

Please refer to FIG. 11. FIG. 11 is a schematic structural diagram of a data transmission device provided by an embodiment of the present application. The data transmission device 110 may include a receiving unit 1101 and a sending unit 1102, where each unit is described as follows:

The receiving unit 1101 is configured to receive a first request sent by a first requesting node or a second request sent by a second requesting node; the first request is used to request to send a first substream to the first requesting node, the The second request is used to request to send a second sub-flow to the second requesting node; the first requesting node is different from the second requesting node; both the first sub-flow and the second sub-flow are created by the original consisting of data blocks in a stream, the first sub-stream being different from the second sub-stream;

A sending unit 1102, configured to send the first subflow to the first requesting node or send the second subflow to the second requesting node.

In a possible implementation manner, the sending unit 1102 is further configured to send the distribution tree height information of the data transmission device to the first request node, and the distribution tree height information of the data transmission device is used for the The first requesting node determines whether to send the first request to the data transmission device.

In a possible implementation manner, the sending unit 1102 is specifically configured to provide the first substream to the data transmission device and the remaining bandwidth of the data transmission device is higher than the bits of the first substream rate, sending the first sub-stream to the first requesting node; or,

The sending unit 1102 is specifically further configured to send the second substream to the The second requesting node sends the second sub-stream; or,

The sending unit 1102 is further configured to provide the first sub-stream and the second sub-stream to the data transmission device, and the remaining bandwidth of the data transmission device is higher than the bits of the first sub-stream rate and the bit rate of the second sub-stream, sending the first sub-stream to the first requesting node, and sending the second sub-stream to the second requesting node.

In a possible implementation manner, the device also includes:

The sending unit 1102 is specifically further configured to send the first substream to the first requesting node when the remaining bandwidth of the first requesting node is greater than the remaining bandwidth of the second requesting node;

an updating unit 1103, configured to update the remaining bandwidth of the data transmission device;

The sending unit 1102 is specifically further configured to send the second substream to the second requesting node when the updated remaining bandwidth of the data transmission device is higher than the bit rate of the second substream .

According to the embodiment of the present application, each unit in the device shown in Fig. 11 can be respectively or all combined into one or several other units to form, or one (some) units can be further divided into functionally more It is composed of multiple small units, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of one unit may also be realized by multiple units, or the functions of multiple units may be realized by one unit. In other embodiments of the present application, the network-based device may also include other units. In practical applications, these functions may also be assisted by other units, and may be implemented cooperatively by multiple units.

It should be noted that, for the implementation of each unit, reference may also be made to the corresponding description of the method embodiment shown in FIG. 8 above.

Regarding the technical effect brought about by any possible implementation in the embodiments of the present application, reference may be made to the introduction corresponding to the second aspect in the summary of the invention and the technical effect of the corresponding implementation.

In the data transmission device 110 described in FIG. 11 , the process of splitting the entire mobile distributed streaming transmission process into multiple sub-stream distribution tree model transmissions can greatly reduce the data transmission pressure on a single node in the streaming transmission network , so that the load of the data sending node is more balanced, and fully matches the uplink bandwidth of each node in the mobile distributed streaming network environment, so that the indestructibility and transmission efficiency of the entire streaming network are higher.

Please refer to FIG. 12 . FIG. 12 is a schematic structural diagram of an electronic device 120 provided by an embodiment of the present application. The electronic device 120 may include a memory 1201 and a processor 1202 . Further optionally, a communication interface 1203 and a bus 1204 may also be included, wherein the memory 1201 , the processor 1202 and the communication interface 1203 are connected to each other through the bus 1204 . The communication interface 1203 is used for data interaction with the above-mentioned data transmission device 100 or the data transmission device 110 .

Wherein, the memory 1201 is used to provide a storage space, in which data such as operating systems and computer programs can be stored. Memory 1201 includes, but is not limited to, random access memory (random access memory, RAM), read-only memory (read-only memory, ROM), erasable programmable read-only memory (erasable programmable read only memory, EPROM), or Portable read-only memory (compact disc read-only memory, CD-ROM).

The processor 1202 is a module for performing arithmetic operations and logic operations, and may be in a processing module such as a central processing unit (central processing unit, CPU), a graphics processing unit (graphics processing unit, GPU) or a microprocessor (microprocessor unit, MPU). one or a combination of more.

A computer program is stored in the memory 1201, and the processor 1202 calls the computer program stored in the memory 1201 to execute the data transmission method shown in FIG. 3 above:

Sending a first substream request to the first sending node; the first substream request is used to request the first sending node to send a first substream, where the first substream includes at least one data block in the original stream;

Sending a second substream request to a second sending node; the second substream request is used to request the second sending node to send a second substream, the second substream including at least one data in the original stream blocks; the first sending node is different from the second sending node, and the data blocks in the first substream are not exactly the same as the data blocks in the second substream;

The first substream and the second substream are received.

For the specific content of the method executed by the processor 1202, reference may be made to the above-mentioned FIG. 3 , which will not be repeated here.

Correspondingly, the processor 1202 calls the computer program stored in the memory 1201, which can also be used to execute the method steps performed by the various units in the data transmission device 100 shown in FIG. I won't repeat them here.

On the other hand, a computer program is stored in the memory 1201, and the processor 1202 calls the computer program stored in the memory 1201 to execute the data transmission method shown in FIG. 8 above:

receiving a first substream request sent by a first requesting node or a second substream request sent by a second requesting node; the first substream request is used to request to send a first substream to the first requesting node, the The second substream request is used to request to send a second substream to the second requesting node; the first substream includes at least one data block in the original stream, and the second substream includes at least one data block in the original stream at least one data block, the data block in the first substream is not identical to the data block in the second substream;

For the specific content of the method executed by the processor 1202, reference may be made to the above-mentioned FIG. 8 , which will not be repeated here.

Correspondingly, the processor 1202 invokes the computer program stored in the memory 1201, which can also be used to execute the method steps performed by each unit in the data transmission device 110 shown in FIG. I won't repeat them here.

In the electronic device 120 described in FIG. 12, the process of splitting the entire mobile distributed streaming transmission process into multiple sub-stream distribution tree model transmissions can greatly reduce the data transmission pressure on a single node in the streaming transmission network. Make the load of the data sending node more balanced, fully match the uplink bandwidth of each node in the mobile distributed streaming network environment, and make the entire streaming network more invulnerable and transmission efficient.

The embodiment of the present application also provides a computer-readable storage medium. The above-mentioned computer-readable storage medium stores a computer program. When the above-mentioned computer program is run on one or more processors, the above-mentioned FIG. 3 and FIG. 8 can be implemented. method shown.

An embodiment of the present application further provides a computer program product, which can implement the methods shown in FIG. 3 and FIG. 8 above when the computer program product is run on a processor.

The embodiment of the present application also provides a chip, the chip includes a processor and a communication interface, the processor is used to call and run instructions from the communication interface, when the processor executes the instructions, the above-mentioned Figure 3 and Figure 3 can be implemented. 8 shows the method.

The embodiment of the present application also provides a data transmission system, which includes at least one data transmission device 100 or data transmission device 110 or electronic device 120 or chip as described above.

To sum up, the process of splitting the entire mobile distributed streaming transmission process into multiple sub-stream distribution tree models can greatly reduce the data transmission pressure on a single node in the streaming transmission network and make the load on the data sending node more efficient. Balanced, fully matching the uplink bandwidth of each node in the mobile distributed streaming network environment, making the entire streaming network more robust and efficient.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be realized. The processes can be completed by hardware related to computer programs, and the computer programs can be stored in computer-readable storage media. When the computer programs are executed, , may include the processes of the foregoing method embodiments. The aforementioned storage medium includes: various media capable of storing computer program codes such as read-only memory ROM or random access memory RAM, magnetic disk or optical disk.

Claims

A data transmission method, characterized in that, comprising:

sending a first request to a first sending node;

receiving the first substream sent by the first sending node in response to the first request;

sending a second request to a second sending node;

receiving the second substream sent by the second sending node in response to the second request; the first sending node is different from the second sending node; the first substream and the second substream are both Consisting of chunks of data in an original stream, said first substream is different from said second substream.
The method according to claim 1, further comprising:

Decoding the first substream and the second substream to obtain the original stream.
The method according to claim 1 or 2, wherein the original stream includes a first file block and a second file block, and both the first sub-stream and the second sub-stream include the first file block and the data blocks in the second file block.
The method according to any one of claims 1 to 3, wherein the first substream includes a data block obtained by redundantly encoding the first file block, or a data block obtained by performing redundant encoding on the second file block A data block obtained by performing redundant encoding; the second substream includes a data block obtained by performing redundant encoding on the first file block, or a data block obtained by performing redundant encoding on the second file block.
The method according to any one of claims 1 to 4, wherein both the first request and the second request include remaining bandwidth information of the first requesting node; the requesting node for the first request and the second request; the remaining bandwidth information of the first requesting node is used by the first sending node to determine whether to send the first sub-stream, and for the second sending The node determines whether to send the second sub-flow.
The method according to any one of claims 1 to 5, wherein before sending the first request to the first sending node, the method further comprises:

obtaining metadata of the original stream;

determining the first substream based on the metadata;

Based on the metadata, the first sending node is determined.
The method according to claim 6, wherein the determining the first sending node based on the metadata comprises:

Based on the metadata, determine a set of candidate sending nodes, where the set of candidate sending nodes includes candidate sending nodes owning the first substream;

Determining a first candidate sending node in the set of candidate sending nodes as the first sending node, where the first candidate sending node is a candidate sending node whose distribution tree height is smaller than a first threshold.
The method according to claim 7, wherein the method further comprises:

In the case that the first substream sent by the first sending node in response to the first request is abnormal, sending a third request to a second candidate sending node in the set of candidate sending nodes; the second The candidate sending node is a candidate sending node whose distribution tree height is smaller than the second threshold and not smaller than the first threshold, and the third request is used to request the second candidate sending node to send the first substream.
The method according to claim 8, wherein when receiving the first sub-stream sent by the first sending node in response to the first request is abnormal, sending the information to the set of candidate sending nodes The second candidate sending node sends a third request, including:

If the first sending node has not sent the first substream within a preset time, sending the third request to the second candidate sending node; or,

If the transmission of the first substream is interrupted during the process of receiving the first substream, sending the third request to the second candidate sending node; or,

In the process of receiving the first substream, if the first transmission speed of the first substream is less than a preset threshold, send the third request to the second candidate sending node; or,

During the process of receiving the first substream and the second substream, the difference between the first transmission speed of the first substream and the second transmission speed of the second substream is greater than a target threshold, and When the first transmission speed is lower than the second transmission speed, sending the third request to the second candidate sending node.
A data transmission method, characterized in that, comprising:

Receive a first request sent by a first requesting node or a second request sent by a second requesting node; the first request is used to request sending the first substream to the first requesting node, and the second request is used to request sending a second substream to the second requesting node; the first requesting node is different from the second requesting node; both the first substream and the second substream are composed of data blocks in the original stream , the first substream is different from the second substream;

Sending the first subflow to the first requesting node or sending the second subflow to the second requesting node.
The method according to claim 10, wherein the original stream includes a first file block and a second file block, and the first sub-stream and the second sub-stream both include the first file block and the second file block. A data block in the second file block.
The method according to claim 10 or 11, wherein the first substream includes a data block obtained by performing redundant encoding on the first file block, or performing redundant encoding on the second file block Obtained data blocks; the second substream includes data blocks obtained by performing redundant encoding on the first file block, or data blocks obtained by performing redundant encoding on the second file block.
The method according to any one of claims 10 to 12, wherein before receiving the first request sent by the first requesting node, the method further comprises:

sending the distribution tree height information of the first sending node to the first requesting node, where the distribution tree height information of the first sending node is used by the first requesting node to determine whether to send the first sending node to the first sending node On request, the first sending node is a sending node sending the first sub-stream or the second sub-stream.
A data transmission device, characterized in that it comprises:

a sending unit, configured to send a first request to a first sending node;

a receiving unit, configured to receive the first substream sent by the first sending node in response to the first request;

The sending unit is further configured to send a second request to a second sending node;

The receiving unit is further configured to receive a second substream sent by the second sending node in response to the second request; the first sending node is different from the second sending node; the first substream Both of the second substreams are composed of data blocks in the original stream, and the first substream is different from the second substream.
The device according to claim 14, wherein the original stream includes a first file block and a second file block, and the first sub-stream and the second sub-stream both include the first file block and the second file block. A data block in the second file block.
The device according to claim 14 or 15, wherein the first substream includes a data block obtained by performing redundant encoding on the first file block, or performing redundant encoding on the second file block Obtained data blocks; the second substream includes data blocks obtained by performing redundant encoding on the first file block, or data blocks obtained by performing redundant encoding on the second file block.
The device according to any one of claims 14 to 16, wherein the device further comprises:

The receiving unit is further configured to obtain metadata of the original stream;

a determining unit, configured to determine the first sub-stream based on the metadata;

The determining unit is further configured to determine the first sending node based on the metadata.
The device according to claim 17, wherein the determining unit is specifically configured to determine a set of candidate sending nodes based on the metadata, and the set of candidate sending nodes includes candidate sending nodes owning the first substream. node;

The determining unit is specifically further configured to determine a first candidate sending node in the set of candidate sending nodes as the first sending node, and the first candidate sending node is a sending candidate whose distribution tree height is smaller than a first threshold node.
The device according to claim 18, wherein the sending unit is further configured to send an A second candidate sending node in the set of candidate sending nodes sends a third request; the second candidate sending node is a candidate sending node whose distribution tree height is less than the second threshold and not less than the first threshold, and the third request It is used to request the second candidate sending node to send the first substream.
The device according to claim 19, wherein the sending unit is further configured to, when the first sending node does not send the first substream within a preset time, send the The second candidate sending node sends the third request; or,

The sending unit is specifically further configured to send the third request to the second candidate sending node when the transmission of the first substream is interrupted during the process of receiving the first substream; or,

The sending unit is further configured to send the second candidate sending node to the second candidate sending node when the first transmission speed of the first substream is lower than a preset threshold during the process of receiving the first substream. the third request; or,

The sending unit is further configured to, during the process of receiving the first substream and the second substream, the first transmission speed of the first substream and the second transmission speed of the second substream When the speed difference is greater than the target threshold and the first transmission speed is smaller than the second transmission speed, sending the third request to the second candidate sending node.
A data transmission device, characterized in that it comprises:

A receiving unit, configured to receive a first request sent by a first requesting node or a second request sent by a second requesting node; the first request is used to request to send a first substream to the first requesting node, and the first requesting node The second request is used to request to send a second substream to the second requesting node; the first requesting node is different from the second requesting node; both the first substream and the second substream are composed of the original stream Composed of data blocks in , the first sub-stream is different from the second sub-stream;

A sending unit, configured to send the first substream to the first requesting node or send the second substream to the second requesting node.
The device according to claim 21, wherein the original stream includes a first file block and a second file block, and the first sub-stream and the second sub-stream both include the first file block and the second file block. A data block in the second file block.
The device according to claim 21 or 22, wherein the first substream includes a data block obtained by performing redundant encoding on the first file block, or performing redundant encoding on the second file block Obtained data blocks; the second substream includes data blocks obtained by performing redundant encoding on the first file block, or data blocks obtained by performing redundant encoding on the second file block.
A data transmission system, characterized by comprising the data transmission device according to any one of claims 14 to 20, or the data transmission device according to any one of claims 21 to 23.