A Video Stream Transmission Control Method and Control System

Abstract

The present invention provides a video stream transmission control method and control system, belonging to the technical field of video transmission. By receiving a video stream request sent by a client to a central scheduler, obtaining its push stream record based on the identifier of the target video stream device, introducing a preset metric to configure a time window for each edge node to which the stream is pushed, and quantitatively evaluating the push stream quality of the edge node within this time window, it is possible to grasp the push stream status of each edge node in real time. In the node selection phase, according to the evaluation results, the edge node with the optimal push stream quality is selected as the target edge node, and this information is sent to the client. Subsequently, the client establishes a connection through the selected target edge node and pulls the video stream. The present invention effectively improves the stability and reliability of video stream transmission by monitoring and evaluating the push stream quality of edge nodes in real time and selecting the optimal node for video stream distribution based on the evaluation results.

Description

Technical Field

[0001] The present invention relates to the technical field of video transmission, and particularly to a video stream transmission control method and control system. Background Art

[0002] With the rapid development of Internet technology, video stream transmission has become an indispensable part of people's daily lives and is widely used in multiple fields such as online education, remote work, and entertainment live streaming. However, there are many challenges in the process of video stream transmission, such as network latency, bandwidth fluctuations, packet loss, etc., which directly affect the user's viewing experience. Especially in the scenario of large-scale video distribution, how to ensure the efficient and stable transmission of video streams has become a technical problem to be solved urgently.

[0003] In the prior art, video stream transmission usually adopts a method combining a central scheduler and edge nodes. The central scheduler is responsible for receiving video stream requests from clients and distributing the requests to appropriate edge nodes according to certain strategies, and the edge nodes provide video stream services to the clients. However, this method is unable to cope with the dynamic changes of the network and often fails to ensure the transmission quality of video streams.

[0004] Specifically, traditional methods usually ignore the real-time monitoring and evaluation of the video pushing quality of edge nodes, resulting in the situation that clients may receive video streams with poor quality when the network conditions are not good. In addition, due to the lack of an effective node selection mechanism, the central scheduler often fails to accurately determine which edge node can provide better video pushing quality when distributing requests, thus affecting the overall effect of video stream transmission.

[0005] Therefore, it is necessary to provide a video stream transmission control method and control system to solve the above technical problems. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides a video stream transmission control method and control system, which effectively improves the stability and reliability of video stream transmission by real-time monitoring and evaluating the video pushing quality of edge nodes and selecting the optimal node for video stream distribution based on the evaluation results.

[0007] The present invention provides a video stream transmission control method, and the control method includes the following steps:

[0008] Receiving a video stream request sent by a client to a central scheduler, where the video stream request includes an identifier of a target video stream device;

[0009] Obtaining the video pushing record of the target video stream device according to the identifier, where the video pushing record includes the edge node to which the video is pushed and the corresponding video pushing quality data;

[0010] Configure a time window for each edge node to which the video stream is pushed, and evaluate the video stream pushing quality of each edge node to which the video stream is pushed according to the configured time window. Among them, the preset metric is the performance stability value, and the video stream pushing quality is quantified by the statistic within the time window;

[0011] Select the edge node with the optimal video stream pushing quality as the target edge node;

[0012] Send the selected target edge node to the client, and the client establishes a connection through the selected target edge node and pulls the video stream pushed by the target video stream device.

[0013] Preferably, the control method further includes:

[0014] If the target video stream device has no video stream pushing record, select an edge node as the target edge node by using the default policy.

[0015] Preferably, the default policy is to select the target edge node based on at least one of the addition time, current load or geographical location of the edge node.

[0016] Preferably, the obtaining the video stream pushing record of the target video stream device according to the identifier includes the following steps:

[0017] Analyze the video stream request sent by the client, and extract the identifier of the target video stream device from it;

[0018] Use the identifier as the query keyword to initiate a query request to the video stream pushing record database in the central scheduler;

[0019] Traverse the query results to find the video stream pushing record entry that exactly matches the identifier of the target video stream device;

[0020] If a matching video stream pushing record is found, extract all relevant video stream pushing information in the record, including the list of edge nodes to which the video stream is pushed and the video stream pushing quality data of each edge node;

[0021] If no matching video stream pushing record is found, select the target edge node by using the default policy.

[0022] Preferably, the configuring a time window for each edge node to which the video stream is pushed based on the preset metric includes the following steps:

[0023] Determine the performance stability value of each edge node as the preset metric;

[0024] Dynamically adjust the size of the time window corresponding to each edge node according to the performance stability value, where the performance stability value and the time window are in an inverse relationship;

[0025] Within each time window, collect and count the push stream quality data of each edge node to which the push stream arrives within the time window, where the push stream quality data includes packet loss rate, latency, and bandwidth utilization;

[0026] Quantify the push stream quality of each edge node to which the push stream arrives according to the push stream quality data.

[0027] Preferably, the quantifying the push stream quality of each edge node to which the push stream arrives according to the push stream quality data includes the following steps:

[0028] Input the packet loss rate, latency, and bandwidth utilization collected within each time window into a predefined push stream quality quantification formula, where the push stream quality quantification formula is:

[0029]

[0030] In the formula, Q is the push stream quality, A, T, and B are the packet loss rate, latency, and bandwidth utilization respectively, α, β, and γ are the weights of the packet loss rate, latency, and bandwidth utilization respectively, and ∈ is a small positive number used to prevent the denominator from being zero.

[0031] Preferably, in the step of selecting the edge node with the optimal push stream quality as the target edge node,

[0032] If there are multiple edge nodes to which the push stream arrives with the same and highest quantified push stream quality, then make a judgment according to the node attributes of the multiple edge nodes to which the push stream arrives, where the node attribute is the address location.

[0033] Preferably, the making a judgment according to the node attributes of the multiple edge nodes to which the push stream arrives includes:

[0034] Compare the address locations of the multiple edge nodes to which the push stream arrives with the highest push stream quality, and select the edge node closest to the geographical location of the client as the target edge node.

[0035] The present invention also provides a video stream transmission control system for executing the described video stream transmission control method, and the control system includes:

[0036] A request receiving module for receiving a video stream request sent by a client to a central scheduler, where the video stream request includes an identifier of a target video stream device;

[0037] A push stream record query module for obtaining the push stream record of the target video stream device according to the identifier, where the push stream record includes the edge nodes to which the push stream arrives and the corresponding push stream quality data;

[0038] An evaluation module, configured to configure a time window for each of the edge nodes to which the streaming is pushed based on a preset metric, and evaluate the streaming quality of each of the edge nodes to which the streaming is pushed according to the configured time window, where the preset metric is a performance stability value, and the streaming quality is quantified by a statistic within the time window;

[0039] An edge node selection module, configured to select the edge node with the optimal streaming quality as the target edge node;

[0040] A target node feedback module, configured to send the selected target edge node to the client, and the client establishes a connection through the selected target edge node and pulls the video stream pushed by the target video stream device.

[0041] Compared with the related art, a video stream transmission control method and control system provided by the present invention have the following beneficial effects:

[0042] The present invention receives a video stream request sent by a client to a central scheduler, obtains its streaming record based on the identifier of the target video stream device, and at the same time introduces a preset metric to configure a time window for each edge node to which the streaming is pushed, and quantitatively evaluates the streaming quality of the edge node within this time window. In this way, the present invention can grasp the streaming status of each edge node in real time, providing a strong basis for subsequent node selection.

[0043] In the node selection stage, the present invention selects the edge node with the optimal streaming quality as the target edge node according to the evaluation result, and sends this information to the client. Subsequently, the client establishes a connection through the selected target edge node and pulls the video stream, thus achieving efficient and stable transmission of the video stream. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flowchart of a video stream transmission control method provided by the present invention;

[0045] Figure 2 is a module structure diagram of a video stream transmission control method provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The present invention will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings rather than all structures. Furthermore, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0047] It should also be noted that, for ease of description, only the parts related to the present invention rather than all the content are shown in the drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but it can also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0048] Embodiment 1

[0049] The present invention provides a video stream transmission control method. Referring to Figure 1 as shown, the control method includes the following steps:

[0050] S1: Receive a video stream request sent by a client to a central scheduler, where the video stream request includes an identifier of a target video stream device.

[0051] In this embodiment, the client sends a request containing an identifier of a target video stream device (such as a device ID, stream name, or URL) to a specific interface of the central scheduler through a network protocol. After receiving the request, the central scheduler first performs request verification to ensure that the request comes from a legitimate client and that the identifier in the request is valid and recognizable. After passing the verification, the central scheduler extracts the identifier of the target video stream device in the request and prepares for subsequent processing.

[0052] S2: Obtain the push stream record of the target video stream device according to the identifier, where the push stream record includes the edge nodes pushed to and the corresponding push stream quality data.

[0053] In this embodiment, the central scheduler uses an internal database to query according to the extracted identifier of the target video stream device.

[0054] The query result includes information about all the edge nodes pushed to by the target video stream device and the push stream quality data on each node.

[0055] S3: Configure a time window for each of the pushed-to edge nodes based on a preset metric, and evaluate the push stream quality of each of the pushed-to edge nodes according to the configured time window, where the preset metric is a performance stability value, and the push stream quality is quantified by a statistic within the time window.

[0056] In this embodiment, the central scheduler first analyzes the historical push stream quality data of each of the pushed-to edge nodes to evaluate its performance stability.

[0057] For those edge nodes with large performance fluctuations, the central scheduler will select a relatively long time window. This longer time window can smooth out some short-term fluctuations, thus more accurately reflecting the average performance of the node over a longer period of time.

[0058] On the contrary, for those edge nodes with stable performance, the central scheduler will select a shorter time window. This can capture small changes in node performance more quickly, ensuring a rapid response when the performance suddenly drops.

[0059] After determining the time window, the central scheduler will collect and calculate the push stream quality of each edge node to which the push stream arrives within this time window.

[0060] S4: Select the edge node with the optimal push stream quality as the target edge node.

[0061] In this embodiment, the central scheduler sorts the evaluation results of the push stream quality of all edge nodes, and based on the sorting results, selects the edge node with the optimal push stream quality as the target edge node.

[0062] If there are multiple edge nodes with similar push stream quality, further screening is considered based on geographical proximity.

[0063] S5: Send the selected target edge node to the client, and the client establishes a connection through the selected target edge node and pulls the video stream pushed by the target video stream device.

[0064] In this embodiment, the central scheduler sends the information of the selected target edge node to the client through a response message. After receiving the response message, the client resolves the information of the target edge node and attempts to establish a network connection with the target edge node. After the connection is successfully established, the client sends a video stream request to the target edge node through this connection and receives the video stream data pushed by the target video stream device.

[0065] In addition, the control method further includes:

[0066] If the target video stream device has no push stream record, a default policy is used to select an edge node as the target edge node.

[0067] Specifically, the default policy is to select the target edge node based on at least one of the addition time, current load, or geographical location of the edge node.

[0068] In this embodiment, if the target video stream device has no push stream record, that is, the device is performing a push stream operation for the first time or the previous push stream record is no longer available, then a default policy is used to select an edge node as the target edge node.

[0069] Based on the addition time of edge nodes:

[0070] Select the most recently added edge node: This helps balance the usage frequency of each node in the system and avoids premature aging of some nodes due to long-term high-load operation.

[0071] Select the node that was added earliest and has a low load: If the newly added node has not been fully tested or its stability verified, you can select a node that was added earlier and currently has a low load as an alternative to ensure service reliability.

[0072] Based on the current load:

[0073] Select the node with the lowest current load: This helps ensure that the performance does not degrade or the quality of service is not impaired due to node overload during the video streaming process.

[0074] Consider load balancing: If there are multiple edge nodes and the load differences among the nodes are not significant, you can select a node that can make the overall load more balanced.

[0075] Based on geographical location:

[0076] Select the node that is geographically closest to the user or the target video stream device: This helps reduce transmission latency and improve the user experience.

[0077] Consider the network topology: When selecting the node that is geographically closest, you also need to consider the network topology to ensure that the network connection between the selected node and the target device is efficient and stable.

[0078] Specifically, step S2 includes the following steps:

[0079] S201: Analyze the video stream request sent by the client and extract the identifier of the target video stream device from it.

[0080] In this embodiment, when the client (such as a camera, mobile device, etc.) initiates a video stream request, the request is sent to the central scheduler. The central scheduler first analyzes this request, which contains the unique identifier of the target video stream device (such as device ID, MAC address, or custom identifier). The analysis process usually involves reading specific fields in the HTTP request header, request body, or query string to extract the identifier of the target video stream device.

[0081] S202: Use the identifier as a query keyword and send a query request to the video streaming record database in the central scheduler.

[0082] In this embodiment, after the identifier of the target video stream device is extracted, the central scheduler constructs a database query statement using this identifier as the query keyword. This query statement is sent to the push stream record database maintained within the central scheduler to retrieve all push stream records related to the target video stream device. The push stream record database can be, but is not limited to, a relational database, a NoSQL database, or any other type of data storage system.

[0083] S203: Traverse the query results to find a push stream record entry that exactly matches the identifier of the target video stream device.

[0084] In this embodiment, after the push stream record database returns the query results, the central scheduler traverses these results. For each push stream record, it checks whether the device identifier in the record exactly matches the identifier of the target video stream device. This matching process is implemented based on string comparison to ensure that the found push stream record indeed belongs to the target video stream device of the current request.

[0085] S204: If a matching push stream record is found, extract all relevant push stream information from this record, including the list of edge nodes to which the stream is pushed and the push stream quality data for each edge node.

[0086] In this embodiment, once a matching push stream record is found, the central scheduler further extracts all relevant push stream information from this record. This information includes the list of edge nodes used during the previous push, the push stream quality data for each edge node, and the push stream timestamp.

[0087] S205: If no matching push stream record is found, select the target edge node through the default policy.

[0088] In this embodiment, if the central scheduler does not find a push stream record that exactly matches the identifier of the target video stream device in the push stream record database, it will instead adopt the default policy to select the target edge node.

[0089] Specifically, step S3 includes the following steps:

[0090] S301: Determine the performance stability value of each edge node as a preset metric.

[0091] In this embodiment, the performance stability value is obtained based on the historical data averaging method, that is, collect the push stream quality data (such as packet loss rate, latency time, bandwidth utilization rate) of each edge node over a period of time in the past, and calculate the average value of these data as the performance stability value.

[0092] S302: Dynamically adjust the time window size corresponding to each edge node according to the performance stability value, where the performance stability value and the time window are in an inverse relationship.

[0093] In this embodiment, the central scheduler dynamically adjusts the size of the corresponding time window according to the performance stability value of each edge node. An inverse relationship is set between the performance stability value and the time window size, that is, the higher the performance stability value (indicating that the node is more stable), the smaller the time window; the lower the performance stability value (indicating that the node fluctuates greatly), the larger the time window.

[0094] Set thresholds and intervals: First, set a series of thresholds for the performance stability value and the corresponding intervals of the time window size.

[0095] Dynamic matching: Dynamically match the closest interval of the time window size according to the actual performance stability value of each edge node.

[0096] Adjust the time window: Finally, adjust the size of the time window corresponding to the edge node according to the matching result.

[0097] S303: Within each time window, collect and statistically analyze the streaming quality data of each edge node to which the stream is pushed within the time window. The streaming quality data includes packet loss rate, latency, and bandwidth utilization.

[0098] In this embodiment, within each set time window, the central scheduler will collect and statistically analyze the streaming quality data of each edge node to which the stream is pushed within the time window. These data include packet loss rate, latency, bandwidth utilization, etc., which can comprehensively reflect the performance of the edge node during the streaming process.

[0099] Data collection: Obtain the streaming quality data through the data reported by the edge node, network monitoring tools or other data sources.

[0100] Data statistics: Statistically process the collected data, and calculate the average packet loss rate, average latency, and average bandwidth utilization of each edge node within each time window.

[0101] S304: Quantify the streaming quality of each edge node to which the stream is pushed according to the streaming quality data.

[0102] In this embodiment, the central scheduler will quantitatively evaluate the streaming quality of each edge node to which the stream is pushed according to the collected streaming quality data. The method of quantitative evaluation is the weighted scoring method: Different weights are assigned to different streaming quality indicators (such as packet loss rate, latency, bandwidth utilization), and the comprehensive score is calculated according to the actual value and weight of each indicator.

[0103] Specifically, the weighted scoring method is to input the packet loss rate, latency, and bandwidth utilization collected within each time window into a predefined streaming quality quantization formula. Among them, the streaming quality quantization formula is:

[0104]

[0105] In the formula, Q is the push stream quality, A, T, and B are the packet loss rate, latency, and bandwidth utilization rate respectively, α, β, and γ are the weights of the packet loss rate, latency, and bandwidth utilization rate respectively, and ∈ is a small positive number used to prevent the denominator from being zero.

[0106] Specifically, in the step of selecting the edge node with the optimal push stream quality as the target edge node,

[0107] If there are multiple edge nodes with the same and highest quantified push stream quality among the edge nodes to which the push is made, then a judgment is made based on the node attributes of the multiple edge nodes to which the push is made, where the node attribute is the address location.

[0108] Specifically, the judgment based on the node attributes includes:

[0109] Compare the address locations of the multiple edge nodes to which the push is made with the highest push stream quality, and select the edge node closest to the geographical location of the client as the target edge node.

[0110] The working principle of a video stream transmission control method provided by the present invention is as follows:

[0111] Request reception and parsing: First, the central scheduler receives a video stream request from the client. The request contains the unique identifier of the target video stream device, which is the basis for subsequent operations. The central scheduler parses the request, extracts key information, and prepares for subsequent processing.

[0112] Push stream record query: Using the extracted identifier of the target video stream device, a query request is sent to the push stream record database. The database stores the historical push stream records of each video stream device, including the list of edge nodes to which they have pushed and the corresponding push stream quality data on these nodes. By traversing the query results, a push stream record matching the identifier of the target video stream device is found, providing data support for subsequent evaluation.

[0113] Time window configuration and push stream quality evaluation: Based on a preset performance stability value index, a time window is configured for each edge node to which the push is made. This time window is a dynamically adjusted observation period used to collect and statistically analyze the push stream quality data of the node within a specific time period, such as the packet loss rate, latency, and bandwidth utilization rate. By statistically analyzing these key indicators, the push stream quality of each edge node can be quantified, providing a scientific basis for subsequent node selection.

[0114] Optimal Edge Node Selection: After evaluating the push stream quality of all edge nodes to which the stream is pushed, the edge node with the optimal push stream quality is selected as the target edge node based on the evaluation results. If there are multiple nodes with the same push stream quality, other attributes of the nodes (such as geographical location, network stability, etc.) will be further considered to make the final selection.

[0115] Target Node Feedback and Connection Establishment: Finally, the information of the selected target edge node is fed back to the client. Based on the received information, the client establishes a connection through the selected target edge node and pulls the video stream pushed by the target video stream device. Since the target edge node is carefully selected and evaluated, it can ensure the efficient and stable transmission of the video stream and improve the user's viewing experience.

[0116] In summary, the video stream transmission control scheme of the present invention realizes the real-time monitoring and evaluation of the push stream quality of edge nodes through a series of intelligent processing steps, and selects the optimal node for video stream distribution based on the evaluation results. This scheme not only improves the stability and reliability of video stream transmission, but also provides a smoother and clearer viewing experience for users.

[0117] Embodiment 2

[0118] The present invention also provides a video stream transmission control system for executing the video stream transmission control method described above. Referring to Figure 2 as shown, the control system includes:

[0119] A request receiving module 100 for receiving a video stream request sent by a client to a central scheduler, where the video stream request includes an identifier of a target video stream device;

[0120] A push stream record query module 200 for obtaining the push stream record of the target video stream device according to the identifier, where the push stream record includes the edge nodes to which the stream is pushed and the corresponding push stream quality data;

[0121] An evaluation module 300 for configuring a time window for each of the edge nodes to which the stream is pushed based on a preset index, and evaluating the push stream quality of each of the edge nodes to which the stream is pushed according to the configured time window, where the preset index is a performance stability value, and the push stream quality is quantified by a statistic within the time window;

[0122] An edge node selection module 400 for selecting the edge node with the optimal push stream quality as the target edge node;

[0123] A target node feedback module 500 for sending the selected target edge node to the client, and the client establishes a connection through the selected target edge node and pulls the video stream pushed by the target video stream device.

[0124] This application is described by referring to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0125] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable storage medium, and the storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0126] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or device. Without more limitations, the element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

Claims

1. A video stream transmission control method, characterized in that: The control method includes the following steps: Receive a video stream request sent by a client to a central scheduler, wherein the video stream request includes an identifier of a target video stream device; Obtaining a streaming record of the target video streaming device according to the identifier, wherein the streaming record includes an edge node to which the streaming is pushed and corresponding streaming quality data; Based on a preset indicator, a time window is configured for each edge node to which the stream is pushed, and the push quality of each edge node to which the stream is pushed is evaluated according to the configured time window, wherein the preset indicator is a performance stability value, and the push quality is quantified by a statistic within the time window; Select the edge node with the best streaming quality as the target edge node. The specific steps are as follows: If there are multiple edge nodes to which the stream is pushed, and the quantized push quality is the same and the quality is the highest, then a judgment is made based on the node attributes of the multiple edge nodes to which the stream is pushed, wherein the node attribute is the address location. Specifically, the judgment is: Comparing the address locations of the plurality of edge nodes to which the streams are pushed with the highest push quality, and selecting the edge node closest to the client's geographical location as the target edge node; Sending the selected target edge node to the client, the client establishing a connection through the selected target edge node and pulling the video stream pushed by the target video stream device; The control method also includes: If the target video streaming device has no streaming record, a default strategy is adopted to select an edge node as the target edge node; The default strategy is to select a target edge node based on at least one of an addition time, a current load, or a geographical location of the edge node.

2. A video stream transmission control method according to claim 1, characterized in that: The step of obtaining the streaming record of the target video streaming device according to the identifier includes the following steps: Parsing the video stream request sent by the client, and extracting the identifier of the target video stream device; Using the identifier as a query keyword, a query request is initiated to the streaming record database in the central scheduler; Traversing the query results to find a streaming record entry that completely matches the identifier of the target video streaming device; If a matching push stream record is found, all relevant push stream information in the record is extracted, including the list of edge nodes to which the stream is pushed and the push stream quality data of each edge node; If no matching push record is found, the target edge node is selected using the default strategy.

3. A video stream transmission control method according to claim 2, characterized in that: The configuring of a time window for each edge node to which the stream is pushed based on a preset indicator comprises the following steps: Determine the performance stability value of each edge node as a preset indicator; Dynamically adjust the time window size corresponding to each edge node according to the performance stability value, wherein the performance stability value and the time window are inversely proportional; In each time window, collect and count the streaming quality data of each edge node to which the streaming is pushed in the time window, wherein the streaming quality data includes packet loss rate, delay time, and bandwidth utilization; The streaming quality of each edge node to which the streaming is pushed is quantified according to the streaming quality data.

4. A video stream transmission control method according to claim 3, characterized in that: The step of quantifying the push quality of each edge node to which the push is sent according to the push quality data comprises the following steps: The packet loss rate, delay time, and bandwidth utilization collected in each time window are input into a predefined streaming quality quantification formula, where the streaming quality quantification formula is: Where, For streaming quality, 、 and They are packet loss rate, delay time and bandwidth utilization, 、 and are the weights of packet loss rate, delay time and bandwidth utilization respectively, is a small positive number used to prevent the denominator from being zero.

5. A video stream transmission control system, configured to execute a video stream transmission control method according to any one of claims 1 to 4, characterized in that: The control system includes: A request receiving module, configured to receive a video stream request sent by a client to a central scheduler, wherein the video stream request includes an identifier of a target video stream device; A streaming record query module, configured to obtain a streaming record of the target video streaming device according to the identifier, wherein the streaming record includes an edge node to which the streaming is pushed and corresponding streaming quality data; An evaluation module, configured to configure a time window for each edge node to which the stream is pushed based on a preset indicator, and evaluate the push quality of each edge node to which the stream is pushed according to the configured time window, wherein the preset indicator is a performance stability value, and the push quality is quantified by a statistic within the time window; The edge node selection module is used to select the edge node with the best streaming quality as the target edge node; The target node feedback module is used to send the selected target edge node to the client, and the client establishes a connection through the selected target edge node and pulls the video stream pushed by the target video stream device.

Images