WO2023116219A1 - Cdn节点分配方法、装置、电子设备、介质及程序产品 - Google Patents

Cdn节点分配方法、装置、电子设备、介质及程序产品 Download PDF

Info

Publication number
WO2023116219A1
WO2023116219A1 PCT/CN2022/129267 CN2022129267W WO2023116219A1 WO 2023116219 A1 WO2023116219 A1 WO 2023116219A1 CN 2022129267 W CN2022129267 W CN 2022129267W WO 2023116219 A1 WO2023116219 A1 WO 2023116219A1
Authority
WO
WIPO (PCT)
Prior art keywords
cdn
quality
target
nodes
type
Prior art date
Application number
PCT/CN2022/129267
Other languages
English (en)
French (fr)
Inventor
乔春雨
王大瑞
孟胜彬
马茜
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2023116219A1 publication Critical patent/WO2023116219A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
    • H04L67/61—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources taking into account QoS or priority requirements

Definitions

  • the present application relates to the technical field of the Internet, and in particular to a CDN node allocation method, device, electronic equipment, media and program product.
  • CDN Content Delivery Network
  • edge servers deployed in various places. Through the load balancing, content distribution, scheduling and other functional modules of the central platform, users can obtain the required content nearby, reduce network congestion, and improve user access response Speed and hit rate.
  • a CDN node allocation method including:
  • the node quality scoring table includes the physical scene and the multiple The mapping relationship of the quality score of each type of CDN node
  • the candidate CDN node set According to the number of nodes corresponding to the plurality of types of candidate CDN nodes in the candidate CDN node set and the quality evaluation results, select a target type of CDN node from the candidate CDN node set, wherein the candidate of the target type CDN nodes are of the highest quality.
  • the method also includes:
  • the historical network data includes: historical video data;
  • determining the quality score of the type of CDN node corresponding to the individual historical network data includes:
  • determining the quality score of the type of CDN node corresponding to the historical video data according to the first screen time, the freeze duration and the freeze times including:
  • the first screen time, the freeze duration and the freeze times are processed to obtain the quality score of the type of CDN node corresponding to the historical video data.
  • the method also includes:
  • the method also includes:
  • the overall quality of the multiple types of CDN nodes and the cost information of the multiple types of CDN nodes determine the number of nodes corresponding to the multiple types of candidate CDN nodes in the candidate CDN node set.
  • the method also includes:
  • the request data corresponding to the target network request is obtained through the CDN node of the target type, and the request data is returned to the terminal device.
  • the target network request is a video playback request
  • the target physical scene corresponding to the target network request includes one or more of the following: video popularity, video bit rate, startup type, network type, and network operator.
  • a CDN node allocation device including:
  • the target physical scene acquisition module is used to obtain the target physical scene corresponding to the target network request
  • a target quality score determination module configured to determine target quality scores of multiple types of CDN nodes corresponding to the target physical scene according to the target physical scene and a pre-established node quality score table; wherein, the node quality score table Including the mapping relationship between the physical scene and the quality scores of the multiple types of CDN nodes;
  • a CDN node quality evaluation module configured to evaluate the quality of the multiple types of CDN nodes according to the target quality scores of the multiple types of CDN nodes, and obtain a quality evaluation result
  • a candidate CDN node determination module configured to select a target type of CDN node from the candidate CDN node set according to the number of nodes respectively corresponding to the plurality of types of candidate CDN nodes in the candidate CDN node set and the quality evaluation results, Among them, the candidate CDN nodes of the target type have the highest quality.
  • the CDN node allocation device also includes:
  • a data acquisition module configured to acquire a plurality of historical network data, a physical scene corresponding to a single historical network data, and a type of CDN node corresponding to a single historical network data;
  • a quality score determination module configured to determine the quality score of the type of CDN node corresponding to the single historical network data according to the single historical network data;
  • a node quality scoring table generating module configured to establish a mapping relationship between a single physical scene corresponding to the historical network data and the quality scoring of the type of CDN node corresponding to the historical network data, and obtain the node quality scoring table.
  • the historical network data includes: historical video data;
  • the quality score determination module is specifically configured to obtain the first screen time and/or freeze duration and/or freeze times of a single historical video data according to the single historical video data; according to the first screen time and/or Or the freeze duration and/or the freeze times, determine the quality score of the type of CDN node corresponding to the historical video data.
  • the quality score determination module determines the quality of the type of CDN node corresponding to the historical video data according to the first screen time, the freeze duration and the freeze times through the following steps score:
  • the first screen time, the freeze duration and the freeze times are processed to obtain the quality score of the type of CDN node corresponding to the historical video data.
  • the CDN node allocation device also includes:
  • a node removal module configured to remove the selected candidate CDN nodes of the target type from the set of candidate CDN nodes
  • a loop module configured to determine the current network request as a target network request, and return to the target physical scene acquisition module until the total number of candidate CDN nodes is 0.
  • the CDN node allocation device also includes:
  • a node number determination module configured to determine the plurality of types of candidate CDN nodes in the set of candidate CDN nodes according to the overall quality of the plurality of types of CDN nodes and the cost information of the plurality of types of CDN nodes corresponding to the number of nodes.
  • the CDN node allocation device also includes:
  • a request data obtaining module configured to obtain the request data corresponding to the target network request through the CDN node of the target type
  • the request data sending module is used to return the request data to the terminal device.
  • the target network request is a video playback request
  • the target physical scene corresponding to the target network request includes one or more of the following: video popularity, video bit rate, startup type, network type, and network operator.
  • an electronic device including: a processor, the processor is configured to execute a computer program stored in a memory, and when the computer program is executed by the processor, the method described in the first aspect is implemented .
  • a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method described in the first aspect is implemented.
  • a computer program product which causes the computer to execute the method described in the first aspect when the computer program product is run on a computer.
  • a computer program which implements the method described in the first aspect when the computer program is executed by a processor.
  • FIG. 1 shows a schematic diagram of the system architecture of an exemplary application environment that can be applied to the CDN node allocation method of the embodiment of the present application;
  • Fig. 2 is a kind of flowchart of CDN node allocation method in the embodiment of the present application
  • Fig. 3 is a kind of flowchart of the establishment method of node quality scoring table in the embodiment of the present application
  • Fig. 4 is another flow chart of the method for assigning CDN nodes in the embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a CDN node allocation device in an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of an electronic device in an embodiment of the present application.
  • CDN nodes can be selected based on loads and costs of CDN nodes from different vendors.
  • the CDN nodes selected based on this method cannot provide users with high-quality network services.
  • the node quality score table includes the mapping relationship between the physical scene and the quality score of multiple types of CDN nodes, so that after receiving the target network request, the corresponding target physical scene can be requested according to the target network, Determine target quality scores of multiple types of CDN nodes corresponding to the target physical scene.
  • the target quality scores of multiple types of CDN nodes the quality of multiple types of CDN nodes is evaluated to obtain a quality evaluation result. For example, evaluate the quality of CDN nodes from different vendors in the target physical scenario.
  • the CDN node with the highest quality may be selected from the candidate CDN nodes, so as to process the target network request through the selected candidate CDN node.
  • this application selects the highest-quality CDN node corresponding to the physical scene for the user according to the physical scene where the user is located, so as to fully consider the difference in the impact of different vendors' CDNs on terminal devices in different physical scenes, and improve the service of the CDN node. quality.
  • FIG. 1 shows a schematic diagram of a system architecture of an exemplary application environment that can be applied to the CDN node allocation method of the embodiment of the present application.
  • the system architecture 100 may include one or more of a terminal device 101, a terminal device 102, and a terminal device 103, and more than one of a server 104, a CDN node 105, a CDN node 106, a CDN node 107, and a CDN node 108. indivual.
  • the system architecture 100 can also be a network, and the network is used to provide a network between the terminal device 101, the terminal device 102, the terminal device 103 and the server 104, and between the server 104 and the CDN node 105, the CDN node 106, the CDN node 107, and the CDN node 108.
  • the medium of the communication link is used to provide a network between the terminal device 101, the terminal device 102, the terminal device 103 and the server 104, and between the server 104 and the CDN node 105, the CDN node 106, the CDN node 107, and the CDN node 108.
  • a network may include various connection types such as wires, wireless communication links, or fiber optic cables, among others.
  • the terminal device 101, the terminal device 102, and the terminal device 103 may be various electronic devices, including but not limited to desktop computers, portable computers, smart phones, and tablet computers. It should be understood that the numbers of terminal devices, networks, CDN nodes and servers in Fig. 1 are only illustrative. According to implementation requirements, there may be any number of terminal devices, networks, CDN nodes and servers.
  • the server 104 may be a server cluster composed of multiple servers.
  • the CDN node allocation method provided in the embodiment of the present application is generally executed by the server 104 , and accordingly, the CDN node allocation device may be set in the server 104 .
  • the server 104 may pre-establish a node quality scoring table, and after receiving the target network request sent by the terminal device 101, based on the CDN node allocation method of the embodiment of the present application, request to allocate a CDN node for the target network.
  • the CDN node 105, the CDN node 106, the CDN node 107, and the CDN node 108 are four types of candidate CDN nodes, namely, the first type of CDN node, the second type of CDN node, the third type of CDN node, and the fourth type of CDN node , according to the node quality scoring table, it is determined that the quality of the second type of CDN node in the target physical scene corresponding to the target network request is the highest, then the target network request is sent to the CDN node 106 to process the target network request through the CDN node 106 , and send the request data to the terminal device 101.
  • the service quality of the CDN node can be improved.
  • FIG. 2 is a flowchart of a CDN node allocation method in the embodiment of the present application, which may include the following steps:
  • Step S210 acquiring the target physical scene corresponding to the target network request.
  • the target network request may be a video playback request, a data download request, and the like.
  • the request types of the target network requests are different, and the corresponding target physical scenarios may also be different.
  • the target network request is a data download request
  • the target physical scene corresponding to the target network request includes one or more of the following: network type, network operator, and province.
  • the popularity of the video has a great impact on the service quality of the CDN node. If it is not stored on the CDN node, the video playback request is more likely to go back to the source, which may cause longer first screen time and more freezes, and the video playback quality is lower. Therefore, the video heat can be used as a reference factor in the physical scene.
  • the popularity of videos can be counted by the relative number of playback times, that is, the number of times videos are played within an hour is counted, and sorted according to the number of playback times. The top 1% of the videos in the ranking are taken as hot videos, and other videos are taken as cold videos.
  • the video bit rate (such as 720p, 540p, 480p) and startup type (cold start or hot start) have a great impact on the service quality of the CDN node
  • the video bit rate and startup type can also be used as a reference in the physical scene factor.
  • cold start means that when the application software is started, there is no process of the application in the background
  • hot start means that when the application software is started, there is a process of the application in the background.
  • the target physical scene corresponding to the target network request may include one or more of the following: video popularity, video bit rate, startup type, network type, network operator, and province.
  • Step S220 according to the target physical scene and the pre-established node quality scoring table, determine the target quality scores of multiple types of CDN nodes corresponding to the target physical scene.
  • the node quality scoring table is pre-established according to historical network data.
  • the node quality scoring table includes the mapping relationship between physical scenarios and the quality scoring of multiple types of CDN nodes, and is used for multiple CDN nodes in different physical scenarios. Types of CDN nodes to evaluate.
  • the multiple types of CDN nodes may be multiple CDN nodes from different manufacturers, or different types of CDN nodes from the same manufacturer, or multiple different types of CDN nodes from different manufacturers.
  • the historical network data used when establishing the node quality scoring table may be the latest network data, for example, the network data within the last half hour.
  • the node quality scoring table can also be continuously updated later to improve the accuracy of the node quality scoring table.
  • the node quality scoring table can be established with reference to more reference factors. The process of establishing the node quality scoring table will be described in detail below, and will not be described in detail here.
  • step S230 the quality of multiple types of CDN nodes is evaluated according to the target quality scores of multiple types of CDN nodes, and a quality evaluation result is obtained.
  • the quality of the CDN node Assuming that there are three types of CDN nodes, the first type of CDN node, the second type of CDN node and the third type of CDN node, the corresponding target quality scores are 6.8, 3.7 and 5.6 respectively, and the lower the target quality score, the quality of the CDN node Therefore, it can be determined that the quality of the second type of CDN nodes is the highest, the quality of the third type of CDN nodes is next, and the quality of the first type of CDN nodes is the lowest.
  • Step S240 according to the number of nodes and quality evaluation results corresponding to multiple types of candidate CDN nodes in the candidate CDN node set, select a target type of CDN node from the candidate CDN node set.
  • the candidate CDN node set includes multiple types of candidate CDN nodes. Each type of candidate CDN node has a corresponding number of nodes. Candidate CDN nodes of the target type can be selected from the candidate CDN node set. The candidate CDN nodes of the target type have the highest quality . The target type is determined from the above step S230. If there are multiple CDN nodes of the target type, just select any one of them. For example, for the above-mentioned first-type CDN nodes, second-type CDN nodes, and third-type CDN nodes, the second-type CDN nodes may be selected. Through verification, this application can reduce the first screen time by 1.2%, reduce the freezing time by 5.1% and the number of freezing times by 5.4%.
  • the request data corresponding to the target network request can be obtained through the target-type CDN node, and the request data can be returned to the terminal device.
  • the node quality score table is established in advance, and the node quality score table includes the mapping relationship between the physical scene and the quality score of multiple types of CDN nodes, so that after receiving the target network request, According to the target physical scene corresponding to the target network request, the target quality scores of multiple types of CDN nodes corresponding to the target physical scene are determined. According to the target quality scores of multiple types of CDN nodes, the quality of multiple types of CDN nodes is evaluated to obtain a quality evaluation result. For example, evaluate the quality of CDN nodes from different vendors in the target physical scenario.
  • the CDN node with the highest quality may be selected from the candidate CDN nodes, so as to process the target network request through the selected candidate CDN node. It can be seen that this application selects the highest-quality CDN node corresponding to the physical scene for the user according to the physical scene where the user is located, so as to fully consider the difference in the impact of different vendors' CDNs on terminal devices in different physical scenes, and improve the service of the CDN node. quality.
  • FIG. 3 is a flow chart of a method for establishing a node quality scoring table in an embodiment of the present application, which may include the following steps:
  • Step S310 acquiring a plurality of historical network data, a physical scene corresponding to a single historical network data, and a type of CDN node corresponding to a single historical network data.
  • the quality score for the CDN node can be determined based on the network data corresponding to the network request, and different types of network requests correspond to different network data. Since the physical scene and the quality score of multiple types of CDN nodes need to be established, the physical scene corresponding to a single historical network data and the type of CDN node corresponding to a single historical network data can also be obtained. A single historical network data corresponds to a type of CDN nodes, multiple historical network data can correspond to many different types of CDN nodes. In this way, the type of the CDN node corresponding to the physical scene can be determined. Furthermore, by determining the quality score of this type of CDN node, the corresponding relationship between the physical scene and the quality score of this type of CDN node can be obtained.
  • Step S320 according to the single historical network data, determine the quality score of the type of CDN node corresponding to the single historical network data.
  • the indicators for evaluating the quality of CDN nodes may also be different.
  • the historical network data includes: historical video data; the quality of the video data can be determined according to indicators such as the first screen time of the video data, the duration of the freeze, and the number of freezes, and the quality of the video data can reflect the quality of the CDN node, so The quality of the CDN node can be represented by the quality of the video data.
  • the first screen time and/or freeze duration and/or freeze times of a single historical video data can be obtained, and according to the first screen time and/or freeze duration and/or freeze times , to determine the quality score of the type of CDN node corresponding to the historical video data.
  • the first screen time refers to the time consumed by the browser to display the first screen page, and the longer the first screen time, the lower the quality of the video data.
  • the freeze duration can be the freeze duration of 100 seconds, etc.
  • the freeze duration of 100 seconds refers to the product of the ratio of the sum of the freeze duration in the video to the viewing time and 100.
  • the freeze duration of 100 seconds indicates that the quality of the video data is lower.
  • the number of freezes can be the number of freezes per 100 seconds, which refers to the product of the ratio of the number of freezes in the video to the viewing time and 100. The more freezes, the lower the quality of the video data.
  • the first screen time, freeze duration, and freeze times can also be weighted and averaged to obtain the quality score of this type of CDN node corresponding to the historical video data.
  • the quality score of this type of CDN node corresponding to historical video data may be equal to first screen time + ⁇ * freeze duration + ⁇ * freeze times, where the values of ⁇ and ⁇ can be determined based on experience.
  • the first screen time, freeze duration and freeze times can be processed to obtain the quality score of the CDN node corresponding to the type of historical video data.
  • the training method of the neural network scoring model can be: obtain multiple sample video videos corresponding to multiple types of CDN nodes, and obtain the first screen time, freeze duration, and freeze times of each sample video data as input. The viewing time of the video data determines the label data, and the training generates a neural network scoring model.
  • Step S330 establishing a mapping relationship between the physical scene corresponding to a single historical network data and the quality score of this type of CDN node corresponding to the historical network data, and obtaining a node quality score table.
  • a mapping relationship between the physical scene corresponding to a single historical network data and the quality score of this type of CDN node can be established.
  • a single historical network data can establish a mapping relationship between a physical scene and the quality score of a type of CDN node.
  • the mapping relationship of the quality scores of multiple types of CDN nodes corresponding to the same physical scene can be obtained, thereby obtaining the node quality score table.
  • the quality score of multiple types of CDN nodes can be determined directly according to the physical scene corresponding to the network request, so as to evaluate the quality of multiple types of CDN nodes to select The highest quality type of CDN node.
  • FIG. 4 is another flow chart of the CDN node allocation method in the embodiment of the present application, which may include the following steps:
  • Step S410 acquiring the target physical scene corresponding to the target network request.
  • multiple different terminal devices usually visit the same website.
  • multiple terminal devices will send target network requests, or the same device can also send multiple target network requests at different times, and the server can Multiple target network requests are respectively processed through the following cyclic process.
  • Step S420 according to the target physical scene and the pre-established node quality scoring table, determine the target quality scores of multiple types of CDN nodes corresponding to the target physical scene; wherein, the node quality scoring table includes the physical scene respectively and multiple types of CDN nodes The mapping relationship of the quality score.
  • Step S430 Evaluate the quality of multiple types of CDN nodes according to the target quality scores of multiple types of CDN nodes to obtain a quality assessment result.
  • Step S440 judging whether the total number of multiple types of candidate CDN nodes in the candidate CDN node set is greater than zero.
  • CDN nodes Multiple types may be pre-allocated in the candidate CDN node set, and each type of CDN node corresponds to a certain number of nodes. Different types of CDN nodes have different costs due to performance differences. Therefore, the CDN node with the highest quality can be selected for each terminal device without increasing the cost.
  • the number of nodes corresponding to multiple types of candidate CDN nodes in the candidate CDN node set may be determined according to the overall quality of multiple types of CDN nodes and cost information (such as prices) of multiple types of CDN nodes. It should be noted that the overall quality is obtained after an overall evaluation of multiple types of CDN nodes, and may be slightly different from the quality of multiple types of CDN nodes corresponding to different physical scenarios. For example, the overall quality of the first-type CDN nodes is the highest, but may not be the highest according to the quality score of the corresponding first-type CDN nodes in a certain physical scenario.
  • the set of candidate CDN nodes includes three types of candidate CDN nodes, the first type of candidate CDN nodes, the second type of candidate CDN nodes and the third type of candidate CDN nodes.
  • the corresponding number of nodes can be 1000, 2000 and 7000 respectively, and the total number of nodes of multiple types of candidate CDN nodes in the candidate CDN node set is 10000.
  • step S450 If the total number of multiple types of candidate CDN nodes in the candidate CDN node set is greater than 0, it means that there are currently candidate CDN nodes that can be selected, and the following step S450 can be performed; if multiple types of candidate CDN nodes in the candidate CDN node set The total node number of the node is equal to 0, which means that there is currently no candidate CDN node that can be selected, and the process ends. Alternatively, after a new candidate CDN node is added to the set of candidate CDN nodes, the following step S450 may be continued.
  • Step S450 according to the number of nodes and quality evaluation results corresponding to multiple types of candidate CDN nodes in the candidate CDN node set, select the target type of CDN nodes from the candidate CDN node set, wherein the target type of candidate CDN nodes has the highest quality.
  • the number of nodes corresponding to the first type of candidate CDN nodes, the second type of candidate CDN nodes and the third type of candidate CDN nodes are respectively 1000, 2000 and 7000, and you can directly select Candidate CDN nodes of the highest quality type.
  • step S430 it is determined that the quality of the second-type CDN nodes is the highest, since the number of second-type candidate CDN nodes in the candidate CDN node set is 0, the second-type candidate CDN nodes cannot be selected. If it is determined according to step S430 that the quality of the first-type CDN nodes is higher than that of the third-type CDN nodes, one of the remaining 50 first-type candidate CDN nodes may be selected.
  • Step S460 removing the candidate CDN nodes of the selected target type from the set of candidate CDN nodes.
  • the selected candidate CDN node may be removed from the set of candidate CDN nodes, so that the candidate CDN node may not be selected next time.
  • Step S470 determine the current network request as the target network request, and return to step S410 until the total number of candidate CDN nodes is 0.
  • the node quality scoring table is established in advance, and the node quality scoring table includes the mapping relationship between the physical scene and the quality scoring of multiple types of CDN nodes, so that after receiving each target network request , according to the target physical scene corresponding to each target network request, determine the target quality scores of multiple types of CDN nodes corresponding to each target physical scene.
  • the quality of multiple types of CDN nodes is evaluated to obtain a quality evaluation result. For example, evaluate the quality of CDN nodes from different vendors in the target physical scenario.
  • the candidate CDN node with the highest quality may be selected from the candidate CDN node set, so as to process the target network request through the selected candidate CDN node.
  • the number of nodes of each type of candidate CDN nodes in the set of candidate CDN nodes can be determined according to the overall quality and cost information of each type of candidate CDN nodes, so that without increasing the cost, according to the physical scene where different users are located , select the CDN node with the highest quality corresponding to the physical scenario for the user, so as to fully consider the difference in the impact of different vendors' CDNs on terminal devices in different physical scenarios, and improve the service quality of the CDN node.
  • the embodiment of the present application also provides a CDN node allocation device.
  • the CDN node configuration device 500 includes:
  • the target physical scene acquisition module 510 is configured to acquire the target physical scene corresponding to the target network request
  • the target quality score determination module 520 is used to determine the target quality scores of multiple types of CDN nodes corresponding to the target physical scene according to the target physical scene and the pre-established node quality score table; wherein, the node quality score table includes the physical scene respectively and The mapping relationship of quality scores of multiple types of CDN nodes;
  • the CDN node quality evaluation module 530 is used to evaluate the quality of multiple types of CDN nodes according to the target quality scores of multiple types of CDN nodes, and obtain a quality evaluation result;
  • the candidate CDN node determination module 540 is configured to select a CDN node of the target type from the candidate CDN node set according to the number of nodes and quality evaluation results respectively corresponding to multiple types of candidate CDN nodes in the candidate CDN node set, wherein the target type of Candidate CDN nodes are of the highest quality.
  • the CDN node allocation device 500 also includes:
  • a data acquisition module configured to acquire a plurality of historical network data, a physical scene corresponding to a single historical network data, and a type of CDN node corresponding to a single historical network data;
  • a quality score determination module configured to determine the quality score of the CDN node of the type corresponding to the single historical network data according to the single historical network data;
  • the node quality scoring table generation module is used to establish the mapping relationship between the physical scene corresponding to a single historical network data and the quality scoring of CDN nodes of the type corresponding to the historical network data, and obtain the node quality scoring table.
  • the historical network data includes: historical video data;
  • the quality score determination module is specifically used to obtain the first screen time and/or freeze duration and/or freeze times of a single historical video data according to a single historical video data; according to the first screen time and/or freeze duration and/or freeze Frame times, determine the quality score of the CDN node corresponding to the type of historical video data.
  • the quality score determination module determines the quality score of the CDN node corresponding to the type of historical video data according to the first screen time, freeze duration and freeze times through the following steps:
  • the first screen time, freeze duration, and freeze times are processed to obtain the quality score of the CDN node corresponding to the type of historical video data.
  • the CDN node allocation device 500 also includes:
  • the node removal module is used to remove the candidate CDN node of the selected target type from the candidate CDN node set
  • the loop module is used to determine the current network request as the target network request, and return to the target physical scene acquisition module until the total number of candidate CDN nodes is 0.
  • the CDN node allocation device 500 also includes:
  • the node number determination module is used to determine the number of nodes corresponding to multiple types of candidate CDN nodes in the candidate CDN node set according to the overall quality of multiple types of CDN nodes and the cost information of multiple types of CDN nodes.
  • the CDN node allocation device also includes:
  • a request data obtaining module configured to obtain request data corresponding to a target network request through a CDN node of the target type
  • the request data sending module is used to return the request data to the terminal device.
  • the target network request is a video playback request
  • the target physical scene corresponding to the target network request includes one or more of the following: video popularity, video bit rate, startup type, network type, and network operator.
  • an electronic device including: a processor; a memory for storing processor-executable instructions; wherein, the processor is configured to perform the above-mentioned CDN node allocation in this exemplary embodiment method.
  • FIG. 6 is a schematic structural diagram of an electronic device in an embodiment of the present application. It should be noted that the electronic device 600 shown in FIG. 6 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.
  • the electronic equipment in the embodiment of the present application may include but not limited to such as mobile phone, notebook computer, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle-mounted terminal (such as mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers and the like.
  • an electronic device 600 includes a central processing unit (CPU) 601, which can operate according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage section 608 into a random access memory (RAM) 603 Instead, various appropriate actions and processes are performed.
  • ROM read-only memory
  • RAM random access memory
  • various programs and data necessary for system operation are also stored.
  • the central processing unit 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604 .
  • the following components are connected to the I/O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 608 including a hard disk, etc. and a communication section 609 including a network interface card such as a local area network (LAN) card, a modem, or the like.
  • the communication section 609 performs communication processing via a network such as the Internet.
  • a drive 610 is also connected to the I/O interface 605 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 610 as necessary so that a computer program read therefrom is installed into the storage section 608 as necessary.
  • the processes described above with reference to the flowcharts can be implemented as computer software programs.
  • the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts.
  • the computer program may be downloaded and installed from a network via communication portion 609 and/or installed from removable media 611 .
  • the central processing unit 601 When the computer program is executed by the central processing unit 601, various functions defined in the apparatus of the present application are performed.
  • a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above CDN node allocation method is implemented.
  • a computer program is also provided, and when the computer program is executed by a processor, the above CDN node allocation method is implemented.
  • the computer-readable storage medium described in this application may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more conductors, portable computer diskettes, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM) or flash memory), fiber optics, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • Program code contained on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wires, optical cables, radio frequency, etc., or any suitable combination of the above.
  • a computer program product is also provided.
  • the computer program product is run on a computer, the computer is made to execute the above method for allocating CDN nodes.

Abstract

本申请涉及一种CDN节点分配方法、装置、电子设备、介质及程序产品，应用于互联网技术领域，所述方法包括：获取目标网络请求对应的目标物理场景；根据目标物理场景和预先建立的节点质量评分表，确定目标物理场景对应的多个类型的CDN节点的目标质量评分；根据多个类型的CDN节点的目标质量评分，对多个类型的CDN节点的质量进行评估，得到质量评估结果；根据候选CDN节点集合中多个类型的候选CDN节点分别对应的节点数量和质量评估结果，从候选CDN节点集合中选取目标类型的CDN节点，目标类型的候选CDN节点质量最高。

Description

CDN节点分配方法、装置、电子设备、介质及程序产品
相关申请的交叉引用
本申请要求于2021年12月20日提交的名称为“CDN节点分配方法、装置、电子设备、介质及程序产品”的中国专利申请第202111562887.X号的优先权，该申请的公开通过引用被全部结合于此。
技术领域
本申请涉及互联网技术领域，尤其涉及一种CDN节点分配方法、装置、电子设备、介质及程序产品。
背景技术
CDN(Content Delivery Network，内容分发网络)是基于部署在各地的边缘服务器，通过中心平台的负载均衡、内容分发、调度等功能模块，使用户就近获取所需内容，减少网络拥堵，提高用户访问响应速度和命中率。
发明内容
根据本申请的第一方面，提供了一种CDN节点分配方法，包括：
获取目标网络请求对应的目标物理场景；
根据所述目标物理场景和预先建立的节点质量评分表，确定所述目标物理场景对应的多个类型的CDN节点的目标质量评分；其中，所述节点质量评分表包括物理场景分别和所述多个类型的CDN节点的质量评分的映射关系；
根据所述多个类型的CDN节点的目标质量评分，对所述多个类型的CDN节点的质量进行评估，得到质量评估结果；
根据候选CDN节点集合中所述多个类型的候选CDN节点分别对应的节点数量和所述质量评估结果，从所述候选CDN节点集合中选取目标类型的CDN节点，其中，所述目标类型的候选CDN节点质量最高。
可选的，所述方法还包括：
获取多个历史网络数据、单个所述历史网络数据对应的物理场景以及单个所述历史网络数据对应的CDN节点的类型；
根据单个所述历史网络数据，确定单个所述历史网络数据对应的所述类型的CDN节点 的质量评分；
建立单个所述历史网络数据对应的物理场景与所述历史网络数据对应的所述类型的CDN节点的质量评分的映射关系，得到所述节点质量评分表。
可选的，所述历史网络数据包括：历史视频数据；
根据单个所述历史网络数据，确定单个所述历史网络数据对应的所述类型的CDN节点的质量评分，包括：
根据单个所述历史视频数据，获取单个所述历史视频数据的首屏时间和/或卡顿时长和/或卡顿次数；
根据所述首屏时间和/或所述卡顿时长和/或所述卡顿次数，确定所述历史视频数据对应的所述类型的CDN节点的质量评分。
可选的，根据所述首屏时间、所述卡顿时长和所述卡顿次数，确定所述历史视频数据对应的所述类型的CDN节点的质量评分，包括：
将所述首屏时间、所述卡顿时长和所述卡顿次数进行加权平均，得到所述历史视频数据对应的所述类型的CDN节点的质量评分；或者，
基于预先训练的神经网络评分模型，对所述首屏时间、所述卡顿时长和所述卡顿次数进行处理，得到所述历史视频数据对应的所述类型的CDN节点的质量评分。
可选的，所述方法还包括：
将选取的所述目标类型的候选CDN节点从所述候选CDN节点集合中移除；
将当前网络请求确定为目标网络请求，并返回所述获取目标网络请求对应的目标物理场景的步骤，直至所述候选CDN节点的总数量为0。
可选的，所述方法还包括：
根据所述多个类型的CDN节点的总体质量和所述多个类型的CDN节点的成本信息，确定所述候选CDN节点集合中所述多个类型的候选CDN节点分别对应的节点数量。
可选的，所述方法还包括：
通过所述目标类型的CDN节点获取所述目标网络请求对应的请求数据，并将请求数据返回至终端设备。
可选的，所述目标网络请求为视频播放请求，所述目标网络请求对应的目标物理场景包括以下一种或多种：视频热度、视频码率、启动类型、网络类型、网络运营商。
根据本申请的第二方面，提供了一种CDN节点分配装置，包括：
目标物理场景获取模块，用于获取目标网络请求对应的目标物理场景；
目标质量评分确定模块，用于根据所述目标物理场景和预先建立的节点质量评分表，确定所述目标物理场景对应的多个类型的CDN节点的目标质量评分；其中，所述节点质量评分表包括物理场景分别和所述多个类型的CDN节点的质量评分的映射关系；
CDN节点质量评估模块，用于根据所述多个类型的CDN节点的目标质量评分，对所述多个类型的CDN节点的质量进行评估，得到质量评估结果；
候选CDN节点确定模块，用于根据候选CDN节点集合中所述多个类型的候选CDN节点分别对应的节点数量和所述质量评估结果，从所述候选CDN节点集合中选取目标类型的CDN节点，其中，所述目标类型的候选CDN节点质量最高。
可选的，所述CDN节点分配装置还包括：
数据获取模块，用于获取多个历史网络数据、单个所述历史网络数据对应的物理场景以及单个所述历史网络数据对应的CDN节点的类型；
质量评分确定模块，用于根据单个所述历史网络数据，确定单个所述历史网络数据对应的所述类型的CDN节点的质量评分；
节点质量评分表生成模块，用于建立单个所述历史网络数据对应的物理场景与所述历史网络数据对应的所述类型的CDN节点的质量评分的映射关系，得到所述节点质量评分表。
可选的，所述历史网络数据包括：历史视频数据；
所述质量评分确定模块，具体用于根据单个所述历史视频数据，获取单个所述历史视频数据的首屏时间和/或卡顿时长和/或卡顿次数；根据所述首屏时间和/或所述卡顿时长和/或所述卡顿次数，确定所述历史视频数据对应的所述类型的CDN节点的质量评分。
可选的，所述质量评分确定模块通过下述步骤实现根据所述首屏时间、所述卡顿时长和所述卡顿次数，确定所述历史视频数据对应的所述类型的CDN节点的质量评分：
将所述首屏时间、所述卡顿时长和所述卡顿次数进行加权平均，得到所述历史视频数据对应的所述类型的CDN节点的质量评分；或者，
基于预先训练的神经网络评分模型，对所述首屏时间、所述卡顿时长和所述卡顿次数进行处理，得到所述历史视频数据对应的所述类型的CDN节点的质量评分。
可选的，所述CDN节点分配装置还包括：
节点移除模块，用于将选取的所述目标类型的候选CDN节点从所述候选CDN节点集合中移除；
循环模块，用于将当前网络请求确定为目标网络请求，并返回所述目标物理场景获取模块，直至所述候选CDN节点的总数量为0。
可选的，所述CDN节点分配装置还包括：
节点数量确定模块，用于根据所述多个类型的CDN节点的总体质量和所述多个类型的CDN节点的成本信息，确定所述候选CDN节点集合中所述多个类型的候选CDN节点分别对应的节点数量。
可选的，所述CDN节点分配装置还包括：
请求数据获取模块，用于通过所述目标类型的CDN节点获取所述目标网络请求对应的请求数据；
请求数据发送模块，用于将请求数据返回至终端设备。
可选的，所述目标网络请求为视频播放请求，所述目标网络请求对应的目标物理场景包括以下一种或多种：视频热度、视频码率、启动类型、网络类型、网络运营商。
根据本申请的第三方面，提供了一种电子设备，包括：处理器，所述处理器用于执行存储于存储器的计算机程序，所述计算机程序被处理器执行时实现第一方面所述的方法。
根据本申请的第四方面，提供了一种非瞬态的计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现第一方面所述的方法。
根据本申请的第五方面，提供了一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机执行第一方面所述的方法。
根据本申请的第六方面，提供了一种计算机程序，当所述计算机程序被处理器执行时实现第一方面所述的方法。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本申请的实施例，并与说明书一起用于解释本申请的原理。
为了更清楚地说明本申请实施例或相关技术中的技术方案，下面将对实施例或相关技术描述中所需要使用的附图作简单地介绍，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1示出了可以应用于本申请实施例的CDN节点分配方法的示例性应用环境的系统架构的示意图；
图2为本申请实施例中CDN节点分配方法的一种流程图；
图3为本申请实施例中节点质量评分表的建立方法的一种流程图；
图4为本申请实施例中CDN节点分配方法的又一种流程图；
图5为本申请实施例中CDN节点分配装置的一种结构示意图；
图6为本申请实施例中电子设备的一种结构示意图。
具体实施方式
为了能够更清楚地理解本申请的上述目的、特征和优点，下面将对本申请的方案进行进一步描述。需要说明的是，在不冲突的情况下，本申请的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本申请，但本申请还可以采用其他不同于在此描述的方式来实施；显然，说明书中的实施例只是本申请的一部分实施例，而不是全部的实施例。
相关技术中，可以基于不同厂商CDN节点的负载和成本进行CDN节点的选取。然而，基于该方法选取的CDN节点无法为用户提供较高质量的网络服务。
本申请实施例提供的技术方案与相关技术相比具有如下优点：
通过预先建立节点质量评分表，节点质量评分表包括物理场景分别和多个类型的CDN节点的质量评分的映射关系，从而可以在接收到目标网络请求后，根据目标网络请求对应的目标物理场景，确定该目标物理场景对应的多个类型的CDN节点的目标质量评分。根据多个类型的CDN节点的目标质量评分，对多个类型的CDN节点的质量进行评估，得到质量评估结果。例如，评估在目标物理场景下不同厂商CDN节点的质量。进而，可以从候选CDN节点中选取质量最高的CDN节点，以通过选取的候选CDN节点处理目标网络请求。可见，本申请根据不同用户所处的物理场景，为用户选取与该物理场景对应的质量最高的CDN节点，从而充分考虑不同厂商CDN对不同物理场景下终端设备的影响差异，提高CDN节点的服务质量。
图1示出了可以应用于本申请实施例的CDN节点分配方法的示例性应用环境的系统架构的示意图。
如图1所示，系统架构100可以包括终端设备101、终端设备102、终端设备103中的一个或多个，服务器104、CDN节点105、CDN节点106、CDN节点107和CDN节点108 中的多个。系统架构100还可以网络，网络用以在终端设备101、终端设备102、终端设备103和服务器104之间，以及服务器104与CDN节点105、CDN节点106、CDN节点107、CDN节点108之间提供通信链路的介质。网络可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。终端设备101、终端设备102、终端设备103可以是各种电子设备，包括但不限于台式计算机、便携式计算机、智能手机和平板电脑等等。应该理解，图1中的终端设备、网络、CDN节点和服务器的数量仅仅是示意性的。根据实现需要，可以具有任意数量的终端设备、网络、CDN节点和服务器。比如服务器104可以是多个服务器组成的服务器集群等。
本申请实施例所提供的CDN节点分配方法一般由服务器104执行，相应地，CDN节点分配装置可以设置于服务器104中。举例而言，服务器104可以预先建立节点质量评分表，在接收到终端设备101发送的目标网络请求后，基于本申请实施例的CDN节点分配方法，为该目标网络请求分配CDN节点。假设CDN节点105、CDN节点106、CDN节点107、CDN节点108为四种类型的候选CDN节点，分别为第一类CDN节点、第二类CDN节点、第三类CDN节点、第四类CDN节点，根据节点质量评分表，确定该目标网络请求对应的目标物理场景下第二类CDN节点的质量最高，那么将目标网络请求发送至CDN节点106，以通过CDN节点106对该目标网络请求进行处理，并将请求数据发送至终端设备101。通过为不同物理场景下的终端设备选取质量最高的CDN节点，从而可以提高CDN节点的服务质量。
以下首先对本申请实施例的CDN节点分配方法进行详细介绍。
参见图2，图2为本申请实施例中CDN节点分配方法的一种流程图，可以包括以下步骤：
步骤S210，获取目标网络请求对应的目标物理场景。
用户在通过终端设备访问网页时，终端设备会发送对应的网络请求。目标网络请求可以是视频播放请求、数据下载请求等。目标网络请求的请求类型不同，对应的目标物理场景也可以不同。例如，目标网络请求为数据下载请求，目标网络请求对应的目标物理场景包括以下一种或多种：网络类型、网络运营商、省份。
当目标网络请求为视频播放请求时，由于视频热度对CDN节点的服务质量具有较大影响，例如，比较热的视频更倾向于存储在CDN节点上，反之，冷视频由于观看次数较少，可能没有被存储在CDN节点上，视频播放请求更容易发生回源，可能造成更久的首屏时间和更多的卡顿，视频播放质量较低。因此，可以将视频热度作为物理场景中的一个参考因 素。其中，视频热度可以以相对播放次数进行统计，即统计一小时内视频的播放次数，并按照播放次数进行排序，取排序前1％的视频作为热视频，其它视频作为冷视频。
类似的，视频码率(例如720p、540p、480p)和启动类型(冷启动或热启动)对CDN节点的服务质量具有较大影响，也可以将视频码率和启动类型作为物理场景中的参考因素。其中，冷启动指应用软件启动时，后台没有该应用的进程，热启动指应用软件启动时，后台有该应用的进程。可选的，目标网络请求对应的目标物理场景可以包括以下一种或多种：视频热度、视频码率、启动类型、网络类型、网络运营商、省份。
步骤S220，根据目标物理场景和预先建立的节点质量评分表，确定目标物理场景对应的多个类型的CDN节点的目标质量评分。
本申请实施例中，节点质量评分表是根据历史网络数据预先建立的，节点质量评分表包括物理场景分别和多个类型的CDN节点的质量评分的映射关系，用于对不同物理场景下多个类型的CDN节点进行评估。多个类型的CDN节点可以是多个不同厂商的CDN节点，也可以是同一厂商不同类型的CDN节点，还可以是多个不同厂商不同类型的CDN节点。
为了提高节点质量评分表的准确性，建立节点质量评分表时所使用的历史网络数据可以是距离当前最近的网络数据，例如，可以是最近半小时内的网络数据。当然，之后也可以对节点质量评分表进行不断更新，以提高节点质量评分表的准确性。
可以理解的是，在建立节点质量评分表时，物理场景中的参考因素越多，根据节点质量评分表确定目标物理场景对应的多个类型的CDN节点的目标质量评分的准确性越高。因此，可以参考更多的参考因素来建立节点质量评分表，下文将对节点质量评分表的建立过程进行详细描述，在此不再详述。
步骤S230，根据多个类型的CDN节点的目标质量评分，对多个类型的CDN节点的质量进行评估，得到质量评估结果。
将多个类型的CDN节点的目标质量评分进行比较，可以得到多个类型的CDN节点的质量排序结果，从而可以知晓哪一种类型的CDN节点质量较高，哪一种类型的CDN节点质量较低。
假设包含三种类型的CDN节点，第一类CDN节点、第二类CDN节点和第三类CDN节点，对应的目标质量评分分别为6.8、3.7和5.6，目标质量评分越低表示CDN节点的质量越高，因此，可以确定第二类CDN节点质量最高，第三类CDN节点质量次之，第一类CDN节点质量最低。
步骤S240，根据候选CDN节点集合中多个类型的候选CDN节点分别对应的节点数量和质量评估结果，从候选CDN节点集合中选取目标类型的CDN节点。
候选CDN节点集合中包括多个类型的候选CDN节点，每种类型的候选CDN节点具有对应的节点数量，可以从候选CDN节点集合中选取目标类型的候选CDN节点，目标类型的候选CDN节点质量最高。该目标类型是从上述步骤S230中确定得到的。如果目标类型的CDN节点的节点数量为多个，选取其中的任意一个即可。例如，对于上述第一类CDN节点、第二类CDN节点和第三类CDN节点，可以选取第二类CDN节点即可。通过验证，本申请可以使首屏时间降低1.2％，使卡顿时长降低5.1％和卡顿次数降低5.4％。
在选取目标类型的CDN节点后，可以通过目标类型的CDN节点获取目标网络请求对应的请求数据，并将请求数据返回至终端设备。
本申请实施例的CDN节点分配方法，通过预先建立节点质量评分表，节点质量评分表包括物理场景分别和多个类型的CDN节点的质量评分的映射关系，从而可以在接收到目标网络请求后，根据目标网络请求对应的目标物理场景，确定该目标物理场景对应的多个类型的CDN节点的目标质量评分。根据多个类型的CDN节点的目标质量评分，对多个类型的CDN节点的质量进行评估，得到质量评估结果。例如，评估在目标物理场景下不同厂商CDN节点的质量。进而，可以从候选CDN节点中选取质量最高的CDN节点，以通过选取的候选CDN节点处理目标网络请求。可见，本申请根据不同用户所处的物理场景，为用户选取与该物理场景对应的质量最高的CDN节点，从而充分考虑不同厂商CDN对不同物理场景下终端设备的影响差异，提高CDN节点的服务质量。
参见图3，图3为本申请实施例中节点质量评分表的建立方法的一种流程图，可以包括以下步骤：
步骤S310，获取多个历史网络数据、单个历史网络数据对应的物理场景以及单个历史网络数据对应的CDN节点的类型。
针对CDN节点的质量评分可以基于网络请求对应的网络数据确定，不同类型的网络请求对应不同的网络数据。由于要建立物理场景和多个类型的CDN节点的质量评分，因此，还可以获取单个历史网络数据对应的物理场景，以及单个历史网络数据对应的CDN节点的类型，单个历史网络数据对应一个类型的CDN节点，多个历史网络数据可以对应多种不同类型的CDN节点。这样，可以确定物理场景对应的CDN节点的类型。进而，通过确定该类型的CDN节点的质量评分，可以得到物理场景和该类型的CDN节点的质量评分的对应关系。
步骤S320，根据单个历史网络数据，确定单个历史网络数据对应的类型的CDN节点的质量评分。
可以理解的是，针对不同类型的网络数据，评价CDN节点质量的指标通常也可以不同。可选的，历史网络数据包括：历史视频数据；视频数据的质量可以根据视频数据的首屏时间、卡顿时长和卡顿次数等指标确定，而视频数据的质量可以反映CDN节点的质量，因此可以通过视频数据的质量表示CDN节点的质量。
可选的，可以根据单个历史视频数据，获取单个历史视频数据的首屏时间和/或卡顿时长和/或卡顿次数，并根据首屏时间和/或卡顿时长和/或卡顿次数，确定历史视频数据对应的类型的CDN节点的质量评分。其中，首屏时间指浏览器显示第一屏页面所消耗的时间，首屏时间越长，表示视频数据的质量越低。卡顿时长可以是百秒卡顿时长等，百秒卡顿时长指视频内卡顿时长之和与观看时长的比值与100的乘积，百秒卡顿时长月长，表示视频数据的质量越低。卡顿次数可以是百秒卡顿次数，百秒卡顿次数指视频内卡顿次数与观看时长的比值与100的乘积。卡顿次数越多，表示视频数据的质量越低。
可选的，还可以将首屏时间、卡顿时长和卡顿次数进行加权平均，得到历史视频数据对应的该类型的CDN节点的质量评分。例如，历史视频数据对应的该类型的CDN节点的质量评分可以等于首屏时间+α*卡顿时长+β*卡顿次数，其中，α和β的值可以根据经验确定。
或者，也可以基于预先训练的神经网络评分模型，对首屏时间、卡顿时长和卡顿次数进行处理，得到历史视频数据对应的类型的CDN节点的质量评分。神经网络评分模型的训练方法可以是：获取多个类型的CDN节点对应的多个样本视频视频，获取每个样本视频数据的首屏时间、卡顿时长和卡顿次数作为输入，可以根据该样本视频数据的观看时长确定标签数据，训练生成神经网络评分模型。
步骤S330，建立单个历史网络数据对应的物理场景与历史网络数据对应的该类型的CDN节点的质量评分的映射关系，得到节点质量评分表。
在确定单个历史网络数据对应的CDN节点的类型和该类型的CDN节点的质量评分后，可以建立单个历史网络数据对应的物理场景与该类型的CDN节点的质量评分的映射关系。单个历史网络数据，可以建立一个物理场景和一个类型的CDN节点的质量评分的映射关系。通过多个历史网络数据，可以得到同一个物理场景对应的多个类型的CDN节点的质量评分的映射关系，从而得到节点质量评分表。
在生成节点质量评分表后，可以接收网络请求后，可以直接根据网络请求对应的物理场景，确定多个类型的CDN节点的质量评分，从而对多个类型的CDN节点的质量进行评估，以选取质量最高的类型的CDN节点。
参见图4，图4为本申请实施例中CDN节点分配方法的又一种流程图，可以包括以下步骤：
步骤S410，获取目标网络请求对应的目标物理场景。
在实际场景下，多个不同的终端设备通常会访问同一个网站，此时，多个终端设备均会发送目标网络请求，或者，同一设备在不同时刻也可以发送多个目标网络请求，服务器可以通过下述循环过程分别对多个目标网络请求进行处理。
步骤S420，根据目标物理场景和预先建立的节点质量评分表，确定目标物理场景对应的多个类型的CDN节点的目标质量评分；其中，节点质量评分表包括物理场景分别和多个类型的CDN节点的质量评分的映射关系。
步骤S430，根据多个类型的CDN节点的目标质量评分，对多个类型的CDN节点的质量进行评估，得到质量评估结果。
步骤S440，判断候选CDN节点集合中多个类型的候选CDN节点的总节点数量是否大于0。
候选CDN节点集合中可以预先分配有多个类型的CDN节点，每个类型的CDN节点均对应有一定的节点数量。不同类型的CDN节点由于性能差异成本也会不同，因此，可以在不增加成本的前提下为每个终端设备选取质量最高的CDN节点。可选的，可以根据多个类型的CDN节点的总体质量和多个类型的CDN节点的成本信息(例如价格等)，确定候选CDN节点集合中多个类型的候选CDN节点分别对应的节点数量。需要说明的是，总体质量是对多个类型的CDN节点进行整体评价之后得到的，与不同物理场景下对应的多个类型的CDN节点的质量可能略有不同。比如，第一类CDN节点的总体质量最高，但根据某一物理场景下对应的第一类CDN节点的质量评分，可能不是最高。
例如，候选CDN节点集合中包括三个类型的候选CDN节点，第一类候选CDN节点、第二类候选CDN节点和第三类候选CDN节点，对应的总体质量和成本信息均依次降低，在不增加成本的前提下，对应的节点数量分别可以为1000、2000和7000，候选CDN节点集合中多个类型的候选CDN节点的总节点数量是10000。
如果候选CDN节点集合中多个类型的候选CDN节点的总节点数量大于0，表示当前还 存在可以选取的候选CDN节点，可以执行下述步骤S450；如果候选CDN节点集合中多个类型的候选CDN节点的总节点数量等于0，表示当前不存在可以选取的候选CDN节点，流程结束。或者，也可以在候选CDN节点集合中添加新的候选CDN节点之后，继续执行下述步骤S450。
步骤S450，根据候选CDN节点集合中多个类型的候选CDN节点分别对应的节点数量和质量评估结果，从候选CDN节点集合中选取目标类型的CDN节点，其中，目标类型的候选CDN节点质量最高。
在从候选CDN节点集合中选取候选CDN节点之前，第一类候选CDN节点、第二类候选CDN节点和第三类候选CDN节点对应的节点数量分别为1000、2000和7000，此时可以直接选取质量最高的类型的候选CDN节点。
假设经过多次循环之后，已经从候选CDN节点集合中选取了多个候选CDN节点，第一类候选CDN节点、第二类候选CDN节点和第三类候选CDN节点对应的节点数量分别为50、0和1000，即使步骤S430中确定第二类CDN节点的质量最高，由于候选CDN节点集合中第二类候选CDN节点的节点数量为0，也无法选取第二类候选CDN节点。如果根据步骤S430确定第一类CDN节点的质量高于第三类CDN节点的质量，可以从剩余50个第一类候选CDN节点中选取其中一个即可。
步骤S460，将选取的目标类型的候选CDN节点从候选CDN节点集合中移除。
在每次选取完成之后，可以将所选取的候选CDN节点从候选CDN节点集合中移除，这样，下次就可以不再选取该候选CDN节点。
步骤S470，将当前网络请求确定为目标网络请求，并返回步骤S410，直至候选CDN节点的总数量为0。
本申请实施例的CDN节点分配方法，通过预先建立节点质量评分表，节点质量评分表包括物理场景分别和多个类型的CDN节点的质量评分的映射关系，从而可以在接收到各个目标网络请求后，根据各个目标网络请求对应的目标物理场景，确定各个目标物理场景对应的多个类型的CDN节点的目标质量评分。根据多个类型的CDN节点的目标质量评分，对多个类型的CDN节点的质量进行评估，得到质量评估结果。例如，评估在目标物理场景下不同厂商CDN节点的质量。进而，可以从候选CDN节点集合中选取质量最高的候选CDN节点，以通过选取的候选CDN节点处理目标网络请求。其中，候选CDN节点集合中各个类型的候选CDN节点的节点数量可以根据各个类型的候选CDN节点的总体质量和成本信息确定， 从而可以在不增加成本的情况下，根据不同用户所处的物理场景，为用户选取与该物理场景对应的质量最高的CDN节点，从而充分考虑不同厂商CDN对不同物理场景下终端设备的影响差异，提高CDN节点的服务质量。
相应于上述方法实施例，本申请实施例还提供了一种CDN节点分配装置，参见图5，CDN节点配置装置500包括：
目标物理场景获取模块510，用于获取目标网络请求对应的目标物理场景；
目标质量评分确定模块520，用于根据目标物理场景和预先建立的节点质量评分表，确定目标物理场景对应的多个类型的CDN节点的目标质量评分；其中，节点质量评分表包括物理场景分别和多个类型的CDN节点的质量评分的映射关系；
CDN节点质量评估模块530，用于根据多个类型的CDN节点的目标质量评分，对多个类型的CDN节点的质量进行评估，得到质量评估结果；
候选CDN节点确定模块540，用于根据候选CDN节点集合中多个类型的候选CDN节点分别对应的节点数量和质量评估结果，从候选CDN节点集合中选取目标类型的CDN节点，其中，目标类型的候选CDN节点质量最高。
可选的，CDN节点分配装置500还包括：
数据获取模块，用于获取多个历史网络数据、单个历史网络数据对应的物理场景以及单个历史网络数据对应的CDN节点的类型；
质量评分确定模块，用于根据单个历史网络数据，确定单个历史网络数据对应的类型的CDN节点的质量评分；
节点质量评分表生成模块，用于建立单个历史网络数据对应的物理场景与历史网络数据对应的类型的CDN节点的质量评分的映射关系，得到节点质量评分表。
可选的，历史网络数据包括：历史视频数据；
质量评分确定模块，具体用于根据单个历史视频数据，获取单个历史视频数据的首屏时间和/或卡顿时长和/或卡顿次数；根据首屏时间和/或卡顿时长和/或卡顿次数，确定历史视频数据对应的类型的CDN节点的质量评分。
可选的，质量评分确定模块通过下述步骤实现根据首屏时间、卡顿时长和卡顿次数，确定历史视频数据对应的类型的CDN节点的质量评分：
将首屏时间、卡顿时长和卡顿次数进行加权平均，得到历史视频数据对应的类型的CDN节点的质量评分；或者，
基于预先训练的神经网络评分模型，对首屏时间、卡顿时长和卡顿次数进行处理，得到历史视频数据对应的类型的CDN节点的质量评分。
可选的，CDN节点分配装置500还包括：
节点移除模块，用于将选取的目标类型的候选CDN节点从候选CDN节点集合中移除；
循环模块，用于将当前网络请求确定为目标网络请求，并返回目标物理场景获取模块，直至候选CDN节点的总数量为0。
可选的，CDN节点分配装置500还包括：
节点数量确定模块，用于根据多个类型的CDN节点的总体质量和多个类型的CDN节点的成本信息，确定候选CDN节点集合中多个类型的候选CDN节点分别对应的节点数量。
可选的，CDN节点分配装置还包括：
请求数据获取模块，用于通过目标类型的CDN节点获取目标网络请求对应的请求数据；
请求数据发送模块，用于将请求数据返回至终端设备。
可选的，目标网络请求为视频播放请求，目标网络请求对应的目标物理场景包括以下一种或多种：视频热度、视频码率、启动类型、网络类型、网络运营商。
上述装置中各模块或单元的具体细节已经在对应的方法中进行了详细的描述，因此此处不再赘述。
应当注意，尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元，但是这种划分并非强制性的。实际上，根据本申请的实施方式，上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之，上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体化。
在本申请的示例性实施例中，还提供一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，处理器被配置为执行本示例实施方式中上述CDN节点分配方法。
图6为本申请实施例中电子设备的一种结构示意图。需要说明的是，图6示出的电子设备600仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。本申请实施例中的电子设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。
如图6所示，电子设备600包括中央处理单元(CPU)601，其可以根据存储在只读存 储器(ROM)602中的程序或者从存储部分608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有系统操作所需的各种程序和数据。中央处理单元601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
以下部件连接至I/O接口605：包括键盘、鼠标等的输入部分606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分607；包括硬盘等的存储部分608；以及包括诸如局域网(LAN)卡、调制解调器等的网络接口卡的通信部分609。通信部分609经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口605。可拆卸介质611，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器610上，以便于从其上读出的计算机程序根据需要被安装入存储部分608。
特别地，根据本申请的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本申请的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分609从网络上被下载和安装，和/或从可拆卸介质611被安装。在该计算机程序被中央处理单元601执行时，执行本申请的装置中限定的各种功能。
本申请实施例中，还提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述CDN节点分配方法。
本申请实施例中，还提供了一种计算机程序，当所述计算机程序被处理器执行时实现上述CDN节点分配方法。
需要说明的是，本申请所示的计算机可读存储介质例如可以是—但不限于—电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器、只读存储器、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。计算机可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、射频等等，或者上述的任意合适的组合。
本申请实施例中，还提供了一种计算机程序产品，当计算机程序产品在计算机上运行时，使得计算机执行上述CDN节点分配方法。
需要说明的是，在本文中，诸如“第一”和“第二”等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅是本申请的具体实施方式，使本领域技术人员能够理解或实现本申请。对这些实施例的多种修改对本领域的技术人员来说将是清楚的，本文中所定义的一般原理可以在不脱离本申请的精神或范围的情况下，在其它实施例中实现。因此，本申请将不会被限制于本文所述的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。

Claims (13)

  1. 一种内容分发网络CDN节点分配方法，所述方法包括：
    获取目标网络请求对应的目标物理场景；
    根据所述目标物理场景和预先建立的节点质量评分表，确定所述目标物理场景对应的多个类型的CDN节点的目标质量评分；其中，所述节点质量评分表包括物理场景分别和所述多个类型的CDN节点的质量评分的映射关系；
    根据所述多个类型的CDN节点的目标质量评分，对所述多个类型的CDN节点的质量进行评估，得到质量评估结果；
    根据候选CDN节点集合中所述多个类型的候选CDN节点分别对应的节点数量和所述质量评估结果，从所述候选CDN节点集合中选取目标类型的CDN节点，其中，所述目标类型的候选CDN节点质量最高。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    获取多个历史网络数据、单个所述历史网络数据对应的物理场景以及单个所述历史网络数据对应的CDN节点的类型；
    根据单个所述历史网络数据，确定单个所述历史网络数据对应的所述类型的CDN节点的质量评分；
    建立单个所述历史网络数据对应的物理场景与所述历史网络数据对应的所述类型的CDN节点的质量评分的映射关系，得到所述节点质量评分表。
  3. 根据权利要求2所述的方法，其中，所述历史网络数据包括：历史视频数据；
    根据单个所述历史网络数据，确定单个所述历史网络数据对应的所述类型的CDN节点的质量评分，包括：
    根据单个所述历史视频数据，获取单个所述历史视频数据的首屏时间和/或卡顿时长和/或卡顿次数；
    根据所述首屏时间和/或所述卡顿时长和/或所述卡顿次数，确定所述历史视频数据对应的所述类型的CDN节点的质量评分。
  4. 根据权利要求3所述的方法，其中，根据所述首屏时间、所述卡顿时长和所述卡顿次数，确定所述历史视频数据对应的所述类型的CDN节点的质量评分，包括：
    将所述首屏时间、所述卡顿时长和所述卡顿次数进行加权平均，得到所述历史视频数 据对应的所述类型的CDN节点的质量评分；或者，
    基于预先训练的神经网络评分模型，对所述首屏时间、所述卡顿时长和所述卡顿次数进行处理，得到所述历史视频数据对应的所述类型的CDN节点的质量评分。
  5. 根据权利要求1或2所述的方法，其中，所述方法还包括：
    将选取的所述目标类型的候选CDN节点从所述候选CDN节点集合中移除；
    将当前网络请求确定为目标网络请求，并返回所述获取目标网络请求对应的目标物理场景的步骤，直至所述候选CDN节点的总数量为0。
  6. 根据权利要求1或2所述的方法，其中，所述方法还包括：
    根据所述多个类型的CDN节点的总体质量和所述多个类型的CDN节点的成本信息，确定所述候选CDN节点集合中所述多个类型的候选CDN节点分别对应的节点数量。
  7. 根据权利要求1或2所述的方法，其中，所述方法还包括：
    通过所述目标类型的CDN节点获取所述目标网络请求对应的请求数据，并将请求数据返回至终端设备。
  8. 根据权利要求1所述的方法，其中，所述目标网络请求为视频播放请求，所述目标网络请求对应的目标物理场景包括以下一种或多种：视频热度、视频码率、启动类型、网络类型、网络运营商。
  9. 一种内容分发网络CDN节点分配装置，所述装置包括：
    目标物理场景获取模块，用于获取目标网络请求对应的目标物理场景；
    目标质量评分确定模块，用于根据所述目标物理场景和预先建立的节点质量评分表，确定所述目标物理场景对应的多个类型的CDN节点的目标质量评分；其中，所述节点质量评分表包括物理场景分别和所述多个类型的CDN节点的质量评分的映射关系；
    CDN节点质量评估模块，用于根据所述多个类型的CDN节点的目标质量评分，对所述多个类型的CDN节点的质量进行评估，得到质量评估结果；
    候选CDN节点确定模块，用于根据候选CDN节点集合中所述多个类型的候选CDN节点分别对应的节点数量和所述质量评估结果，从所述候选CDN节点集合中选取目标类型的CDN节点，其中，所述目标类型的候选CDN节点质量最高。
  10. 一种电子设备，包括：处理器，所述处理器用于执行存储于存储器的计算机程序，所述计算机程序被处理器执行时实现如权利要求1-8中任一项所述的方法。
  11. 一种非瞬态的计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-8中任一项所述的方法。
  12. 一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得所述计算机执行如权利要求1-8中任一项所述的方法。
  13. 一种计算机程序，当所述计算机程序被处理器执行时实现如权利要求1-8中任一项所述的方法。
PCT/CN2022/129267 2021-12-20 2022-11-02 Cdn节点分配方法、装置、电子设备、介质及程序产品 WO2023116219A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111562887.XA CN114268672B (zh) 2021-12-20 2021-12-20 Cdn节点分配方法、装置、电子设备、介质及程序产品
CN202111562887.X 2021-12-20

Publications (1)

Publication Number Publication Date
WO2023116219A1 true WO2023116219A1 (zh) 2023-06-29

Family

ID=80828115

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/129267 WO2023116219A1 (zh) 2021-12-20 2022-11-02 Cdn节点分配方法、装置、电子设备、介质及程序产品

Country Status (2)

Country Link
CN (1) CN114268672B (zh)
WO (1) WO2023116219A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114268672B (zh) * 2021-12-20 2024-01-12 北京字节跳动网络技术有限公司 Cdn节点分配方法、装置、电子设备、介质及程序产品
CN114745565B (zh) * 2022-04-14 2023-10-20 上海哔哩哔哩科技有限公司 边缘节点的调度方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107911722A (zh) * 2017-10-31 2018-04-13 链家网（北京）科技有限公司 一种内容分发网络调度方法及装置
CN108563499A (zh) * 2018-04-27 2018-09-21 努比亚技术有限公司 Cdn服务器切换方法、移动终端及计算机可读存储介质
CN110891077A (zh) * 2018-09-07 2020-03-17 阿里巴巴集团控股有限公司 Cdn节点检测方法及装置
CN111901425A (zh) * 2020-07-28 2020-11-06 平安科技（深圳）有限公司 基于Pareto算法的CDN调度方法、装置、计算机设备及存储介质
CN114268672A (zh) * 2021-12-20 2022-04-01 北京字节跳动网络技术有限公司 Cdn节点分配方法、装置、电子设备、介质及程序产品

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9544346B1 (en) * 2014-06-06 2017-01-10 Amazon Technologies, Inc. Systems and methods for selecting a node for media streaming
CN106034330B (zh) * 2015-03-17 2019-08-02 网宿科技股份有限公司 基于内容分发网络的移动终端流量处理方法、装置及系统
CN105898402A (zh) * 2015-11-13 2016-08-24 乐视云计算有限公司 网络调度方法和系统
CN106231365B (zh) * 2016-08-18 2019-08-06 北京斗牛科技有限公司 一种调度方法和系统
US11049012B2 (en) * 2017-11-21 2021-06-29 Fair Isaac Corporation Explaining machine learning models by tracked behavioral latent features
CN108306769B (zh) * 2018-01-31 2021-08-20 北京奇艺世纪科技有限公司 一种cdn的节点部署控制方法和系统
TR201811297A2 (tr) * 2018-08-03 2018-08-27 Medianova Internet Hizmetleri Ve Ticaret Anonim Sirketi CDN Şirketlerinin Kullanıcılara Verdikleri Kaliteyi Geliştirmek Ve Kaynak Kullanımını Optimize Etmek İçin Kullanılan Sistem
CN109831511B (zh) * 2019-02-18 2020-10-23 华为技术有限公司 调度内容分发网络cdn边缘节点的方法及设备
CN110708256B (zh) * 2019-08-26 2023-05-02 中移（杭州）信息技术有限公司 Cdn调度方法、装置、网络设备及存储介质
CN110636339B (zh) * 2019-09-30 2022-11-15 北京字节跳动网络技术有限公司 基于码率的调度方法、装置及电子设备
CN110944061A (zh) * 2019-12-06 2020-03-31 北京博睿宏远数据科技股份有限公司 内容分发网络调度方法、装置、计算机设备及存储介质
CN112749974A (zh) * 2021-01-29 2021-05-04 腾讯科技（深圳）有限公司 一种交易数据处理方法、装置、设备及存储介质
CN113099261B (zh) * 2021-04-27 2023-04-18 上海哔哩哔哩科技有限公司 节点处理方法及装置、节点处理系统
CN113505854B (zh) * 2021-07-29 2023-08-15 济南博观智能科技有限公司 一种人脸图像质量评价模型构建方法、装置、设备及介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107911722A (zh) * 2017-10-31 2018-04-13 链家网（北京）科技有限公司 一种内容分发网络调度方法及装置
CN108563499A (zh) * 2018-04-27 2018-09-21 努比亚技术有限公司 Cdn服务器切换方法、移动终端及计算机可读存储介质
CN110891077A (zh) * 2018-09-07 2020-03-17 阿里巴巴集团控股有限公司 Cdn节点检测方法及装置
CN111901425A (zh) * 2020-07-28 2020-11-06 平安科技（深圳）有限公司 基于Pareto算法的CDN调度方法、装置、计算机设备及存储介质
CN114268672A (zh) * 2021-12-20 2022-04-01 北京字节跳动网络技术有限公司 Cdn节点分配方法、装置、电子设备、介质及程序产品

Also Published As

Publication number Publication date
CN114268672B (zh) 2024-01-12
CN114268672A (zh) 2022-04-01

Similar Documents

Publication Publication Date Title
WO2023116219A1 (zh) Cdn节点分配方法、装置、电子设备、介质及程序产品
US20200304483A1 (en) Authentication mechanism
CN112087644B (zh) 拉流请求处理方法、装置、系统、电子设备和存储介质
CN108307207A (zh) 一种视频推送方法及装置
WO2020107624A1 (zh) 信息推送方法、装置、电子设备及计算机可读存储介质
CN109862100B (zh) 用于推送信息的方法和装置
KR101783431B1 (ko) 크라우드 펀딩 시스템을 통해 엔터테인먼트 관련 펀딩 정보 및 컨설팅 정보를 제공하는 방법
WO2020094036A1 (zh) 用于终端的无线网络连接方法
CN111246302B (zh) 浏览器下载数据的方法、装置和终端
CN110781373B (zh) 榜单更新方法、装置、可读介质和电子设备
CN109635986A (zh) 门店推送方法、装置、设备及存储介质
CN108600780B (zh) 用于推送信息的方法、电子设备、计算机可读介质
CN111209306A (zh) 业务逻辑判断方法、装置、电子设备和存储介质
CN108282668B (zh) 一种视频的获取方法及系统
WO2015035957A1 (zh) 一种视频资源获取方法、后台服务器、视频客户端及系统
CN109639813B (zh) 视频文件传输处理方法及装置、电子设备和存储介质
CN111178781A (zh) 在线应答系统的应答资源分配方法、装置、设备及介质
CN114003337A (zh) 访问请求的分配方法及装置
CN110083771A (zh) 一种信息推送的方法、装置、设备和介质
CN106817296B (zh) 信息推荐的测试方法、装置以及电子设备
CN111262744B (zh) 多媒体信息发送方法、备份服务器及介质
CN110913270A (zh) 直播方法和装置
WO2022183940A1 (zh) 推荐内容资源的获取方法、装置、设备、介质及程序产品
CN109804349B (zh) 用于减少下载要求的系统和方法
WO2020078049A1 (zh) 用户信息处理方法和装置、服务器及可读介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22909536

Country of ref document: EP

Kind code of ref document: A1