Source return scheduling method and device and computing equipment

Abstract

The invention discloses a back-to-source scheduling method, a back-to-source scheduling device and computing equipment. The method comprises the following steps: receiving a back-to-source request of a target client; determining a target scheduling mode corresponding to the back-to-source request from the plurality of scheduling modes according to mode quality values of the plurality of scheduling modes, wherein the mode quality values are generated by client back-to-source quality index values belonging to the corresponding scheduling modes in a historical time period; candidate nodes matched with the back-to-source request and belonging to the target scheduling mode are screened, node quality values of the candidate nodes are obtained, and the node quality values are generated by client back-to-source quality index values belonging to the corresponding back-to-source nodes in the historical time period; and determining a target back-to-source node from the candidate nodes according to the node quality value. According to the scheme, back-to-source scheduling is performed according to the back-to-source quality index value of the client side, so that the user experience can be improved; and the target scheduling mode is dynamically determined from the plurality of scheduling modes according to the mode quality value, so that the back-to-source scheduling precision and the system resource utilization rate are improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and specifically to a back-to-source scheduling method, apparatus, computing device, computer storage medium, and computer program product. Background Art

[0002] Content Delivery Network (CDN) is a network that places service nodes in multiple locations, with one or more service nodes processing user requests. In application scenarios such as live broadcast and on-demand, the content delivery network will go back to the source when processing user requests, that is, transmit the resources requested by the user to the client through one or more nodes in the content delivery network.

[0003] However, the inventors found that the prior art has the following defects during implementation: the prior art performs back-to-source scheduling based on node load and node-client distance. Using this back-to-source scheduling scheme in the prior art, the user experience on the client side is poor and resource utilization is insufficient. Summary of the invention

[0004] In view of the above problems, the present application is proposed to provide a back-to-source scheduling method, apparatus, computing device, computer storage medium and computer program product that overcome the above problems or at least partially solve the above problems.

[0005] According to a first aspect of the present application, a back-to-source scheduling method is provided, including:

[0006] Receive the target client's back-to-origin request;

[0007] Determining a target scheduling mode corresponding to the back-to-source request from the multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes; wherein the mode quality value is generated by a back-to-source quality indicator value of a client belonging to the corresponding scheduling mode in a historical period;

[0008] Selecting candidate nodes that match the back-to-source request and belong to the target scheduling mode from the back-to-source nodes, and obtaining node quality values ​​of the candidate nodes; wherein the node quality values ​​are generated by the back-to-source quality index values ​​of the clients belonging to the corresponding back-to-source nodes in the historical period;

[0009] A target back-to-source node corresponding to the back-to-source request is determined from the candidate nodes according to the node quality value.

[0010] In an optional embodiment, the method further includes:

[0011] Receive the client's client return quality indicator value;

[0012] Assign corresponding node labels, scheduling mode labels, and timestamp labels to the client back-to-source quality indicator values;

[0013] The client back-to-source quality indicator includes at least one of the following indicators: a freeze indicator, an error indicator, and a first frame time consumption indicator.

[0014] In an optional implementation manner, the node quality value is generated in the following manner:

[0015] For any back-to-source node, obtain a client back-to-source quality indicator value whose timestamp label is within the first historical period and whose node label matches the back-to-source node;

[0016] The node quality value of the back-to-source node is calculated based on the matched client back-to-source quality indicator value.

[0017] In an optional implementation, the mode quality value is generated in the following manner:

[0018] For any scheduling mode, obtaining a client back-to-source quality indicator value whose timestamp tag is within the second historical period and whose scheduling mode tag matches the scheduling mode;

[0019] The mode quality value of the scheduling mode is calculated based on the matched client back-to-source quality indicator value.

[0020] In an optional implementation, the method further includes: determining priorities of the multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes;

[0021] The determining of the target scheduling mode corresponding to the return request from the multiple scheduling modes according to the mode quality values ​​of the multiple scheduling modes includes:

[0022] A target scheduling method corresponding to the back-to-source request is determined from the multiple scheduling methods according to the priority of the scheduling method.

[0023] In an optional implementation, determining the target scheduling mode corresponding to the back-to-source request from the multiple scheduling modes according to the priority of the scheduling mode includes:

[0024] Taking the scheduling method with the highest priority as the target scheduling method;

[0025] Determine whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode;

[0026] If yes, taking the back-to-source node that belongs to the target scheduling mode and matches the back-to-source request as a candidate node;

[0027] If not, the target scheduling mode is updated to a scheduling mode with a priority second only to the current target scheduling mode, and the step of determining whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode is performed.

[0028] In an optional implementation, the scheduling mode is divided according to node coverage and / or operator, and each scheduling mode has a corresponding node range label and operator similarity and difference label;

[0029] The step of selecting candidate nodes that match the return-to-source request and belong to the target scheduling mode from the return-to-source nodes includes:

[0030] Filter out candidate nodes from the back-to-source nodes that match the back-to-source request, whose coverage matches the node coverage label of the target scheduling method, and whose operator difference results between the node and the target client are consistent with the operator difference label of the target scheduling method;

[0031] Among them, the scheduling method includes at least multiple of the following methods: provincial coverage of the same operator, regional coverage of the same operator, national coverage of the same operator, provincial coverage across operators, regional coverage across operators, and national coverage across operators.

[0032] According to a second aspect of the present application, a back-to-source scheduling device is provided, including:

[0033] The receiving module is used to receive the return request from the target client;

[0034] A scheduling mode determination module, configured to determine a target scheduling mode corresponding to the back-to-source request from among the multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes; wherein the mode quality value is generated by a back-to-source quality indicator value of a client belonging to the corresponding scheduling mode in a historical period;

[0035] A node determination module is used to filter out candidate nodes that match the back-to-source request and belong to the target scheduling method from the back-to-source nodes, and obtain the node quality value of the candidate node; wherein the node quality value is generated by the client back-to-source quality indicator value belonging to the corresponding back-to-source node in a historical period; and determine the target back-to-source node corresponding to the back-to-source request from the candidate nodes according to the node quality value.

[0036] In an optional implementation, the receiving module is used to: receive a client back-to-source quality indicator value of the client;

[0037] The device also includes: an allocation module, which is used to allocate corresponding node labels, scheduling mode labels and timestamp labels to the client back-to-source quality indicator value;

[0038] The client back-to-source quality indicator includes at least one of the following indicators: a freeze indicator, an error indicator, and a first frame time consumption indicator.

[0039] In an optional implementation, the device further includes: a node quality value calculation module, configured to obtain, for any back-to-source node, a client back-to-source quality index value whose timestamp label is within the first historical period and whose node label matches the back-to-source node;

[0040] The node quality value of the back-to-source node is calculated based on the matched client back-to-source quality indicator value.

[0041] In an optional implementation, the device further includes: a mode quality value calculation module, configured to obtain, for any scheduling mode, a client back-to-source quality indicator value whose timestamp tag is within the second historical period and whose scheduling mode tag matches the scheduling mode;

[0042] The mode quality value of the scheduling mode is calculated based on the matched client back-to-source quality indicator value.

[0043] In an optional implementation, the device further includes: a priority determination module, configured to determine priorities of multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes;

[0044] The scheduling mode determination module is used to determine the target scheduling mode corresponding to the back-to-source request from the multiple scheduling modes according to the priority of the scheduling mode.

[0045] In an optional implementation, the scheduling mode determination module is used to: use the scheduling mode with the highest priority as the target scheduling mode;

[0046] Determine whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode;

[0047] If yes, taking the back-to-source node that belongs to the target scheduling mode and matches the back-to-source request as a candidate node;

[0048] If not, the target scheduling mode is updated to a scheduling mode with a priority second only to the current target scheduling mode, and the step of determining whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode is performed.

[0049] In an optional implementation, the scheduling mode is divided according to node coverage and / or operator, and each scheduling mode has a corresponding node range label and operator similarity and difference label;

[0050] The node determination module is used to: select candidate nodes that match the return request from the return-to-source nodes, whose coverage matches the node coverage label of the target scheduling mode, and whose operator similarity and difference results between the node and the target client are consistent with the operator similarity and difference label of the target scheduling mode;

[0051] Among them, the scheduling method includes at least multiple of the following methods: provincial coverage of the same operator, regional coverage of the same operator, national coverage of the same operator, provincial coverage across operators, regional coverage across operators, and national coverage across operators.

[0052] According to a third aspect of the present application, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0053] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned back-to-source scheduling method.

[0054] According to a fourth aspect of the present application, a computer storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned back-to-source scheduling method.

[0055] According to a fifth aspect of the present application, a computer program product is provided, comprising at least one executable instruction, wherein the executable instruction enables a processor to perform operations corresponding to the above-mentioned back-to-source scheduling method.

[0056] The embodiment of the present application generates a method quality value of the scheduling method and a node quality value of the back-to-source node according to the client back-to-source quality indicator value, so as to reflect the advantages and disadvantages of the scheduling method and the back-to-source node from the user experience dimension, and then the target back-to-source node obtained according to the method quality value and the node quality value can match the user experience and improve the user experience; and the present application provides multiple scheduling methods, and dynamically determines the most matching target scheduling method according to the method quality value of the scheduling method, thereby not only improving the back-to-source scheduling accuracy, but also making full use of system resources and improving the system resource utilization rate.

[0057] After receiving the client back-to-source quality index value, the embodiment of the present application assigns a corresponding node label, a scheduling method label and a timestamp label to it, thereby being able to quickly and accurately filter out the data required for calculating the node quality value based on the node label and the timestamp label, and being able to quickly and accurately filter out the data required for calculating the method quality value based on the scheduling method label and the timestamp label, thereby improving the calculation efficiency and accuracy of the node quality value and the method quality value.

[0058] The embodiment of the present application generates the priority of the scheduling method in advance according to the method quality value of the scheduling method, so that the target scheduling method can be quickly determined according to the priority of the scheduling method, thereby improving the processing efficiency of the back-to-source request.

[0059] The embodiment of the present application divides multiple scheduling methods according to node coverage and / or operators, thereby improving the rationality of the scheduling method and further improving the utilization rate of system resources.

[0060] The embodiment of the present application screens candidate nodes based on node coverage labels and operator difference result labels, which can improve the screening accuracy and efficiency of candidate nodes.

[0061] The embodiment of the present application uses the jamming index, error index and first frame time consumption index as the client back-to-source quality index, so that the back-to-source experience of the user on the client can be accurately reflected through the client back-to-source quality index.

[0062] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0064] Figure 1 A schematic diagram of an operating environment provided for implementing at least one embodiment of the present application is shown;

[0065] Figure 2 A flowchart of a back-to-source scheduling method provided in Embodiment 1 of the present application is shown;

[0066] Figure 3 A flowchart of a back-to-source scheduling method provided in Embodiment 2 of the present application is shown;

[0067] Figure 4 A flowchart of a back-to-source scheduling method provided in Embodiment 3 of the present application is shown;

[0068] Figure 5 A schematic diagram of the structure of a back-to-source scheduling device provided in Embodiment 4 of the present application is shown;

[0069] Figure 6 A schematic diagram of the structure of a computing device provided in Embodiment 5 of the present application is shown. DETAILED DESCRIPTION

[0070] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0071] It should be noted that the client back-to-source quality indicator values ​​involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0072] Figure 1 The present invention is applicable to an application environment including, but not limited to, a client 2 , a server 4 , and a network 6 .

[0073] in:

[0074] The server 4 may be composed of a single or multiple computing devices. The multiple computing devices may include virtualized computing instances. Virtualized computing instances may include virtual machines, such as simulations of computer systems, operating systems, servers, etc. The computing device may load a virtual machine based on a virtual image and / or other data defining specific software (e.g., operating system, dedicated application, server) for simulation. As the demand for different types of processing services changes, different virtual machines may be loaded and / or terminated on one or more computing devices. A hypervisor may be implemented to manage the use of different virtual machines on the same computing device.

[0075] The server 4 may be configured to communicate with the client 2, etc., via a network 6. The network 6 includes various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and / or the like. The network 6 may include physical links, such as coaxial cable links, twisted pair cable links, optical fiber links, combinations thereof, etc., or wireless links, such as cellular links, satellite links, Wi-Fi links, etc.

[0076] The server 4 can provide storage, reading, downloading, writing, querying, deleting and other services, such as providing static resource download services to clients through multiple domain names.

[0077] Client 2 can be running Windows, Android TM) or IOS and other operating systems, such as smart phones, tablet devices, laptop computers, virtual reality devices, gaming devices, set-top boxes, car terminals, smart TVs. Based on the above operating systems, various applications, such as browsers, can be run.

[0078] Embodiment 1

[0079] Figure 2 A flow chart of a back-to-source scheduling method provided in the first embodiment of the present application is shown. The back-to-source scheduling method can be executed on the server side, for example, it can be applied to CDN (Content Distribution Network).

[0080] like Figure 2 As shown, the method specifically comprises the following steps:

[0081] Step S202: receiving a back-to-source request from a target client.

[0082] When the user wants to obtain the corresponding resources, he will initiate a back-to-source request to the server through the relevant operations of the client, so that the server can determine the back-to-source node that provides the back-to-source service to the client, and then the client can obtain resources from the corresponding back-to-source node. The embodiment of the present application mainly provides a solution for scheduling the back-to-source node for the current client. The client whose back-to-source node is currently to be determined is called the target client. For example, in a live broadcast scene or a video-on-demand scene, when the audience user wants to view a live stream or a video file, the back-to-source request can be triggered through the corresponding operation in the client. The client is called the target client, and the server determines the target back-to-source node that provides the back-to-source service to the target client through the implementation of the embodiment of the present application.

[0083] Step S202, determining a target scheduling method corresponding to the back-to-source request from multiple scheduling methods according to method quality values ​​of the multiple scheduling methods; wherein the method quality value is generated by a client back-to-source quality indicator value belonging to the corresponding scheduling method in a historical period.

[0084] In the back-to-source scheduling scheme of the prior art, both the node load and the node-client distance are server-side data, which cannot meet the needs of the client-side users and result in a poor user experience.

[0085] In view of the technical drawbacks of poor user experience in the prior art, the embodiment of the present application introduces the client-side back-to-source feedback data, which is specifically the client back-to-source quality index value. The client back-to-source quality index value is a specific value of an indicator used to detect the client-side back-to-source quality, and the client back-to-source quality index value can well reflect the user experience of the client side.

[0086] In an optional implementation, the client back-to-source quality index includes at least one of the following indicators: a jamming index, an error index, and a first frame time consumption index. Among them, the jamming index is used to reflect the jamming of the resource targeted by the client back-to-source request during the playback process. The jamming index includes but is not limited to the jamming rate, jamming duration, number of jamming times, etc.; the error index is used to reflect the number of errors (such as failure to establish a connection, response time timeout, etc.) that occur during the client back-to-source or resource playback process, the severity of the error, and / or the error rate, etc.; the first frame time consumption index is used to reflect the time it takes for the client to load the first frame or the first byte of the resource targeted by the back-to-source request. The client back-to-source quality index value is the specific value of the client back-to-source quality index.

[0087] The client back-to-source quality index value can be actively fed back by the client or pulled by the server. For example, the client back-to-source quality index value can be regularly fed back or pulled according to the corresponding feedback or pulling cycle (such as every day, etc.), so that the server performs back-to-source scheduling based on the client back-to-source quality index value. Therefore, the present application can fully consider the user experience on the client side, so that the back-to-source scheduling result meets the user needs and improves the user experience.

[0088] Furthermore, the prior art uses a fixed and single scheduling method when performing back-to-source scheduling. For example, the prior art generally uses a regional scheduling method to use a node in the same region as the client as the back-to-source node of the client when performing back-to-source scheduling. However, under this scheduling scheme, it is easy to cause waste of some node resources and reduce the resource utilization of the entire CDN system. In order to improve the utilization of system resources and improve the accuracy of back-to-source scheduling, the embodiment of the present application generates a variety of scheduling methods and determines the most suitable scheduling method according to the actual situation.

[0089] In an optional implementation, the scheduling method in the embodiment of the present application is divided according to the node coverage and / or operator, that is, the scheduling method is divided from the node coverage dimension and / or operator dimension.

[0090] Node coverage specifically refers to the geographical coverage attributes of all nodes under the scheduling method, that is, the coverage of all nodes under the same scheduling method is the same, and the coverage may include: provincial coverage, regional coverage, and national coverage. Node coverage is usually a node attribute, and the coverage information of the node can be obtained by searching the node attribute. Among them, provincial coverage means that the node can only provide back-to-source services for clients in the same province; regional coverage means that the node can provide back-to-source services for clients in the same region; national coverage means that the node can provide back-to-source services for clients across the country.

[0091] The operator division dimension is based on whether the node and the client belong to the same operator. It can also be expressed as the difference in the operator of the node and the client. That is, the judgment result of whether the node and the corresponding client belong to the same operator is the same under the same scheduling method. For example, the results after division by operator include: same operator and cross-operator; for the same operator scheduling method, the client and its back-to-source node belong to the same operator under this scheduling method; for the cross-operator scheduling method, the client and its back-to-source node belong to different operators under this scheduling method.

[0092] Combining the above-mentioned node coverage dimension and operator dimension, the scheduling method of the embodiment of the present application includes at least multiple of the following methods: provincial coverage of the same operator, regional coverage of the same operator, national coverage of the same operator, provincial coverage across operators, regional coverage across operators, and national coverage across operators. Among them, in the scheduling method of provincial coverage of the same operator, all node coverage is provincial coverage, and the client and the corresponding source node belong to the same operator; in the scheduling method of national coverage across operators, all node coverage is national coverage, and the client and the corresponding source node belong to different operators. Therefore, in this embodiment, each scheduling method has a corresponding node coverage label and operator difference label. Among them, the node coverage label may include: provincial coverage, regional coverage and / or national coverage; the operator difference label may include: same operator, cross-operator.

[0093] In order to determine the most suitable scheduling method according to the actual situation, the embodiment of the present application generates a method quality value of the scheduling method according to the client back-to-source quality index value belonging to the scheduling method in the historical period for any scheduling method. The method quality value is obtained based on the back-to-source quality feedback data on the client side, so that the method quality value can reflect the pros and cons of the scheduling method from the user experience dimension. Among them, the method quality value can be calculated in real time, or it can be generated in advance to improve the efficiency of back-to-source request processing. For example, it can be periodically updated according to the client back-to-source quality index value, and the embodiment of the present application does not limit this.

[0094] Further, the target scheduling method corresponding to the return request is determined from multiple scheduling methods according to the method quality value. Specifically, according to the method quality values ​​of multiple scheduling methods, the most currently matching scheduling method is determined from multiple scheduling methods as the target scheduling method, and the target scheduling method is the scheduling method corresponding to the return request. For example, the scheduling method with the highest method quality value can be used as the target scheduling method. The target scheduling method is subsequently used for return scheduling.

[0095] Step S203: select candidate nodes that match the back-to-source request and belong to the target scheduling mode from the back-to-source nodes.

[0096] Filter out candidate nodes from the back-to-source nodes included in the system. The candidate node matches the back-to-source request, that is, the candidate node can provide matching resources for the target client, specifically, the candidate node can provide resources that match the resource information (resource ID or resource name, etc.) carried in the back-to-source request. In addition, the situation of the target client and the candidate node belongs to the target scheduling method. For example, the location of the target client can be determined by parsing the address of the target client carried in the back-to-source request (such as the IP address), and the operator information of the target client can be extracted, and then the location of the target client and the operator information can be determined according to the location of the target client and the operator information. Whether the node belongs to the target scheduling method.

[0097] In an optional implementation, since the scheduling method in the embodiment of the present application is divided by node coverage and operator, the candidate nodes are specifically determined in the following manner: select candidate nodes from the back-to-source nodes that match the back-to-source request, and whose node coverage matches the node coverage label of the target scheduling method, and whose operator differences and similarities between the node and the target client are consistent with the operator differences and similarities label of the target scheduling method. Thus, the candidate node not only matches the back-to-source request, but also the candidate node coverage matches the node coverage label of the target scheduling method, and the result of whether the candidate node and the target client operator are the same is the same as the operator difference label of the target scheduling method.

[0098] Step S204, obtaining a node quality value of the candidate node; wherein the node quality value is generated by a client back-to-source quality index value belonging to the corresponding back-to-source node within a historical period.

[0099] In order to facilitate the subsequent accurate screening of the target return source node from the candidate nodes, the embodiment of the present application also generates the node quality value of the return source node according to the client return source quality index value belonging to the corresponding return source node in the historical period. The node quality value can be generated in real time or in advance and periodically, which is not described in detail in the embodiment of the present application. Generating the node quality value of the return source node according to the client return source quality index value can indicate the quality of the return source node from the user experience dimension. This step obtains the node quality value of each candidate node for the subsequent screening of the target return source node.

[0100] Step S205: Determine a target back-to-source node corresponding to the back-to-source request from the candidate nodes according to the node quality value.

[0101] The target back-to-source node is screened out from the candidate nodes according to the node quality value of the candidate nodes. The target back-to-source node is the back-to-source node corresponding to the back-to-source request and is also the back-to-source node that provides resources for the back-to-source request of the target client. For example, the candidate node with the highest node quality value can be determined as the target back-to-source node, or the target back-to-source node can be determined comprehensively by combining the node quality value and other dimensional data (such as node load, distance between the node and the target client, etc.). When combining other dimensional data, the scores of the candidate nodes can be calculated for the node quality dimension and other dimensions respectively, and the scores can be weighted and summed to obtain the final scores of the candidate nodes, and then the candidate node with the highest score can be selected as the target back-to-source node.

[0102] It can be seen that the back-to-source scheduling method provided in the embodiment of the present application generates a method quality value of the scheduling method and a node quality value of the back-to-source node according to the client back-to-source quality indicator value, so that the advantages and disadvantages of the scheduling method and the back-to-source node can be reflected from the user experience dimension, and then the target back-to-source node obtained according to the method quality value and the node quality value can match the user experience and improve the user experience; and the present application provides multiple scheduling methods, and dynamically determines the most matching target scheduling method according to the method quality value of the scheduling method, thereby not only improving the back-to-source scheduling accuracy, but also making full use of system resources and improving system resource utilization.

[0103] Embodiment 2

[0104] Figure 3 A flowchart of a back-to-source scheduling method provided in Example 2 of the present application is shown. The back-to-source scheduling method can be executed on the server side, for example, in a CDN (content distribution network). The present application embodiment mainly provides a specific implementation scheme for calculating a node quality value and / or a mode quality value based on a client back-to-source quality value.

[0105] like Figure 3 As shown, the method specifically comprises the following steps:

[0106] Step S301: receiving a client back-to-source quality indicator value of a client, and assigning a corresponding node label, a scheduling mode label, and a timestamp label to the client back-to-source quality indicator value.

[0107] Client feedback can be obtained periodically or in real time, or the client back-to-source quality indicator value on the client side can be pulled periodically.

[0108] In order to quickly calculate the mode quality value and / or node quality value later, the embodiment of the present application determines the time information of each client return-to-source quality indicator value data (for example, the time information can be the data generation time, or the return-to-source time, resource playback time, etc.) for each acquired client return-to-source quality indicator value, and assigns it a timestamp label that matches the time information; and each client return-to-source quality indicator value data corresponds to a return-to-source, and a node label is assigned to it according to the node information of the return-to-source node corresponding to the return-to-source, and a scheduling mode label is assigned to it according to the mode information of the scheduling mode adopted by the return-to-source. Thus, the timestamp label of the client return-to-source quality indicator value data reflects the time information of the data, the scheduling mode label reflects the scheduling mode adopted in the return-to-source process corresponding to the data, and the node label reflects the return-to-source node that provides resources in the return-to-source process corresponding to the data.

[0109] Step S302: For any back-to-source node, obtain the client back-to-source quality indicator value whose timestamp label is within the first historical period and whose node label matches the back-to-source node.

[0110] The node quality value of the back-to-source node can be calculated periodically or when a corresponding trigger condition is met (such as receiving a calculation instruction, etc.). When calculating the node quality value, the client back-to-source quality index value whose timestamp label is within the first historical period and whose node label matches the back-to-source node is obtained. The first historical period can be a recent historical period such as the most recent day. The client back-to-source quality index values ​​that meet the conditions can be quickly screened out through the timestamp label and the node label.

[0111] Step S303: Calculate the node quality value of the back-to-source node based on the matched client back-to-source quality indicator value.

[0112] The node quality value of the back-to-source node is calculated according to the client back-to-source quality index value filtered out in step S302.

[0113] In an optional implementation, there may be multiple client back-to-source quality indicators. For each client back-to-source quality indicator, the values ​​of each client back-to-source quality indicator belonging to the client back-to-source quality indicator screened out in step S302 are determined, and the node sub-quality value under the client back-to-source quality indicator is calculated according to the values ​​of each client back-to-source quality indicator belonging to the client back-to-source quality indicator. The node quality value of the back-to-source node is obtained according to the node sub-quality values ​​of each client back-to-source quality indicator.

[0114] For example, the node quality value can be calculated by the following formula 1:

[0115]

[0116] Where Ns represents the node quality value; M represents the number of client back-to-source quality indicators, which can be a jamming indicator, an error indicator, and a first frame time-consuming indicator; Q i represents the node sub-quality value corresponding to the i-th client back-to-source quality indicator; w i Indicates the weight corresponding to the i-th client back-to-source quality indicator.

[0117] Further optionally, when calculating the node sub-quality value under the client back-to-source quality index according to the various client back-to-source quality index values ​​belonging to the client back-to-source quality index, the large-scale client back-to-source quality index value can be counted (for example, the average value, mode, median, and other statistical values ​​of the various client back-to-source quality index values ​​belonging to the client back-to-source quality index in the system during the first historical period can be used as the large-scale client back-to-source quality index value), and the corresponding statistical value (such as the average value, mode, median, etc.) is calculated according to the various client back-to-source quality index values ​​belonging to the client back-to-source quality index, and the node sub-quality value under the client back-to-source quality index is obtained according to the statistical value and the large-scale client back-to-source quality index value. For example, for the jamming index, the sub-quality value can be 100 when the statistical value is lower than the large-scale client back-to-source quality index value, the sub-quality value can be 0 when the statistical value exceeds 1.3 times the large-scale client back-to-source quality index value, and the sub-quality value can be reduced proportionally between 1 and 1.3 times. Other sub-quality value determination methods can be adopted in the actual implementation process, and this application does not limit this.

[0118] Step S304: for any scheduling mode, obtain the client back-to-source quality indicator value whose timestamp tag is within the second historical period and whose scheduling mode tag matches the scheduling mode.

[0119] The method quality value of the scheduling method can be calculated periodically or when the corresponding trigger conditions are met (such as receiving a calculation instruction, etc.). When calculating the method quality value, obtain the client back-to-source quality index value whose timestamp tag is in the second historical period and whose scheduling method tag matches the scheduling method. The second historical period can be the most recent day, etc. The second historical period can be the same as the first historical period or different. The timestamp tag and the scheduling method tag can quickly filter out the client back-to-source quality index values ​​that meet the conditions.

[0120] Step S305: Calculate the mode quality value of the scheduling mode based on the matched client back-to-source quality indicator value.

[0121] The mode quality value of the scheduling mode is calculated according to the client back-to-source quality indicator value filtered out in step S304.

[0122] In an optional implementation, there may be multiple client back-to-source quality indicators. For each client back-to-source quality indicator, the values ​​of each client back-to-source quality indicator belonging to the client back-to-source quality indicator screened out in step S304 are determined, and a mode sub-quality value under the client back-to-source quality indicator is calculated according to each client back-to-source quality indicator value belonging to the client back-to-source quality indicator, and a mode quality value of the scheduling mode is obtained according to the mode sub-quality values ​​of each client back-to-source quality indicator.

[0123] For example, the mode quality value can be calculated by the following formula 2:

[0124]

[0125] Wherein, Fs represents the mode quality value; M represents the number of client back-to-source quality indicators, which may include a jamming indicator, an error indicator, and a first frame time consumption indicator; P i represents the mode quality value corresponding to the i-th client back-to-source quality indicator; w i Indicates the weight corresponding to the i-th client back-to-source quality indicator.

[0126] Further optionally, when calculating the mode sub-quality value under the client back-to-source quality index according to the values ​​of the various client back-to-source quality indexes belonging to the client back-to-source quality index, the value of the large-scale client back-to-source quality index can be counted (for example, the average value, mode, median, and other statistical values ​​of the various client back-to-source quality index values ​​belonging to the client back-to-source quality index in the system during the second historical period can be used as the large-scale client back-to-source quality index value), and the corresponding statistical value (such as the average value, mode, median, etc.) is calculated according to the values ​​of the various client back-to-source quality indexes belonging to the client back-to-source quality index, and the node sub-quality value under the client back-to-source quality index is obtained according to the statistical value and the large-scale client back-to-source quality index value. For example, for the jamming index, the sub-quality value can be 100 when the statistical value is lower than the value of the large-scale client back-to-source quality index, the sub-quality value can be 0 when the statistical value exceeds 1.3 times the value of the large-scale client back-to-source quality index, and the sub-quality value can be reduced proportionally between 1 and 1.3 times. Other sub-quality value determination methods can be adopted in the actual implementation process, and this application does not limit this.

[0127] Step S306: determining priorities of the multiple scheduling modes according to the mode quality values ​​of the multiple scheduling modes.

[0128] In order to improve the processing efficiency of subsequent back-to-source requests, after obtaining or updating the method quality value of the scheduling method, the priorities of multiple scheduling methods can be further determined according to the method quality values ​​of the multiple scheduling methods. Specifically, the method quality values ​​are arranged in order from high to low, and then the corresponding priorities are determined according to the arrangement order. The higher the method quality value is, the higher the priority of the corresponding scheduling method is.

[0129] The initial priority of multiple scheduling methods is: provincial coverage with the same operator > regional coverage with the same operator > national coverage with the same operator > provincial coverage with different operators > regional coverage with different operators > national coverage with different operators. The quality value of the scheduling method is subsequently updated by calculating the client backhaul quality indicator value, thereby updating the priority of the scheduling method.

[0130] It can be seen that the back-to-source scheduling method provided in the embodiment of the present application assigns corresponding node labels, scheduling mode labels and timestamp labels to the client back-to-source quality index value after receiving it, thereby being able to quickly and accurately filter out the data required for calculating the node quality value based on the node label and the timestamp label, and being able to quickly and accurately filter out the data required for calculating the mode quality value based on the scheduling mode label and the timestamp label, thereby improving the calculation efficiency and accuracy of the node quality value and the mode quality value.

[0131] Embodiment 3

[0132] Figure 4 A flow chart of a back-to-source scheduling method provided in Embodiment 3 of the present application is shown. The back-to-source scheduling method can be executed on the server side, for example, in a CDN (Content Distribution Network).

[0133] like Figure 4 As shown, the method specifically comprises the following steps:

[0134] Step S401: receiving a back-to-source request from a target client.

[0135] Step S402, obtaining priorities of multiple pre-generated scheduling modes.

[0136] In the embodiment of the present application, the priority of the scheduling method is generated in advance according to the method quality value of the scheduling method, so that the target scheduling method corresponding to the back-to-source request can be determined from multiple scheduling methods according to the priority of the scheduling method. Therefore, when processing the back-to-source request, there is no need to compare the size of the method quality value of the scheduling method, thereby improving the processing efficiency of the back-to-source request.

[0137] Step S403: taking the scheduling mode with the highest priority as the target scheduling mode.

[0138] When determining the target scheduling method, first use the scheduling method with the highest priority as the current target scheduling method. And determine the back-to-source node belonging to the target scheduling method. Among them, the back-to-source node belonging to the target scheduling method means: the coverage of the back-to-source node matches the coverage label of the target scheduling method, and the operator difference results between the target client and the back-to-source node are consistent with the operator difference label of the target scheduling method.

[0139] Step S404, determining whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode; if so, executing step S405; if not, executing step S406.

[0140] Specifically, it is to determine whether there is a back-to-source node among the back-to-source nodes belonging to the target scheduling mode that can provide the requested resources to the target client.

[0141] Step S405: taking the back-to-source node that belongs to the target scheduling mode and matches the back-to-source request as a candidate node.

[0142] If there is a back-to-source node that can match the back-to-source request under the current target scheduling mode, it means that the current target scheduling mode is selected correctly, and the back-to-source node that belongs to the target scheduling mode and matches the back-to-source request is used as a candidate node.

[0143] Step S406: Update the target scheduling mode to a scheduling mode with a priority second only to the current target scheduling mode.

[0144] If there is no back-to-source node that can match the back-to-source request under the current target scheduling mode, the target scheduling mode is updated to a scheduling mode with a priority next to the current target scheduling mode, that is, the next scheduling mode of the current target scheduling mode in the priority link is used as the new target scheduling mode. Step S404 is further executed to determine whether there is a back-to-source node that matches the back-to-source request under the new target scheduling mode.

[0145] Step S407: determine a target back-to-source node corresponding to the back-to-source request from the candidate nodes according to the node quality values ​​of the candidate nodes.

[0146] It can be seen that the back-to-source scheduling method provided in the embodiment of the present application generates the priority of the scheduling method according to the method quality value of the scheduling method in advance, so that the target scheduling method can be quickly determined according to the priority of the scheduling method, thereby improving the processing efficiency of the back-to-source request.

[0147] Embodiment 4

[0148] Figure 5 FIG. 4 shows a schematic diagram of the structure of a back-to-source scheduling device provided in Embodiment 4 of the present application. Figure 5As shown, the device 500 includes: a receiving module 510, a scheduling mode determination module 520 and a node determination module 530.

[0149] The receiving module 510 is used to receive a return request from a target client;

[0150] A scheduling mode determination module 520, configured to determine a target scheduling mode corresponding to the back-to-source request from the multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes; wherein the mode quality value is generated by a back-to-source quality indicator value of a client belonging to the corresponding scheduling mode in a historical period;

[0151] The node determination module 530 is used to filter out candidate nodes that match the back-to-source request and belong to the target scheduling method from the back-to-source nodes, and obtain the node quality value of the candidate node; wherein the node quality value is generated by the client back-to-source quality indicator value belonging to the corresponding back-to-source node in a historical period; and determine the target back-to-source node corresponding to the back-to-source request from the candidate nodes according to the node quality value.

[0152] In an optional implementation, the receiving module 510 is used to: receive a client back-to-source quality indicator value of the client;

[0153] The device also includes: an allocation module (not shown in the figure), which is used to allocate corresponding node labels, scheduling mode labels and timestamp labels to the client back-to-source quality indicator value;

[0154] The client back-to-source quality indicator includes at least one of the following indicators: a freeze indicator, an error indicator, and a first frame time consumption indicator.

[0155] In an optional implementation, the device further includes: a node quality value calculation module (not shown in the figure), configured to obtain, for any back-to-source node, a client back-to-source quality index value whose timestamp label is within the first historical period and whose node label matches the back-to-source node;

[0156] The node quality value of the back-to-source node is calculated based on the matched client back-to-source quality indicator value.

[0157] In an optional implementation, the device further includes: a mode quality value calculation module (not shown in the figure), which is used to obtain, for any scheduling mode, a client back-to-source quality indicator value whose timestamp tag is within the second historical period and whose scheduling mode tag matches the scheduling mode;

[0158] The mode quality value of the scheduling mode is calculated based on the matched client back-to-source quality indicator value.

[0159] In an optional implementation, the device further includes: a priority determination module (not shown in the figure), configured to determine the priorities of the plurality of scheduling modes according to the mode quality values ​​of the plurality of scheduling modes;

[0160] The scheduling mode determination module 520 is used to determine the target scheduling mode corresponding to the back-to-source request from the multiple scheduling modes according to the priority of the scheduling mode.

[0161] In an optional implementation, the scheduling mode determination module 520 is used to: use the scheduling mode with the highest priority as the target scheduling mode;

[0162] Determine whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode;

[0163] If yes, taking the back-to-source node that belongs to the target scheduling mode and matches the back-to-source request as a candidate node;

[0164] If not, the target scheduling mode is updated to a scheduling mode with a priority second only to the current target scheduling mode, and the step of determining whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode is performed.

[0165] In an optional implementation, the scheduling mode is divided according to node coverage and / or operator, and each scheduling mode has a corresponding node range label and operator similarity and difference label;

[0166] The node determination module 530 is used to: select candidate nodes that match the return-to-source request from the return-to-source nodes, whose coverage matches the node coverage label of the target scheduling mode, and whose operator similarity and difference results between the node and the target client are consistent with the operator similarity and difference label of the target scheduling mode;

[0167] Among them, the scheduling method includes at least multiple of the following methods: provincial coverage of the same operator, regional coverage of the same operator, national coverage of the same operator, provincial coverage across operators, regional coverage across operators, and national coverage across operators.

[0168] It can be seen that the back-to-source scheduling device provided in the embodiment of the present application generates a method quality value of the scheduling method and a node quality value of the back-to-source node according to the client back-to-source quality indicator value, so that the advantages and disadvantages of the scheduling method and the back-to-source node can be reflected from the user experience dimension, and then the target back-to-source node obtained according to the method quality value and the node quality value can match the user experience and improve the user experience; and the present application provides multiple scheduling methods, and dynamically determines the most matching target scheduling method according to the method quality value of the scheduling method, thereby not only improving the back-to-source scheduling accuracy, but also making full use of system resources and improving system resource utilization.

[0169] Embodiment 5

[0170] Figure 6 A structural schematic diagram of a computing device embodiment provided in Embodiment 5 of the present application is shown. The specific embodiments of the present application do not limit the specific implementation of the computing device.

[0171] like Figure 6 As shown, the computing device may include: a processor (processor) 602 , a communications interface (Communications Interface) 604 , a memory (memory) 606 , and a communication bus 608 .

[0172] The processor 602, the communication interface 604, and the memory 606 communicate with each other via the communication bus 608. The communication interface 604 is used to communicate with other devices such as a client or other server network elements. The processor 602 is used to execute the program 610, which can specifically execute the relevant steps in the above-mentioned embodiment of the back-to-source scheduling method for computing devices.

[0173] Specifically, the program 610 may include program codes, which include computer operation instructions.

[0174] The processor 602 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0175] The memory 606 is used to store the program 610. The memory 606 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The program 610 can be specifically used to enable the processor 602 to perform the operations in the above-mentioned back-to-source scheduling method embodiment.

[0176] Embodiment 6

[0177] Embodiment 6 of the present application provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction or computer program, which enables a processor to perform operations corresponding to the back-to-source scheduling method in any of the above method embodiments.

[0178] Embodiment 7

[0179] Embodiment 7 of the present application provides a computer program product, which includes at least one executable instruction or computer program, and the executable instruction or computer program can enable a processor to perform operations corresponding to the back-to-source scheduling method in any of the above method embodiments.

[0180] In summary, according to the computing device, computer storage medium and computer program product provided in the embodiments of the present application, a method quality value of the scheduling method and a node quality value of the back-to-source node are generated according to the client back-to-source quality indicator value, so that the advantages and disadvantages of the scheduling method and the back-to-source node can be reflected from the user experience dimension, and then the target back-to-source node obtained according to the method quality value and the node quality value can match the user experience and improve the user experience; and the present application provides multiple scheduling methods, and dynamically determines the most matching target scheduling method according to the method quality value of the scheduling method, thereby not only improving the back-to-source scheduling accuracy, but also making full use of system resources and improving system resource utilization.

[0181] The algorithm or display provided here are not inherently related to any specific computer, virtual system or other equipment. Various general systems can also be used together with the teaching based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the present application embodiment is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present application described here, and the above description of specific languages ​​is to disclose the best mode of implementation of the present application.

[0182] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0183] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the embodiments of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the claims below, the inventive aspects are less than all the features of the single embodiment disclosed above. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0184] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0185] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0186] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components according to the embodiments of the present application. The application can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0187] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be constructed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A back-to-source scheduling method, characterized in that: include: Receive the target client's back-to-origin request; Determining a target scheduling mode corresponding to the back-to-source request from the multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes; wherein the mode quality value is generated by a back-to-source quality indicator value of a client belonging to the corresponding scheduling mode in a historical period; Selecting candidate nodes that match the back-to-source request and belong to the target scheduling mode from the back-to-source nodes, and obtaining node quality values ​​of the candidate nodes; wherein the node quality values ​​are generated by the back-to-source quality index values ​​of the clients belonging to the corresponding back-to-source nodes in the historical period; A target back-to-source node corresponding to the back-to-source request is determined from the candidate nodes according to the node quality value.

2. The method according to claim 1, characterized in that The method further comprises: Receive the client's client return quality indicator value; Assign corresponding node labels, scheduling mode labels, and timestamp labels to the client back-to-source quality indicator values; The client back-to-source quality indicator includes at least one of the following indicators: a freeze indicator, an error indicator, and a first frame time consumption indicator.

3. The method according to claim 2, characterized in that The node quality value is generated in the following way: For any back-to-source node, obtain a client back-to-source quality indicator value whose timestamp label is within the first historical period and whose node label matches the back-to-source node; The node quality value of the back-to-source node is calculated based on the matched client back-to-source quality indicator value.

4. The method according to claim 2, characterized in that: The quality value of the method is generated in the following way: For any scheduling mode, obtaining a client back-to-source quality indicator value whose timestamp tag is within the second historical period and whose scheduling mode tag matches the scheduling mode; The mode quality value of the scheduling mode is calculated based on the matched client back-to-source quality indicator value.

5. The method according to any one of claims 1 to 4, characterized in that The method further includes: determining priorities of multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes; The determining of the target scheduling mode corresponding to the return-to-source request from the multiple scheduling modes according to the mode quality values ​​of the multiple scheduling modes includes: A target scheduling method corresponding to the back-to-source request is determined from the multiple scheduling methods according to the priority of the scheduling method.

6. The method according to claim 5, characterized in that Determining the target scheduling mode corresponding to the return request from the multiple scheduling modes according to the priority of the scheduling modes includes: Taking the scheduling method with the highest priority as the target scheduling method; Determine whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode; If yes, taking the back-to-source node that belongs to the target scheduling mode and matches the back-to-source request as a candidate node; If not, the target scheduling mode is updated to a scheduling mode with a priority second only to the current target scheduling mode, and the step of determining whether there is a back-to-source node matching the back-to-source request among the back-to-source nodes belonging to the target scheduling mode is performed.

7. The method according to any one of claims 1 to 6, characterized in that The scheduling methods are divided according to node coverage and / or operator, and each scheduling method has a corresponding node range label and operator similarity and difference label; The step of screening out candidate nodes that match the return-to-source request and belong to the target scheduling mode from the return-to-source nodes includes: Filter out candidate nodes from the back-to-source nodes that match the back-to-source request, whose coverage matches the node coverage label of the target scheduling method, and whose operator difference results between the node and the target client are consistent with the operator difference label of the target scheduling method; Among them, the scheduling method includes at least multiple of the following methods: provincial coverage of the same operator, regional coverage of the same operator, national coverage of the same operator, provincial coverage across operators, regional coverage across operators, and national coverage across operators.

8. A back-to-source scheduling device, characterized in that: include: The receiving module is used to receive the return request from the target client; A scheduling mode determination module, configured to determine a target scheduling mode corresponding to the back-to-source request from among the multiple scheduling modes according to mode quality values ​​of the multiple scheduling modes; wherein the mode quality value is generated by a back-to-source quality indicator value of a client belonging to the corresponding scheduling mode in a historical period; A node determination module is used to filter out candidate nodes that match the back-to-source request and belong to the target scheduling method from the back-to-source nodes, and obtain the node quality value of the candidate node; wherein the node quality value is generated by the client back-to-source quality indicator value belonging to the corresponding back-to-source node in a historical period; and determine the target back-to-source node corresponding to the back-to-source request from the candidate nodes according to the node quality value.

9. A computing device, characterized in that include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the back-to-source scheduling method according to any one of claims 1-7.

10. A computer storage medium, characterized in that: The storage medium stores at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the back-to-source scheduling method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the back-to-source scheduling method according to any one of claims 1 to 7.

Images