CDN routing pathfinding method and apparatus, and electronic device

Abstract

Embodiments of the present application provide a CDN routing pathfinding method and apparatus, and an electronic device. The method comprises: acquiring CDN pathfinding request information, wherein the CDN pathfinding request information is used for requesting a routing result; and on the basis of the CDN pathfinding request information, CDN network topology information, and a CDN routing selection model, obtaining the routing result matched with the CDN pathfinding request, wherein the CDN routing selection model is used for outputting the routing result.

Description

CDN routing method, device and electronic device

[0001] Cross-references

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on June 26, 2023, with application number 2023107649375 and invention name “CDN routing method, device and electronic device”. The entire contents of the application are incorporated by reference into this application. Technical Field

[0003] The present application relates to the technical field of Content Delivery Network (CDN), and in particular to a CDN routing method, device, and electronic device. Background Art

[0004] In internet applications, CDN technology is a crucial tool for ensuring the quality of internet services. By distributing and caching content globally, CDN technology improves the speed and quality of user access to internet services. However, due to the complexity and dynamism of CDN network topology, CDN routing strategies may not maximize user experience, resulting in inconvenience and a negative experience.

[0005] In related technologies, CDN routing strategies are primarily based on manually pre-defined rules and static CDN network topologies. This approach often fails to adapt to changes in CDN network topologies and the diversity of user requests. For example, a route may be optimal in some situations, but may create bottlenecks and delays in others. Therefore, finding the optimal route is a key challenge facing current CDN technology.

[0006] Summary of the Invention

[0007] The purpose of the embodiments of the present application is to provide a CDN routing method, device and electronic device that can solve the problem of not being able to obtain better routing results in the CDN network.

[0008] To solve the above technical problems, the embodiments of the present application are implemented through the following aspects.

[0009] In a first aspect, an embodiment of the present application provides a CDN routing method, comprising: obtaining CDN routing request information, wherein the CDN routing request information is used to request a routing result; based on the CDN routing request information, CDN network topology information, and a CDN routing selection model, obtaining a routing result that matches the CDN routing request; wherein the CDN routing selection model is used to output the routing result.

[0010] In a second aspect, an embodiment of the present application provides a CDN routing device, comprising: an acquisition module for acquiring CDN routing request information, wherein the CDN routing request information is used to request a routing result; an output module for obtaining a routing result that matches the CDN routing request based on the CDN routing request information, CDN network topology information, and a CDN routing selection model; wherein the CDN routing selection model is used to output the routing result.

[0011] In a third aspect, an embodiment of the present application provides an electronic device comprising: a memory, a processor, and computer-executable instructions stored on the memory and executable on the processor, wherein the computer-executable instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0012] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which is used to store computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the method described in the first aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0014] FIG1 is a schematic diagram showing a flow chart of a CDN routing method provided by an embodiment of the present application;

[0015] FIG2 is a schematic diagram of a system block diagram of a CDN routing method provided by an embodiment of the present application;

[0016] FIG3 is a schematic diagram showing the structure of a CDN routing device according to an embodiment of the present application;

[0017] FIG4 is a schematic diagram of the hardware structure of an electronic device that executes the CDN routing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0019] FIG1 illustrates a flow chart of a CDN routing method provided by an embodiment of the present application. This method can be executed by an electronic device, such as a terminal device or a server device. In other words, the method can be executed by software or hardware installed on the terminal device or server device. The server device includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. As shown in FIG1 , the method may include the following steps.

[0020] Step S10: Obtain CDN routing request information, where the CDN routing request information is used to request a routing result.

[0021] In one embodiment, the CDN routing request information may include at least one of the following: user IP address, MD5 data of user requested content, and user special request file information.

[0022] Step S20: obtaining a routing result that matches the CDN routing request based on the CDN routing request information, the CDN network topology information, and the CDN routing selection model; wherein the CDN routing selection model is used to output the routing result.

[0023] Before executing this embodiment, the CDN routing model can be trained based on CDN routing request information, real-time CDN network topology information, and the best routing result that matches the CDN routing request. The CDN routing model can automatically learn and optimize routing strategies. Through continuous trial and error and learning, the routing strategies can be gradually optimized, thereby improving the CDN service quality and user experience.

[0024] In one embodiment, the CDN network topology information (or CDN network topology map) may include at least one of the following: CDN network element service operation status information, CDN network link status information, and CDN network element hardware indicator information. The CDN network topology information in this embodiment can be obtained in real time. Compared to related art solutions that obtain routing results based on a static CDN network topology structure, this embodiment can obtain optimal routing results, thereby improving the CDN service quality and user experience.

[0025] This embodiment may further include at least one of the following steps: 1) obtaining CDN network element operation logs from the CDN network's log file system, and obtaining CDN network element service operation information based on the CDN network element operation logs; 2) obtaining CDN network link status information based on the CDN network's network link status logs; and 3) obtaining CDN network element operation parameters from the CDN network's data collection interface, and obtaining CDN network element hardware indicator information based on the CDN network element operation parameters. This embodiment facilitates obtaining real-time CDN network topology information, thereby facilitating optimal routing results and improving CDN service quality and user experience.

[0026] In this embodiment, the routing results that match the CDN routing request include one of the following: 1) the best routing result that matches the user IP address and the MD5 data of the user requested content. The best routing result may have the lowest latency, the highest reliability quality, etc.; 2) the routing result that matches the user's special requirement file information. The routing result may be the best routing result that meets the user's special requirements.

[0027] In various embodiments of the present application, after obtaining a routing result that matches the CDN routing request, the method further includes: transmitting the routing result to a CDN control network element, so that the CDN control network element implements the routing path to the CDN by redirecting the user service.

[0028] The embodiments of the present application provide a CDN routing method, which obtains routing results based on CDN network topology information and a CDN routing selection model. The CDN routing selection model can automatically learn and optimize routing selection strategies. Through continuous trial and error and learning, the routing selection strategies can be gradually optimized, thereby improving the service quality and user experience of the CDN. Routing results are obtained based on real-time CDN network topology information, which is conducive to obtaining the optimal routing results and improving the service quality and user experience of the CDN.

[0029] The CDN network topology information in the embodiment shown in FIG1 includes a CDN network topology structure diagram. The embodiment shown in FIG1 further includes the following steps: obtaining a CDN log file; and generating a CDN network topology structure diagram based on the CDN log file.

[0030] This embodiment generates a CDN network topology diagram based on the CDN log file, including: performing streaming analysis and calculation on the CDN log file based on CDN log file analysis technology and network topology perception technology to generate a CDN network topology diagram.

[0031] This embodiment uses streaming log file analysis technology, which is conducive to obtaining real-time CDN network topology information, which is conducive to obtaining optimal routing results and improving the CDN service quality and user experience.

[0032] Each of the above embodiments may further include the following steps: based on training set data, using a reinforcement learning algorithm to generate or iteratively train the CDN routing selection model; wherein the training set data includes: the CDN routing request information, the CDN network topology information, and routing results that match the CDN routing request.

[0033] Reinforcement learning is a method in the field of machine learning that learns behavioral strategies through a trial-and-error process to maximize rewards. This embodiment uses a reinforcement learning algorithm to establish a CDN routing model. It can also use a reinforcement learning algorithm to iteratively train the CDN routing model. Through continuous trial and error and learning, the CDN routing model can automatically learn and optimize routing strategies. In other words, CDN routing request information and CDN network topology information can be used as input to design a state and action space suitable for the CDN. The established CDN routing model is then used to find and output the optimal routing result. Through continuous trial and error and learning, the CDN routing model can gradually optimize the routing strategy, thereby improving the CDN service quality and user experience.

[0034] Technically, this embodiment uses reinforcement learning AI technology to implement intelligent routing, thereby improving CDN service quality and user experience. Furthermore, this embodiment can provide CDN operators with more decision-making support and management tools, thereby improving CDN management efficiency and operational stability. In practical applications, this embodiment can help CDN providers implement more efficient content distribution networks, improve user access speed and quality, and thus enhance user stickiness and satisfaction.

[0035] Furthermore, this embodiment has broad application prospects and can be applied to internet applications such as live video streaming, online gaming, music, and social networking. With the increasing popularity and development of internet services, the application prospects of CDN technology are also expanding. At the same time, with the continuous changes in network topology and service quality, the demand for intelligent routing is becoming increasingly urgent. Therefore, this embodiment has a very broad application prospect and very high commercial value and social significance.

[0036] This embodiment can solve the problem of intelligent routing selection in existing CDN technology and has obvious practical applications and economic benefits.

[0037] Compared with the traditional CDN routing method, this embodiment has at least the following advantages:

[0038] 1. Intelligence: This embodiment uses a reinforcement learning algorithm to establish a CDN routing model. It is intelligent and can automatically learn and optimize routing strategies to adapt to the dynamic CDN network topology and the diversity of user requests.

[0039] 2. Adaptability: This embodiment is based on CDN network topology information (such as CDN network topology structure and performance indicators), and is designed to be suitable for the state and action space of CDN. It has the characteristics of adaptability and can select the best routing strategy according to different situations to improve user experience.

[0040] 3. Improve service quality and user experience: The ultimate goal of this embodiment is to improve the service quality and user experience of the CDN. Through intelligent routing selection and optimization strategies, user experience and satisfaction can be effectively improved.

[0041] In summary, the technical solution of this embodiment has significant practical value and economic benefits. It can solve the intelligent routing problem in existing CDN technology, thereby improving CDN service quality and user experience. This technical solution can provide CDN providers with a more efficient content delivery network, enhance user stickiness and satisfaction, and has very broad commercial application prospects and social significance.

[0042] This embodiment can provide more ideas and solutions for the development and application of CDN technology. By using reinforcement learning AI technology to establish an intelligent CDN routing model, it can effectively improve CDN service quality and user experience. This solution is not only highly technical and innovative, but also has broad application prospects and commercial value in practical applications.

[0043] To illustrate the CDN routing method provided in the embodiment of the present application in detail, the following will be described in conjunction with a specific application scenario and a specific embodiment.

[0044] The application environment of the embodiments of this application is primarily for internet service providers, particularly those that provide CDN services. With the increasing popularity and development of internet services, CDN technology is being used more and more widely, encompassing internet application areas such as live video streaming, online gaming, music, and social networking. In these application scenarios, providing fast, reliable, and high-quality content distribution services is crucial, and as a result, CDN technology is playing an increasingly prominent role.

[0045] CDN providers are the primary target audience for the embodiments of this application. These companies need to provide efficient and reliable CDN services to meet user access needs for content. In this context, the optimal routing method for CDN user requests based on reinforcement learning AI technology provided in the embodiments of this application can better optimize routing strategies and improve the quality and performance of CDN services.

[0046] In addition, the embodiments of the present application are also applicable to the internal networks of Internet service providers, especially those enterprises with complex and dynamic network topologies. Using the routing selection method provided by the embodiments of the present application can effectively solve routing selection problems in internal networks and improve network performance and operational stability.

[0047] In summary, the application environment of the embodiments of this application is primarily for Internet service providers, especially CDN providers, and enterprises with complex and dynamic network topologies. These enterprises need to provide efficient and reliable CDN services and network services to meet the needs of users and internal employees. The CDN routing method based on reinforcement learning AI technology provided in the embodiments of this application can effectively improve the quality and performance of CDN services and network services, and has broad practical application value and commercial significance.

[0048] The system block diagram of the embodiment of the present application is shown in Figure 2, which consists of four layers: hardware layer, data layer, application layer, and main control layer. The following will explain the functions of each layer and the functions of the modules within each layer.

[0049] Hardware layer

[0050] The hardware layer mainly consists of existing network element devices and data probes in the CDN network, which serve as the underlying hardware resource devices for mobilization.

[0051] CDN network element devices (abbreviated as network element devices): Network element concepts such as sub-servers and sub-virtual groups. They are mainly used as source devices (including physical devices and virtual devices) for calculated indicators.

[0052] Data Probe: This module connects to the hardware-layer network element devices and the data collection and data distribution interfaces at the data layer. Data probes, distributed across subservers and sub-virtual groups, collect the metrics generated by network element devices for calculation. Upon receiving data collection tasks from the data distribution interface, this module collects the corresponding metrics from the network element devices and uploads them to the data collection interface, completing the data collection operation.

[0053] Data Layer

[0054] The data layer includes a data collection interface, a data distribution interface, a data task management module, and a log file system. This layer primarily handles data transmission and verification. It also registers newly added data collection tasks and adds them to the data collection task queue; registers and removes newly removed data collection tasks from the data collection task queue; registers and modifies newly modified data collection tasks; and queries data collection tasks in the queue.

[0055] Data Collection Interface: This interface connects the data probes at the hardware layer and the data task management module on the data side. After collecting data, the data probes upload it to the data collection interface. After receiving the data collected by the data probes, the interface aggregates the data into the data task management module, assigning a unified timestamp and managing it for use by various business processing units at the application layer.

[0056] Data delivery interface: This interface connects the data probes at the hardware layer and the data task management module at the data layer. After receiving the task signal from the current data collection task queue in the data task management module, this module delivers the task collection signal to the data probes, driving them to collect the corresponding indicator data.

[0057] Data Task Management Module: This module is connected to the data acquisition interface and data delivery interface in the data layer, as well as the optimal routing reinforcement learning training module in the application layer. The main functions of this module include: 1) providing a persistent database to store historical data of various indicators of each network element; 2) maintaining the data task queue and sending each signal in the data task queue to the corresponding module to drive module operation, that is, for newly added data acquisition tasks, registering and adding to the data acquisition task queue; for newly removed data acquisition tasks, registering and removing from the data acquisition task queue; for newly modified data acquisition tasks, registering and modifying the data acquisition task queue; and querying data acquisition tasks in the queue. At the same time, for the data collected by the data acquisition interface, this module aggregates this data and uniformly marks the time for invocation by individual business processing units in the application layer.

[0058] Log File System: This system is a centralized log file management system within the CDN network system. It contains log file information, alarm information, fault information, and network transmission log information between each CDN network element device and its connected CDN network elements. During optimal routing training, this embodiment uses the network transmission log information in this system, combined with constraints manually input through the main control module, to calculate the optimal routing path. This optimal routing path is used as part of the training set for optimal routing reinforcement learning algorithm training.

[0059] Application Layer

[0060] The application layer primarily consists of various business processing units, including the optimal routing reinforcement learning training module, the optimal routing output module, and the task execution module. This layer is the main business layer of this system and includes the vast majority of its functions. The following will explain this layer in detail.

[0061] Optimal routing reinforcement learning training module: This module obtains the network transmission log information between CDN network element devices in the log file system: 1) The status of the network path between CDN network element devices is obtained, and the CDN network element service operation status information is obtained based on the CDN network element operation log; 2) Network element indicator information - CDN network element operation parameters are obtained from the data acquisition interface of the CDN network, and the CDN network element hardware indicator information is obtained based on the CDN network element operation parameters to avoid routing to abnormal network elements; 3) The restriction conditions input by the main control module; 4) The CDN network link status information is obtained based on the network link status log of the CDN network. The optimal routing path is calculated by the traversal algorithm, and the optimal routing path is used as part of the training set to train the reinforcement learning model, and finally the CDN routing selection model is obtained (in the absence of an initial model) or iterated (in the case of an initial model that already exists).

[0062] Optimal Route Output Module: This module primarily uses information from log files, including: 1) inter-CDN network element device network transmission log information—obtaining the status of inter-CDN network element network paths and, based on the CDN network element operation logs, obtaining CDN network element service operation information; 2) network element indicator information—obtaining CDN network element operation parameters from the CDN network's data collection interface and, based on these parameters, obtaining CDN network element hardware indicator information to avoid routing to abnormal network elements; 3) constraints input by the master control module; and 4) CDN network link status information obtained based on the CDN network's network link status logs. These information are then input into the CDN routing model to determine the optimal routing path.

[0063] Task Execution Module: This module is primarily controlled by the Master Control Module and can execute two types of tasks: 1) training and generating a CDN routing model; and 2) iteratively training a CDN routing model. Specific examples are described in the next chapter.

[0064] Main control layer

[0065] This layer is mainly used to control system training or iteration of the CDN routing model, as well as input artificial constraints. In some cases, customers may not choose the optimal routing path due to business needs, but instead choose a routing method that meets their business needs. This type of information is input into the main control module, thereby changing the optimal routing path output by the optimal routing reinforcement learning model. The following will be explained in conjunction with a specific embodiment.

[0066] Example 1

[0067] This embodiment is a training process embodiment, which includes the following steps:

[0068] The main control module issues training instructions and also issues user-specific requirement file information (such as CDN network element restrictions, content restrictions, etc.).

[0069] The task execution module receives the training instructions and special requirement file information, adds the training task to the task queue, and waits for the task queue to reach the training task before starting execution.

[0070] The optimal routing reinforcement learning module obtains the corresponding CDN network element operation log (whether the business operation status is good) and CDN network link status log from the log file system; obtains the operation parameters of each CDN network element from the data acquisition interface to calculate the hardware indicator information of each CDN network element (whether the hardware operation status is normal).

[0071] The optimal routing reinforcement learning module uses this data, combined with the user's specific requirements document, to calculate the optimal routing link, thus forming a training set. The training set consists of [CDN network element service operation status, CDN network link status, CDN network element hardware specifications, user specific requirements; and the optimal routing result].

[0072] The optimal routing reinforcement learning module uses a reinforcement learning algorithm to train based on the above training set to obtain a CDN routing selection model.

[0073] Example 2

[0074] This embodiment is an iterative process embodiment, including the following steps:

[0075] The main control module issues iteration instructions and at the same time issues user-specific requirement file information (network element restrictions, content restrictions, etc.).

[0076] The task execution module receives iteration instructions and special requirement file information, adds the training task to the task queue, and waits for the task queue to reach the training task before starting execution.

[0077] The optimal routing reinforcement learning module obtains the corresponding CDN network element operation log (whether the business operation status is good) and CDN network link status log from the log file system; obtains the operation parameters of each CDN network element from the data acquisition interface to calculate the hardware indicator information of each CDN network element (whether the hardware operation status is normal).

[0078] The optimal routing reinforcement learning module uses this data, combined with the user's specific requirements document, to calculate the optimal routing link, thus forming a training set. The training set consists of [CDN network element service operation status, CDN network link status, CDN network element hardware specifications, user specific requirements; and the optimal routing result].

[0079] The optimal routing reinforcement learning module uses a reinforcement learning algorithm to iteratively train the CDN routing selection model based on the above training set to iteratively obtain the optimal CDN routing selection model.

[0080] Example 3

[0081] This embodiment is an optimal routing application embodiment, including the following steps:

[0082] The main control module sends a routing request, the request content includes the user's IP address, the MD5 data of the request content, and the user's special request file information.

[0083] The task execution module receives the pathfinding request and adds the task to the queue.

[0084] The optimal route output module calls the log file system to obtain the corresponding CDN network element operation log (whether the business operation status is good) and CDN network link status log; obtains the operation parameters of each CDN network element from the data acquisition interface to calculate the hardware indicator information of each CDN network element (whether the hardware operation status is normal), and constitutes the [CDN network element business operation status, CDN network link status, CDN network element hardware indicators, user special requirements] data, and obtains the optimal routing path through the CDN routing selection model.

[0085] The main control module passes the optimal routing path to the CDN control network element, and by redirecting user services, it achieves the optimal routing path to the CDN, allowing users to obtain the best and fastest content services.

[0086] The embodiments of this application provide a method for optimal routing of CDN user requests based on reinforcement learning AI technology. This method addresses the intelligent routing selection issues in existing CDN technologies, including the complexity and dynamics of network topology, the diversity of user requests, node failures, and network congestion. The main innovations and improvements are as follows:

[0087] 1. Application of reinforcement learning algorithm: Using reinforcement learning algorithm to establish CDN routing model, it has the characteristics of intelligence and adaptability. Through continuous trial and error and learning, the CDN routing model can gradually optimize the routing strategy and improve the CDN service quality and user experience.

[0088] 2. Design based on CDN network topology information (such as CDN network topology structure and performance indicators): Taking CDN network topology information as input, the design is suitable for the state and action space of CDN. It has the characteristics of adaptability and can select the best routing strategy according to different situations to improve user experience.

[0089] 3. Improve service quality and user experience: The ultimate goal is to improve the service quality and user experience of CDN. Through intelligent routing selection and optimization strategies, user experience and satisfaction can be effectively improved.

[0090] Compared with the traditional CDN routing method, this embodiment has at least the following advantages:

[0091] 1. Intelligence: This embodiment uses a reinforcement learning algorithm to establish a CDN routing model. It is intelligent and can automatically learn and optimize routing strategies to adapt to the dynamic CDN network topology and the diversity of user requests.

[0092] 2. Adaptability: This embodiment is based on CDN network topology information (such as CDN network topology structure and performance indicators), and is designed to be suitable for the state and action space of CDN. It has the characteristics of adaptability and can select the best routing strategy according to different situations to improve user experience.

[0093] 3. Improve service quality and user experience: The ultimate goal of this embodiment is to improve the service quality and user experience of the CDN. Through intelligent routing selection and optimization strategies, user experience and satisfaction can be effectively improved.

[0094] In summary, the technical solution of this embodiment has significant practical value and economic benefits. It can solve the intelligent routing problem in existing CDN technology, thereby improving CDN service quality and user experience. This technical solution can provide CDN providers with a more efficient content delivery network, enhance user stickiness and satisfaction, and has very broad commercial application prospects and social significance.

[0095] This embodiment can provide more ideas and solutions for the development and application of CDN technology. By using reinforcement learning AI technology to establish an intelligent CDN routing model, it can effectively improve CDN service quality and user experience. This solution is not only highly technical and innovative, but also has broad application prospects and commercial value in practical applications.

[0096] FIG3 shows a schematic structural diagram of a CDN routing device provided in an embodiment of the present application. The device 300 includes the following modules.

[0097] The acquisition module 302 is configured to acquire CDN routing request information, where the CDN routing request information is used to request a routing result.

[0098] The output module 304 is configured to obtain a routing result that matches the CDN routing request based on the CDN routing request information, the CDN network topology information, and the CDN routing selection model; wherein the CDN routing selection model is configured to output the routing result.

[0099] In the embodiments of the present application, routing results are obtained based on CDN network topology information and a CDN routing model. The CDN routing model can automatically learn and optimize routing strategies. Through continuous trial and error and learning, the routing strategies can be gradually optimized, thereby improving the service quality and user experience of the CDN. Routing results are obtained based on real-time CDN network topology information, which is conducive to obtaining the optimal routing results and improving the service quality and user experience of the CDN.

[0100] In one embodiment, the device further includes a model training module for generating or iteratively training the CDN routing selection model using a reinforcement learning algorithm based on training set data; wherein the training set data includes: the CDN routing request information, the CDN network topology information, and routing results matching the CDN routing request.

[0101] In one embodiment, the CDN routing request information includes at least one of the following: user IP address, MD5 data of user requested content, and user special requirement file information; or the CDN network topology information includes at least one of the following: CDN network element service operation status information, CDN network link status information, and CDN network element hardware indicator information.

[0102] In one embodiment, the acquisition module 302 is further used for at least one of the following: 1) obtaining the CDN network element operation status log from the log file system of the CDN network, and obtaining the CDN network element service operation status information based on the CDN network element operation status log; 2) obtaining the CDN network link status information based on the network link status log of the CDN network; 3) obtaining the CDN network element operation parameters from the data acquisition interface of the CDN network, and obtaining the CDN network element hardware indicator information based on the CDN network element operation parameters.

[0103] In one embodiment, the routing result that matches the CDN routing request includes one of the following: 1) the best routing result that matches the user IP address and the MD5 data of the user request content; 2) the routing result that matches the user's special request file information.

[0104] In one embodiment, the device further includes a transmission module, configured to transmit the routing result to a CDN control network element, so that the CDN control network element realizes the routing path arrival of the CDN by redirecting the user service.

[0105] In one embodiment, the acquisition module 302 is further configured to acquire CDN log files; and generate a CDN network topology diagram based on the CDN log files.

[0106] In one embodiment, the acquisition module 302 is configured to perform streaming analysis and calculation on the CDN log file based on CDN log file analysis technology and network topology awareness technology to generate a CDN network topology diagram.

[0107] The device 300 provided in the embodiment of the present application can execute the various methods described in the above method embodiments and realize the functions and beneficial effects of the various methods described in the above method embodiments, which will not be repeated here.

[0108] FIG4 shows a schematic diagram of the hardware structure of an electronic device that implements an embodiment of the present application. Referring to the figure, at the hardware level, the electronic device includes a processor, and optionally, an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage device. Of course, the electronic device may also include hardware required for other services.

[0109] The processor, network interface, and memory can be interconnected via an internal bus, such as an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. These buses can be classified as address buses, data buses, and control buses. For ease of illustration, the figure uses only one bidirectional arrow, but this does not imply that there is only one bus or only one type of bus.

[0110] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0111] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, logically forming a device for locating the target user. The processor executes the program stored in the memory and is specifically configured to perform the methods disclosed in the embodiments shown in Figures 1-2 and to achieve the functions and benefits of the various methods described in the preceding method embodiments, which will not be further described here.

[0112] The methods disclosed in the embodiments shown in Figures 1-2 of the present application can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0113] The electronic device can also execute the methods described in the above method embodiments and realize the functions and beneficial effects of the methods described in the above method embodiments, which will not be described in detail here.

[0114] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0115] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method disclosed in the embodiment shown in Figures 1-2 and realizes the functions and beneficial effects of the various methods described in the previous method embodiments, which will not be repeated here.

[0116] The computer-readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0117] Furthermore, an embodiment of the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the following process is implemented: the method disclosed in the embodiment shown in Figures 1-2 and the functions and beneficial effects of the various methods described in the previous method embodiments are implemented, which will not be repeated here.

[0118] In short, the above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0119] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0120] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0122] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

Claims

1. A CDN routing method, comprising: Obtain CDN routing request information, where the CDN routing request information is used to request a routing result; Based on the CDN routing request information, CDN network topology information and a CDN routing selection model, a routing result matching the CDN routing request is obtained; wherein the CDN routing selection model is used to output the routing result.

2. The method according to claim 1, wherein: The method further comprises: Based on the training set data, a reinforcement learning algorithm is used to generate or iteratively train the CDN routing selection model; The training set data includes: the CDN routing request information, the CDN network topology information, and the routing result matching the CDN routing request.

3. The method according to claim 1 or 2, wherein: The CDN routing request information includes at least one of the following: user IP address, MD5 data of user requested content, user special request file information; or The CDN network topology information includes at least one of the following: CDN network element service operation status information, CDN network link status information, and CDN network element hardware indicator information.

4. The method according to claim 3, wherein: The method further comprises at least one of the following: Obtaining a CDN network element operation status log from a log file system of the CDN network, and obtaining the CDN network element service operation status information based on the CDN network element operation status log; Obtaining the CDN network link status information based on the network link status log of the CDN network; Obtain CDN network element operation parameters from a data collection interface of the CDN network, and obtain the CDN network element hardware indicator information based on the CDN network element operation parameters.

5. The method according to claim 3, wherein: The routing result matching the CDN routing request includes one of the following: The best routing result that matches the user IP address and the MD5 data of the user request content; The routing result that matches the user's special requirement file information.

6. The method according to any one of claims 1 to 5, wherein: After obtaining the routing result matching the CDN routing request, the method further includes: The routing result is passed to the CDN control network element, so that the CDN control network element realizes the routing path arrival of the CDN by redirecting the user service.

7. The method according to claim 1, wherein: The CDN network topology information includes a CDN network topology structure diagram, and the method further includes: Get CDN log files; A CDN network topology diagram is generated based on the CDN log file.

8. The method according to claim 7, wherein: Generating a CDN network topology diagram based on the CDN log file includes: Based on CDN log file analysis technology and network topology perception technology, streaming analysis and calculation are performed on the CDN log file to generate a CDN network topology diagram.

9. A CDN routing device, comprising: An acquisition module, used to acquire CDN pathfinding request information, wherein the CDN pathfinding request information is used to request a routing result; An output module is used to obtain a routing result matching the CDN routing request based on the CDN routing request information, the CDN network topology information and the CDN routing selection model; wherein the CDN routing selection model is used to output the routing result.

10. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to perform the steps of the method of any one of claims 1 to 8.

11. A computer-readable medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute the steps of the method according to any one of claims 1 to 8.

Images