[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2023125175A1 - 一种算路系统路径推荐方法及相关设备 - Google Patents

一种算路系统路径推荐方法及相关设备 Download PDF

Info

Publication number
WO2023125175A1
WO2023125175A1 PCT/CN2022/140542 CN2022140542W WO2023125175A1 WO 2023125175 A1 WO2023125175 A1 WO 2023125175A1 CN 2022140542 W CN2022140542 W CN 2022140542W WO 2023125175 A1 WO2023125175 A1 WO 2023125175A1
Authority
WO
WIPO (PCT)
Prior art keywords
control device
paths
network
network path
path
Prior art date
Application number
PCT/CN2022/140542
Other languages
English (en)
French (fr)
Inventor
崔文琦
王宇辰
王阳
王宁
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023125175A1 publication Critical patent/WO2023125175A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/22—Alternate routing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H04L45/123—Evaluation of link metrics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/20—Hop count for routing purposes, e.g. TTL
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/24—Multipath
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/24—Multipath
    • H04L45/247—Multipath using M:N active or standby paths

Definitions

  • the embodiments of the present application relate to the field of information transmission, and in particular to a route recommendation method for a route calculation system and related equipment.
  • the path calculation system is a very important part of the network service distribution process. How to calculate the correct and reasonable network path for the service is very important for customers to save available resources and realize commercial value.
  • the main method adopted is to calculate the shortest network path, and then send the information of the shortest network path to the user.
  • the path calculation system loads information such as business constraints, remaining bandwidth, and delay as high-dimensional weight information through preprocessing, and then calculates the shortest delay, hop count, or distance in the abstract system network topology diagram.
  • the network path, and then the shortest network path in the system network topology diagram is post-processed to obtain the actual shortest network path, that is, the service path used to execute the service.
  • the shortest network path is then sent to the user equipment, and is used to execute corresponding services after being confirmed by the user equipment.
  • the embodiment of the present application provides a path recommendation method and related equipment for a path calculation system, which are used to more flexibly and accurately select a network path required by a user to execute a service.
  • the first aspect of the embodiment of the present application provides a path recommendation method for a route calculation system, which is used to more flexibly and accurately select the network path required by the user to perform services.
  • the route calculation system includes a control device, and the method includes: the control device according to multiple The selection strategy determines the corresponding multiple candidate network paths, and the candidate network paths are the network paths that the control device can use to execute the target service; the control device divides the multiple candidate network paths according to the similarity between the multiple candidate network paths It is a set of multiple network paths; the control device determines multiple optimal paths in multiple network path sets, and the multiple optimal paths correspond to multiple network path sets; the control device compares the multiple optimal paths and the corresponding recommended The information is sent to the user equipment, so that the user equipment determines the target network path according to the multiple optimal paths, and the recommendation information indicates the reason why the control device determines the multiple optimal paths.
  • the control device of the path calculation system determines corresponding multiple candidate network paths according to multiple selection strategies, and then the control device sends multiple optimal paths and corresponding recommendation information to the user equipment, so that the user can Selecting one of the multiple optimal paths as the target network path to execute the target service increases the user's selectivity, thereby meeting the needs of the user, and also increases the accuracy that the target network path is the network path most needed by the user; Moreover, the recommendation information corresponding to the optimal path is also provided to the user equipment, which is convenient for the user to understand and make a choice.
  • the above method further includes: the control device receives confirmation information sent by the user equipment, where the confirmation information instructs the user to determine that the target network path is used to execute the target service.
  • the control device determines the target network path according to the confirmation information of the user, and the target network path is used to execute the target service.
  • the above method further includes: controlling The device determines the ranking scores of the multiple candidate network paths through a sorting algorithm according to the path information of the multiple candidate network paths.
  • the above-mentioned control device determining multiple optimal paths in multiple network path sets includes: the control device determining multiple network path sets according to ranking scores of multiple candidate network paths Multiple optimal paths in .
  • the controller can select multiple optimal paths in each network path set according to the ranking scores of the multiple candidate network paths, so as to recommend them to the user, increasing the user's selectivity.
  • the above method further includes: the control device optimizes the sorting algorithm according to the confirmation information.
  • control device can learn the selection preference of the user online, summarize the real demand of the user, and recommend a network path that better meets the demand for the user.
  • the selection strategy includes: the control device selects a network path that can avoid all faulty nodes in the network; or the control device selects a network path that includes temporary faulty nodes; Network path for network load balancing.
  • control device can select a network path according to a multiple selection strategy to meet different needs of users, increase the possibility of selection by users, and have a better handling method for faults.
  • the recommendation information includes: delay, bandwidth, availability, identifiers of passing network elements, and whether there is a fault point.
  • the second aspect of the embodiment of the present application provides a path recommendation method for a path calculation system, which is used to more flexibly and accurately select the network path required by the user to perform services.
  • the path calculation system includes a control device, and the method includes: the user equipment receives the control device The multiple optimal paths sent and the corresponding recommendation information, the recommendation information indicates the reason why the control device determines the multiple optimal paths; the user equipment determines the target network path, and the target network path is the network indicated by the user for the control device to perform the target service
  • the multiple optimal paths include the target network path; the user equipment sends confirmation information to the control device, and the confirmation information instructs the user to determine the target network path for the control device to execute the target service.
  • the control device of the path calculation system determines corresponding multiple candidate network paths according to multiple selection strategies, and then the control device sends multiple optimal paths and corresponding recommendation information to the user equipment, so that the user can Selecting one of the multiple optimal paths as the target network path to execute the target service increases the user's selectivity, thereby meeting the needs of the user, and also increases the accuracy that the target network path is the network path most needed by the user; Moreover, the recommendation information corresponding to the optimal path is also provided to the user equipment, which is convenient for the user to understand and make a choice.
  • a third aspect of the present application provides a storage system device, where the storage system device has a function of implementing the method in the foregoing first aspect or any possible implementation manner of the first aspect.
  • This function may be implemented by hardware, or may be implemented by executing corresponding software on the hardware.
  • the hardware or software includes one or more modules corresponding to the above functions, such as a sending unit.
  • a fourth aspect of the present application provides a network storage node device, and the network storage node device has a function of implementing the method of the second aspect or any possible implementation manner of the second aspect.
  • This function can be realized by hardware, and can also be realized by executing corresponding software by hardware.
  • the hardware or software includes one or more modules corresponding to the above functions, for example: a receiving unit.
  • the fifth aspect of the present application provides a storage system device, the storage system device includes at least one processor, a memory, an input/output (input/output, I/O) interface, and a program stored in the memory and operable on the processor
  • the computer executes the instruction.
  • the processor executes the method according to the above first aspect or any possible implementation manner of the first aspect.
  • the sixth aspect of the present application provides a network storage node device
  • the network storage node device includes at least one processor, memory, input/output (input/output, I/O) interface and stored in the memory and can be on the processor
  • the running computer executes the instructions, and when the computer executes the instructions are executed by the processor, the processor executes the method according to the second aspect or any possible implementation manner of the second aspect.
  • the seventh aspect of the present application provides a computer-readable storage medium storing one or more computer-executable instructions.
  • the processor executes any one of the above-mentioned first aspect or the first aspect. method of implementation.
  • the eighth aspect of the present application provides a computer-readable storage medium that stores one or more computer-executable instructions.
  • the processor executes any one of the above-mentioned second or second aspects. method of implementation.
  • the ninth aspect of the present application provides a computer program product that stores one or more computer-executable instructions.
  • the processor executes any of the possible implementations of the above-mentioned first aspect or the first aspect. Methods.
  • the tenth aspect of the present application provides a computer program product that stores one or more computer-executable instructions.
  • the processor executes any of the above-mentioned second aspect or any possible implementation of the second aspect. Methods.
  • the eleventh aspect of the present application provides a chip system, where the chip system includes at least one processor, and the at least one processor is configured to implement the functions involved in the above first aspect or any possible implementation manner of the first aspect.
  • the system-on-a-chip may also include a memory, which is used to store necessary program instructions and data of the device for processing the artificial intelligence model.
  • the system-on-a-chip may consist of chips, or may include chips and other discrete devices.
  • a twelfth aspect of the present application provides a system-on-a-chip, where the system-on-a-chip includes at least one processor, and the at least one processor is configured to implement the functions involved in the above-mentioned second aspect or any possible implementation manner of the second aspect.
  • the system-on-a-chip may further include a memory, which is used to store necessary program instructions and data of the device for data processing based on the artificial intelligence model.
  • the system-on-a-chip may consist of chips, or may include chips and other discrete devices.
  • the control device of the path calculation system determines corresponding multiple candidate network paths according to multiple selection strategies, and then the control device sends multiple optimal paths and corresponding recommendation information to the user equipment, so that the user can Selecting one of the multiple optimal paths as the target network path to execute the target service increases the user's selectivity, thereby meeting the needs of the user, and also increases the accuracy that the target network path is the network path most needed by the user; Moreover, the recommendation information corresponding to the optimal path is also provided to the user equipment, which is convenient for the user to understand and make a choice.
  • FIG. 1 is a schematic diagram of a scenario of a path recommended by the path calculation system
  • FIG. 2 is a schematic diagram of a scene of a path recommendation method of a path calculation system in an embodiment of the present application
  • Fig. 3 is a signaling flowchart of the path recommendation method of the path calculation system in the embodiment of the present application.
  • FIG. 4 is a schematic flow diagram of a route recommendation method of the route calculation system in an embodiment of the present application
  • Fig. 5 is another schematic flow chart of the route recommendation method of the route calculation system in the embodiment of the present application.
  • Fig. 6 is another schematic flow chart of the route recommendation method of the route calculation system in the embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of all optimal paths and corresponding recommendation information in the embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a control device in an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a user equipment in an embodiment of the present application.
  • FIG. 10 is another schematic structural diagram of the control device in the embodiment of the present application.
  • FIG. 11 is another schematic structural diagram of user equipment in the embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of a network system in an embodiment of the present application.
  • the embodiment of the present application provides a path recommendation method and related equipment for a path calculation system, which are used to more flexibly and accurately select a network path required by a user to execute a service.
  • the path calculation system is a very important part of the network service distribution process. How to calculate the correct and reasonable network path for the service is crucial to saving available resources for customers and realizing business value.
  • the main method adopted is to calculate the shortest network path, and then send the information of the shortest network path to the user. Specifically, the path calculation system loads information such as business constraints, remaining bandwidth, and delay as high-dimensional weight information through preprocessing, and then calculates the shortest delay, hop count, or distance in the abstract system network topology diagram.
  • the network path, and then the shortest network path in the system network topology diagram is post-processed to obtain the actual shortest network path, that is, the service path used to execute the service.
  • the shortest network path is then sent to the user equipment, and is used to execute corresponding services after being confirmed by the user equipment.
  • the embodiment of the present application provides a route recommendation method for a route calculation system.
  • the method is applied to a route calculation recommendation system.
  • the route calculation recommendation system includes a control device, which can communicate with user equipment and a service system.
  • the service system includes multiple network nodes, and multiple network nodes are connected to each other to form multiple network paths.
  • the route calculation recommendation system stores the identification of all network nodes and the fault status of all network nodes in the business system, so that the service can be determined in the corresponding network node topology map according to the identification of all network nodes and the fault status of all network nodes. network path.
  • the route calculation recommendation system after calculating the multiple network paths available for the service through various strategies, sends the multiple network paths and the recommendation information of the multiple network paths to the user equipment, so that the user can use the user equipment Determine the target network path used to execute the service, and then confirm the target network path through the confirmation information of the user equipment.
  • a process of the route recommendation method of the route calculation system in the embodiment of the present application includes:
  • the control device determines multiple candidate network paths.
  • the control device determines the corresponding multiple candidate network paths through the pathfinding algorithm according to the multiple selection policies and the needs of the user's target service, and the multiple candidate network paths is the network path that can be used to execute the target service.
  • the user's target service requirements include information such as the start node and end node service constraints of the alternative network path in the service system, and may also include the user's target service requirements, such as service types, etc., specifically here No limit.
  • control device may select one or more candidate network paths through a pathfinding algorithm according to any path calculation selection strategy, or may not select a candidate network path that meets the policy requirements.
  • control device can determine multiple candidate network paths through k shortest paths (top-k-shortest paths, KSP) algorithm, and can also determine multiple candidate network paths through other pathfinding algorithms, such as Dijkstra
  • KSP top-k-shortest paths
  • Dijkstra The algorithm is not limited here.
  • the selection strategy can be the following types of selection strategies:
  • the control device selects a network path that can avoid all faulty nodes in the network, so as to ensure that the selected network path supports instant delivery of services and is not affected by faulty nodes.
  • the control device selects a network path including temporary faulty nodes, so as to avoid the situation that a large number of temporary faulty nodes cause the network path to detour too far, and help users find fault points and expandable points.
  • the control device selects a network path that balances the load of the entire network.
  • the control device determines ranking scores of multiple candidate network paths.
  • the control device determines the ranking scores of the multiple candidate network paths through a sorting algorithm according to the path information of the multiple candidate network paths, and the path information includes the topology characteristics of the paths, network nodes and link characteristics passed through.
  • the control device determines the alternative network path 1-10 through the pathfinding algorithm according to the selection strategy 1 and the user's target service requirements (that is, the starting point A, the end point B), and then according to the alternative network path 1-10
  • the path information determines the ranking scores of candidate network paths 1-10 through a sorting algorithm.
  • control device can obtain path information such as the topological characteristics, passing network nodes and link characteristics of each network path through the database, and then use the topological characteristics, passing network nodes and link characteristics of each network path to pass RankNet
  • the model ranks multiple candidate network paths, and calculates the ranking score of each network path.
  • the RankNet model is a ranking algorithm model trained by learning user habits.
  • control device sorts multiple candidate network paths through the RankNet model.
  • sorting algorithm models such as logistic regression models, etc., may also be used, which are not limited here.
  • the control device determines multiple optimal paths in multiple network path sets.
  • control device divides the multiple candidate network paths into multiple network path sets according to the similarity between the multiple candidate network paths, and then the control device determines multiple optimal network paths in the multiple network path sets Paths, multiple optimal paths are in one-to-one correspondence with multiple network path sets.
  • the control device calculates the similarity between any two candidate network paths through the path similarity algorithm according to the path information such as the topology characteristics of multiple candidate network paths, the passing network nodes and link characteristics, and then uses The clustering algorithm divides the candidate network paths whose similarity is higher than the preset value into multiple network path sets, and the similarity of any two network paths in each network path set is higher than the preset value; then the control device Determine the optimal path in each network path set according to the ranking score of each candidate network path, that is, determine the candidate network path with the highest ranking score in each network path set as the optimal path in the candidate network path set , so as to determine multiple optimal paths recommended to users.
  • the path information such as the topology characteristics of multiple candidate network paths, the passing network nodes and link characteristics
  • control device calculates the similarity between any two candidate network paths from path 1 to path 10 through the path similarity algorithm, and then divides path 1
  • the multiple candidate network paths to path 10 are divided into three network path sets, path set one includes: path 1, path 3, path 5 and path 10, path set two includes: path 2, path 4 and path 8, path Set two includes: path 6, path 7 and path 9.
  • the candidate network path with the highest ranking score is determined from each network path set as the candidate network path in the candidate network path set
  • the optimal path can avoid multiple recommended paths being too similar and improve the diversity of recommendation results.
  • the control device sends multiple optimal paths and corresponding recommendation information to the user equipment.
  • the control device sends multiple optimal paths and corresponding recommendation information to the user equipment, where the recommendation information indicates the path characteristics of the corresponding network paths, that is, the reason why the control device recommends the network path to the user.
  • the recommended information of network path 1 is: (estimated time delay: 3500; fault: insufficient bandwidth of line L; solution: widen the bandwidth of line L)
  • the recommended information of network path 2 is: (estimated time delay: 4200; Fault: Line K is degraded; solution: upgrade line K)
  • the recommended information of network path 3 is: (estimated delay: 5000).
  • control device uses LIME technology to obtain the important influencing factors of the RankNet score of the current path through linear model fitting according to the path and similar paths, so that the reason why the path is recommended can be provided in the interface , to improve the interpretability of the algorithm.
  • the recommended information may include recommended information such as delay, bandwidth, passed network element identification, and whether there is a fault point.
  • it may also include other information indicating the characteristics of the network path, such as Availability rate and repair plan, etc., are not limited here.
  • the user equipment determines a target network path.
  • the user equipment determines a target network path, where the target network path is a network path indicated by the user for controlling the device to execute the target service, and the multiple optimal paths include the target network path.
  • the user equipment After receiving multiple optimal paths and corresponding recommendation information sent by the control device, the user equipment presents the multiple optimal paths and corresponding recommendation information to the user. If a certain path includes a temporarily faulty node, It will also display the repair plan of the return path, and then the user selects the target path that best meets the needs among multiple optimal paths according to the needs to execute the target business.
  • control device may send all optimal paths and corresponding recommendation information to the user equipment, or may send part of the optimal paths and corresponding recommendation information to the user equipment; the user equipment may send all optimal paths and corresponding recommendation information to the user equipment.
  • the corresponding recommendation information is displayed to the user, and some optimal paths and corresponding recommendation information may also be displayed to the user, which is not limited here.
  • the control device receives confirmation information sent by the user equipment.
  • the user equipment sends confirmation information to the control equipment, and accordingly, the control equipment receives the confirmation information sent by the user equipment.
  • the confirmation information indicates that the user determines that the target network path is used to execute the target service, that is, the user selects the target among multiple optimal paths.
  • the network paths carry out the target business.
  • control device determines the target network path according to the confirmation information of the user, and the target network path is used to execute the target service.
  • the control device can send the confirmation information or the identification of the target network path to the service system, and the service system can use the target network path to perform the target task according to the confirmation information or the identification of the target network path.
  • the control device optimizes the sorting algorithm according to the confirmation information.
  • control device After the control device receives the confirmation information sent by the user device, that is, the user's selection result, the control device background will receive feedback, and the control device can train the ranking algorithm model online based on the user's selection result to update the recommendation effect.
  • control device 800 provided in the embodiment of the present application.
  • the control device may be the control device in the above-mentioned FIG. 3, and the control device 800 includes:
  • the first determining module 801 is configured to determine corresponding multiple candidate network paths according to multiple selection strategies, and the candidate network paths are network paths that can be used by the control device to execute target services; for specific implementation methods, please refer to the implementation shown in Figure 3 Step 301 in the example: the control device determines multiple candidate network paths, which will not be repeated here.
  • the fourth determination module 802 is configured to determine the ranking scores of the multiple candidate network paths through a sorting algorithm according to the path information of the multiple candidate network paths. For a specific implementation manner, please refer to step 302 in the embodiment shown in FIG. 3: the control device determines the ranking scores of multiple candidate network paths, which will not be repeated here.
  • the dividing module 803 is used to divide the multiple candidate network paths into multiple network path sets according to the similarity between the multiple candidate network paths; for the specific implementation, please refer to step 303 in the embodiment shown in Figure 3: control The device determines multiple optimal paths in multiple network path sets, which will not be repeated here.
  • the second determining module 804 is configured to determine multiple optimal paths in multiple network path sets, and the multiple optimal paths correspond to multiple network path sets; for specific implementation methods, please refer to the embodiment shown in FIG. 3 Step 303: The control device determines multiple optimal paths in multiple network path sets, which will not be repeated here.
  • the second determining module 804 is specifically configured to: determine multiple optimal paths in multiple network path sets according to ranking scores of multiple candidate network paths. For a specific implementation manner, please refer to step 303 in the embodiment shown in FIG. 3: the control device determines multiple optimal paths in multiple network path sets, which will not be repeated here.
  • the sending module 805 is configured to send multiple optimal paths and corresponding recommendation information to the user equipment, so that the user equipment determines the target network path according to the multiple optimal paths, and the recommendation information indicates the reason why the control device determines the multiple optimal paths ;
  • the control device sends multiple optimal paths and corresponding recommendation information to the user equipment, which will not be repeated here.
  • the receiving module 806 is configured to receive confirmation information sent by the user equipment, where the confirmation information indicates that the user determines that the target network path is used to execute the target service.
  • the control device receives the confirmation information sent by the user equipment, which will not be repeated here.
  • the third determining module 807 is configured to determine a target network path according to the confirmation information of the user, and the target network path is used to execute the target service.
  • the control device receives the confirmation information sent by the user equipment, which will not be repeated here.
  • An optimization module 808, configured to optimize the sorting algorithm according to the confirmation information.
  • the control device optimizes the sorting algorithm according to the confirmation information, which will not be repeated here.
  • control device may perform the operations performed by the control device in any one of the embodiments shown in FIG. 3 , which will not be detailed here.
  • the user equipment in the embodiment of the present application is described below. Please refer to FIG. 9, a user equipment 900 provided in the embodiment of the present application.
  • the user equipment may be the user equipment in the above-mentioned FIG. 3, and the user equipment 900 includes:
  • the receiving module 901 is configured to receive multiple optimal paths and corresponding recommendation information sent by the control device, and the recommendation information indicates the reasons why the control device determines multiple optimal paths; for specific implementation methods, please refer to the steps in the embodiment shown in Figure 3 304: The control device sends multiple optimal paths and corresponding recommendation information to the user equipment, which will not be repeated here.
  • the determination module 902 is used to determine the target network path, the target network path is the network path indicated by the user for controlling the device to execute the target service, and multiple optimal paths include the target network path; for specific implementation methods, please refer to the implementation shown in Figure 3 Step 305 in the example: the user equipment determines the target network path, which will not be repeated here.
  • the sending module 903 is configured to send confirmation information to the control device, where the confirmation information instructs the user to determine the target network path for the control device to execute the target service.
  • the control device receives the confirmation information sent by the user equipment, which will not be repeated here.
  • the user equipment may perform the operations performed by the user equipment in any one of the embodiments shown in FIG. 3 , which will not be detailed here.
  • FIG. 10 is a schematic structural diagram of a control device provided by an embodiment of the present application.
  • the control device 1000 may include one or more central processing units (central processing units, CPU) 1001 and a memory 1005, and the memory 1005 stores one or one above applications or data.
  • CPU central processing units
  • the storage 1005 may be a volatile storage or a persistent storage.
  • the program stored in the memory 1005 may include one or more modules, and each module may include a series of instructions to operate on the control device.
  • the central processing unit 1001 may be configured to communicate with the memory 1005 , and execute a series of instruction operations in the memory 1005 on the control device 1000 .
  • the central processing unit 1001 is used to execute the computer program in the memory 1005, so that the control device 1000 is used to execute: the control device determines corresponding multiple candidate network paths according to multiple selection strategies, and the candidate network paths are available to the control device The network path for executing the target service; the control device divides the multiple candidate network paths into multiple network path sets according to the similarity between the multiple candidate network paths; the control device determines the multiple optimal network paths in the multiple network path sets Optimal paths, multiple optimal paths correspond to multiple network path sets one-to-one; the control device sends multiple optimal paths and corresponding recommendation information to the user equipment, so that the user equipment determines the target network path according to the multiple optimal paths , the recommendation information indicates the reason why the control device determines multiple optimal paths.
  • steps 301-308 in the embodiment shown in FIG. 3 which will not be repeated here.
  • the control device 1000 can also include one or more power supplies 1002, one or more wired or wireless network interfaces 1003, one or more input and output interfaces 1004, and/or, one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • one or more operating systems such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the control device 1000 may perform the operations performed by the first control device in the foregoing embodiment shown in FIG. 3 , and the details will not be repeated here.
  • FIG. 11 is a schematic structural diagram of a user equipment provided by an embodiment of the present application.
  • the user equipment 1100 may include one or more central processing units (central processing units, CPU) 1101 and a memory 1105, and the memory 1105 stores one or one above applications or data.
  • CPU central processing units
  • the storage 1105 may be a volatile storage or a persistent storage.
  • the program stored in the memory 1105 may include one or more modules, and each module may include a series of instructions to operate on the user equipment.
  • the central processing unit 1101 may be configured to communicate with the memory 1105 , and execute a series of instruction operations in the memory 1105 on the user equipment 1100 .
  • the central processing unit 1101 is used to execute the computer program in the memory 1105, so that the user equipment 1100 is used to perform: the user equipment receives multiple optimal paths and corresponding recommendation information sent by the control equipment, and the recommendation information instructs the control equipment to determine more The reason for the optimal path; the user equipment determines the target network path, the target network path is the network path indicated by the user for the control device to execute the target service, and multiple optimal paths include the target network path; the user equipment sends a confirmation message to the control device , the confirmation information instructs the user to determine the target network path for controlling the device to perform the target service; for the specific implementation, please refer to steps 301-308 in the embodiment shown in FIG. 3 , which will not be repeated here.
  • User equipment 1100 may also include one or more power sources 1102, one or more wired or wireless network interfaces 1103, one or more input and output interfaces 1104, and/or, one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • one or more operating systems such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the user equipment 1100 may perform the operations performed by the user equipment in the foregoing embodiment shown in FIG. 3 , which will not be detailed here.
  • FIG. 12 is a schematic diagram of a network system 1200 provided by an embodiment of the present application.
  • the network system 1200 may include a user equipment 1201, a route calculation system 1202, and a service system 1203.
  • the route calculation system 1202 includes a control device 1204.
  • the user equipment 1201, The route calculation system 1202 and the service system 1203 are used to execute the operations performed by the user equipment, the route calculation system, the control device and the service system in the embodiment shown in FIG. 3 , and details are not repeated here.
  • the disclosed system, device and method can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • a unit described as a separate component may or may not be physically separated, and a component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
  • the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a control device, etc.) execute all or part of the steps of the methods in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), magnetic disk or optical disc, etc., which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请实施例公开了一种算路系统路径推荐方法及相关设备，用于更加灵活准确地选择用户需要的网络路径执行业务。本申请实施例方法包括：控制设备根据多个选择策略确定对应的多条备选网络路径，备选网络路径为控制设备可用于执行目标业务的网络路径；控制设备根据多条备选网络路径之间的相似度将多条备选网络路径划分为多个网络路径集合；控制设备确定多个网络路径集合中的多条最优路径，多条最优路径与多个网络路径集合一一对应；控制设备将多条最优路径及对应的推荐信息发送给用户设备，以使得用户设备根据多条最优路径确定目标网络路径，推荐信息指示控制设备确定多条最优路径的原因。

Description

一种算路系统路径推荐方法及相关设备
本申请要求于2021年12月31日提交中国专利局、申请号为CN202111676100.2、申请名称为“一种算路系统路径推荐方法及相关设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及信息传输领域，尤其涉及一种算路系统路径推荐方法及相关设备。
背景技术
在网络的业务下发过程中，算路系统是非常重要的一部分，如何为业务算出正确合理的网络路径，对客户节约可用资源，实现商业价值至关重要。
在传统的算路系统中，采用的主要方式是计算出最短的网络路径，然后将最短的网络路径的信息发送给用户。具体地，算路系统通过预处理，将业务约束、剩余带宽和时延等信息加载为高维权重信息，然后再在抽象的系统网络拓扑图中计算出时延、跳数或距离等最短的网络路径，再将系统网络拓扑图中的最短的网络路径通过后处理得到实际的最短网络路径，即用于执行业务的业务路径。再将该最短网络路径发送给用户设备，经过用户设备确认后用于执行相应地业务。
现有的算路系统路径推荐方法中，很难识别用户当时的真实意图，只将该最短网络路径发送给用户设备，寻路方式及发送给用户的网络路径单一。
发明内容
本申请实施例提供了一种算路系统路径推荐方法及相关设备，用于更加灵活准确地选择用户需要的网络路径执行业务。
本申请实施例第一方面提供了一种算路系统路径推荐方法，用于更加灵活准确地选择用户需要的网络路径执行业务，该算路系统包括控制设备，该方法包括：控制设备根据多个选择策略确定对应的多条备选网络路径，备选网络路径为控制设备可用于执行目标业务的网络路径；控制设备根据多条备选网络路径之间的相似度将多条备选网络路径划分为多个网络路径集合；控制设备确定多个网络路径集合中的多条最优路径，多条最优路径与多个网络路径集合一一对应；控制设备将多条最优路径及对应的推荐信息发送给用户设备，以使得用户设备根据多条最优路径确定目标网络路径，推荐信息指示控制设备确定多条最优路径的原因。
本申请实施例中，算路系统的控制设备向根据多个选择策略确定对应的多条备选网络路径，然后控制设备向用户设备发送多条最优路径及对应的推荐信息，从而使得用户可以在多条最优路径中选择一条作为目标网络路径来执行目标业务，增加了用户的可选择性，从而可以满足用户的需求，也增加了目标网络路径是用户最需要的网络路径的准确性；并且给用户设备的还包括最优路径对应的推荐信息，方便用户理解并进行选择。
在第一方面的一种可能的实现方式中，上述方法还包括：控制设备接收用户设备发送的确认信息，确认信息指示用户确定目标网络路径用于执行目标业务。控制设备根据用户 的确认信息确定目标网络路径，目标网络路径用于执行目标业务。
在第一方面的一种可能的实现方式中，上述控制设备根据多条备选网络路径之间的相似度将多条备选网络路径划分为多个网络路径集合之前，上述方法还包括：控制设备根据多条备选网络路径的路径信息通过排序算法确定多条备选网络路径的排序分数。
在第一方面的一种可能的实现方式中，上述控制设备确定多个网络路径集合中的多条最优路径，包括：控制设备根据多条备选网络路径的排序分数确定多个网络路径集合中的多条最优路径。
该种可能的实现方式中，控制器可以根据多条备选网络路径的排序分数选择出各个网络路径集合中的多条最优路径，从而可以推荐给用户，增加了用户的可选择性。
在第一方面的一种可能的实现方式中，上述方法还包括：控制设备根据确认信息优化排序算法。
该种可能的实现方式中，控制设备可以在线学习用户的选择偏好，总结用户的真实需求，从而为用户推荐更加符合需求的网络路径。
在第一方面的一种可能的实现方式中，上述选择策略包括：控制设备选择可以规避网络中所有故障节点的网络路径；或控制设备选择包括临时故障节点的网络路径；或控制设备选择使得整个网络负载均衡的网络路径。
该种可能的实现方式中，控制设备可以根据多中选择策略选择网络路径，满足用户的不同需求，增加用户的选择可能性，对于故障也有更好的处理方式。
在第一方面的一种可能的实现方式中，上述推荐信息包括：时延、带宽、可用率、经过的网元标识和是否存在故障点。
本申请实施例第二方面提供了一种算路系统路径推荐方法，用于更加灵活准确地选择用户需要的网络路径执行业务，该算路系统包括控制设备，该方法包括：用户设备接收控制设备发送的多条最优路径及对应的推荐信息，推荐信息指示控制设备确定多条最优路径的原因；用户设备确定目标网络路径，目标网络路径为用户指示的用于控制设备执行目标业务的网络路径，多条最优路径包括目标网络路径；用户设备向控制设备发送确认信息，确认信息指示用户确定目标网络路径用于控制设备执行目标业务。
本申请实施例中，算路系统的控制设备向根据多个选择策略确定对应的多条备选网络路径，然后控制设备向用户设备发送多条最优路径及对应的推荐信息，从而使得用户可以在多条最优路径中选择一条作为目标网络路径来执行目标业务，增加了用户的可选择性，从而可以满足用户的需求，也增加了目标网络路径是用户最需要的网络路径的准确性；并且给用户设备的还包括最优路径对应的推荐信息，方便用户理解并进行选择。
本申请第三方面提供一种存储系统设备，该存储系统设备具有实现上述第一方面或第一方面任意一种可能实现方式的方法的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块，例如：发送单元。
本申请第四方面提供一种网络存储节点设备，该网络存储节点设备具有实现上述第二方面或第二方面任意一种可能实现方式的方法的功能。该功能可以通过硬件实现，也可以 通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块，例如：接收单元。
本申请第五方面提供一种存储系统设备，该存储系统设备包括至少一个处理器、存储器、输入/输出(input/output，I/O)接口以及存储在存储器中并可在处理器上运行的计算机执行指令，当计算机执行指令被处理器执行时，处理器执行如上述第一方面或第一方面任意一种可能的实现方式的方法。
本申请第六方面提供一种网络存储节点设备，该网络存储节点设备包括至少一个处理器、存储器、输入/输出(input/output，I/O)接口以及存储在存储器中并可在处理器上运行的计算机执行指令，当计算机执行指令被处理器执行时，处理器执行如上述第二方面或第二方面任意一种可能的实现方式的方法。
本申请第七方面提供一种存储一个或多个计算机执行指令的计算机可读存储介质，当计算机执行指令被处理器执行时，处理器执行如上述第一方面或第一方面任意一种可能的实现方式的方法。
本申请第八方面提供一种存储一个或多个计算机执行指令的计算机可读存储介质，当计算机执行指令被处理器执行时，处理器执行如上述第二方面或第二方面任意一种可能的实现方式的方法。
本申请第九方面提供一种存储一个或多个计算机执行指令的计算机程序产品，当计算机执行指令被处理器执行时，处理器执行如上述第一方面或第一方面任意一种可能的实现方式的方法。
本申请第十方面提供一种存储一个或多个计算机执行指令的计算机程序产品，当计算机执行指令被处理器执行时，处理器执行如上述第二方面或第二方面任意一种可能的实现方式的方法。
本申请第十一方面提供了一种芯片系统，该芯片系统包括至少一个处理器，至少一个处理器用于实现上述第一方面或第一方面任意一种可能的实现方式中所涉及的功能。在一种可能的设计中，芯片系统还可以包括存储器，存储器，用于保存处理人工智能模型的装置必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
本申请第十二方面提供了一种芯片系统，该芯片系统包括至少一个处理器，至少一个处理器用于实现上述第二方面或第二方面任意一种可能的实现方式中所涉及的功能。在一种可能的设计中，芯片系统还可以包括存储器，存储器，用于保存基于人工智能模型的数据处理的装置必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
从以上技术方案可以看出，本申请实施例具有以下优点：
本申请实施例中，算路系统的控制设备向根据多个选择策略确定对应的多条备选网络路径，然后控制设备向用户设备发送多条最优路径及对应的推荐信息，从而使得用户可以在多条最优路径中选择一条作为目标网络路径来执行目标业务，增加了用户的可选择性，从而可以满足用户的需求，也增加了目标网络路径是用户最需要的网络路径的准确性；并 且给用户设备的还包括最优路径对应的推荐信息，方便用户理解并进行选择。
附图说明
图1为算路系统推荐路径的场景示意图；
图2为本申请实施例中算路系统路径推荐方法的一个场景示意图；
图3为本申请实施例中算路系统路径推荐方法的一个信令流程图；
图4为本申请实施例中算路系统路径推荐方法的一个流程示意图；
图5为本申请实施例中算路系统路径推荐方法的另一个流程示意图；
图6为本申请实施例中算路系统路径推荐方法的另一个流程示意图；
图7为本申请实施例中所有最优路径及对应的推荐信息的一个结构示意图；
图8为本申请实施例中控制设备的一个结构示意图；
图9为本申请实施例中用户设备的一个结构示意图；
图10为本申请实施例中控制设备的另一个结构示意图；
图11为本申请实施例中用户设备的另一个结构示意图；
图12为本申请实施例中网络系统的一个结构示意图。
具体实施方式
本申请实施例提供了一种算路系统路径推荐方法及相关设备，用于更加灵活准确地选择用户需要的网络路径执行业务。
下面结合附图，对本申请的实施例进行描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。本领域普通技术人员可知，随着技术的发展和新场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
如图1所示，在网络的业务下发过程中，算路系统是非常重要的一部分，如何为业务算出正确合理的网络路径，对客户节约可用资源，实现商业价值至关重要。在传统的算路系统中，采用的主要方式是计算出最短的网络路径，然后将最短的网络路径的信息发送给用户。具体地，算路系统通过预处理，将业务约束、剩余带宽和时延等信息加载为高维权重信息，然后再在抽象的系统网络拓扑图中计算出时延、跳数或距离等最短的网络路径，再将系统网络拓扑图中的最短的网络路径通过后处理得到实际的最短网络路径，即用于执行业务的业务路径。再将该最短网络路径发送给用户设备，经过用户设备确认后用于执行相应地业务。
如图2所示，本申请实施例提供了一种算路系统路径推荐方法，该方法应用于算路推荐系统，该算路推荐系统包括控制设备，该控制设备可以与用户设备和业务系统之间传输信 息，从而为用户提供多个可选择的网络路径以及对应的推荐理由。业务系统中包括多个网络节点，多个网络节点之间相互连接构成多条网络路径。算路推荐系统中存储有业务系统中所有网络节点的标识和所有网络节点的故障状态，从而可以根据所有网络节点的标识和所有网络节点的故障状态在对应的网络节点拓扑图中确定业务可用的网络路径。本申请实施例中，算路推荐系统通过多种策略计算出业务可用的多个网络路径后，将该多个网络路径以及多个网络路径的推荐信息发送给用户设备，从而让用户通过用户设备确定用来执行业务的目标网络路径，然后通过用户设备的确认信息确认目标网络路径。
基于包括上述算路推荐系统，下面对本申请实施例中的算路系统路径推荐方法进行描述：
如图3所示，本申请实施例中的算路系统路径推荐方法的一个流程包括：
301、控制设备确定多条备选网络路径。
如图4所示，在用户设备发起算路指令后，控制设备根据多个选择策略和用户的目标业务的需求通过寻路算法确定对应的多条备选网络路径，该多条备选网络路径为可用于执行目标业务的网络路径。
本申请实施例中，用户的目标业务的需求包括备选网络路径在业务系统中的起点节点、终点节点业务约束等信息，还可以包括用户的目标业务的需求，例如业务类型等，具体此处不做限定。
本申请实施例中，控制设备可以根据任一个算路选择策略通过寻路算法选择出一个或多条备选网络路径，也可以没有选择出满足策略要求的备选网络路径。
本申请实施例中，控制设备可以通过k条最短路径(top-k-shortest pathes，KSP)算法确定多条备选网络路径，也可以通过其他寻路算法确定多条备选网络路径，例如Dijkstra算法，具体此处不做限定。
本申请实施例中，选择策略可以是如下类型的选择策略：
a、控制设备选择可以规避网络中所有故障节点的网络路径，从而保证选择的网络路径支持即时下发业务，不受故障节点的影响。
b、控制设备选择包括临时故障节点的网络路径，从而避免大量临时故障节点导致网络路径绕路太远的情况，并帮助用户发现故障点和可扩容点。
c、控制设备选择使得整个网络负载均衡的网络路径。
本申请实施例中，除了上述类型的选择策略之外，也可以是其他选择策略，具体此处不做限制。
302、控制设备确定多条备选网络路径的排序分数。
如图5所示，控制设备根据多条备选网络路径的路径信息通过排序算法确定多条备选网络路径的排序分数，该路径信息包括路径的拓扑特征、经过的网络节点和链路特征。如图5所示，控制设备根据选择策略一和用户的目标业务的需求(即起点A，终点B)，通过寻路算法确定备选网络路径1-10，然后根据备选网络路径1-10的路径信息通过排序算法确定备选网络路径1-10的排序分数。
具体地，控制设备可以通过数据库获取每条网络路径的拓扑特征、经过的网络节点和 链路特征等路径信息，然后通过每条网络路径的拓扑特征、经过的网络节点和链路特征，通过RankNet模型对多条备选网络路径进行排序，计算出每条网络路径的排序分数，该RankNet模型为通过学习用户习惯训练好的排序算法模型。
本申请实施例中，控制设备通过RankNet模型对多条备选网络路径进行排序，除此之外，还可以使用其他排序算法模型，例如逻辑回归模型等，具体此处不作限定。
303、控制设备确定多个网络路径集合中的多条最优路径。
如图6所示，控制设备根据多条备选网络路径之间的相似度将多条备选网络路径划分为多个网络路径集合，然后控制设备确定多个网络路径集合中的多条最优路径，多条最优路径与多个网络路径集合一一对应。
具体地，控制设备根据多条备选网络路径的拓扑特征、经过的网络节点和链路特征等路径信息，通过路径相似度算法计算出任意两个备选网络路径之间的相似度，然后通过聚类算法将相似度高于预设值的备选网络路径分为多个网络路径集合，每个网络路径集合中的任意两个网络路径的相似度都高于预设值；然后控制设备再根据每条备选网络路径的排序分数确定每个网络路径集合中的最优路径，即确定每个网络路径集合中排序分数最高的备选网络路径为该备选网络路径集合中的最优路径，从而确定推荐给用户的多条最优路径。如图6所示，控制设备通过路径相似度算法计算出路径1至路径10中任意两个备选网络路径之间的相似度，然后根据多条备选网络路径之间的相似度将路径1至路径10这多条备选网络路径划分为三个网络路径集合，路径集合一包括：路径1、路径3、路径5和路径10，路径集合二包括：路径2、路径4和路径8，路径集合二包括：路径6、路径7和路径9。
本申请实施例中，通过将相似度高的备选网络路径分为多个网络路径集合，在从每个网络路径集合中确定排序分数最高的备选网络路径为该备选网络路径集合中的最优路径，可以避免推荐的多条路径过于相似，提高推荐结果的多样性。
304、控制设备将多条最优路径及对应的推荐信息发送给用户设备。
如图7所示，控制设备将多条最优路径及对应的推荐信息发送给用户设备，该推荐信息指示对应的网络路径的路径特征，即控制设备向用户推荐该网络路径的原因。例如图7中，网络路径1的推荐信息为：(预计时延：3500；故障：线路L带宽不足；方案：拓宽线路L带宽)，网络路径2的推荐信息为：(预计时延：4200；故障：线路K降级态；方案：升级线路K)，网络路径3的推荐信息为：(预计时延：5000)。
本申请实施例中，控制设备利用LIME技术，根据路径及相似路径，通过线性模型拟合，可以得到当前路径的RankNet分数的重要的影响因素，这样就可以在界面中提供该路径被推荐的原因，提高算法的可解释性。
本申请实施例中，该推荐信息可以包括：时延、带宽、经过的网元标识和是否存在故障点等推荐信息，除此之外，也可以包括其他指示该网络路径的特征的信息，例如可用率和修复方案等，具体此处不做限定。
305、用户设备确定目标网络路径。
用户设备确定目标网络路径，目标网络路径为用户指示的用于控制设备执行目标业务的网络路径，多条最优路径中包括目标网络路径。
具体地，用户设备在接收到控制设备发送的多条最优路径及对应的推荐信息后，将该多条最优路径及对应的推荐信息展示给用户，若某条路径中包括临时故障节点，还会显示还路径的修复方案，然后用户根据需求在多条最优路径中选出最符合需求的目标路径去执行目标业务。
本申请实施例中，控制设备可以将所有最优路径及对应的推荐信息发送给用户设备，也可以将部分最优路径及对应的推荐信息发送给用户设备；用户设备可以将所有最优路径及对应的推荐信息展示给用户，也可以将部分最优路径及对应的推荐信息展示给用户，具体此处不做限定。
306、控制设备接收用户设备发送的确认信息。
用户设备向控制设备发送确认信息，相应地，控制设备接收用户设备发送的确认信息，该确认信息指示用户确定目标网络路径用于执行目标业务，即用户在多条最优路径中选择了该目标网络路径执行目标业务。
然后控制设备根据用户的确认信息确定目标网络路径，目标网络路径用于执行目标业务。控制设备可以将确认信息或目标网络路径的标识发送给业务系统，业务系统可以根据确认信息或目标网络路径的标识，使用目标网络路径执行目标任务。
307、控制设备根据确认信息优化排序算法。
控制设备在接收到用户设备发送的确认信息即用户的选择结果后，控制设备后台会收到反馈，控制设备可以基于用户的选择结果在线训练排序算法模型，更新推荐效果。
下面对本申请实施例中的控制设备进行描述，请参阅图8，本申请实施例提供的一种控制设备800，该控制设备可以为上述图3中控制设备，该控制设备800包括：
第一确定模块801，用于根据多个选择策略确定对应的多条备选网络路径，备选网络路径为控制设备可用于执行目标业务的网络路径；具体实现方式，请参考图3所示实施例中步骤301：控制设备确定多条备选网络路径，这里不再赘述。
第四确定模块802，用于根据多条备选网络路径的路径信息通过排序算法确定多条备选网络路径的排序分数。具体实现方式，请参考图3所示实施例中步骤302：控制设备确定多条备选网络路径的排序分数，这里不再赘述。
划分模块803，用于根据多条备选网络路径之间的相似度将多条备选网络路径划分为多个网络路径集合；具体实现方式，请参考图3所示实施例中步骤303：控制设备确定多个网络路径集合中的多条最优路径，这里不再赘述。
第二确定模块804，用于确定多个网络路径集合中的多条最优路径，多条最优路径与多个网络路径集合一一对应；具体实现方式，请参考图3所示实施例中步骤303：控制设备确定多个网络路径集合中的多条最优路径，这里不再赘述。
该第二确定模块804具体用于：根据多条备选网络路径的排序分数确定多个网络路径集合中的多条最优路径。具体实现方式，请参考图3所示实施例中步骤303：控制设备确定多个网络路径集合中的多条最优路径，这里不再赘述。
发送模块805，用于将多条最优路径及对应的推荐信息发送给用户设备，以使得用户设备根据多条最优路径确定目标网络路径，推荐信息指示控制设备确定多条最优路径的原 因；具体实现方式，请参考图3所示实施例中步骤304：控制设备将多条最优路径及对应的推荐信息发送给用户设备，这里不再赘述。
接收模块806，用于接收用户设备发送的确认信息，确认信息指示用户确定目标网络路径用于执行目标业务。具体实现方式，请参考图3所示实施例中步骤306：控制设备接收用户设备发送的确认信息，这里不再赘述。
第三确定模块807，用于根据用户的确认信息确定目标网络路径，目标网络路径用于执行目标业务。具体实现方式，请参考图3所示实施例中步骤306：控制设备接收用户设备发送的确认信息，这里不再赘述。
优化模块808，用于根据确认信息优化排序算法。具体实现方式，请参考图3所示实施例中步骤307：控制设备根据确认信息优化排序算法，这里不再赘述。
本实施例中，控制设备可以执行前述图3中任一项所示实施例中控制设备所执行的操作，具体此处不再赘述。
下面对本申请实施例中的用户设备进行描述，请参阅图9，本申请实施例提供的一种用户设备900，该用户设备可以为上述图3中用户设备，该用户设备900包括：
接收模块901，用于接收控制设备发送的多条最优路径及对应的推荐信息，推荐信息指示控制设备确定多条最优路径的原因；具体实现方式，请参考图3所示实施例中步骤304：控制设备将多条最优路径及对应的推荐信息发送给用户设备，这里不再赘述。
确定模块902，用于确定目标网络路径，目标网络路径为用户指示的用于控制设备执行目标业务的网络路径，多条最优路径包括目标网络路径；具体实现方式，请参考图3所示实施例中步骤305：用户设备确定目标网络路径，这里不再赘述。
发送模块903，用于向控制设备发送确认信息，确认信息指示用户确定目标网络路径用于控制设备执行目标业务。具体实现方式，请参考图3所示实施例中步骤306：控制设备接收用户设备发送的确认信息，这里不再赘述。
本实施例中，用户设备可以执行前述图3中任一项所示实施例中用户设备所执行的操作，具体此处不再赘述。
图10是本申请实施例提供的一种控制设备结构示意图，该控制设备1000可以包括一个或一个以上中央处理器(central processing units，CPU)1001和存储器1005，该存储器1005中存储有一个或一个以上的应用程序或数据。
其中，存储器1005可以是易失性存储或持久存储。存储在存储器1005的程序可以包括一个或一个以上模块，每个模块可以包括对控制设备中的一系列指令操作。更进一步地，中央处理器1001可以设置为与存储器1005通信，在控制设备1000上执行存储器1005中的一系列指令操作。
其中，中央处理器1001用于执行存储器1005中的计算机程序，以使得控制设备1000用于执行：控制设备根据多个选择策略确定对应的多条备选网络路径，备选网络路径为控制设备可用于执行目标业务的网络路径；控制设备根据多条备选网络路径之间的相似度将多条备选网络路径划分为多个网络路径集合；控制设备确定多个网络路径集合中的多条最优路径，多条最优路径与多个网络路径集合一一对应；控制设备将多条最优路径及对应的 推荐信息发送给用户设备，以使得用户设备根据多条最优路径确定目标网络路径，推荐信息指示控制设备确定多条最优路径的原因。具体实现方式，请参考图3所示实施例中步骤301-308，此处不再赘述。
控制设备1000还可以包括一个或一个以上电源1002，一个或一个以上有线或无线网络接口1003，一个或一个以上输入输出接口1004，和/或，一个或一个以上操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等。
该控制设备1000可以执行前述图3所示实施例中第一控制设备所执行的操作，具体此处不再赘述。
图11是本申请实施例提供的一种用户设备结构示意图，该用户设备1100可以包括一个或一个以上中央处理器(central processing units，CPU)1101和存储器1105，该存储器1105中存储有一个或一个以上的应用程序或数据。
其中，存储器1105可以是易失性存储或持久存储。存储在存储器1105的程序可以包括一个或一个以上模块，每个模块可以包括对用户设备中的一系列指令操作。更进一步地，中央处理器1101可以设置为与存储器1105通信，在用户设备1100上执行存储器1105中的一系列指令操作。
其中，中央处理器1101用于执行存储器1105中的计算机程序，以使得用户设备1100用于执行：用户设备接收控制设备发送的多条最优路径及对应的推荐信息，推荐信息指示控制设备确定多条最优路径的原因；用户设备确定目标网络路径，目标网络路径为用户指示的用于控制设备执行目标业务的网络路径，多条最优路径包括目标网络路径；用户设备向控制设备发送确认信息，确认信息指示用户确定目标网络路径用于控制设备执行目标业务；具体实现方式，请参考图3所示实施例中步骤301-308，此处不再赘述。
用户设备1100还可以包括一个或一个以上电源1102，一个或一个以上有线或无线网络接口1103，一个或一个以上输入输出接口1104，和/或，一个或一个以上操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等。
该用户设备1100可以执行前述图3所示实施例中用户设备所执行的操作，具体此处不再赘述。
图12为本申请实施例提供的一种网络系统1200示意图，该网络系统1200可以包括用户设备1201、算路系统1202和业务系统1203，该算路系统1202包括控制设备1204，该用户设备1201、算路系统1202和业务系统1203用于执行前述图3所示实施例中用户设备、算路系统、控制设备和业务系统所执行的操作，具体此处不再赘述。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合 或通信连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者控制设备等)执行本申请各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，read-only memory)、随机存取存储器(RAM，random access memory)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (21)

  1. 一种算路系统路径推荐方法，其特征在于，所述算路系统包括控制设备,所述方法包括：
    控制设备根据多个选择策略确定对应的多条备选网络路径，所述备选网络路径为所述控制设备可用于执行目标业务的网络路径；
    所述控制设备根据所述多条备选网络路径之间的相似度将所述多条备选网络路径划分为多个网络路径集合；
    所述控制设备确定所述多个网络路径集合中的多条最优路径，所述多条最优路径与所述多个网络路径集合一一对应；
    所述控制设备将所述多条最优路径及对应的推荐信息发送给用户设备，以使得用户设备根据所述多条最优路径确定目标网络路径，所述推荐信息指示所述控制设备确定所述多条最优路径的原因。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    所述控制设备接收所述用户设备发送的确认信息，所述确认信息指示用户确定所述目标网络路径用于执行目标业务；
    所述控制设备根据用户的确认信息确定目标网络路径，所述目标网络路径用于执行目标业务。
  3. 根据权利要求2所述的方法，其特征在于，在所述控制设备根据所述多条备选网络路径之间的相似度将所述多条备选网络路径划分为多个网络路径集合之前，所述方法还包括：
    所述控制设备根据所述多条备选网络路径的路径信息通过排序算法确定所述多条备选网络路径的排序分数。
  4. 根据权利要求3所述的方法，其特征在于，所述控制设备确定所述多个网络路径集合中的多条最优路径，包括：
    所述控制设备根据所述多条备选网络路径的排序分数确定所述多个网络路径集合中的多条最优路径。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    所述控制设备根据所述确认信息优化所述排序算法。
  6. 根据权利要求1所述的方法，其特征在于，所述选择策略包括：
    所述控制设备选择可以规避网络中所有故障节点的网络路径；或
    所述控制设备选择包括临时故障节点的网络路径；或
    所述控制设备选择使得整个网络负载均衡的网络路径。
  7. 根据权利要求1所述的方法，其特征在于，所述推荐信息包括：时延、带宽、可用率、经过的网元标识和是否存在故障点。
  8. 一种算路系统路径推荐方法，其特征在于，所述方法包括：
    用户设备接收控制设备发送的多条最优路径及对应的推荐信息，所述推荐信息指示所述控制设备确定所述多条最优路径的原因；
    所述用户设备确定目标网络路径，所述目标网络路径为所述用户指示的用于所述控制设备执行目标业务的网络路径，所述多条最优路径包括所述目标网络路径；
    所述用户设备向所述控制设备发送确认信息，所述确认信息指示所述用户确定所述目标网络路径用于所述控制设备执行目标业务。
  9. 一种控制设备，其特征在于，所述控制设备包括：
    第一确定模块，用于根据多个选择策略确定对应的多条备选网络路径，所述备选网络路径为所述控制设备可用于执行目标业务的网络路径；
    划分模块，用于根据所述多条备选网络路径之间的相似度将所述多条备选网络路径划分为多个网络路径集合；
    第二确定模块，用于确定所述多个网络路径集合中的多条最优路径，所述多条最优路径与所述多个网络路径集合一一对应；
    发送模块，用于将所述多条最优路径及对应的推荐信息发送给用户设备，以使得用户设备根据所述多条最优路径确定目标网络路径，所述推荐信息指示所述控制设备确定所述多条最优路径的原因。
  10. 根据权利要求9所述的控制设备，其特征在于，所述控制设备还包括：
    接收模块，用于接收所述用户设备发送的确认信息，所述确认信息指示用户确定所述目标网络路径用于执行目标业务；
    第三确定模块，用于根据用户的确认信息确定目标网络路径，所述目标网络路径用于执行目标业务。
  11. 根据权利要求10所述的控制设备，其特征在于，所述控制设备还包括：
    第四确定模块，用于根据所述多条备选网络路径的路径信息通过排序算法确定所述多条备选网络路径的排序分数。
  12. 根据权利要求11所述的控制设备，其特征在于，所述第二确定模块具体用于：
    根据所述多条备选网络路径的排序分数确定所述多个网络路径集合中的多条最优路径。
  13. 根据权利要求12所述的控制设备，其特征在于，所述控制设备还包括：
    优化模块，用于根据所述确认信息优化所述排序算法。
  14. 一种用户设备，其特征在于，所述用户设备包括：
    接收模块，用于接收控制设备发送的多条最优路径及对应的推荐信息，所述推荐信息指示所述控制设备确定所述多条最优路径的原因；
    确定模块，用于确定目标网络路径，所述目标网络路径为所述用户指示的用于所述控制设备执行目标业务的网络路径，所述多条最优路径包括所述目标网络路径；
    发送模块，用于向所述控制设备发送确认信息，所述确认信息指示所述用户确定所述目标网络路径用于所述控制设备执行目标业务。
  15. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1-7任一项所述的方法。
  16. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序 被处理器执行时实现如权利要求8所述的方法。
  17. 一种控制器，其特征在于，包括处理器和存储有计算机程序的计算机可读存储介质；
    所述处理器与所述计算机可读存储介质耦合，所述计算机程序被所述处理器执行时实现如权利要求1-7任一项所述的方法。
  18. 一种路由器，其特征在于，包括处理器和存储有计算机程序的计算机可读存储介质；
    所述处理器与所述计算机可读存储介质耦合，所述计算机程序被所述处理器执行时实现如权利要求8所述的方法。
  19. 一种芯片系统，其特征在于，包括处理器，所述处理器被调用用于执行如权利要求1-7任一项所述的方法。
  20. 一种芯片系统，其特征在于，包括处理器，所述处理器被调用用于执行如权利要求8所述的方法。
  21. 一种网络系统，其特征在于，所述网络系统包括权利要求9-13中任一项所述的控制设备和权利要求14所述的用户设备。
PCT/CN2022/140542 2021-12-31 2022-12-21 一种算路系统路径推荐方法及相关设备 WO2023125175A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111676100.2 2021-12-31
CN202111676100.2A CN116418737A (zh) 2021-12-31 2021-12-31 一种算路系统路径推荐方法及相关设备

Publications (1)

Publication Number Publication Date
WO2023125175A1 true WO2023125175A1 (zh) 2023-07-06

Family

ID=86997781

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/140542 WO2023125175A1 (zh) 2021-12-31 2022-12-21 一种算路系统路径推荐方法及相关设备

Country Status (2)

Country Link
CN (1) CN116418737A (zh)
WO (1) WO2023125175A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118921321A (zh) * 2024-07-17 2024-11-08 北京翼鸥教育科技有限公司 一种广域网网络路径处理方法、装置、设备及介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104104718A (zh) * 2014-07-02 2014-10-15 北京邮电大学 一种基于软件定义网络的用户自主路由定制系统和方法
CN108512760A (zh) * 2018-03-09 2018-09-07 西安电子科技大学 基于SDN保障业务QoS的路由方法
US20190288933A1 (en) * 2018-01-31 2019-09-19 International Business Machines Corporation Distributed storage path configuration
CN110569450A (zh) * 2018-05-18 2019-12-13 北京搜狗科技发展有限公司 一种路径推荐方法及装置
CN110661704A (zh) * 2018-06-30 2020-01-07 华为技术有限公司 转发路径的计算方法及sdn控制器
US20210392072A1 (en) * 2020-06-16 2021-12-16 Nokia Solutions And Networks Oy Supporting candidate path selection

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8751638B2 (en) * 2010-07-02 2014-06-10 Futurewei Technologies, Inc. System and method to implement joint server selection and path selection
CN110661715B (zh) * 2018-06-28 2022-04-19 中兴通讯股份有限公司 一种业务路径优化方法、装置、设备及可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104104718A (zh) * 2014-07-02 2014-10-15 北京邮电大学 一种基于软件定义网络的用户自主路由定制系统和方法
US20190288933A1 (en) * 2018-01-31 2019-09-19 International Business Machines Corporation Distributed storage path configuration
CN108512760A (zh) * 2018-03-09 2018-09-07 西安电子科技大学 基于SDN保障业务QoS的路由方法
CN110569450A (zh) * 2018-05-18 2019-12-13 北京搜狗科技发展有限公司 一种路径推荐方法及装置
CN110661704A (zh) * 2018-06-30 2020-01-07 华为技术有限公司 转发路径的计算方法及sdn控制器
US20210392072A1 (en) * 2020-06-16 2021-12-16 Nokia Solutions And Networks Oy Supporting candidate path selection

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118921321A (zh) * 2024-07-17 2024-11-08 北京翼鸥教育科技有限公司 一种广域网网络路径处理方法、装置、设备及介质

Also Published As

Publication number Publication date
CN116418737A (zh) 2023-07-11

Similar Documents

Publication Publication Date Title
CN111148174B (zh) 一种移动边缘计算中服务迁移路径选择方法
CN104641598B (zh) 用于混合通信网络的转发表
CN108076158B (zh) 基于朴素贝叶斯分类器的最小负载路由选择方法及系统
US9110884B2 (en) Message publishing and subscribing method and apparatus
US9680665B2 (en) Apparatus and method for dynamic hybrid routing in SDN networks to avoid congestion and balance loads under changing traffic load
US11411808B2 (en) Managing failover region availability for implementing a failover service
US10498643B2 (en) Method for constructing multipath forwarding rule, apparatus, and system
CN103929492A (zh) 业务链负载均衡方法及其装置、系统
US20230140281A1 (en) Task delegation and cooperation for automated assistants
CN105119840A (zh) 基于sdn使用胖树拓扑结构的数据中心网络负载均衡方法
CN109218213B (zh) 一种流量调控方法及装置
JP2017515244A (ja) オンサイトサービスを提供するシステム及び方法
CN104113482A (zh) 流表更新的方法、装置和系统
KR20200062887A (ko) 강화학습에 기반하여 시스템의 제어 동작의 품질을 보장하기 위한 장치 및 방법
WO2023125175A1 (zh) 一种算路系统路径推荐方法及相关设备
CN109617820A (zh) 一种sdn系统和路由更新方法
CN111817959A (zh) 网络路径管理方法、装置、sdn控制器及可读存储介质
CN112995303B (zh) 跨集群调度方法及装置
CN112825509A (zh) 一种路径切换方法及相关装置
CN109451557B (zh) 一种无线传感器网络动态分簇路由方法及装置
WO2021212823A1 (zh) 一种重新路由方法及装置、电子设备、计算机可读介质
WO2022188592A1 (zh) 一种服务器的选择方法、装置、设备及介质
CN101984596A (zh) 一种避免路由黑洞的方法、装置及路由设备
CN105743786A (zh) 一种软件定义无线网络映射方法及装置
CN112866120A (zh) 基于分类搜索的sdn流表无环一致性更新方法和系统

Legal Events

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

Ref document number: 22914429

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22914429

Country of ref document: EP

Kind code of ref document: A1