WO2021190050A1 - 监控业务的方法、装置和系统 - Google Patents

监控业务的方法、装置和系统 Download PDF

Info

Publication number
WO2021190050A1
WO2021190050A1 PCT/CN2020/141354 CN2020141354W WO2021190050A1 WO 2021190050 A1 WO2021190050 A1 WO 2021190050A1 CN 2020141354 W CN2020141354 W CN 2020141354W WO 2021190050 A1 WO2021190050 A1 WO 2021190050A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
data packet
stage
stage category
category
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2020/141354
Other languages
English (en)
French (fr)
Inventor
刘敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
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 Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to EP20927202.0A priority Critical patent/EP4106334B1/en
Publication of WO2021190050A1 publication Critical patent/WO2021190050A1/zh
Priority to US17/951,744 priority patent/US12341666B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5003—Managing SLA; Interaction between SLA and QoS
    • H04L41/5009—Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/069—Management of faults, events, alarms or notifications using logs of notifications; Post-processing of notifications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5061—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the interaction between service providers and their network customers, e.g. customer relationship management
    • H04L41/5067—Customer-centric QoS measurements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/508—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement
    • H04L41/509—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement wherein the managed service relates to media content delivery, e.g. audio, video or TV
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H04L43/0894—Packet rate
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/12—Network monitoring probes
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
    • H04N21/647—Control signaling between network components and server or clients; Network processes for video distribution between server and clients, e.g. controlling the quality of the video stream, by dropping packets, protecting content from unauthorised alteration within the network, monitoring of network load, bridging between two different networks, e.g. between IP and wireless

Definitions

  • This application relates to the field of network communication technology, and in particular to a method, device and system for monitoring services.
  • the embodiments of the application provide a method, device, and system for monitoring services, and the operating status of the services can be understood in time by using the application.
  • a method for monitoring services includes:
  • the target service Receive the current data packet of the target service; add detection indication information to the current data packet to obtain the target data packet, where the detection indication information includes the target stage category corresponding to the current data packet, and the target stage category is used to indicate that the current data packet is in the target In the target stage of at least one key stage in the service, the detection indication information is used to indicate the detection of the current data packet; the target data packet is transmitted to the next hop node.
  • the data packet sender of the target service sends a data packet and enters the detection domain through network transmission, and the first detection node in the detection domain receives the data packet (the data packet is the current data packet).
  • the first detection node in the detection domain is hereinafter referred to as the first detection node for short.
  • the first detection node can obtain the stage category of the current data packet (that is, the target stage category), and the target stage category can be used to indicate at least one (at least one indicating one or more) key stages of the current data packet in the target service. The goal stage. Then the first detection node can add detection indication information to the current data packet to obtain the target data packet.
  • the detection indication information includes the target stage category corresponding to the current data packet. Then the first detection node can query the destination address in the target data packet in the forwarding table to obtain the next hop node. Then the first detection node sends the target data packet to the next hop node.
  • the running status of the service can be detected along with the flow based on the stage category to which the data packet belongs, the running status of the service can be understood in time.
  • the method further includes: obtaining the network KPI corresponding to the target stage category, and setting the network KPI corresponding to the target stage category in the detection instruction information, wherein the network KPI corresponding to the target stage category is the target business The network KPI corresponding to when the QoE indicators meet the target ideal conditions in the target stage.
  • the network KPI corresponding to the target stage category refers to the network KPI required in the key stage indicated by the target stage category under the QoE indicator desired by the operation and maintenance personnel (that is, the QoE indicator satisfies the target ideal condition).
  • the target value is different based on different QoE standards.
  • the QoE standard is a scoring standard
  • the QoE index is 0 to 5
  • 5 represents the highest QoE index
  • 0 represents the lowest QoE index
  • the ideal target condition is that the value of the QoE index is greater than Or equal to 4 etc.
  • the first detection node can obtain the network KPI corresponding to the target stage category, and then can set the network KPI in the detection indication information of the current data packet. In this way, other detection nodes in the detection domain can obtain the network KPI corresponding to the target stage category in the detection indication information.
  • the network KPI corresponding to at least one stage category of the target business is obtained; wherein, at least one stage category is used to indicate at least one key stage of the target business, at least one stage category includes the target stage category, and at least one
  • the network KPI corresponding to the stage category is determined according to the historical business data, business type and key parameters of the target business.
  • the key parameters include the target ideal conditions of the QoE index, the parameters of the data packet sending end and the data packet receiving end, or the location of the data packet receiving end.
  • One or more of the location information; the network KPI corresponding to at least one stage category is added to the forwarding table; in the forwarding table, the network KPI corresponding to the target stage category is determined.
  • a node outside the detection domain can determine the network KPIs and key parameters corresponding to at least one stage category of the target business according to the historical business data, business type and key parameters of the target business It includes one or more of the target ideal conditions of the QoE indicator, the location information of the data packet receiving end, or the parameters of the data packet receiving end and the data packet sending end.
  • the statistics node may send the network KPI corresponding to at least one stage category of the target service to the first detection node. In this way, the first detection node can obtain the network KPI corresponding to at least one stage category of the target service. Then the first detection node may add the acquired network KPI corresponding to at least one stage category of the target service to the forwarding table. In this way, the first detection node can obtain the network KPI corresponding to the target stage category in the forwarding table.
  • obtaining the network KPI corresponding to the target stage category includes: obtaining the network KPI corresponding to the target stage category in the current data packet.
  • the data packet sender can obtain the network KPI of the current data packet to the network in real time (that is, the data packet sender can know the network KPI required by the current data packet), and the data packet sender can send the current data
  • the network KPI corresponding to the target stage category of the package is added to the current data package.
  • the current data packet will include the network KPI corresponding to the target stage category.
  • the first detection node may obtain the network KPI corresponding to the target stage category in the current data packet.
  • the method further includes: in the current data packet, obtaining the target stage category corresponding to the current data packet; or, according to the characteristics of the current data packet, determining the target stage category corresponding to the current data packet.
  • the data sending end when sending a data packet, can determine the stage category of the key stage to which the data packet belongs (that is, the target stage category) based on the characteristics of the data packet. Then the data sending end can add the target stage category to the application header of the data packet, and send it to the first detection node along with the data packet.
  • the first detection node receives the data packet, that is, obtains the current data packet, and can obtain the target stage category corresponding to the current data packet in the current data packet. After receiving the current data packet, the first detection node can analyze the characteristics of the current data packet using a traffic classification algorithm (such as in-depth packet analysis or a traffic recognition model) to determine the service type of the current data packet.
  • a traffic classification algorithm such as in-depth packet analysis or a traffic recognition model
  • the current data packet is divided into the key phase to which the current data packet belongs.
  • the phase type of the key phase is the target phase type corresponding to the current data packet. In this way, the first detection node can obtain the target stage category.
  • the target service is a live video service
  • the key phase is any of the head-end collection phase, the initial buffer phase, the scene switching phase, or the head rotation rendering phase.
  • the network KPIs corresponding to the stage categories collected by the headend and the initial cached stage categories include bandwidth; the network KPIs corresponding to the stage categories of scene switching include maximum bandwidth, average bandwidth, and packet loss of key internal images Information; the network KPI corresponding to the stage category of head rotation rendering includes time delay information.
  • the network KPIs corresponding to the stage category of the head-end collection and the stage category of the initial cache include bandwidth. Since the maximum bandwidth, average bandwidth, and packet loss of key internal pictures will affect scene switching, The network KPIs corresponding to the stage category of scene switching include the maximum bandwidth, average bandwidth, and packet loss information of key internal pictures. Since the delay will affect the rendering of the head rotation, the network KPI corresponding to the stage category of the head rotation rendering includes the delay information.
  • a method for monitoring services includes:
  • the target data packet includes detection indication information
  • the detection indication information includes a target stage category
  • the target stage category is used to indicate the target stage of the current data packet in at least one key stage of the target service ;
  • Detect the target data packet according to the detection instruction information to determine the network key performance indicator KPI of the target data packet; if it is determined that the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category, an abnormal event notification is generated, where,
  • the network KPI corresponding to the target stage category is the network KPI corresponding to the target stage of the target business when the QoE index meets the target ideal condition; the abnormal event notification is transmitted to the statistics node.
  • the second detection node receives the target data packet of the target service, where the target data packet includes detection indication information, the detection indication information includes the target stage category, and the target stage category is used to indicate that the current data packet is in the target service At least one of the key stages in the target stage.
  • the second detection node may detect the target data packet according to the detection indication information. Specifically, the second detection node may obtain the target stage category in the detection indication information of the target data packet. Then the second detection node determines the network KPI corresponding to the target stage category. The second detection node can detect only the various network KPIs indicated by the network KPI for the target data packet.
  • the second detection node can determine whether the network KPI of the target data packet meets the network KPI corresponding to the target stage category, and if it is determined that the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category, an abnormal event notification can be generated. Then the second detection node sends an abnormal event notification to the statistics node.
  • the running status of the service can be detected with the package based on the stage category to which the data packet belongs, the running status of the service can be understood in time.
  • the method further includes: obtaining the network KPI corresponding to the target stage category in the detection indication information.
  • the method further includes: receiving a network KPI corresponding to at least one stage category of the target service, wherein the at least one stage category is used to indicate at least one key stage of the target service, and the at least one stage category includes Target stage category, the network KPI corresponding to at least one stage category is determined according to the historical business data of the target business, the business type of the target business and key parameters.
  • the key parameters include the target ideal conditions of the QoE indicator, the data packet sending end and the data packet receiving One or more of the parameters of the terminal or the location information of the data packet receiving terminal; the network KPI corresponding to at least one stage category is added to the forwarding table. In the forwarding table, determine the network KPI corresponding to the target stage category.
  • the statistics node before performing the target business, can send the network KPI corresponding to at least one stage category of the target business to each detection node in the detection domain, so that the second detection node can also obtain the target The network KPI corresponding to at least one stage category of the business. Then the second detection node may add the network KPI corresponding to at least one stage category of the target service to the forwarding table. Specifically, when the statistical node sends the network KPI corresponding to at least one stage category of the target service, it also sends the IP address of the data receiving end.
  • the forwarding table When added to the forwarding table, it can be the destination IP address of the forwarding table (that is, the data packet In the information corresponding to the IP address of the receiving end, a network KPI corresponding to at least one stage category is added.
  • the second detection node when the second detection node does not include the network KPI corresponding to the target stage category in the detection indication information, the second detection node can use the destination IP address and target stage category of the target data packet in the forwarding table to find the target stage category The corresponding network KPI.
  • a method for monitoring services includes:
  • the network KPI corresponding to at least one stage category of the target business determines the network KPI corresponding to at least one stage category of the target business; among them, the key parameters include the target ideal conditions of the QoE index, the parameters of the data packet sending end and the data packet receiving end, or One or more of the location information of the data packet receiving end, at least one stage category is used to indicate at least one key stage of the target business, for any stage category, the network KPI corresponding to the stage category is the key stage to which the stage category belongs The corresponding network KPI when the QoE indicator meets the target ideal condition; the network KPI corresponding to at least one stage category is sent.
  • the key parameters include the target ideal conditions of the QoE index, the parameters of the data packet sending end and the data packet receiving end, or One or more of the location information of the data packet receiving end, at least one stage category is used to indicate at least one key stage of the target business, for any stage category, the network KPI corresponding to the stage category is the key stage to which the stage category belongs The corresponding
  • the statistical node provides a user interface (UI) for the operation and maintenance personnel, and the operation and maintenance personnel provide the statistical node with multiple pieces of historical business data of the target business through the user interface, and each piece of historical business data includes the network KPI and QoE indicators.
  • the operation and maintenance personnel can also input the service type of the target service (such as the video live service type, etc.), the parameters of the data receiving end and the data sending end, the location information of the data receiving end and the data sending end, and the target of the QoE index through the user interface. Ideal conditions (for example, the value of the QoE indicator is higher than a certain value).
  • the statistical node After the statistical node obtains the historical business data, it can divide the historical business data into at least one key stage according to the business type and the characteristics of the historical business data.
  • the target service is a live video service
  • the key phases include the head-end collection phase, the initial caching phase, and the scene switching phase.
  • the target business is the live broadcast business of cloud virtual reality.
  • the key stages include the head-end acquisition stage, the initial caching stage, the scene switching stage, and the head rotation rendering stage.
  • the statistics node can determine the network KPI corresponding to at least one key stage when the QoE indicator meets the target ideal condition based on the network KPI and QoE indicators and key parameters included in each piece of historical business data (here can be obtained through neural network training, or It can be obtained by fitting the relationship function between the network KPI and the QoE index, which is not limited in the embodiment of the present application).
  • the statistical node can obtain the network KPI corresponding to at least one stage of the target service, and the statistical node also obtains the network KPI corresponding to at least one stage category of the target service.
  • the target service is a live video service
  • the parameters of the data packet sender and the data packet receiver include the key quality index (KQI) of image quality, and the key parameters also include video transmission mode and video Codec standards.
  • KQI key quality index
  • sending the network KPI corresponding to at least one stage category includes: sending the network KPI corresponding to at least one stage category to the first detection node of the detection domain; or; sending the network KPI corresponding to at least one stage category
  • the network KPI is sent to each detection node in the detection domain; the detection domain is a network domain that detects the target service.
  • the network KPI corresponding to each stage category is provided for the detection nodes in the detection domain.
  • the method further includes: receiving an abnormal event notification sent by the detection node, where the abnormal event notification is used to indicate that the network KPI of the current data packet of the target service does not meet the network KPI corresponding to the target stage category,
  • the target stage category is used to indicate the target stage of at least one key stage of the current data packet in the target service.
  • the statistical node can timely notify the operation status of the business based on abnormal event notifications.
  • the present application provides an apparatus for monitoring services.
  • the apparatus includes a plurality of modules that execute instructions to implement the method for monitoring services provided in the above-mentioned first aspect.
  • the present application provides an apparatus for monitoring services.
  • the apparatus includes a plurality of modules that execute instructions to implement the method for monitoring services provided in the second aspect.
  • the present application provides an apparatus for monitoring services.
  • the apparatus includes a plurality of modules that execute instructions to implement the method for monitoring services provided in the third aspect.
  • the present application provides a computing device that includes a memory and a processor, and the processor executes computer instructions stored in the memory, so that the computing device executes the monitoring described in the first aspect.
  • Business approach includes a processor, and the processor executes computer instructions stored in the memory, so that the computing device executes the monitoring described in the first aspect.
  • the present application provides a computing device that includes a memory and a processor, and the processor executes computer instructions stored in the memory, so that the computing device executes the monitoring described in the second aspect.
  • Business approach includes a processor, and the processor executes computer instructions stored in the memory, so that the computing device executes the monitoring described in the second aspect.
  • the present application provides a computing device that includes a memory and a processor, and the processor executes computer instructions stored in the memory, so that the computing device executes the monitoring described in the third aspect.
  • Business approach includes a processor, and the processor executes computer instructions stored in the memory, so that the computing device executes the monitoring described in the third aspect.
  • a computer-readable storage medium stores computer instructions.
  • the computing device executes The method for monitoring services described in the first aspect described above, or the computing device may realize the functions of the apparatus described in the fourth aspect.
  • a computer-readable storage medium stores computer instructions.
  • the computing device executes the method for monitoring services described in the second aspect above, or enable the computing device to implement the functions of the apparatus described in the fifth aspect.
  • a computer-readable storage medium stores computer instructions.
  • the computing device executes the method for monitoring services described in the third aspect, or enable the computing device to implement the function of the apparatus described in the sixth aspect.
  • this application provides a computer program product, the computer program product comprising computer instructions, and when the computer instructions are executed by a computing device, the computing device executes the monitoring services described in the first aspect. method.
  • the present application provides a computer program product, the computer program product includes computer instructions, and when the computer instructions are executed by a computing device, the computing device executes the monitoring service described in the second aspect. method.
  • this application provides a computer program product, the computer program product comprising computer instructions, and when the computer instructions are executed by a computing device, the computing device executes the monitoring service described in the second aspect. method.
  • a system for monitoring services includes a first detection node, a second detection node, and a statistics node.
  • the first detection node is the device described in the fourth aspect above
  • the second detection node is the device described in the fifth aspect above
  • the statistical node is the device described in the sixth aspect above.
  • Fig. 1 is a schematic structural diagram of a detection node provided by an exemplary embodiment of the present application
  • Fig. 2 is a schematic structural diagram of a detection node provided by an exemplary embodiment of the present application
  • Fig. 3 is a schematic structural diagram of a computing device provided by an exemplary embodiment of the present application.
  • Fig. 4 is a schematic diagram of an application scenario of a method for monitoring a service provided by an exemplary embodiment of the present application
  • FIG. 5 is a schematic flowchart of a method for monitoring services provided by an exemplary embodiment of the present application
  • FIG. 6 is a schematic flowchart of a method for monitoring services provided by an exemplary embodiment of the present application.
  • FIG. 7 is a schematic diagram of data packet transmission provided by an exemplary embodiment of the present application.
  • FIG. 8 is a schematic diagram of the relationship between the QoE indicator of the video and the network KPI provided by an exemplary embodiment of the present application;
  • FIG. 9 is a schematic flowchart of a method for monitoring services provided by an exemplary embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an apparatus for monitoring services provided by an exemplary embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of an apparatus for monitoring services provided by an exemplary embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of an apparatus for monitoring services provided by an exemplary embodiment of the present application.
  • Fig. 13 is a schematic structural diagram of an apparatus for monitoring services provided by an exemplary embodiment of the present application.
  • QoE the user's subjective perception of the quality and performance of equipment, networks and systems, applications or services.
  • QoE refers to the user's subjective perception of the quality and performance of a certain service.
  • Network KPIs mainly include network bandwidth, delay information, packet loss information, etc.
  • Bandwidth refers to the amount of data that can be transmitted within a unit time.
  • the service is a live broadcast service of cloud virtual reality
  • the KQI may include resolution, frame rate, and so on.
  • the execution subject of this method can be a detection node or a statistics node.
  • the detection node and the statistics node can be hardware devices or software devices.
  • the detection node When the detection node is a software device, the detection node may be a router, a switch, etc. realized by software. When the detection node is a hardware device, the detection node may be a router, a switch, etc. realized by hardware.
  • the statistical node When the statistical node is a software device, the statistical node may be a program installed on a hardware device or the like. When the statistical node is a hardware device, the statistical node may be a computing device such as a server.
  • the detection node may establish a communication connection with the statistics node.
  • the statistical node may send the network KPI corresponding to the stage category of each stage of the service to the detection node (the detailed process is described later).
  • the detection node When the detection node is a hardware device, as shown in Figure 1, a schematic diagram of the structure of a router or a switch is provided.
  • the detection node includes a main control board 101 and an interface board 102.
  • the main control board 101 includes a processor 1011 and a memory 1012.
  • the interface board 102 includes a processor 1021, a memory 1022, and an interface card 1023.
  • a communication connection is established between the main control board 101 and the interface board 102.
  • the processor 1011 may be a central processing unit (Central Processing Unit, CPU), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or the like.
  • the processor 302 may include one or more chips.
  • the memory 1012 may be a read only memory (Read Only Memory, ROM), a static storage device, a dynamic storage device, or a random access memory (Random Access Memory, RAM).
  • the memory 1012 may store computer instructions. When the computer instructions stored in the memory 1012 are executed by the processor 1011, the processor 1011 executes the method of monitoring services.
  • the processor 1021 may be a CPU, an application specific integrated circuit ASIC, or the like.
  • the processor 1021 may include one or more chips.
  • the memory 1022 may be a ROM, a static storage device, a dynamic storage device, or RAM.
  • the memory 1022 may store computer instructions. When the computer instructions stored in the memory 1022 are executed by the processor 1021, the processor 1021 executes the method for monitoring services.
  • the interface board 102 can implement message receiving and sending processing.
  • the detection node When the detection node is a hardware device, as shown in FIG. 2, a schematic structural diagram of another router or switch is also provided.
  • the detection node includes a memory 201, a processor 202, a transceiver 203, and a bus 204.
  • the memory 201, the processor 202, and the transceiver 203 communicate with each other through the bus 204.
  • the memory 201 may be a ROM, a static storage device, a dynamic storage device, or RAM.
  • the memory 201 may store computer instructions. When the computer instructions stored in the memory 201 are executed by the processor 202, the processor 202 and the transceiver 203 are used to execute a method for monitoring services.
  • the memory may also store data. For example, a part of the memory 201 is used to store data required by the method of monitoring a business, and is used to store intermediate data or result data during program execution.
  • the processor 202 may adopt a general CPU, an application ASIC, a graphics processing unit (Graphics Processing Unit, GPU), or any combination thereof.
  • the processor 202 may include one or more chips.
  • the transceiver 203 uses a transceiver module such as but not limited to a transceiver to implement communication between the detection node and other devices or communication networks.
  • a transceiver module such as but not limited to a transceiver to implement communication between the detection node and other devices or communication networks.
  • the transceiver 203 may be used to obtain data required for monitoring services.
  • the bus 204 may include a path for transmitting information between various components of the detection node (for example, the memory 201, the processor 202, and the transceiver 203).
  • the computing device includes a memory 301, a processor 302, a transceiver 303, and a bus 304.
  • the memory 301, the processor 302, and the transceiver 303 realize the communication connection between each other through the bus 304.
  • the memory 301 may be a ROM, a static storage device, a dynamic storage device, or RAM.
  • the memory 301 may store computer instructions. When the computer instructions stored in the memory 301 are executed by the processor 302, the processor 302 and the transceiver 303 are used to execute a method for monitoring services.
  • the memory may also store data. For example, a part of the memory 301 is used to store data required by the method of monitoring a business, and used to store intermediate data or result data during program execution.
  • the processor 302 may adopt a general-purpose CPU, an application ASIC, a graphics processor, or any combination thereof.
  • the processor 302 may include one or more chips.
  • the transceiver 303 uses a transceiver module such as but not limited to a transceiver to implement communication between the network device and other devices or a communication network.
  • a transceiver module such as but not limited to a transceiver to implement communication between the network device and other devices or a communication network.
  • the transceiver 303 may be used to obtain data required for monitoring services.
  • the bus 304 may include a path for transferring information between various components of the network device (for example, the memory 301, the processor 302, and the transceiver 303).
  • the embodiment of the present application provides a method for monitoring a service.
  • the method can be applied to the scenario shown in FIG. 4, in which the data packet sending end, detection domain, data packet receiving end, and statistics node of the service are included in the scenario. All the detection nodes or part of the detection nodes in the detection domain are used to detect whether the network KPI of the data packet of the service meets the network KPI of the key stage to which the data packet belongs.
  • the data packet sender is used to send service data packets to the data packet receiver.
  • the data packet receiver can be the user's terminal device.
  • the statistics node can be used to receive abnormal event notifications sent by the detection nodes in the detection domain.
  • the statistics node can also be used to determine the network KPI corresponding to the stage category of at least one key stage of the service, and to deliver the network corresponding to the stage category of the at least one critical stage of the service to the node in the detection domain. KPI.
  • Figure 4 is taken as an example to describe the flow of the method for monitoring services, as shown in Figure 5:
  • Step 501 The first detection node in the detection domain receives the current data packet of the target service.
  • the detection domain may be a network domain for detecting the target service.
  • the first detection node in the detection domain may be the first node that the data packet of the target service passes after entering the detection domain, or other nodes that the data packet of the target service passes after entering the detection domain.
  • the target business is a business to be monitored, such as live video services (cloud virtual reality live broadcast services, three-dimensional (Three Dimensional, 3D) live video services, etc.).
  • the target service can be indicated by the quintuple information, or at least one element in the quintuple information (such as the IP address and port number of the data packet sender).
  • the target service can also be indicated in other ways, such as the type of the target service. Etc., the embodiment of the present application does not limit it.
  • the current data packet is the data packet currently processed by the detection node.
  • the sending end of the data packet of the target service sends a data packet, and enters the detection domain through network transmission, and the first detection node in the detection domain receives the data packet (the data packet is the current data packet).
  • the first detection node in the detection domain is hereinafter referred to as the first detection node for short.
  • Step 502 The first detection node of the detection domain adds detection indication information to the current data packet to obtain the target data packet.
  • the detection indication information includes the target stage category corresponding to the current data packet, the target stage category is used to indicate the target stage in at least one key stage of the current data packet in the target business, and the detection indication information is used to indicate that the current data packet is Perform testing.
  • the detection instruction information may be an in-band flow information telemetry (in-situ Flow Information Telemetry, iFiT) command header, or an in-situ Operation Administration and Maintenance (in-situ Operation Administration and Maintenance, iOAM) command header.
  • the detection instruction information may also be other instruction headers used for flow detection, which is not limited in the embodiment of the present application.
  • the first detection node may obtain the stage category (ie, target stage category) of the current data packet, and the target stage category may be used to indicate the target stage of at least one key stage of the current data packet in the target service.
  • the target stage category may be used to indicate the target stage of at least one key stage of the current data packet in the target service.
  • at least one indicates one or more, which means that the target business can be in one key stage or multiple key stages.
  • the first detection node can add detection indication information to the current data packet to obtain the target data packet.
  • the detection indication information includes the target stage category corresponding to the current data packet.
  • the target stage category may be an extension field in the iFiT command header or an extension field in the iOAM command header.
  • Step 503 The first detection node in the detection domain transmits the target data packet to the next hop node.
  • the first detection node after the first detection node obtains the target data packet, it can query the destination address in the target data packet in the forwarding table to obtain the next hop node. Then the first detection node sends the target data packet to the next hop node.
  • the first detection node may also only add detection indication information to certain data packets according to service requirements. For example, add detection instruction information to the data packet every two data packets.
  • step 502 the following two methods can be used to determine the stage category of the current data packet:
  • Manner 1 The first detection node obtains the target stage category corresponding to the current data packet in the current data packet.
  • the data sending end when sending a data packet, can determine the phase category of the key phase to which the data packet belongs based on the characteristics of the data packet (that is, the target phase category). Then the data sending end can add the target stage category to the application information header of the data packet, and send it to the first detection node along with the data packet.
  • the first detection node receives the data packet, that is, obtains the current data packet, and can obtain the target stage category corresponding to the current data packet in the current data packet.
  • the first detection node determines the target stage category corresponding to the current data packet according to the characteristics of the current data packet.
  • the first detection node can use a traffic classification algorithm (such as in-depth packet analysis or a traffic recognition model) to analyze the characteristics of the current data packet and determine the service type of the current data packet. . Then, based on at least one key phase corresponding to the service type, the current data packet is divided into the key phase to which the current data packet belongs, and the phase type of the key phase is the target phase type corresponding to the current data packet. For example, when the target service is a live video service, and the interval between the current data packet and the previous data packet is less than a certain value, it can be determined that the current data packet is in the scene switching stage, and the target stage category is the stage category of the scene switching stage.
  • a traffic classification algorithm such as in-depth packet analysis or a traffic recognition model
  • the detection indication information further includes the network KPI corresponding to the target stage category.
  • the first detection node obtains the network KPI corresponding to the target stage category, and sets the network KPI corresponding to the target stage category in the detection indication information.
  • the network KPI corresponding to the target stage category refers to the network KPI required in the key stage indicated by the target stage category under the QoE indicator desired by the operation and maintenance personnel (that is, the QoE indicator satisfies the target ideal condition).
  • the target value is different based on different QoE index standards.
  • the QoE index standard is a scoring standard
  • the QoE index ranges from 0 to 5
  • 5 represents the highest QoE index
  • 0 represents the lowest QoE index
  • the target ideal condition is the selection of the QoE index.
  • the value is greater than or equal to 4, etc.
  • the first detection node may obtain the network KPI corresponding to the target stage category, and then may set the network KPI in the detection indication information of the current data packet. In this way, other detection nodes in the detection domain can obtain the network KPI corresponding to the target stage category in the detection indication information.
  • the first detection node may use the following two methods to determine the network KPI corresponding to the target stage category.
  • Manner 1 The first detection node obtains the network KPI corresponding to the target stage category in the current data packet.
  • the data packet sender can obtain the network KPI of the current data packet to the network in real time based on the time sequence of the target service (that is, the data packet sender can know the network KPI required by the current data packet). For example, if the target service is a video service, the data packet sender can know the data in the collection phase, the data packets in the initial buffering phase, and so on. The data packet sender can add the network KPI corresponding to the target stage category of the current data packet to the current data packet. In this way, the current data packet will include the network KPI corresponding to the target stage category. After receiving the current data packet, the first detection node may obtain the network KPI corresponding to the target stage category in the current data packet.
  • the data sending end supports Application-aware Internet Protocol Version 6 Networking (APN6) technology.
  • API6 Application-aware Internet Protocol Version 6 Networking
  • the required network KPIs are already carried in the data packet.
  • the first detection node can obtain the network KPI required by the data packet in the data packet.
  • the data packet sender may carry the network KPI in the application information header of the data packet.
  • the first detection node obtains the network KPI corresponding to at least one stage category of the target service; wherein, at least one stage category is used to indicate at least one key stage of the target business. At least one stage category includes the target stage category, and at least one stage category corresponds to The network KPI is determined according to the historical business data, business type and key parameters of the target business.
  • the key parameters include the target ideal condition of the QoE index, the location information of the data packet receiving end or the parameters of the data packet receiving end and the data packet sending end.
  • each stage category corresponds to its own network KPI.
  • a node outside the detection domain can determine the network KPI corresponding to at least one stage category of the target service according to the historical service data, service type, and key parameters of the target service (the process is in (Described later), the key parameters include one or more of the target ideal conditions of the QoE indicator, the location information of the data packet receiving end, or the parameters of the data packet receiving end and the data packet sending end.
  • the statistics node may send the network KPI corresponding to at least one stage category of the target service to the first detection node. In this way, the first detection node can obtain the network KPI corresponding to at least one stage category of the target service.
  • the first detection node may add the acquired network KPI corresponding to at least one stage category of the target service to the forwarding table.
  • the statistical node sends the network KPI corresponding to at least one stage category of the target service, it also sends the IP address of the data packet receiving end.
  • the first detection node is added to the forwarding table, it may be the destination IP of the forwarding table.
  • a network KPI corresponding to at least one stage category is added.
  • a timer can be set for the network KPI, and when the timer expires, the network KPI corresponding to at least one stage category is deleted. In this way, the effective duration can be set for the network KPI corresponding to at least one stage category.
  • the subsequent first detection node uses the target stage category in the forwarding table to find the network KPI corresponding to the target stage category.
  • the first detection node may detect the network KPI corresponding to at least one stage category based on its own detection. To update the received network KPI corresponding to at least one stage category of the target service, so that the first detection node can obtain a more accurate network KPI corresponding to at least one stage category of the target service. For example, if the network KPI corresponding to at least one stage category of the target business is obtained based on a neural network algorithm, the first detection node may optimize the model obtained by the neural network algorithm to obtain a more accurate corresponding to at least one stage category of the target business Network KPI.
  • the first detection node can determine the network KPI of the current data packet, and then determine whether the network KPI of the current data packet meets the network KPI corresponding to the target stage category. If the network KPI of the current data packet meets the network KPI corresponding to the target stage category, an abnormal event notification can be generated. Then the first detection node may add the abnormal event notification to the detection indication information of the target data packet, or the first detection node may send the abnormal event notification to the node for statistical abnormal event notification.
  • the node that determines the network KPI corresponding to at least one stage category and the node that receives the abnormal event notification may be the same node. Of course, the two nodes may also be different nodes, which is not limited in the embodiment of the present application.
  • the first detection node in the detection domain adds detection indication information to the current data packet, and other detection nodes in the detection domain will detect the target data packet.
  • the network KPI can then determine whether the network KPI of the target data packet is satisfied.
  • the network KPI at the critical stage of the target data packet determines whether to generate an abnormal event notification (the detailed process is described later). Therefore, based on the flow detection, we can understand the running status of the target business in a timely manner.
  • the embodiment of the present application also provides the processing of other detection nodes (hereinafter may be referred to as the second detection node) in the detection domain except the first detection node. process:
  • Step 601 The second detection node receives the target data packet of the target service, where the target data packet includes detection indication information, the detection indication information includes the target stage category, and the target stage category is used to indicate at least the current data packet in the target service.
  • the target stage in a key stage.
  • the first detection node in the detection domain sends the target data packet to the next hop node of the first detection node.
  • Other detection nodes in the detection domain that is, the second detection node
  • Step 602 The second detection node detects the target data packet according to the detection indication information to determine the network KPI of the target data packet.
  • the second detection node may detect the target data packet according to the detection indication information. Specifically, it may be that the second detection node obtains the target stage category in the detection indication information of the target data packet. Then the second detection node determines the network KPI corresponding to the target stage category. The second detection node can detect only the various network KPIs indicated by the network KPI for the target data packet. For example, if the network KPI corresponding to the target stage category includes delay, only the delay of the target data packet can be detected. For another example, the network KPI corresponding to the target stage category includes the number of lost packets, and it can be detected whether the sequence number in the last data packet of the target data packet and the sequence number of the target data packet are continuous.
  • the second detection node determines the target data The number of lost packets of the packet is 0. If it is not continuous, the second detection node determines that the number of lost packets of the target data packet is the difference between the sequence number of the target data packet and the sequence number of the previous data packet of the target data packet.
  • the second detection node can determine the data volume of the transmitted data packet within the unit time period before receiving the target data packet, that is, obtain the bandwidth. If the network KPI includes time delay, the second detection node can determine the length of time from when the target data packet enters the second detection node to when it is sent from the second detection node, that is, the time delay is obtained. If the network KPI includes the number of lost packets, the second detection node determines the difference between the sequence number of the target data packet and the sequence number of the previous data packet of the target data packet, that is, obtains the number of lost packets.
  • Step 603 If it is determined that the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category, the second detection node generates an abnormal event notification.
  • the second detection node can determine whether the network KPI of the target data packet meets the network KPI corresponding to the target stage category. If it is determined that the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category, an exception can be generated Event notification. For example, if the network KPI delay of the target data packet is 10 milliseconds, and the delay in the network KPI corresponding to the target stage category is less than or equal to 8 milliseconds, it is determined that the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category .
  • the network KPI of the target data packet has 3 packet losses, and the network KPI corresponding to the target stage category includes less than or equal to 2, and it is determined that the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category.
  • the abnormal event notification may also include the target stage category, so that the statistical node can know that the abnormality occurred when the data packet of the key stage of the target stage category was transmitted.
  • the network KPI of the target data packet meets the network KPI corresponding to the target stage category, it is considered a normal event, the current network KPI can meet the business needs, and the user's QoE indicators also meet the target ideal conditions (that is, meet the operation and maintenance requirements) , No exception event notification will be generated.
  • the network KPI corresponding to the target stage category includes multiple types of network KPIs
  • the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category.
  • One or more types of network KPIs do not meet the network KPIs corresponding to the target stage category.
  • Step 604 The second detection node transmits the abnormal event notification to the statistics node.
  • the second detection node after the second detection node generates the abnormal event notification, it can perform either of two processing, the first of which is: the second detection node adds the abnormal event notification to the target data packet, and transmits To the next hop node, until the last detection node in the detection domain sends the target data packet to the statistics node; the second type is: the second detection node directly sends the abnormal event notification to the statistics node. It should be noted here that in the first type, only the last detection node in the detection domain reports all abnormal event notifications. In the second type, any detection node in the detection domain, as long as it generates an abnormal event notification itself , Can send abnormal event notifications to the statistics node.
  • the statistical node may send the notification of the abnormal event to the terminal of the operation and maintenance personnel.
  • the terminal of the operation and maintenance personnel will directly obtain the abnormal event notification.
  • the detection indication information of the target data packet includes the network KPI corresponding to the target stage category, so that the second detection node can obtain the network KPI corresponding to the target stage category in the detection indication information.
  • the detection indication information of the target data packet does not include the network KPI corresponding to the target stage category.
  • the forwarding table of the second detection node includes network KPIs respectively corresponding to at least one stage category of the target service.
  • the statistics node may send the network KPI corresponding to at least one stage category of the target business to each detection node in the detection domain, so that the second detection node can also obtain at least one of the target business The network KPI corresponding to the stage category, and then the second detection node may add the network KPI corresponding to at least one stage category of the target service to the forwarding table.
  • the statistical node when the statistical node sends the network KPI corresponding to at least one stage category of the target service, it also sends the IP address of the data receiving end.
  • it can be the destination IP address of the forwarding table (that is, the data packet In the information corresponding to the IP address of the receiving end, a network KPI corresponding to at least one stage category is added.
  • a timer can be set for the network KPI, and when the timer expires, the network KPI corresponding to at least one stage category is deleted. In this way, the effective duration can be set for the network KPI corresponding to at least one stage category.
  • the statistical node may issue the network KPI corresponding to at least one stage category of the target service.
  • the controller delivers network KPIs corresponding to at least one stage category of the target service to the detection nodes in the detection domain.
  • the second detection node when the second detection node does not include the network KPI corresponding to the target stage category in the detection indication information, the second detection node can use the destination IP address and target stage category of the target data packet in the forwarding table to find the target stage category The corresponding network KPI.
  • each detection node when each detection node sends an abnormal event notification to the statistics node separately, the processing performed by each detection node except the first detection node in the detection domain is basically It is exactly the same, except that the last detection node is also responsible for deleting the instruction header containing the detection indication information in the target data packet.
  • the detection node in the detection domain except the last detection node will add the abnormal event notification to the target packet when generating an abnormal event notification Until the target data packet reaches the last detection node in the detection domain, the last detection is in the target data packet, and the abnormal event notification is obtained, and the abnormal event notification is sent to the statistics node.
  • the last detection node here if If an abnormal event notification is also generated, the generated abnormal event notification will also be sent to the statistics node.
  • the abnormal event notification is obtained by comparing the network KPI corresponding to the stage category of each data packet with the network KPI when the QoE indicator meets the target ideal condition.
  • the second detection node will notify the statistics node as soon as possible, so that the operation and maintenance personnel can understand the operation status of the business in a timely manner.
  • the second detection node will send an abnormal event notification to the statistics node, and will not monitor normal events, which can reduce the data sent to the statistics node. quantity.
  • the data packets of the business are divided into at least one key stage, and the monitoring of network KPIs in the key stages can ensure the quality of user experience as much as possible, and optimize the utilization of network resources.
  • a schematic diagram of transmitting the target data packet is also provided.
  • the data sending end sends the data packet to the first detection node in the detection domain.
  • the node adds detection indication information, and each detection node in the detection domain detects the target data packet.
  • each node that the target data packet passes through in the detection domain may be the second detection node, or part of the nodes that the target data packet passes through in the detection domain is the second detection node. The latter is to select some nodes through which the target data packet passes, as the second detection node.
  • the application layer of the data sending end does not notify the network layer of the network KPI corresponding to at least one stage category of the target service (that is, the data packet does not carry the network KPI)
  • the embodiment of the present application The network KPI corresponding to at least one stage category of the target business can be determined as follows, and the processing process is as follows:
  • the statistics node determines the network KPI corresponding to at least one stage category of the target business according to the historical business data, business type and key parameters of the target business; among them, the key parameters include the target ideal conditions of the QoE indicator, the parameters of the data receiving end and the data sending end, or One or more of the location information of the terminal.
  • At least one stage category is used to indicate at least one key stage of the target service.
  • the network KPI corresponding to the stage category is the key stage to which the stage category belongs.
  • the QoE indicator The corresponding network KPI when the target ideal condition is met, the network KPI corresponding to at least one stage category is sent.
  • QoE influencing factors include both subjective factors and objective factors of the user.
  • the target service is a live service of cloud virtual reality.
  • the objective factors of QoE mainly include video quality and human vision (physiological experience), and the KQI that affects video quality mainly includes resolution, frame rate, and field of view. Angle and PPD, etc.
  • the KQI that affects human vision mainly includes Media Transfer Protocol (MTP), interactive experience, limited cognitive ability, initial cache time, freeze/frozen, etc.
  • MTP Media Transfer Protocol
  • the bandwidth in the network KPI affects the video quality, initial cache duration, freeze/flickering, etc.
  • the delay in the network KPI affects the MTO and interactive experience. Packet loss in network KPIs affects freeze/flickering, etc.
  • the statistical node provides a user interface (UI) for operation and maintenance personnel, and the operation and maintenance personnel provide multiple pieces of historical business data of the target business for the statistical node through the user interface, and each historical business data includes network KPIs and QoE indicators.
  • the operation and maintenance personnel can also input the service type of the target service (such as the video live service type, etc.), the parameters of the data receiving end and the data sending end, the location information of the data receiving end, the data sending end, and the target of the QoE indicator through the user interface. Ideal conditions (such as the value of QoE is greater than a certain value, etc.).
  • the statistical node After the statistical node obtains the historical business data, it can divide the historical business data into at least one key stage according to the business type and the characteristics of the historical business data.
  • the target service is a live video service
  • the key phases include the head-end collection phase, the initial caching phase, and the scene switching phase.
  • the target business is the live broadcast business of cloud virtual reality.
  • the key stages include the head-end acquisition stage, the initial caching stage, the scene switching stage, and the head rotation rendering stage.
  • the characteristics of historical service data may include characteristics such as packet interval and packet delay.
  • the statistics node can determine the network KPI corresponding to at least one key stage when the QoE indicator meets the target ideal condition based on the network KPI and QoE indicators and key parameters included in each piece of historical business data (here can be obtained through neural network training, or It can be obtained by fitting the relationship function between the network KPI and the QoE index, which is not limited in the embodiment of the present application).
  • the statistical node can obtain the network KPI corresponding to at least one key stage of the target service, and the statistical node also obtains the network KPI corresponding to at least one stage category of the target service.
  • the statistics node can send the network KPI corresponding to at least one stage category to the first detection node in the detection domain.
  • the first detection node can obtain the network KPI corresponding to at least one stage category, which can be subsequently included in the detection instructions. Add the network KPI corresponding to the target stage category.
  • the statistics node may send the network KPIs corresponding to at least one stage category to each detection node in the detection domain, so that each detection node can add the network KPIs corresponding to the at least one stage category to the forwarding table.
  • the key parameters mainly affect the parameters of certain layers.
  • the key parameters mainly affect the parameters defined in the relational function.
  • the above process of determining the network KPI corresponding to at least one key stage is actually to specify the target ideal condition of the QoE indicator desired by the operator (that is, limited to the QoE indicator meeting the target ideal condition), and then determine the network KPI corresponding to at least one key stage process.
  • the parameters of the data packet receiving end may include the KQI of image quality, and the KQI may include resolution, frame rate, field of view (FoV), Angular resolution (Pixels Per Degree, PPD), etc.
  • the key parameters may also include video coding and decoding standards (such as h.264, h.265, etc.) and video transmission mode.
  • the video transmission mode may include a full-view mode or a field-of-view transmission mode.
  • the reason for dividing the target service into at least one key stage is: the factors related to the bandwidth of the network KPI include video quality and limited cognitive attention in human visual experience. Video The content will also affect the efficiency of encoding and compression, thereby affecting the bandwidth of network KPIs, and some behaviors of users watching videos, such as rewinding, fast forwarding, etc., will also affect the requirements of network KPIs. Therefore, in the time domain of video live broadcast services, The QoE indicator's demand for network KPIs changes dynamically, rather than a static network KPI.
  • the bandwidth in the network KPI corresponding to the key stage of the head-end collection is 2.5 switching bandwidth; the bandwidth in the network KPI corresponding to the critical stage of the initial cache is 250 Mbits per second; the network KPI corresponding to the critical stage of scene switching
  • the maximum bandwidth is 500 Mbits per second, the average bandwidth is 250 Mbits per second, and the number of lost packets for key content images (ie, key i-frames) is 0.
  • the delay in the network KPI corresponding to the key stage of the head-end terminal rendering is 20ms.
  • the reason for inputting the parameters of the data sending end and the data receiving end is that for a service data sending end and data receiving end, it will also affect the user's QoE of the service.
  • the target service is a live video service
  • the data sending end is the video image collection end
  • the data receiving end is the video image playback end.
  • the resolution and frame rate of the data sending end and the data sending end will affect the user’s viewing of the live video screen. QoE.
  • Step 901 The first detection node receives the current data packet of the target service.
  • Step 902 The first detection node adds detection indication information to the current data packet to obtain the target data packet.
  • Step 903 The first detection node transmits the target data packet to the next hop node.
  • Step 904 The second detection node receives the target data packet of the target service.
  • Step 905 The second detection node detects the target data packet according to the detection instruction information to determine the network KPI of the target data packet.
  • Step 906 If it is determined that the network KPI of the target data packet does not meet the network KPI corresponding to the target stage category, the second detection node generates an abnormal event notification.
  • Step 907 The second detection node transmits the abnormal event notification to the statistics node.
  • the detection node in the detection domain can timely discover that the network KPI may affect the QoE, and notify the statistical node, so that the operation and maintenance personnel can optimize the network in time.
  • Fig. 10 is a structural diagram of an apparatus for monitoring services provided by an embodiment of the present application.
  • the device can be implemented as part or all of the device through software, hardware or a combination of the two.
  • the device provided in the embodiment of the present application can implement the processes described in Figures 5 and 9 of the embodiment of the present application.
  • the device includes: a receiving module 1010, an adding module 1020, and a sending module 1030, wherein:
  • the receiving module 1010 is configured to receive the current data packet of the target service, and can be specifically used to implement the receiving function of step 501 and the implicit steps included in step 501;
  • the adding module 1020 is configured to add detection indication information to the current data packet to obtain a target data packet, wherein the detection indication information includes the target stage category corresponding to the current data packet, and the target stage category is used for Indicate the target stage of at least one key stage of the current data packet in the target service, and the detection indication information is used to indicate the detection of the current data packet, which can be specifically used to implement the addition of step 502 Functions and hidden steps included in step 502;
  • the sending module 1030 is configured to transmit the target data packet to the next hop node, and can be specifically used to implement the sending function of step 503 and the implicit steps included in step 503.
  • the receiving module 1010 is further configured to obtain the network KPI corresponding to the target stage category;
  • the adding module 1020 is further configured to set the network KPI corresponding to the target stage category in the detection indication information, wherein the network KPI corresponding to the target stage category is the QoE indicator of the target stage of the target service The corresponding network KPI when the ideal conditions of the target are met.
  • the receiving module 1010 is further configured to:
  • the at least one stage category is used to indicate at least one key stage of the target business
  • the at least one stage category includes the target stage category
  • the network KPI corresponding to the at least one stage category is determined according to the historical service data, service type and key parameters of the target service.
  • the key parameters include the target ideal conditions of the QoE index, the parameters of the data packet sending end and the data packet receiving end Or one or more of the location information of the receiving end of the data packet;
  • the adding module 1020 is further configured to add the network KPI corresponding to the at least one stage category to the forwarding table;
  • the adding module 1020 is also used for:
  • the network KPI corresponding to the target stage category is determined.
  • the adding module 1020 is further used for:
  • the network KPI corresponding to the target stage category is obtained.
  • the adding module 1020 is further used for:
  • the target stage category corresponding to the current data packet is determined.
  • the target service is a live video broadcast service
  • the critical phase is any one of the head-end collection phase, the initial buffer phase, the scene switching phase, or the head rotation rendering phase.
  • the network KPI corresponding to the stage category collected by the head-end and the stage category initially cached includes bandwidth
  • the network KPI corresponding to the stage category of the scene switching includes maximum bandwidth, average bandwidth, and packet loss information of key internal pictures
  • the network KPI corresponding to the stage category of the head rotation rendering includes time delay information.
  • Fig. 11 is a structural diagram of an apparatus for monitoring services provided by an embodiment of the present application.
  • the device can be implemented as part or all of the device through software, hardware or a combination of the two.
  • the device provided by the embodiment of the present application can implement the process described in Figure 6 and Figure 9 of the embodiment of the present application.
  • the device includes: a receiving module 1110, a detecting module 1120, a generating module 1130, and a transmitting module 1140, wherein:
  • the receiving module 1110 is configured to receive a target data packet of a target service, wherein the target data packet includes detection indication information, the detection indication information includes a target stage category, and the target stage category is used to indicate that the current data packet is in
  • the target stage in at least one key stage in the target business may be specifically used to implement the receiving function of step 601 and the implicit steps included in step 601;
  • the detection module 1120 is configured to detect the target data packet according to the detection indication information to determine the network KPI of the target data packet, which can be specifically used to implement the detection function of step 602 and the implicit steps included in step 602 ;
  • the generating module 1130 is configured to generate an abnormal event notification if it is determined that the network KPI of the target data packet does not satisfy the network KPI corresponding to the target stage category, where the network KPI corresponding to the target stage category is the target service
  • the network KPI corresponding to the target stage when the QoE index meets the target ideal condition can be specifically used to realize the generation function of step 603 and the implicit steps included in step 603;
  • the transmission module 1140 is configured to transmit the abnormal event notification to the statistical node, which can be specifically used to implement the transmission function of step 604 and the implicit steps included in step 604.
  • the receiving module 1110 is further configured to:
  • the network KPI corresponding to the target stage category is obtained.
  • the receiving module 1110 is further configured to:
  • the network KPI corresponding to the at least one stage category is determined according to the historical service data of the target service, the service type of the target service, and key parameters.
  • the key parameters include the target ideal condition of the QoE indicator, and the data packet sending end And one or more of the parameters of the data packet receiving end or the location information of the data packet receiving end;
  • the network KPI corresponding to the target stage category is determined.
  • Fig. 12 is a structural diagram of a device for monitoring services provided by an embodiment of the present application.
  • the device can be implemented as part or all of the device through software, hardware or a combination of the two.
  • the device provided in the embodiment of the present application can implement the process of determining the network KPI corresponding to the key stage category in the embodiment of the present application.
  • the device includes: a determining module 1210 and a sending module 1220, wherein:
  • the determining module 1210 is used to determine the network KPI corresponding to at least one stage category of the target business according to the historical business data, business type and key parameters of the target business; wherein, the key parameters include the target ideal conditions and data of the QoE index One or more of the parameters of the packet sending end and the data packet receiving end or the location information of the data packet receiving end, the at least one stage category is used to indicate at least one critical stage of the target service, for any Stage category, the network KPI corresponding to the stage category is the network KPI corresponding to the key stage to which the stage category belongs when the QoE index meets the target ideal condition;
  • the sending module 1220 is configured to send the network KPI corresponding to the at least one stage category.
  • the target service is a live video service
  • the parameters of the data packet sending end and the data packet receiving end include KQI of image quality
  • the key parameters also include video transmission mode and video coding. Decoding standards.
  • the sending module 1220 is configured to:
  • the detection domain is a network domain for detecting the target service.
  • the device further includes a receiving module 1230, configured to:
  • an abnormal event notification sent by a detection node where the abnormal event notification is used to indicate that the network KPI of the current data packet of the target service does not meet the network KPI corresponding to the target stage category, and the target stage category is used to indicate the The target stage of at least one key stage where the current data packet is in the target service.
  • the division of modules in the above embodiments of the present application is illustrative, and it is only a logical function division. In actual implementation, there may also be other division methods.
  • the functional modules in the various embodiments of the present application may be integrated in A processor may also exist alone physically, or two or more modules may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software function modules.
  • the computer program product includes one or more computer instructions, and when the computer program instructions are loaded and executed on a server or a terminal, the processes or functions described in the embodiments of the present application are generated in whole or in part.
  • the computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer instructions may be transmitted from a website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a server or a terminal, or a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (such as a floppy disk, a hard disk, a tape, etc.), an optical medium (such as a digital video disk (Digital Video Disk, DVD), etc.), or a semiconductor medium (such as a solid-state hard disk, etc.).

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Computer Security & Cryptography (AREA)
  • Environmental & Geological Engineering (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Cardiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请提供了一种监控业务的方法、装置和系统，属于网络通信技术领域。该方法包括：接收目标业务的当前数据包，在当前数据包中添加检测指示信息，以获得目标数据包，其中，检测指示信息包括当前数据包对应的目标阶段类别，目标阶段类别用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶段，检测指示信息用于指示对当前数据包进行检测，将目标数据包传输至下一跳节点。采用本申请，可以及时的了解业务的运行状态。

Description

监控业务的方法、装置和系统
本申请要求于2020年03月25日提交的申请号为202010218866.5、发明名称为“监控业务的方法、装置和系统”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
本申请涉及网络通信技术领域，特别涉及一种监控业务的方法、装置和系统。
背景技术
随着网络技术的发展，出现了越来越多的业务(如云虚拟现实的直播业务(Cloud Virtual Reality，CloudVR)等)，运营商会基于用户对业务的体验质量(Quality of Experience，QoE)指标，来运维业务，所以运营商运营监控的直接诉求是用户对业务的QoE指标，而不是业务所在网络的网络关键绩效指标(Key Performance Indicators，KPI)。
相关技术中，运营商在获取QoE指标时，仅能通过用户对业务的评价，获得QoE指标。然后基于QoE指标，判断业务的运行状态。
由于只有在使用完业务时，用户才能对业务进行评价，所以运营商获取的QoE指标有可能会存在延迟，导致不能及时了解业务的运行状态。
发明内容
本申请实施例提供了一种监控业务的方法、装置和系统，采用本申请可以及时的了解业务的运行状态。
第一方面，提供了一种监控业务的方法，该方法包括：
接收目标业务的当前数据包；在当前数据包中添加检测指示信息，以获得目标数据包，其中，检测指示信息包括当前数据包对应的目标阶段类别，目标阶段类别用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶段，检测指示信息用于指示对当前数据包进行检测；将目标数据包传输至下一跳节点。
本申请所示的方案，目标业务的数据包发送端发出数据包，经过网络传输进入检测域，检测域中的第一个检测节点接收到该数据包(该数据包即为当前数据包)。为了方便描述，检测域中的第一个检测节点在后文中简称为第一检测节点。第一检测节点可以获取当前数据包的阶段类别(即目标阶段类别)，目标阶段类别可以用于指示当前数据包在目标业务中所处的至少一个(至少一个指示一个或多个)关键阶段中的目标阶段。然后第一检测节点可以在当前数据包中添加检测指示信息，获得目标数据包。检测指示信息包括当前数据包对应的目标阶段类别。然后第一检测节点可以在转发表中查询目标数据包中的目的地址，获得下一跳节点。然后第一检测节点将目标数据包发送至下一跳节点。
这样，由于可以基于数据包所属的阶段类别，随流检测业务的运行状态，所以可以及时的了解业务的运行状态。
在一种可能的实现方式中，该方法还包括：获取目标阶段类别对应的网络KPI，在检测指示信息中设置目标阶段类别对应的网络KPI，其中，目标阶段类别对应的网络KPI是目标业务的目标阶段在QoE指标满足目标理想条件时对应的网络KPI。
其中，目标阶段类别对应的网络KPI是指在运维人员想要的QoE指标下(即QoE指标满足目标理想条件)，目标阶段类别所指示的关键阶段中所要求的网络KPI。其中，目标数值基于不同的QoE标准也不相同，例如，QoE标准为打分标准，QoE指标为0至5，5代表最高QoE指标，0代表最低QoE指标，目标理想条件为QoE指标的取值大于或等于4等。
本申请所示的方案，第一检测节点可以获取目标阶段类别对应的网络KPI，然后可以将该网络KPI，设置在当前数据包的检测指示信息中。这样，检测域中的其他检测节点可以在检测指示信息中获取到目标阶段类别对应的网络KPI。
在一种可能的实现方式中，获取目标业务的至少一个阶段类别对应的网络KPI；其中，至少一个阶段类别用于指示目标业务的至少一个关键阶段，至少一个阶段类别包括目标阶段类别，至少一个阶段类别对应的网络KPI是根据目标业务的历史业务数据、业务类型和关键参数确定的，关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或数据包接收端所处位置信息中的一种或多种；将至少一个阶段类别对应的网络KPI添加至转发表；在转发表中，确定目标阶段类别对应的网络KPI。
本申请所示的方案，在检测域之外的某个节点(如统计节点)可以根据目标业务的历史业务数据、业务类型和关键参数确定目标业务的至少一个阶段类别对应的网络KPI，关键参数包括QoE指标的目标理想条件、数据包接收端所处位置信息或数据包接收端和数据包发送端的参数中的一种或多种。统计节点可以将目标业务的至少一个阶段类别对应的网络KPI发送至第一检测节点。这样，第一检测节点可以获取到目标业务的至少一个阶段类别对应的网络KPI。然后第一检测节点可以将获取到的目标业务的至少一个阶段类别对应的网络KPI，添加至转发表。这样，第一检测节点可以在转发表中获取到目标阶段类别对应的网络KPI。
在一种可能的实现方式中，获取目标阶段类别对应的网络KPI，包括：在当前数据包中，获取目标阶段类别对应的网络KPI。
本申请所示的方案，数据包发送端可以实时的获取到当前数据包对网络的网络KPI(即数据包发送端可以知悉当前数据包所要求的网络KPI)，数据包发送端可以将当前数据包的目标阶段类别对应的网络KPI，添加至当前数据包。这样，当前数据包中就会包括目标阶段类别对应的网络KPI。第一检测节点在接收到当前数据包后，可以在当前数据包中，获取到目标阶段类别对应的网络KPI。
在一种可能的实现方式中，该方法还包括：在当前数据包中，获取当前数据包对应的目标阶段类别；或者，根据当前数据包的特征，确定当前数据包对应的目标阶段类别。
本申请所示的方案，数据发送端在发送数据包时，可以基于该数据包的特征，确定出该数据包所属的关键阶段的阶段类别(即目标阶段类别)。然后数据发送端可以将目标阶段类别添加至该数据包的应用(application)信息头中，随数据包一起发送至第一检测节点。第一检测节点接收到该数据包，即获取当前数据包，可以在当前数据包中获取到当前数据包对应的目标阶段类别。第一检测节点在接收到当前数据包后，可以使用流量分类算法(如报文深度解析或者流量识别模型)分析当前数据包的特征，确定当前数据包所属业务的业务类型。然后基于该业务类型对应的至少一个关键阶段，将当前数据包划分到当前数据包所属的关键阶 段，该关键阶段的阶段类别，即为当前数据包对应的目标阶段类别。这样，可以使第一检测节点获取到目标阶段类别。
在一种可能的实现方式中，目标业务为视频直播业务，关键阶段为头端采集的阶段、初始缓存的阶段、场景切换的阶段或头部转动渲染的阶段中的任一种。
在一种可能的实现方式中，头端采集的阶段类别和初始缓存的阶段类别对应的网络KPI包括带宽；场景切换的阶段类别对应的网络KPI包括最大带宽、平均带宽和关键内部画面的丢包信息；头部转动渲染的阶段类别对应的网络KPI包括时延信息。
这样，由于带宽会影响采集和初始缓存，所以头端采集的阶段类别和初始缓存的阶段类别对应的网络KPI包括带宽，由于最大带宽、平均带宽和关键内部画面的丢包会影响场景切换，所以场景切换的阶段类别对应的网络KPI包括最大带宽、平均带宽和关键内部画面的丢包信息，由于时延会影响头部转动的渲染，所以头部转动渲染的阶段类别对应的网络KPI包括时延信息。
第二方面，提供了一种监控业务的方法，该方法包括：
接收目标业务的目标数据包，其中，目标数据包包括检测指示信息，检测指示信息包括目标阶段类别，目标阶段类别用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶段；根据检测指示信息对目标数据包进行检测，以确定目标数据包的网络关键绩效指标KPI；若确定目标数据包的网络KPI不满足目标阶段类别对应的网络KPI，则生成异常事件通知，其中，目标阶段类别对应的网络KPI是目标业务的目标阶段在QoE指标满足目标理想条件时对应的网络KPI；将异常事件通知传输至统计节点。
本申请所示的方案，第二检测节点接收目标业务的目标数据包，其中，目标数据包包括检测指示信息，检测指示信息包括目标阶段类别，目标阶段类别用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶段。第二检测节点可以根据检测指示信息对目标数据包进行检测，具体可以是第二检测节点在目标数据包的检测指示信息中，获取到目标阶段类别。然后第二检测节点确定目标阶段类别对应的网络KPI。第二检测节点可以对目标数据包，仅检测该网络KPI指示的各项网络KPI。第二检测节点可以判断目标数据包的网络KPI是否满足目标阶段类别对应的网络KPI，若确定目标数据包的网络KPI不满足目标阶段类别对应的网络KPI，则可以生成异常事件通知。然后第二检测节点向统计节点发送异常事件通知。
这样，由于可以基于数据包所属的阶段类别，随包检测业务的运行状态，所以可以及时的了解业务的运行状态。
在一种可能的实现方式中，该方法还包括：在检测指示信息中，获取目标阶段类别对应的网络KPI。
在一种可能的实现方式中，该方法还包括：接收目标业务的至少一个阶段类别对应的网络KPI，其中，至少一个阶段类别分别用于指示目标业务的至少一个关键阶段，至少一个阶段类别包括目标阶段类别，至少一个阶段类别对应的网络KPI是根据目标业务的历史业务数据、目标业务的业务类型和关键参数确定的，关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或数据包接收端所处位置信息中的一种或多种；将至少一个阶段类别对应的网络KPI添加至转发表。在转发表中，确定目标阶段类别对应的网络KPI。
本申请所示的方案，在进行目标业务之前，统计节点可以将目标业务的至少一个阶段类 别分别对应的网络KPI发送至检测域中的每个检测节点，这样第二检测节点也能获取到目标业务的至少一个阶段类别对应的网络KPI。然后第二检测节点可以将目标业务的至少一个阶段类别对应的网络KPI添加至转发表。具体的，统计节点在发送目标业务的至少一个阶段类别对应的网络KPI时，还发送了数据接收端的IP地址，在添加至转发表中时，可以是在转发表的目的IP地址(即数据包接收端的IP地址)对应的信息中，添加至少一个阶段类别对应的网络KPI。这样，第二检测节点在检测指示信息中不包括目标阶段类别对应的网络KPI时，第二检测节点可以在转发表中，使用目标数据包的目的IP地址和目标阶段类别，查找到目标阶段类别对应的网络KPI。
第三方面，提供了一种监控业务的方法，该方法包括：
根据目标业务的历史业务数据、业务类型和关键参数，确定目标业务的至少一个阶段类别对应的网络KPI；其中，关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或数据包接收端所处位置信息中的一种或多种，至少一个阶段类别用于指示目标业务的至少一个关键阶段，对于任一阶段类别，阶段类别对应的网络KPI是阶段类别所属的关键阶段在QoE指标满足目标理想条件时对应的网络KPI；发送至少一个阶段类别对应的网络KPI。
本申请所示的方案，统计节点为运维人员提供用户接口(User Interface，UI)，运维人员通过该用户接口为统计节点提供目标业务的多条历史业务数据，每条历史业务数据包括网络KPI和QoE指标。并且运维人员还可以通过该用户接口输入目标业务的业务类型(如视频直播业务类型等)、数据接收端和数据发送端的参数、数据接收端和数据发送端所处位置信息、QoE指标的目标理想条件(如QoE指标的取值高于一定数值)。统计节点获取到历史业务数据后，可以根据业务类型和历史业务数据的特征，将历史业务数据划分为至少一个关键阶段。例如，目标业务为视频直播业务，关键阶段包括头端采集的阶段、初始缓存的阶段、场景切换的阶段等。目标业务为云虚拟现实的直播业务，关键阶段包括头端采集的阶段、初始缓存的阶段、场景切换的阶段和头部转动渲染的阶段等。然后统计节点可以根据每一条历史业务数据包括的网络KPI和QoE指标、关键参数，确定QoE指标满足目标理想条件时，至少一个关键阶段对应的网络KPI(此处可以是通过神经网络训练获得，也可以通过网络KPI与QoE指标之间的关系函数拟合获得，本申请实施例不做限定)。这样，统计节点可以获得目标业务的至少一个阶段对应的网络KPI，那么统计节点也就获得目标业务的至少一个阶段类别对应的网络KPI。
在一种可能的实现方式中，目标业务为视频直播业务；数据包发送端和数据包接收端的参数包括图像质量的关键质量指标(Key Quality Index，KQI)，关键参数还包括视频传输方式和视频编解码标准。
在一种可能的实现方式中，发送至少一个阶段类别对应的网络KPI，包括：将至少一个阶段类别对应的网络KPI发送至检测域的第一个检测节点；或者；将至少一个阶段类别对应的网络KPI发送至检测域中的各个检测节点；其中，检测域是对目标业务进行检测的网络域。
这样，为检测域中的检测节点提供各个阶段类别对应的网络KPI。
在一种可能的实现方式中，该方法还包括：接收检测节点发送的异常事件通知，其中，异常事件通知用于指示目标业务的当前数据包的网络KPI不满足目标阶段类别对应的网络KPI，目标阶段类别用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶 段。
这样，统计节点可以及时的基于异常事件通知，了解业务的运行状态。
第四方面，本申请提供了一种监控业务的装置，该装置包括多个模块，该多个模块通过执行指令来实现上述第一方面所提供的监控业务的方法。
第五方面，本申请提供了一种监控业务的装置，该装置包括多个模块，该多个模块通过执行指令来实现上述第二方面所提供的监控业务的方法。
第六方面，本申请提供了一种监控业务的装置，该装置包括多个模块，该多个模块通过执行指令来实现上述第三方面所提供的监控业务的方法。
第七方面，本申请提供了一种计算设备，所述计算设备包括存储器和处理器，所述处理器执行所述存储器存储的计算机指令，使得所述计算设备执行上述第一方面所述的监控业务的方法。
第八方面，本申请提供了一种计算设备，所述计算设备包括存储器和处理器，所述处理器执行所述存储器存储的计算机指令，使得所述计算设备执行上述第二方面所述的监控业务的方法。
第九方面，本申请提供了一种计算设备，所述计算设备包括存储器和处理器，所述处理器执行所述存储器存储的计算机指令，使得所述计算设备执行上述第三方面所述的监控业务的方法。
第十方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，当所述计算机可读存储介质中的计算机指令被计算设备执行时，使得所述计算设备执行上述第一方面所述的监控业务的方法，或者使得所述计算设备实现第四方面所述装置的功能。
第十一方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，当所述计算机可读存储介质中的计算机指令被计算设备执行时，使得所述计算设备执行上述第二方面所述的监控业务的方法，或者使得所述计算设备实现第五方面所述装置的功能。
第十二方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，当所述计算机可读存储介质中的计算机指令被计算设备执行时，使得所述计算设备执行上述第三方面所述的监控业务的方法，或者使得所述计算设备实现第六方面所述装置的功能。
第十三方面，本申请提供了一种计算机程序产品，所述计算机程序产品包括计算机指令，当所述计算机指令被计算设备执行时，所述计算设备执行上述第一方面所述的监控业务的方法。
第十四方面，本申请提供了一种计算机程序产品，所述计算机程序产品包括计算机指令，当所述计算机指令被计算设备执行时，所述计算设备执行上述第二方面所述的监控业务的方法。
第十五方面，本申请提供了一种计算机程序产品，所述计算机程序产品包括计算机指令，当所述计算机指令被计算设备执行时，所述计算设备执行上述第二方面所述的监控业务的方法。
第十六方面，提供了一种监控业务的系统，该系统包括第一检测节点、第二检测节点和统计节点。其中，第一检测节点，如上述第四方面所述的装置，第二检测节点如上述第五方 面所述的装置，统计节点，如上述第六方面所述的装置。
附图说明
图1是本申请一个示例性实施例提供的检测节点的结构示意图；
图2是本申请一个示例性实施例提供的检测节点的结构示意图；
图3是本申请一个示例性实施例提供的计算设备的结构示意图；
图4是本申请一个示例性实施例提供的监控业务的方法的应用场景示意图；
图5是本申请一个示例性实施例提供的监控业务的方法的流程示意图；
图6是本申请一个示例性实施例提供的监控业务的方法的流程示意图；
图7是本申请一个示例性实施例提供的数据包的传输示意图；
图8是本申请一个示例性实施例提供的视频的QoE指标与网络KPI的关系示意图；
图9是本申请一个示例性实施例提供的监控业务的方法的流程示意图；
图10是本申请一个示例性实施例提供的监控业务的装置的结构示意图；
图11是本申请一个示例性实施例提供的监控业务的装置的结构示意图；
图12是本申请一个示例性实施例提供的监控业务的装置的结构示意图；
图13是本申请一个示例性实施例提供的监控业务的装置的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
为了便于对本申请实施例的理解，下面首先介绍所涉及到的名词的概念：
QoE，用户对设备、网络和系统、应用或业务的质量和性能的主观感受。在本申请中，QoE指用户使用某个业务的质量和性能的主观感受。
网络KPI，主要包括网络的带宽、时延信息、丢包信息等，带宽指单位时长内能传输的数据量。
关键质量指标，针对不同业务提出的贴近用户感受的业务质量参数。例如，业务为云虚拟现实的直播业务，KQI可以包括分辨率、帧率等。
本申请中为了解决不能及时的了解业务的运行状态的问题，提出了一种监控业务的方法。该方法的执行主体可以是检测节点或者统计节点。检测节点和统计节点可以是硬件装置，也可以是软件装置。
检测节点为软件装置时，检测节点可以是通过软件实现的路由器、交换机等。检测节点为硬件装置时，检测节点可以是通过硬件实现的路由器、交换机等。
统计节点为软件装置时，统计节点可以是安装在硬件设备上的程序等。统计节点为硬件装置时，统计节点可以是服务器等计算设备。
在本申请实施例中，检测节点可以与统计节点建立有通信连接。在某些情况下，统计节点可以向检测节点发送业务的各个阶段的阶段类别对应的网络KPI等(详细过程在后文中描述)。
检测节点为硬件装置时，如图1所示，提供了路由器或者交换机的结构示意图。检测节 点包括主控板101和接口板102，主控板101包括处理器1011和存储器1012。接口板102包括处理器1021、存储器1022和接口卡1023。主控板101和接口板102之间建立有通信连接。
处理器1011可以是中央处理器(Central Processing Unit，CPU)，应用专用集成电路(Application Specific Integrated Circuit，ASIC)等。处理器302可以包括一个或多个芯片。存储器1012可以是只读存储器(Read Only Memory，ROM)、静态存储设备、动态存储设备或者随机存取存储器(Random Access Memory，RAM)。存储器1012可以存储计算机指令，当存储器1012中存储的计算机指令被处理器1011执行时，处理器1011执行监控业务的方法。
处理器1021可以是CPU，应用专用集成电路ASIC等。处理器1021可以包括一个或多个芯片。存储器1022可以是ROM、静态存储设备、动态存储设备或者RAM。存储器1022可以存储计算机指令，当存储器1022中存储的计算机指令被处理器1021执行时，处理器1021执行监控业务的方法。接口板102可以实现报文的接收和发送处理。
检测节点为硬件装置时，如图2所示，还提供了另一种路由器或者交换机的结构示意图，检测节点包括存储器201、处理器202、收发器203以及总线204。其中，存储器201、处理器202、收发器203通过总线204实现彼此之间的通信连接。
存储器201可以是ROM、静态存储设备、动态存储设备或者RAM。存储器201可以存储计算机指令，当存储器201中存储的计算机指令被处理器202执行时，处理器202和收发器203用于执行监控业务的方法。存储器还可以存储数据，例如，存储器201中的一部分用来存储监控业务的方法所需的数据，以及用于存储程序执行过程中的中间数据或结果数据。
处理器202可以采用通用的CPU，应用ASIC，图形处理器(Graphics Processing Unit，GPU)或其任意组合。处理器202可以包括一个或多个芯片。
收发器203使用例如但不限于收发器一类的收发模块，来实现检测节点与其他设备或通信网络之间的通信。例如，可以通过收发器203获取监控业务时所需的数据。
总线204可包括在检测节点各个部件(例如，存储器201、处理器202、收发器203)之间传送信息的通路。
统计节点为计算设备时，如图3所示，计算设备包括存储器301、处理器302、收发器303以及总线304。其中，存储器301、处理器302、收发器303通过总线304实现彼此之间的通信连接。
存储器301可以是ROM、静态存储设备、动态存储设备或者RAM。存储器301可以存储计算机指令，当存储器301中存储的计算机指令被处理器302执行时，处理器302和收发器303用于执行监控业务的方法。存储器还可以存储数据，例如，存储器301中的一部分用来存储监控业务的方法所需的数据，以及用于存储程序执行过程中的中间数据或结果数据。
处理器302可以采用通用的CPU，应用ASIC，图形处理器或其任意组合。处理器302可以包括一个或多个芯片。
收发器303使用例如但不限于收发器一类的收发模块，来实现网络设备与其他设备或通信网络之间的通信。例如，可以通过收发器303获取监控业务时所需的数据。
总线304可包括在网络设备各个部件(例如，存储器301、处理器302、收发器303)之间传送信息的通路。
本申请实施例提供了一种监控业务的方法，该方法可以应用于如图4所示的场景中，在 该场景中包括业务的数据包发送端、检测域、数据包接收端和统计节点，该检测域中的全部检测节点或者部分检测节点用于检测业务的数据包的网络KPI是否满足该数据包所属的关键阶段的网络KPI。数据包发送端用于发送业务的数据包给数据包接收端。数据包接收端可以是用户的终端设备。统计节点可以用于接收检测域中的检测节点发送的异常事件通知。
另外，在图4的场景中，统计节点还可以用于确定业务的至少一个关键阶段的阶段类别对应的网络KPI，以及为检测域中节点下发业务的至少一个关键阶段的阶段类别对应的网络KPI。
本申请实施例中以图4为例，描述监控业务的方法的流程，如图5所示：
步骤501，检测域中的第一个检测节点接收目标业务的当前数据包。
其中，检测域可以是对目标业务进行检测的网络域。检测域中的第一个检测节点可以是目标业务的数据包进入检测域后经过的第一个节点，或者目标业务的数据包进入检测域后经过的其他节点。目标业务为要进行监控的业务，如视频直播业务(云虚拟现实的直播业务、三维(Three Dimensional，3D)视频直播业务等)等。目标业务可以使用五元组信息指示，也可以使用五元组信息中的至少一元(如数据包发送端的IP地址和端口号)指示，当然目标业务也可以使用其他方式指示，如目标业务的类型等，本申请实施例不做限定。当前数据包为检测节点当前处理的数据包。
在本实施例中，目标业务的数据包发送端发出数据包，经过网络传输进入检测域，检测域中的第一个检测节点接收到该数据包(该数据包即为当前数据包)。为了方便描述，检测域中的第一个检测节点在后文中简称为第一检测节点。
步骤502，检测域的第一个检测节点在当前数据包中添加检测指示信息，以获得目标数据包。
其中，检测指示信息包括当前数据包对应的目标阶段类别，目标阶段类别用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶段，检测指示信息用于指示对当前数据包进行检测。检测指示信息可以是带内流量信息遥测(in-situ Flow Information Telemetry，iFiT)指令头，也可以是带内运行管理与维护(in-situ Operation Administration and Maintenance，iOAM)指令头。当然检测指示信息也可以是其他用于随流检测的指令头，本申请实施例不做限定。
在本实施例中，第一检测节点可以获取当前数据包的阶段类别(即目标阶段类别)，目标阶段类别可以用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶段，此处至少一个指示一个或多个，即说明目标业务可以处于一个关键阶段或者多个关键阶段。
然后第一检测节点可以在当前数据包中添加检测指示信息，获得目标数据包。检测指示信息包括当前数据包对应的目标阶段类别，具体的，目标阶段类别可以是iFiT指令头中的一个扩展字段，也可以是iOAM指令头中的一个扩展字段。
步骤503，检测域的第一个检测节点将目标数据包传输至下一跳节点。
在本实施例中，第一检测节点获得目标数据包后，可以在转发表中查询目标数据包中的目的地址，获得下一跳节点。然后第一检测节点将目标数据包发送至下一跳节点。
需要说明的是，第一检测节点也可以按照业务的需要，仅对某些数据包添加检测指示信息。如每隔两个数据包为数据包添加检测指示信息。
在一种可能的实现方式中，在步骤502中，可以使用如下两种方式确定当前数据包的阶 段类别：
方式一，第一检测节点在当前数据包中，获取当前数据包对应的目标阶段类别。
在本实施例中，数据发送端在发送数据包时，可以基于该数据包的特征，确定出该数据包所属的关键阶段的阶段类别(即目标阶段类别)。然后数据发送端可以将目标阶段类别添加至该数据包的应用信息头中，随数据包一起发送至第一检测节点。
第一检测节点接收到该数据包，即获取当前数据包，可以在当前数据包中获取到当前数据包对应的目标阶段类别。
方式二，第一检测节点根据当前数据包的特征，确定当前数据包对应的目标阶段类别。
在本实施例中，第一检测节点在接收到当前数据包后，可以使用流量分类算法(如报文深度解析或者流量识别模型)分析当前数据包的特征，确定当前数据包所属业务的业务类型。然后基于该业务类型对应的至少一个关键阶段，将当前数据包划分到当前数据包所属的关键阶段，该关键阶段的阶段类别，即为当前数据包对应的目标阶段类别。例如，在目标业务为视频直播业务时，当前数据包与前一个数据包的间隔小于一定数值，则可以确定当前数据包处于场景切换阶段，目标阶段类别为场景切换阶段的阶段类别。
在一种可能的实现方式中，检测域中除第一检测节点之外的其他检测节点没有目标阶段类别对应的网络KPI的情况下，在检测指示信息中还包括目标阶段类别对应的网络KPI。处理过程为：
第一检测节点获取目标阶段类别对应的网络KPI，在检测指示信息中设置目标阶段类别对应的网络KPI。
其中，目标阶段类别对应的网络KPI是指在运维人员想要的QoE指标下(即QoE指标满足目标理想条件)，目标阶段类别所指示的关键阶段中所要求的网络KPI。其中，目标数值基于不同的QoE指标标准也不相同，例如，QoE指标标准为打分标准，QoE指标为0至5，5代表最高QoE指标，0代表最低QoE指标，目标理想条件为QoE指标的取值大于或等于4等。
在本实施例中，第一检测节点可以获取目标阶段类别对应的网络KPI，然后可以将该网络KPI，设置在当前数据包的检测指示信息中。这样，检测域中的其他检测节点可以在检测指示信息中获取到目标阶段类别对应的网络KPI。
在一种可能的实现方式中，第一检测节点可以使用以下两种方式，确定出目标阶段类别对应的网络KPI。
方式一，第一检测节点在当前数据包中，获取目标阶段类别对应的网络KPI。
在本实施例中，数据包发送端基于目标业务的进行时序，可以实时的获取到当前数据包对网络的网络KPI(即数据包发送端可以知悉当前数据包所要求的网络KPI)。例如，目标业务为视频业务，数据包发送端可以知晓采集阶段的数据、初始缓存阶段的数据包等。数据包发送端可以将当前数据包的目标阶段类别对应的网络KPI，添加至当前数据包。这样，当前数据包中就会包括目标阶段类别对应的网络KPI。第一检测节点在接收到当前数据包后，可以在当前数据包中，获取到目标阶段类别对应的网络KPI。例如，数据发送端中支持应用感知互联网协议第6版网络(Application-aware Internet Protocol Version 6 Networking，APN6)技术，此种情况下，在数据包中已经携带了所要求的网络KPI。这样第一检测节点可以在数据包中获取到该数据包所要求的网络KPI。
在一种可能的实现方式中，数据包发送端可以将网络KPI携带在数据包的应用信息头。
方式二，第一检测节点获取目标业务的至少一个阶段类别对应的网络KPI；其中，至少一个阶段类别用于指示目标业务的至少一个关键阶段至少一个阶段类别包括目标阶段类别，至少一个阶段类别对应的网络KPI是根据目标业务的历史业务数据、业务类型和关键参数确定的，关键参数包括QoE指标的目标理想条件、数据包接收端所处位置信息或数据包接收端和数据包发送端的参数中的一种或多种；将至少一个阶段类别对应的网络KPI添加至转发表；在转发表中，确定目标阶段类别对应的网络KPI。
其中，少一个阶段类别为多个阶段类别时，每个阶段类别均对应自身的网络KPI。
在本实施例中，在检测域之外的某个节点(如统计节点)可以根据目标业务的历史业务数据、业务类型和关键参数确定目标业务的至少一个阶段类别对应的网络KPI(该过程在后文中描述)，关键参数包括QoE指标的目标理想条件、数据包接收端所处位置信息或数据包接收端和数据包发送端的参数中的一种或多种。统计节点可以将目标业务的至少一个阶段类别对应的网络KPI发送至第一检测节点。这样，第一检测节点可以获取到目标业务的至少一个阶段类别对应的网络KPI。
然后第一检测节点可以将获取到的目标业务的至少一个阶段类别对应的网络KPI，添加至转发表。具体的，统计节点在发送目标业务的至少一个阶段类别对应的网络KPI时，还发送了数据包接收端的IP地址，第一检测节点在添加至转发表中时，可以是在转发表的目的IP地址(即数据包接收端的IP地址)对应的信息中，添加至少一个阶段类别对应的网络KPI。在转发表中添加至少一个阶段类别对应的网络KPI时，可以为该网络KPI设置计时器，在计时器时间结束时，即删除至少一个阶段类别对应的网络KPI。这样，可以为至少一个阶段类别对应的网络KPI设置有效时长。
后续第一检测节点在转发表中，使用目标阶段类别，查找到目标阶段类别对应的网络KPI。
另外，在检测域之外的某个节点在将目标业务的至少一个阶段类别对应的网络KPI发送至第一检测节点后，第一检测节点可以基于自身检测到的至少一个阶段类别对应的网络KPI，对接收到的目标业务的至少一个阶段类别对应的网络KPI进行更新处理，使第一检测节点获取到更准确的目标业务的至少一个阶段类别对应的网络KPI。例如，如果目标业务的至少一个阶段类别对应的网络KPI是基于神经网络算法获得，第一检测节点可以对神经网络算法获得的模型进行优化，以获得更准确的目标业务的至少一个阶段类别对应的网络KPI。
另外，第一检测节点在接收到当前数据包后，可以确定当前数据包的网络KPI，然后确定当前数据包的网络KPI，是否满足目标阶段类别对应的网络KPI。若当前数据包的网络KPI满足目标阶段类别对应的网络KPI，则可以生成异常事件通知。然后第一检测节点可以将异常事件通知添加至目标数据包的检测指示信息中，或者第一检测节点可以将异常事件通知发送至用于统计异常事件通知的节点。此处确定至少一个阶段类别对应的网络KPI的节点与接收异常事件通知的节点可以是相同节点，当然，这两个节点也可以是不相同的节点，本申请实施例不做限定。
这样，在检测域中的第一个检测节点在当前数据包中添加检测指示信息，检测域中的其他检测节点会对目标数据包进行检测网络KPI，进而可以判断目标数据包的网络KPI是否满足目标数据包所处的关键阶段的网络KPI，进而决定是否生成异常事件通知(详细过程在后文中描述)。因此，基于随流检测及时的了解目标业务的运行状态。
对应图5所示的流程，如图6所示，本申请实施例中还提供了检测域中除第一检测节点之外的其他检测节点(后文可以称为是第二检测节点)的处理过程：
步骤601，第二检测节点接收目标业务的目标数据包，其中，目标数据包包括检测指示信息，检测指示信息包括目标阶段类别，目标阶段类别用于指示当前数据包在目标业务中所处的至少一个关键阶段中的目标阶段。
在本实施例中，在图5的流程中，检测域中的第一检测节点将目标数据包发送至第一检测节点的下一跳节点。在检测域中的其他检测节点(即第二检测节点)可以接收到目标业务的数据包。
步骤602，第二检测节点根据检测指示信息对目标数据包进行检测，以确定目标数据包的网络KPI。
在本实施例中，第二检测节点可以根据检测指示信息对目标数据包进行检测，具体可以是第二检测节点在目标数据包的检测指示信息中，获取到目标阶段类别。然后第二检测节点确定目标阶段类别对应的网络KPI。第二检测节点可以对目标数据包，仅检测该网络KPI指示的各项网络KPI。例如，目标阶段类别对应的网络KPI包括时延，则可以仅检测目标数据包的时延。再例如，目标阶段类别对应的网络KPI包括丢包数目，可以检测目标数据包的上一个数据包中的序列号和目标数据包的序列号是否连续，若连续，则第二检测节点确定目标数据包的丢包数目为0，若不连续，则第二检测节点确定目标数据包的丢包数目为目标数据包的序列号与目标数据包的上一个数据包的序列号的差值。
此处需要说明的是，若网络KPI包括带宽，则第二检测节点可以确定接收到目标数据包之前的单位时长内，传输数据包的数据量，即获得带宽。若网络KPI包括时延，则第二检测节点可以确定目标数据包进入第二检测节点至从第二检测节点发出的时长，即获得时延。若网络KPI包括丢包数目，则第二检测节点确定目标数据包的序列号与目标数据包的上一个数据包的序列号的差值，即获得丢包数目。
步骤603，若确定目标数据包的网络KPI不满足目标阶段类别对应的网络KPI，则第二检测节点生成异常事件通知。
在本实施例中，第二检测节点可以判断目标数据包的网络KPI是否满足目标阶段类别对应的网络KPI，若确定目标数据包的网络KPI不满足目标阶段类别对应的网络KPI，则可以生成异常事件通知。例如，目标数据包的网络KPI的时延为10毫秒，目标阶段类别对应的网络KPI中的时延为小于或等于8毫秒，则确定目标数据包的网络KPI不满足目标阶段类别对应的网络KPI。目标数据包的网络KPI的丢包数目为3个，目标阶段类别对应的网络KPI包括的丢包数目为小于或等于2个，则确定目标数据包的网络KPI不满足目标阶段类别对应的网络KPI。具体的，该异常事件通知中还可以包括目标阶段类别，这样，统计节点可以知晓是在传输目标阶段类别的关键阶段的数据包时，发生异常。
另外，若确定目标数据包的网络KPI满足目标阶段类别对应的网络KPI，则认为是正常事件，当前的网络KPI可以满足业务需求，用户的QoE指标也满足目标理想条件(即满足运维要求)，不会生成异常事件通知。
此处需要说明的是，在目标阶段类别对应的网络KPI包括多种类型的网络KPI时，目标数据包的网络KPI不满足目标阶段类别对应的网络KPI是指目标数据包的网络KPI中有任一种类型或多种类型的网络KPI不满足目标阶段类别对应的网络KPI。
步骤604，第二检测节点将异常事件通知传输至统计节点。
在本实施例中，第二检测节点在生成异常事件通知后，可以进行两种处理中的任一种，其中第一种为：第二检测节点将异常事件通知添加至目标数据包中，传输至下一跳节点，直至检测域中的最后一个检测节点将目标数据包发送至统计节点；第二种为：第二检测节点直接将异常事件通知发送至统计节点。此处需要说明的是，在第一种中，只有检测域中的最后一个检测节点上报所有的异常事件通知，在第二种中，检测域中的任一检测节点，只要自身生成异常事件通知，都可以向统计节点发送异常事件通知。
统计节点接收到异常事件通知后，可以向运维人员的终端发送该异常事件通知。当然如果统计节点是运维人员的终端，则运维人员的终端直接会获取到异常事件通知。
在一种可能的实现方式中，目标数据包的检测指示信息中包括目标阶段类别对应的网络KPI，这样，第二检测节点可以在检测指示信息中，获取到目标阶段类别对应的网络KPI。
在另一种可能的实现方式中，目标数据包的检测指示信息中不包括目标阶段类别对应的网络KPI。此种情况下，在第二检测节点的转发表中包括目标业务的至少一个阶段类别分别对应的网络KPI。具体的，在进行目标业务之前，统计节点可以将目标业务的至少一个阶段类别分别对应的网络KPI发送至检测域中的每个检测节点，这样第二检测节点也能获取到目标业务的至少一个阶段类别对应的网络KPI，然后第二检测节点可以将目标业务的至少一个阶段类别对应的网络KPI添加至转发表。具体的，统计节点在发送目标业务的至少一个阶段类别对应的网络KPI时，还发送了数据接收端的IP地址，在添加至转发表中时，可以是在转发表的目的IP地址(即数据包接收端的IP地址)对应的信息中，添加至少一个阶段类别对应的网络KPI。在转发表中添加至少一个阶段类别对应的网络KPI时，可以为该网络KPI设置计时器，在计时器时间结束时，即删除至少一个阶段类别对应的网络KPI。这样，可以为至少一个阶段类别对应的网络KPI设置有效时长。当然，此处也可以不是由统计节点直接向检测域中的检测节点发送目标业务的至少一个阶段类别分别对应的网络KPI，统计节点可以将目标业务的至少一个阶段类别分别对应的网络KPI下发至检测域中的控制器。该控制器将目标业务的至少一个阶段类别分别对应的网络KPI下发至检测域中的检测节点。
这样，第二检测节点在检测指示信息中不包括目标阶段类别对应的网络KPI时，第二检测节点可以在转发表中，使用目标数据包的目的IP地址和目标阶段类别，查找到目标阶段类别对应的网络KPI。
需要说明的是，在图6的实施例中，在每个检测节点分别向统计节点发送异常事件通知的情况，检测域中除第一个检测节点之外的其他各个检测节点所做的处理基本完全相同，只不过最后一个检测节点还负责将目标数据包中的包含检测指示信息的指令头删除。在检测域中仅有最后一个检测节点向统计节点发送异常事件通知的情况，检测域除最后一个检测节点之外的检测节点，在生成异常事件通知时，会将异常事件通知添加至目标数据包中，直到目标数据包到达检测域中的最后一个检测节点，该最后一个检测在目标数据包中，获取到异常事件通知，将异常事件通知发送至统计节点，当然，此处最后一个检测节点如果也生成异常事件通知，则也会向统计节点发送生成的异常事件通知。
在本实施例中，通过比对各个数据包的阶段类别对应的网络的KPI与QoE指标满足目标理想条件时的网络KPI，获得异常事件通知。第二检测节点尽快通知给统计节点，使运维人员及时的了解到业务的运行状态。而且仅在目标数据包的网络KPI不满足目标阶段类别对应 的网络KPI的情况下，第二检测节点才向统计节点发送异常事件通知，不会监控正常事件，可以减少向统计节点发送数据的数据量。而且将业务的数据包划分到至少一个关键阶段，分关键阶段的监测网络KPI，可以尽可能的保证用户的体验质量，使网络资源的利用率最优化。
另外，为了更好的理解本申请实施例，还提供了传输目标数据包的示意图，如图7所示，数据发送端将数据包发送至检测域中的第一个检测节点，第一个检测节点添加检测指示信息，检测域中的各个检测节点对目标数据包进行检测。
在图6的流程中需要说的是，目标数据包在检测域中经过的每个节点都可以是第二检测节点，或者，目标数据包在检测域中经过的部分节点是第二检测节点。后一种是选定目标数据包经过的部分节点，作为第二检测节点。
在本申请实施例中，在一种场景中，数据发送端的应用层未给网络层通知目标业务的至少一个阶段类别对应的网络KPI(即数据包中不会携带网络KPI)，本申请实施例可以按照如下方式确定目标业务的至少一个阶段类别对应的网络KPI，处理过程为：
统计节点根据目标业务的历史业务数据、业务类型和关键参数，确定目标业务的至少一个阶段类别对应的网络KPI；其中，关键参数包括QoE指标的目标理想条件、数据接收端和数据发送端的参数或终端所处位置信息中的一种或多种，至少一个阶段类别用于指示目标业务的至少一个关键阶段，对于任一阶段类别，阶段类别对应的网络KPI是阶段类别所属的关键阶段在QoE指标满足目标理想条件时对应的网络KPI，发送至少一个阶段类别对应的网络KPI。
在本实施例中，QoE影响因素既包括用户的主观因素，也包括客观因素，在本实施例中，仅考虑客观因素。例如，目标业务为云虚拟现实的直播业务，如图8所示，QoE的客观因素主要包括视频质量和人的视觉(生理体验)，影响视频质量的KQI主要包括分辨率、帧率、视场角和PPD等，影响人的视觉的KQI主要包括媒体传输协议(Media Transfer Protocol，MTP)、交互体验、认知有限能力、初始缓存时长、卡顿/花屏等。网络KPI中的带宽影响视频质量、初始缓存时长、卡顿/花屏等。网络KPI中的时延影响MTO和交互体验。网络KPI中的丢包影响卡顿/花屏等。
统计节点为运维人员提供用户接口(User Interface，UI)，运维人员通过该用户接口为统计节点提供目标业务的多条历史业务数据，每条历史业务数据包括网络KPI和QoE指标。并且运维人员还可以通过该用户接口输入目标业务的业务类型(如视频直播业务类型等)、数据接收端和数据发送端的参数、数据接收端、数据发送端所处位置信息、QoE指标的目标理想条件(如QoE的取值大于一定数值等)。统计节点获取到历史业务数据后，可以根据业务类型和历史业务数据的特征，将历史业务数据划分为至少一个关键阶段。例如，目标业务为视频直播业务，关键阶段包括头端采集的阶段、初始缓存的阶段、场景切换的阶段等。目标业务为云虚拟现实的直播业务，关键阶段包括头端采集的阶段、初始缓存的阶段、场景切换的阶段和头部转动渲染的阶段等。此处需要说明的是，历史业务数据的特征可以包括包间隔、包时延等特征。
然后统计节点可以根据每一条历史业务数据包括的网络KPI和QoE指标、关键参数，确定QoE指标满足目标理想条件时，至少一个关键阶段对应的网络KPI(此处可以是通过神经网络训练获得，也可以通过网络KPI与QoE指标之间的关系函数拟合获得，本申请实施例不做限定)。这样，统计节点可以获得目标业务的至少一个关键阶段对应的网络KPI，那么统计 节点也就获得目标业务的至少一个阶段类别对应的网络KPI。然后统计节点可以将至少一个阶段类别对应的网络KPI发送至检测域的第一个检测节点，这样，第一个检测节点可以获取到至少一个阶段类别对应的网络KPI，后续可以在检测指示信息中添加目标阶段类别对应的网络KPI。或者，统计节点可以将至少一个阶段类别分别对应的网络KPI发送至检测域的各个检测节点，这样该各个检测节点可以将至少一个阶段类别分别对应的网络KPI添加至转发表中。此处需要说明的是，在神经网络算法中，关键参数主要影响的是某些层的参数等。在使用关系函数拟合时，关键参数主要影响的是关系函数中定义的参数。上述确定至少一个关键阶段对应的网络KPI过程，实际上是规定运营商想要的QoE指标的目标理想条件(即限定在QoE指标满足目标理想条件下)，进而确定至少一个关键阶段对应的网络KPI过程。
例如，在目标业务为视频直播业务中的云虚拟现实的直播业务，数据包接收端的参数可以包括图像质量的KQI，KQI可以包括分辨率、帧率、视场角(Field of View，FoV)、角分辨率(Pixels Per Degree，PPD)等。关键参数还可以包括视频编解码标准(如h.264、h.265等)和视频传输方式，视频传输方式可以包括全视角方式还是视场角传输方式。
需要说明的是，针对视频直播业务，将目标业务划分为至少一个关键阶段的原因为：与网络KPI的带宽相关的因素有视频质量类以及人的视觉体验中的认知有限注意力等，视频的内容也会影响编码压缩的效率，从而影响网络KPI的带宽，而且用户观看视频的一些行为，如回退，快进等也会影响网络KPI的需求，所以在视频直播业务的时域上，QoE指标对网络KPI的需求是动态变化的，而非一个静态网络KPI。例如，头端采集的关键阶段对应的网络KPI中的带宽为2.5交换带宽；初始缓存的的关键阶段对应的网络KPI中的带宽为250兆比特每秒；场景切换的关键阶段对应的网络KPI中的最大带宽为500兆比特每秒、平均带宽为250兆比特每秒、关键内容画面(即关键i帧)的丢包数目为0。头端终端渲染的关键阶段对应的网络KPI中的时延为20ms。
此处还需要说明的是，输入数据发送端和数据接收端的参数的原因为：对于一个业务数据发送端和数据接收端也会影响用户对业务的QoE。例如，目标业务为视频直播业务，数据发送端为视频图像的采集端，数据接收端为视频图像的播放端，当然数据发送端和数据发送端的分辨率、帧率会影响用户观看视频直播画面的QoE。
另外，为了更好的理解本申请实施例，如图9所示，还提供了如下流程：
步骤901，第一检测节点接收目标业务的当前数据包。
步骤902，第一检测节点在当前数据包中添加检测指示信息，以获得目标数据包。
步骤903，第一检测节点将目标数据包传输至下一跳节点。
步骤904，第二检测节点接收目标业务的目标数据包。
步骤905，第二检测节点根据检测指示信息对目标数据包进行检测，以确定目标数据包的网络KPI。
步骤906，若确定目标数据包的网络KPI不满足目标阶段类别对应的网络KPI，则第二检测节点生成异常事件通知。
步骤907，第二检测节点将异常事件通知传输至统计节点。
在图9所示的流程的处理，可以参考图5和图6所示的流程中的描述。
这样，检测域中的检测节点可以及时的发现网络KPI有可能会影响QoE，并通知给统计节点，以使运维人员及时对网络进行优化。
图10是本申请实施例提供的监控业务的装置的结构图。该装置可以通过软件、硬件或者两者的结合实现成为装置中的部分或者全部。本申请实施例提供的装置可以实现本申请实施例图5和图9所述的流程，该装置包括：接收模块1010、添加模块1020和发送模块1030，其中：
接收模块1010，用于接收目标业务的当前数据包，具体可以用于实现步骤501的接收功能以及步骤501包含的隐含步骤；
添加模块1020，用于在所述当前数据包中添加检测指示信息，以获得目标数据包，其中，所述检测指示信息包括所述当前数据包对应的目标阶段类别，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段，所述检测指示信息用于指示对所述当前数据包进行检测，具体可以用于实现步骤502的添加功能以及步骤502包含的隐含步骤；
发送模块1030，用于将所述目标数据包传输至下一跳节点，具体可以用于实现步骤503的发送功能以及步骤503包含的隐含步骤。
在一种可能的实现方式中，所述接收模块1010，还用于获取所述目标阶段类别对应的网络KPI；
所述添加模块1020，还用于在所述检测指示信息中设置所述目标阶段类别对应的网络KPI，其中，所目标阶段类别对应的网络KPI是所述目标业务的所述目标阶段在QoE指标满足目标理想条件时对应的网络KPI。
在一种可能的实现方式中，所述接收模块1010，还用于：
获取所述目标业务的至少一个阶段类别对应的网络KPI；其中，所述至少一个阶段类别用于指示所述目标业务的至少一个关键阶段，所述至少一个阶段类别包括所述目标阶段类别，所述至少一个阶段类别对应的网络KPI是根据所述目标业务的历史业务数据、业务类型和关键参数确定的，所述关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种；
所述添加模块1020，还用于将所述至少一个阶段类别对应的网络KPI添加至转发表；
所述添加模块1020，还用于：
在所述转发表中，确定所述目标阶段类别对应的网络KPI。
在一种可能的实现方式中，所述添加模块1020，还用于：
在所述当前数据包中，获取所述目标阶段类别对应的网络KPI。
在一种可能的实现方式中，所述添加模块1020，还用于：
在所述当前数据包中，获取所述当前数据包对应的目标阶段类别；或者，
根据所述当前数据包的特征，确定所述当前数据包对应的目标阶段类别。
在一种可能的实现方式中，所述目标业务为视频直播业务，所述关键阶段为头端采集的阶段、初始缓存的阶段、场景切换的阶段或头部转动渲染的阶段中的任一种。
在一种可能的实现方式中，所述头端采集的阶段类别和所述初始缓存的阶段类别对应的网络KPI包括带宽；
所述场景切换的阶段类别对应的网络KPI包括最大带宽、平均带宽和关键内部画面的丢包信息；
所述头部转动渲染的阶段类别对应的网络KPI包括时延信息。
图11是本申请实施例提供的监控业务的装置的结构图。该装置可以通过软件、硬件或者两者的结合实现成为装置中的部分或者全部。本申请实施例提供的装置可以实现本申请实施例图6和图9所述的流程，该装置包括：接收模块1110、检测模块1120、生成模块1130和传输模块1140，其中：
接收模块1110，用于接收目标业务的目标数据包，其中，所述目标数据包包括检测指示信息，所述检测指示信息包括目标阶段类别，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段，具体可以用于实现步骤601的接收功能以及步骤601包含的隐含步骤；
检测模块1120，用于根据所述检测指示信息对所述目标数据包进行检测，以确定所述目标数据包的网络KPI，具体可以用于实现步骤602的检测功能以及步骤602包含的隐含步骤；
生成模块1130，用于若确定所述目标数据包的网络KPI不满足所述目标阶段类别对应的网络KPI，则生成异常事件通知，其中，所述目标阶段类别对应的网络KPI是所述目标业务的所述目标阶段在QoE指标满足目标理想条件时对应的网络KPI，具体可以用于实现步骤603的生成功能以及步骤603包含的隐含步骤；
传输模块1140，用于将所述异常事件通知传输至统计节点，具体可以用于实现步骤604的传输功能以及步骤604包含的隐含步骤。
在一种可能的实现方式中，所述接收模块1110，还用于：
在所述检测指示信息中，获取所述目标阶段类别对应的网络KPI。
在一种可能的实现方式中，所述接收模块1110，还用于：
接收所述目标业务的至少一个阶段类别对应的网络KPI，其中，所述至少一个阶段类别分别用于指示所述目标业务的至少一个关键阶段，所述至少一个阶段类别包括所述目标阶段类别，所述至少一个阶段类别对应的网络KPI是根据所述目标业务的历史业务数据、所述目标业务的业务类型和关键参数确定的，所述关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种；
将所述至少一个阶段类别对应的网络KPI添加至转发表；
在所述转发表中，确定所述目标阶段类别对应的网络KPI。
图12是本申请实施例提供的监控业务的装置的结构图。该装置可以通过软件、硬件或者两者的结合实现成为装置中的部分或者全部。本申请实施例提供的装置可以实现本申请实施例确定关键阶段类别对应的网络KPI的流程，该装置包括：确定模块1210和发送模块1220，其中：
确定模块1210，用于根据目标业务的历史业务数据、业务类型和关键参数，确定所述目标业务的至少一个阶段类别对应的网络KPI；其中，所述关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种，所述至少一个阶段类别用于指示所述目标业务的至少一个关键阶段，对于任一阶段类别，所述阶段类别对应的网络KPI是所述阶段类别所属的关键阶段在QoE指标满足目标理想条件时对应的网络KPI；
发送模块1220，用于发送所述至少一个阶段类别对应的网络KPI。
在一种可能的实现方式中，所述目标业务为视频直播业务；所述数据包发送端和所述数据包接收端的参数包括图像质量的KQI，所述关键参数还包括视频传输方式和视频编解码标 准。
在一种可能的实现方式中，所述发送模块1220，用于：
将所述至少一个阶段类别对应的网络KPI发送至检测域的第一个检测节点；或者；
将所述至少一个阶段类别对应的网络KPI发送至所述检测域中的各个检测节点；
其中，所述检测域是对所述目标业务进行检测的网络域。
在一种可能的实现方式中，如图13所示，所述装置还包括接收模块1230，用于：
接收检测节点发送的异常事件通知，其中，所述异常事件通知用于指示所述目标业务的当前数据包的网络KPI不满足目标阶段类别对应的网络KPI，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段。
上述本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时也可以有另外的划分方式，另外，在本申请各个实施例中的各功能模块可以集成在一个处理器中，也可以是单独物理存在，也可以两个或两个以上模块集成为一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现，当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令，在服务器或终端上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴光缆、光纤、数字用户线)或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是服务器或终端能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(如软盘、硬盘和磁带等)，也可以是光介质(如数字视盘(Digital Video Disk，DVD)等)，或者半导体介质(如固态硬盘等)。

Claims (28)

  1. 一种监控业务的方法，其特征在于，所述方法包括：
    接收目标业务的当前数据包；
    在所述当前数据包中添加检测指示信息，以获得目标数据包，其中，所述检测指示信息包括所述当前数据包对应的目标阶段类别，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段，所述检测指示信息用于指示对所述当前数据包进行检测；
    将所述目标数据包传输至下一跳节点。
  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：
    获取所述目标阶段类别对应的网络关键绩效指标KPI；
    在所述检测指示信息中设置所述目标阶段类别对应的网络KPI，其中，所述目标阶段类别对应的网络KPI是所述目标业务的所述目标阶段在体验质量QoE指标满足目标理想条件时对应的网络KPI。
  3. 根据权利要求2所述的方法，其特征在于，所述方法还包括：
    获取所述目标业务的至少一个阶段类别对应的网络KPI；其中，所述至少一个阶段类别用于指示所述目标业务的至少一个关键阶段，所述至少一个阶段类别包括所述目标阶段类别，所述至少一个阶段类别对应的网络KPI是根据所述目标业务的历史业务数据、业务类型和关键参数确定的，所述关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种；
    将所述至少一个阶段类别对应的网络KPI添加至转发表；
    所述获取所述目标阶段类别对应的网络KPI，包括：
    在所述转发表中，确定所述目标阶段类别对应的网络KPI。
  4. 根据权利要求2所述的方法，其特征在于，所述获取所述目标阶段类别对应的网络KPI，包括：
    在所述当前数据包中，获取所述目标阶段类别对应的网络KPI。
  5. 根据权利要求1至4任一项所述的方法，其特征在于，所述方法还包括：
    在所述当前数据包中，获取所述当前数据包对应的目标阶段类别；或者，
    根据所述当前数据包的特征，确定所述当前数据包对应的目标阶段类别。
  6. 根据权利要求1至5任一所述的方法，其特征在于，所述目标业务为视频直播业务，所述关键阶段为头端采集的阶段、初始缓存的阶段、场景切换的阶段或头部转动渲染的阶段中的任一种。
  7. 根据权利要求6所述的方法，其特征在于，所述头端采集的阶段类别和所述初始缓存的阶段类别对应的网络KPI包括带宽；
    所述场景切换的阶段类别对应的网络KPI包括最大带宽、平均带宽和关键内部画面的丢包信息；
    所述头部转动渲染的阶段类别对应的网络KPI包括时延信息。
  8. 一种监控业务的方法，其特征在于，所述方法包括：
    接收目标业务的目标数据包，其中，所述目标数据包包括检测指示信息，所述检测指示信息包括目标阶段类别，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段；
    根据所述检测指示信息对所述目标数据包进行检测，以确定所述目标数据包的网络关键绩效指标KPI；
    若确定所述目标数据包的网络KPI不满足所述目标阶段类别对应的网络KPI，则生成异常事件通知，其中，所述目标阶段类别对应的网络KPI是所述目标业务的所述目标阶段在体验质量QoE指标满足目标理想条件时对应的网络KPI；
    将所述异常事件通知传输至统计节点。
  9. 根据权利要求8所述的方法，其特征在于，所述方法还包括：
    在所述检测指示信息中，获取所述目标阶段类别对应的网络KPI。
  10. 根据权利要求8所述的方法，其特征在于，所述方法还包括：
    接收所述目标业务的至少一个阶段类别对应的网络KPI，其中，所述至少一个阶段类别用于指示所述目标业务的至少一个关键阶段，所述至少一个阶段类别包括所述目标阶段类别，所述至少一个阶段类别对应的网络KPI是根据所述目标业务的历史业务数据、所述目标业务的业务类型和关键参数确定的，所述关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种；
    将所述至少一个阶段类别对应的网络KPI添加至转发表；
    在所述转发表中，确定所述目标阶段类别对应的网络KPI。
  11. 一种监控业务的方法，其特征在于，所述方法包括：
    根据目标业务的历史业务数据、业务类型和关键参数，确定所述目标业务的至少一个阶段类别对应的网络关键绩效指标KPI；其中，所述关键参数包括体验质量QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种，所述至少一个阶段类别用于指示所述目标业务的至少一个关键阶段，对于任一阶段类别，所述阶段类别对应的网络KPI是所述阶段类别所属的关键阶段在QoE指标满足目标理想条件时对应的网络KPI；
    发送所述至少一个阶段类别对应的网络KPI。
  12. 根据权利要求11所述的方法，其特征在于，所述目标业务为视频直播业务；所述数据包发送端和所述数据包接收端的参数包括图像质量的关键质量指标KQI，所述关键参数还包括视频传输方式和视频编解码标准。
  13. 根据权利要求11或12所述的方法，其特征在于，所述发送所述至少一个阶段类别对应的网络KPI，包括：
    将所述至少一个阶段类别对应的网络KPI发送至检测域的第一个检测节点；或者；
    将所述至少一个阶段类别对应的网络KPI发送至所述检测域中的各个检测节点；
    其中，所述检测域是对所述目标业务进行检测的网络域。
  14. 根据权利要求11至13任一项所述的方法，其特征在于，所述方法还包括：
    接收检测节点发送的异常事件通知，其中，所述异常事件通知用于指示所述目标业务的当前数据包的网络KPI不满足目标阶段类别对应的网络KPI，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段。
  15. 一种监控业务的装置，其特征在于，所述装置包括：
    接收模块，用于接收目标业务的当前数据包；
    添加模块，用于在所述当前数据包中添加检测指示信息，以获得目标数据包，其中，所述检测指示信息包括所述当前数据包对应的目标阶段类别，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段，所述检测指示信息用于指示对所述当前数据包进行检测；
    发送模块，用于将所述目标数据包传输至下一跳节点。
  16. 根据权利要求15所述的装置，其特征在于，所述接收模块，还用于获取所述目标阶段类别对应的网络关键绩效指标KPI；
    所述添加模块，还用于在所述检测指示信息中设置所述目标阶段类别对应的网络KPI，其中，所述目标阶段类别对应的网络KPI是所述目标业务的所述目标阶段在体验质量QoE指标满足目标理想条件时对应的网络KPI。
  17. 根据权利要求16所述的装置，其特征在于，所述接收模块，还用于：
    获取所述目标业务的至少一个阶段类别对应的网络KPI；其中，所述至少一个阶段类别用于指示所述目标业务的至少一个关键阶段，所述至少一个阶段类别包括所述目标阶段类别，所述至少一个阶段类别对应的网络KPI是根据所述目标业务的历史业务数据、业务类型和关键参数确定的，所述关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种；
    所述添加模块，还用于将所述至少一个阶段类别对应的网络KPI添加至转发表；
    所述添加模块，还用于在所述转发表中，确定所述目标阶段类别对应的网络KPI。
  18. 根据权利要求16所述的装置，其特征在于，所述添加模块，还用于：
    在所述当前数据包中，获取所述目标阶段类别对应的网络KPI。
  19. 根据权利要求15至18任一项所述的装置，其特征在于，所述添加模块，还用于：
    在所述当前数据包中，获取所述当前数据包对应的目标阶段类别；或者，
    根据所述当前数据包的特征，确定所述当前数据包对应的目标阶段类别。
  20. 一种监控业务的装置，其特征在于，所述装置包括：
    接收模块，用于接收目标业务的目标数据包，其中，所述目标数据包包括检测指示信息，所述检测指示信息包括目标阶段类别，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段；
    检测模块，用于根据所述检测指示信息对所述目标数据包进行检测，以确定所述目标数据包的网络关键绩效指标KPI；
    生成模块，用于若确定所述目标数据包的网络KPI不满足所述目标阶段类别对应的网络KPI，则生成异常事件通知，其中，所述目标阶段类别对应的网络KPI是所述目标业务的所述目标阶段在体验质量QoE指标满足目标理想条件时对应的网络KPI；
    传输模块，用于将所述异常事件通知传输至统计节点。
  21. 根据权利要求20所述的装置，其特征在于，所述接收模块，还用于：
    在所述检测指示信息中，获取所述目标阶段类别对应的网络KPI。
  22. 根据权利要求20所述的装置，其特征在于，所述接收模块，还用于：
    接收所述目标业务的至少一个阶段类别对应的网络KPI，其中，所述至少一个阶段类别 用于指示所述目标业务的至少一个关键阶段，所述至少一个阶段类别包括所述目标阶段类别，所述至少一个阶段类别对应的网络KPI是根据所述目标业务的历史业务数据、所述目标业务的业务类型和关键参数确定的，所述关键参数包括QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种；
    将所述至少一个阶段类别对应的网络KPI添加至转发表；
    在所述转发表中，确定所述目标阶段类别对应的网络KPI。
  23. 一种监控业务的装置，其特征在于，所述装置包括：
    确定模块，用于根据目标业务的历史业务数据、业务类型和关键参数，确定所述目标业务的至少一个阶段类别对应的网络关键绩效指标KPI；其中，所述关键参数包括体验质量QoE指标的目标理想条件、数据包发送端和数据包接收端的参数或所述数据包接收端所处位置信息中的一种或多种，所述至少一个阶段类别用于指示所述目标业务的至少一个关键阶段，对于任一阶段类别，所述阶段类别对应的网络KPI是所述阶段类别所属的关键阶段在QoE指标满足目标理想条件时对应的网络KPI；
    发送模块，用于发送所述至少一个阶段类别对应的网络KPI。
  24. 根据权利要求23所述的装置，其特征在于，所述目标业务为视频直播业务；所述数据包发送端和所述数据包接收端的参数包括图像质量的关键质量指标KQI，所述关键参数还包括视频传输方式和视频编解码标准。
  25. 根据权利要求23或24所述的装置，其特征在于，所述发送模块，用于：
    将所述至少一个阶段类别对应的网络KPI发送至检测域的第一个检测节点；或者；
    将所述至少一个阶段类别对应的网络KPI发送至所述检测域中的各个检测节点；
    其中，所述检测域是对所述目标业务进行检测的网络域。
  26. 根据权利要求23至25任一项所述的装置，其特征在于，所述装置还包括：接收模块用于：
    接收检测节点发送的异常事件通知，其中，所述异常事件通知用于指示所述目标业务的当前数据包的网络KPI不满足目标阶段类别对应的网络KPI，所述目标阶段类别用于指示所述当前数据包在所述目标业务中所处的至少一个关键阶段中的目标阶段。
  27. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机指令，当所述计算机可读存储介质中的计算机指令被计算设备执行时，使得所述计算设备执行所述权利要求1至14任一项权利要求所述的方法，或者使得所述计算设备实现所述权利要求15至26任一项所述装置的功能。
  28. 一种监控业务的系统，其特征在于，所述系统包括第一检测节点、第二检测节点和统计节点；
    所述第一检测节点，如权利要求15至19任一项所述的装置；
    所述第二检测节点，如权利要求20至22任一项所述的装置；
    所述统计节点，如权利要求23至26任一项所述的装置。
PCT/CN2020/141354 2020-03-25 2020-12-30 监控业务的方法、装置和系统 Ceased WO2021190050A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20927202.0A EP4106334B1 (en) 2020-03-25 2020-12-30 Service monitoring method, apparatus and system
US17/951,744 US12341666B2 (en) 2020-03-25 2022-09-23 Service monitoring method, apparatus, and system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010218866.5 2020-03-25
CN202010218866.5A CN113453024B (zh) 2020-03-25 2020-03-25 监控业务的方法、装置和系统

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/951,744 Continuation US12341666B2 (en) 2020-03-25 2022-09-23 Service monitoring method, apparatus, and system

Publications (1)

Publication Number Publication Date
WO2021190050A1 true WO2021190050A1 (zh) 2021-09-30

Family

ID=77806766

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/141354 Ceased WO2021190050A1 (zh) 2020-03-25 2020-12-30 监控业务的方法、装置和系统

Country Status (4)

Country Link
US (1) US12341666B2 (zh)
EP (1) EP4106334B1 (zh)
CN (1) CN113453024B (zh)
WO (1) WO2021190050A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114501511B (zh) * 2022-02-15 2025-03-21 华为技术有限公司 测量方法和测量装置
CN116506499B (zh) * 2023-04-10 2025-11-25 浙江华睿科技股份有限公司 一种数据传输方法、装置及电子设备
US20240385817A1 (en) * 2023-05-18 2024-11-21 Oracle International Corporation Techniques for building a data center using a skills service

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104486156A (zh) * 2014-12-15 2015-04-01 成都科来软件有限公司 一种网络性能的监测方法及装置
CN105828376A (zh) * 2016-05-09 2016-08-03 中国联合网络通信集团有限公司 基于用户感知的业务质量监测方法和设备
WO2017116853A1 (en) * 2015-12-30 2017-07-06 T-Mobile Usa, Inc. Contextual quality of user experience analysis using equipment dynamics
US10581664B1 (en) * 2018-09-20 2020-03-03 Spirent Communications, Inc. Predicting subscriber experience based on QoE

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101483559B (zh) * 2008-01-07 2011-04-20 上海未来宽带技术及应用工程研究中心有限公司 一种分布式iptv业务传输质量的监测方法
EP2525587B1 (en) * 2011-05-17 2017-07-05 Alcatel Lucent Method for streaming video content, node in a network for monitoring video content streaming
GB2524958A (en) * 2014-04-03 2015-10-14 Orbital Multi Media Holdings Corp Data flow control method
US10778586B2 (en) * 2017-01-30 2020-09-15 Sandvince Corporation System and method for traffic steering and analysis
CN106850298A (zh) * 2017-02-08 2017-06-13 中国联合网络通信集团有限公司 Iptv业务质量监测方法、终端及系统
US10560554B2 (en) * 2017-05-12 2020-02-11 Futurewei Technologies, Inc. In-situ OAM sampling and data validation
US10931542B2 (en) * 2018-08-10 2021-02-23 Futurewei Technologies, Inc. Network embedded real time service level objective validation
US10749710B2 (en) * 2018-11-02 2020-08-18 Cisco Technology, Inc. Service offload or bypass initiated by a service function forwarder in a service function chaining network
US11218376B2 (en) * 2018-11-16 2022-01-04 Cisco Technology, Inc. Algorithmic problem identification and resolution in fabric networks by software defined operations, administration, and maintenance
CN110730111A (zh) * 2019-10-23 2020-01-24 北京锐安科技有限公司 一种网络质量监测方法、装置、服务器及介质
US11489823B2 (en) * 2020-03-04 2022-11-01 Cisco Technology, Inc. Network enclave attestation for network and compute devices

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104486156A (zh) * 2014-12-15 2015-04-01 成都科来软件有限公司 一种网络性能的监测方法及装置
WO2017116853A1 (en) * 2015-12-30 2017-07-06 T-Mobile Usa, Inc. Contextual quality of user experience analysis using equipment dynamics
CN105828376A (zh) * 2016-05-09 2016-08-03 中国联合网络通信集团有限公司 基于用户感知的业务质量监测方法和设备
US10581664B1 (en) * 2018-09-20 2020-03-03 Spirent Communications, Inc. Predicting subscriber experience based on QoE

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4106334A4

Also Published As

Publication number Publication date
US20230020974A1 (en) 2023-01-19
US12341666B2 (en) 2025-06-24
CN113453024B (zh) 2022-06-14
EP4106334A4 (en) 2023-08-09
EP4106334B1 (en) 2024-10-02
EP4106334A1 (en) 2022-12-21
CN113453024A (zh) 2021-09-28

Similar Documents

Publication Publication Date Title
EP3780523B1 (en) Network traffic identification method and related device
US8806550B1 (en) Rules engine for troubleshooting video content delivery network
CN101577631B (zh) 评价用户体验质量的方法、系统及网络装置
US9521178B1 (en) Dynamic bandwidth thresholds
US12341666B2 (en) Service monitoring method, apparatus, and system
CN106850337A (zh) 一种网络质量检测方法及装置
US20090113039A1 (en) Method and system for content handling
CN112104893B (zh) 一种实现网页端无插件播放的视频流管理方法及装置
EP4201074B1 (en) Estimating video resolution delivered by an encrypted video stream
CN106850298A (zh) Iptv业务质量监测方法、终端及系统
JP2023130418A (ja) クライアント、サーバ、受信方法及び送信方法
CN108769805A (zh) 数据传输方法、装置、计算机设备及存储介质
EP4507311A1 (en) Data transmission methods, apparatus, electronic device, and storage medium
CN106454388B (zh) 一种用于确定直播设置信息的方法与设备
Li et al. Real‐Time QoE Monitoring System for Video Streaming Services with Adaptive Media Playout
CN102136962A (zh) 质量问题定界方法及相关设备与系统
US20160373509A1 (en) APPARATUS AND METHOD FOR REPORTING QoS/QoE IN MOBILE ENVIRONMENT
CN113596112A (zh) 一种面向视频监控的传输方法
CN114339869A (zh) 网络管理方法、装置、电子设备和存储介质
CN101695044A (zh) 一种流媒体服务节点及其负载均衡方法
CN109831335B (zh) 一种数据监控方法、监控终端、存储介质及数据监控系统
US9306996B2 (en) Streaming connection management method and streaming data connection system
US10638202B1 (en) State synchronization and management for two-way connected consumer electronic devices
Lopes et al. A multi-layer probing approach for video over 5G in vehicular scenarios
GB2639473A (en) Updating protocol data unit set parameters based on analytics in a wireless communication system

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: 20927202

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020927202

Country of ref document: EP

Effective date: 20220915

NENP Non-entry into the national phase

Ref country code: DE