WO2022061900A1 - 故障自治能力的确定方法以及相关设备 - Google Patents

故障自治能力的确定方法以及相关设备 Download PDF

Info

Publication number
WO2022061900A1
WO2022061900A1 PCT/CN2020/118446 CN2020118446W WO2022061900A1 WO 2022061900 A1 WO2022061900 A1 WO 2022061900A1 CN 2020118446 W CN2020118446 W CN 2020118446W WO 2022061900 A1 WO2022061900 A1 WO 2022061900A1
Authority
WO
WIPO (PCT)
Prior art keywords
fault
autonomous
level
function
autonomy
Prior art date
Application number
PCT/CN2020/118446
Other languages
English (en)
French (fr)
Inventor
许瑞岳
陈贤松
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2020/118446 priority Critical patent/WO2022061900A1/zh
Publication of WO2022061900A1 publication Critical patent/WO2022061900A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Definitions

  • the embodiments of the present application relate to the field of data processing, and in particular, to a method for determining fault autonomy and related devices.
  • a method to determine the fault autonomy capability is to qualitatively define the autonomy capability of the fault autonomy link from the participation degree of people and machines in each link of the fault autonomy end-to-end workflow, and the result is a certain part of the fault autonomy process. Whether the autonomous function has fault autonomy. This method is less accurate in determining fault autonomy.
  • the embodiments of the present application provide a method for determining the fault autonomy capability and related equipment, which are used to improve the accuracy of determining the fault autonomy capability.
  • a first aspect of the embodiments of the present application provides a method for determining a fault autonomy capability, including:
  • the first device determines the performance index of the fault autonomous function corresponding to the fault dimension information by acquiring the fault data corresponding to the fault dimension information.
  • the fault data may be original fault data or fault statistical data, which is not specifically limited here.
  • the fault dimension information includes at least one of a fault scenario and a fault type.
  • the fault autonomous function includes at least one of an alarm compression function, a fault self-identification function, a fault self-prediction function, a fault self-diagnosis function, and a fault self-healing function. Then, the first device determines the first fault autonomy level according to the performance index of the fault autonomous function, wherein the first fault autonomy level describes the autonomous capability of the fault autonomous system, which is embodied as a quantifiable value, and is a reference to the fault autonomous system. A comprehensive evaluation of the autonomous capabilities of the fault autonomous function.
  • the first fault autonomy level determined by the first device may describe the autonomous capability of the fault autonomous system corresponding to different fault scenarios and/or different fault types, and is embodied in a quantifiable form, which improves the determination of fault autonomy Accuracy of ability.
  • the first device may determine the first fault autonomous function level corresponding to the fault dimension information according to the performance index of the fault autonomous function, and the first fault autonomous function level Describes the autonomous capability of the fault autonomous function corresponding to the fault dimension information. Then, according to the first fault autonomous function level, a second fault autonomy level corresponding to the fault dimension information is determined, and the second fault autonomy level describes the autonomy capability of the fault autonomous system corresponding to the fault dimension information. Then, according to the second fault autonomy level, the first fault autonomy level is determined.
  • the first fault autonomous function level describes the autonomous capability of the fault autonomous function corresponding to the fault dimension information, and the second fault autonomous level describes the autonomous capability of the fault autonomous system corresponding to the fault dimension information.
  • the first device may further determine the first fault autonomous function level, may optimize the fault autonomous function according to the first fault autonomous function level, and may also determine the fault autonomous system under a certain fault scenario or fault type
  • the autonomous capability of that is, the second fault autonomy level, optimizes the fault autonomous system in a targeted manner.
  • the first device may determine the first fault autonomous function level corresponding to the fault dimension information according to the performance index of the fault autonomous function, and the first fault autonomous function level Describes the autonomous capability of the fault autonomous function corresponding to the fault dimension information. Then, according to the first fault autonomous function level, a second fault autonomous function level is determined, wherein the second fault autonomous function level describes the autonomous capability of the fault autonomous function, which may correspond to multiple different fault scenarios, or may correspond to multiple Different fault types may also correspond to different fault scenarios and different fault types, which are not specifically limited here. Then, the first fault autonomy level is determined according to the second fault autonomous function level, wherein the fault situation corresponding to the first fault autonomous function level is the same as the fault situation corresponding to the second fault autonomous function level.
  • the first device may also determine the autonomous capability of the fault autonomous function under different fault conditions, that is, the second fault autonomous function level, and can optimize the fault autonomous function in a targeted manner.
  • the first device may send the first fault autonomous function to the telecommunication device grade.
  • the first device may send the second fault autonomy level to the telecommunication device.
  • the telecommunication device may be a network device or a management device, which is not specifically limited here.
  • the second device described below is the telecommunication device here.
  • the first device may send the first fault autonomous function level and the second fault autonomous function level to the second device at the same time, or may send the first fault autonomous function level and the second fault autonomous function level respectively.
  • the second fault autonomy level only the first fault autonomous function level or the second fault autonomy level may be sent, which is not specifically limited here.
  • the first device sends at least one of the determined first fault autonomous function level and the second fault autonomous function level to the second device, so that the second device can determine the first fault autonomous function level or the second fault autonomous function level according to the second device.
  • the fault autonomy level determines the first fault autonomy level, which can reduce the computing cost of the first device and save memory resources.
  • the first device after determining the first fault autonomous function level, may send the first fault autonomous function to the second device functional level. After determining the second fault autonomous function level, the first device may send the second fault autonomous function level to the second device.
  • the first device may send the first fault autonomous function level and the second fault autonomous function level to the second device at the same time, or may send the first fault autonomous function level and the second fault autonomous function level respectively.
  • the second fault autonomous function level only the first fault autonomous function level or the second fault autonomous function level may be sent, which is not specifically limited here.
  • the first device sends at least one of the determined first fault autonomous function level and the second fault autonomous function level to the second device, so that the second device can determine the first fault autonomous function level or the second fault autonomous function level according to the second device.
  • the second fault autonomous function level determines the first fault autonomy level, which can reduce the computing cost of the first device and save memory resources.
  • the first device determines the first fault autonomous After the level, the first fault autonomy level may be sent to the second device, so that the second device displays the first fault autonomy level to the user, research and development personnel or network administrator.
  • the first device may send the first fault autonomy level to the second device, so that the second device displays the specific content of the first fault autonomy level to the user, R&D personnel or network administrator, and the user, R&D personnel or The network manager can optimize the faulty autonomous system accordingly.
  • the first device determines, according to the fault data, After the performance index of the fault autonomy function corresponding to the fault dimension information, the performance index may be sent to the second device, so that the second device determines the first fault autonomy level according to the performance index.
  • the first device determines the performance index of the fault autonomy function
  • it can send the performance index to the second device, so that the second device determines the first fault autonomy level according to the performance index, which can reduce the first The computing cost of the device is reduced, and the memory resources are saved.
  • the performance index includes an alarm At least one of recognition rate, fault self-identification accuracy rate, fault self-prediction rate, fault self-prediction accuracy rate, fault self-diagnosis rate, fault self-diagnosis accuracy rate, fault self-healing rate, and fault self-healing accuracy rate.
  • the autonomous capabilities of different fault autonomous functions can be determined according to different performance indicators, which can adapt to different needs in practical applications and improve the flexibility of the solution.
  • the failure scenario includes a single network element failure scenario, At least one of a single domain failure scenario, a radio access network RAN domain failure scenario, a core network CN failure scenario, a transmission network TN domain failure scenario, and a cross-domain failure scenario.
  • the fault autonomous function or the autonomous capability of the fault autonomous system corresponding to different fault scenarios can be determined according to different fault scenarios, which can be selected according to different requirements in practical applications, thereby improving the flexibility of the solution.
  • the fault type includes a configuration fault type, and the software At least one of a class failure type, a hardware class failure type, a performance class failure type, and a business class failure type.
  • hardware faults and performance faults can be further subdivided according to the needs of different application scenarios.
  • the types of hardware failures include at least one of base station disconnection failures, fronthaul/optical port failures, clock failures, cell out-of-service failures, and standing wave failures.
  • the performance type faults include at least one of interference problem type faults, parameter problem type faults, coverage problem type faults, and capacity problem type faults.
  • the fault autonomous function or the autonomous capability of the fault autonomous system corresponding to different fault types can be determined according to different fault types, and the selection can be made according to different requirements in practical applications, so as to improve the flexibility of the solution.
  • the first device may receive the third device by receiving Send the original fault data, and determine the original fault data as fault data.
  • the first device may also receive a third
  • the fault raw data sent by the device is statistically analyzed to obtain fault statistical data, and the fault statistical data is determined as fault data.
  • the first device to acquire the fault data, which can be selected according to the memory resources and computing capability of the first device, which improves the flexibility and practicability of the solution.
  • the first embodiment of the present application is the first In a twelfth embodiment of the aspect, the first device may be a service operation unit.
  • the first device may be a cross-domain Manage functional units.
  • the first device may be a service operation unit or a cross-domain management function unit.
  • selection is made according to the requirements of network element deployment, which improves the flexibility and practicability of the solution.
  • a second aspect of the embodiments of the present application provides a method for determining a fault autonomy capability, including:
  • the second device obtains the performance index of the fault autonomous function corresponding to the fault dimension information, the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level, the first fault autonomy level, and the second fault corresponding to the fault dimension information. At least one of the levels of autonomy.
  • a fault autonomous level describes the autonomy capability of a faulty autonomous system.
  • the second device can receive different types of data, and can directly or indirectly determine the first fault autonomy level according to the data.
  • a specific determination method can be selected according to actual needs, which improves the Flexibility and achievability of solutions.
  • the performance indicators include an alarm compression rate, a fault self-identification rate, a fault self-identification accuracy rate, a fault self-prediction rate, a fault self-prediction accuracy rate, and a fault self-recognition rate. At least one of self-diagnosis rate, fault self-diagnosis accuracy rate, fault self-healing rate, and fault self-healing accuracy rate.
  • the autonomous capabilities of different fault autonomous functions can be determined according to different performance indicators, which can adapt to different needs in practical applications and improve the flexibility of the solution.
  • the fault dimension information includes at least one of a fault scenario and a fault type.
  • the failure scenarios include at least one of single network element failure scenarios, single domain failure scenarios, radio access network RAN domain failure scenarios, core network CN failure scenarios, transmission network TN domain failure scenarios, and cross-domain failure scenarios.
  • the fault types include at least one of configuration fault types, software fault types, hardware fault types, performance fault types, and service fault types.
  • the first fault autonomy level corresponding to different fault dimension information can be determined according to different fault dimension information, and can be selected according to different requirements in practical applications, thereby improving the flexibility of the solution.
  • the fault autonomous function includes an alarm compression function, a fault self-identification function, and a fault self-identification function. At least one of a self-prediction function, a fault self-diagnosis function, and a fault self-healing function.
  • the type of the fault autonomous function included in the fault autonomous system can be determined according to the needs of the actual application, so as to improve the flexibility of the solution.
  • the second device may be a service operation unit, The service operator unit, the third-party fault autonomous evaluation unit, or other management devices are not specifically limited here.
  • This embodiment of the present application takes the service operation unit as an example. After the service operation unit determines the first fault autonomous function level, the second fault autonomous function level, the first fault autonomy level, or the second fault autonomous level, it can display these levels. For users, network administrators or researchers.
  • the service operation unit may display the determined different types of level information, so that users, network managers or researchers can optimize the fault autonomous function or the fault autonomous system in a targeted manner.
  • a third aspect of the embodiments of the present application provides a method for determining fault autonomy, including:
  • the third device acquires fault data corresponding to the fault dimension information, and sends the fault data to the first device, so that the first device uses the fault data to determine the first fault autonomy level.
  • the fault data corresponding to the fault dimension information may be the fault original data corresponding to the fault dimension information.
  • the fault data corresponding to the fault dimension information may be fault statistics data corresponding to the fault dimension information.
  • the third device may be a domain management functional unit , or a cross-domain management functional unit.
  • third devices there are various types of third devices, and there are various types of fault data sent by the third device to the first device, which can be selected according to specific needs in practical applications, which improves the flexibility of the solution.
  • a fourth aspect of the embodiment of the present application provides a device for determining fault autonomy, including:
  • an acquiring unit configured to acquire fault data corresponding to the fault dimension information, where the fault dimension information includes at least one of a fault scenario and a fault type;
  • the determination unit is used to determine the performance index of the fault autonomous function corresponding to the fault dimension information according to the fault data.
  • the fault autonomous function includes the alarm compression function, the fault self-identification function, the fault self-prediction function, the fault self-diagnosis function, and the fault self-healing function. at least one of;
  • the determining unit is further configured to determine the first fault autonomy level according to the performance index of the fault autonomous function, where the first fault autonomy level describes the autonomous capability of the fault autonomous system.
  • the device for determining the fault autonomy capability is used to execute the method of the aforementioned first aspect.
  • a fifth aspect of the embodiment of the present application provides a device for determining fault autonomy, including:
  • the acquiring unit is used to acquire the performance index of the fault autonomous function corresponding to the fault dimension information, the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level, the first fault autonomy level, and the first fault autonomous function level corresponding to the fault dimension information.
  • At least one of two fault autonomous levels wherein the first fault autonomous function level describes the autonomous capability of the fault autonomous function corresponding to the fault dimension information, the second fault autonomous function level describes the autonomous capability of the fault autonomous function, and the first fault autonomous level Describes the autonomous capability of the faulty autonomous system, and the second fault autonomy level describes the autonomous capability of the faulty autonomous system corresponding to the fault dimension information;
  • the determining unit is configured to determine the first fault autonomy level, the first fault autonomous function level, the first fault autonomous function level, the first fault autonomous level, or the second fault autonomous level according to the performance index of the fault autonomous function, the first fault autonomous function level, the first fault autonomous function level
  • the autonomy level describes the autonomous capability of a faulty autonomous system.
  • the device for determining the fault autonomy capability is used to execute the method of the aforementioned second aspect.
  • a sixth aspect of the embodiment of the present application provides a device for determining fault autonomy, including:
  • an acquisition unit used to acquire fault data corresponding to the fault dimension information
  • the sending unit is configured to send the fault data corresponding to the fault dimension information to the first device.
  • the device for determining the fault autonomy capability is used to execute the method of the aforementioned third aspect.
  • a seventh aspect of the embodiments of the present application provides a computer device, including:
  • processors memories, input and output devices, and buses.
  • the processor, memory, and input and output devices are connected to the bus.
  • the processor is used to perform the following steps:
  • fault data corresponding to the fault dimension information includes at least one of a fault scenario and a fault type
  • the fault autonomous function includes at least one of a fault self-identification function, a fault self-prediction function, a fault self-diagnosis function, and a fault self-healing function;
  • the first fault autonomy level is determined according to the performance index of the fault autonomous function, and the first fault autonomy level describes the autonomous capability of the fault autonomous system.
  • the computer device is adapted to perform the method of the aforementioned first aspect.
  • An eighth aspect of the embodiments of the present application provides a computer device, including:
  • processors memories, input and output devices, and buses.
  • the processor, memory, and input and output devices are connected to the bus.
  • the processor is used to perform the following steps:
  • the performance index of the fault autonomous function corresponding to the fault dimension information the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level, the first fault autonomous level, and the second fault autonomous level corresponding to the fault dimension information. at least one of;
  • the first fault autonomous function level, the second fault autonomous function level, the first fault autonomous level, or the second fault autonomous level the first fault autonomous level is determined, and the first fault autonomous level describes the fault autonomy System autonomy.
  • the computer device is adapted to perform the method of the aforementioned second aspect.
  • a ninth aspect of an embodiment of the present application provides a computer device, including:
  • processors memories, input and output devices, and buses.
  • the processor, memory, and input and output devices are connected to the bus.
  • the processor is used to perform the following steps:
  • the fault data corresponding to the fault dimension information is sent to the first device.
  • the computer device is adapted to perform the method of the aforementioned third aspect.
  • a tenth aspect of an embodiment of the present application provides a computer-readable storage medium, where a program is stored in the computer-readable storage medium, and when the computer executes the program, the methods of the first, second, and third aspects are executed .
  • An eleventh aspect of the embodiments of the present application provides a computer program product.
  • the computer program product When the computer program product is executed on a computer, the computer executes the methods of the first, second, and third aspects.
  • a twelfth aspect of an embodiment of the present application provides a communication system, where the communication system includes a first device, a second device, and a third device;
  • the first device is configured to execute the method described in any one of the foregoing first aspect, the first embodiment to the thirteenth embodiment of the first aspect;
  • the second device is configured to perform the method described in any one of the foregoing second aspect and the first embodiment to the fourth embodiment of the second aspect;
  • the third device is configured to perform the method described in any one of the third aspect and the first to third embodiments of the second aspect.
  • 1 is a system architecture diagram in an embodiment of the application
  • FIG. 2 is a schematic diagram of an embodiment of a fault autonomous system in an embodiment of the present application
  • FIG. 3 is a schematic flowchart of a method for determining a fault autonomy capability according to an embodiment of the present application
  • FIG. 4 is a schematic diagram of an embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application
  • FIG. 5 is a schematic diagram of another embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application
  • FIG. 6 is a schematic diagram of another embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application.
  • FIG. 7 is a schematic diagram of another embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application.
  • FIG. 8 is a schematic diagram of another embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application.
  • FIG. 9 is a schematic diagram of another embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an apparatus for determining a fault autonomy capability according to an embodiment of the present application.
  • FIG. 11 is another schematic structural diagram of the device for determining fault autonomy according to an embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of a communication system in an embodiment of the application.
  • FIG. 13 is a schematic structural diagram of a computer device according to an embodiment of the present application.
  • FIG. 14 is another schematic structural diagram of a computer device according to an embodiment of the present application.
  • the embodiment of the present application provides a method for determining a fault autonomy capability, which is used to improve the accuracy of determining the fault autonomy capability.
  • the embodiments of the present application can be applied to the system architecture shown in FIG. 1 , and mainly involve the following four network elements:
  • the business operation unit also known as the communication service management function (CSMF)
  • CSMF communication service management function
  • CSMF can provide functions such as billing, settlement, accounting, customer service, business, network monitoring, communication service life cycle management, and business intent translation. and management services. It can be used in the operation system of the operator, or the operation system in the vertical industry (vertical operational technology system, VOTS), which is not limited here.
  • Cross-domain management functional unit also known as network management function (NMF)
  • cross-domain management functional unit provides one or more of the following functions or management services: network life cycle management, network deployment, Network fault management, network performance management, network configuration management, network assurance, network optimization function, translation of network intent from communication service provider (intent-CSP), communication service user Network intent (intent from communication service consumer, intent-CSC) translation, etc.
  • the network may include one or more network elements, and may also include sub-networks or network slices, which are not specifically limited here.
  • the cross-domain management functional unit may be a network slice management function (NSMF), a management data analytical function (MDAF), or a cross-domain self-organizing network function (self-organization).
  • network function, SON-function it can also be a cross-domain intent management functional unit, which is not limited here.
  • the functions of cross-domain management function units are different. It can provide one or more of the following management functions or management services: lifecycle management of sub-networks, deployment of sub-networks, fault management of sub-networks, performance management of sub-networks, configuration management of sub-networks, assurance of sub-networks, sub-networks
  • lifecycle management of sub-networks deployment of sub-networks
  • fault management of sub-networks performance management of sub-networks
  • configuration management of sub-networks configuration management of sub-networks
  • assurance of sub-networks sub-networks
  • the optimization function of the network, the translation of the sub-network intention of the communication service provider, the translation of the sub-network intention of the communication service user, etc. are not specifically limited here.
  • the sub-network includes multiple small sub-networks or multiple network slice sub-networks.
  • Domain management functional unit also known as sub network management function (SNMF) or network element management function (NEMF)
  • domain management functional unit provides one or more of the following functions Or management services: life cycle management of sub-networks or network elements, deployment of sub-networks or network elements, fault management of sub-networks or network elements, performance management of sub-networks or network elements, guarantee of sub-networks or network elements, sub-networks or network elements Or optimization management of network elements, intent translation of sub-networks or network elements, etc., which are not specifically limited here.
  • the sub-network here may include one or more network elements, and may also include one or more sub-networks, that is, one or more sub-networks form a sub-network with a larger coverage, and may also include one or more network slice sub-networks.
  • Sub-networks have various forms, which can be networks in a certain technical domain, such as wireless access networks, core networks, and transmission networks. It can be a network of a certain standard, such as a global system for mobile communications (GSM) network, a long term evolution (LTE) network, a fifth generation mobile communication network (5G), etc. . It may also be a network provided by a certain equipment manufacturer, such as a network provided by equipment manufacturer X, and the like. It can also be a network of a certain geographical area, such as a network of a factory, a network of an urban area, and so on. There is no specific limitation here.
  • GSM global system for mobile communications
  • LTE long term evolution
  • 5G fifth generation mobile communication network
  • a network element refers to an entity that provides network services, and may be a network element included in a core network or a network element included in an access network, etc. Different network elements have different representations.
  • the network elements included in the core network may be at least one of the following network elements: an access and mobility management function (AMF) entity, a session management function (session management function, SMF) entity , the policy control function (PCF) entity, the network data analysis function (NWDAF) entity, and the network repository function (NRF) gateway, which are not limited here.
  • AMF access and mobility management function
  • SMF session management function
  • PCF policy control function
  • NWDAF network data analysis function
  • NDF network repository function
  • the network elements included in the access network may be at least one of the following network elements: various types of base stations, a centralized control unit (central unit control panel, CUCP), a centralized unit (central unit, CU), a distributed unit ( distributed unit, DU), and centralized user plane unit (central unit user panel, CUUP), which are not specifically limited here.
  • the various types of base stations include: a next-generation base station (generation node B, gNB), or an evolved base station (evolved Node B, eNB).
  • the business operation unit is a management service provider, and other business operator units can be management service consumers.
  • the management service is provided by the above-mentioned cross-domain management function unit
  • the cross-domain management function unit is the management service provider
  • the business operation unit is the management service consumer.
  • the domain management function unit is the management service provider
  • the cross-domain management function unit or the business operation unit is the management service consumer.
  • the network element is the management service provider
  • the domain management functional unit or the cross-domain management functional unit or the business operation unit is the management service consumer. Providers and consumers of management services are selected according to actual application needs, which are not specifically limited here.
  • FIG. 2 is a schematic diagram of an embodiment of the fault autonomous system 200 in the embodiment of the application.
  • the fault autonomous system 200 mainly includes five fault autonomous functions, which are respectively an alarm correlation function. Fault identification function, fault prediction function, fault diagnosis function, and fault self-healing function. The contents of these five parts are described below.
  • Alarm correlation refers to merging or compressing multiple alarms with a correlation relationship.
  • the correlation relationship can be preset according to the needs of the actual application. It can be the correlation between the alarm generation time and the alarm generation object, or the alarm time and the alarm serial number. The relationship between them is not specifically limited here. For example, a two-minute time window is used to correlate or compress alarms, that is, if two alarms occur within 1 minute before and after, the two alarms are correlated.
  • Fault identification refers to the analysis of alarm information and network operation data to identify network faults.
  • the network fault represents information related to the fault, which may be the identified fault occurrence time, the object of the fault, or the number of fault events, which is not specifically limited here.
  • Fault prediction refers to analyzing alarm information and network operation data, predicting the development trend of network status, and discovering potential faults that may cause abnormality in advance. Through the fault prediction function, potential faults can be checked in advance, and the potential faults can be solved before the potential faults affect the normal operation of the equipment, so as to reduce the adverse effects of the faults on the normal work.
  • Fault diagnosis refers to the demarcation and location analysis of the fault based on the identified or predicted fault information, so as to determine the root cause of the fault. Fault diagnosis can be divided into two stages: fault delimitation and fault location.
  • Fault delimitation refers to the delimitation of the faults that are or predicted, including the delimitation of cross-domain scenarios to specific technical domains, and the delimitation of single-domain scenarios. to a specific network element.
  • Fault locating refers to further locating the fault delimitation result to determine the specific location of the fault, including but not limited to specific boards, ports, links, and at least one of the configurations. Fault locating can support the recovery plan. generation.
  • Fault self-healing refers to generating several alternative repair solutions based on the results of fault diagnosis.
  • the repair solutions used for different diagnosis results are also different.
  • the repair solutions can be to modify the configuration, restart the network element, or Element isolation can also be a single board replacement, which is not limited here.
  • FIG. 3 is a schematic flowchart of the method for determining the fault autonomy capability of the embodiment of the present application.
  • the network element that obtains the original fault data may be a domain management functional unit or a cross-domain management functional unit, which is selected according to actual application needs, which is not specifically limited here.
  • the original fault data includes original alarm information, fault information, a fault processing log, and at least one of log information included in the fault processing log, which is not specifically limited here.
  • the original alarm information may be an alarm serial number, an alarm generation time, or an alarm generation object, which is not specifically limited here.
  • the fault information can be a fault type or a fault scenario, which is not limited here.
  • the fault handling log can be either a fault diagnosis log or a fault self-healing log.
  • the log information contained in the fault handling log can be either fault diagnosis log information or fault self-healing log information, which is not described here. limited.
  • the fault statistical data is determined by statistical analysis of the original fault data, including fault statistical data corresponding to various fault types or fault events.
  • the fault statistical data includes: the number of alarm events, or the number of identified fault events, or the number of predicted fault events, or the number of diagnosed fault events, or the number of self-healing fault events, which is not specifically limited here.
  • the number of fault events existing in the live network can be manually input or It is obtained by the device itself, which is not specifically limited here.
  • the fault statistical data corresponding to the fault information dimension may be determined from the fault original data.
  • the fault dimension information can be different fault scenarios, different fault types, different fault statistics objects, or different fault statistics time, which is not limited here.
  • the failure scenarios include: a single network element failure scenario, a single domain failure scenario, a radio access network (RAN) domain failure scenario, a core network (core network, CN) domain failure scenario, a transport network (transport network) domain failure scenario , TN) domain failure scenarios, or cross-domain failure scenarios, which are not specifically limited here.
  • RAN radio access network
  • core network core network
  • CN core network
  • transport network transport network domain failure scenario
  • TN cross-domain failure scenarios
  • the fault statistics data corresponding to the RAN domain fault scenario include: the number of alarm events, the number of identified fault events in the RAN domain, the number of predicted fault events in the RAN domain, the number of fault events diagnosed in the RAN domain, or the number of RAN domain fault events The number of domain self-healing failure events, which is not limited here.
  • the number of RAN domain fault events existing in the existing network identifying the accurate number of RAN domain fault events, predicting the correct number of RAN domain fault events, diagnosing the correct number of RAN domain fault events, or successfully self-healing RAN domain fault events
  • the quantity may be manually input or obtained by the device itself, which is not specifically limited here.
  • the fault types include: configuration faults, software faults, hardware faults, or service faults, which are not specifically limited here.
  • hardware faults and performance faults can be further subdivided according to the needs of different application scenarios.
  • the hardware fault types include at least one of base station out-of-control faults, fronthaul/optical port faults, clock faults, cell out-of-service faults, and standing wave faults, which are not specifically limited here.
  • the performance type fault includes at least one of interference problem type fault, parameter problem type fault, coverage problem type fault, and capacity problem type fault, which is not specifically limited here.
  • the embodiment of the present application takes configuration faults as an example.
  • the fault statistics data corresponding to the configuration faults include: the number of alarm events, the number of fault events identified by the configuration type, the number of predicted fault events of the configuration type, the number of fault events diagnosed by the The number of recovery failure events is not limited here.
  • the number of configuration fault events existing in the live network the number of accurately identified configuration fault events, the number of accurate predicted configuration fault events, the number of correctly diagnosed configuration fault events, or the number of configuration fault events that have been successfully self-healing
  • the quantity may be manually input or obtained by the device itself, which is not specifically limited here.
  • the fault statistics objects include: areas, network element types, or network types, which are not specifically limited here.
  • the network element types include: 5G base station, next-station base station distributed unit (generation node B distributed unit, GNBDU), or network elements included in the 5G core network, which are not specifically limited here.
  • the network type includes an LTE network, a 5G network, a wireless network, or a core network, which is not specifically limited here.
  • the fault statistics time refers to the time for statistics of faults in practical applications, which may be calculated in different units, such as hours or days, which are not specifically limited here.
  • the fault statistical data corresponding to the fault statistical object or the fault statistical time is similar to the fault statistical data corresponding to the aforementioned different fault scenarios or different fault types, and details are not repeated here.
  • the performance indicators of the fault autonomous function can be determined according to the fault statistical data.
  • the performance indicators of the fault autonomous function include: alarm compression rate, fault self-identification rate, fault identification accuracy rate, fault self-prediction rate, fault self-prediction accuracy rate, fault self-prediction rate Self-diagnosis rate, fault self-diagnosis accuracy rate, fault self-healing processing rate, or fault self-healing accuracy rate, which are not specifically limited here.
  • the performance indicators of the fault autonomous function corresponding to the different fault dimension information may also be determined according to the fault statistics data corresponding to the different fault dimension information.
  • the autonomous capabilities of different fault autonomous functions can be determined according to different performance indicators, which can adapt to different needs in practical applications and improve the flexibility of the solution.
  • the fault scenario is a RAN domain fault scenario as an example.
  • the performance indicators of the fault autonomous function corresponding to the RAN domain fault scenario include: alarm compression ratio, RAN domain fault Self-identification rate, RAN domain fault identification accuracy, RAN domain fault self-prediction rate, RAN domain fault self-prediction accuracy, RAN domain fault self-diagnosis rate, RAN domain fault self-diagnosis accuracy, RAN domain fault self-healing processing rate, or RAN domain fault self-healing accuracy, which is not limited here.
  • the embodiment of the present application takes the fault type as a configuration fault as an example, and the performance indicators of the fault autonomous function corresponding to the configuration fault include: alarm compression ratio, self-identification rate of configuration faults, identification accuracy rate of configuration faults, configuration Class fault self-prediction rate, configuration-type fault self-prediction accuracy, configuration-type fault self-diagnosis rate, configuration-type fault self-diagnosis accuracy, configuration-type fault self-healing processing rate, or configuration-type fault self-healing accuracy rate. Do limit.
  • the fault autonomy level is determined according to the performance index of the fault autonomy function. Specifically, the fault autonomy level can be determined according to the performance index of the fault autonomous function, and the fault autonomy level describes the autonomous capability of the fault autonomous system without considering the fault dimension information.
  • the fault autonomy level of the fault autonomous system corresponding to one or several kinds of fault dimension information may also be determined according to the performance index of the fault autonomous function corresponding to the fault dimension information.
  • the fault autonomous system in this embodiment of the present application may include any of an alarm compression function, a fault self-identification function, a fault self-prediction function, a fault self-diagnosis function, and a fault self-healing function, which are not specifically limited here. .
  • the types of fault autonomous functions included in the fault autonomous system can be determined according to actual needs, which enhances the flexibility of the scheme.
  • step 304 includes the following two:
  • the first fault autonomous function level corresponding to the fault dimension information may be determined according to the performance index of the fault autonomous function corresponding to the fault dimension information.
  • the autonomous capability of a fault autonomous function corresponding to the dimension information According to the first fault autonomy function level, the second fault autonomy level corresponding to the fault dimension information can be determined, and the second fault autonomy level describes the autonomy capability of the fault autonomous system corresponding to the fault dimension information. According to the second fault autonomy level, the first fault autonomy level can be determined, and the first fault autonomy level describes the autonomous capability of the faulty autonomous system.
  • the first fault autonomous function level can be determined, so that the user or developer can optimize the fault autonomous function according to the first fault autonomous function level, and can also determine the fault autonomous system under a certain fault scenario or fault type
  • the autonomous capability of that is, the second fault autonomy level, enables users or developers to optimize the fault autonomous system in a targeted manner.
  • the first fault autonomy level is determined according to the second fault autonomy level, and the basis for the determination may be the second fault autonomy level corresponding to multiple different fault scenarios, the second fault autonomy level corresponding to multiple different fault types, and the It may be the second fault autonomy level corresponding to at least one fault scenario and the second fault autonomy level corresponding to at least one fault type, which are selected according to actual application needs, which are not specifically limited here.
  • a fault autonomous system with an alarm compression function, a fault self-identification function, a fault self-prediction function, a fault self-diagnosis function, and a fault self-healing function is taken as an example, and the above-mentioned determination of the first fault autonomous system is described in detail. grading process.
  • the first fault autonomous function level corresponding to the single-domain fault scenario is determined. Specifically, the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level is shown in Table 5:
  • Performance Indicators of Fault Autonomy Function First fault autonomous function level Alarm compression ratio Fault autonomy function level of the alarm compression function Fault self-identification rate and fault identification accuracy Fault autonomous function level of fault self-identification function Fault self-prediction rate and fault self-prediction accuracy Fault autonomous function level of fault self-prediction function Fault self-diagnosis rate and fault diagnosis accuracy Fault autonomy function level of fault self-diagnosis function Fault self-healing processing rate and fault self-healing accuracy rate Fault autonomous function level of fault self-healing function
  • the fault self-identification function in the single-domain fault scenario is the capability of level 2 to level 3, then the fault in the single-domain fault scenario
  • the performance index of the self-identification function corresponds to a value between 2 and 3. For example, if the fault self-identification rate in a single-domain fault scenario is 50%, and the fault identification accuracy in a single-domain fault scenario is 50%, the single-domain fault scenario can be determined.
  • the first fault autonomous function level of the lower fault self-identification function is 2.5.
  • the first fault autonomous function level of each other autonomous function in the single-domain fault scenario can be determined.
  • the range of the first fault autonomous function level of each autonomous function can be preset, and the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level of each autonomous function can also be preset, which is not limited here.
  • the second fault autonomy level corresponding to the single-domain fault scenario may be determined.
  • determine can be weighted summation of the fault autonomous function level of each autonomous function, or multiplication of the fault autonomous function level of each autonomous function, or it can be determined by using other functions. There is no specific limitation here.
  • the second fault autonomy level corresponding to the single-domain fault scenario the first fault autonomous function level of the alarm compression function in the single-domain fault scenario ⁇ weight 1 + the first fault autonomous function level of the fault self-identification function ⁇ weight 2+ The first fault autonomous function level of the fault self-prediction function ⁇ weight 3+the first fault autonomous function level of the fault self-diagnosis function ⁇ weight 4+the first fault autonomous function level of the fault self-healing function ⁇ weight 5.
  • the weight of each fault autonomous function can be determined according to actual application requirements, which is not specifically limited here.
  • the second fault autonomy level obtained at this time is the first fault autonomy level.
  • the autonomous capability of the faulty autonomous system under multiple fault scenarios can also be determined, and the processing can be performed in the same manner as in this embodiment.
  • the multiple fault scenarios here can be the same fault scenario corresponding to multiple different fault statistics time, the same fault scenario corresponding to multiple different fault statistics objects, or the same fault statistics time corresponding to multiple different
  • the fault scenario may also be multiple different fault scenarios corresponding to the same fault statistics object, which can be selected according to the needs of the actual application, which is not specifically limited here.
  • the first fault-autonomous function level corresponding to the service-type fault type is determined. Specifically, the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level is shown in Table 6:
  • Performance Indicators of Fault Autonomy Function First fault autonomous function level Alarm compression ratio Fault autonomy function level of the alarm compression function Fault self-identification rate and fault identification accuracy Fault autonomous function level of fault self-identification function Fault self-diagnosis rate and fault diagnosis accuracy Fault autonomy function level of fault self-diagnosis function Fault self-healing processing rate and fault self-healing accuracy rate Fault autonomous function level of fault self-healing function
  • the performance index of the fault self-diagnosis function under the service fault type corresponds to a value between 4 and 5. For example, if the fault self-diagnosis rate is 50% under the business fault type, and the fault diagnosis accuracy is 50% under the business fault type, it can be determined that the first fault autonomous function level of the fault self-diagnosis function under the business fault type is 4.2.
  • the first fault autonomous function level of each other autonomous function under the service-type fault type can be determined.
  • the range of the first fault autonomous function level of each autonomous function can be preset, and the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level of each autonomous function can also be preset, which is not limited here.
  • the second fault autonomy level corresponding to the service fault type can be determined.
  • determine can be weighted summation of the fault autonomous function level of each autonomous function, or multiplication of the fault autonomous function level of each autonomous function, or it can be determined by using other functions. There is no specific limitation here.
  • the second fault autonomy level corresponding to the service fault type the first fault autonomous function level of the alarm compression function under the service fault type ⁇ weight 1 + the first fault autonomous function level of the fault self-identification function ⁇ weight 2+ The first fault autonomous function level of the fault self-diagnosis function ⁇ weight value 3+the first fault autonomous function level of the fault self-healing function ⁇ weight value 4.
  • the weight of each fault autonomous function can be determined according to actual application requirements, which is not specifically limited here.
  • the second fault autonomy level obtained at this time is the first fault autonomy level.
  • the autonomous capability of the faulty autonomous system under multiple fault types can also be determined, and the processing can be performed in the same manner as in this embodiment.
  • the multiple fault types here can be the same fault type corresponding to multiple different fault statistics time, the same fault type corresponding to multiple different fault statistics objects, or the same fault statistics time corresponding to multiple different fault types
  • the fault type can also be a plurality of different fault types corresponding to the same fault statistics object, which is selected according to the needs of the actual application, which is not specifically limited here.
  • the first fault autonomous function level corresponding to the CN domain fault scenario and the software fault type is determined. Specifically, the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level is shown in Table 7:
  • Performance Indicators of Fault Autonomy Function First fault autonomous function level Fault self-identification rate and fault identification accuracy Fault autonomous function level of fault self-identification function Fault self-diagnosis rate and fault diagnosis accuracy Fault autonomy function level of fault self-diagnosis function Fault self-healing processing rate and fault self-healing accuracy rate Fault autonomous function level of fault self-healing function
  • the performance index of the fault self-healing function in the CN domain fault scenario and the software fault type corresponds to a value between 6 and 7.
  • the fault self-healing rate is 50% in the CN domain fault scenario and software fault type
  • the fault self-healing accuracy is 50% in the service fault type
  • the fault self-healing rate in the CN domain fault scenario and software fault type is 50%.
  • the first fault autonomous function level of the recovery function is 6.5.
  • the second fault autonomy level corresponding to the CN domain fault scenario and the software fault type can be determined.
  • determine can be weighted summation of the fault autonomous function level of each autonomous function, or multiplication of the fault autonomous function level of each autonomous function, or it can be determined by using other functions. There is no specific limitation here.
  • the second fault autonomy level corresponding to the CN domain fault scenario and the software-type fault type the first fault autonomous function level of the fault self-identification function ⁇ weight value 1 + the first fault autonomous function level of the fault self-diagnosis function ⁇ weight value 2+The first fault autonomous function level of the fault self-healing function ⁇ weight 3.
  • the weight of each fault autonomous function can be determined according to actual application requirements, which is not specifically limited here.
  • the second fault autonomy level obtained at this time is the first fault autonomy level.
  • the autonomous capability of the fault autonomous system corresponding to at least one fault scenario and at least one fault type may also be determined, which may be processed in the same manner as in this embodiment.
  • the at least one fault scenario here may be the same fault scenario corresponding to multiple different fault statistics times, the same fault scenario corresponding to multiple different fault statistics objects, or multiple different fault statistics corresponding to the same fault statistics time.
  • the fault scenario may also be multiple different fault scenarios corresponding to the same fault statistics object, which can be selected according to the needs of the actual application, which is not specifically limited here.
  • At least one fault type here may be the same fault type corresponding to multiple different fault statistics time, may be the same fault type corresponding to multiple different fault statistics objects, or may be multiple different fault types corresponding to the same fault statistics time, It can also be a plurality of different fault types corresponding to the same fault statistics object, which can be selected according to actual application needs, which is not specifically limited here.
  • the combination of at least one fault scenario and at least one fault type has multiple combinations, which can be one fault scenario and multiple fault types, multiple fault scenarios and multiple fault types, or multiple fault scenarios and multiple fault types. Multiple fault types can be selected according to actual application needs, which are not limited here.
  • the first fault autonomous function level corresponding to the fault dimension information can be determined according to the performance index of the fault autonomous function corresponding to the fault dimension information.
  • the autonomy capability of a certain fault autonomous function According to the first fault autonomous function level, the second fault autonomous function level can be determined. Then, according to the second fault autonomy function level, the first fault autonomy level is determined.
  • the autonomous capability of the fault autonomous function under different fault conditions can also be determined, so that the user or developer can optimize the fault autonomous function in a targeted manner.
  • this embodiment takes a fault autonomous system with a fault self-identification function, a fault self-diagnosis function, and a fault self-healing function in a TN domain fault scenario as an example to specifically describe the above process of determining the first fault autonomy level.
  • the first fault autonomous function level corresponding to the TN domain fault scenario is determined. Specifically, the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level is shown in Table 8:
  • Performance Indicators of Fault Autonomy Function First fault autonomous function level Fault self-identification rate and fault identification accuracy Fault autonomous function level of fault self-identification function Fault self-diagnosis rate and fault diagnosis accuracy Fault autonomy function level of fault self-diagnosis function Fault self-healing processing rate and fault self-healing accuracy rate Fault autonomous function level of fault self-healing function
  • the fault self-identification function in the TN domain fault scenario is the capability of level 2 to level 3, then the fault in the TN domain fault scenario is faulty.
  • the performance index of the self-identification function corresponds to a value between 2 and 3. For example, if the fault self-identification rate in the TN domain fault scenario is 50%, and the fault identification accuracy in the TN domain fault scenario is 50%, the TN domain fault scenario can be determined.
  • the first fault autonomous function level of the lower fault self-identification function is 2.5.
  • the first fault autonomous function level of each other autonomous function in the TN domain failure scenario can be determined.
  • the range of the first fault autonomous function level of each autonomous function can be preset, and the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level of each autonomous function can also be preset, which is not limited here.
  • the second fault autonomous function level may be determined.
  • determine can be weighted summation of the first fault autonomous function level of each autonomous function, or multiplication of the first fault autonomous function level of each autonomous function, or using other The function of , is not limited here.
  • the second fault autonomous function level here is the autonomous capability of the fault autonomous function corresponding to multiple fault scenarios.
  • the multiple fault scenarios here can be the same corresponding to multiple different fault statistics time.
  • the fault scenario can be the same fault scenario corresponding to multiple different fault statistics objects, or multiple different fault scenarios corresponding to the same fault statistics time, or multiple different fault scenarios corresponding to the same fault statistics object. needs to be selected, which is not limited here.
  • This embodiment describes the above process of determining the second fault autonomous function level by taking the same fault scenario corresponding to multiple different fault statistics objects as an example.
  • the second fault autonomous function level the first fault autonomous function level corresponding to the TN domain fault scenario in the LTE network ⁇ weight 1 + the first fault autonomous function level corresponding to the TN domain fault scenario in the 5G network ⁇ weight 2+
  • the first fault autonomous function level corresponding to the TN domain fault scenario in the wireless network ⁇ weight 3 the weight of the first fault autonomous function level corresponding to the fault scenario in different fault statistics objects can be selected according to the needs of the actual application. Do limit.
  • the first fault autonomy level may be determined according to the second fault autonomous function level corresponding to the multiple TN domain fault scenarios.
  • the second fault autonomous function level corresponding to the multiple TN domain fault scenarios.
  • the first fault autonomous level corresponding to multiple TN domain fault scenarios the second fault autonomous function level of the fault self-identification function ⁇ weight 1 + the second fault autonomous function level of the fault self-diagnosis function ⁇ weight 2 + fault
  • the weight of the second fault autonomous function level corresponding to the multiple TN domain fault scenarios may be determined according to actual application requirements, which is not specifically limited here.
  • this embodiment takes a fault autonomous system with an alarm compression function, a fault self-identification function, a fault self-diagnosis function, and a fault self-healing function under the configuration fault type as an example, and specifically describes the above-mentioned method for determining the first fault autonomy level. Process.
  • the first fault autonomous function level corresponding to the configuration fault type is determined according to the performance index of the fault autonomous function corresponding to the configuration fault type. Specifically, the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level is shown in Table 9:
  • Performance Indicators of Fault Autonomy Function First fault autonomous function level Alarm compression ratio Fault autonomy function level of the alarm compression function Fault self-identification rate and fault identification accuracy Fault autonomous function level of fault self-identification function Fault self-diagnosis rate and fault diagnosis accuracy Fault autonomy function level of fault self-diagnosis function Fault self-healing processing rate and fault self-healing accuracy rate Fault autonomous function level of fault self-healing function
  • the fault self-identification function under the configuration type fault type is the capability of level 2 to level 3
  • the fault self-identification function under the configuration type fault type is The performance index of the self-identification function corresponds to a value between 2 and 3. For example, if the fault self-identification rate is 50% under the configuration fault type, and the fault identification accuracy is 50% under the configuration type fault type, the configuration type fault type can be determined.
  • the first fault autonomous function level of the lower fault self-identification function is 2.5.
  • the first fault autonomous function level of each other autonomous function under the configuration fault type can be determined.
  • the range of the first fault autonomous function level of each autonomous function can be preset, and the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level of each autonomous function can also be preset, which is not limited here.
  • the second fault autonomous function level can be determined. There are many ways to determine, which can be weighted summation of the first fault autonomous function level of each autonomous function, or multiplication of the first fault autonomous function level of each autonomous function, or using other The function of , is not limited here.
  • the second fault autonomous function level here is the autonomous capability of the fault autonomous function corresponding to multiple fault types.
  • the multiple fault types here can be the same corresponding to multiple different fault statistics time.
  • the fault type can be the same fault type corresponding to multiple different fault statistics objects, or multiple different fault types corresponding to the same fault statistics time, or multiple different fault types corresponding to the same fault statistics object. needs to be selected, which is not limited here.
  • the above-mentioned process of determining the second fault autonomous function level is described by taking the same fault type corresponding to a plurality of different fault statistics times as an example.
  • the second fault autonomous function level the first fault autonomous function level corresponding to the configuration type fault type under the first fault time ⁇ weight 1 + the first fault autonomous function level corresponding to the configuration type fault type under the second fault time ⁇ Weight 2 + the first fault autonomous function level corresponding to the configuration fault type under the third fault time ⁇ weight 3
  • the weight of the first fault autonomous function level corresponding to the fault type under different fault statistics fault times can be based on the needs of practical applications Make a selection, which is not limited here.
  • the first fault autonomy level can be determined according to the second fault autonomous function level corresponding to the multiple configuration fault types.
  • determine can be weighted summation of the second fault autonomous function level of each autonomous function, or multiplication of the second fault autonomous function level of each autonomous function, or using other The function of , is not limited here.
  • the first fault autonomy level corresponding to multiple configuration fault types the second fault autonomous function level of the alarm compression function ⁇ the weight value 1 + the second fault autonomous function level of the fault self-identification function ⁇ the weight value 2 + the fault autonomous function level
  • the weight of the second fault autonomous function level corresponding to the multiple configuration fault types can be determined according to actual application requirements, which is not specifically limited here.
  • this embodiment takes a fault autonomous system with a fault self-identification function, a fault self-diagnosis function, and a fault self-healing function under a cross-domain fault scenario and a hardware fault type as an example, and specifically describes the above-mentioned determination of the first fault autonomy level. the process of.
  • the first fault-autonomous function level corresponding to the cross-domain fault scenario and the hardware-related fault type is determined. Specifically, the corresponding relationship between the performance index of the fault autonomous function and the first fault autonomous function level is shown in Table 10:
  • Performance Indicators of Fault Autonomy Function First fault autonomous function level Fault self-identification rate and fault identification accuracy Fault autonomous function level of fault self-identification function Fault self-diagnosis rate and fault diagnosis accuracy Fault autonomy function level of fault self-diagnosis function Fault self-healing processing rate and fault self-healing accuracy rate Fault autonomous function level of fault self-healing function
  • the performance indicators of the fault self-healing function in cross-domain fault scenarios and hardware-type fault types correspond to values between 6 and 7.
  • the fault self-healing rate is 50% in cross-domain fault scenarios and hardware fault types, and the fault self-healing accuracy is 50% in business fault types, it can be determined that the fault self-healing rate in cross-domain fault scenarios and hardware fault types is 50%.
  • the first fault autonomous function level of the recovery function is 6.5.
  • the second fault autonomous function level may be determined.
  • determine can be weighted summation of the first fault autonomous function level of each autonomous function, or multiplication of the first fault autonomous function level of each autonomous function, or using other The function of , is not limited here.
  • the second fault autonomous function level here is the autonomous capability of the fault autonomous function corresponding to at least one fault scenario and at least one fault type.
  • the at least one fault scenario here can be multiple different faults.
  • the same fault scenario corresponding to the statistical time can be the same fault scenario corresponding to multiple different fault statistics objects, or multiple different fault scenarios corresponding to the same fault statistical time, or multiple different faults corresponding to the same fault statistical object
  • the scene is selected according to the needs of the actual application, which is not limited here.
  • At least one fault type here may be the same fault type corresponding to multiple different fault statistics time, may be the same fault type corresponding to multiple different fault statistics objects, or may be multiple different fault types corresponding to the same fault statistics time, It can also be a plurality of different fault types corresponding to the same fault statistics object, which can be selected according to actual application needs, which is not specifically limited here.
  • the combination of at least one fault scenario and at least one fault type has multiple combinations, which can be one fault scenario and multiple fault types, multiple fault scenarios and multiple fault types, or multiple fault scenarios and multiple fault types. Multiple fault types can be selected according to actual application needs, which are not limited here.
  • This embodiment describes the above process of determining the second fault autonomous function level by taking the same cross-domain fault scenario and hardware fault type corresponding to multiple different fault statistics time as examples.
  • the second fault autonomous function level the first fault autonomous function level corresponding to the cross-domain fault scenario and the hardware-type fault type under the first fault time ⁇ weight 1 + the cross-domain fault scenario and hardware-type fault under the second fault time
  • the weight of the first fault autonomous function level can be selected according to the needs of practical applications, which is not specifically limited here.
  • the first fault autonomy level may be determined according to the second fault autonomy function level corresponding to the multiple cross-domain fault scenarios and the hardware-type fault types.
  • the second fault autonomy function level corresponding to the multiple cross-domain fault scenarios and the hardware-type fault types.
  • the first fault autonomy level corresponding to multiple cross-domain fault scenarios and hardware-type fault types the second fault autonomous function level of the alarm compression function ⁇ weight value 1 + the second fault autonomous function level of the fault self-identification function ⁇ weight Value 2+second fault autonomous function level of fault self-diagnosis function ⁇ weight value 3+second fault autonomous function level of fault self-healing function ⁇ weight value 4.
  • the weight of the second fault autonomous function level corresponding to the multiple cross-domain fault scenarios and the hardware-type fault types can be determined according to actual application needs, which is not specifically limited here.
  • the obtained first fault autonomy level can be determined in a specific fault scenario or fault type, and in a quantifiable form, the accuracy of determining the fault autonomy capability is improved.
  • the obtained first fault autonomy level can be determined in a specific fault scenario or fault type, and in a quantifiable form, the accuracy of determining the fault autonomy capability is improved.
  • different network elements may also be deployed to determine the fault autonomy level, which will be described separately below:
  • the first fault autonomy level is determined by the cross-domain management functional unit.
  • FIG. 4 is a schematic diagram of an embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application:
  • the base station sends the original fault data to the domain management functional unit;
  • the domain management functional unit may receive the original fault data sent by the base station.
  • the specific content of the original fault data has been described in detail in step 301 of the embodiment shown in FIG. 3 , and will not be repeated here.
  • the domain management functional unit determines fault statistics
  • the domain management functional unit determines the fault statistical data according to the received fault original data.
  • the specific determination method has been specifically described in step 302 in the embodiment shown in FIG. 3 , and will not be repeated here.
  • the domain management functional unit receives a request message sent by the cross-domain management functional unit;
  • the domain management functional unit will receive a request message sent by the cross-domain management functional unit, the request message carries at least one of fault dimension information, and the fault dimension information includes the fault scenario, the fault type, the fault statistics time, or the fault statistics object, There is no specific limitation here.
  • the function of the request message is to indicate the type of fault statistics data that the cross-domain management functional unit actually needs to use.
  • the request message can be a fault statistics data query request, a subscription request, or a task creation request. There are no restrictions.
  • the domain management functional unit sends fault statistics to the cross-domain management functional unit
  • the fault statistical data may be sent to the cross-domain management functional unit.
  • step 403 may or may not be performed, which is not specifically limited here. It should be noted that, if step 403 is executed, the fault statistics data sent in step 404 corresponds to the fault dimension information carried in the request message of step 403 . If step 403 is not executed, the fault statistics sent in step 404 can be determined according to the needs of the actual application, which can be fault statistics corresponding to multiple fault scenarios, or faults corresponding to multiple fault scenarios and multiple fault types. Statistical data, which is not limited here. The types of fault statistics have been specifically described in the embodiment 302 shown in FIG. 3 , and are not repeated here.
  • the cross-domain management functional unit determines the performance index of the fault autonomy function
  • the cross-domain management functional unit may determine the performance index of the fault autonomous function according to the fault statistical data.
  • the specific determination method has been specifically described in step 302 in the embodiment shown in FIG. 3 , and will not be repeated here.
  • the cross-domain management functional unit determines a first fault autonomy level
  • the cross-domain management function unit can determine the first fault autonomy level according to the performance index of the fault autonomous function corresponding to the fault dimension information, and the first fault autonomy level describes the autonomous capability of the fault autonomous system.
  • the specific way of determining the first fault autonomy level has been specifically described in step 304 in the embodiment shown in FIG. 3 , and details are not repeated here.
  • the cross-domain management functional unit may also determine at least one of the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level, and the second fault autonomy level corresponding to the fault dimension information. species, which is not specifically limited here.
  • the cross-domain management functional unit sends the first fault autonomy level to the service operation unit
  • the telecommunications equipment that finally receives the first fault autonomy level can be a service operation unit, a service operator unit, a third-party fault autonomous evaluation unit, or other management equipment. It is determined according to actual application needs, which is not specifically limited here.
  • the embodiment of the present application takes a service operation unit as an example.
  • the cross-domain management functional unit may send the first fault autonomy level to the service operation unit.
  • the cross-domain management functional unit may further determine at least one of the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level and the second fault autonomy level corresponding to the fault dimension information, and the cross-domain The management function unit may send the determined at least one of the first fault autonomous function level, the second fault autonomous function level, and the fault dimension second fault autonomy level to the service operation unit.
  • the specific determination method has been specifically described in step 304 in the embodiment shown in FIG. 3 , and will not be repeated here.
  • the service operation unit may These levels of information are displayed to users or researchers, so that users or researchers can determine the fault autonomous function or the autonomous capability of the fault autonomous system, and then optimize the fault autonomous function or the fault autonomous system. There are many ways of displaying, which may be in the form of text or in the form of voice, which is not specifically limited here.
  • the service operation unit can further determine the first fault autonomous level according to these level information, thereby reducing the cross-domain management function unit. The computing cost is reduced, and the memory resources are saved.
  • the obtained first fault autonomy level can be determined in a specific fault scenario or fault type, and in a quantifiable form, the accuracy of determining the fault autonomy capability is improved.
  • fault statistics and the first fault autonomy level can be determined respectively by different network elements, which can adapt to changeable deployment scenarios and improve the flexibility of the solution.
  • the first fault autonomy level is determined by the business operation unit.
  • the telecommunications equipment that determines the first fault autonomy level can be a service operation unit, a service operator unit, a third-party fault autonomous evaluation unit, or other management equipment.
  • the actual application needs to be determined, which is not specifically limited here.
  • the embodiments shown in FIG. 5 to FIG. 9 take a service operation unit as an example.
  • the service operation unit can receive different types of data, and can directly or indirectly determine the first fault autonomy level according to the data. In practical applications, different types of data can be selected according to actual needs.
  • the deployment method improves the flexibility and achievability of the scheme.
  • the service operation unit receives the performance index of the fault autonomy function, and determines the first fault autonomy level according to the performance index.
  • FIG. 5 is a schematic diagram of an embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application:
  • the base station sends the original fault data to the domain management functional unit;
  • the domain management functional unit determines fault statistics
  • the domain management functional unit receives a request message sent by the cross-domain management functional unit;
  • the domain management functional unit sends fault statistics to the cross-domain management functional unit
  • the cross-domain management functional unit determines the performance index of the fault autonomy function
  • steps 501 to 505 are similar to steps 401 to 405 in the embodiment shown in FIG. 4 , and details are not repeated here.
  • the cross-domain management function unit sends the performance index of the fault autonomy function to the service operation unit;
  • the cross-domain management function unit may send the performance index to the service operation unit.
  • the business operation unit determines the first fault autonomy level
  • the service operation unit may determine the first fault autonomy level according to the performance index of the fault autonomous function corresponding to the fault dimension information, and the first fault autonomy level describes the autonomous capability of the fault autonomous system.
  • the specific way of determining the first fault autonomy level has been specifically described in step 304 in the embodiment shown in FIG. 3 , and details are not repeated here.
  • the cross-domain management function unit may directly send the performance index to the service operation unit, so that the service operation unit determines the first fault autonomy level according to the performance index, thereby The operation cost of cross-domain management functional units is reduced, and memory resources are saved.
  • the business operation unit may also determine at least one of the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level and the second fault autonomy level corresponding to the fault dimension information, There is no specific limitation here.
  • the service operation unit determines at least one of the first fault autonomy function level corresponding to the fault dimension information, the second fault autonomous function level, the second fault autonomy level corresponding to the fault dimension information, and the first fault autonomy level, it can be These levels of information are displayed to users or researchers, so that users or researchers can determine the autonomous function or the autonomous capability of the autonomous system, and then optimize the autonomous function or the autonomous system.
  • displaying There are many ways of displaying, which may be in the form of text or in the form of voice, which is not specifically limited here.
  • the obtained first fault autonomy level can be determined in a specific fault scenario or fault type, and in a quantifiable form, the accuracy of determining the fault autonomy capability is improved.
  • the service operation unit can receive the performance index of the fault autonomy function to determine the first fault autonomy level, and can also display the first fault autonomy level to users or researchers, which improves the flexibility and achievability of the solution.
  • the service operation unit receives the fault statistics and determines the first fault autonomy level.
  • FIG. 6 is a schematic diagram of an embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application:
  • the base station sends the original fault data to the domain management functional unit;
  • Step 601 is similar to step 401 in the embodiment shown in FIG. 4 , and details are not repeated here.
  • the domain management functional unit sends the original fault data to the cross-domain management functional unit;
  • the domain management functional unit may send the original fault data to the cross-domain management functional unit.
  • the cross-domain management functional unit determines fault statistics
  • the cross-domain management function unit receives the request message sent by the service operation unit;
  • the cross-domain management functional unit sends fault statistics to the business operation unit
  • Steps 603 to 605 are similar to steps 402 to 404 in the aforementioned embodiment shown in FIG. 4 , and will not be repeated here. The difference is that the execution subjects of actions in steps 603 to 605 in the embodiment shown in FIG. 6 are inconsistent with the execution subjects of actions in steps 402 to 404 in the embodiment shown in FIG. 4 .
  • the executive body for determining the fault statistical data according to the fault original data is the cross-domain management functional unit.
  • the executive body that receives the request message and sends the fault statistics is also a functional unit of cross-domain management.
  • the execution subject that sends the request message and receives the fault statistics data is the business operation unit.
  • the cross-domain management function unit may directly send the fault statistical data to the service operation unit, so that the service operation unit determines the first fault autonomy level according to the fault statistical data, thereby reducing the It reduces the computing cost of cross-domain management functional units and saves memory resources.
  • the business operation unit determines the performance index of the fault autonomy function
  • the business operation unit determines the first fault autonomy level
  • Steps 606 and 607 are similar to steps 405 and 406 in the aforementioned embodiment shown in FIG. 4 , and will not be repeated here. The difference is that the execution subjects of actions in steps 606 and 607 in the embodiment shown in FIG. 6 are inconsistent with the execution subjects of actions in steps 405 and 406 in the embodiment shown in FIG. 4 .
  • the performance index of the fault autonomy function is determined according to the fault statistical data
  • the execution subject of the first fault autonomy level is determined according to the performance index is the service operation unit.
  • the business operation unit may also determine at least one of the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level and the second fault autonomy level corresponding to the fault dimension information, There is no specific limitation here. The specific determination method has been specifically described in the embodiment 304 shown in FIG. 3 , and will not be repeated here.
  • the service operation unit can display the level information to users or researchers , so that users or researchers can determine the autonomous function or the autonomous capability of the autonomous system, and then optimize the autonomous function or the autonomous system.
  • displaying There are many ways of displaying, which may be in the form of text or in the form of voice, which is not specifically limited here.
  • FIG. 7 is a schematic diagram of an embodiment of the method for determining fault autonomy according to the embodiment of the present application:
  • the base station sends the original fault data to the domain management functional unit;
  • the domain management functional unit determines fault statistics
  • Steps 701 and 702 are similar to steps 601 and 602 in the embodiment shown in FIG. 6 , and will not be repeated here.
  • the domain management functional unit receives the request message sent by the service operation unit;
  • the domain management functional unit sends fault statistics to the service operation unit;
  • Steps 703 and 704 are similar to steps 604 and 605 in the embodiment shown in FIG. 6 , and will not be repeated here. The difference is that the execution subjects of actions in steps 703 and 704 in the embodiment shown in FIG. 7 are inconsistent with the execution subjects of actions in steps 604 and 605 in the embodiment shown in FIG. 6 .
  • the executive body that receives the request message and sends the fault statistics data is the domain management functional unit, not the cross-domain management functional unit in the embodiment shown in FIG. 6 .
  • the business operation unit determines the performance index of the fault autonomy function
  • the business operation unit determines the first fault autonomy level
  • Steps 705 and 706 are similar to steps 606 and 607 in the foregoing embodiment shown in FIG. 6 , and are not described again here.
  • the obtained first fault autonomy level can be determined in a specific fault scenario or fault type, and in a quantifiable form, the accuracy of determining the fault autonomy capability is improved.
  • the domain management functional unit and the cross-domain management functional unit may simultaneously appear in a network deployment, and the domain management functional unit may perform the action of the cross-domain management functional unit, so that the solution can be applied to different In the deployment scenario of , the flexibility of the solution is improved.
  • the business operation unit receives the original data and determines the first fault autonomy level.
  • FIG. 8 is a schematic diagram of an embodiment of a method for determining a fault autonomy capability according to an embodiment of the present application:
  • the base station sends the original fault data to the domain management functional unit;
  • the domain management functional unit sends the original fault data to the cross-domain management functional unit;
  • Steps 801 and 802 are similar to steps 601 and 602 in the aforementioned embodiment shown in FIG. 6 , and will not be repeated here.
  • the cross-domain management functional unit sends the original fault data to the business operation unit;
  • the cross-domain management functional unit may send the original fault data to the service operation unit.
  • the business operation unit determines fault statistics
  • Step 804 is similar to step 402 in the embodiment shown in FIG. 4 , and details are not repeated here. The difference is that the execution subject of step 804 in the embodiment shown in FIG. 8 is inconsistent with the execution subject of step 402 in the embodiment shown in FIG. 4 . In the embodiment shown in FIG. 8 , it is the service operation unit that determines the fault statistical data according to the original fault data, not the domain management functional unit in the embodiment shown in FIG. 4 .
  • the business operation unit determines the performance index of the fault autonomy function
  • the business operation unit determines the first fault autonomy level
  • Steps 805 and 806 are similar to steps 606 and 607 in the aforementioned embodiment shown in FIG. 6 , and will not be repeated here.
  • the obtained first fault autonomy level can be determined in a specific fault scenario or fault type, and in a quantifiable form, the accuracy of determining the fault autonomy capability is improved.
  • the business operation unit can process the original fault data to obtain fault statistical data, so as to obtain the performance index of the fault autonomous function, finally determine the first fault autonomy level, and reduce the data. forwarding steps to reduce delay and reduce the risk of data loss.
  • FIG. 9 is a schematic diagram of an embodiment of the method for determining fault autonomy according to the embodiment of the present application:
  • the base station sends the original fault data to the domain management functional unit
  • step 901 and step 801 in the embodiment shown in FIG. 8 will not be repeated here.
  • the domain management functional unit sends the original fault data to the service operation unit;
  • the domain management functional unit After receiving the original fault data sent by the base station, the domain management functional unit can send the original fault data to a service operation unit.
  • the business operation unit determines fault statistics
  • the business operation unit determines the performance index of the fault autonomy function
  • the business operation unit determines the first fault autonomy level
  • Steps 903 to 905 are similar to steps 804 to 806 in the embodiment shown in FIG. 8 , and are not repeated here.
  • the obtained first fault autonomy level can be determined in a specific fault scenario or fault type, and in a quantifiable form, the accuracy of determining the fault autonomy capability is improved.
  • the domain management functional unit may directly send the original fault data to the service operation unit, thereby further reducing the number of data forwarding and reducing the risk of data loss.
  • FIG. 10 is a schematic diagram of an apparatus 1000 for determining a fault autonomy capability in an embodiment of the present application.
  • An embodiment of the apparatus 1000 for determining a fault autonomy capability in the present application includes:
  • an acquiring unit 1001 configured to acquire fault data corresponding to fault dimension information, where the fault dimension information includes at least one of a fault scenario and a fault type;
  • the determining unit 1002 is used to determine the performance index of the fault autonomous function corresponding to the fault dimension information according to the fault data. A sort of;
  • the determining unit 1002 is further configured to determine a first fault autonomy level according to the performance index of the fault autonomous function, where the first fault autonomy level describes the autonomous capability of the fault autonomous system.
  • the determining unit 1002 is further configured to:
  • the performance index of the fault autonomous function determine the first fault autonomous function level corresponding to the fault dimension information
  • the second fault autonomy level determine the second fault autonomy level corresponding to the fault dimension information
  • the first fault autonomy level is determined.
  • the determining unit 1002 is further configured to:
  • the performance index of the fault autonomous function determine the first fault autonomous function level corresponding to the fault dimension information
  • the second fault autonomous function level determine the second fault autonomous function level
  • the first fault autonomy level is determined.
  • the apparatus 1000 for determining the fault autonomy capability further includes a sending unit 1003 .
  • a sending unit 1003, configured to send the first fault autonomous function level to the network device
  • the sending unit 1003 is further configured to send the second fault autonomy level to the network device.
  • the apparatus 1000 for determining the fault autonomy capability further includes a sending unit 1003 .
  • the sending unit 1003 is further configured to send the first fault autonomous function level to the network device;
  • the sending unit 1003 is further configured to send the second fault autonomous function level to the network device.
  • the apparatus 1000 for determining the fault autonomy capability further includes a sending unit 1003 .
  • the sending unit 1003 is further configured to send the first fault autonomy level to the network device.
  • the apparatus 1000 for determining the fault autonomy capability further includes a sending unit 1003 .
  • the sending unit 1003 is further configured to send the performance index of the fault autonomy function to the network device.
  • the device 1000 for determining the fault autonomy capability may perform the operations performed by the cross-domain management functional unit in the embodiment shown in FIG. 4 or the operations performed by the cross-domain management functional unit and the service operation unit in the embodiment shown in FIG.
  • the operations performed, or the operations performed by the service operation unit in the foregoing embodiments shown in FIG. 6 to FIG. 9 will not be described in detail here.
  • FIG. 11 is a schematic diagram of an apparatus 1100 for determining a fault autonomy capability in an embodiment of the present application.
  • An embodiment of the apparatus 1100 for determining a fault autonomy capability in the present application includes:
  • the acquiring unit 1101 is configured to acquire the performance index of the fault autonomous function corresponding to the fault dimension information, the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level, the first fault autonomous level, and the corresponding fault dimension information. at least one of the second fault autonomy levels;
  • the determining unit 1102 is configured to determine, according to the performance index of the fault autonomous function, the first fault autonomous function level, the second fault autonomous function level, the first fault autonomous level, or the second fault autonomous level, the first fault autonomous level, the first fault autonomous level
  • the fault autonomy level describes the autonomous capability of the fault autonomous system.
  • the device 1100 for determining the fault autonomy capability may perform the operations performed by the service operation unit in the foregoing embodiment shown in FIG. 5 , and details are not repeated here.
  • FIG. 12 is a schematic structural diagram of a communication system 1200 according to an embodiment of the present application.
  • the communication system 1200 includes a first device 1201 , a second device 1202 and a third device 1203 , and a communication connection is established between the first device 1201 , the second device 1202 and the third device 1203 .
  • a first device 1201 configured to acquire fault data corresponding to fault dimension information, where the fault dimension information includes at least one of a fault scenario and a fault type;
  • the fault autonomous function includes at least one of a fault self-identification function, a fault self-prediction function, a fault self-diagnosis function, and a fault self-healing function;
  • the first fault autonomy level is determined according to the performance index, and the first fault autonomy level describes the autonomous capability of the fault autonomous system.
  • the first device 1201 may perform the operations performed by the cross-domain management functional unit in the foregoing embodiment shown in FIG. 4 , or the operations performed by the cross-domain management functional unit and the service operation unit in the foregoing embodiment shown in FIG. 5 . operations, or operations performed by the service operation unit in the embodiments shown in FIG. 6 to FIG. 9 , and details are not repeated here.
  • the second device 1202 is configured to acquire the performance index of the fault autonomous function corresponding to the fault dimension information, the first fault autonomous function level corresponding to the fault dimension information, the second fault autonomous function level, the first fault autonomy level, and the corresponding fault dimension information at least one of the second fault autonomy levels of the
  • the autonomy level describes the autonomous capability of the faulty autonomous system
  • the second fault autonomy level describes the autonomous capability of the faulty autonomous system corresponding to the fault dimension information
  • the first fault autonomous function level, the second fault autonomous function level, the first fault autonomous level, or the second fault autonomous level, the first fault autonomous level is determined, and the first fault autonomous level describes the autonomous capability of the fault autonomous system .
  • the second device 1202 may perform the operations performed by the service operation unit in the foregoing embodiment shown in FIG. 5 , and details are not described herein again.
  • the third device 1203 is configured to obtain fault data corresponding to the fault dimension information
  • the fault data corresponding to the fault dimension information is sent to the first device.
  • the third device 1203 may perform the operations performed by the base station in the foregoing embodiments shown in FIG. 4 to FIG. 9 , and details are not repeated here.
  • the computer device 1300 may include one or more central processing units (CPUs) 1301 and a memory 1305.
  • the memory 1305 stores one or more central processing units (CPUs) 1301. More than one application or data.
  • the memory 1305 may be volatile storage or persistent storage.
  • a program stored in memory 1305 may include one or more modules, each of which may include a series of instructions to operate on a computer device.
  • the central processing unit 1301 may be arranged to communicate with the memory 1305 to execute a series of instruction operations in the memory 1305 on the computer device 1300.
  • Computer device 1300 may also include one or more power supplies 1302, one or more wired or wireless network interfaces 1303, one or more input and output interfaces 1304, and/or, one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • one or more operating systems such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the computer device 1300 can perform the operations performed by the cross-domain management functional unit in the foregoing embodiment shown in FIG. 4, or the operations performed by the cross-domain management functional unit and the service operation unit in the foregoing embodiment shown in FIG. The operations performed by the service operation unit in the embodiments shown in FIG. 6 to FIG. 9 will not be described in detail here.
  • the computer device 1400 may include one or more central processing units (central processing units, CPU) 1401 and a memory 1405, and the memory 1405 stores one or more More than one application or data.
  • CPU central processing units
  • the memory 1405 may be volatile storage or persistent storage.
  • a program stored in memory 1405 may include one or more modules, each of which may include a series of instructions to operate on a computer device.
  • the central processing unit 1401 may be arranged to communicate with the memory 1405 to execute a series of instruction operations in the memory 1405 on the computer device 1400.
  • Computer device 1400 may also include one or more power supplies 1402, one or more wired or wireless network interfaces 1403, one or more input and output interfaces 1404, and/or, one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • one or more operating systems such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the computer device 1400 can perform the operations performed by the service operation unit in the foregoing embodiment shown in FIG. 5 , and details are not repeated here.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium.
  • the part or all or part of the technical solution of the present application that contributes substantially may be embodied in the form of a software product, and the computer software product is stored in a storage medium and includes several instructions for making A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), magnetic disk or optical disk and other media that can store program codes .

Abstract

一种故障自治能力的确定方法，用于提升确定故障自治能力的精确度。包括：通过获取故障维度信息对应的故障数据，确定故障维度信息对应的故障自治功能的性能指标，根据性能指标确定第一故障自治等级。其中，故障维度信息包括故障场景和故障类型中的至少一种，故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种，第一故障自治等级描述故障自治系统的自治能力。

Description

故障自治能力的确定方法以及相关设备 技术领域
本申请实施例涉及数据处理领域，尤其涉及故障自治能力的确定方法以及相关设备。
背景技术
现代社会更加注重提高工作效率和减少时间成本，许多行业都希望通过引入自动化技术来提升效率，降低时间成本，在故障处理领域同样如此。在实际应用自动化技术处理电信网络系统的故障时，需要确定电信网络自动化系统的故障自治能力，从而准确地发现电信网络自动化的故障自治的问题，有针对性地不断优化故障自治能力。
一种确定故障自治能力的方法是从故障自治端到端工作流中每个环节的人和机器的参与程度来定性地定义故障自治环节的自治能力，得到的结果是故障自治过程中的某一自治功能是否具有故障自治能力。该方法确定故障自治能力的精确度较低。
发明内容
本申请实施例提供了故障自治能力的确定方法及相关设备，用于提高确定故障自治能力的精确度。
本申请实施例第一方面提供了一种故障自治能力的确定方法，包括：
第一设备通过获取故障维度信息对应的故障数据，确定故障维度信息对应的故障自治功能的性能指标。其中，故障数据可以是故障原始数据，也可以是故障统计数据，具体此处不做限定。故障维度信息包括故障场景和故障类型中的至少一种。故障自治功能包括告警压缩功能，故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种。然后第一设备根据故障自治功能的性能指标确定第一故障自治等级，其中，第一故障自治等级描述(describe)故障自治系统的自治能力，体现为可量化的数值，是对故障自治系统中包括的故障自治功能的自治能力的综合评价。
本申请实施例中，第一设备确定出的第一故障自治等级可以描述故障自治系统对应于不同故障场景和/或不同故障类型的自治能力，并以可量化的形式体现，提升了确定故障自治能力的精确度。
结合第一方面，本申请实施第一方面的第一种实现方式中，第一设备可以根据故障自治功能的性能指标，确定故障维度信息对应的第一故障自治功能等级，第一故障自治功能等级描述故障维度信息对应的故障自治功能的自治能力。之后，根据第一故障自治功能等级，确定故障维度信息对应的第二故障自治等级，第二故障自治等级描述故障维度信息对应的故障自治系统的自治能力。然后根据第二故障自治等级，确定第一故障自治等级。其中，第一故障自治功能等级描述故障维度信息对应的故障自治功能的自治能力，第二故障自治等级描述故障维度信息对应的故障自治系统的自治能力。
本申请实施例中，第一设备还可以确定出第一故障自治功能等级，可以根据第一故障自治功能等级对故障自治功能进行优化，还可以确定出某种故障场景或故障类型下故障自 治系统的自治能力，即第二故障自治等级，有针对性地对故障自治系统进行优化。
结合第一方面，本申请实施第一方面的第二种实现方式中，第一设备可以根据故障自治功能的性能指标，确定故障维度信息对应的第一故障自治功能等级，第一故障自治功能等级描述故障维度信息对应的故障自治功能的自治能力。之后，根据第一故障自治功能等级，确定第二故障自治功能等级，其中，第二故障自治功能等级描述故障自治功能的自治能力，可以对应于多个不同的故障场景，也可以对应于多个不同的故障类型，还可以对应于不同故障场景和不同故障类型，具体此处不做限定。然后根据第二故障自治功能等级，确定第一故障自治等级，其中，第一故障自治等级对应的故障情形与第二故障自治功能等级对应的故障情形相同。
本申请实施例中，第一设备还可以确定出不同故障情形下故障自治功能的自治能力，即第二故障自治功能等级，可以有针对性地对故障自治功能进行优化。
结合第一方面的第一种实施方式，本申请实施例第一方面的第三种实施方式中，第一设备在确定出第一故障自治功能等级之后，可以向电信设备发送第一故障自治功能等级。第一设备在确定出第二故障自治等级之后，可以向电信设备发送第二故障自治等级。需要注意的是，电信设备可以是网络设备，也可以是管理设备，具体此处不做限定。为了方便阅读，下文所述的第二设备，即为此处的电信设备。
本申请实施例第一方面的第三种实施方式中，第一设备可以同时向第二设备发送第一故障自治功能等级和第二故障自治等级，也可以分别发送第一故障自治功能等级和第二故障自治等级，还可以只发送第一故障自治功能等级或第二故障自治等级，具体此处不做限定。
本申请实施例中，第一设备将确定出的第一故障自治功能等级和第二故障自治等级中的至少一个，发送给第二设备，使得第二设备根据第一故障自治功能等级或第二故障自治等级确定第一故障自治等级，可以降低第一设备的运算成本，节约内存资源。
结合第一方面的第二种实施方式，本申请实施例第一方面的第四种实施方式中，第一设备在确定出第一故障自治功能等级之后，可以向第二设备发送第一故障自治功能等级。第一设备在确定出第二故障自治功能等级之后，可以向第二设备发送第二故障自治功能等级。
本申请实施例第一方面的第四种实施方式中，第一设备可以同时向第二设备发送第一故障自治功能等级和第二故障自治功能等级，也可以分别发送第一故障自治功能等级和第二故障自治功能等级，还可以只发送第一故障自治功能等级或第二故障自治功能等级，具体此处不做限定。
本申请实施例中，第一设备将确定出的第一故障自治功能等级和第二故障功能自治等级中的至少一个，发送给第二设备，使得第二设备根据第一故障自治功能等级或第二故障自治功能等级确定第一故障自治等级，可以降低第一设备的运算成本，节约内存资源。
结合第一方面、第一方面的第一种实施方式至第四种实施方式中的任一种，本申请实施例第一方面的第五种实施方式中，第一设备在确定第一故障自治等级之后，可以向第二设备发送第一故障自治等级，使得第二设备将第一故障自治等级显示给用户、研发人员或 者网络管理者。
本申请实施例中，第一设备可以向第二设备发送第一故障自治等级，使得第二设备将第一故障自治等级的具体内容显示给用户、研发人员或者网络管理者，用户、研发人员或者网络管理者可以据此对故障自治系统进行优化。
结合第一方面、第一方面的第一种实施方式至第四种实施方式中的任一种，本申请实施例第一方面的第六种实施方式中，第一设备在根据故障数据，确定故障维度信息对应的故障自治功能的性能指标之后，可以将该性能指标发送给第二设备，使得第二设备根据该性能指标确定第一故障自治等级。
本申请实施例中，第一设备确定出故障自治功能的性能指标后，即可将该性能指标发送给第二设备，使得第二设备根据该性能指标确定第一故障自治等级，可以降低第一设备的运算成本，节约内存资源。
结合第一方面、第一方面的第一种实施方式至第六种实施方式中的任一种，本申请实施例第一方面的第七种实施方式中，性能指标包括告警压缩率，故障自识别率，故障自识别准确率，故障自预测率，故障自预测准确率，故障自诊断率，故障自诊断准确率，故障自愈率，和故障自愈准确率中的至少一个。
本申请实施例中，可以根据不同的性能指标，确定不同故障自治功能的自治能力，在实际应用中能够适应不同的需求，提升方案的灵活性。
结合第一方面、第一方面的第一种实施方式至第七种实施方式中的任一种，本申请实施例第一方面的第八种实施方式中，故障场景包括单网元故障场景，单域故障场景，无线接入网络RAN域故障场景，核心网CN故障场景，传输网TN域故障场景，和跨域故障场景中的至少一种。
本申请实施例中，可以根据不同的故障场景确定不同故障场景对应的故障自治功能或故障自治系统的自治能力，可以在实际应用根据不同的需求进行选择，提升方案的灵活性。
结合第一方面、第一方面的第一种实施方式至第八种实施方式中的任一种，本申请实施例第一方面的第九种实施方式中，故障类型包括配置类故障类型，软件类故障类型，硬件类故障类型，性能类故障类型，和业务类故障类型中的至少一种。在实际应用中，可以根据不同的应用场景的需要，对硬件类故障和性能类故障进一步进行细分。其中，硬件类故障类型包括基站脱管类故障、前传/光口类故障、时钟类故障、小区退服类故障、驻波类故障中的至少一种。性能类故障类型包括干扰问题类故障、参数问题类故障、覆盖问题类故障、容量问题类故障中的至少一种。
本申请实施例中，可以根据不同的故障类型确定不同故障类型对应的故障自治功能或故障自治系统的自治能力，可以在实际应用根据不同的需求进行选择，提升方案的灵活性。
结合第一方面、第一方面的第一种实施方式至第九种实施方式中的任一种，本申请实施例第一方面的第十种实施方式中，第一设备可以通过接收第三设备发送的故障原始数据，将故障原始数据确定为故障数据。
结合第一方面、第一方面的第一种实施方式至第九种实施方式中的任一种，本申请实施例第一方面的第十一种实施方式中，第一设备还可以接收第三设备发送的故障原始数据， 对故障原始进行统计分析得到故障统计数据，将故障统计数据确定为故障数据。
本申请实施例中，第一设备获取故障数据的方式有多种，可以根据第一设备的内存资源和运算能力进行选择，提升了方案的灵活性和可实现性。
结合第一方面，第一方面的第一种实施方式至第二种实施方式，或第一方面的第七种实施方式至第十一种实施方式中的任一种，本申请实施例第一方面的第十二种实施方式中，第一设备可以是业务运营单元。
结合第一方面、第一方面的第一种实施方式至第十一种实施方式中的任一种，本申请实施例第一方面的第十三种实施方式中，第一设备可以是跨域管理功能单元。
本申请实施例中，第一设备可以是业务运营单元，也可以是跨域管理功能单元，在实际应用中，根据网元部署的需求进行选择，提升了方案的灵活性和可实现性。
本申请实施例第二方面提供了一种故障自治能力的确定方法，包括：
第二设备获取故障维度信息对应的故障自治功能的性能指标，故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，和故障维度信息对应的第二故障自治等级中的至少一种。
然后根据获取到的根据故障自治功能的性能指标，第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，或第二故障自治等级，确定第一故障自治等级，其中，第一故障自治等级描述故障自治系统的自治能力。
本申请实施例中，第二设备可以收到不同类型的数据，根据这些数据可以直接或者间接地确定出第一故障自治等级，在实际应用中，可以根据实际需求选择具体的确定方式，提升了方案的灵活性和可实现性。
结合第二方面，本申请实施例第二方面的第一种实现方式中，性能指标包括告警压缩率，故障自识别率，故障自识别准确率，故障自预测率，故障自预测准确率，故障自诊断率，故障自诊断准确率，故障自愈率，和故障自愈准确率中的至少一个。
本申请实施例中，可以根据不同的性能指标，确定不同故障自治功能的自治能力，在实际应用中能够适应不同的需求，提升方案的灵活性。
结合第二方面、第二方面的第一种实现方式，本申请实施例第二方面的第二种实现方式中，故障维度信息包括故障场景和故障类型中的至少一种。故障场景包括单网元故障场景，单域故障场景，无线接入网络RAN域故障场景，核心网CN故障场景，传输网TN域故障场景，和跨域故障场景中的至少一种。故障类型包括配置类故障类型，软件类故障类型，硬件类故障类型，性能类故障类型，和业务类故障类型中的至少一种。
本申请实施例中，可以根据不同的故障维度信息确定不同故障维度信息对应的第一故障自治等级，可以在实际应用根据不同的需求进行选择，提升方案的灵活性。
结合第二方面、第二方面的第一种实现方式至第二种实现方式，本申请实施例第二方面的第三种实现方式中，故障自治功能包括告警压缩功能，故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种。
本申请实施例中，可以根据实际应用的需要，确定故障自治系统包含的故障自治功能的类型，提升方案的灵活性。
结合第二方面、第二方面的第一种实现方式至第三种实现方式中的任一种，本申请实施例第二方面的第四种实现方式中，第二设备可以是业务运营单元，业务运营商单元，第三方故障自治评估单元或者其他的管理设备，具体此处不做限定。本申请实施例以业务运营单元为例，业务运营单元在确定出第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，或第二故障自治等级后，可以将这些等级显示给用户、网络管理者或者研究人员。
本申请实施例中，业务运营单元可以将确定出的不同类型的等级信息显示出来，使得用户、网络管理者或者研究人员有针对性的对故障自治功能或故障自治系统进行优化。
本申请实施例第三方面提供了一种故障自治能力的确定方法，包括:
第三设备获取故障维度信息对应的故障数据，并向第一设备发送该故障数据，使得第一设备利用该故障数据确定第一故障自治等级。
结合第三方面，本申请实施例第三方面的第一种实现方式中，故障维度信息对应的故障数据可以是故障维度信息对应的故障原始数据。
结合第三方面、第三方面的第一种实现方式，本申请实施例第三方面的第二种实现方式中，故障维度信息对应的故障数据可以是故障维度信息对应的故障统计数据。
结合第三方面、第三方面的第一种实现方式至第二种实现方式中的任一种，本申请实施例第三方面的第三种实现方式中，第三设备可以是域管理功能单元，也可以是跨域管理功能单元。
本申请实施例中，第三设备的类型有多种，第三设备向第一设备发送的故障数据有多种，在实际应用中可以根据具体需要进行选择，提升了方案的灵活性。
本申请实施例第四方面提供了一种故障自治能力的确定装置，包括:
获取单元，用于获取故障维度信息对应的故障数据，故障维度信息包括故障场景和故障类型中的至少一种；
确定单元，用于根据故障数据，确定故障维度信息对应的故障自治功能的性能指标，故障自治功能包括告警压缩功能，故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种；
确定单元，还用于根据故障自治功能的性能指标确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
该故障自治能力的确定装置用于执行前述第一方面的方法。
本申请实施例第五方面提供了一种故障自治能力的确定装置，包括:
获取单元，用于获取故障维度信息对应的故障自治功能的性能指标，故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，和故障维度信息对应的第二故障自治等级中的至少一种，其中，第一故障自治功能等级描述故障维度信息对应的故障自治功能的自治能力，第二故障自治功能等级描述故障自治功能的自治能力，第一故障自治等级描述故障自治系统的自治能力，第二故障自治等级描述故障维度信息对应的故障自治系统的自治能力；
确定单元，用于根据故障自治功能的性能指标，第一故障自治功能等级，第二故障自 治功能等级，第一故障自治等级，或第二故障自治等级，确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
该故障自治能力的确定装置用于执行前述第二方面的方法。
本申请实施例第六方面提供了一种故障自治能力的确定装置，包括:
获取单元，用于获取故障维度信息对应的故障数据；
发送单元，用于向第一设备发送故障维度信息对应的故障数据。
该故障自治能力的确定装置用于执行前述第三方面的方法。
本申请实施例第七方面提供了一种计算机设备，包括：
处理器、存储器、输入输出设备以及总线。其中处理器、存储器、输入输出设备与总线相连。处理器用于执行以下步骤：
获取故障维度信息对应的故障数据，故障维度信息包括故障场景和故障类型中的至少一种；
根据故障数据，确定故障维度信息对应的故障自治功能的性能指标，故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种；
根据故障自治功能的性能指标确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
该计算机设备用于执行前述第一方面的方法。
本申请实施例第八方面提供了一种计算机设备，包括：
处理器、存储器、输入输出设备以及总线。其中处理器、存储器、输入输出设备与总线相连。处理器用于执行以下步骤：
获取故障维度信息对应的故障自治功能的性能指标，故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，和故障维度信息对应的第二故障自治等级中的至少一种；
根据故障自治功能的性能指标，第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，或第二故障自治等级，确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
该计算机设备用于执行前述第二方面的方法。
本申请实施例第九方面提供了一种计算机设备，包括：
处理器、存储器、输入输出设备以及总线。其中处理器、存储器、输入输出设备与总线相连。处理器用于执行以下步骤：
获取故障维度信息对应的故障数据；
向第一设备发送故障维度信息对应的故障数据。
该计算机设备用于执行前述第三方面的方法。
本申请实施例第十方面提供了一种计算机可读存储介质，该计算机可读存储介质中保存有程序，当该计算机执行程序时，执行前述第一方面、第二方面和第三方面的方法。
本申请实施例第十一方面提供了一种计算机程序产品，当该计算机程序产品在计算机上执行时，该计算机执行前述第一方面、第二方面和第三方面的方法。
本申请实施例第十二方面提供了一种通信系统，该通信系统包括第一设备、第二设备以及第三设备；
其中，第一设备用于执行如前述第一方面、第一方面的第一种实施方式至第十三种实施方式中任一项所描述的方法；
第二设备用于执行如前述第二方面、第二方面的第一种实施方式至第四种实施方式中任一项所描述的方法；
第三设备用于执行如前述第三方面、第二方面的第一种实施方式至第三种实施方式中任一项所描述的方法。
附图说明
图1为本申请实施例中的一个系统架构图；
图2为本申请实施例中故障自治系统的一个实施例示意图；
图3为本申请实施例故障自治能力确定方法的一个流程示意图；
图4为本申请实施例故障自治能力确定方法的一个实施例示意图；
图5为本申请实施例故障自治能力确定方法的另一个实施例示意图；
图6为本申请实施例故障自治能力确定方法的另一个实施例示意图；
图7为本申请实施例故障自治能力确定方法的另一个实施例示意图；
图8为本申请实施例故障自治能力确定方法的另一个实施例示意图；
图9为本申请实施例故障自治能力确定方法的另一个实施例示意图；
图10为本申请实施例故障自治能力确定装置的一个结构示意图；
图11为本申请实施例故障自治能力确定装置的另一个结构示意图；
图12为本申请实施例中通信系统的一个结构示意图；
图13为本申请实施例计算机设备的一个结构示意图；
图14为本申请实施例计算机设备的另一个结构示意图。
具体实施方式
本申请实施例提供了一种故障自治能力的确定方法，用于提升确定故障自治能力的精确度。
本申请实施例可以应用在如图1所示的系统架构中，主要涉及的网元有以下四种：
业务运营单元，也可以称为通信业务管理功能单元(communication service management function，CSMF)，可以提供计费、结算、帐务、客服、营业、网络监控、通信业务生命周期管理，业务意图翻译等功能和管理服务。可以使用在运营商的运营系统，也可以使用在垂直行业的运营系统(vertical operational technology system，VOTS)，具体此处不做限定。
跨域管理功能单元，也可以称之为网络管理功能单元(network management function，NMF)，跨域管理功能单元提供以下一项或几项功能或者管理服务：网络的生命周期管理，网络的部署，网络的故障管理，网络的性能管理，网络的配置管理，网络的保障，网络的 优化功能，通信服务提供商的网络意图(intent from communication service provider，intent-CSP)的翻译，通信服务使用者的网络意图(intent from communication service consumer，intent-CSC)的翻译等。这里的网络可以包括一个或者多个网元，也可以包括子网络或者网络切片，具体此处不做限定。例如，跨域管理功能单元可以是网络切片管理功能(network slice management function，NSMF)，可以是管理数据分析功能(management data analytical function，MDAF)，也可以是跨域自组织网络功能(self-organization network function，SON-function)，还可以是跨域意图管理功能单元，具体此处不做限定。
需要说明的是，在不同运营商的部署场景下，跨域管理功能单元的作用有所不同。可以提供以下一项或几项管理功能或者管理服务：子网络的生命周期管理，子网络的部署，子网络的故障管理，子网络的性能管理，子网络的配置管理，子网络的保障，子网络的优化功能，通信服务提供商的子网络意图的翻译，通信服务使用者的子网络意图的翻译等，具体此处不做限定。其中，子网络包括多个小的子网络或者多个网络切片子网络。
域管理功能单元，也可以称之为子网络管理功能单元(sub network management function，SNMF)或者网元管理功能单元(network element management function，NEMF),域管理功能单元提供以下一项或者多项功能或者管理服务：子网络或者网元的生命周期管理，子网络或者网元的部署，子网络或者网元的故障管理，子网络或者网元的性能管理，子网络或者网元的保障，子网络或者网元的优化管理，子网络或者网元的意图翻译等，具体此处不做限定。这里的子网络可以包括一个或者多个网元，也可以包括一个或多个子网络，即一个或多个子网络组成一个更大覆盖范围的子网络，还可以包括一个或多个网络切片子网络。子网络有多种的表现形式，可以是某个技术域的网络，比如无线接入网，核心网，传输网等。可以是某个制式的网络，比如全球移动通讯系统(global system for mobile communications，GSM)网络，长期演进(long term evolution，LTE)网络，第五代移动通信网络(5th generation mobile network，5G)等。还可以是某个设备商提供的网络，比如设备商X提供的网络等。还可以是某个地理区域的网络，比如某个工厂的网络，某个市区的网络等。具体此处不做限定。
网元，是指提供网络服务的实体，可以是核心网所包括的网元，或者接入网所包括的网元等，不同的网元有不同的表现形式。例如，核心网所包括的网元可以是如下所示网元中的至少一种：接入与移动管理功能(access and mobility management function，AMF)实体，会话管理功能(session management function，SMF)实体，策略控制功能(policy control function，PCF)实体，网络数据分析功能(network data analysis function，NWDAF)实体，以及网络存储功能(network repository function，NRF)网关，具体此处不做限定。接入网所包括的网元可以是如下所示网元中的至少一种：各类基站，集中控制单元(central unit control panel，CUCP)，集中单元(central unit，CU)，分布式单元(distributed unit，DU)，以及集中用户面单元(central unit user panel，CUUP)，具体此处不做限定。其中，各类基站包括：下一代基站(generation node B，gNB)，或者演进型基站(evolved Node B，eNB)。
在服务化管理架构下，聚焦管理服务的提供者(management service producer，MnS  Producer)和管理服务的消费者(management service consumer，MnS Consumer)，可以理解的是：当管理服务由上述业务运营单元提供时，业务运营单元为管理服务提供者，其他业务运营商单元可以为管理服务消费者。当管理服务由上述跨域管理功能单元提供时，跨域管理功能单元为管理服务提供者，业务运营单元为管理服务消费者。当管理服务由上述域管理功能单元提供时，域管理功能单元为管理服务提供者，跨域管理功能单元或者业务运营单元为管理服务消费者。当管理服务由上述网元提供时，网元为管理服务提供者，域管理功能单元或者跨域管理功能单元或者业务运营单元为管理服务消费者。管理服务的提供者和消费者根据实际应用的需要进行选择，具体此处不做限定。
故障自治可以基于上述系统框架实现，请参阅图2，图2为本申请实施例中故障自治系统200的一个实施例示意图，故障自治系统200主要包括五个故障自治功能，分别为告警关联功能，故障识别功能，故障预测功能，故障诊断功能，和故障自愈功能。下面分别对这五个部分的内容进行介绍。
一、告警关联功能：
告警关联是指对具有关联关系的多条告警进行合并或者压缩，关联关系可以根据实际应用的需要进行预设，可以是告警产生时间和告警产生对象的关联，也可以是告警时间和告警流水号之间的关联，具体此处不做限定。例如，采用两分钟的时间窗来关联或者压缩告警，即如果两个告警的发生时间在前后1分钟内，那这两个告警就被关联起来。
二、故障识别功能：
故障识别是指对告警信息以及网络运行数据进行分析，识别出网络故障。该网络故障表示的是与故障相关的信息，可以是识别出的故障产生时间，也可以是发生故障的对象，还可以是故障事件的数量，具体此处不做限定。
三、故障预测功能：
故障预测是指对告警信息以及网络运行数据进行分析，预测网络状态的发展趋势，提前发现可能导致异常的潜在故障。通过故障预测功能，可以预先对潜在故障进行排查，在潜在故障影响设备的正常工作之前，解决潜在故障，减少故障对正常工作造成的不良影响。
四、故障诊断功能：
故障诊断是指根据识别或预测出的故障信息，对故障进行问题的定界定位分析，从而确定故障发生的根本原因。故障诊断可以分为故障定界和故障定位两个阶段，故障定界是指对是被或预测的故障进行定界，包括对于跨域场景定界到具体的技术域，对单域场景定界到具体的网元。故障定位是指对故障定界结果进行进一步定位，确定故障发生的具体位置，包括但不限于具体的单板，以及端口，以及链路，以及配置中的至少一种，故障定位能够支撑恢复方案的生成。
五、故障自愈功能：
故障自愈是指根据故障诊断的结果生成若干备选的修复方案，对不同的诊断结果使用的修复方案也会有所不同，修复方案可以是修改配置，可以是重启网元，还可以是网元隔离，还可以是更换单板，具体此处不做限定。
需要注意的是，由于不同的应用场景对于故障自治的需求不同，所以在实际应用中的 故障自治系统可以选用这五个功能中的部分功能，具体此处不做限定。
本申请实施例主要的流程如图3所示，请参阅图3，本申请实施例故障自治能力确定方法的一个流程示意图。
301、获取故障原始数据；
获取故障原始数据的网元可以是域管理功能单元，也可以是跨域管理功能单元，根据实际应用的需要进行选择，具体此处不做限定。
故障原始数据包括原始告警信息，以及故障信息，以及故障处理日志，以及故障处理日志包含的日志信息中的至少一种，具体此处不做限定。
其中，原始告警信息可以是告警流水号，也可以是告警产生时间，还可以是告警产生对象，具体此处不做限定。故障信息可以是故障类型，也可以是故障场景，具体此处不做限定。故障处理日志可以是故障诊断日志，也可以是故障自愈日志，相应地，故障处理日志包含的日志信息可以是故障诊断的日志信息，也可以是故障自愈的日志信息，具体此处不做限定。
302、确定故障统计数据；
故障统计数据是对故障原始数据进行统计分析确定的，包括各种故障类型或故障事件对应的故障统计数据。具体的，故障统计数据包括：告警事件数量，或识别故障事件数量，或预测故障事件数量，或诊断故障事件数量，或自愈故障事件数量，具体此处不做限定。
具体的，故障统计数据的具体内容如下表1所示：
表1
Figure PCTCN2020118446-appb-000001
其中，现网中存在的故障事件数量，识别准确的故障事件数量，预测准确的故障事件数量，诊断正确的故障事件数量，或成功自愈处理的故障事件数量可以是由人工输入的，也可以是由设备自行得到的，具体此处不做限定。
可选的，可以从故障原始数据中确定故障信息维度对应的故障统计数据。故障维度信息可以是不同的故障场景，可以是不同的故障类型，也可以是不同的故障统计对象，还可以是不同的故障统计时间，具体此处不做限定。
具体的，故障场景包括：单网元故障场景，单域故障场景，无线接入网络(radio access network，RAN)域故障场景，核心网(core network，CN)域故障场景，传输网(transport network，TN)域故障场景，或跨域故障场景，具体此处不做限定。
本申请实施例中，用于确定故障统计数据，从而确定故障自治功能或故障自治系统的自治能力的故障场景有多种情况，可以在实际应用根据不同的需求进行选择，提升方案的灵活性。
本申请实施例以RAN域故障场景为例，RAN域故障场景对应的故障统计数据包括：告警事件数量，RAN域识别故障事件数量，RAN域预测故障事件数量，RAN域诊断故障事件数量，或RAN域自愈故障事件数量，具体此处不做限定。
具体的，RAN域故障场景对应的故障统计数据的具体内容如下表2所示：
表2
Figure PCTCN2020118446-appb-000002
其中，现网中存在的RAN域故障事件数量，识别准确的RAN域故障事件数量，预测准确的RAN域故障事件数量，诊断正确的RAN域故障事件数量，或成功自愈处理的RAN域故障事件数量可以是由人工输入的，也可以是由设备自行得到的，具体此处不做限定。
具体的，故障类型包括：配置类故障，软件类故障，硬件类故障，或业务类故障，具体此处不做限定。在实际应用中，还可以根据不同的应用场景的需要，对硬件类故障和性能类故障进一步进行细分。其中，硬件类故障类型包括基站脱管类故障、前传/光口类故障、时钟类故障、小区退服类故障、驻波类故障中的至少一种，具体此处不做限定。性能类故障类型包括干扰问题类故障、参数问题类故障、覆盖问题类故障、容量问题类故障中的至少一种，具体此处不做限定。
本申请实施例中，用于确定故障统计数据，从而确定故障自治功能或故障自治系统的自治能力的故障类型有多种情况，可以在实际应用根据不同的需求进行选择，提升方案的灵活性。
本申请实施例以配置类故障为例，配置类故障对应的故障统计数据包括：告警事件数 量，配置类识别故障事件数量，配置类预测故障事件数量，配置类诊断故障事件数量，或配置类自愈故障事件数量，具体此处不做限定。
具体的，配置类故障对应的故障统计数据的具体内容如下表3所示：
表3
Figure PCTCN2020118446-appb-000003
其中，现网中存在的配置类故障事件数量，识别准确的配置类故障事件数量，预测准确的配置类故障事件数量，诊断正确的配置类故障事件数量，或成功自愈处理的配置类故障事件数量可以是由人工输入的，也可以是由设备自行得到的，具体此处不做限定。
具体的，故障统计对象包括：区域，网元类型，或网络类型，具体此处不做限定。其中，网元类型包括：5G基站，下一站基站分布式单元(generation node B distributed unit，GNBDU)，或5G核心网所包括的网元，具体此处不做限定。网络类型包括LTE网络，5G网络，无线网络，或核心网，具体此处不做限定。
具体的，故障统计时间是指在实际应用中统计故障的时间，可以采用不同的单位进行计算，如小时或天等，具体此处不做限定。
故障统计对象或故障统计时间所对应的故障统计数据与前述不同故障场景或不同故障类型所对应的故障统计数据类似，具体此处不再赘述。
303、确定故障自治功能的性能指标；
故障自治功能的性能指标可以根据故障统计数据确定，具体的，故障自治功能的性能指标包括：告警压缩率，故障自识别率，故障识别准确率，故障自预测率，故障自预测准确率，故障自诊断率，故障自诊断准确率，故障自愈处理率，或故障自愈准确率，具体此处不做限定。
具体的，不同故障自治功能的性能指标的计算方式有所不同，具体方式可以如表4所示：
表4
Figure PCTCN2020118446-appb-000004
具体的，还可以根据不同故障维度信息对应的故障统计数据确定不同故障维度信息对应的故障自治功能的性能指标。
本申请实施例中，可以根据不同的性能指标，确定不同故障自治功能的自治能力，在实际应用中能够适应不同的需求，提升方案的灵活性。
具体的故障维度信息如前文所述，本申请实施例以故障场景为RAN域故障场景为例，与之对应的RAN域故障场景对应的故障自治功能的性能指标包括：告警压缩率，RAN域故障自识别率，RAN域故障识别准确率，RAN域故障自预测率，RAN域故障自预测准确率，RAN域故障自诊断率，RAN域故障自诊断准确率，RAN域故障自愈处理率，或RAN域故障自愈准确率，具体此处不做限定。
本申请实施例以故障类型为配置类故障为例，与之对应的配置类故障对应的故障自治功能的性能指标包括：告警压缩率，配置类故障自识别率，配置类故障识别准确率，配置类故障自预测率，配置类故障自预测准确率，配置类故障自诊断率，配置类故障自诊断准确率，配置类故障自愈处理率，或配置类故障自愈准确率，具体此处不做限定。
304、确定第一故障自治等级；
故障自治等级是根据故障自治功能的性能指标确定的。具体的，可以根据故障自治功能的性能指标，确定故障自治等级，该故障自治等级描述(describe)不考虑故障维度信息的故障自治系统的自治能力。还可以根据故障维度信息对应的故障自治功能的性能指标， 确定某一种或某几种故障维度信息对应的故障自治系统的故障自治等级。
具体的，本申请实施例中的故障自治系统可以包括告警压缩功能，故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的任意几个，具体此处不做限定。在实际应用中，可以根据实际需要，确定故障自治系统包含的故障自治功能的类型，增强了方案的灵活性。
步骤304的实现方式包括以下两种：
其中，在第一种实现方式中，可以根据故障维度信息对应的故障自治功能的性能指标，确定故障维度信息对应的第一故障自治功能等级，第一故障自治功能等级描述故障自治过程中，故障维度信息对应的某一个故障自治功能的自治能力。根据第一故障自治功能等级，可以确定故障维度信息对应的第二故障自治等级，第二故障自治等级描述故障维度信息对应的故障自治系统的自治能力。根据第二故障自治等级，可以确定出第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
本申请实施例中，可以确定出第一故障自治功能等级，使得用户或者开发人员根据第一故障自治功能等级对故障自治功能进行优化，还可以确定出某种故障场景或故障类型下故障自治系统的自治能力，即第二故障自治等级，使得用户或者开发人员有针对性地对故障自治系统进行优化。
具体的，根据第二故障自治等级确定第一故障自治等级，确定的依据可以是多个不同故障场景对应的第二故障自治等级，可以是多个不同故障类型对应的第二故障自治等级，还可以是至少一个故障场景对应的第二故障自治等级和至少一个故障类型对应的第二故障自治等级，根据实际应用的需要进行选择，具体此处不做限定。
示例的，以单域故障场景下，具有告警压缩功能，故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能的故障自治系统为例，具体描述上述确定第一故障自治等级的过程。
根据单域故障场景对应的故障自治功能的性能指标，确定单域故障场景对应的第一故障自治功能等级。具体的，故障自治功能的性能指标与第一故障自治功能等级的对应关系如表5所示：
表5
故障自治功能的性能指标 第一故障自治功能等级
告警压缩率 告警压缩功能的故障自治功能等级
故障自识别率和故障识别准确率 故障自识别功能的故障自治功能等级
故障自预测率和故障自预测准确率 故障自预测功能的故障自治功能等级
故障自诊断率和故障诊断准确率 故障自诊断功能的故障自治功能等级
故障自愈处理率和故障自愈准确率 故障自愈功能的故障自治功能等级
示例的，以确定单域故障场景下故障自识别功能的第一故障自治功能等级为例，若单域故障场景下故障自识别功能为等级2到等级3的能力，则单域故障场景下故障自识别功能的性能指标对应2到3之间的数值，例如，单域故障场景下故障自识别率为50％，单域故障场景下故障识别准确率为50％，则可以确定单域故障场景下故障自识别功能的第一故 障自治功能等级为2.5。
具体的，根据相同的方式，可以确定出其他各个自治功能在单域故障场景下的第一故障自治功能等级。具体的，各个自治功能的第一故障自治功能等级范围可以预先设置，故障自治功能的性能指标与各个自治功能的第一故障自治功能等级的对应关系也可以预先设置，具体此处不做限定。
具体的，根据单域故障场景对应的第一故障自治功能等级，可以确定单域故障场景对应的第二故障自治等级。确定的方式有多种，可以是对每个自治功能的故障自治功能等级进行加权求和，也可以是对每个自治功能的故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
例如，单域故障场景对应的第二故障自治等级＝单域故障场景下告警压缩功能的第一故障自治功能等级×权值1+故障自识别功能的第一故障自治功能等级×权值2+故障自预测功能的第一故障自治功能等级×权值3+故障自诊断功能的第一故障自治功能等级×权值4+故障自愈功能的第一故障自治功能等级×权值5。各个故障自治功能的权重可以根据实际应用的需要进行确定，具体此处不做限定。
需要注意的是，由于本实施例中确定的是单域故障场景下的故障自治系统的自治能力，所以此时得到的第二故障自治等级即为第一故障自治等级。在实际应用中，也可以确定多个故障场景下的故障自治系统的自治能力，可以使用与本实施例相同的方式进行处理。具体的，此处的多个故障场景可以是多个不同故障统计时间对应的相同故障场景，可以是多个不同故障统计对象对应的相同故障场景，也可以是同一故障统计时间对应的多个不同故障场景，还可以是同一故障统计对象对应的多个不同故障场景，根据实际应用的需要进行选择，具体此处不做限定。
示例的，以业务类故障类型下，具有告警压缩功能，故障自识别功能，故障自诊断功能，和故障自愈功能的故障自治系统为例，具体描述上述确定第一故障自治等级的过程。
根据业务类故障类型对应的故障自治功能的性能指标，确定业务类故障类型对应的第一故障自治功能等级。具体的，故障自治功能的性能指标与第一故障自治功能等级的对应关系如表6所示：
表6
故障自治功能的性能指标 第一故障自治功能等级
告警压缩率 告警压缩功能的故障自治功能等级
故障自识别率和故障识别准确率 故障自识别功能的故障自治功能等级
故障自诊断率和故障诊断准确率 故障自诊断功能的故障自治功能等级
故障自愈处理率和故障自愈准确率 故障自愈功能的故障自治功能等级
示例的，以确定业务类故障类型下故障自诊断功能的第一故障自治功能等级为例，若预设业务类故障类型下故障自诊断功能为等级4到等级5的能力，且预设故障自诊断率的权重低于故障诊断准确率，则业务类故障类型下故障自诊断功能的性能指标对应4到5之间的数值。例如，业务类故障类型下故障自诊断率为50％，业务类故障类型下故障诊断准确率为50％，则可以确定业务类故障类型下故障自诊断功能的第一故障自治功能等级为 4.2。
具体的，根据相同的方式，可以确定出其他各个自治功能在业务类故障类型下的第一故障自治功能等级。具体的，各个自治功能的第一故障自治功能等级范围可以预先设置，故障自治功能的性能指标与各个自治功能的第一故障自治功能等级的对应关系也可以预先设置，具体此处不做限定。
具体的，根据业务类故障类型对应的第一故障自治功能等级，可以确定业务类故障类型对应的第二故障自治等级。确定的方式有多种，可以是对每个自治功能的故障自治功能等级进行加权求和，也可以是对每个自治功能的故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
例如，业务类故障类型对应的第二故障自治等级＝业务类故障类型下告警压缩功能的第一故障自治功能等级×权值1+故障自识别功能的第一故障自治功能等级×权值2+故障自诊断功能的第一故障自治功能等级×权值3+故障自愈功能的第一故障自治功能等级×权值4。各个故障自治功能的权重可以根据实际应用的需要进行确定，具体此处不做限定。
需要注意的是，由于本实施例中确定的是业务类故障类型下的故障自治系统的自治能力，所以此时得到的第二故障自治等级即为第一故障自治等级。在实际应用中，也可以确定多个故障类型下的故障自治系统的自治能力，可以使用与本实施例相同的方式进行处理。具体的，此处的多个故障类型可以是多个不同故障统计时间对应的相同故障类型，可以是多个不同故障统计对象对应的相同故障类型，也可以是同一故障统计时间对应的多个不同故障类型，还可以是同一故障统计对象对应的多个不同故障类型，根据实际应用的需要进行选择，具体此处不做限定。
示例的，以CN域故障场景和软件类故障类型下，具有故障自识别功能，故障自诊断功能，和故障自愈功能的故障自治系统为例，具体描述上述确定第一故障自治等级的过程。
根据CN域故障场景和软件类故障类型共同对应的故障自治功能的性能指标，确定CN域故障场景和软件类故障类型共同对应的第一故障自治功能等级。具体的，故障自治功能的性能指标与第一故障自治功能等级的对应关系如表7所示：
表7
故障自治功能的性能指标 第一故障自治功能等级
故障自识别率和故障识别准确率 故障自识别功能的故障自治功能等级
故障自诊断率和故障诊断准确率 故障自诊断功能的故障自治功能等级
故障自愈处理率和故障自愈准确率 故障自愈功能的故障自治功能等级
示例的，以确定CN域故障场景和软件类故障类型下故障自愈功能的第一故障自治功能等级为例，若预设CN域故障场景和软件类故障类型下故障自愈功能为等级6到等级7的能力，且预设故障自愈处理率的权重与故障自愈准确率相同，则CN域故障场景和软件类故障类型下故障自愈功能的性能指标对应6到7之间的数值。例如，CN域故障场景和软件类故障类型下故障自愈处理率为50％，业务类故障类型下故障自愈准确率为50％，则可以确定CN域故障场景和软件类故障类型下故障自愈功能的第一故障自治功能等级为6.5。
具体的，根据CN域故障场景和软件类故障类型共同对应的第一故障自治功能等级，可 以确定CN域故障场景和软件类故障类型共同对应的第二故障自治等级。确定的方式有多种，可以是对每个自治功能的故障自治功能等级进行加权求和，也可以是对每个自治功能的故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
例如，CN域故障场景和软件类故障类型共同对应的第二故障自治等级＝故障自识别功能的第一故障自治功能等级×权值1+故障自诊断功能的第一故障自治功能等级×权值2+故障自愈功能的第一故障自治功能等级×权值3。各个故障自治功能的权重可以根据实际应用的需要进行确定，具体此处不做限定。
需要注意的是，由于本实施例中确定的是CN域故障场景和软件类故障类型共同对应的故障自治系统的自治能力，所以此时得到的第二故障自治等级即为第一故障自治等级。在实际应用中，也可以确定至少一个故障场景和至少一个故障类型共同对应的故障自治系统的自治能力，可以使用与本实施例相同的方式进行处理。
具体的，此处的至少一个故障场景可以是多个不同故障统计时间对应的相同故障场景，可以是多个不同故障统计对象对应的相同故障场景，也可以是同一故障统计时间对应的多个不同故障场景，还可以是同一故障统计对象对应的多个不同故障场景，根据实际应用的需要进行选择，具体此处不做限定。此处的至少一个故障类型可以是多个不同故障统计时间对应的相同故障类型，可以是多个不同故障统计对象对应的相同故障类型，也可以是同一故障统计时间对应的多个不同故障类型，还可以是同一故障统计对象对应的多个不同故障类型，根据实际应用的需要进行选择，具体此处不做限定。至少一个故障场景和至少一个故障类型的组合，有多种组合情况，可以是一个故障场景和多个故障类型，也可以是多个故障场景和多个故障类型，还可以是多个故障场景和多个故障类型，根据实际应用的需要进行选择，具体此处不做限定。
第二种实现方式中，可以根据故障维度信息对应的故障自治功能的性能指标，确定故障维度信息对应的第一故障自治功能等级，第一故障自治功能等级描述故障自治过程中，故障维度信息对应的某一个故障自治功能的自治能力。根据第一故障自治功能等级，可以确定第二故障自治功能等级。然后根据第二故障自治功能等级，确定第一故障自治等级。
本申请实施例中，还可以确定出不同故障情形下故障自治功能的自治能力，即第二故障自治功能等级，使得用户或者开发人员可以有针对性地对故障自治功能进行优化。
示例的，本实施例以TN域故障场景下，具有故障自识别功能，故障自诊断功能，和故障自愈功能的故障自治系统为例，具体描述上述确定第一故障自治等级的过程。
根据TN域故障场景对应的故障自治功能的性能指标，确定TN域故障场景对应的第一故障自治功能等级。具体的，故障自治功能的性能指标与第一故障自治功能等级的对应关系如表8所示：
表8
故障自治功能的性能指标 第一故障自治功能等级
故障自识别率和故障识别准确率 故障自识别功能的故障自治功能等级
故障自诊断率和故障诊断准确率 故障自诊断功能的故障自治功能等级
故障自愈处理率和故障自愈准确率 故障自愈功能的故障自治功能等级
示例的，以确定TN域故障场景下故障自识别功能的第一故障自治功能等级为例，若TN域故障场景下故障自识别功能为等级2到等级3的能力，则TN域故障场景下故障自识别功能的性能指标对应2到3之间的数值，例如，TN域故障场景下故障自识别率为50％，TN域故障场景下故障识别准确率为50％，则可以确定TN域故障场景下故障自识别功能的第一故障自治功能等级为2.5。
具体的，根据相同的方式，可以确定出其他各个自治功能在TN域故障场景下的第一故障自治功能等级。具体的，各个自治功能的第一故障自治功能等级范围可以预先设置，故障自治功能的性能指标与各个自治功能的第一故障自治功能等级的对应关系也可以预先设置，具体此处不做限定。
具体的，根据TN域故障场景对应的第一故障自治功能等级，可以确定第二故障自治功能等级。确定的方式有多种，可以是对每个自治功能的第一故障自治功能等级进行加权求和，也可以是对每个自治功能的第一故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
需要注意的是，此处的第二故障自治功能等级为多个故障场景共同对应的故障自治功能的自治能力，具体的，此处的多个故障场景可以是多个不同故障统计时间对应的相同故障场景，可以是多个不同故障统计对象对应的相同故障场景，也可以是同一故障统计时间对应的多个不同故障场景，还可以是同一故障统计对象对应的多个不同故障场景，根据实际应用的需要进行选择，具体此处不做限定。
本实施例以多个不同故障统计对象对应的相同故障场景为例，描述上述确定第二故障自治功能等级的过程。此时，第二故障自治功能等级＝LTE网络中TN域故障场景对应的第一故障自治功能等级×权值1+5G网络中TN域故障场景对应的第一故障自治功能等级×权值2+无线网络中TN域故障场景对应的第一故障自治功能等级×权值3，不同故障统计对象中故障场景对应的第一故障自治功能等级的权重可以根据实际应用的需要进行选择，具体此处不做限定。
具体的，根据多个TN域故障场景共同对应的第二故障自治功能等级，可以确定第一故障自治等级。确定的方式有多种，可以是对每个自治功能的第二故障自治功能等级进行加权求和，也可以是对每个自治功能的第二故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
例如，多个TN域故障场景共同对应的第一故障自治等级＝故障自识别功能的第二故障自治功能等级×权值1+故障自诊断功能的第二故障自治功能等级×权值2+故障自愈功能的第二故障自治功能等级×权值3。多个TN域故障场景共同对应的第二故障自治功能等级的权重可以根据实际应用的需要进行确定，具体此处不做限定。
示例的，本实施例以配置类故障类型下，具有告警压缩功能，故障自识别功能，故障自诊断功能，和故障自愈功能的故障自治系统为例，具体描述上述确定第一故障自治等级的过程。
根据配置类故障类型对应的故障自治功能的性能指标，确定配置类故障类型对应的第一故障自治功能等级。具体的，故障自治功能的性能指标与第一故障自治功能等级的对应 关系如表9所示：
表9
故障自治功能的性能指标 第一故障自治功能等级
告警压缩率 告警压缩功能的故障自治功能等级
故障自识别率和故障识别准确率 故障自识别功能的故障自治功能等级
故障自诊断率和故障诊断准确率 故障自诊断功能的故障自治功能等级
故障自愈处理率和故障自愈准确率 故障自愈功能的故障自治功能等级
示例的，以确定配置类故障类型下故障自识别功能的第一故障自治功能等级为例，若配置类故障类型下故障自识别功能为等级2到等级3的能力，则配置类故障类型下故障自识别功能的性能指标对应2到3之间的数值，例如，配置类故障类型下故障自识别率为50％，配置类故障类型下故障识别准确率为50％，则可以确定配置类故障类型下故障自识别功能的第一故障自治功能等级为2.5。
具体的，根据相同的方式，可以确定出其他各个自治功能在配置类故障类型下的第一故障自治功能等级。具体的，各个自治功能的第一故障自治功能等级范围可以预先设置，故障自治功能的性能指标与各个自治功能的第一故障自治功能等级的对应关系也可以预先设置，具体此处不做限定。
具体的，根据配置类故障类型对应的第一故障自治功能等级，可以确定第二故障自治功能等级。确定的方式有多种，可以是对每个自治功能的第一故障自治功能等级进行加权求和，也可以是对每个自治功能的第一故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
需要注意的是，此处的第二故障自治功能等级为多个故障类型共同对应的故障自治功能的自治能力，具体的，此处的多个故障类型可以是多个不同故障统计时间对应的相同故障类型，可以是多个不同故障统计对象对应的相同故障类型，也可以是同一故障统计时间对应的多个不同故障类型，还可以是同一故障统计对象对应的多个不同故障类型，根据实际应用的需要进行选择，具体此处不做限定。
本实施例以多个不同故障统计时间对应的相同故障类型为例，描述上述确定第二故障自治功能等级的过程。此时，第二故障自治功能等级＝第一故障时间下配置类故障类型对应的第一故障自治功能等级×权值1+第二故障时间下配置类故障类型对应的第一故障自治功能等级×权值2+第三故障时间下配置类故障类型对应的第一故障自治功能等级×权值3，不同故障统计故障时间下故障类型对应的第一故障自治功能等级的权重可以根据实际应用的需要进行选择，具体此处不做限定。
具体的，根据多个配置类故障类型共同对应的第二故障自治功能等级，可以确定第一故障自治等级。确定的方式有多种，可以是对每个自治功能的第二故障自治功能等级进行加权求和，也可以是对每个自治功能的第二故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
例如，多个配置类故障类型共同对应的第一故障自治等级＝告警压缩功能的第二故障自功能等级×权值1+故障自识别功能的第二故障自治功能等级×权值2+故障自诊断功能的 第二故障自治功能等级×权值3+故障自愈功能的第二故障自治功能等级×权值4。多个配置类故障类型共同对应的第二故障自治功能等级的权重可以根据实际应用的需要进行确定，具体此处不做限定。
示例的，本实施例以跨域故障场景和硬件类故障类型下，具有故障自识别功能，故障自诊断功能，和故障自愈功能的故障自治系统为例，具体描述上述确定第一故障自治等级的过程。
根据跨域故障场景和硬件类故障类型共同对应的故障自治功能的性能指标，确定跨域故障场景和硬件类故障类型共同对应的第一故障自治功能等级。具体的，故障自治功能的性能指标与第一故障自治功能等级的对应关系如表10所示：
表10
故障自治功能的性能指标 第一故障自治功能等级
故障自识别率和故障识别准确率 故障自识别功能的故障自治功能等级
故障自诊断率和故障诊断准确率 故障自诊断功能的故障自治功能等级
故障自愈处理率和故障自愈准确率 故障自愈功能的故障自治功能等级
示例的，以确定跨域故障场景和硬件类故障类型下故障自愈功能的第一故障自治功能等级为例，若预设跨域故障场景和硬件类故障类型下故障自愈功能为等级6到等级7的能力，且预设故障自愈处理率的权重与故障自愈准确率相同，则跨域故障场景和硬件类故障类型下故障自愈功能的性能指标对应6到7之间的数值。例如，跨域故障场景和硬件类故障类型下故障自愈处理率为50％，业务类故障类型下故障自愈准确率为50％，则可以确定跨域故障场景和硬件类故障类型下故障自愈功能的第一故障自治功能等级为6.5。
具体的，根据跨域故障场景和硬件类故障类型对应的第一故障自治功能等级，可以确定第二故障自治功能等级。确定的方式有多种，可以是对每个自治功能的第一故障自治功能等级进行加权求和，也可以是对每个自治功能的第一故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
需要注意的是，此处的第二故障自治功能等级为至少一个故障场景和至少一个故障类型共同对应的故障自治功能的自治能力，具体的，此处的至少一个故障场景可以是多个不同故障统计时间对应的相同故障场景，可以是多个不同故障统计对象对应的相同故障场景，也可以是同一故障统计时间对应的多个不同故障场景，还可以是同一故障统计对象对应的多个不同故障场景，根据实际应用的需要进行选择，具体此处不做限定。此处的至少一个故障类型可以是多个不同故障统计时间对应的相同故障类型，可以是多个不同故障统计对象对应的相同故障类型，也可以是同一故障统计时间对应的多个不同故障类型，还可以是同一故障统计对象对应的多个不同故障类型，根据实际应用的需要进行选择，具体此处不做限定。至少一个故障场景和至少一个故障类型的组合，有多种组合情况，可以是一个故障场景和多个故障类型，也可以是多个故障场景和多个故障类型，还可以是多个故障场景和多个故障类型，根据实际应用的需要进行选择，具体此处不做限定。
本实施例以多个不同故障统计时间对应的相同跨域故障场景和硬件类故障类型为例，描述上述确定第二故障自治功能等级的过程。此时，第二故障自治功能等级＝第一故障时间 下跨域故障场景和硬件类故障类型对应的第一故障自治功能等级×权值1+第二故障时间下跨域故障场景和硬件类故障类型对应的第一故障自治功能等级×权值2+第三故障时间下跨域故障场景和硬件类故障类型对应的第一故障自治功能等级×权值3，不同故障统计故障时间下故障类型对应的第一故障自治功能等级的权重可以根据实际应用的需要进行选择，具体此处不做限定。
具体的，根据多个跨域故障场景和硬件类故障类型共同对应的第二故障自治功能等级，可以确定第一故障自治等级。确定的方式有多种，可以是对每个自治功能的第二故障自治功能等级进行加权求和，也可以是对每个故障自治功能的第二故障自治功能等级进行乘法运算，还可以是使用其他的函数确定，具体此处不做限定。
例如，多个跨域故障场景和硬件类故障类型共同对应的第一故障自治等级＝告警压缩功能的第二故障自功能等级×权值1+故障自识别功能的第二故障自治功能等级×权值2+故障自诊断功能的第二故障自治功能等级×权值3+故障自愈功能的第二故障自治功能等级×权值4。多个跨域故障场景和硬件类故障类型共同对应的第二故障自治功能等级的权重可以根据实际应用的需要进行确定，具体此处不做限定。本申请实施例中，得到的第一故障自治等级可以确定到具体的故障场景或故障类型中，并以体现为可量化的形式，提升了确定故障自治能力的精确度。
本申请实施例中，得到的第一故障自治等级可以确定到具体的故障场景或故障类型中，并以体现为可量化的形式，提升了确定故障自治能力的精确度。
进一步的，用于确定故障自治等级的故障自治功能的性能指标有多种情形，同时根据该性能指标确定第一故障自治等级的方式有多种，使得方案能够具体应用到多种实际情境中，提升了方案的灵活性和可实现性。
本申请实施例中还可以部署不同的网元来确定故障自治等级，下面分别进行说明：
一、由跨域管理功能单元确定第一故障自治等级。
请参阅图4，本申请实施例故障自治能力确定方法的一个实施例示意图：
401、基站向域管理功能单元发送故障原始数据；
域管理功能单元可以接收到基站发送的故障原始数据，故障原始数据的具体内容在图3所示实施例步骤301中已经具体阐述，此处不再赘述。
402、域管理功能单元确定故障统计数据；
域管理功能单元根据接收到的故障原始数据确定故障统计数据，具体的确定方式在图3所示实施例步骤302中已经具体阐述，此处不再赘述。
403、域管理功能单元接收跨域管理功能单元发送的请求消息；
域管理功能单元会接收到跨域管理功能单元发送的请求消息，该请求消息中携带故障维度信息中的至少一种，故障维度信息包括故障场景，故障类型，故障统计时间，或故障统计对象，具体此处不做限定。该请求消息的作用是用于指示跨域管理功能单元实际需要使用的故障统计数据的类型，该请求消息可以是故障统计数据查询请求，也可以是订阅请求，还可以是任务创建请求，具体此处不做限定。
404、域管理功能单元向跨域管理功能单元发送故障统计数据；
域管理功能单元在确定故障统计数据之后，可以将故障统计数据发送给跨域管理功能单元。
可选的，步骤403可以执行，也可以不执行，具体此处不做限定。需要注意的是，若执行步骤403，则步骤404发送的故障统计数据对应于步骤403的请求消息中携带的故障维度信息。若不执行步骤403，则步骤404发送的故障统计数据可以根据实际应用的需要进行确定，可以是多个故障场景对应的故障统计数据，也可以是多个故障场景和多个故障类型对应的故障统计数据，具体此处不做限定。故障统计数据的类型在图3所示实施例302中已经具体阐述，此处不再赘述。
405、跨域管理功能单元确定故障自治功能的性能指标；
跨域管理功能单元在收到域管理功能单元发送的故障统计数据之后，可以根据故障统计数据确定故障自治功能的性能指标。具体的确定方式在图3所示实施例步骤302中已经具体阐述，此处不再赘述。
406、跨域管理功能单元确定第一故障自治等级；
跨域管理功能单元在收到故障自治功能的性能指标之后，可以根据故障维度信息对应的故障自治功能的性能指标，确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。具体确定第一故障自治等级的方式在图3所示实施例步骤304中已经具体阐述，此处不再赘述。
跨域管理功能单元在确定第一故障自治等级时，还可以确定故障维度信息对应的第一故障自治功能等级、第二故障自治功能等级和故障维度信息对应的第二故障自治等级中的至少一种，具体此处不做限定。
407、跨域管理功能单元向业务运营单元发送第一故障自治等级；
需要注意的是，最终接收第一故障自治等级的电信设备有多种选择，可以是业务运营单元，可以是业务运营商单元，也可以第三方故障自治评估单元，还可以是其他的管理设备，根据实际应用的需要进行确定，具体此处不做限定，本申请实施例以业务运营单元为例。
跨域管理功能单元在确定第一故障自治等级后，可以向业务运营单元发送第一故障自治等级。
在步骤406中，跨域管理功能单元还可以确定故障维度信息对应的第一故障自治功能等级、第二故障自治功能等级和故障维度信息对应的第二故障自治等级中的至少一种，跨域管理功能单元可以向业务运营单元发送确定出的第一故障自治功能等级、第二故障自治功能等级和故障维第二故障自治等级中的至少一种。具体的确定方式在图3所示实施例步骤304中已经具体阐述，此处不再赘述。
业务运营单元在收到故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，故障维度信息对应的第二故障自治等级，和第一故障自治等级中的至少一种后，可以向将这些等级信息显示给用户或者研究人员，使得用户或者研究人员确定故障自治功能或者故障自治系统的自治能力，进而优化故障自治功能或者故障自治系统。显示的方式有多种，可以是文字形式，也可以是语音形式，具体此处不做限定。业务运营单元在收到第 一故障自治功能等级、第二故障自治功能等级或第二故障自治等级之后，还可以根据这些等级信息，进一步确定出第一故障自治等级，从而降低跨域管理功能单元的运算成本，节约内存资源。
本申请实施例中，得到的第一故障自治等级可以确定到具体的故障场景或故障类型中，并以体现为可量化的形式，提升了确定故障自治能力的精确度。
进一步的，可以由不同的网元分别确定故障统计数据和第一故障自治等级，可以适应多变的部署情景，提升方案的灵活性。
二、由业务运营单元确定第一故障自治等级。
需要注意的是，确定第一故障自治等级的电信设备有多种选择，可以是业务运营单元，可以是业务运营商单元，也可以第三方故障自治评估单元，还可以是其他的管理设备，根据实际应用的需要进行确定，具体此处不做限定。为了方便理解，图5至图9所示实施例以业务运营单元为例。
图5至图9所示实施例中，业务运营单元可以收到不同类型的数据，并根据这些数据可以直接或者间接地确定出第一故障自治等级，在实际应用中，可以根据实际需求选择不同的部署方式，提升了方案的灵活性和可实现性。
(1)业务运营单元接收故障自治功能的性能指标，根据该性能指标确定第一故障自治等级。
请参阅图5，本申请实施例故障自治能力确定方法的一个实施例示意图：
501、基站向域管理功能单元发送故障原始数据；
502、域管理功能单元确定故障统计数据；
503、域管理功能单元接收跨域管理功能单元发送的请求消息；
504、域管理功能单元向跨域管理功能单元发送故障统计数据；
505、跨域管理功能单元确定故障自治功能的性能指标；
本申请实施例中，步骤501至步骤505与图4所示实施例中步骤401至步骤405类似，此处不再赘述。
506、跨域管理功能单元向业务运营单元发送故障自治功能的性能指标；
跨域管理功能单元在根据故障统计数据确定出故障自治功能的性能指标后，可以将该性能指标发送给业务运营单元。
507、业务运营单元确定第一故障自治等级；
业务运营单元在收到故障自治功能的性能指标之后，可以根据故障维度信息对应的故障自治功能的性能指标，确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。具体确定第一故障自治等级的方式在图3所示实施例步骤304中已经具体阐述，此处不再赘述。
本申请实施例中，跨域管理功能单元在确定出故障自治功能的性能指标之后，可以直接向业务运营单元发送该性能指标，使得业务运营单元根据该性能指标确定出第一故障自治等级，从而降低了跨域管理功能单元的运算成本，节约内存资源。
业务运营单元在确定第一故障自治等级时，还可以确定故障维度信息对应的第一故障 自治功能等级、第二故障自治功能等级和故障维度信息对应的第二故障自治等级中的至少一种，具体此处不做限定。
业务运营单元在确定出故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，故障维度信息对应的第二故障自治等级，和第一故障自治等级中的至少一种后，可以向将这些等级信息显示给用户或者研究人员，使得用户或者研究人员确定自治功能或者自治系统的自治能力，进而优化自治功能或者自治系统。显示的方式有多种，可以是文字形式，也可以是语音形式，具体此处不做限定。
本申请实施例中，得到的第一故障自治等级可以确定到具体的故障场景或故障类型中，并以体现为可量化的形式，提升了确定故障自治能力的精确度。
进一步的，业务运营单元可以接收故障自治功能的性能指标，从而确定第一故障自治等级，还可以将第一故障自治等级显示给用户或者研究人员，提升了方案的灵活性和可实现性。
(2)业务运营单元接收故障统计数据，确定第一故障自治等级。
请参阅图6，本申请实施例故障自治能力确定方法的一个实施例示意图：
601、基站向域管理功能单元发送故障原始数据；
步骤601与图4所示实施例中步骤401类似，此处不再赘述。
602、域管理功能单元向跨域管理功能单元发送故障原始数据；
域管理功能单元接收到基站发送的故障原始数据后，可以将故障原始数据发送给跨域管理功能单元。
603、跨域管理功能单元确定故障统计数据；
604、跨域管理功能单元接收业务运营单元发送的请求消息；
605、跨域管理功能单元向业务运营单元发送故障统计数据；
步骤603至步骤605与前述图4所示实施例中的步骤402至步骤404类似，此处不再赘述。不同之处在于图6所示实施例中步骤603至步骤605中动作的执行主体与图4所示实施例中的步骤402至步骤404中动作的执行主体不一致。图6所示实施例中，根据故障原始数据确定故障统计数据的执行主体是跨域管理功能单元。接收请求消息，发送故障统计数据的执行主体也是跨域管理功能单元。发送请求消息，接收故障统计数据的执行主体是业务运营单元。
本申请实施例中，跨域管理功能单元在确定出故障统计数据之后，可以直接向业务运营单元发送该故障统计数据，使得业务运营单元根据该故障统计数据确定出第一故障自治等级，从而降低了跨域管理功能单元的运算成本，节约内存资源。
606、业务运营单元确定故障自治功能的性能指标；
607、业务运营单元确定第一故障自治等级；
步骤606和步骤607与前述图4所示实施例中的步骤405和步骤406类似，此处不再赘述。不同之处在于图6所示实施例中步骤606和步骤607中动作的执行主体与图4所示实施例中的步骤405和步骤406中动作的执行主体不一致。图6所示实施例中，根据故障统计数据确定故障自治功能的性能指标，根据该性能指标确定第一故障自治等级的执行主 体是业务运营单元。
业务运营单元在确定第一故障自治等级时，还可以确定故障维度信息对应的第一故障自治功能等级、第二故障自治功能等级和故障维度信息对应的第二故障自治等级中的至少一种，具体此处不做限定。具体的确定方式在图3所示实施例304中已经具体阐述，此处不再赘述。
业务运营单元在确定第一故障自治功能等级，第二故障自治功能等级，第二故障自治等级，和第一故障自治等级中的至少一种后，可以向将这些等级信息显示给用户或者研究人员，使得用户或者研究人员确定自治功能或者自治系统的自治能力，进而优化自治功能或者自治系统。显示的方式有多种，可以是文字形式，也可以是语音形式，具体此处不做限定。
图6所示实施例中，跨域管理功能单元执行的动作也可以由域管理功能单元执行，具体的操作流程请参阅图7，本申请实施例故障自治能力确定方法的一个实施例示意图：
701、基站向域管理功能单元发送故障原始数据；
702、域管理功能单元确定故障统计数据；
步骤701和步骤702与图6所示实施例中步骤601和步骤602类似，此处不再赘述。
703、域管理功能单元接收业务运营单元发送的请求消息；
704、域管理功能单元向业务运营单元发送故障统计数据；
步骤703和步骤704与图6所示实施例中步骤604和步骤605类似，此处不再赘述。不同之处在于图7所示实施例中步骤703和步骤704中动作的执行主体与图6所示实施例中的步骤604和步骤605中动作的执行主体不一致。图7所示实施例中，接收请求消息，发送故障统计数据的执行主体是域管理功能单元，而不是图6所示实施例中的跨域管理功能单元。
705、业务运营单元确定故障自治功能的性能指标；
706、业务运营单元确定第一故障自治等级；
步骤705和步骤706与前述图6所示实施例中的步骤606和步骤607类似，此处不再赘述。
本申请实施例中，得到的第一故障自治等级可以确定到具体的故障场景或故障类型中，并以体现为可量化的形式，提升了确定故障自治能力的精确度。
进一步的，本申请实施例中域管理功能单元和跨域管理功能单元可以同时出现在一种网络部署中，也可以由域管理功能单元执行跨域管理功能单元的动作，使得方案可以应用到不同的部署场景中，提升了方案的灵活性。
(3)业务运营单元接收原始数据，确定第一故障自治等级。
请参阅图8，本申请实施例故障自治能力确定方法的一个实施例示意图：
801、基站向域管理功能单元发送故障原始数据；
802、域管理功能单元向跨域管理功能单元发送故障原始数据；
步骤801和步骤802与前述图6所示实施例中步骤601和步骤602类似，此处不再赘述。
803、跨域管理功能单元向业务运营单元发送故障原始数据；
跨域管理功能单元接收到域管理功能单元发送的故障原始数据后，可以将故障原始数据发送给业务运营单元。
804、业务运营单元确定故障统计数据；
步骤804与图4所示实施例中步骤402类似，此处不再赘述。不同之处在于，图8所示实施例中步骤804的执行主体与图4所示实施例中的步骤402的执行主体不一致。图8所示实施例中，根据故障原始数据确定故障统计数据的是业务运营单元，而不是图4所示实施例中的域管理功能单元。
805、业务运营单元确定故障自治功能的性能指标；
806、业务运营单元确定第一故障自治等级；
步骤805和步骤806与前述图6所示实施例中的步骤606和步骤607类似，此处不再赘述。
本申请实施例中，得到的第一故障自治等级可以确定到具体的故障场景或故障类型中，并以体现为可量化的形式，提升了确定故障自治能力的精确度。
进一步的，本申请实施例中业务运营单元获取到故障原始数据之后，便可以对故障原始数据进行处理得到故障统计数据，从而得到故障自治功能的性能指标，最终确定第一故障自治等级，减少数据的转发步骤，减少时延，同时还可以降低数据丢失的风险。
图8所示实施例中，跨域管理功能单元执行的动作也可以由域管理功能单元执行，具体的操作流程请参阅图9，本申请实施例故障自治能力确定方法的一个实施例示意图：
901、基站向域管理功能单元发送故障原始数据；
步骤901与图8所示实施例中步骤801类型，具体此处不再赘述。
902、域管理功能单元向业务运营单元发送故障原始数据；
域管理功能单元收到基站发送的故障原始数据后，可以将故障原始数据发送个业务运营单元。
903、业务运营单元确定故障统计数据；
904、业务运营单元确定故障自治功能的性能指标；
905、业务运营单元确定第一故障自治等级；
步骤903至步骤905与图8所示实施例中步骤804至步骤806类似，此处不再赘述。
本申请实施例中，得到的第一故障自治等级可以确定到具体的故障场景或故障类型中，并以体现为可量化的形式，提升了确定故障自治能力的精确度。
进一步的，本申请实施例中，可以由域管理功能单元直接向业务运营单元发送故障原始数据，进一步减少数据的转发次数，可以降低数据丢失的风险。
下面对本申请实施例中故障自治能力的确定装置进行描述：
请参阅图10，图10为本申请实施例中故障自治能力确定装置1000的一个示意图，本申请中故障自治能力确定装置1000的一个实施例包括：
获取单元1001，用于获取故障维度信息对应的故障数据，故障维度信息包括故障场景和故障类型中的至少一种；
确定单元1002，用于根据故障数据，确定故障维度信息对应的故障自治功能的性能指标，故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种；
确定单元1002，还用于根据故障自治功能的性能指标确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
在本申请的一些可选实施例中，确定单元1002，还用于：
根据故障自治功能的性能指标，确定故障维度信息对应的第一故障自治功能等级；
根据第一故障自治功能等级，确定故障维度信息对应的第二故障自治等级；
根据第二故障自治等级，确定第一故障自治等级。
在本申请的一些可选实施例中，确定单元1002，还用于：
根据故障自治功能的性能指标，确定故障维度信息对应的第一故障自治功能等级；
根据第一故障自治功能等级，确定第二故障自治功能等级；
根据第二故障自治功能等级，确定第一故障自治等级。
在本申请的一些可选实施例中，故障自治能力确定装置1000还包括发送单元1003。
发送单元1003，用于向网络设备发送第一故障自治功能等级；
发送单元1003，还用于向网络设备发送第二故障自治等级。
在本申请的一些可选实施例中，故障自治能力确定装置1000还包括发送单元1003。
发送单元1003，还用于向网络设备发送第一故障自治功能等级；
发送单元1003，还用于向网络设备发送第二故障自治功能等级。
在本申请的一些可选实施例中，故障自治能力确定装置1000还包括发送单元1003。
发送单元1003，还用于向网络设备发送第一故障自治等级。
在本申请的一些可选实施例中，故障自治能力确定装置1000还包括发送单元1003。
发送单元1003，还用于向网络设备发送故障自治功能的性能指标。
本实施例中，故障自治能力确定装置1000可以执行前述图4所示实施例中跨域管理功能单元所执行的操作，或前述图5所示实施例中跨域管理功能单元和业务运营单元所执行的操作，或前述图6至图9所示实施例中业务运营单元所执行的操作，具体此处不再赘述。
请参阅图11，图11为本申请实施例中故障自治能力确定装置1100的一个示意图，本申请中故障自治能力确定装置1100的一个实施例包括：
获取单元1101，用于获取故障维度信息对应的故障自治功能的性能指标，故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，和故障维度信息对应的第二故障自治等级中的至少一种；
确定单元1102，用于根据故障自治功能的性能指标，第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，或第二故障自治等级，确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
本实施例中，故障自治能力确定装置1100可以执行前述图5所示实施例中业务运营单元所执行的操作，具体此处不再赘述。
请参阅图12，图12为本申请实施例中通信系统1200的一个结构示意图。通信系统1200 包括第一设备1201、第二设备1202和第三设备1203，第一设备1201、第二设备1202和第三设备1203之间建立通信连接。
第一设备1201，用于获取故障维度信息对应的故障数据，故障维度信息包括故障场景和故障类型中的至少一种；
根据故障数据，确定故障维度信息对应的故障自治功能的性能指标，故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种；
根据性能指标确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
本实施例中，第一设备1201可以执行前述图4所示实施例中跨域管理功能单元所执行的操作，或前述图5所示实施例中跨域管理功能单元和业务运营单元所执行的操作，或前述图6至图9所示实施例中业务运营单元所执行的操作，具体此处不再赘述。
第二设备1202，用于获取故障维度信息对应的故障自治功能的性能指标，故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，和故障维度信息对应的第二故障自治等级中的至少一种，其中，第一故障自治功能等级描述故障维度信息对应的故障自治功能的自治能力，第二故障自治功能等级描述故障自治功能的自治能力，第一故障自治等级描述故障自治系统的自治能力，第二故障自治等级描述故障维度信息对应的故障自治系统的自治能力；
根据性能指标，第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，或第二故障自治等级，确定第一故障自治等级，第一故障自治等级描述故障自治系统的自治能力。
本实施例中，第二设备1202可以执行前述图5所示实施例中业务运营单元所执行的操作，具体此处不再赘述。
第三设备1203，用于获取故障维度信息对应的故障数据；
向第一设备发送故障维度信息对应的故障数据。
本实施例中，第三设备1203可以执行前述图4至图9所示实施例中基站所执行的操作，具体此处不再赘述。
图13是本申请实施例提供的一种计算机设备的结构示意图，该计算机设备1300可以包括一个或一个以上中央处理器(central processing units，CPU)1301和存储器1305，该存储器1305中存储有一个或一个以上的应用程序或数据。
其中，存储器1305可以是易失性存储或持久存储。存储在存储器1305的程序可以包括一个或一个以上模块，每个模块可以包括对计算机设备中的一系列指令操作。更进一步地，中央处理器1301可以设置为与存储器1305通信，在计算机设备1300上执行存储器1305中的一系列指令操作。
计算机设备1300还可以包括一个或一个以上电源1302，一个或一个以上有线或无线网络接口1303，一个或一个以上输入输出接口1304，和/或，一个或一个以上操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等。
该计算机设备1300可以执行前述图4所示实施例中跨域管理功能单元所执行的操作， 或前述图5所示实施例中跨域管理功能单元和业务运营单元所执行的操作，或前述图6至图9所示实施例中业务运营单元所执行的操作，具体此处不再赘述。
图14是本申请实施例提供的一种计算机设备的结构示意图，该计算机设备1400可以包括一个或一个以上中央处理器(central processing units，CPU)1401和存储器1405，该存储器1405中存储有一个或一个以上的应用程序或数据。
其中，存储器1405可以是易失性存储或持久存储。存储在存储器1405的程序可以包括一个或一个以上模块，每个模块可以包括对计算机设备中的一系列指令操作。更进一步地，中央处理器1401可以设置为与存储器1405通信，在计算机设备1400上执行存储器1405中的一系列指令操作。
计算机设备1400还可以包括一个或一个以上电源1402，一个或一个以上有线或无线网络接口1403，一个或一个以上输入输出接口1404，和/或，一个或一个以上操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等。
该计算机设备1400可以执行前述图5所示实施例中业务运营单元所执行的操作，具体此处不再赘述。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上做出贡献的部分或者该技术方案的全部或部分可以体现为软件产品的形式，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，read-only memory)、随机存取存储器(RAM，random access memory)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (32)

  1. 一种故障自治能力的确定方法，其特征在于，包括：
    获取故障维度信息对应的故障数据，所述故障维度信息包括故障场景和故障类型中的至少一种；
    根据所述故障数据，确定所述故障维度信息对应的故障自治功能的性能指标，所述故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种；
    根据所述性能指标确定第一故障自治等级，所述第一故障自治等级描述故障自治系统的自治能力。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述性能指标确定第一故障自治等级，包括：
    根据所述性能指标，确定所述故障维度信息对应的第一故障自治功能等级，所述第一故障自治功能等级描述所述故障维度信息对应的故障自治功能的自治能力；
    根据所述第一故障自治功能等级，确定所述故障维度信息对应的第二故障自治等级，所述第二故障自治等级描述所述故障维度信息对应的故障自治系统的自治能力；
    根据所述第二故障自治等级，确定所述第一故障自治等级。
  3. 根据权利要求1所述的方法，其特征在于，所述根据所述性能指标确定第一故障自治等级，包括：
    根据所述性能指标，确定所述故障维度信息对应的第一故障自治功能等级；
    根据所述第一故障自治功能等级，确定第二故障自治功能等级，所述第二故障自治功能等级描述故障自治功能的自治能力；
    根据所述第二故障自治功能等级，确定所述第一故障自治等级。
  4. 根据权利要求2所述的方法，其特征在于，在所述确定所述故障维度信息对应的第一故障自治功能等级之后，所述方法还包括：
    向电信设备发送所述第一故障自治功能等级；
    在所述确定所述故障维度信息对应的第二故障自治等级之后，所述方法还包括：
    向所述电信设备发送所述第二故障自治等级。
  5. 根据权利要求3所述的方法，其特征在于，在所述确定所述故障维度信息对应的第一故障自治功能等级之后，所述方法还包括：
    向所述电信设备发送所述第一故障自治功能等级；
    在确定所述第二故障自治功能等级之后，所述方法还包括：
    向所述电信设备发送所述第二故障自治功能等级。
  6. 根据权利要求1至5中任一项所述的方法，其特征在于，在所述确定第一故障自治等级之后，所述方法还包括：
    向所述电信设备发送所述第一故障自治等级。
  7. 根据权利要求1至5中任一项所述的方法，其特征在于，在所述根据所述故障数据，确定所述故障维度信息对应的故障自治功能的性能指标之后，所述方法还包括：
    向所述电信设备发送所述性能指标。
  8. 根据权利要求1至5中任一项所述的方法，其特征在于，所述性能指标包括故障自识别率，故障自识别准确率，故障自预测率，故障自预测准确率，故障自诊断率，故障自诊断准确率，故障自愈率，和故障自愈准确率中的至少一个。
  9. 根据权利要求1至5中任一项所述的方法，其特征在于，所述故障场景包括单网元故障场景，单域故障场景，无线接入网络RAN域故障场景，核心网CN故障场景，传输网TN域故障场景，和跨域故障场景中的至少一种。
  10. 根据权利要求1至5中任一项所述的方法，其特征在于，所述故障类型包括配置类故障类型，软件类故障类型，硬件类故障类型，性能类故障类型，和业务类故障类型中的至少一种。
  11. 一种故障自治能力的确定方法，其特征在于，包括：
    获取故障维度信息对应的故障自治功能的性能指标，故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，和故障维度信息对应的第二故障自治等级中的至少一种，其中，所述第一故障自治功能等级描述所述故障维度信息对应的故障自治功能的自治能力，所述第二故障自治功能等级描述故障自治功能的自治能力，所述第一故障自治等级描述故障自治系统的自治能力，所述第二故障自治等级描述所述故障维度信息对应的故障自治系统的自治能力；
    根据所述性能指标，所述第一故障自治功能等级，所述第二故障自治功能等级，所述第一故障自治等级，或所述第二故障自治等级，确定所述第一故障自治等级，所述第一故障自治等级描述故障自治系统的自治能力。
  12. 根据权利要求11所述的方法，其特征在于，所述性能指标包括故障自识别率，故障自识别准确率，故障自预测率，故障自预测准确率，故障自诊断率，故障自诊断准确率，故障自愈率，和故障自愈准确率中的至少一个。
  13. 根据权利要求11所述的方法，其特征在于，所述故障维度信息包括故障场景和故障类型中的至少一种；
    所述故障场景包括单网元故障场景，单域故障场景，无线接入网络RAN域故障场景，核心网CN故障场景，传输网TN域故障场景，和跨域故障场景中的至少一种；
    所述故障类型包括配置类故障类型，软件类故障类型，硬件类故障类型，性能类故障类型，和业务类故障类型中的至少一种。
  14. 根据权利要求11至13中任一项所述的方法，其特征在于，所述故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种。
  15. 一种故障自治能力的确定装置，其特征在于，包括：
    获取单元，用于获取故障维度信息对应的故障数据，所述故障维度信息包括故障场景和故障类型中的至少一种；
    确定单元，用于根据所述故障数据，确定所述故障维度信息对应的故障自治功能的性能指标，所述故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种；
    所述确定单元，还用于根据所述性能指标确定第一故障自治等级，所述第一故障自治等级描述故障自治系统的自治能力。
  16. 根据权利要求15所述的装置，其特征在于，所述确定单元，具体用于：
    根据所述性能指标，确定所述故障维度信息对应的第一故障自治功能等级，所述第一故障自治功能等级描述所述故障维度信息对应的故障自治功能的自治能力；
    根据所述第一故障自治功能等级，确定所述故障维度信息对应的第二故障自治等级，所述第二故障自治等级描述所述故障维度信息对应的故障自治系统的自治能力；
    根据所述第二故障自治等级，确定所述第一故障自治等级。
  17. 根据权利要求15所述的装置，其特征在于，所述确定单元，具体用于：
    根据所述性能指标，确定所述故障维度信息对应的第一故障自治功能等级；
    根据所述第一故障自治功能等级，确定第二故障自治功能等级，所述第二故障自治功能等级描述故障自治功能的自治能力；
    根据所述第二故障自治功能等级，确定所述第一故障自治等级。
  18. 根据权利要求16所述的装置，其特征在于，所述装置还包括发送单元；
    所述发送单元，用于向电信设备发送所述第一故障自治功能等级；
    所述发送单元，还用于向所述电信设备发送所述第二故障自治等级。
  19. 根据权利要求17所述的装置，其特征在于，所述装置还包括发送单元；
    所述发送单元，用于向所述电信设备发送所述第一故障自治功能等级；
    所述发送单元，还用于向所述电信设备发送所述第二故障自治功能等级。
  20. 根据权利要求15至19中任一项所述的装置，其特征在于，所述装置还包括发送单元；
    所述发送单元，用于向所述电信设备发送所述第一故障自治等级。
  21. 根据权利要求15至19中任一项所述的装置，其特征在于，所述装置还包括发送单元；
    所述发送单元，用于向所述电信设备发送所述性能指标。
  22. 根据权利要求15至19中任一项所述的装置，其特征在于，所述性能指标包括故障自识别率，故障自识别准确率，故障自预测率，故障自预测准确率，故障自诊断率，故障自诊断准确率，故障自愈率，和故障自愈准确率中的至少一个。
  23. 根据权利要求15至19中任一项所述的装置，其特征在于，所述故障场景包括单网元故障场景，单域故障场景，无线接入网络RAN域故障场景，核心网CN故障场景，传输网TN域故障场景，和跨域故障场景中的至少一种。
  24. 根据权利要求15至19中任一项所述的装置，其特征在于，所述故障类型包括配置类故障类型，软件类故障类型，硬件类故障类型，性能类故障类型，和业务类故障类型中的至少一种。
  25. 一种故障自治能力的确定装置，其特征在于，包括：
    获取单元，用于获取故障维度信息对应的故障自治功能的性能指标，故障维度信息对应的第一故障自治功能等级，第二故障自治功能等级，第一故障自治等级，和故障维度信 息对应的第二故障自治等级中的至少一种，其中，所述第一故障自治功能等级描述所述故障维度信息对应的故障自治功能的自治能力，所述第二故障自治功能等级描述故障自治功能的自治能力，所述第一故障自治等级描述故障自治系统的自治能力，所述第二故障自治等级描述所述故障维度信息对应的故障自治系统的自治能力；
    确定单元，用于根据所述性能指标，所述第一故障自治功能等级，所述第二故障自治功能等级，所述第一故障自治等级，或所述第二故障自治等级，确定所述第一故障自治等级，所述第一故障自治等级描述故障自治系统的自治能力。
  26. 根据权利要求25所述的装置，其特征在于，所述性能指标包括故障自识别率，故障自识别准确率，故障自预测率，故障自预测准确率，故障自诊断率，故障自诊断准确率，故障自愈率，和故障自愈准确率中的至少一个。
  27. 根据权利要求25所述的装置，其特征在于，所述故障维度信息包括故障场景和故障类型中的至少一种；
    所述故障场景包括单网元故障场景，单域故障场景，无线接入网络RAN域故障场景，核心网CN故障场景，传输网TN域故障场景，和跨域故障场景中的至少一种；
    所述故障类型包括配置类故障类型，软件类故障类型，硬件类故障类型，性能类故障类型，和业务类故障类型中的至少一种。
  28. 根据权利要求25至27中任一项所述的装置，其特征在于，所述故障自治功能包括故障自识别功能，故障自预测功能，故障自诊断功能，和故障自愈功能中的至少一种。
  29. 一种计算机设备，其特征在于，包括：
    处理器、存储器、输入输出设备以及总线；
    所述处理器、存储器、输入输出设备与所述总线相连；
    所述处理器用于执行权利要求1至10中任一项所述的方法。
  30. 一种计算机设备，其特征在于，包括：
    处理器、存储器、输入输出设备以及总线；
    所述处理器、存储器、输入输出设备与所述总线相连；
    所述处理器用于执行权利要求11至14中任一项所述的方法。
  31. 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中保存有程序，当所述计算机执行所述程序时，执行如权利要求1至14中任一项所述的方法。
  32. 一种计算机程序产品，其特征在于，当所述计算机程序产品在计算机上执行时，所述计算机执行如权利要求1至14中任一项所述的方法。
PCT/CN2020/118446 2020-09-28 2020-09-28 故障自治能力的确定方法以及相关设备 WO2022061900A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/118446 WO2022061900A1 (zh) 2020-09-28 2020-09-28 故障自治能力的确定方法以及相关设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/118446 WO2022061900A1 (zh) 2020-09-28 2020-09-28 故障自治能力的确定方法以及相关设备

Publications (1)

Publication Number Publication Date
WO2022061900A1 true WO2022061900A1 (zh) 2022-03-31

Family

ID=80846100

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/118446 WO2022061900A1 (zh) 2020-09-28 2020-09-28 故障自治能力的确定方法以及相关设备

Country Status (1)

Country Link
WO (1) WO2022061900A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115206031A (zh) * 2022-07-15 2022-10-18 鹿马智能科技（上海）有限公司 酒店设备故障处理方法、电子设备及可存储介质
CN115225453A (zh) * 2022-06-09 2022-10-21 广东省智能网联汽车创新中心有限公司 一种车辆告警管理方法与系统
WO2023185467A1 (zh) * 2022-04-01 2023-10-05 华为技术有限公司 一种网络自治能力评估方法、装置及存储介质
WO2024051805A1 (zh) * 2022-09-08 2024-03-14 华为技术有限公司 一种运维网络自治等级的评估方法、装置及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070055915A1 (en) * 2005-09-07 2007-03-08 Kobylinski Krzysztof R Failure recognition, notification, and prevention for learning and self-healing capabilities in a monitored system
CN103996147A (zh) * 2014-03-20 2014-08-20 国家电网公司 配电网综合评估方法
CN104573947A (zh) * 2014-12-29 2015-04-29 国家电网公司 区域智能配电网低压台区综合评价方法
CN104701831A (zh) * 2015-03-30 2015-06-10 国家电网公司 配电网自愈控制方法
CN105303466A (zh) * 2015-11-17 2016-02-03 福州大学 一种基于ahp-gra的智能电网工程项目的综合评价方法
CN110176759A (zh) * 2019-04-02 2019-08-27 深圳供电局有限公司 一种孤网自治运行能力评估方法及装置
CN111463774A (zh) * 2020-03-11 2020-07-28 广东电网有限责任公司 一种基于ahp法的城市配电网自愈能力评估方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070055915A1 (en) * 2005-09-07 2007-03-08 Kobylinski Krzysztof R Failure recognition, notification, and prevention for learning and self-healing capabilities in a monitored system
CN103996147A (zh) * 2014-03-20 2014-08-20 国家电网公司 配电网综合评估方法
CN104573947A (zh) * 2014-12-29 2015-04-29 国家电网公司 区域智能配电网低压台区综合评价方法
CN104701831A (zh) * 2015-03-30 2015-06-10 国家电网公司 配电网自愈控制方法
CN105303466A (zh) * 2015-11-17 2016-02-03 福州大学 一种基于ahp-gra的智能电网工程项目的综合评价方法
CN110176759A (zh) * 2019-04-02 2019-08-27 深圳供电局有限公司 一种孤网自治运行能力评估方法及装置
CN111463774A (zh) * 2020-03-11 2020-07-28 广东电网有限责任公司 一种基于ahp法的城市配电网自愈能力评估方法

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023185467A1 (zh) * 2022-04-01 2023-10-05 华为技术有限公司 一种网络自治能力评估方法、装置及存储介质
CN115225453A (zh) * 2022-06-09 2022-10-21 广东省智能网联汽车创新中心有限公司 一种车辆告警管理方法与系统
CN115225453B (zh) * 2022-06-09 2024-03-01 广东省智能网联汽车创新中心有限公司 一种车辆告警管理方法与系统
CN115206031A (zh) * 2022-07-15 2022-10-18 鹿马智能科技（上海）有限公司 酒店设备故障处理方法、电子设备及可存储介质
WO2024051805A1 (zh) * 2022-09-08 2024-03-14 华为技术有限公司 一种运维网络自治等级的评估方法、装置及系统

Similar Documents

Publication Publication Date Title
WO2022061900A1 (zh) 故障自治能力的确定方法以及相关设备
WO2019184433A1 (zh) 一种网络数据的监测方法及装置
US11102219B2 (en) Systems and methods for dynamic analysis and resolution of network anomalies
CN107947968B (zh) 网络质量投诉信息的处理方法和装置
CN103795817B (zh) 为设备设置网络协议中的租约时间值的方法和系统
US8144599B2 (en) Binary class based analysis and monitoring
US11012461B2 (en) Network device vulnerability prediction
WO2017041406A1 (zh) 一种故障定位方法及装置
US10536348B2 (en) Operational micro-services design, development, deployment
US11855873B2 (en) Virtualized cellular network multi-stage test and ticketing environment
US20230281071A1 (en) Using User Equipment Data Clusters and Spatial Temporal Graphs of Abnormalities for Root Cause Analysis
WO2021233224A1 (zh) 一种故障处理方法、装置及系统
US20180367940A1 (en) Distributed testing of wireless networks
US20200236562A1 (en) Node profiling based on a key performance indicator (kpi)
CN112054917A (zh) 一种获取性能意图指标的方法、装置及系统
CN112100020A (zh) 基站的数据上报方法、装置、电子装置和存储介质
Rizwan et al. A zero-touch network service management approach using ai-enabled cdr analysis
FI20185598A1 (en) Automatic network monitoring and control
CN113760634A (zh) 一种数据处理方法和装置
WO2023045931A1 (zh) 一种网络性能异常分析方法、装置及可读存储介质
Pan et al. An intelligent customer care assistant system for large-scale cellular network diagnosis
WO2021208979A1 (zh) 一种网络故障的处理方法及装置
CN111371908B (zh) 发送信息的方法、装置、存储介质及电子装置
US10296365B1 (en) Dynamically configurable operation information collection
US10841821B2 (en) Node profiling based on combination of performance management (PM) counters using machine learning techniques

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: 20954750

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20954750

Country of ref document: EP

Kind code of ref document: A1