Service assurance method and electronic device

Abstract

The present application relates to the field of network operation and maintenance management, and discloses a service assurance method and an electronic device. The service assurance method is applied to an operation and maintenance management system. The method comprises: setting a service level objective (SLO) on the basis of a service objective in a service connection request, and sending the SLO to a network device, the service connection request being used for creating a connection service; on the basis of received service data sent by the network device, determining a network anomaly point in the connection service; and, on the basis of the network anomaly point, sending an assurance instruction to the network device, the assurance instruction being used for instructing the network device to perform service assurance.

Description

Service guarantee method and electronic equipment

[0001] Cross-references

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on December 8, 2023, with application number 202311691816.9 and application name “Service Assurance Method and Electronic Device”. The entire contents of the application are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of network operation and maintenance management, and specifically to a service assurance method and electronic equipment. Background Art

[0004] In related technologies, the Service Level Objectives (SLOs) of 5G private networks are primarily based on the O&M capabilities of the operator's Element Management System (EMS) in large-scale network scenarios. When SLO anomalies occur, a passive demarcation and positioning process is generally adopted, whereby O&M personnel analyze and handle the problem after it occurs, resulting in a time-consuming problem resolution. When 5G private networks are used in vertical industries, low latency and high reliability requirements are placed on 5G industry private networks. At this point, if the EMS O&M capabilities of large-scale network scenarios are continued to be used, the low latency and high reliability demands of vertical industries cannot be guaranteed.

[0005] Summary of the Invention

[0006] This application aims to provide a service assurance method and electronic equipment, at least to solve the problem that the EMS operation and maintenance capabilities used in large-scale network scenarios in related technologies cannot guarantee the low latency and high reliability demands of vertical industries.

[0007] In the first aspect, an embodiment of the present application proposes a business assurance method, which is applied to an operation and maintenance management system. The method includes: setting a service level objective SLO based on the business goal in the business connection request, and sending the SLO to the network device, wherein the business connection request is used to create a connection business; determining the network anomaly point in the connection business based on the business data received from the network device; and sending an assurance instruction to the network device based on the network anomaly point, wherein the assurance instruction is used to instruct the network device to perform business assurance.

[0008] In the second aspect, an embodiment of the present application proposes a service assurance method, which is applied to a first network device, and the method includes: receiving an SLO sent by an operation and maintenance management system or a sub-SLO and a service message feature model sent by a second network device, wherein the SLO is the target corresponding to the connection service, and the service message feature model is a model determined by the second network device based on the service message characteristics corresponding to the type of the connection service; based on the SLO or the sub-SLO, service data is collected; according to the SLO, the sub-SLO, the service message feature model and the service data, service self-assurance is performed; in the event that the service self-assurance fails, the service data is sent to the operation and maintenance management system, or the service data and assurance failure information are sent to the operation and maintenance management system and the second network device; based on the service data, an assurance instruction is received from the operation and maintenance management system; and service assurance is performed according to the assurance instruction.

[0009] On the third aspect, an embodiment of the present application proposes a service assurance method, which is applied to a second network device, and the method includes: receiving an SLO sent by an operation and maintenance management system, and determining multiple sub-SLOs based on the SLO, where the SLO is the target corresponding to the connection service; based on the type of the connection service, obtaining preset service message characteristics; based on the service message characteristics, determining a service message characteristic model; sending the multiple sub-SLOs and the service message characteristic model to the first network device, so that the first network device performs service self-assurance based on the sub-SLO and the service message characteristic model.

[0010] In a fourth aspect, an embodiment of the present application proposes an electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect, or implements the steps of the method described in the second aspect, or implements the steps of the method described in the third aspect.

[0011] In a fifth aspect, an embodiment of the present application proposes a storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented, or the steps of the method described in the third aspect are implemented.

[0012] In the sixth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect, or to implement the steps of the method described in the third aspect.

[0013] In the seventh aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect, or the steps of the method described in the second aspect, or the steps of the method described in the third aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] FIG1 is a flow chart of a service assurance method provided by an embodiment of the present application;

[0015] FIG2 is a flow chart of another service assurance method provided by an embodiment of the present application;

[0016] FIG3 is a flow chart of another service assurance method provided by an embodiment of the present application;

[0017] FIG4 is a schematic diagram of a detailed flow chart of a service assurance method provided by an embodiment of the present application;

[0018] FIG5 is a structural block diagram of a service assurance system provided by an embodiment of the present application;

[0019] FIG6 is a schematic diagram of a service assurance process provided by an embodiment of the present application;

[0020] FIG7 is a schematic structural diagram of a service assurance device provided by an embodiment of the present application;

[0021] FIG8 is a schematic structural diagram of another service assurance device provided by an embodiment of the present application;

[0022] FIG9 is a schematic structural diagram of another service assurance device provided by an embodiment of the present application;

[0023] FIG10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0025] The terms "first" and "second" in the specification and claims of this application may explicitly or implicitly refer to one or more of the features. Throughout the description of this application, unless otherwise specified, "plurality" means two or more. Furthermore, "and / or" in the specification and claims refers to at least one of the connected entities, and the character " / " generally indicates an "or" relationship between the connected entities.

[0026] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0027] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0028] The service assurance method and electronic device provided in the embodiments of the present application are described in detail below with reference to Figures 1 to 10 through specific embodiments and their application scenarios.

[0029] Figure 1 is a flow chart of a service assurance method provided by an embodiment of the present application. As shown in Figure 1 , the service assurance method is applied to an operation and maintenance management system, and the service assurance method may include the contents shown in S101 to S103.

[0030] In S101 , a service level objective (SLO) is set based on a business objective in a business connection request, and the SLO is sent to a network device. The business connection request is used to create a connection service.

[0031] Among them, the connection service refers to the end-to-end connection relationship. The service connection request carries the terminal address and / or application address. The end-to-end connection relationship can refer to the connection relationship between a single 5G module terminal customer premises equipment (CPE) and an industry application, or it can refer to the connection relationship between a dual 5G module terminal CPE dual transmission and selective reception redundancy mechanism (frame replication and elimination for reliability, FRER) and an industry application, or it can refer to the connection relationship between 5G terminals and 5G terminals. The SLO is determined according to the type of connection service. Different connection services correspond to different SLOs. The SLO may include latency, reliability, delay jitter, etc., and can be specifically determined according to actual applications. This embodiment does not limit it.

[0032] In S102 , a network abnormality point in the connection service is determined based on the received service data sent by the network device.

[0033] A network anomaly refers to a situation where the actual reliability of an industry service is lower than the SLO, or the latency is greater than the SLO. For example, if the SLO is set at 99.999% reliability and 20ms latency, but the actual reliability is lower than 99.99% and the latency is 30ms, this indicates a network anomaly and requires identification of the anomaly point.

[0034] In S103, a protection instruction is sent to the network device based on the network abnormality point, where the protection instruction is used to instruct the network device to perform service protection.

[0035] It is worth noting that assurance instructions can be divided into two categories. One is network optimization or expansion, reducing anomalies at the network level, involving network expansion, neighboring cell adjustment, and wireless parameter adjustment; the other is service assurance target adjustment related to service connection, optimizing wireless air interface scheduling, involving 5G service quality identification (5QI) adjustment, service indicator adjustment (such as segment delay), which will be described in detail in subsequent embodiments.

[0036] In an embodiment of the present application, a service level objective SLO is first set based on the business goal in the business connection request, and the SLO is sent to the network device. The business connection request is used to create a connection business. Then, based on the business data received from the network device, a network anomaly point in the connection business is determined. Finally, based on the network anomaly point, a guarantee instruction is sent to the network device. The guarantee instruction is used to instruct the network device to perform business guarantee. In an embodiment of the present application, an SLO is set when establishing a connection business, so that the network device is instructed to perform self-guarantee based on the SLO. When a network anomaly occurs in the connection business, the network anomaly point is determined, and a guarantee instruction is sent to the network device based on the anomaly point, so that the network device can perform business guarantee based on the guarantee instruction. The business guarantee of the network device improves the guarantee efficiency and enhances the reliability of the business.

[0037] In one possible implementation of the present application, before setting a service level objective SLO based on the business objective in the business connection request, the method may also include: upon receiving a business connection request, creating a terminal-to-terminal or terminal-to-application connection service based on the terminal address and / or application address, and the business connection request carries the terminal address and / or application address.

[0038] In other words, a connection service can be either end-to-end or end-to-application, determined based on the address information carried in the service connection request. Accordingly, the SLO can be either end-level or application-level. Based on the SLO corresponding to the connection service type, network devices can determine how to decompose the SLO into multiple sub-SLOs to better ensure service assurance.

[0039] The network device can be a single network device (i.e., the main network device). The main network device can provide service assurance based on the SLO sent by the operation and maintenance management system. In the event that the main network device is unable to provide service assurance, service assurance can be jointly provided by the collaborative network device. Specifically, in one possible implementation of the present application, the network device includes a first network device and a second network device; sending the SLO to the network device can include: sending the SLO to the second network device so that the second network device determines multiple sub-SLOs based on the SLO and sends them to the first network device, where the sub-SLOs are segmented assurance targets of the SLO.

[0040] That is to say, if the network equipment is divided into a main network equipment (first network equipment) and a collaborative network equipment (second network equipment), the operation and maintenance management system sends the SLO to the collaborative network equipment, and the collaborative network equipment decomposes the SLO into multiple sub-SLOs according to the type of SLO, wherein the multiple sub-SLOs correspond to multiple segments between the end-to-end connection services, that is, the collaborative network equipment can be divided into multiple segments according to the network elements involved between the end-to-end connection services, or it can be decomposed into multiple segments according to different networking. The specific details can be determined according to actual applications, and this embodiment does not limit it. The collaborative network equipment sends multiple sub-SLOs to the main network equipment so that the main network equipment performs segmented service assurance according to the multiple sub-SLOs. The segmented service assurance can more quickly determine the network anomaly points, and then more quickly provide service assurance for the network anomaly points, so that they can resume normal operation and make the connection service more stable.

[0041] For example, a connection service is a terminal-to-application connection, which is divided into terminal-to-air interface, base station internal, base station-to-cooperative network device, cooperative network device internal, and cooperative network device-to-application. Accordingly, the SLO can be divided into five sub-SLOs.

[0042] In one possible implementation of the present application, after sending the SLO to the network device, the service assurance method may further include: receiving service data sent by the first network device, the service data including service level measurement indicators (Service Level Identifier, SLI), statistics, alarms, status, signaling messages and black box information.

[0043] Among them, black box information refers to the information such as abnormal point location conclusion generated by network equipment when it performs business self-protection based on the analysis products obtained during the self-protection process (such as abnormal association rules, corresponding 5QI strategies, fault points, etc.).

[0044] In this embodiment, the operation and maintenance management system sends the SLO to the second network device, the second network device decomposes the SLO into multiple sub-SLOs, and the second network device sends the multiple sub-SLOs to the first network device. The first network device can provide service assurance for the corresponding segments based on the multiple sub-SLOs. The first network device can send the collected service data to the operation and maintenance management system, so that the operation and maintenance management system can determine the network anomalies in the connection service based on the service data, and then send a guarantee instruction to instruct the first network device to perform service assurance to ensure the stability and reliability of the connection service.

[0045] In a possible implementation of the present application, determining a network anomaly point in a connection service based on service data received and sent by a network device may include: determining whether the reception and / or transmission of a terminal device in the connection service is abnormal; if the reception and / or transmission of the terminal device is abnormal, extracting statistical data associated with the terminal device in the service data, as well as alarms, status, signaling messages, and black box information sent by the terminal device; in the case where the statistical data, alarms, status, signaling messages, and / or black box information are abnormal, determining that the network anomaly point in the connection service is a terminal device; in the case where the network anomaly point is a non-terminal device, analyzing the network anomaly point and tracing the root cause of the anomaly point based on the service level measurement indicators SLI, SLO, preset guarantee thresholds, and network device status in the service data to determine the network anomaly point in the connection service.

[0046] It is worth noting that according to historical data, most of the anomalies (80% to 90%) occur in the terminal equipment (CPE). Therefore, priority is given to analyzing the group or individual failure of the CPE. This can be determined by whether the reception and / or transmission of the terminal equipment in the connected service is abnormal. If the reception and / or transmission of the terminal equipment is abnormal, the statistical data associated with the terminal equipment in the service data, as well as the alarms, status, signaling messages, black box information and other data sent by the terminal equipment are extracted. In other words, the information of the terminal equipment obtained by the network equipment and the information of the terminal equipment itself sent to the network equipment are judged, and then it is determined whether the anomaly point is in the terminal equipment. If the above judgment shows that the anomaly point is not in the terminal equipment, that is, the anomaly point is not in the terminal equipment, then based on the SLI, SLO, preset protection threshold and network equipment status in the service data, the network anomaly point can be analyzed and the root cause of the anomaly point can be traced through preset or dynamically learned association rules, AI algorithms, etc. to determine the network anomaly point in the connected service.

[0047] If it is detected that the SLI of the connection service does not meet the SLO, or the downward trend of the SLI exceeds the guarantee threshold, it is determined that a network anomaly has occurred in the connection service. The network anomaly point is then analyzed and the root cause of the anomaly point is traced to determine the network anomaly point in the connection service.

[0048] In one possible implementation of the present application, sending a protection instruction to a network device based on a network anomaly point may include: generating a service anomaly feature based on the network anomaly point and the network anomaly phenomenon when the network anomaly point is a non-terminal device; generating a network optimization or expansion instruction, or generating a service protection target adjustment instruction for a service connection based on the service anomaly feature; sending a network optimization or expansion instruction, or a service protection target adjustment instruction for a service connection to the network device; and receiving an analysis conclusion and protection result returned by the network device.

[0049] In this embodiment, when it is determined that a network anomaly point is a non-terminal device, service anomaly features can be generated based on the network anomaly point and network anomaly phenomena. Service anomaly features can include network anomalies such as interference, coverage, and capacity. Service anomaly features can also include air interface anomalies such as latency anomalies, message retransmissions, and block error rate (BLER) anomalies. Based on the above different service anomaly features, corresponding assurance instructions are generated, such as network optimization or expansion instructions, or service assurance target adjustment instructions for service connections, and sent to the network device to instruct the network device to perform service assurance. The analysis conclusion and assurance results returned by the network device are then received.

[0050] In other words, network devices can self-assure services based on the SLOs (Service Level Optimization) (SLOs) sent by the operation and maintenance management system. This means that when an anomaly is detected, the device can dynamically adjust the Quality of Service (QoS) control policy, adjust the network element air interface scheduling policy, and adjust resource allocation to achieve the SLO. If network device assurance fails, the failure can be reported to the operation and maintenance management system. The operation and maintenance management system identifies the network anomaly points and generates service anomaly signatures based on the anomaly points and the anomaly phenomena. Based on the anomaly signatures, the system generates a set of location / self-healing execution instructions, known as assurance instructions, to perform diagnostic analysis, policy adjustments, parameter modifications, and actions on the network element devices. Assurance instructions can be divided into two categories: one is network optimization or capacity expansion, which reduces network-level anomalies and involves network expansion, neighboring cell adjustments, and wireless parameter adjustments. The other is service assurance target adjustments related to service connections, optimizing wireless air interface scheduling and involving 5QI adjustments and service indicator adjustments (such as segment latency).

[0051] In a possible implementation of the present application, the service assurance method may further include: when the assurance result returned by the network device is an assurance failure, generating a manual intervention processing suggestion based on the network anomaly points, network anomaly phenomena, service anomaly characteristics, service assurance process, and service data after service assurance in the analysis conclusion; updating the network anomaly points, network anomaly phenomena, service anomaly characteristics, service assurance process, service data after service assurance, manual intervention processing suggestions, and execution results in the analysis conclusion to a preset fault tree knowledge base.

[0052] In other words, if the O&M management system sends a security instruction to a network device, and the network device fails to provide service security according to the instruction, the system will analyze the network anomaly points, anomaly phenomena, service anomaly characteristics, service security process, and service data after service security returned from the network device. This system will then generate manual intervention recommendations for O&M personnel to address and restore normal service. This information, including the anomaly points, anomaly phenomena, service anomaly characteristics, service security process, service data after service security, manual intervention recommendations, and execution results, will be updated to a pre-set fault tree knowledge base. This allows for subsequent handling of the same or similar network anomalies, thereby improving service security efficiency.

[0053] Figure 2 is a flow chart of a service assurance method provided by an embodiment of the present application. As shown in Figure 2, the service assurance method is applied to a first network device, ie, a main network device, and the service assurance method may include the contents shown in S201 to S206.

[0054] In S201, an SLO sent by an operation and maintenance management system or a sub-SLO and a service message feature model sent by a second network device is received.

[0055] The SLO is the target corresponding to the connected service, and the service message feature model is a model determined by the second network device based on the service message features corresponding to the type of connected service. Sub-SLOs are decomposed by the second network device (i.e., the collaborative network device) based on the SLO type. These sub-SLOs are described in detail in the above embodiments and will not be repeated in this embodiment. For details, see above.

[0056] In S202 , business data is collected based on the SLO or sub-SLO.

[0057] In S203 , service self-assurance is performed based on the SLO, sub-SLO, service message feature model, and service data.

[0058] Among them, service self-assurance refers to the closed-loop assurance performed by the first network device based on the acquired data, which can ensure the reliable operation of the connected service without the assistance of external equipment, making the SLO or sub-SLO achievable.

[0059] In S204, when the service self-assurance fails, the service data is sent to the operation and maintenance management system, or the service data and the assurance failure information are sent to the operation and maintenance management system and the second network device.

[0060] That is to say, if the first network device fails to ensure its own services, the operation and maintenance management system, or the operation and maintenance management system and the second network device need to intervene to jointly provide service assurance to ensure the reliability of the connection service, that is, to ensure that the SLO or sub-SLO is achievable.

[0061] In S205 , a guarantee instruction sent by the operation and maintenance management system is received based on the business data.

[0062] In S206, service assurance is performed according to the assurance instruction.

[0063] In an embodiment of the present application, the SLO sent by the operation and maintenance management system or the sub-SLO and the business message feature model sent by the second network device are first received, and then based on the SLO or sub-SLO, business data is collected, and business self-assurance is performed according to the SLO, sub-SLO, business message feature model and business data. In the event of failure of business self-assurance, the business data is sent to the operation and maintenance management system, or the business data and the assurance failure information are sent to the operation and maintenance management system and the second network device. Finally, based on the business data, the assurance instruction sent by the operation and maintenance management system is received, and business assurance is performed according to the assurance instruction. In an embodiment of the present application, the first network device can perform business self-assurance based on the SLO sent by the operation and maintenance management system or the sub-SLO and the business message feature model sent by the second network device, to ensure the reliable operation of the connected business, so that the SLO or sub-SLO is reachable. In the event of failure of self-assurance, business assurance can be performed based on the assurance instruction sent by the operation and maintenance management system. Multiple assurance methods can improve assurance efficiency and enhance business reliability.

[0064] In a possible implementation of the present application, service self-assurance is performed based on SLO, sub-SLO, service message feature model and service data, which may include: performing data correlation analysis on signaling messages and statistical data in the service data corresponding to the SLO, analyzing network anomaly points and tracing the root causes of the anomaly points to determine the network anomaly points in the connection service; adjusting the priority of the quality of service QoS, wireless air interface and resource scheduling strategy corresponding to the network anomaly points based on the SLO, network anomaly points, service anomaly features, and the correspondence between the service anomaly features and the trained adjustment strategies.

[0065] That is, the first network device can perform self-protection based on the SLO sent by the operation and maintenance management system, and adjust the priority of the quality of service QoS, wireless air interface and resource scheduling strategy corresponding to the network anomaly point to ensure that the SLO is reachable.

[0066] In a possible implementation of the present application, service self-assurance is performed based on SLO, sub-SLO, service message feature model and service data, which may include: performing data correlation analysis on signaling messages and statistical data in the service data corresponding to the sub-SLO, analyzing network anomaly points and tracing the root causes of the anomaly points to determine the network anomaly points in the connection service; adjusting the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly points based on the sub-SLO, service message feature model, network anomaly points, service anomaly characteristics, and the correspondence between the service anomaly characteristics and the trained adjustment strategy.

[0067] In this embodiment, when the first network device fails to ensure itself, it can work with the second network device to jointly provide service assurance, that is, the second network device sends an SLO based on the operation and maintenance management system and decomposes it into multiple sub-SLOs. The first network device obtains the corresponding service data based on the sub-SLO sent by the second network device, and then performs data correlation analysis based on the signaling messages and statistical data in the service data corresponding to the sub-SLO, analyzes the network anomaly points and traces the root causes of the anomaly points, determines the network anomaly points in the connection service, and then adjusts the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly points to ensure that each sub-SLO can be reached, thereby improving the reliability of the connection service.

[0068] In one possible implementation of the present application, providing service assurance based on assurance instructions may include: receiving network optimization or expansion instructions sent by the operation and maintenance management system; based on the network optimization or expansion instructions, adjusting network coverage, cell neighborhood, and network service strategies to reduce network interference and switching frequency and increase network capacity.

[0069] In other words, in response to the two types of security instructions from the operation and maintenance management system, the first network device adopts different adjustment strategies. Specifically, for network optimization or expansion instructions, it adjusts network coverage, cell neighborhoods, and network service strategies to reduce network interference and handoff frequency and increase network capacity. The second type of instructions from the operation and maintenance management system are shown below.

[0070] In a possible implementation of the present application, performing service assurance according to the assurance instruction may include: receiving a service assurance target adjustment instruction for a service connection sent by the operation and maintenance management system; determining multiple sub-SLOs based on the terminal-level SLO and application-level SLO sent by the operation and maintenance management system; adjusting the sub-SLO based on the service assurance target adjustment instruction for the service connection; determining a message feature model based on the service message features in the service data; performing data correlation analysis on the signaling messages and statistical data in the service data, analyzing the network anomaly points and tracing the root causes of the anomaly points to determine the network anomaly points in the connection service; adjusting the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly points based on the service message feature model, the adjusted sub-SLO, the network anomaly points, the service anomaly features, and the correspondence between the service anomaly features and the trained adjustment strategies.

[0071] In this embodiment, for the second type of assurance instructions of the operation and maintenance management system, namely, the business assurance target adjustment instructions for business connections, the business assurance target, namely, SLO or sub-SLO, is adjusted based on the business assurance target adjustment instructions for business connections, self-assurance is re-performed, business data is collected, and anomalies are determined. Based on the business message feature model, the adjusted sub-SLO, the network anomaly point, the business anomaly characteristics, and the correspondence between the business anomaly characteristics and the trained adjustment strategy, the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly point are adjusted to ensure that the SLO or sub-SLO is reachable.

[0072] Furthermore, the business assurance results can be fed back to the operation and maintenance management system, or the operation and maintenance management system and the second network device. In the event of business assurance failure, that is, the predetermined goal cannot be achieved, the abnormal root cause location conclusion is output based on the analysis products of the assurance process (such as abnormal association rules, corresponding to 5QI strategies, fault points), forming black box information and reporting to the operation and maintenance management system.

[0073] Figure 3 is a flow chart of a service assurance method provided by an embodiment of the present application. As shown in Figure 3, the service assurance method is applied to the second network device, ie, the collaborative network device, and the service assurance method may include the contents shown in S301 to S304.

[0074] In S301 , an SLO sent by an operation and maintenance management system is received, and multiple sub-SLOs are determined based on the SLO, where the SLO is a target corresponding to the connection business.

[0075] Among them, the sub-SLO is what the second network device decomposes the SLO into according to the type of SLO. It has been described in detail in the above embodiment and will not be repeated in this embodiment. Please see above for details.

[0076] In S302, based on the type of the connection service, a preset service message feature is obtained.

[0077] Among them, the preset business message features correspond to the connection services, and the corresponding business message features can be obtained according to the type of connection services. If the subsequent business message features are updated, the updated business message features can be updated to the preset position for subsequent acquisition and use.

[0078] In S303, a service message feature model is determined based on the service message feature.

[0079] In S304 , the plurality of sub-SLOs and the service message feature model are sent to the first network device, so that the first network device performs service self-assurance based on the sub-SLOs and the service message feature model.

[0080] In an embodiment of the present application, an SLO sent by an operation and maintenance management system is first received, and multiple sub-SLOs are determined based on the SLO, where the SLO is the target corresponding to the connection service. Then, based on the type of the connection service, preset service message features are obtained, and based on the service message features, a service message feature model is determined. Finally, the multiple sub-SLOs and the service message feature model are sent to the first network device, so that the first network device performs service self-assurance based on the sub-SLOs and the service message feature model. In this embodiment, the second network device can decompose the SLO sent by the operation and maintenance management system into multiple sub-SLOs, so that the first network device can perform service self-assurance based on the multiple sub-SLO segments, thereby improving the reliability of the connection service.

[0081] In a possible implementation of the present application, the service assurance method may further include: based on the connection service, statistically analyzing the service messages of the connection service to obtain the corresponding service message characteristics and service message characteristic model; updating the service message characteristics to the preset service message characteristics; based on the service message characteristics and the preset period, obtaining the SLI corresponding to the SLO or sub-SLO, and reporting the SLI to the operation and maintenance management system.

[0082] That is, the second network device can obtain corresponding service message characteristics and service message characteristic models based on statistical analysis of the service packets of the connected service, and update them into the pre-set service message characteristics for subsequent use. The second network device can also periodically obtain the SLI corresponding to the SLO or sub-SLO based on the service message characteristics and a preset period (e.g., 5 seconds), and report the SLI to the operation and maintenance management system so that the operation and maintenance management system can identify network anomalies.

[0083] In a possible implementation of the present application, the service assurance method may further include: adjusting the sub-SLO and the service message feature model when it is detected that the SLI of the connection service does not meet the SLO, or the downward trend of the SLI exceeds the assurance threshold, or when assurance failure information sent by the first network device is received.

[0084] That is to say, when a network anomaly occurs or the first network device fails to ensure security, it is necessary to adjust the sub-SLO and service message feature model so that the first network device can ensure the normal operation of the connection service based on the adjusted sub-SLO and ensure that the SLO is reachable.

[0085] Figure 4 is a detailed flow chart of a service assurance method. As shown in Figure 4, the operation and maintenance management system is used to connect the service management, which can issue the wireless network element SLO assurance requirement to the first network device (i.e., the wireless network element A in Figure 4), so that the first network device can perform self-assurance of the small closed-loop service based on the SLO, and issue the cross-network element SLO assurance requirement to the second network device (i.e., the collaborative network element B in Figure 4), so that the first network device and the second network device can jointly perform large closed-loop service assurance. It should be noted that the first network device can first perform a small closed-loop, and in the event that the small closed-loop fails, it can work with the second network device to perform large closed-loop service assurance.

[0086] Among them, wireless network element A includes modules such as wireless intelligent body, data statistical analysis, signaling plane functional body, and user plane functional body. Among them, the wireless intelligent body is used to realize active service assurance and diagnostic self-healing disposal on the network side, and report network element abnormal events, abnormal indicators, black box and other information to the operation and maintenance management system; the data statistical analysis module is used to report service statistical data and signaling statistical data, that is, to associate the data obtained by the signaling plane functional body and the user plane functional body and report the statistical data to the wireless intelligent body; the signaling plane functional body and the user plane functional body are used to communicate with terminal equipment (such as CPE terminals) to obtain signaling messages and data messages.

[0087] Wireless network element B includes modules such as QoS assurance coordination body, intelligent packet insight, service traffic statistics and service flow export. Among them, the QoS assurance coordination body provides the ability to decompose collaborative assurance targets and dynamically adjust assurance parameters across network elements, and sends information such as segmented assurance targets, service packet characteristics of predefined service characteristics, and 5QI policy parameters to wireless network element A; intelligent packet insight and service traffic statistics periodically count new service packet characteristics and report observed SLI service indicators to the QoS assurance coordination body; the service flow export is used to connect with applications.

[0088] It's worth noting that wireless network element A's wireless intelligence and data statistics analysis can be collectively referred to as the AI ​​intelligent assurance module (i.e., the AI ​​intelligent assurance module in the first network device in Figure 5 ); wireless network element B's QoS assurance collaboration, intelligent message insights, and service traffic statistics can be collectively referred to as the AI ​​intelligent assurance module (i.e., the AI ​​intelligent assurance module in the second network device in Figure 5 ). The AI ​​intelligent assurance modules of wireless network elements A and B can be co-located, integrating their capabilities for better service assurance.

[0089] The embodiment of the present application provides a service assurance system, including an operation and maintenance management system, a first network device, and a second network device. The structure of the first network device is the structure of the wireless network element A shown in FIG4 , and the structure of the second network device is the structure of the wireless network device B shown in FIG4 .

[0090] Figure 5 shows the specific structure of the operation and maintenance management system. As shown in Figure 5, the operation and maintenance management system can include modules such as connection service management, service SLO monitoring, service anomaly tracing, service AI intelligent assurance, performance evaluation, and guided fault handling. This enables automated closed-loop processing based on service assurance objectives, collaborates with network devices, and completes service assurance in scenarios where network devices or services are abnormal.

[0091] Among them, the connection service management module: provides the creation of end-to-end connections for various network services, such as the connection relationship between a single 5G module terminal CPE and an industry application, the connection relationship between a dual 5G module terminal CPE FRER mode and an industry application, and the connection relationship between 5G terminals and 5G terminals; when creating an end-to-end network service connection, you can set the UE-level or APP-level service SLO guarantee target under the connection service.

[0092] Service SLO monitoring module: This module presents network service SLI indicators based on end-to-end network service connections, including end-to-end indicators and segmented or upstream and downstream indicators. The data source can be directly from network devices or indicator information obtained through DPI probe technology. Based on the operation and maintenance theory of network reliability engineering (SRE), when the service SLO target or the downward trend of the service SLO target exceeds the set assurance threshold, a network service anomaly alarm is generated and a closed-loop processing process is automatically initiated.

[0093] Service anomaly tracing module: Provides service anomaly tracing analysis. Based on equipment fault alarms or network service anomaly alarms, KPI indicators, service observation SLI indicators, expert rule knowledge base / maps, AI correlation analysis, group / individual fault analysis methods, etc., it analyzes anomalies in devices associated with end-to-end connections of network services to locate the location of the anomaly.

[0094] Service AI Intelligent Assurance Module: Provides system-level service AI intelligent assurance. Based on the results of service anomaly tracing, it implements system-level fault location processing. Also based on AI algorithms or expert knowledge base information, the AI ​​engine outputs fault location information and performs secondary confirmation of service dialing, service self-healing (such as dynamic adjustment of network resources), and diagnostic analysis of network equipment (including CPE terminals).

[0095] Effect Evaluation: This system provides AI-powered intelligent assurance performance evaluation and knowledge recovery capabilities, dynamically generating troubleshooting recommendations requiring human intervention. Based on the self-healing results, it outputs effect evaluation and analysis conclusions, and uses the automated exception handling results as knowledge for knowledge recovery. If the self-healing result fails, it dynamically generates troubleshooting recommendations requiring human intervention based on the latest self-healing diagnostic information and the fault tree knowledge base.

[0096] Wizard-style troubleshooting: This system provides a wizard-style process for manual troubleshooting, allowing users to quickly resolve faults. Online feedback on the status of the completed form guides users through the troubleshooting process. The final results of the process are also sent to the effectiveness evaluation module.

[0097] FIG6 is a schematic diagram of the service assurance process. As shown in FIG6 , the service assurance process is as follows:

[0098] Business self-assurance: For established business connections and SLOs, the O&M management system defines and dynamically loads SLO assurance templates, issuing assurance settings (slice + 5QI + UE or app level) based on business connections. Anomaly events are generated based on abnormal trend analysis using the SRE error budget.

[0099] Network element equipment: It is divided into a single-site small closed loop (that is, the first network device alone provides service assurance) and a cross-site large closed loop (the first network device and the second network device jointly provide service assurance). Among them, the single-site small closed loop specifically periodically collects signaling and data message information, collects statistics on service indicators and service reliability indicators, performs data correlation analysis, and discovers anomalies; based on the issued SLO assurance targets (such as latency, reliability, and 5QI), the QoS control policy is dynamically adjusted and takes effect dynamically.

[0100] The cross-site large closed loop specifically involves the second network device intelligently detecting and analyzing data plane messages, and obtaining service message characteristics (such as packet size, periodicity, arrival time, flow direction, etc.) through AI technology; the second network device decomposes segmented service objectives (such as segment latency) based on the UE-level and APP-level SLO assurance targets of the service connection; the second network device sends the message feature model, segmented service assurance targets, and 5QI (custom or predefined) to the first network device; the first network device performs service SLO assurance control in a single-site closed-loop manner.

[0101] Self-healing process: When a business anomaly occurs in the system, relevant anomaly information is collected.

[0102] Operation and maintenance management system: Based on service observation indicators (SLIs), alarms, performance KPIs, MRs, probe messages, and other data reported by network elements, AI algorithms are used to analyze anomalies, trace their locations, and complete demarcation analysis. Based on the anomaly locations and abnormal phenomena, the system generates service anomaly characteristics (such as network anomalies: interference, coverage, and capacity; air interface anomalies: latency anomalies, message retransmissions, and BLER anomalies) through a fault handling tree knowledge library. Based on different service anomaly characteristics, it generates assurance instructions to perform diagnostic analysis, policy adjustments, parameter modifications, and actions on network element devices. Assurance instructions fall into two categories: one is network optimization or expansion to reduce network-level anomalies, involving network expansion, neighboring cell adjustments, and wireless parameter adjustments; the other is service assurance target adjustments related to service connections, optimizing wireless air interface scheduling, and involving 5QI adjustments and service indicator adjustments (such as segment latency).

[0103] Network element equipment: For the first type of instructions, which are used to take effect based on the current capabilities of the network element equipment, the AI ​​intelligent assurance module needs to pay attention to changes in sensitive parameters to update the QoS assurance policy. For the second type of instructions, which are used to adjust the service assurance goals based on the new dynamic policies or segmented indicators issued by the operation and maintenance management system, the self-closed loop (including large closed loops) is retried, two statistical cycles are collected, and the self-closed loop effect is fed back. If the self-closed loop result cannot achieve the predetermined goal, the process analysis product of the self-closed loop process (such as abnormal association rules corresponding to 5QI policies and fault points) is used to output the abnormal root cause location conclusion, form black box information, and report it to the operation and maintenance management system.

[0104] The above processing process has been described in detail in the above embodiments and will not be repeated in this embodiment. Please refer to the above embodiments for details.

[0105] After performing business self-protection and self-healing, the operation and maintenance management system also includes processes such as effect evaluation and guided fault handling.

[0106] Among them, effect evaluation: used for completed system self-healing processing, which requires effect evaluation and knowledge recovery based on the self-healing process and results for reuse; the operation and maintenance management system establishes a network fault and anomaly processing knowledge base based on knowledge graph technology; updates the node or relationship information in the knowledge base based on each abnormal phenomenon, abnormal characteristics, self-closed loop processing process and results; based on the generated dynamic processing suggestion tree, the processing results obtained by the manual guided fault processing process are updated to the knowledge base; based on the knowledge information in the knowledge base, provides a set of processing suggestion actions (and processes) corresponding to the abnormal phenomena and characteristics.

[0107] Wizard-style fault handling: used for completed effect evaluations where self-healing fails and manual intervention is required. Based on the fault or business anomaly and related known information, the operation and maintenance management system calls the fault handling recommended action set (and process) provided by the effect evaluation module to dynamically generate a wizard-style visual UI interface. According to the wizard-style interface, the user is prompted to perform step-by-step operations to quickly complete the fault handling. For relatively fixed and complex operations, one-click operation execution is provided to reduce operational complexity and improve operational efficiency. The manual fault handling results and intermediate process status of the corresponding fault are written back to the knowledge base of the effect evaluation module.

[0108] In one possible implementation of the present application, taking the CPE terminal, 5G wireless network (NR network element) (i.e., the first network device) and 5G core network user plane function (UPF network element) (i.e., the second network device) scenarios as an example, and taking the SLO instantiation (reliability 99.999%, latency <= 20ms) controlled by the programmable logic controller (PLC) in industrial production as an example, how the entire system implements a closed-loop service assurance system is described in detail, as shown below.

[0109] In the operation and maintenance management system, users create a new PLC connection service through the connection service management module. When creating the connection service, they need to associate the terminal type of this connection service. When creating the connection service, they need to associate the corresponding SLO template based on the PLC control service scenario and set the corresponding service SLO in the template (such as 20ms latency, 59% reliability, 3ms latency jitter, etc.). Specifically, after the connection service with service SLO target guarantee is created, the connection service management module notifies the AI ​​intelligent assurance module of the network device of the connection service information. The connection service management module preferentially sends it to the UPF network element, which decomposes the SLO (such as 12ms latency, 3ms latency jitter) based on the large closed-loop process and notifies the AI ​​intelligent assurance module of the NR network element. If the NR network element does not support the large closed-loop process, the connection service management module also directly sends the SLO to the AI ​​intelligent assurance module of the NR network element. After the connection service with service SLO target guarantee is created, the connection service management module notifies the service SLO monitoring module of the connection service information.

[0110] Network elements automatically provide assurance based on SLOs and report real-time service status (and black box information) to the operation and maintenance management system. Specifically, upon receiving the SLO settings for the corresponding connection service, the network device's AI-powered intelligent assurance system converts the SLO into internal 5QI-level parameters or physical resource block (PRB) resource scheduling policies. The connection service assurance process is automatically initiated. If any SLO anomalies (glitches) occur, the module automatically analyzes and records signaling calls or abnormal events in related service modules, such as the signaling plane function body and user plane function, and records the black box information. The device side regularly reports the network element's service SLI indicators and black box information to the operation and maintenance management system (e.g., every 5 seconds).

[0111] The business SLO monitoring module presents the business SLI indicators of all connected businesses. When the business SLO target of a connected business or the business SLO target downward curve trend exceeds the current assurance level threshold, the self-healing closed-loop process is actively initiated. The specific details are as shown in the above embodiments and will not be described in detail in this embodiment.

[0112] The effectiveness evaluation module of the operation and maintenance management system outputs the automatic closed-loop effectiveness evaluation analysis conclusion of the current problem based on the self-healing and diagnosis results of the network elements, and records the phenomena, actions and results of the automated processing of this abnormal scenario as knowledge accumulation for abnormal scenario processing, completing knowledge recycling; if the self-healing evaluation result of this abnormal scenario is successful, the current guarantee closed-loop process ends.

[0113] If the system self-healing closed loop fails in this abnormal scenario, the wizard-style fault handling module of the operation and maintenance management system will dynamically generate fault handling suggestions that require manual intervention based on the network element diagnosis and handling information and the fault tree knowledge base, and prompt the user to perform manual handling on the interface.

[0114] Users can quickly handle faults using a wizard-style process according to the fault handling suggestions displayed by the operation and maintenance management system, provide online feedback on the status, and be guided to complete fault handling. The results of the user's manual fault handling process will also be recorded in the effect evaluation module as closed-loop feedback for the fault tree knowledge base.

[0115] Figure 7 is a schematic diagram of a service assurance device provided in an embodiment of the present application. As shown in Figure 7, the service assurance device is applied to an operation and maintenance management system. The service assurance device may include: a setting module 701, a first receiving module 702 and a first sending module 703.

[0116] Among them, the setting module 701 is used to set the service level objective SLO based on the business goal in the business connection request and send the SLO to the network device. The business connection request is used to create a connection business; the first receiving module 702 is used to determine the network anomaly point in the connection business based on the business data sent by the received network device; the first sending module 703 is used to send a guarantee instruction to the network device based on the network anomaly point, and the guarantee instruction is used to instruct the network device to perform business guarantee.

[0117] In an embodiment of the present application, first, a setting module 701 sets a service level objective SLO based on the business goal in the business connection request, and sends the SLO to the network device. The business connection request is used to create a connection business. Then, the first receiving module 702 determines the network anomaly point in the connection business based on the business data received from the network device. Finally, the first sending module 703 sends a guarantee instruction to the network device based on the network anomaly point. The guarantee instruction is used to instruct the network device to perform business guarantee. In an embodiment of the present application, the SLO is set when establishing a connection business, so that the network device is instructed to perform self-guarantee based on the SLO. When a network anomaly occurs in the connection business, the network anomaly point is determined, and a guarantee instruction is sent to the network device based on the anomaly point, so that the network device can perform business guarantee based on the guarantee instruction. The business guarantee of the network device improves the guarantee efficiency and enhances the reliability of the business.

[0118] In a possible implementation manner of the present application, the service assurance device may further include: a creation module.

[0119] The creation module is used to create a terminal-to-terminal or terminal-to-application connection service according to the terminal address and / or application address when receiving a service connection request, and the service connection request carries the terminal address and / or application address.

[0120] In a possible implementation of the present application, the network device includes a first network device and a second network device; the setting module 701 is used to: send the SLO to the second network device, so that the second network device determines multiple sub-SLOs based on the SLO and sends them to the first network device, where the sub-SLO is a segmented guarantee target of the SLO.

[0121] In a possible implementation manner of the present application, the service assurance device may further include: a second receiving module.

[0122] The service data sent by the first network device is received, where the service data includes service level measurement indicators (SLIs), statistical data, alarms, status, signaling messages, and black box information.

[0123] In a possible implementation of the present application, the first receiving module 702 is used to: determine whether the reception and / or transmission of the terminal device in the connection service is abnormal; if the reception and / or transmission of the terminal device is abnormal, extract the statistical data associated with the terminal device in the service data, as well as the alarms, status, signaling messages, and black box information sent by the terminal device; in the case where the statistical data, alarms, status, signaling messages and / or black box information are abnormal, determine that the network anomaly point in the connection service is the terminal device; in the case where the network anomaly point is a non-terminal device, based on the service level measurement indicators SLI, SLO, preset guarantee thresholds and network device status in the service data, analyze the network anomaly point and trace the root cause of the anomaly point to determine the network anomaly point in the connection service.

[0124] In one possible implementation of the present application, the first sending module 703 is used to: generate business anomaly characteristics based on the network anomaly point and the network anomaly phenomenon when the network anomaly point is a non-terminal device; generate network optimization or expansion instructions, or generate business assurance target adjustment instructions for business connections based on the business anomaly characteristics; send network optimization or expansion instructions, or business assurance target adjustment instructions for business connections to the network device; and receive analysis conclusions and assurance results returned by the network device.

[0125] In a possible implementation manner of the present application, the service assurance device may further include: a generation module and an update module.

[0126] Among them, the generation module is used to generate manual intervention processing suggestions based on the network anomaly points, network anomaly phenomena, business anomaly characteristics, business assurance process, and business data after business assurance in the analysis conclusion when the assurance result returned by the network device is assurance failure; the update module is used to update the network anomaly points, network anomaly phenomena, business anomaly characteristics, business assurance process, business data after business assurance, manual intervention processing suggestions, and execution results in the analysis conclusion to the preset fault tree knowledge base.

[0127] The service assurance device provided in the embodiment of the present application can implement each process implemented in the method embodiment of Figure 1 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0128] Figure 8 is a structural diagram of a service assurance device provided in an embodiment of the present application. As shown in Figure 8, the service assurance device is applied to a first network device. The service assurance device may include: a third receiving module 801, a collection module 802, a first assurance module 803, a second sending module 804, a fourth receiving module 805 and a second assurance module 806.

[0129] Among them, the third receiving module 801 is used to receive the SLO sent by the operation and maintenance management system or the sub-SLO and business message feature model sent by the second network device, where the SLO is the target corresponding to the connection service, and the business message feature model is a model determined by the second network device based on the business message characteristics corresponding to the type of connection service; the collection module 802 is used to collect business data based on the SLO or sub-SLO; the first guarantee module 803 is used to perform business self-guarantee based on the SLO, sub-SLO, business message feature model and business data; the second sending module 804 is used to send business data to the operation and maintenance management system in the event of business self-guarantee failure, or to send business data and guarantee failure information to the operation and maintenance management system and the second network device; the fourth receiving module 805 is used to receive guarantee instructions sent by the operation and maintenance management system based on business data; the second guarantee module 806 is used to perform business guarantee according to the guarantee instructions.

[0130] In an embodiment of the present application, first, the third receiving module 801 receives the SLO sent by the operation and maintenance management system or the sub-SLO and business message feature model sent by the second network device, and then the collection module 802 collects business data based on the SLO or sub-SLO, and the first guarantee module 803 performs business self-guarantee based on the SLO, sub-SLO, business message feature model and business data. The second sending module 804 sends the business data to the operation and maintenance management system in the event of failure of business self-guarantee, or sends the business data and guarantee failure information to the operation and maintenance management system and the second network device. Finally, the fourth receiving module 805 receives the guarantee instruction sent by the operation and maintenance management system based on the business data, and the second guarantee module 806 performs business guarantee according to the guarantee instruction. In an embodiment of the present application, the first network device can perform business self-guarantee based on the SLO sent by the operation and maintenance management system or the sub-SLO and business message feature model sent by the second network device, to ensure the reliable operation of the connected business, so that the SLO or sub-SLO is reachable. In the event of failure of self-guarantee, business guarantee can be performed based on the guarantee instruction sent by the operation and maintenance management system. Multiple guarantee methods can improve guarantee efficiency and enhance business reliability.

[0131] In a possible implementation of the present application, the first assurance module 803 is used to: perform data correlation analysis on the signaling messages and statistical data in the business data corresponding to the SLO, analyze the network anomaly points and trace the root causes of the anomaly points to determine the network anomaly points in the connection business; based on the SLO, network anomaly points, business anomaly characteristics, and the correspondence between the business anomaly characteristics and the trained adjustment strategy, adjust the priority of the service quality QoS, wireless air interface and resource scheduling strategy corresponding to the network anomaly points.

[0132] In a possible implementation of the present application, the first assurance module 803 is used to: perform data correlation analysis on the signaling messages and statistical data in the business data corresponding to the sub-SLO, analyze the network anomaly points and trace the root causes of the anomaly points to determine the network anomaly points in the connection business; based on the sub-SLO, business message feature model, network anomaly points, business anomaly features, and the correspondence between the business anomaly features and the trained adjustment strategy, adjust the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly points.

[0133] In one possible implementation of the present application, the second guarantee module 806 is used to: receive network optimization or expansion instructions sent by the operation and maintenance management system; based on the network optimization or expansion instructions, adjust network coverage, cell neighborhood, and network service strategies to reduce network interference and switching frequency and improve network capacity.

[0134] In a possible implementation of the present application, the second assurance module 806 is used to: receive a service assurance target adjustment instruction for a service connection sent by the operation and maintenance management system; determine multiple sub-SLOs based on the terminal-level SLO and application-level SLO sent by the operation and maintenance management system; adjust the sub-SLO based on the service assurance target adjustment instruction for the service connection; determine a message feature model based on the service message features in the service data; perform data correlation analysis on the signaling messages and statistical data in the service data, analyze the network anomaly points and trace the root causes of the anomaly points to determine the network anomaly points in the connection service; adjust the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly points based on the service message feature model, the adjusted sub-SLO, the network anomaly points, the service anomaly features, and the correspondence between the service anomaly features and the trained adjustment strategies.

[0135] The service assurance device provided in the embodiment of the present application can implement each process implemented in the method embodiment of Figure 2 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0136] Figure 9 is a schematic diagram of the structure of a service assurance device provided in an embodiment of the present application. As shown in Figure 9, the service assurance device is applied to a second network device and may include: a first determination module 901, an acquisition module 902, a second determination module 903, and a third sending module 904.

[0137] Among them, the first determination module 901 is used to receive the SLO sent by the operation and maintenance management system, and determine multiple sub-SLOs based on the SLO, where the SLO is the target corresponding to the connection service; the acquisition module 902 is used to obtain preset business message characteristics based on the type of connection service; the second determination module 903 is used to determine the business message characteristic model based on the business message characteristics; the third sending module 904 is used to send multiple sub-SLOs and business message characteristic models to the first network device, so that the first network device can perform business self-protection based on the sub-SLO and business message characteristic model.

[0138] In an embodiment of the present application, first, the first determination module 901 receives the SLO sent by the operation and maintenance management system, and determines multiple sub-SLOs based on the SLO, where the SLO is the target corresponding to the connection service. Then, the acquisition module 902 obtains the preset service message characteristics based on the type of the connection service. The second determination module 903 determines the service message characteristic model based on the service message characteristics. Finally, the third sending module 904 sends the multiple sub-SLOs and the service message characteristic model to the first network device, so that the first network device performs service self-guarantee based on the sub-SLO and the service message characteristic model. In this embodiment, the second network device can decompose the SLO sent by the operation and maintenance management system into multiple sub-SLOs, so that the first network device can perform service self-guarantee based on multiple sub-SLO segments, thereby improving the reliability of the connection service.

[0139] In a possible implementation manner of the present application, the service assurance device may further include: a statistics module, a second updating module, and a second acquisition module.

[0140] Among them, the statistical module is used to statistically analyze the business messages of the connection business based on the connection business, and obtain the corresponding business message characteristics and business message characteristic models; the second update module is used to update the business message characteristics to the preset business message characteristics; the second acquisition module is used to obtain the SLI corresponding to the SLO or sub-SLO based on the business message characteristics and the preset period, and report the SLI to the operation and maintenance management system.

[0141] In a possible implementation manner of the present application, the service assurance device may further include: an adjustment module.

[0142] Among them, the adjustment module is used to adjust the sub-SLO and the service message feature model when it is detected that the SLI of the connection service does not meet the SLO, or the downward trend of the SLI exceeds the guarantee threshold, or when the guarantee failure information sent by the first network device is received.

[0143] The service assurance device provided in the embodiment of the present application can implement each process implemented in the method embodiment of Figure 3 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0144] As shown in Figure 10, an embodiment of the present application also provides an electronic device 1000, including a processor 1001, a memory 1002, and a program or instruction stored in the memory 1002 and executable on the processor 1001. When the program or instruction is executed by the processor 1001, the various processes of the above-mentioned business assurance method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, they will not be described here.

[0145] The present application also provides a storage medium storing a program or instruction. When executed by a processor, the program or instruction implements the various processes of the service assurance method provided in any of the above embodiments. The same technical effects can be achieved, and to avoid repetition, they are not described here.

[0146] The processor is the processor in the electronic device described in the above embodiment. The storage medium includes a computer storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0147] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned service assurance method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0148] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0149] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-mentioned service assurance method embodiment and can achieve the same technical effect. To avoid repetition, it is not repeated here.

[0150] The embodiment of the present application further provides a processing device, which is configured to execute each process of the above-mentioned service assurance method embodiment and can achieve the same technical effect. To avoid repetition, it is not described here.

[0151] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0152] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0153] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A business assurance method, applied to an operation and maintenance management system, comprising: Setting a service level objective SLO based on a business objective in a business connection request, and sending the SLO to a network device, wherein the business connection request is used to create a connection business; Determining a network anomaly point in the connection service based on the received service data sent by the network device; A guarantee instruction is sent to the network device based on the network abnormal point, wherein the guarantee instruction is used to instruct the network device to perform service guarantee.

2. The method according to claim 1, wherein: Before setting the service level objective SLO based on the business goal in the business connection request, the method further includes: When a service connection request is received, a terminal-to-terminal or terminal-to-application connection service is created according to the terminal address and / or application address, wherein the service connection request carries the terminal address and / or application address.

3. The method according to claim 1, wherein: The network device includes a first network device and a second network device; sending the SLO to the network device includes: The SLO is sent to the second network device, so that the second network device determines a plurality of sub-SLOs based on the SLO and sends the sub-SLOs to the first network device, wherein the sub-SLOs are segmented guarantee targets of the SLO.

4. The method according to claim 3, wherein: After sending the SLO to the network device, the method further includes: Receive business data sent by the first network device, where the business data includes service level measurement indicators SLI, statistical data, alarms, status, signaling messages and black box information.

5. The method according to claim 1, wherein: The determining of the network abnormality point in the connection service based on the received service data sent by the network device includes: Determining whether reception and / or transmission of a terminal device in the connection service is abnormal; If the receiving and / or sending of the terminal device is abnormal, the statistical data associated with the terminal device in the service data, as well as the alarm, status, and signaling sent by the terminal device are extracted. Messages and black box information; In the case where the statistical data, the alarm, the status, the signaling message and / or the black box information are abnormal, determining that the network abnormal point in the connection service is the terminal device; In the case where the network anomaly point is a non-terminal device, based on the service level measurement indicator SLI in the business data, the SLO, the preset guarantee threshold and the network equipment status, the network anomaly point is analyzed and the root cause of the anomaly point is traced to determine the network anomaly point in the connection business.

6. The method according to claim 5, wherein: The sending of a protection instruction to the network device based on the network abnormal point includes: In the case where the network abnormal point is a non-terminal device, generating a service abnormality feature based on the network abnormal point and the network abnormal phenomenon; Based on the abnormal service characteristics, generate a network optimization or expansion instruction, or generate a service assurance target adjustment instruction for the service connection; Sending a network optimization or expansion instruction, or a service assurance target adjustment instruction of a service connection to the network device; Receive the analysis conclusion and assurance result returned by the network device.

7. The method according to claim 6, wherein: The method further comprises: In the case where the assurance result returned by the network device is assurance failure, generating a manual intervention processing suggestion based on the network abnormality points, network abnormality phenomena, service abnormality characteristics, service assurance process, and service data after service assurance in the analysis conclusion; The network anomaly points, network anomaly phenomena, business anomaly characteristics, business assurance process, business data after business assurance, manual intervention processing suggestions, and execution results in the analysis conclusion are updated to a preset fault tree knowledge base.

8. A service assurance method, applied to a first network device, the method comprising: Receive an SLO sent by the operation and maintenance management system or a sub-SLO and a service message feature model sent by a second network device, wherein the SLO is a target corresponding to the connection service, and the service message feature model is a model determined by the second network device based on service message features corresponding to the type of the connection service; Based on the SLO or the sub-SLO, collect business data; Performing business self-assurance according to the SLO, the sub-SLO, the business message feature model and the business data; In the event that the service self-assurance fails, sending the service data to the operation and maintenance management system, or sending the service data and assurance failure information to the operation and maintenance management system and the second network device; Receiving a guarantee instruction sent by the operation and maintenance management system based on the business data; Business assurance is performed according to the assurance instruction.

9. The method according to claim 8, wherein: The performing service self-assurance according to the SLO, the sub-SLO, the service message feature model and the service data includes: Performing data correlation analysis on the signaling messages and statistical data in the service data corresponding to the SLO, analyzing the network anomaly points and tracing the root causes of the anomaly points to determine the network anomaly points in the connection service; Based on the SLO, the network anomaly point, the business anomaly characteristics, and the correspondence between the business anomaly characteristics and the trained adjustment strategy, the priority of the quality of service QoS, the wireless air interface and the resource scheduling strategy corresponding to the network anomaly point are adjusted.

10. The method according to claim 8, wherein: The performing service self-assurance according to the SLO, the sub-SLO, the service message feature model and the service data includes: Performing data correlation analysis on the signaling messages and statistical data in the service data corresponding to the sub-SLO, analyzing the network anomaly points and tracing the root causes of the anomaly points to determine the network anomaly points in the connection service; Based on the sub-SLO, the service message feature model, the network anomaly point, the service anomaly features, and the correspondence between the service anomaly features and the trained adjustment strategy, the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly point are adjusted.

11. The method according to claim 8, wherein: The performing of business assurance according to the assurance instruction includes: Receiving network optimization or capacity expansion instructions sent by the operation and maintenance management system; Based on the network optimization or expansion instructions, adjust network coverage, cell neighborhood, and network service strategy to reduce network interference and switching frequency and improve network capacity.

12. The method according to claim 8, wherein: The performing of business assurance according to the assurance instruction includes: Receiving a service assurance target adjustment instruction for a service connection sent by the operation and maintenance management system; Determine a plurality of sub-SLOs based on the terminal-level SLO and the application-level SLO sent by the operation and maintenance management system; Adjusting the sub-SLO based on the service assurance objective adjustment instruction of the service connection; Determining a message feature model according to the service message features in the service data; Performing data correlation analysis on the signaling messages and statistical data in the service data, analyzing network anomalies and tracing the root causes of the anomalies to determine the network anomalies in the connection service; Based on the service message feature model, the adjusted sub-SLO, the network anomaly point, the service anomaly features, and the correspondence between the service anomaly features and the trained adjustment strategy, the QoS priority, wireless air interface and resource scheduling strategy corresponding to the network anomaly point are adjusted.

13. A service assurance method, applied to a second network device, the method comprising: Receiving an SLO sent by an operation and maintenance management system, and determining a plurality of sub-SLOs based on the SLO, wherein the SLO is a target corresponding to the connection business; Based on the type of the connection service, obtaining preset service message characteristics; Based on the service message characteristics, determining a service message characteristic model; The plurality of sub-SLOs and the service message feature model are sent to a first network device, so that the first network device performs service self-assurance based on the sub-SLOs and the service message feature model.

14. The method according to claim 13, wherein: The method further comprises: Based on the connection service, statistically analyzing the service messages of the connection service to obtain corresponding service message features and a service message feature model; Updating the service message characteristics to the preset service message characteristics; Based on the service message characteristics and the preset period, obtain the SLO or the sub-SLO The corresponding SLI is reported to the operation and maintenance management system.

15. The method according to claim 13, wherein: The method further comprises: When it is detected that the SLI of the connection service does not meet the SLO, or the downward trend of the SLI exceeds the guarantee threshold, or guarantee failure information sent by the first network device is received, the sub-SLO and the service message feature model are adjusted.

16. An electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the service assurance method according to any one of claims 1 to 15.

17. A storage medium storing a program or an instruction, wherein the program or the instruction, when executed by a processor, implements the steps of the service assurance method according to any one of claims 1 to 15.

Images