Policy configuration management method and related apparatus

Abstract

Provided in the embodiments of the present application are a policy configuration management method and a related apparatus. The method comprises: receiving a first inference policy from a second device, wherein the first inference policy comprises a first threshold and / or a second threshold, the first threshold being used for triggering an inference function when a first network performance indicator of a first network element does not meet the first threshold, the second threshold being used for triggering the inference function when a second network performance indicator of a first area does not meet the second threshold, and the first area being an area in which the first network element is located; and triggering the inference function on the basis of the first inference policy. The embodiments of the present application can satisfy continuously increasing network optimization requirements.

Description

A strategy configuration management method and related apparatus

[0001] This application claims priority to Chinese Patent Application No. 202411189658.1, filed on August 27, 2024, entitled "A Strategy Configuration Management Method and Related Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of wireless communication, and in particular to a policy configuration management method and related apparatus. Background Technology

[0003] In radio access network (RAN) management service systems that deploy artificial intelligence / machine learning (AI / ML) capabilities, management service consumers (such as domain management function units) can send inference policies to management service producers (such as network elements). Management service producers (such as network elements) can then trigger AI / ML inference functions, such as energy saving (ES), mobility load balancing (MLB), and mobility robustness optimization (MRO), based on the policy configuration of these inference policies, thereby optimizing network performance. However, the policy configurations of traditional inference policies are generic and struggle to meet the ever-increasing demands for network optimization.

[0004] Therefore, how to meet the ever-increasing demands for network optimization is an urgent problem to be solved in the development of RAN technology in the current communications field. Summary of the Invention

[0005] This application provides a policy configuration management method and related apparatus, which can improve the network performance of wireless access networks.

[0006] In a first aspect, embodiments of this application provide a policy configuration management method applied to a first device, the method comprising:

[0007] The system receives a first inference policy from a second device, wherein the first inference policy includes a first threshold and / or a second threshold. The first threshold is used to trigger the inference function when the first network performance indicator of the first network element does not meet the first threshold, and the second threshold is used to trigger the inference function when the second network performance indicator of the first region does not meet the second threshold. The first region is the region where the first network element is located.

[0008] The reasoning function is triggered based on the first reasoning strategy.

[0009] In the above method, the inference function can be an ES function, an MLB function, or an MRO function, etc. Considering that the inference function corresponds to different network optimization requirements, when configuring the first inference strategy, the above method can set the first threshold and / or the second threshold in the first inference strategy according to different network optimization requirements, so that the first device can trigger the inference function to optimize the network performance when the network performance of a single network element (i.e., local network performance) and / or the network performance of the area where the single network element is located (i.e., overall network performance) fails to meet the network optimization requirements.

[0010] Because the first inference strategy has a relatively flexible configuration, the embodiments of this application can meet the ever-increasing network optimization requirements. Furthermore, in the embodiments of this application, the first device can focus on triggering the inference function based on the network performance of a local area and / or the overall network performance of the area, thereby improving the stability of network performance.

[0011] In one alternative implementation, the first inference strategy further includes regional scope information, which includes a list of network element identifiers, a list of cell identifiers, or a list of latitude and longitude information.

[0012] The above method configures the regional range information into the first inference strategy, further enhancing the flexibility of the strategy configuration of the first inference strategy, thereby meeting the network optimization needs with regional restrictions, and thus optimizing network performance more finely.

[0013] In another alternative implementation, the first inference strategy also includes strategy type information, which indicates the type of inference function, namely, energy saving (ES) function, mobile load balancing (MLB) function, and mobile robust optimization (MRO) function.

[0014] In another alternative implementation, the first inference strategy also includes strategy priority information, which is used to indicate the importance level of the inference function.

[0015] The above method configures policy priority information into the first inference policy, further enhancing the flexibility of the policy configuration of the first inference policy, thereby meeting the network optimization requirements with inference function type priority restrictions, and thus optimizing network performance more finely.

[0016] In another alternative implementation, the first inference strategy also includes inference granularity information;

[0017] The inference function is an ES function, and the inference granularity information includes one or more of the following: shut-off cell, shut-off carrier, and shut-off time slot;

[0018] Alternatively, the inference function is an MLB function, and the inference granularity information includes one or more of the following: equalized slice load, equalized cell load, and equalized beam load.

[0019] Alternatively, the inference function is an MRO function, and the inference granularity information includes one or more of the following: adjustment beam mobility parameters and / or adjustment cell mobility parameters.

[0020] The above method configures inference granularity information into the first inference strategy, further enhancing the flexibility of the first inference strategy configuration, thereby meeting the network optimization needs with operation type restrictions, and thus optimizing network performance more finely.

[0021] In another alternative implementation, the inference function is the ES function, the first network performance indicator is the network element energy consumption, and the second network performance indicator is the regional energy consumption, which is the average energy consumption, total energy consumption, or maximum energy consumption of all network elements in the region.

[0022] Alternatively, the inference function is the MLB function, the first network performance indicator is the network element resource utilization rate, the second network performance indicator is the regional resource utilization rate, and the regional resource utilization rate is the average resource utilization rate, total resource utilization rate, or highest resource utilization rate of all network elements in the region.

[0023] Alternatively, the inference function is the MRO function, the first network performance indicator is the number of successful network element handover requests, and the second network performance indicator is the number of successful area handover requests. The number of successful area handover requests is the average number of successful handover requests for all network elements in the area, the total number of successful handover requests in the area, or the highest number of successful handover requests in the area.

[0024] In yet another alternative implementation, the method further includes:

[0025] A first inference report is sent to the second device, wherein the first inference report includes the operations performed by the network element in the first area.

[0026] After the first device triggers the inference function in the above method, it can also send a first inference report to the second device so that the second device can obtain the triggering result of the inference function, which is beneficial for subsequent optimization of the inference model corresponding to the inference function, thereby further improving the optimization effect of network performance.

[0027] In another alternative implementation, the first inference report also includes the time when the network element in the first area performs the operation.

[0028] In another alternative implementation, the first network element is any network element in the first region, and the first inference report also includes a third network performance indicator after the first network element performs an operation on the network elements in the first region, and a fourth network performance indicator after the first region performs an operation on the network elements in the first region.

[0029] In another alternative implementation, the inference function is the ES function, and the third network performance indicator includes one or more of the following: network element energy consumption, network element energy efficiency, network element resource utilization, network element uplink and downlink throughput, cell uplink and downlink throughput, network element uplink and downlink throughput, and cell uplink and downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink and downlink throughput, and regional uplink and downlink throughput.

[0030] Alternatively, the inference function is the MLB function, and the third network performance indicator includes one or more of the following: network element resource utilization, cell resource utilization, network element uplink / downlink throughput, cell uplink / downlink throughput, network element uplink / downlink throughput, and cell uplink / downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput.

[0031] Alternatively, the inference function is the MRO function, and the third network performance indicator includes one or more of the following: network element handover success rate, cell handover success rate, network element handover failure rate, cell handover failure rate, number of network element handovers that are too early, number of cell handovers that are too early and fail, number of network element handovers that are too late, number of cell handovers that are too late, number of network element handovers with incorrect cells, and number of cell handover errors. The fourth network performance indicator includes one or more of the following: area handover success rate, area handover failure rate, number of area handovers that are too early, number of area handovers that are too late, and number of area handovers with incorrect cells.

[0032] In another alternative implementation:

[0033] The first device is a cross-domain management function entity, and the second device is a business support system, or...

[0034] The first device is a domain management function entity, and the second device is a cross-domain management function entity, or...

[0035] The first device is one or more network elements in the first region, and the second device is a cross-domain management function entity.

[0036] Secondly, embodiments of this application provide a policy configuration management method applied to a second device, the policy configuration management method comprising:

[0037] Configure a first inference strategy, wherein the first inference strategy includes a first threshold and / or a second threshold. The first threshold is used to trigger the inference function when the first network performance indicator of the first network element does not meet the first threshold. The second threshold is used to trigger the inference function when the second network performance indicator of the first region does not meet the second threshold. The first region is the region where the first network element is located.

[0038] A first inference strategy is sent to a first device, wherein the first inference strategy is used to trigger the inference function.

[0039] In one alternative implementation, the first inference strategy further includes regional scope information, which includes a list of network element identifiers, a list of cell identifiers, or a list of latitude and longitude information.

[0040] In another alternative implementation, the first inference strategy also includes strategy type information, which indicates the type of inference function, namely, energy saving (ES) function, mobile load balancing (MLB) function, and mobile robust optimization (MRO) function.

[0041] In another alternative implementation, the first inference strategy also includes strategy priority information, which is used to indicate the importance level of the inference function.

[0042] In another alternative implementation, the first inference strategy also includes inference granularity information;

[0043] The inference function is an ES function, and the inference granularity information includes one or more of the following: shut-off cell, shut-off carrier, and shut-off time slot;

[0044] Alternatively, the inference function is an MLB function, and the inference granularity information includes one or more of the following: equalized slice load, equalized cell load, and equalized beam load.

[0045] Alternatively, the inference function is an MRO function, and the inference granularity information includes adjusting the mobility parameters of the beam and / or adjusting the mobility parameters of the cell.

[0046] In another alternative implementation, the inference function is the ES function, the first network performance indicator is the network element energy consumption, and the second network performance indicator is the regional energy consumption, which is the average energy consumption, total energy consumption, or maximum energy consumption of all network elements in the region.

[0047] Alternatively, the inference function is the MLB function, the first network performance indicator is the network element resource utilization rate, and the second network performance indicator is the regional resource utilization rate. The regional resource utilization rate is the average resource utilization rate, total resource utilization rate, or highest resource utilization rate of all network elements in the region.

[0048] Alternatively, the inference function is the MRO function, the first network performance indicator is the number of successful network element handover requests, the second network performance indicator is the number of successful area handover requests, and the number of successful area handover requests is the average number of successful handover requests for all network elements in the area, the total number of successful handover requests in the area, or the highest number of successful handover requests in the area.

[0049] In yet another alternative implementation, the method further includes:

[0050] A first inference report is sent to a second device, wherein the first inference report includes the operations performed by the network element in the first area.

[0051] In another alternative implementation, the first inference report also includes the time when the network element in the first area performs the operation.

[0052] In another alternative implementation, the first network element is any network element in the first region, and the first inference report also includes a third network performance indicator after the first network element performs an operation on the network elements in the first region, and a fourth network performance indicator after the first region performs an operation on the network elements in the first region.

[0053] In another alternative implementation, the inference function is the ES function, and the third network performance indicator includes one or more of the following: network element energy consumption, network element energy efficiency, network element resource utilization, network element uplink and downlink throughput, cell uplink and downlink throughput, network element uplink and downlink throughput, and cell uplink and downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink and downlink throughput, and regional uplink and downlink throughput.

[0054] Alternatively, the inference function is the MLB function, and the third network performance indicator includes one or more of the following: network element resource utilization, cell resource utilization, network element uplink / downlink throughput, cell uplink / downlink throughput, network element uplink / downlink throughput, and cell uplink / downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput.

[0055] Alternatively, the inference function is the MRO function, and the third network performance indicator includes one or more of the following: network element handover success rate, cell handover success rate, network element handover failure rate, cell handover failure rate, number of network element handovers that are too early, number of cell handovers that are too early and fail, number of network element handovers that are too late, number of cell handovers that are too late, number of network element handovers with incorrect cells, and number of cell handover errors. The fourth network performance indicator includes one or more of the following: area handover success rate, area handover failure rate, number of area handovers that are too early, number of area handovers that are too late, and number of area handovers with incorrect cells.

[0056] Thirdly, embodiments of this application provide a communication device, which can be the first device in the first aspect or any possible implementation of the first aspect, wherein:

[0057] The communication device includes a module for performing the method described in the first aspect or any possible implementation thereof.

[0058] Fourthly, embodiments of this application provide a communication device, which can be the second device in the second aspect or any possible implementation of the second aspect, wherein:

[0059] The communication device includes a module for performing the method described in the second aspect or any possible implementation thereof.

[0060] Fifthly, embodiments of this application provide a communication device, characterized in that it includes a logic circuit and an interface, the logic circuit and the interface being coupled; the interface is used for inputting and / or outputting information, wherein:

[0061] This logic circuit is used to perform the method described in the first aspect or any possible implementation thereof, or...

[0062] This logic circuit is used to execute the method described in the second aspect or any possible implementation of the second aspect.

[0063] Sixthly, embodiments of this application provide a communication system, characterized in that the communication system includes a first communication device and a second communication device, wherein:

[0064] The first communication device is used to perform the method described in the first aspect or any possible implementation thereof, and the second communication device is used to perform the method described in the second aspect or any possible implementation thereof.

[0065] In a seventh aspect, embodiments of this application provide a computer-readable storage medium for storing a computer program, wherein:

[0066] When executed, the computer program is capable of implementing the first aspect or any possible implementation of the first aspect, or...

[0067] When the computer program is executed, it is capable of implementing the second aspect or any possible implementation of the second aspect.

[0068] The beneficial effects of the methods, systems, and apparatus provided by any possible implementation of the second to seventh aspects of this application can be referred to the beneficial effects of the technical solutions provided by the first aspect and any possible implementation of the first aspect, which will not be repeated here. Attached Figure Description

[0069] The accompanying drawings used in the embodiments of this application are described below.

[0070] Figure 1 is a schematic diagram of the architecture of a management service system provided in an embodiment of this application;

[0071] Figure 2 is a flowchart illustrating a strategy configuration management method provided in an embodiment of this application;

[0072] Figure 3 is a flowchart illustrating another policy configuration management method provided in an embodiment of this application;

[0073] Figure 4 is a flowchart illustrating another policy configuration management method provided in an embodiment of this application;

[0074] Figure 5 is a schematic diagram of the architecture of another management service system provided in an embodiment of this application;

[0075] Figure 6 is a flowchart illustrating another policy configuration management method provided in an embodiment of this application;

[0076] Figure 7 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0077] Figure 8 is a schematic diagram of another communication device provided in an embodiment of this application;

[0078] Figure 9 is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0079] The embodiments of this application are described below with reference to the accompanying drawings.

[0080] The radio access network (RAN) is a key element in mobile telecommunications system architecture. It acts as a channel for transmitting information between user equipment (UE) and the core network, providing wireless services such as mobile data, voice and video, and broadband access. The RAN consists of multiple devices, including base stations, UEs, and network equipment. Network elements (such as base stations) are the core components of the RAN, primarily responsible for transmitting and receiving radio signals, connecting UEs to the core network. Units in the RAN management service system can manage the RAN and implement various network functions. For ease of understanding, the RAN management service system will be explained below with reference to Figure 1.

[0081] Please refer to Figure 1, which is a schematic diagram of the architecture of a management service system provided in an embodiment of this application. As shown in Figure 1, the RAN management service system 10 includes a business support system (BSS) 101, a cross domain management function (CD-MnF) unit 102, a domain management function (D-MnF) unit, and multiple network elements.

[0082] The embodiments of this application do not impose strict limitations on the number of domain management functional units and network elements; the numbers shown in Figure 1 are merely examples. The following explanation uses BSS101, CD-MnF unit 102, D-MnF unit 103, and network elements 104 to 106 in the RAN management service system 10 as examples to further illustrate the RAN management service system 10.

[0083] BSS101 can provide one or more of the following management functions or services: billing, settlement, accounting, customer service, sales, network monitoring, and communication service lifecycle management. Optionally, BSS101 can be an operator's operating system in the telecommunications industry, or an operating system in other industries related to the telecommunications industry, i.e., a vertical OT system.

[0084] CD-MnF unit 102 can provide one or more of the following management functions or services: network lifecycle management, network deployment, network fault management, network performance management, network configuration management, network assurance, network optimization, and network intent translation. Optionally, CD-MnF unit 102 can be a network slicing management function unit, a cross-domain management data analysis function unit, a cross-domain self-organizing network function unit, or a cross-domain intent management function unit. Optionally, CD-MnF unit 102 can be a network management entity such as a network management system (NMS) or a network function management service consumer (NFMS_C).

[0085] D-MnF unit 103 can provide one or more of the following management functions or services: network lifecycle management, network deployment, network fault management, network performance management, network configuration management, network assurance, network optimization, and network intent translation. Optionally, D-MnF unit 103 can be a network slicing management function unit, a domain management data analysis function unit, a domain self-organizing network function unit, or a domain intent management function unit. Optionally, D-MnF unit 103 can be a wireless automation engine or a network element management system, etc. Optionally, domain management function units can be classified according to network type; for example, D-MnF unit 103 can be an access network domain management function unit, a core network domain management function unit, or a transmission network domain management function unit. Optionally, domain management function units can be classified according to administrative region; for example, D-MnF unit 103 can be a Shanghai domain management function unit, a Beijing domain management function unit, or a Wuhan domain management function unit.

[0086] The term "network" as used in the aforementioned management functions or services may include one or more network elements, one or more subnetworks, and network slices. A subnetwork may be a subnetwork composed of one or more network elements, a network set composed of multiple subnetworks, or a network slice subnetwork composed of multiple network sets.

[0087] Network elements 104 to 106 are located in the same area and can all be managed by D-MnF unit 103. Multiple network elements in the same area can communicate wirelessly. Taking network element 104 as an example, network element 104 can provide one or more of the following management functions or services: network element lifecycle management, network element deployment, network element fault management, network element performance management, network element assurance, network element optimization functions, and translation of network element intents, etc. Network element 104 is an entity; for example, network element 104 can be a core network element or an access network element. Core network elements can provide access and mobility management functions, session management functions, policy control functions, network data analysis units, network warehouse units, and gateways, etc. Access network elements can be base stations (such as 4G base stations eNB, 5G base stations gNB), central unit control plane (CUCP), central unit (CU), distribution unit (DU), central unit user plane (CUUP), etc.

[0088] In the RAN management service system 10, the unit providing management services is called the management service consumer, and the unit receiving management services is called the management service producer. For example, if BSS 101 provides management services to CD-MnF unit 102, BSS 101 is the management service consumer, and CD-MnF unit 102 is the management service producer; if CD-MnF unit 102 provides management services to D-MnF unit 103, CD-MnF unit 102 is the management service consumer, and D-MnF unit 103 is the management service producer; if D-MnF unit 103 provides management services to network element 104, D-MnF unit 103 is the management service consumer, and network element 104 is the management service producer.

[0089] Furthermore, with the application of artificial intelligence (AI) and machine learning (ML) technologies in the communications field, AI / ML functions can be deployed in the RAN management service system 10. AI / ML functions include training, testing, simulation, and inference functions. The different types of AI / ML functions mentioned above can be deployed in different units of the RAN management service system 10, or they can be deployed in the same unit of the RAN management service system 10. For example, both training and inference functions can be deployed in the D-MnF unit 103, or the training function can be deployed in the D-MnF unit 103, and the inference function can be deployed in network element 104.

[0090] In some related technologies, a unit deployed with inference capabilities can receive inference policies sent by a unit that configures inference strategies, and can trigger inference functions based on the policy configuration of these inference policies, such as energy saving (ES), mobility load balancing (MLB), and mobility robustness optimization (MRO) functions, thereby optimizing network performance. It should be noted that ES functions can also be called network energy saving (NES), MLB functions can also be called load balancing (LB), and MRO functions can also be called mobility optimization (MO); the embodiments in this application do not strictly limit these definitions.

[0091] For example, in a single-domain autonomous scenario, the unit in the RAN management service system 10 used to configure inference policies can be a CD-MnF unit 102, and the unit deployed with inference functions can be a D-MnF unit 103 or a network element 104; in a cross-domain autonomous scenario, the unit in the RAN management service system 10 used to configure inference policies can be a BSS 101, and the unit deployed with inference functions can be a CD-MnF unit 102.

[0092] However, the strategy configuration for this inference strategy is generic, regardless of whether it's for the same type of inference function or different types of inference functions. For example, the inference strategy includes activation region information, which indicates the regions where network optimization is desired. Therefore, traditional inference strategies struggle to meet the ever-increasing demands for network optimization.

[0093] Therefore, embodiments of this application provide a policy configuration management method and related apparatus to meet the ever-increasing network optimization requirements.

[0094] Please refer to Figure 2, which is a flowchart illustrating a policy configuration management method provided in an embodiment of this application. This method can be implemented based on the architecture shown in Figure 1, or on other architectures. The method includes, but is not limited to, the following steps:

[0095] Step S201: The second device sends the first inference strategy to the first device.

[0096] The first device is the one with inference capabilities deployed, and the second device is used to configure the inference strategy. The second device can send the configured first inference strategy to the first device.

[0097] It is understood that the first device and the second device can be entities or components within two different units of the RAN management service system 10 shown in Figure 1. For example, in a single-domain autonomous scenario, the second device can be an entity (hereinafter referred to as a CD-MnF entity) corresponding to CD-MnF unit 102 or a component within the CD-MnF entity, and the first device can be an entity (hereinafter referred to as a D-MnF entity) corresponding to D-MnF unit 103 or a component within the D-MnF entity, or network element 104; in a cross-domain autonomous scenario, the second device can be an entity or a component within BSS 101, and the first device can be a CD-MnF entity or a component within the CD-MnF entity.

[0098] In this embodiment, the second device can directly transmit information to the first device, or indirectly transmit information to the first device through an intermediate device. For example, the second device is a CD-MnF entity, and the first device is a D-MnF entity. The CD-MnF entity can directly send the first inference strategy to the D-MnF entity. Alternatively, if the second device is a CD-MnF entity and the first device is network element 104, the CD-MnF entity can send the first inference strategy to network element 104 through the D-MnF entity; that is, the CD-MnF entity can first send the first inference strategy to the D-MnF entity, and then the D-MnF entity can send the first inference strategy to network element 104.

[0099] The first inference strategy includes a first threshold and / or a second threshold. The first threshold is used to trigger the inference function when a first network performance indicator of a first network element fails to meet the first threshold, and the second threshold is used to trigger the inference function when a second network performance indicator of a first region fails to meet the second threshold. The first region is the region where the first network element is located. The first network element is any one of multiple network elements in the first region. The inference function is used to optimize network performance. Optionally, the inference function includes one of the following: ES function, MRO function, and MRO function.

[0100] It is understood that the first threshold and the second threshold can be used as threshold values ​​for the first device to trigger the inference function, the first network performance index is an index used to reflect the network performance of a single network element before the first device triggers the inference function, and the second network performance index is an index used to reflect the network performance of the first area before the first device triggers the inference function.

[0101] In this embodiment, "the first network performance indicator does not meet the first threshold" can be understood as "the first network performance indicator does not meet the first preset condition related to the first threshold." This first preset condition defines the relationship between the first network performance indicator and the first threshold. For example, the first preset condition could be that the first network performance indicator is less than the first threshold, or it could be that the first network performance indicator is greater than the first threshold. This embodiment does not strictly limit the first preset condition; both the first preset condition and the first threshold can be set according to actual network optimization needs. Similarly, in this embodiment, "the second network performance indicator does not meet the second threshold" can be understood as "the second network performance indicator does not meet the second preset condition related to the second threshold," which will not be elaborated further here.

[0102] Optionally, the inference function is the ES function, the first network performance indicator is network element energy consumption, and the second network performance indicator is regional energy consumption. Regional energy consumption can be the average energy consumption, total energy consumption, or maximum energy consumption of all network elements in the region. For example, the unit of energy consumption can be "joule" or "kilowatt-hour".

[0103] Optionally, the inference function is the ES function. The first network performance indicator is the network element energy-saving cost, and the second network performance indicator is the regional cost. The regional cost can be the average energy-saving cost, total energy-saving cost, or highest energy-saving cost of all network elements in the region. In practical applications, the network element cost can be obtained by converting the network element energy consumption according to a preset conversion formula. For example, the energy-saving cost can be represented by an integer, where 0 represents the minimum measured energy consumption and 10000 represents the maximum measured energy consumption.

[0104] Optionally, the inference function is the ES function. The first network performance indicator is network element energy efficiency, and the second network performance indicator is regional energy efficiency. Regional energy efficiency can be the average energy efficiency, total energy efficiency, or highest energy efficiency of all network elements in the region. For example, energy efficiency can be calculated as the ratio of data volume to energy-saving cost, where data volume can be the data volume transmitted by users of base stations or the data volume transmitted by users of all base stations in the region.

[0105] Optionally, the inference function is an MLB function. The first network performance metric is network element resource utilization, and the second network performance metric is regional resource utilization. Regional resource utilization can be the average resource utilization of all network elements in the region, the total resource utilization of the region, or the highest resource utilization of the region. For example, resource utilization can be physical resource block (PRB) utilization, including uplink and downlink PRB utilization.

[0106] Optionally, the inference function is the MRO function, the first network performance indicator is a network element handover related indicator, and the second network performance indicator is a region handover related indicator. For example, handover related indicators may include the number of successful / failed handover requests, the number of successful / failed handover resource allocation requests, the number of successful / failed beam handover executions, etc. In this embodiment, handover may be base station handover, intra-base station handover, or inter-system handover. This embodiment does not impose any limitations on this.

[0107] Optionally, in addition to the first and second thresholds, the first inference strategy may also include other thresholds to constrain other network performance indicators. For example, the first inference strategy may further include a third threshold, which is used to trigger the inference function when the third network performance indicator of the first network element does not meet the third threshold. The inference function is an ES function, the first network performance indicator is network element energy consumption, the second network performance indicator is regional energy consumption, and the third network performance indicator is network element energy efficiency. That is to say, the first inference strategy can set corresponding thresholds for different network performance indicators, and the number of thresholds in the first inference strategy is not strictly limited in this embodiment.

[0108] Optionally, during the actual inference process using the AI / ML model corresponding to the inference function, the first device needs to perform inference based on the target values ​​corresponding to each network performance indicator to ensure that the inference result meets the target values ​​as much as possible. The target values ​​can be default parameters or configured through a first inference strategy. For example, the first network performance indicator corresponds to a first target value, and the second network performance indicator corresponds to a second target value. Optionally, the first inference strategy may also include the first target value and / or the second target value. Optionally, the first threshold in the first inference strategy may be equal to the first target value, and / or the second threshold may be equal to the second target value. It should be noted that the AI / ML model can also be called an AI model or an ML model; this embodiment does not strictly limit the terminology.

[0109] Step S202: The first device triggers the reasoning function according to the first reasoning strategy.

[0110] The first device can obtain the first network performance index of the first network element and / or the second network performance index of the first area, and, according to the first threshold and / or the second threshold configured in the received first inference strategy, trigger the inference function to optimize network performance when the first network performance index of the first network element does not meet the first threshold and / or the second network performance index of the first area does not meet the second threshold.

[0111] It should be noted that the operation of the first device to obtain the first network performance index and / or the second network performance index can be performed before or after step S201, and this application embodiment does not strictly limit this.

[0112] In one optional implementation, the first device can obtain a first network performance indicator for each network element in the first region, and then determine a second network performance indicator for the first region based on the first network performance indicators of each network element in the first region. For example, the first device sends a first indication message to a first network element, and after receiving the first indication message, the first network element sends its first network performance indicator to the first device. After receiving the first network performance indicators of each network element in the first region, the first device determines the second network performance indicator for the first region.

[0113] In one optional implementation, the first region can be the region managed by default by the first device. For example, when the first device is the D-MnF entity in the RAN management service system 10 shown in FIG1, the first region is the region where network elements 104 to 106, which are directly managed by the D-MnF entity, are located. The first region can also be the region where the first device is located. For example, when the first device is network element 104 in the RAN management service system 10 shown in FIG1, the first region is the region where network elements 104 to 106 are located.

[0114] In an optional implementation, the first inference strategy may further include regional range information. The first device can determine the first region based on the regional range information. The regional range information includes the identity information of a network element, the identity information of the communication area where the network element provides network services, or the geographical location information of the first region. For example, when the network element is a base station, the regional range information includes a base station identifier list, a cell identifier list, or a list of latitude and longitude information of the first region. The first device can determine the first region using the base station identifier list, the cell identifier list, or the list of latitude and longitude information of the first region.

[0115] In one alternative implementation, the first inference strategy further includes strategy type information, which indicates the type of inference function, as described above, which is one of ES function, MLB function and MRO function.

[0116] In one optional implementation, the first inference strategy further includes strategy priority information, which indicates the importance level of the inference function. It is understood that when the first device receives multiple inference strategies, it can prioritize the execution of more important inference functions based on the strategy priority information. For example, the strategy priority could be that the MLB function strategy takes precedence over others. Therefore, when the first device receives both the MLB function strategy and the MRO function strategy, it will prioritize the execution of the MLB function strategy, and then proceed with the MRO function strategy.

[0117] In one optional implementation, the first inference strategy further includes inference granularity information, which is used to constrain the type of operation that the network element in the first area needs to perform. Optionally, the inference function is an ES function, and the inference granularity information includes one or more of cell shutdown, carrier shutdown, and time slot shutdown. Optionally, the inference function is an MLB function, and the inference granularity information includes one or more of slice load equalization, cell load equalization, and beam load equalization. Optionally, the inference function is an MRO function, and the inference granularity information includes adjusting beam mobility parameters and / or adjusting cell mobility parameters.

[0118] In one optional implementation, after the first device triggers the inference function, it can cause network elements in the first area to perform operations related to optimizing network performance. For example, after triggering the inference function, the first device obtains a first inference result; that is, the first device uses the AI / ML model corresponding to the inference function to perform inference and obtain the first inference result. The first inference result may include the operations that the network elements in the first area need to perform. The first device can send a second instruction message to the network elements in the first area that need to perform operations. After receiving the second instruction message, the network elements in the first area that need to perform operations perform the corresponding operations to optimize network performance.

[0119] Optionally, the inference function is an ES function, and the operations to be performed by the network element include one or more of cell shutdown, carrier shutdown, and time slot shutdown. Optionally, the inference function is an MLB function, and the operations to be performed by the network element include one or more of slice load balancing, cell load balancing, and beam load balancing. Optionally, the inference function is an MRO function, and the operations to be performed by the network element include adjusting beam mobility parameters and / or adjusting cell mobility parameters. Optionally, the first inference strategy also includes inference granularity information, and the operations to be performed by the network element in the first region of the first inference result belong to the operations included in the inference granularity information.

[0120] In one optional implementation, after a network element in a first area performs an operation related to optimizing network performance, the first device sends a first inference report to a second device. The first inference report reflects the triggering result of the inference function. The first inference report includes the operations performed by the network element in the first area. For example, the first inference report includes multiple information groups, where each information group includes the identifier of a network element in the first area and the operation corresponding to that network element.

[0121] Optionally, the first inference report may also include the time when the network element in the first area performs the operation.

[0122] Optionally, the first inference report may further include a third network performance indicator after the first network element performs an operation in the first area, and / or a fourth network performance indicator after the first area performs an operation in the first area. For example, if the inference function is an ES function, the network element is a base station, and the third network performance indicator includes one or more of base station energy consumption, base station energy efficiency, base station / cell resource utilization, base station / cell uplink / downlink throughput, and base station / cell uplink / downlink throughput, and the fourth network performance indicator includes one or more of regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput. For example, if the inference function is an MLB function, the network element is a base station, and the third network performance indicator includes one or more of base station / cell resource utilization, base station / cell uplink / downlink throughput, and base station / cell uplink / downlink throughput, and the fourth network performance indicator includes one or more of regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput. For example, the inference function is the MRO function, the network element is the base station, and the third network performance indicator includes one or more of the following: base station / cell handover success rate, base station / cell handover failure rate, number of early handovers, number of late handovers, and number of handover errors. The fourth network performance indicator includes one or more of the following: area handover success rate, area handover failure rate, number of early handovers, number of late handovers, and number of handover errors.

[0123] It should be noted that the regional performance index in this application embodiment can be the sum, average, or maximum value of the base station performance indexes of all base stations in the region. For example, if the regional performance index is the regional uplink and downlink throughput, and the base station performance index is the base station uplink and downlink throughput, then the regional uplink and downlink throughput can be the sum, average, or maximum value of the base station uplink and downlink throughput of all base stations in the region.

[0124] Optionally, the first device can further determine whether the third network performance indicator of the first network element and / or the fourth network performance indicator of the first area meet the performance indicator threshold. If the third network performance indicator and / or the fourth network performance indicator do not meet the performance indicator threshold, and the training function is deployed on the second device, the first device can send retraining instruction information to the second device. The retraining instruction information is used to instruct the AI / ML model to be retrained. After receiving the retraining instruction information sent by the first device, the second device can retrain the AI / ML model that implements the inference function according to the retraining instruction information. It should be noted that the retraining instruction information can be sent to the second device along with the first inference report, or it can be sent to the second device as a third instruction message independently of the first inference report. This application embodiment does not limit this. The performance indicator threshold can be a default setting in the first device, or it can be sent by the second device to the first device. This application embodiment does not limit this.

[0125] If the training function is deployed on other devices, the first device can send retraining instructions directly to the other devices, thereby instructing the other devices to retrain the AI / ML model that implements the inference function.

[0126] In summary, in this embodiment, the inference function can be an ES function, an MLB function, or an MRO function, etc. Considering that the inference function corresponds to different network optimization needs, this embodiment can set the first threshold and / or the second threshold in the first inference strategy according to different network optimization needs when configuring the first inference strategy. This allows the first device to trigger the inference function when the network performance of a single network element (i.e., local network performance) and / or the network performance of the area where the single network element is located (i.e., overall network performance) fails to meet the network optimization needs, thereby optimizing network performance. Because the first inference strategy has flexible configuration, this embodiment can meet continuously improving network optimization needs. Furthermore, in this embodiment, the first device can focus on triggering the inference function based on the local network performance and / or the overall network performance of the area, thereby improving the stability of network performance.

[0127] In addition, the embodiments of this application can further enhance the flexibility of the strategy configuration of the first inference strategy by configuring one or more of the regional range information, strategy priority information and inference granularity information into the first inference strategy, thereby meeting the network optimization requirements with regional restrictions and / or inference function type priority restrictions and / or operation type restrictions, and thus optimizing network performance more finely.

[0128] Furthermore, in this embodiment, after the first device triggers the inference function, it can also send a first inference report to the second device so that the second device can obtain the triggering result of the inference function, which is beneficial to optimize the inference model corresponding to the inference function, thereby further improving the optimization effect of network performance.

[0129] The following description, in conjunction with Figure 1 and specific application scenarios, provides an exemplary illustration of the embodiment shown in Figure 2.

[0130] Application Scenario 1: The network element is a base station, the first device is a D-MnF entity, the second device is a CD-MnF entity, and the inference function is the ES function.

[0131] For clarity, please refer to Figure 3. Figure 3 is a flowchart illustrating another policy configuration management method provided in this application embodiment. This method can be implemented based on the architecture shown in Figure 1, or on other architectures. The method includes, but is not limited to, the following steps:

[0132] Step S301: The CD-MnF entity sends the first inference strategy to the D-MnF entity.

[0133] The first inference strategy includes at least a first threshold and / or a second threshold. Optionally, the CD-MnF entity sends a first instantiation request and a first inference strategy to the D-MnF entity. After receiving the first instantiation request, the D-MnF entity creates a first inference strategy object instance and populates the first inference strategy object instance with the received first inference strategy. Optionally, the first inference strategy may also include a first target value and / or a second target value.

[0134] For an explanation of step S301, please refer to the description of the corresponding part in step S201 of the embodiment shown in FIG2, which will not be repeated here.

[0135] Step S302: The first base station sends the first energy consumption to the D-MnF entity.

[0136] Step S303: The second base station sends the second energy consumption to the D-MnF entity.

[0137] Step S304: The third base station sends the third energy consumption to the D-MnF entity.

[0138] Specifically, in steps S301 to S304, the area where the first base station, the second base station, and the third base station are located is the first area. For an explanation of the first area, please refer to the explanation of the first area in the embodiment shown in Figure 2; it will not be repeated here. It can be understood that the first energy consumption is the base station energy consumption of the first base station before the ES function is triggered, the second energy consumption is the base station energy consumption of the second base station before the ES function is triggered, and the third energy consumption is the base station energy consumption of the third base station before the ES function is triggered.

[0139] It should be noted that the order of steps S301 to S304 is not strictly limited in the embodiments of this application.

[0140] Step S305: The D-MnF entity determines the first average energy consumption of the first region.

[0141] Specifically, the D-MnF entity uses the average of the first energy consumption, the second energy consumption, and the third energy consumption as the first average energy consumption of the first region. This can be understood as the region's average energy consumption of the first base station before the ES function is triggered.

[0142] Step S306: The D-MnF entity triggers the ES function according to the first inference strategy.

[0143] The D-MnF entity triggers the ES function when the energy consumption of any one of the first, second, and third base stations exceeds the first threshold in the first inference strategy, and / or when the average energy consumption of the first region exceeds the second threshold.

[0144] Step S307: The D-MnF entity generates the first inference result.

[0145] After triggering the ES function, the D-MnF entity generates a first inference result, which includes at least the ES operation to be performed by each base station in the first area. Optionally, after triggering the ES function, the D-MnF entity performs inference based on a first target value and / or a second target value to generate the first inference result. Optionally, the D-MnF entity can send a first indication message to each base station in the first area according to the first inference result to instruct the base station to perform the corresponding ES operation.

[0146] Step S308: The first base station performs the first ES operation.

[0147] Step S309: The second base station performs the second ES operation.

[0148] Step S310: The third base station performs the third ES operation.

[0149] In steps S308 to S310, the first base station, the second base station, and the third base station respectively perform the corresponding ES operations. It should be noted that the order of steps S308 to S310 is not strictly limited in this embodiment.

[0150] Step S311 (optional): The first base station sends the fourth energy consumption to the D-MnF entity.

[0151] Step S312 (optional): The second base station sends the fifth energy consumption to the D-MnF entity.

[0152] Step S313 (optional): The third base station sends the sixth energy consumption to the D-MnF entity.

[0153] In steps S311 to S313, after the first base station, the second base station, and the third base station complete their respective ES operations, they send their corresponding base station energy consumption data to the D-MnF entity. It can be understood that the fourth energy consumption is the base station energy consumption of the first base station after completing the first ES operation, the fifth energy consumption is the base station energy consumption of the second base station after completing the second ES operation, and the sixth energy consumption is the base station energy consumption of the third base station after completing the third ES operation.

[0154] In an optional embodiment, the D-MnF entity may also use the average of the fourth, fifth, and sixth energy consumptions as the second average energy consumption of the first region. It is understood that the second average energy consumption is the region-wide average energy consumption after each base station in the first region has performed its corresponding ES operation.

[0155] In one optional embodiment, after the first base station, the second base station, and the third base station have completed their respective ES operations, they may also send other network performance indicators to the D-MnF entity, such as one or more of the following: base station energy efficiency, base station resource utilization, uplink and downlink throughput of the base station and / or cell, and uplink and downlink throughput of the base station and / or cell.

[0156] It should be noted that the order of steps S301 to S304 is not strictly limited in the embodiments of this application.

[0157] Step S314: The D-MnF entity generates the first inference report.

[0158] The first inference report includes at least the ES operations performed by the base station in the first region. Optionally, the D-MnF entity can create a first inference report object instance, populate the first inference report object instance with the generated first inference report, and associate the first inference report object instance with a first inference policy object instance.

[0159] Step S315: The D-MnF entity sends the first inference report to the CD-MnF entity.

[0160] It should be noted that the order of steps S308 to S313 and step S314 is not strictly limited in this embodiment. It is understood that steps S308 to S313 may occur between steps S307 and S314, or after step S314, or simultaneously with step S314. For a detailed explanation of steps S306 to S315, please refer to the description of the corresponding part in step S202 of the embodiment shown in Figure 2. Furthermore, the beneficial effects of the embodiment shown in Figure 3 can be found in the beneficial effects of the embodiment shown in Figure 2, and will not be repeated here.

[0161] Application Scenario 2: The network element is a base station, the first device is the first base station, the second device is a CD-MnF entity, and the inference function is the MLB function.

[0162] For clarity, please refer to Figure 4. Figure 4 is a flowchart illustrating another policy configuration management method provided in this application embodiment. This method can be implemented based on the architecture shown in Figure 1, or on other architectures. The method includes, but is not limited to, the following steps:

[0163] Step S401: The CD-MnF entity sends the first inference strategy to the D-MnF entity.

[0164] The first inference strategy includes at least a first threshold and / or a second threshold. Optionally, the CD-MnF entity sends a first instantiation request and a first inference strategy to the D-MnF entity. After receiving the first instantiation request, the D-MnF entity creates a first inference strategy object instance and populates the received first inference strategy into the first inference strategy object instance. Optionally, the first inference strategy may also include a first target value and / or a second target value.

[0165] Step S402: The D-MnF entity sends the first inference strategy to the first base station.

[0166] For an explanation of steps S401 and S402, please refer to the description of the corresponding part in step S201 of the embodiment shown in FIG2, which will not be repeated here.

[0167] Step S403: The first base station determines the first resource utilization rate.

[0168] Step S404: The second base station sends the second resource utilization rate to the first base station.

[0169] Step S405: The third base station sends the third resource utilization rate to the first base station.

[0170] Specifically, in steps S402 to S405, the area where the first base station, the second base station, and the third base station are located is the first area. For an explanation of the first area, please refer to the explanation of the first area in the embodiment shown in Figure 2; it will not be repeated here. It can be understood that the first resource utilization rate is the base station resource utilization rate of the first base station before the MLB function is triggered, the second resource utilization rate is the base station resource utilization rate of the second base station before the MLB function is triggered, and the third resource utilization rate is the base station resource utilization rate of the third base station before the MLB function is triggered.

[0171] It should be noted that the order of steps S401 to S405 is not strictly limited in the embodiments of this application.

[0172] Step S406: The first base station determines the first average resource utilization rate of the first area.

[0173] Specifically, the first base station uses the average of the first resource utilization rate, the second resource utilization rate, and the third resource utilization rate as the first average resource utilization rate of the first area. This can be understood as the average resource utilization rate of the first area before the ES function is triggered.

[0174] Step S407: The first base station triggers the MLB function according to the first inference strategy.

[0175] If the resource utilization rate of the first base station is lower than the first threshold in the first inference strategy when any one of the first utilization rate, second utilization rate and third utilization rate is lower than the second threshold, and / or if the first average resource utilization rate is lower than the second threshold, the MLB function is triggered.

[0176] Step S408: The first base station generates the first inference result.

[0177] After the first base station triggers the MLB function, it generates a first inference result, which includes at least the MLB operations that each base station in the first area needs to perform. Optionally, after triggering the MLB function, the first base station performs inference based on a first target value and / or a second target value to generate the first inference result. Optionally, the first base station can send a first indication message to each base station in the first area according to the first inference result to instruct the base station to perform the corresponding MLB operation.

[0178] Step S409: The first base station performs the first MLB operation.

[0179] Step S410: The second base station performs the second MLB operation.

[0180] Step S411: The third base station performs the third MLB operation.

[0181] In steps S409 to S411, the first base station, the second base station, and the third base station respectively perform the corresponding MLB operations. It should be noted that the order of steps S409 to S411 is not strictly limited in this embodiment of the application.

[0182] Step S412 (optional): The first base station determines the fourth resource utilization rate.

[0183] It is understandable that the fourth resource utilization rate is the base station resource utilization rate after the first base station has completed the first MLB operation.

[0184] Step S413 (optional): The second base station sends the fifth resource utilization rate to the first base station.

[0185] Step S414 (optional): The third base station sends the sixth resource utilization rate to the first base station.

[0186] In steps S413 and S414, after the second and third base stations complete their respective MLB operations, they send the corresponding resource utilization rates to the first base station. It can be understood that the fifth resource utilization rate is the base station resource utilization rate after the second base station completes the second MLB operation, and the third resource utilization rate is the base station resource utilization rate after the third base station completes the third MLB operation.

[0187] In an optional embodiment, the D-MnF entity may also use the average of the fourth, fifth, and sixth resource utilization rates as the second average resource utilization rate of the first region. It is understood that the second resource utilization rate is the region average resource utilization rate after each base station in the first region has performed its corresponding ES operation.

[0188] In one optional embodiment, after the first base station, the second base station, and the third base station have completed their respective ES operations, they may also send other corresponding network performance indicators to the D-MnF entity, such as one or more of the following: resource utilization of the base station and / or cell, uplink and downlink throughput of the base station and / or cell, and uplink and downlink throughput of the base station and / or cell.

[0189] It should be noted that the order of steps S412 to S414 is not strictly limited in the embodiments of this application.

[0190] Step S415: The first base station generates the first inference report.

[0191] The first inference report includes at least the MLB operations performed by the base station in the first region.

[0192] Step S416: The first base station sends a first inference report to the D-MnF entity.

[0193] Optionally, the D-MnF entity can create a first inference report object instance, populate the first inference report object instance with the generated first inference report, and associate the first inference report object instance with the first inference strategy object instance.

[0194] Step S417: The D-MnF entity sends the first inference report to the CD-MnF entity.

[0195] It should be noted that the order of steps S409 to S414 and step S415 is not strictly limited in this embodiment. It is understood that steps S409 to S414 can occur between steps S408 and S415, after step S415, or simultaneously with step S415. For a detailed explanation of steps S409 to S417, please refer to the description of the corresponding part in step S202 of the embodiment shown in Figure 2. Furthermore, the beneficial effects of the embodiment shown in Figure 4 can be found in the beneficial effects of the embodiment shown in Figure 2, and will not be repeated here.

[0196] Furthermore, please refer to Figure 5, which is a schematic diagram of the architecture of another management service system provided in this application embodiment. As shown in Figure 5, the RAN management service system 50 includes an operation and maintenance system 501 and multiple network elements. The operation and maintenance system 501 includes a management and orchestration platform 5011 and an operation and maintenance unit 5012. The management and orchestration platform 5011 includes a management and orchestration unit 5013, a training unit 5014, and a storage unit 5015. The operation and maintenance unit 5012 stores at least one operation and maintenance application (APP), such as an operation and maintenance APP 5016. This application embodiment does not strictly limit the number of operation and maintenance APPs and network elements; the numbers shown in Figure 5 are merely examples.

[0197] AI / ML functions can be deployed in the RAN management service system 50. These functions include training, testing, simulation, and inference. For example, the training, testing, and simulation functions can all be deployed in the management and orchestration platform 5011, while the inference function can be deployed in the operation and maintenance application of the operation and maintenance unit 5012.

[0198] Specifically, the management and orchestration platform 5011 provides management and orchestration of ML models. It also provides a management interface to the operations and maintenance app in the operations and maintenance unit 5012, enabling ML model registration and discovery, and managing ML model loading. Specifically, the management and orchestration unit 5013 configures inference strategies that can trigger ML models to perform inference, the training unit 5014 trains ML models, and the storage unit 5015 stores ML models.

[0199] The 5016 operation and maintenance APP can be of two types: network operation APP and service operation APP. It is used to provide specific management functions for network operation and maintenance, such as network construction management functions, network optimization management functions, network maintenance management functions, service provisioning management functions, and service assurance management functions.

[0200] Network elements 502 to 504 are located in the same area and can all be managed by the operation and maintenance APP 5016. Multiple network elements in the same area can communicate wirelessly. For an explanation of the network elements, please refer to the description of the network elements in the embodiment shown in Figure 1, which will not be repeated here.

[0201] Similar to the RAN management service system 10 shown in Figure 1, an inference function unit (such as the operation and maintenance unit 5012) is deployed. It can accept inference policies sent by the unit (such as the management and orchestration unit 5013) for configuring inference policies, and can trigger inference functions, such as ES function, MLB function and MRO function, based on the policy configuration of the inference policy, thereby optimizing network performance.

[0202] Therefore, it is understood that the method embodiment shown in Figure 2 can also be implemented based on the architecture shown in Figure 5. For example, when the method embodiment shown in Figure 2 is implemented based on the architecture shown in Figure 5, the first device is the entity corresponding to the operation and maintenance unit 5012 shown in Figure 5 (hereinafter referred to as the operation and maintenance entity for ease of description), and the second device is the entity corresponding to the management and orchestration unit 5013 shown in Figure 5 (hereinafter referred to as the management and orchestration entity for ease of description).

[0203] For clarity and exemplification, please refer to Figure 6, which is a flowchart illustrating another policy configuration management method provided in an embodiment of this application. The method includes:

[0204] Step S601: The management and orchestration entity sends the first inference policy to the operations entity.

[0205] Specifically, the management and orchestration entity sends the first inference policy to the operations and maintenance application within the operations and maintenance entity. The management and orchestration entity belongs to the management and orchestration platform, which also includes a training entity and a storage entity, used for training and storing ML models, respectively.

[0206] Step S602: The operation and maintenance entity triggers the reasoning function according to the first reasoning strategy.

[0207] Specifically, the operation and maintenance APP in the operation and maintenance entity triggers the reasoning function according to the first reasoning strategy.

[0208] Step S603: The operations entity sends the first inference report to the management and orchestration entity.

[0209] Specifically, the operations and maintenance app in the operations and maintenance entity sends the first inference report to the management and orchestration entity.

[0210] Step S604: The operation and maintenance entity sends a retraining instruction message to the training entity.

[0211] Specifically, the operations and maintenance (O&M) app within the O&M entity sends a retraining instruction message to the training entity. This retraining instruction message instructs the first device to retrain the AI / ML model that implements the inference function.

[0212] It should be noted that for a detailed explanation of step S601, please refer to the description of the corresponding part in step S201 in the embodiment shown in Figure 2. For a detailed explanation of steps S602 to S604, please refer to the description of the corresponding part in step S202 in the embodiment shown in Figure 2. Furthermore, the beneficial effects of the embodiment shown in Figure 6 can be found in the beneficial effects of the embodiment shown in Figure 2, and will not be repeated here.

[0213] The following describes the communication device provided in the embodiments of this application.

[0214] Figure 7 is a schematic diagram of a communication device provided in an embodiment of this application. As shown in Figure 7, the communication device 70 includes a processing module 701 and a transceiver module 702. The transceiver module 702 can implement corresponding communication functions, and the processing module 701 is used for data processing. The transceiver module 702 can also be referred to as an interface, a communication interface, or a communication module, etc.

[0215] In some embodiments of this application, the communication device can be used to perform the actions performed by the first or second device in the above method embodiments. The transceiver module 702 is used to perform transceiver-related operations performed by the first or second device in the above method embodiments. For example, the transmitting end can be the device itself or a chip or functional module configurable in the device. The processing module 701 is used to perform processing-related operations performed by the first or second device in the above method embodiments. The processing module 701 can perform corresponding operations by calling a computer program or by performing corresponding operations through corresponding hardware circuits. The transceiver module 702 can perform transceiver operations independently or under the control of the processing module 701.

[0216] For example, the communication device 70 shown in FIG7 can be the first device or a component in the first device in the above method embodiment. The processing module 701 and the transceiver module 702 in the communication device 70 can respectively perform the following operations:

[0217] The transceiver module 702 is used to receive a first inference strategy from a second device, wherein the first inference strategy includes a first threshold and / or a second threshold, the first threshold is used to trigger the inference function when the first network performance indicator of the first network element does not meet the first threshold, and the second threshold is used to trigger the inference function when the second network performance indicator of the first region does not meet the second threshold, wherein the first region is the region where the first network element is located.

[0218] The processing module 701 is used to trigger the reasoning function according to the first reasoning strategy.

[0219] In one alternative implementation, the first inference strategy further includes regional scope information, which includes a list of network element identifiers, a list of cell identifiers, or a list of latitude and longitude information.

[0220] In one alternative implementation, the first inference strategy further includes strategy type information, which indicates the type of inference function, namely, energy saving (ES) function, mobile load balancing (MLB) function, and mobile robust optimization (MRO) function.

[0221] In one alternative implementation, the first inference strategy also includes strategy priority information, which is used to indicate the importance level of the inference function.

[0222] In one alternative implementation, the first inference strategy also includes inference granularity information;

[0223] The inference function is an ES function, and the inference granularity information includes one or more of the following: shut-off cell, shut-off carrier, and shut-off time slot;

[0224] Alternatively, the inference function is an MLB function, and the inference granularity information includes one or more of the following: equalized slice load, equalized cell load, and equalized beam load.

[0225] Alternatively, the inference function is an MRO function, and the inference granularity information includes adjusting the mobility parameters of the beam and / or adjusting the mobility parameters of the cell.

[0226] In one optional implementation, the inference function is the ES function, the first network performance indicator is the network element energy consumption, and the second network performance indicator is the regional energy consumption, which is the average energy consumption, total energy consumption, or maximum energy consumption of all network elements in the region.

[0227] Alternatively, the inference function is the MLB function, the first network performance indicator is the network element resource utilization rate, the second network performance indicator is the regional resource utilization rate, and the regional resource utilization rate is the average resource utilization rate, total resource utilization rate, or highest resource utilization rate of all network elements in the region.

[0228] Alternatively, the inference function is the MRO function, the first network performance indicator is the number of successful network element handover requests, the second network performance indicator is the number of successful area handover requests, and the number of successful area handover requests is the average number of successful handover requests for all network elements in the area, the total number of successful handover requests in the area, or the highest number of successful handover requests in the area.

[0229] In one alternative implementation:

[0230] The transceiver module 702 is used to send a first inference report to the second device, wherein the first inference report includes the operations performed by the network element in the first area.

[0231] In one alternative implementation, the first inference report also includes the time when the network element in the first area performs the operation.

[0232] In one alternative implementation, the first network element is any network element in the first region, and the first inference report also includes a third network performance indicator after the first network element performs an operation in the network elements in the first region, and a fourth network performance indicator after the first region performs an operation in the network elements in the first region.

[0233] In one optional implementation, the inference function is the ES function, and the third network performance indicator includes one or more of the following: network element energy consumption, network element energy efficiency, network element resource utilization, cell resource utilization, network element uplink / downlink throughput, cell uplink / downlink throughput, network element uplink / downlink throughput, and cell uplink / downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput.

[0234] Alternatively, the inference function is the MLB function, and the third network performance indicator includes one or more of the following: network element resource utilization, cell resource utilization, network element uplink / downlink throughput, cell uplink / downlink throughput, network element uplink / downlink throughput, and cell uplink / downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput.

[0235] Alternatively, the inference function is the MRO function, and the third network performance indicator includes one or more of the following: network element handover success rate, cell handover success rate, network element handover failure rate, cell handover failure rate, number of network element handovers that are too early, number of cell handovers that are too early and fail, number of network element handovers that are too late, number of cell handovers that are too late, number of network element handovers with incorrect cells, and number of cell handover errors. The fourth network performance indicator includes one or more of the following: area handover success rate, area handover failure rate, number of area handovers that are too early, number of area handovers that are too late, and number of area handovers with incorrect cells.

[0236] Reusing Figure 7, in some other embodiments of this application, for example, the communication device 70 shown in Figure 7 can be a second device or a component in a second device in the method embodiments described above. The processing module 701 and the transceiver module 702 in this communication device can respectively perform the following operations:

[0237] The processing module 701 is used to configure a first inference strategy, wherein the first inference strategy includes a first threshold and / or a second threshold. The first threshold is used to trigger the inference function when the first network performance indicator of the first network element does not meet the first threshold, and the second threshold is used to trigger the inference function when the second network performance indicator of the first region does not meet the second threshold. The first region is the region where the first network element is located.

[0238] The transceiver module 702 is used to send a first inference strategy to the first device, wherein the first inference strategy is used to trigger the inference function.

[0239] In one alternative implementation, the first inference strategy further includes regional scope information, which includes a list of network element identifiers, a list of cell identifiers, or a list of latitude and longitude information.

[0240] In one alternative implementation, the first inference strategy further includes strategy type information, which indicates the type of inference function, namely, energy saving (ES) function, mobile load balancing (MLB) function, and mobile robust optimization (MRO) function.

[0241] In one alternative implementation, the first inference strategy also includes strategy priority information, which is used to indicate the importance level of the inference function.

[0242] In one alternative implementation, the first inference strategy also includes inference granularity information;

[0243] The inference function is an ES function, and the inference granularity information includes one or more of the following: shut-off cell, shut-off carrier, and shut-off time slot;

[0244] Alternatively, the inference function is an MLB function, and the inference granularity information includes one or more of the following: equalized slice load, equalized cell load, and equalized beam load.

[0245] Alternatively, the inference function is an MRO function, and the inference granularity information includes adjusting the mobility parameters of the beam and / or adjusting the mobility parameters of the cell.

[0246] In one optional implementation, the inference function is the ES function, the first network performance indicator is the network element energy consumption, and the second network performance indicator is the regional energy consumption, which is the average energy consumption, total energy consumption, or maximum energy consumption of all network elements in the region.

[0247] Alternatively, the inference function is the MLB function, the first network performance indicator is the network element resource utilization rate, and the second network performance indicator is the regional resource utilization rate. The regional resource utilization rate is the average resource utilization rate, total resource utilization rate, or highest resource utilization rate of all network elements in the region.

[0248] Alternatively, the inference function is the MRO function, the first network performance indicator is the number of successful network element handover requests, the second network performance indicator is the number of successful area handover requests, and the number of successful area handover requests is the average number of successful handover requests for all network elements in the area, the total number of successful handover requests in the area, or the highest number of successful handover requests in the area.

[0249] In another alternative implementation:

[0250] The transceiver module 702 is used to receive a first inference report from a first device, wherein the first inference report includes operations performed by the network element in the first area.

[0251] In another alternative implementation, the first inference report also includes the time when the network element in the first area performs the operation.

[0252] In another alternative implementation, the first network element is any network element in the first region, and the first inference report also includes a third network performance indicator after the first network element performs an operation on the network elements in the first region, and a fourth network performance indicator after the first region performs an operation on the network elements in the first region.

[0253] In another alternative implementation, the inference function is the ES function, and the third network performance indicator includes one or more of the following: network element energy consumption, network element energy efficiency, network element resource utilization, cell resource utilization, network element uplink / downlink throughput, cell uplink / downlink throughput, network element uplink / downlink throughput, and cell uplink / downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput.

[0254] Alternatively, the inference function is the MLB function, and the third network performance indicator includes one or more of the following: network element resource utilization, cell resource utilization, network element uplink / downlink throughput, cell uplink / downlink throughput, network element uplink / downlink throughput, and cell uplink / downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput.

[0255] Alternatively, the inference function is the MRO function, and the third network performance indicator includes one or more of the following: network element handover success rate, cell handover success rate, network element handover failure rate, cell handover failure rate, number of network element handovers that are too early, number of cell handovers that are too early and fail, number of network element handovers that are too late, number of cell handovers that are too late, number of network element handovers with incorrect cells, and number of cell handover errors. The fourth network performance indicator includes one or more of the following: area handover success rate, area handover failure rate, number of area handovers that are too early, number of area handovers that are too late, and number of area handovers with incorrect cells.

[0256] The specific descriptions of the transceiver module 702 and the processing module 701 shown in the above embodiments are merely examples. For the specific functions or execution steps of the transceiver module 702 and the processing module 701, please refer to the above method embodiments, which will not be described in detail here.

[0257] The communication device according to the embodiments of this application has been described above. The possible product forms of the communication device are described below. Any product possessing the functions of the communication device described in FIG7 above falls within the protection scope of the embodiments of this application.

[0258] The following description is merely an example and does not limit the product form of the communication device in the embodiments of this application to this.

[0259] In one possible implementation, in the communication device 70 shown in FIG7, the processing module 701 can be one or more processors, and the transceiver module 702 can be a transceiver, or the transceiver module 702 can also be a transmitting module and a receiving module. The transmitting module can be a transmitter, and the receiving module can be a receiver. The transmitting module and the receiving module are integrated into one device, such as a transceiver. In the embodiments of this application, the processor and the transceiver can be coupled, etc., and the connection method of the processor and the transceiver is not limited in the embodiments of this application. In the process of executing the above method, the process of sending information in the above method can be the process of the processor outputting the above information. When outputting the above information, the processor outputs the above information to the transceiver so that the transceiver can transmit it. After the above information is output by the processor, it may need to undergo other processing before reaching the transceiver. Similarly, the process of receiving information in the above method can be the process of the processor receiving the input above information. When the processor receives the input information, the transceiver receives the above information and inputs it into the processor. Furthermore, after the transceiver receives the above information, the above information may need to undergo other processing before being input into the processor.

[0260] As shown in Figure 8, the communication device 80 includes one or more processors 802 and transceivers 801. Exemplarily, the transceiver 801 is used to execute the functions or steps implemented by the transceiver module 702 shown in Figure 7, and the processor 802 is used to execute the functions or steps implemented by the processing module 701 shown in Figure 7. Detailed descriptions of the processor 802 and transceiver 801 can be found in Figure 7 or the method embodiments shown above, and will not be elaborated further here.

[0261] The descriptions of the relevant steps and information in the above embodiments can be found in the descriptions of the method embodiments above, and will not be detailed here.

[0262] In various implementations of the communication device shown in Figure 8, the transceiver may include a receiver for performing a receiving function (or operation) and a transmitter for performing a transmitting function (or operation). The transceiver is also used to communicate with other devices / appliances via a transmission medium.

[0263] Optionally, the communication device 80 may further include one or more memories 803 for storing program instructions and / or data. The memory 803 is coupled to the processor 802. The coupling in this embodiment is an indirect coupling or communication connection between devices, units, or modules, and can be electrical, mechanical, or other forms, used for information exchange between devices, units, or modules. The processor 802 may operate in conjunction with the memory 803. The processor 802 may execute program instructions stored in the memory 803. Optionally, at least one of the above-mentioned memories may be included in the processor.

[0264] This application embodiment does not limit the specific connection medium between the transceiver 801, processor 802, and memory 803. In Figure 8, the memory 803, processor 802, and transceiver 801 are connected via a bus 804, which is represented by a thick line. The connection methods between other components are for illustrative purposes only and are not intended to be limiting. The bus can be categorized as an address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in Figure 8, but this does not indicate that there is only one bus or one type of bus.

[0265] In the embodiments of this application, the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules within the processor.

[0266] In this application embodiment, the memory may include, but is not limited to, non-volatile memory such as hard disk drive (HDD) or solid-state drive (SSD), random access memory (RAM), erasable programmable read-only memory (EPROM), read-only memory (ROM), or compact disc read-only memory (CD-ROM), etc. Memory is any storage medium capable of carrying or storing program code having instruction or data structure forms, and capable of being read and / or written by a computer (such as the communication device shown in this application), but is not limited to this. The memory in this application embodiment may also be a circuit or any other device capable of implementing storage functions, used to store program instructions and / or data.

[0267] The processor 802 is mainly used to process communication protocols and data, control the entire communication device, execute software programs, and process the data from those programs. The memory 803 is mainly used to store software programs and data. The transceiver 801 may include control circuitry and an antenna. The control circuitry is mainly used for converting baseband signals to radio frequency signals and processing radio frequency signals. The antenna is mainly used for transmitting and receiving radio frequency signals in the form of electromagnetic waves. Input / output devices, such as touchscreens, displays, and keyboards, are mainly used to receive user input data and output data to the user.

[0268] When the communication device is powered on, the processor 802 can read the software program in the memory 803, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 802 performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit processes the baseband signal and transmits the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor 802. The processor 802 converts the baseband signal into data and processes the data.

[0269] In another implementation, the radio frequency circuitry and antenna can be set up independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antenna can be arranged remotely, independent of the communication device.

[0270] The communication device shown in this application embodiment may also have more components than those in Figure 8, and this application embodiment does not limit this. The methods executed by the processor and transceiver shown above are only examples, and the specific steps executed by the processor and transceiver can be referred to the methods described above.

[0271] In another possible implementation, in the communication device shown in Figure 7, the processing module 701 can be one or more logic circuits, and the transceiver module 702 can be an input / output interface, or a communication interface, or an interface circuit, or an interface, etc. Alternatively, the transceiver module 702 can also be a transmitting module and a receiving module. The transmitting module can be an output interface, and the receiving module can be an input interface. The transmitting module and the receiving module are integrated into one module, such as an input / output interface. As shown in Figure 9, the communication device 90 shown in Figure 9 includes a logic circuit 901 and an interface 902. That is, the above-mentioned processing module 701 can be implemented using the logic circuit 901, and the transceiver module 702 can be implemented using the interface 902. Among them, the logic circuit 901 can be a chip, a processing circuit, an integrated circuit, or a system-on-a-chip (SoC) chip, etc., and the interface 902 can be a communication interface, an input / output interface, pins, etc. For example, Figure 9 illustrates the above-mentioned communication device as a chip, which includes a logic circuit 901 and an interface 902.

[0272] In this embodiment, the logic circuit and the interface can also be coupled to each other. The specific connection method of the logic circuit and the interface is not limited in this embodiment. For example, the logic circuit 901 can be used to execute the functions or steps implemented by the processing module 701 shown in FIG. 7, and the interface 902 can be used to execute the functions or steps implemented by the transceiver module 702 shown in FIG. 7. For a detailed description of the logic circuit 901 and the interface 902, please refer to FIG. 7 or the method embodiment shown above, which will not be detailed here.

[0273] The above description of the communication device is only an example. For a detailed description of the communication device shown in Figure 9, please refer to the above method embodiment or Figure 7 or Figure 8. It will not be described in detail here.

[0274] The communication device shown in the embodiments of this application can implement the method provided in the embodiments of this application in hardware form, or it can implement the method provided in the embodiments of this application in software form, etc., and the embodiments of this application do not limit it in this way.

[0275] The descriptions of relevant steps and information in the above embodiments can be found in the method embodiments described above, and will not be detailed here. For the specific implementation methods of the embodiments shown in Figure 9, please also refer to the above embodiments, which will not be detailed here.

[0276] This application also provides a communication system, which includes a first communication device and a second communication device. The first communication device and the second communication device interact with each other. The first communication device is used to perform all or part of the operations of the first device in any of the foregoing method embodiments, and the second communication device is used to perform all or part of the operations of the second device in any of the foregoing method embodiments.

[0277] In addition, this application also provides a computer program for implementing the operations and / or processes performed by various computing resource management devices in the methods provided in this application.

[0278] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform the operations and / or processes performed by various computing resource management devices in the methods provided in this application.

[0279] This application also provides a computer program product comprising computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by various entities in the method provided in this application to be executed.

[0280] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, or it may be an electrical, mechanical, or other form of connection.

[0281] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the technical effects of the solutions provided in the embodiments of this application.

[0282] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0283] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0284] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0285] Furthermore, unless otherwise stated, the use of ordinal numbers such as "first" and "second" in the embodiments of this application is for distinguishing multiple objects, and is not for limiting the order, sequence, priority or importance of multiple objects, such as first inference strategy and first inference report.

[0286] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A strategy configuration management method, characterized in that, Applied to a first device, the method includes: The system receives a first inference policy from a second device, wherein the first inference policy includes a first threshold and / or a second threshold. The first threshold is used to trigger the inference function when the first network performance indicator of the first network element does not meet the first threshold, and the second threshold is used to trigger the inference function when the second network performance indicator of the first region does not meet the second threshold. The first region is the region where the first network element is located. The reasoning function is triggered based on the first reasoning strategy.

2. The method according to claim 1, characterized in that, The first inference strategy also includes regional range information, which includes a list of network element identifiers, a list of cell identifiers, or a list of latitude and longitude information.

3. The method according to claim 1 or 2, characterized in that, The first inference strategy also includes strategy type information, which is used to indicate the type of the inference function. The type of the inference function is one of the following: energy saving (ES) function, mobile load balancing (MLB) function, and mobile robust optimization (MRO) function.

4. The method according to claim 3, characterized in that, The first reasoning strategy also includes strategy priority information, which is used to indicate the importance level of the reasoning function.

5. The method according to any one of claims 1-4, characterized in that, The first inference strategy also includes inference granularity information; The inference function is the ES function, and the inference granularity information includes one or more of the following: cell shutdown, carrier shutdown, and time slot shutdown. Alternatively, the inference function is an MLB function, and the inference granularity information includes one or more of equalized slice load, equalized cell load, and equalized beam load. Alternatively, the inference function is an MRO function, and the inference granularity information includes adjusting the mobility parameters of the beam and / or adjusting the mobility parameters of the cell.

6. The method according to any one of claims 1-5, characterized in that: The inference function is the ES function, the first network performance indicator is the network element energy consumption, the second network performance indicator is the regional energy consumption, and the regional energy consumption is the average energy consumption, total energy consumption, or maximum energy consumption of all network elements in the region. Alternatively, the inference function is an MLB function, the first network performance indicator is the network element resource utilization rate, the second network performance indicator is the regional resource utilization rate, and the regional resource utilization rate is the average resource utilization rate, total resource utilization rate, or highest resource utilization rate of all network elements in the region. Alternatively, the inference function is an MRO function, the first network performance indicator is the number of successful network element handover requests, the second network performance indicator is the number of successful area handover requests, and the number of successful area handover requests is the average number of successful handover requests for all network elements in the area, the total number of successful handover requests in the area, or the highest number of successful handover requests in the area.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: A first inference report is sent to the second device, wherein the first inference report includes the operations performed by the network element in the first area.

8. The method according to claim 7, characterized in that, The first inference report also includes the time when the network element in the first region performs the operation.

9. The method according to claim 7 or 8, characterized in that, The first network element is any network element in the first region. The first inference report also includes a third network performance indicator after the first network element performs an operation in the network elements in the first region, and a fourth network performance indicator after the first region performs an operation in the network elements in the first region.

10. The method according to claim 9, characterized in that: The inference function is the ES function. The third network performance indicator includes one or more of the following: network element energy consumption, network element energy efficiency, network element resource utilization, cell resource utilization, network element uplink and downlink throughput, cell uplink and downlink throughput, network element uplink and downlink throughput, and cell uplink and downlink throughput. The fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink and downlink throughput, and regional uplink and downlink throughput. Alternatively, the inference function is an MLB function, and the third network performance indicator includes one or more of the following: network element resource utilization, cell resource utilization, network element uplink / downlink throughput, cell uplink / downlink throughput, network element uplink / downlink throughput, and cell uplink / downlink throughput; and the fourth network performance indicator includes one or more of the following: regional resource utilization, regional uplink / downlink throughput, and regional uplink / downlink throughput. Alternatively, the inference function is an MRO function, and the third network performance indicator includes one or more of the following: network element handover success rate, cell handover success rate, network element handover failure rate, cell handover failure rate, number of network element handovers that were too early, number of cell handovers that failed too early, number of network element handovers that were too late, number of cell handovers that were too late, number of network element handovers with incorrect cells, and number of cell handover errors. The fourth network performance indicator includes one or more of the following: area handover success rate, area handover failure rate, number of area handovers that were too early, number of area handovers that were too late, and number of area handovers with incorrect cells.

11. The method according to any one of claims 1-10, characterized in that: The first device is a cross-domain management function entity, and the second device is a business support system, or... The first device is a domain management function entity, and the second device is a cross-domain management function entity, or... The first device is one or more network elements in the first region, and the second device is a cross-domain management function entity.

12. A strategy configuration management method, characterized in that, Applied to a second device, the method includes: Configure a first inference strategy, wherein the first inference strategy includes a first threshold and / or a second threshold, the first threshold is used to trigger the inference function when the first network performance indicator of the first network element does not meet the first threshold, and the second threshold is used to trigger the inference function when the second network performance indicator of the first region does not meet the second threshold, wherein the first region is the region where the first network element is located; The first inference strategy is sent to the first device, wherein the first inference strategy is used to trigger the inference function.

13. The method according to claim 12, characterized in that, The method further includes receiving a first inference report from the first device, wherein the first inference report includes operations performed by the network element in the first area.

14. The method according to claim 13, characterized in that, The first inference report also includes the time when the network element in the first region performs the operation.

15. The method according to any one of claims 12-14, characterized in that, The first network element is any network element in the first region. The first inference report also includes a third network performance indicator after the first network element performs an operation in the network elements in the first region, and a fourth network performance indicator after the first region performs an operation in the network elements in the first region.

16. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 1-11; or, the communication device includes a processor for performing the method as described in any one of claims 1-11.

17. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 12-15; or, the communication device includes a processor for performing the method as described in any one of claims 12-15.

18. A communication device, characterized in that, Includes logic circuits and interfaces, wherein the logic circuits and interfaces are coupled; The interface is used for inputting and / or outputting information, and the logic circuit is used for performing the method as described in any one of claims 1-15.

19. A communication system, characterized in that, The communication system includes a first communication device and a second communication device, wherein the first communication device is used to perform the method as described in any one of claims 1-11, and the second communication device is used to perform the method as described in any one of claims 12-15.

20. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, which, when executed, performs the method as described in any one of claims 1-15.

Images