WO2023143371A1

WO2023143371A1 - Communication method and apparatus

Info

Publication number: WO2023143371A1
Application number: PCT/CN2023/073147
Authority: WO
Inventors: 石小丽; 许瑞岳; 邹兰
Original assignee: 华为技术有限公司
Priority date: 2022-01-30
Filing date: 2023-01-19
Publication date: 2023-08-03
Also published as: CN116567649A

Abstract

Embodiments of the present application provide a communication method. A first management entity is used as a management service producer; a second management entity is used as a management service consumer; required feedback information is determined by the first management entity or the second management entity; and the second management entity verifies, according to the determined feedback information, a management data analysis (MDA) report and/or a machine learning (ML) training report generated by the first management entity and generates a feedback report. The feedback report is used for accurately feeding back a specific scene and feedback information of the MDA report and/or the ML training report, such that MDA or ML training is ensured to be more accurate, and the requirements of operators are met.

Description

A communication method and device

This application claims the priority of the Chinese patent application with the application number 202210113450.6 and the application title “A Communication Method and Device” filed with the China Patent Office on January 30, 2022, the entire contents of which are incorporated in this application by reference.

technical field

The embodiments of the present application relate to the communication field, and more specifically, to a communication method and device.

Background technique

Management data analytics (MDA) can provide processing and analysis-related reports for network and service operations, so as to realize the normal operation of network and service operations. In network service management, MDA can help perform management tasks in the preparation, commissioning, operation and termination phases. For example, in the preparation phase, MDA can support service provisioning by preparing service catalogs, assessing network requirements for new services, and conducting feasibility checks. ;During the operational phase, MDA can identify ongoing issues affecting network and service performance and spot potential issues early that could lead to potential failures and/or performance degradation; MDA can also help predict network and service needs to enable timely resource provisioning and Deployment for rapid network and service deployment.

In the existing technology, MDA can be combined with artificial intelligence (machine learning, ML) and machine learning technology to realize the intelligentization of network service management and coordination. For example, MDA can include ML model training process and management data analysis process. The MDA management service producer will provide the trained ML model and the ML training report to the MDA management service consumer; the MDA management service producer will pass the trained ML model Analyze data and provide MDA reports to MDA management service consumers, MDA management service consumers can verify MDA reports and ML training reports, and provide report verification feedback to MDA management service producers.

Therefore, there is an urgent need for a communication method for reporting verification feedback for different application scenarios, so as to ensure more accurate MDA analysis or ML training and meet the needs of operators.

Contents of the invention

The embodiments of the present application provide a communication method and device, which can realize accurate feedback on report verification for different application scenarios, so as to ensure more accurate MDA analysis or ML training and meet the needs of operators.

In a first aspect, a communication method is provided, the method includes: a first management entity sends first information, and the first information is used for a second management entity to perform verification of an MDA report and/or a ML training report and generate a first Feedback report: the first management entity receives the first feedback report, and the first feedback report is used to give feedback on the verification of the MDA report and/or ML training report.

In this application, the first management entity acts as a management service producer, and the second management entity acts as a management service consumer.

In this application, the first management entity may generate the MDA report and the ML training report.

In this application, the second management entity can verify the MDA report and the ML training report and obtain feedback from the MDA report and the ML training report.

Based on the above technical solution, the first management entity can send the first information to the second management entity for the second management entity to give feedback on the MDA report and/or ML report of the first management entity, so that a feedback report can be generated in a targeted manner Further, a feedback report can also be generated for a specific scene, so that the MDA function can analyze the specific scene more accurately, and output a more accurate analysis result for use by the operator.

In a possible implementation manner, the first information includes first feedback information, where the first feedback information is information that is determined by the first management entity and needs to be fed back by the second management entity.

In this application, the first feedback information may be understood as information that the first management entity expects to be fed back by the second management entity.

In a possible implementation manner, the first feedback information includes information that the first management entity performs MDA analysis and/or ML training.

Based on the above technical solution, the report is fed back to the feedback information required by the first management entity, thereby improving the accuracy of MDA analysis and the speed of ML model training by the first management entity.

In a possible implementation manner, the first information is the MDA report and/or the ML training report generated by the first management entity.

Based on the above technical solution, the first management entity carries the first information when sending the MDA report and/or the ML training report, which helps to save signaling overhead and improve the transmission rate.

In a possible implementation manner, the sending of the first information by the first management entity includes: the first management entity receives a first request message, the first request message includes second feedback information, and the second The feedback information is the information determined by the second management entity that needs to be fed back; the first management entity sends the first information according to the first request message.

In a possible implementation manner, the second feedback information may be understood as information determined by the second management entity that the first management entity performs MDA analysis and/or ML training.

Based on the above technical solution, the second management entity determines the feedback information and requests the first management entity for confirmation, so that the MDA function can more accurately analyze specific scenarios and output more accurate analysis results for operators to use.

In a possible implementation manner, the first request message may be a feedback request message or a feedback notification message, for example, the first request message is a Feedback request operation or a feedback notification operation.

It should be noted that the feedback request message may be sent through an existing operation or notification, or through a newly defined operation or notification message, which is not limited in this application.

In a possible implementation manner, the first request message is feedback instance request information, and the feedback instance request information is used to request the first management entity to create a feedback instance.

For example, the first request message may be a create MDAFeedback IOC Request operation.

It should be noted that the feedback instance request message may be sent through an existing operation or a newly defined operation, which is not limited in this application.

Based on the above technical solution, the second management entity carries the feedback information confirmed by itself through the feedback instance object, which is beneficial to save signaling overhead.

In a possible implementation manner, before the first management entity sends the first information according to the first request message, the first management entity creates the feedback instance.

Based on the above technical solution, the first management entity creates a feedback instance object to confirm the feedback information determined by the second management entity, which is beneficial to save signaling overhead.

In a possible implementation manner, the first information is a first response message of the first request message.

For example, when the first request message is a feedback instance request information, the response message may be a create MDAFeedback IOC Response operation; when the first request message is a feedback request message or a feedback notification message, the response message may be a feedback response operation .

Based on the above technical solution, the first management entity responds to the feedback information requested by the second management entity for confirmation, so as to be used by the second management entity for feedback of the MDA report and/or the ML training report.

In a possible implementation manner, the first management entity sends the first feedback information.

Based on the above technical solution, the first management entity can also send the feedback information confirmed by itself to the second management entity, which is used for the second management entity to more accurately determine the information that needs to be fed back, which greatly improves the efficiency of MDA analysis or ML training. Accuracy, to meet the needs of operators.

In a possible implementation manner, the first feedback information or the second feedback information includes at least one of a feedback type, a feedback range, and a feedback state, where the feedback type includes an MDA type and/or ML training type, the feedback range includes the time accuracy of the feedback, and the feedback status includes the status of the MDA report and/or ML report.

Based on the above technical solution, the feedback information determined by the first management entity or the second management entity can include any information that needs to be fed back, so that the feedback of the second management entity to the report can support specific feedback information and feedback of specific scenarios, greatly improving It improves the accuracy of MDA analysis or ML training and meets the needs of operators.

In a possible implementation manner, the feedback type includes MDA type and/or ML training type, and the MDA type includes coverage problem analysis type, slice coverage problem analysis type, paging optimization analysis type, fault analysis type, fault One or more of predictive analysis types, end-to-end delay analysis types, energy-saving analysis types, mobility analysis types, network slice load analysis types, network slice throughput analysis types, KPI abnormal analysis types, and software upgrade analysis types , the ML training type includes a coverage problem analysis model training type, a slice coverage problem analysis model training type, a paging optimization analysis model training type, a fault analysis model training type, a fault prediction analysis model training type, and an end-to-end delay analysis model One of training type, energy saving analysis model training type, mobility analysis model training type, network slice load analysis model training type, network slice throughput analysis model training type, KPI anomaly analysis model training type, and software upgrade analysis model training type or more.

In a possible implementation manner, the feedback range includes a feedback accuracy and a suggested measure, the feedback accuracy includes a feedback period accuracy and/or time accuracy, and the suggested measure includes a data source measure.

In a possible implementation manner, the status of the feedback includes whether the MDA report is corrected or not corrected based on the feedback, or whether the ML training report is corrected or not corrected based on the feedback.

In a possible implementation manner, the first feedback report includes a first-type report and a second-type report, and the first-type report includes a feedback report type, a feedback report status, a feedback report accuracy, a feedback report timestamp and At least one of feedback report suggestions, the second type of report includes at least one of coverage problem analysis, failure event analysis, mobility management analysis, KPI anomaly analysis, and energy saving analysis.

In a possible implementation manner, the first feedback information is the same as the second feedback information.

In a second aspect, a communication method is provided, the method includes: a second management entity receives first information; the second management entity performs verification of the MDA report and/or ML training report and generates a first feedback report; the The second management entity sends the first feedback report, where the first feedback report is used to give feedback on the verification of the MDA report and/or the ML training report.

Based on the above technical solution, the second management entity may base the first management entity on the basis of the predetermined first information MDA report and/or ML report provide feedback, so that feedback reports can be generated in a targeted manner, and further, feedback reports can also be generated for specific scenarios, so that the MDA function can more accurately analyze specific scenarios and output more accurate analysis The result is used by the operator.

Based on the above technical solution, the second management entity feeds back the report according to the feedback information required by the first management entity, thereby improving the accuracy of MDA analysis and the speed of ML model training by the first management entity.

Based on the above technical solution, the second management entity receives the first information when receiving the MDA report and/or the ML training report, which helps to save signaling overhead and improve the transmission rate.

In a possible implementation manner, the receiving the first information by the second management entity includes: the second management entity determines second feedback information, and the second feedback information is a demand determined by the second management entity. Feedback information; the second management entity sends a first request message, and the first request message includes second feedback information; the second management entity receives the first information.

In a possible implementation manner, the second feedback information includes information determined by the second management entity that the first management entity performs MDA analysis and/or ML training.

It should be noted that the feedback request message may be sent through an existing operation or notification message, or through a newly defined operation or notification message, which is not limited in this application.

For example, when the first request message is a feedback instance request information, the response message may be a create MDAFeedback IOC Response operation; when the first request message is a feedback request message or a feedback notification message, the response message may be a feedbackresponse operation.

In a possible implementation manner, the second management entity receives the first feedback information.

Based on the above technical solution, the second management entity can also receive the feedback information confirmed by the first management entity, and the second management entity can more accurately determine the information that needs to be fed back, which greatly improves the accuracy of MDA analysis or ML training, and satisfies operator needs.

In a third aspect, a communication device is provided, which includes: a sending unit, configured to send first information, and the first information is used by a second management entity to perform verification of an MDA report and/or an ML training report and generate a second A feedback report; a receiving unit configured to receive the first feedback report, and the first feedback report is used to give feedback on the verification of the MDA report and/or the ML training report.

In a possible implementation manner, the receiving unit is further configured to receive a first request message, and the first request message The information includes second feedback information, where the second feedback information is the information determined by the second management entity that needs to be fed back; the sending unit is further configured to send the first information according to the first request message.

In a possible implementation manner, the first request message may be a feedback request message or a feedback notification message.

For example, the first request message is a Feedback request operation or a feedback notification operation.

In a possible implementation manner, the apparatus further includes a processing unit configured to create the feedback instance.

In a possible implementation manner, the sending unit is further configured to send the first feedback information.

In a possible implementation manner, the first feedback report includes a first-type report and a second-type report, and the first-type report includes a feedback report type, a feedback report status, a feedback report accuracy, a feedback report timestamp and opposite At least one of report suggestions is given, and the second type of report includes at least one of coverage problem analysis, fault event analysis, mobility management analysis, KPI anomaly analysis, and energy saving analysis.

For the beneficial effects of the above technical solutions, reference may be made to the technical effects of the first aspect, which will not be repeated here.

In a fourth aspect, a communication device is provided, which includes: a receiving unit, configured to receive first information; a processing unit, configured to perform verification of an MDA report and/or ML training report and generate a first feedback report; a sending unit , for sending the first feedback report, where the first feedback report is used to give feedback on the verification of the MDA report and/or the ML training report.

In a possible implementation manner, the processing unit is further configured to determine second feedback information, where the second feedback information is information that needs to be fed back determined by the second management entity; the sending unit is also configured to send A first request message, where the first request message includes second feedback information.

In a possible implementation manner, the second feedback information includes information determined by the second management entity that the first management entity performs MDA analysis and/or ML training

In a possible implementation manner, the receiving unit is further configured to receive the first feedback information.

In a possible implementation manner, the status of the feedback includes whether the MDA report is revised based on the feedback or not Corrected, alternatively, the ML training report is corrected or uncorrected based on feedback.

For the beneficial effects of the above technical solutions, reference may be made to the technical effects of the second aspect, which will not be repeated here.

In a fifth aspect, a communication device is provided, including: at least one processor, the at least one processor is coupled to at least one memory, and the at least one processor is used to execute the computer program or instruction stored in the at least one memory, so that The communication device executes the method in any possible implementation manner of the foregoing first aspect or second aspect.

According to the sixth aspect, a computer-readable storage medium is provided, and a computer program or instruction is stored on the computer-readable storage medium, and when the computer program or instruction is run on a computer, the computer is made to perform the above-mentioned first aspect, the first The second aspect, the method in any possible implementation manner of the third aspect or the fourth aspect.

In a seventh aspect, there is provided a chip system, including: a processor, the processor is used to execute computer programs or instructions in the memory, so as to realize any one of the first aspect, the second aspect, the third aspect or the fourth aspect method in one possible implementation.

In an eighth aspect, a chip is provided, including: a processing circuit and an input-output interface, the input-output interface is used to input or output signals or information, and the processing circuit is used to perform the above-mentioned first aspect, the second aspect, and the third aspect Or the method of the fourth aspect and any possible implementation thereof.

A ninth aspect provides a computer program product, including a computer program or an instruction, when the computer program or instruction is executed, so that the method in any possible implementation of the above-mentioned first aspect or the above-mentioned second aspect The method in any possible implementation manner in the above-mentioned third aspect or the method in any possible implementation manner in the above-mentioned fourth aspect is executed.

In a tenth aspect, an apparatus is provided, including the function or module for realizing the above-mentioned first aspect, the second aspect, the third aspect or the fourth aspect.

Description of drawings

FIG. 1 shows a schematic diagram of an application system architecture 100 applicable to an embodiment of the present application;

FIG. 2 shows a schematic diagram applicable to an application scenario 200 provided by an embodiment of the present application;

Fig. 3 shows a schematic diagram of a management entity applicable to the embodiment of the present application;

Fig. 4 shows a schematic block diagram applicable to the communication method provided by the embodiment of the present application;

Fig. 5 shows a schematic interaction diagram applicable to the communication method provided by the embodiment of the present application;

FIG. 6 shows a schematic interaction diagram applicable to the communication method provided by the embodiment of the present application;

Fig. 7 shows a schematic interaction diagram applicable to the communication method provided by the embodiment of the present application;

Fig. 8 shows a schematic structural diagram of a communication device applicable to the embodiment of the present application;

Fig. 9 shows a schematic architecture diagram of a communication device applicable to the embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

The technical solution of the embodiment of the present application can be applied to various communication systems, such as: Global System of Mobile communication (Global System of Mobile communication, GSM) system, code division multiple access (Code Division Multiple Access, CDMA) system, broadband code division multiple access (Wideband Code Division Multiple Access, WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, fifth generation (5th Generation, 5G) System or New Radio (New Radio, NR) and future communication systems.

The terminal equipment in the embodiment of the present application may refer to user equipment, access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. The terminal equipment can also be a cellular phone, a cordless phone, a Session Initiation Protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, a personal digital processing (Personal Digital Assistant, PDA), a wireless communication Functional handheld devices, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, terminal devices in the future 5G network or future evolution of the public land mobile network (Public Land Mobile Network, PLMN) The terminal device and the like are not limited in this embodiment of the present application.

The network device in the embodiment of the present application may be a device for communicating with a terminal device, and the network device may be a Global System of Mobile communication (GSM) system or a code division multiple access (Code Division Multiple Access, CDMA) The base station (Base Transceiver Station, BTS) in the wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA) system (NodeB, NB) can also be the evolved base station (Evolutionary Base Station) in the LTE system NodeB, eNB or eNodeB), it can also be a wireless controller in the cloud radio access network (Cloud Radio Access Network, CRAN) scenario, or the network device can be a relay station, access point, vehicle equipment, wearable device and future The embodiment of the present application does not limit the network equipment in the 5G network or the network equipment in the future evolved PLMN network.

The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

In order to facilitate understanding of the embodiment of the present application, firstly, a schematic structural diagram of a service management architecture 100 of the embodiment of the present application is briefly described with reference to FIG. 1 .

As shown in Figure 1, the service management architecture includes at least one business support system (business support system, BSS), such as the business support system 110 shown in Figure 1; also includes at least one cross domain management function unit (cross domain management function , CD-MnF), cross-domain management function unit 120 as shown in Figure 1; The management function unit 132 also includes a plurality of network elements (elements), such as the network elements 141, 142, 143 and 144 shown in FIG. 1 .

Among them, the business support system is oriented to communication services, and is used to provide functions and management such as billing, settlement, accounting, customer service, sales, network monitoring, communication service life cycle management, and business intent translation. Serve.

In the embodiment of the present application, the service support system may be an operator's operation system, or may be a vertical industry operation system (vertical OT system).

Among them, the cross-domain management function unit, also called network management function unit (network management function, NMF), can be, for example, a network management system (network management system, NMS), a network function management service consumer (network function management service consumer, NFMS_C ) and other network management entities. Among them, the cross-domain management functional unit provides one or more of the following management functions or management services: network lifecycle management, network deployment, network fault management, network performance management, network configuration management, network security, network The optimization function and the translation of the service producer's network intent (intent from communication service provider, Intent-CSP), etc.

In the embodiment of this application, the cross-domain management functional unit can be nodes such as NMS, MnS Producer, and MnS Consumer, and the domain management functional unit can be nodes such as EMS, MAE, MnS Producer, and MnS Consumer

It should be understood that the network referred to in the foregoing management function or management service may include one or more network elements or sub-networks, and may also be a network slice. That is to say, the network management function unit can be a network slice management function unit (network slice management function, NSMF), or a cross-domain management data analysis function unit (management data analytical function, MDAF), or a cross-domain self-organizing network function (self -organization network function, SON Function) or cross-domain intent management function unit (intent driven management service, MnS).

An optional implementation solution, in some deployment scenarios, the cross-domain management functional unit can also provide subnetwork lifecycle management, subnetwork deployment, subnetwork fault management, subnetwork performance management, subnetwork Configuration management, guarantee of sub-network, optimization function of sub-network, network intent of service producer of sub-network (Intent-CSP) or network intent of service consumer of sub-network (intent from communication service consumer, Intent-CSC) translation etc. The sub-network here is composed of multiple small sub-networks, which can be network slicing sub-networks.

Wherein, the domain management function unit (domain management function, Domain-MnF) is also called a sub-network management function unit (network management function, NMF) or a network element management function unit. For example, the domain management functional unit may be a wireless automation engine (MBB automation engine, MAE), a network element management system (element management system, EMS), a network function management service provider (network function management service provider, NFMS_P) and other network element management entity.

Among them, the domain management functional unit provides one or more of the following functions or management services: lifecycle management of subnetworks or network elements, deployment of subnetworks or network elements, fault management of subnetworks or network elements, subnetwork or network element Performance management of subnetworks or network elements, optimization of subnetworks or network elements, and translation of intent from network operators (Intent-NOPs) of subnetworks or network elements. The subnet here includes one or more network elements. A subnetwork may also include subnetworks, that is, one or more subnetworks form a larger subnetwork.

Optionally, the subnetwork here may also be a network slice subnetwork. The domain management system can be network slice subnet management function (network slice subnet management function, NSSMF), domain management data analysis function unit (management data analytical function, Domain MDAF), domain self-organization network function (self-organization network function, SON Function), domain intent management function unit Intent Driven MnS, etc.

Among them, domain management functional units can be classified in the following ways, including:

According to the network type, it can be divided into: access network domain management function unit (radio access network domain management function, RAN-Domain-MnF), core network domain management function unit (core network domain management function, CN-Domain-MnF), Transport network domain management function (TN-Domain-MnF), etc. It should be noted that the domain management functional unit can also be a certain domain network management system, which can manage one or more of the access network, core network or transmission network;

According to the classification of administrative regions, it can be divided into: domain management functional units of a certain region, such as Shanghai domain management functional units, Beijing domain management functional units, etc.

Wherein, a network element is an entity providing network services, including a core network element, an access network element, and the like. Among them, the core network elements include: access and mobility management function (access and mobility management function, AMF), session management function (session management function, SMF), policy control function (policy control function, PCF), network data analysis Unit (network data analytical function, NWDAF), network warehouse unit (NF Repository Function, NRF) and gateway. Access network elements include: base station (such as gNB, eNB), centralized control unit (central unit control plane, CUCP), central unit (central unit, CU), distributed unit (distribution unit, DU), centralized user plane unit (central unit user plane, CUUP) and so on.

Among them, the network element can provide one or more of the following management functions or management services: network element lifecycle management, network element deployment, network element fault management, network element performance management, network element guarantee, network element Optimization functions and translation of network element intent, etc.

As an example and not a limitation, when the service management architecture 100 performs management services, if the management service is the management service provided by the cross-domain management function unit 120, then the cross-domain management function unit 120 is a management service producer, and the business support system 110 is Manage service consumers.

As an example but not a limitation, if the management service is provided by the domain management function unit 131, then the domain management function unit 131 is a management service producer, and the cross-domain management function unit 120 is a management service consumer.

As an example but not a limitation, when the management service is provided by the network element 141, the network element 141 is a management service producer, and the domain management function unit 131 is a management service consumer.

The above examples are for illustrative purposes only. In specific implementation, management service producers or management service consumers are determined according to the specific provision of management services or consumption of management services, which is not limited in this embodiment of the present application.

In the present application, the structural arrangement of the system or the functional unit is only for illustration, and the architecture may also include other systems or network elements, which is not limited in this embodiment of the present application.

FIG. 2 shows a schematic diagram of an application scenario 200 provided by an embodiment of the present application.

As shown in FIG. 2 , the scenario 200 is applicable to the service management architecture shown in FIG. 1 , and the scenario 200 may include at least two management entities, such as management entity #A and management entity #B shown in FIG. 1 . Wherein, management entity #A and management entity #B can provide management service or consumption management service in the service management structure, for example, provide MDA analysis to realize normal operation of network and service.

For example, the management entity #A in Figure 2 can be used as an MDA management service producer to analyze management data, and the management entity #B in Figure 1 can be used as a management service consumer to verify the data report generated by the management entity #A and report to the management entity #A Feedback report results.

In one implementation, in the service-giving management architecture, the MDA process can be combined with AI and ML technologies to realize the intelligence of network service management. For example, as shown in Figure 2, the management entity #A may include a model training unit 210 and a data analysis unit 220, through which the model training unit 210 can train the ML model and provide the management entity #B provides a training report 211, the data analysis unit 220 can perform data analysis through the trained ML model, and provide the data analysis report 221 to the management entity #B, and the management entity #B can verify the training report and data through the report verification unit 230 Analyze the report, and provide a feedback report 231 to the management entity #A, and the management entity #A can perform model optimization and data analysis optimization according to the feedback report 231 .

Wherein, the training data of the model training unit 210 can be obtained from the management entity #B, can also be obtained from other network elements, and can also be the data preset by the management entity #A, which is not limited in this embodiment of the present application.

The data analyzed by the data analysis unit 220 may be obtained from other network elements, or may be data preset by the management entity #A, which is not limited in this embodiment of the present application.

In this application, the structural settings of the model training unit 210 and the data analysis unit 220 are only illustrative. The model training unit can also be an external module of the management entity #A, or it can be coupled with the data analysis unit 220. Data analysis The training model used by unit 220 may also be pre-trained, which is not limited in this embodiment of the present application.

In this application, MDA management service producer (management entity #A), for example, can be MAE, EMS network element management entity; MDA management service consumer (management entity #B), for example, can be NMS, NF, SON, Network element management entities such as AF can also be network and service optimization tools/functions, SLS guarantee functions, human operators, etc.

It should be understood that some management entities can act as both management service producers and management service consumers. For example, the management function (management function, MnF), in the service-giving management architecture, MnF acts as a management service producer (management service producer) or a management service consumer (management service consumer). The management service produced by the management service producer of MnF may have multiple consumers. MnF can consume multiple management services from one or more management service producers.

Fig. 3 shows a schematic diagram of a management entity applicable to the embodiment of the present application. The management entity can be a management entity defined by 3GPP, and its externally visible behaviors and interfaces are defined as management services. The management entity can be used as a management service producer, and the management services generated by it can be provided to multiple management services. Consumer: The management entity can also serve as a management service consumer, and the management service consumer can obtain management services from one or more management service producers. For example, the management entity can be a management function (management function, MnF). The management service produced by the management service producer of the MnF, as shown in the figure, management service #a and management service #b, can be provided to multiple consumers. The management service consumers of the MnF, for example, service consumer #a, service consumer #b, and service consumer #c shown in FIG. 3 , can consume multiple management services from one or more management service producers.

It should be understood that FIG. 2 is only a simplified schematic diagram for ease of understanding, and other devices may also be included in this scene, which are not shown in FIG. 2 .

It should also be understood that FIG. 2 is only an application scenario of the embodiment of the present application, and the application does not limit the application scenario of the method. In the embodiments shown below, the method provided by the embodiment of the present application is described in detail by taking the interaction between management entities in the scenario of combining MDA and ML technology as an example for the convenience of understanding and description.

The technical solution of the present application will be described in detail below with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

In the prior art, the management service producer can generate MDA report and ML report, wherein, the MDA report includes coverage problem analysis, slice coverage problem analysis, paging optimization analysis, fault analysis, fault prediction analysis, end-to-end delay analysis, Energy saving analysis, mobility analysis, network slice load analysis, network slice throughput analysis, KPI exception analysis, software upgrade analysis, performance management data analysis, tracking data analysis, user perception experience analysis, etc. one or more evaluation reports, ML report Including coverage problem analysis, slice coverage problem analysis, paging optimization analysis, fault analysis, Fault prediction analysis, end-to-end delay analysis, energy saving analysis, mobility analysis, network slice load analysis, network slice throughput analysis, KPI exception analysis, software upgrade analysis, performance management data analysis, tracking data analysis, user perception experience analysis Waiting for one or more model reports, the MDA report can be evaluated in terms of quality and accuracy, and the feedback from the evaluation can be used to optimize the MDA analysis. In the prior art, there is no control over the feedback of the evaluation, so the feedback information may be biased. The optimization for MDA analysis is limited, so it cannot meet the needs of operators.

An optional understanding that MDA can be combined with ML, the ML model report can evaluate the trained ML model, and the feedback from the evaluation can be used to further train the ML model. However, in the existing technology, the scenarios generated by the MDA report and the ML report may be different. Therefore, it is necessary for the management service consumer to verify the report based on different scenarios in order to provide an accurate feedback report to the management service producer.

In view of this, the present application provides a communication method and device, which can realize accurate feedback on report verification for different application scenarios, so as to ensure more accurate MDA analysis or ML training and meet the needs of operators.

A communication method and device provided in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

In the following embodiments, in order to distinguish without loss of generality, the first management entity is an example of a management service producer, the first management entity produces MDA reports and ML reports, the second management entity is an example of a management service consumer, and the second management entity The entity performs validation against MDA reports and ML reports and generates reported feedback.

Fig. 4 shows a schematic block diagram applicable to the communication method provided by the embodiment of the present application, and the method 400 shown in Fig. 4 may be executed by the management entity #A and the management entity #B shown in Fig. 2 .

S410. The first management entity sends first information.

In this application, the first management entity performs data analysis and model training, and may generate an MDA report and/or an ML training report. It should be noted that the ML report may be included in the MDA report, or may exist independently. For the specific content of the MDA report and the ML training report, refer to the detailed description above, and details will not be repeated here.

Specifically, the first management entity sends the first information to the second management entity, and correspondingly, the second management entity receives the first information.

In this application, the first information is used by the second management entity to verify the MDA report and/or the ML training report and generate the first feedback report.

In a possible implementation manner, the first information includes first feedback information, where the first feedback information is information that is determined by the first management entity and needs to be fed back by the second management entity. It should be noted that the first information here is the first feedback information.

In an optional understanding, the first feedback information may be understood as information that the first management entity expects to be fed back by the second management entity.

It should be noted that the first feedback information is the information determined by the first management entity that the second management entity needs to feed back. It can be understood that the first management instance expects the information fed back by the second management entity. When the entity gives feedback, it may also feed back other information that needs to be fed back, which is not limited in this embodiment of the present application.

In an optional understanding, the first feedback information may be understood to include information about MDA analysis and/or ML training performed by the first management entity.

Exemplarily, the first feedback information may include at least one of feedback type, feedback range, and feedback state, wherein the feedback type includes MDA type and/or ML training type, and the feedback range includes feedback accuracy and suggestion measures, the feedback status includes the status of the MDA report and/or ML report.

By way of example and not limitation, feedback types include MDA types, ML training types, further MDA types It can also include coverage problem analysis, slice coverage problem analysis, paging optimization analysis, fault analysis, fault prediction analysis, end-to-end delay analysis, energy saving analysis, mobility analysis, network slice load analysis, network slice throughput analysis, KPI Abnormal analysis, software upgrade analysis and other types; corresponding ML training types can also further include coverage problem analysis, slice coverage problem analysis, paging optimization analysis, fault analysis, fault prediction analysis, end-to-end delay analysis, energy saving analysis, mobile Performance analysis, network slicing load analysis, network slicing throughput analysis, KPI anomaly analysis, software upgrade analysis and other model training types. For example, MDAFeedbackType can be "CoverageAnalysis", "AlarmAnalysis"..., MLTrainingFeedbackType can be "CoverageMLTraining", "AlarmMLTraining" and so on.

It should be noted that the MDA type also includes other scenarios where management data analysis can be performed, as well as types of scenarios such as performance management data analysis, tracking data analysis, and user perception experience (QoE, Quality of Experience) analysis. The embodiments of the present application are not limited here. The scenarios corresponding to the ML training type and the MDA type are the same, and are not repeated in this embodiment of the present application.

It should also be noted that the ML training type is the ML model training type.

By way of example and not limitation, the scope of the feedback includes the accuracy of the feedback and suggested actions. The specific accuracy of the feedback may be the feedback period and the feedback time interval. The suggested action for feedback may be data source feedback.

As an example but not a limitation, the status of the feedback can be understood as the provided MDA report is corrected/uncorrected based on the feedback, or the provided ML training report is corrected/uncorrected based on the feedback.

Optionally, the status of the feedback may also include which feedback report is corrected based on, specifically, it may be represented by an identifier of the feedback report. For example, the status of the feedback for the MDA report is revised based on the feedback report. It can also be expressed in other ways, which are not limited in this embodiment of the present application. The above examples are only exemplary. During specific implementation, the first feedback information may include any parameter status and information expected to be fed back by the first management entity, which is not limited in this embodiment of the present application.

In an implementation manner, the first information is carried when the first management entity sends the MDA report and/or the ML training report to the second management entity.

In another implementation manner, the first information may also be transmitted through other signaling between the first management entity and the second management entity, and the embodiment of the present application does not limit the sending manner of the first information.

In a possible implementation manner, before the first management entity sends the first information, the first management entity receives a first request message sent by the second management entity, where the request message includes second feedback information, and the second feedback information For the feedback information determined by the second management entity, the first information is sent according to the first request message.

It should be noted that the first information here is the first response message of the first request message, and the first response message is used to confirm the content of the second feedback information of the second management entity, and further optionally, inform the second The management entity's subsequent analysis may be performed based on the second feedback information.

In this application, the second feedback information is the feedback information determined by the second management entity, the type of information included in the second feedback information is the same as that included in the first feedback information, and the specific content included in the second feedback information is the same as that included in the first feedback information may or may not be the same.

It should be understood that the feedback information determined by the second management entity can be understood as the feedback information determined by the second management entity as needed, or any information that the second management entity wants to feed back, which is not limited in this embodiment of the present application.

It should be understood that the first request message may be a request message sent to the first management entity after the second management entity determines the feedback information (second feedback information) by itself, requesting confirmation of the second feedback information, and the request for confirmation Can It is understood that the first management entity is requested to allow the second management entity to perform verification on the MDA report and/or ML report based on the second feedback information to generate a feedback report.

In an implementation manner, the first request message may be a feedback instance request message, for example, the first request message is the create MDAFeedback IOC Request operation. The feedback instance request information is used to request the first management entity to create a feedback instance. After the first management entity receives the feedback instance request information, the first management entity creates the feedback instance according to the second feedback information included in the first request message. The above feedback instance is created, and a response message for creating the feedback instance is sent to the second management entity. For example, the response message can be the create MDAFeedback IOC Response operation. In this case, the above-mentioned first information may be a response message of the request information of the feedback instance.

In yet another implementation manner, the first request message may be a feedback request message or a feedback notification message, for example, the first request message is a Feedbackrequest operation or a feedbacknotification operation. After receiving the feedback request message or the feedback notification message, the first management entity determines according to the second feedback information included in the first request message that a response message can be sent to the second management entity, for example, the response message may be a feedback response operation. That is, the above-mentioned first information may be a response message of the feedback request information.

It should be noted that the first request message may be sent through an existing operation message or a newly defined operation message, which is not limited in this application.

It should be noted that the feedback notification message may be sent through an existing notification message, or through a newly defined notification message, such as a newly defined Notification Feedback, which is not limited in this application. The feedback notification message may be a feedback request message, and the feedback request message may be sent through an existing request operation or a newly defined request operation, such as a newly defined Feedback, which is not limited herein.

In an optional implementation method, after the first management entity receives the first request message sent by the second management entity, the first management entity may also send the first feedback information.

It can be understood that, after receiving the feedback information (second feedback information) determined by the second management entity, the first management entity may also send the desired feedback information (first feedback information) to the second management entity, and the second management entity The entity can further determine more appropriate feedback information.

It can be understood that the second management entity can give feedback according to the first feedback information sent by the first management entity, or can give feedback according to the second feedback information determined by itself, or can give feedback in combination with the two feedback information. This is not limited.

In a possible implementation manner, the first management entity may carry the first feedback information when sending the first information. The embodiment of the present application does not limit the sending manner of the first feedback information.

S420, the second management entity receives the first information, verifies the MDA report and/or the ML training report, and generates a first feedback report.

In this application, after the second management entity receives the first information, the second management entity verifies the received MDA report and/or ML training report and generates the first feedback report.

Specifically, the second management entity performs verification based on the received first information and generates a first feedback report.

It should be understood that the process of performing verification belongs to product implementation, and this application does not limit the specific implementation process and method.

In this application, the first feedback report may include one or more of the following: feedback report type, feedback report status, feedback report timestamp, feedback report accuracy, feedback report suggestion, etc., and the feedback report may be specific to a specific scenario The feedback report, or a whole feedback report, is not limited in this application again.

It should be noted that the specific scenarios are MDA scenarios and/or ML scenarios, wherein the MDA scenarios and/or ML scenarios include coverage problem analysis, slice coverage problem analysis, paging optimization analysis, fault analysis, and fault prediction Scenarios such as analysis, end-to-end latency analysis, energy saving analysis, mobility analysis, network slice load analysis, network slice throughput analysis, KPI exception analysis, software upgrade analysis, performance management data analysis, tracking data analysis, and user perception experience analysis One or more of them, for details, refer to the scenarios defined in 3GPP TS 28.401 and TR 28.809.

Specifically, the first feedback report includes a first-type feedback report and a second-type feedback report.

Wherein, the first type of feedback report may be a unified feedback report, that is, a feedback report applicable to all scenarios, specifically may include one or more of the following feedback types, and the feedback types include MDA type and/or ML training type, wherein MDA type and/or ML type include coverage problem analysis, slice coverage problem analysis, paging optimization analysis, fault analysis, fault prediction analysis, end-to-end delay analysis, energy saving analysis, mobility analysis, network slice load analysis, network slice The types corresponding to scenarios such as throughput analysis, KPI exception analysis, software upgrade analysis, performance management data analysis, tracking data analysis, user perception experience analysis, etc., such as "MDA", "ML model" ... further include types ("coverage issue analysis ", "Load level information", "alarm incident", etc.). For details, please refer to the scenarios defined in 3GPP TS 28.401 and TR 28.809.

It may also include: feedback report status: for example, acceptance status, rejection status; specifically, which type of feedback report status may also be included, such as MDA feedback report status, ML feedback report status. Further, it may also include the feedback report status of the specific scene of the MDA, such as the feedback report status of the coverage problem analysis, the feedback report status of the coverage problem analysis of the slice, and the like.

It may also include: a feedback report time stamp, such as the time of the feedback report, which may be an absolute time or a relative time. Specifically, which type of feedback report time stamp may also be included, for example, MDA feedback report time stamp, ML feedback report time stamp. Further, it may also include the feedback report time stamp of the specific scene of the MDA, for example, the time stamp of the feedback report of the coverage problem analysis, the time stamp of the feedback report of the coverage problem analysis of the slice, and the like.

Can also include: Feedback reporting accuracy such as inaccurate analysis ranges, e.g. time ranges, region ranges, thresholds, etc. Specifically, it may also include which type of feedback report accuracy, such as MDA feedback report accuracy, ML feedback report accuracy. Further, it may also include the feedback report precision of the specific scene of the MDA, for example, the feedback report precision of the coverage problem analysis, the coverage problem analysis feedback report precision of the slice, and the like.

Can also include: Feedback report suggestions, such as reanalysis or retraining, etc. According to the specific implementation process, any content that needs to be fed back can be selected for feedback. Specifically, which type of feedback report suggestion may also be included, for example, MDA feedback report suggestion, ML feedback report suggestion. Further, feedback report suggestions for specific scenarios of the MDA may also be included, for example, feedback report suggestions for coverage problem analysis, feedback report suggestions for coverage problem analysis for slices, and the like. The examples of this application are not limited to this.

Wherein, the second type of feedback report may include a feedback report of a specific scenario, and the feedback report of a specific scenario includes the following content in addition to the above-mentioned unified feedback report content: coverage analysis feedback report, fault analysis feedback report, mobility analysis feedback report, KPI At least one of an abnormality analysis feedback report and an energy saving analysis feedback report. Among them, the coverage problem analysis scenario specifically includes one or more of inaccurate analysis range, analysis range suggestion, coverage problem threshold inaccuracy, threshold value suggestion, repairable/unrepairable coverage problem list, etc.; for fault analysis Scenarios, including repairable/unrepairable fault lists, further indicating one or more of CN or RAN; for mobility analysis scenarios, specifically including repairable/unrepairable handover problem cells, and unreasonable handover mechanisms ,cut One or more of the recommendations for switching mechanisms, unreasonable switching range, and switching range recommendations; for KPI abnormal analysis scenarios, specifically including one or more of inaccurate KPI thresholds, KPI threshold recommendations, etc.; for energy saving Analysis scenarios, specifically including repairable/unrepairable energy efficiency problem cells/UPF, cell energy saving status/UPF energy saving status, unreasonable energy saving time period, time period suggestions, energy saving candidate cells/UPF unreasonable, candidate cell/UPF suggestions, etc. One or more of the contents. The above is only an exemplary description, and the feedback content of a specific scene may include any report content about scene analysis, which is not limited in this embodiment of the present application.

In a possible implementation manner, the first feedback report is a feedback report for the first information. If the first information includes the first feedback information, the first feedback report generated by the second management entity is a report for the first feedback information, that is, the first feedback report includes information feedback of specific content in the first feedback information.

In yet another possible implementation, the second management entity determines to perform verification on the MDA report and/or the ML training report, the second management entity determines the second feedback information, and sends the second feedback information to the first management entity through the first request message information, after receiving the first information (response message to the first request message), the second management entity may determine that feedback can be performed according to the second feedback information.

Optionally, the second management entity may also receive the first feedback information. In this case, the second management entity may perform feedback based on the first feedback information, may also perform feedback based on the second feedback information, or may combine the first feedback information The information and the second feedback information are fed back, which is not limited in this embodiment of the present application.

In this application, the content of the first feedback information, the second feedback information, and the first feedback report may include the content exemplified above, or may include other required content, which is not limited in this embodiment of the application.

Exemplarily, Table 1 shows the attributes of the first feedback report provided by the embodiment of the present application, and the specific content is shown in Table 1 below.

Table 1

It should be understood that the content of the feedback report shown in Table 1 above is only illustrative, and is not limited in this embodiment of the present application.

S430. The second management entity sends the first feedback report.

According to the technical solution of the embodiment of the present application, the second management entity can give feedback to the MDA report and/or ML report of the first management entity based on the predetermined feedback information, so that the feedback report can be generated in a targeted manner. Further, it can also A feedback report is generated for a specific scene, so that the MDA function can analyze the specific scene more accurately, and output more accurate analysis results for operators to use.

FIG. 5 shows a schematic interaction diagram applicable to the communication method provided by the embodiment of the present application; the method 500 shown in FIG. 5 can be executed by the management entity #A and the management entity #B shown in FIG. The method 500 described above is the specific implementation steps of the method 300 shown in FIG. 3 .

The method 500 includes step S510-step S530, and the following is a specific description of step S510-step S530.

S510. The first management entity sends first feedback information to the second management entity.

Specifically, the first management entity sends the first feedback information to the second management entity, and correspondingly, the second management entity receives the first feedback information from the first management entity.

In this application, for the specific content of the first feedback information, refer to the detailed explanation of the method 400, and details are not repeated here.

In this application, the specific content of the MDA report and the ML report refers to the detailed explanation above, and will not be repeated here.

In this application, the first management entity generates the MDA report and the ML training report, and sends the MDA report and the ML training report to the second management entity.

In a possible implementation manner, the first management entity directly sends the first feedback message to the second management entity.

In yet another possible implementation manner, the first feedback information is carried when the first management entity sends the MDA report and the ML training report to the second management entity.

It should be noted that, the embodiment of the present application does not set any limitation on the sending manner of the first feedback information.

S520, the second management entity receives the first feedback information, verifies the MDA report and/or the ML training report, and generates the first feedback report.

In this application, for the first feedback report, reference may be made to the detailed description of the method 400 , which will not be repeated here.

In this application, when the second management entity receives the first feedback information, it can confirm that the feedback report (the first type of feedback report) can be determined according to the feedback information, wherein the feedback includes the feedback report for the analysis of the specific scene (the second type of feedback report). Type Feedback Report).

In this application, for the specific content of the feedback report analyzed for a specific scene, refer to the detailed explanation in method 400 , which will not be repeated here.

For example, the MDA type included in the first feedback message is coverage problem analysis, then the first feedback report is a report for the analysis of the coverage problem, and further includes an analysis report for the coverage problem scenario, for example, the analysis range is inaccurate, the analysis One or more of range advice, coverage issue threshold inaccuracy, threshold advice, list of fixable/unfixable coverage issues, etc.

In this application, the second management entity performs the verification of the MDA report and/or the ML training report, and any verification method may be used, which is not limited in this embodiment of the present application.

S530. The second management entity sends the first feedback report to the first management entity.

Specifically, the second management entity sends the first feedback report to the first management entity, and correspondingly, the first management entity receives the first feedback report.

In a possible implementation manner, the first management entity trains a model or optimizes analysis according to the feedback report.

For example, the feedback report includes a feedback report suggestion, the suggestion is to re-analyze the MDA or retrain the ML model, then the first management entity re-analyzes the MDA or retrains the ML model.

According to the technical solution of the embodiment of the present application, the first management entity can directly send expected feedback information to the second management entity, and the second management entity can give feedback to the MDA report and/or ML report of the first management entity based on the feedback information , so that feedback reports can be generated in a targeted manner, and further, feedback reports can also be generated for specific scenarios, so that the MDA function can more accurately analyze specific scenarios, and output more accurate analysis results for operators to use.

FIG. 6 shows a schematic interaction diagram applicable to the communication method provided by the embodiment of the present application; the method 600 shown in FIG. 6 can be executed by the management entity #A and the management entity #B shown in FIG. The described method 600 is shown in Figure 4 The specific implementation steps of the method 400.

The method 600 includes step S610-step S660, and the following is a specific description of step S610-step S660.

S610. The second management entity determines second feedback information.

Specifically, for the specific content of the second feedback information, refer to the detailed description in the method 400, which will not be repeated here.

In a possible implementation manner, the second management entity may determine the second feedback information according to historical records.

In yet another possible implementation manner, the second management entity may determine the second feedback information according to a preset performance index.

In this application, the above is only an exemplary description, and no limitation is imposed on the manner in which the second management entity determines the second feedback information.

S620. The second management entity sends a feedback IOC creation request message to the first management entity.

In this application, the feedback IOC creation request message is an example of a feedback instance request message, and is used to request creation of an MOI instance object.

As an example but not a limitation, the feedback IOC creation request message is the create MDAFeedback IOC Request operation.

In this application, it is also possible to request to create any other feedback instance, or to use an existing operation, which is not limited in this embodiment of this application.

In a possible implementation manner, the feedback IOC creation request message includes the second feedback information.

S630. The first management entity creates a feedback MOI instance and confirms the MOI.

In this application, the first management entity creates and configures a feedback instance.

S640. The first management entity sends a first response message to the second management entity.

Specifically, the first management entity sends the first response message to the second management entity, and correspondingly, the second management entity receives the first response message from the first management entity.

As an example but not a limitation, the first response message is the create MDAFeedback IOC Response operation.

In this application, the first response message is used to inform the second management entity of the feedback reported according to the second feedback information.

In an optional implementation manner, the first management entity may also send first feedback information, and the first feedback information is used by the second management entity to further determine the feedback content of the report.

Exemplarily, the first feedback information is included in the first response message.

Exemplarily, the first feedback information is carried when the first management entity sends the MDA report and the ML training report to the second management entity.

S650. The second management entity receives the first response message, verifies the MDA report and/or the ML training report, and generates a first feedback report.

In this application, after receiving the first response message, the second management entity can confirm that a feedback report can be generated according to the second feedback information, where the feedback includes a feedback report for scene analysis.

In this application, for the specific content of the feedback report analyzed for a specific scene, refer to the detailed explanation in method 400, in This will not be repeated here.

For example, the MDA type included in the second feedback message is coverage problem analysis, then the first feedback report is a report for the analysis of the coverage problem, further, it also includes an analysis report for the coverage problem scenario, for example, the analysis range is inaccurate, the analysis One or more of range advice, coverage issue threshold inaccuracy, threshold advice, list of fixable/unfixable coverage issues, etc.

Optionally, when the first management entity also sends the first feedback information, the second management entity generates a feedback report according to the first feedback information and the second feedback information.

In this case, the second management entity may perform feedback based on the first feedback information, may also perform feedback based on the second feedback information, or may perform feedback in combination with the first feedback information and the second feedback information, and this embodiment of the present application does not make any limited.

S660. The second management entity sends the first feedback report to the first management entity.

According to the technical solution of the embodiment of the present application, the second management entity triggers the management and control configuration of the feedback report, and after being confirmed by the first management entity, the second management entity can report the MDA report and/or ML report to the first management entity based on the feedback information Feedback, so that feedback reports can be generated in a targeted manner, and further, feedback reports can also be generated for specific scenarios, so that the MDA function can more accurately analyze specific scenarios, and output more accurate analysis results for operators to use.

FIG. 7 shows a schematic interaction diagram applicable to the communication method provided by the embodiment of the present application; the method 700 shown in FIG. 7 can be executed by the management entity #A and the management entity #B shown in FIG. The method 700 described above is the specific implementation steps of the method 400 shown in FIG. 4 .

The method 700 includes step S710-step S750, and the following is a specific description of step S710-step S750.

S710. The second management entity determines second feedback information.

S720, the second management entity sends a feedback request message to the first management entity.

In this application, the feedback request message is used to request the first management entity to allow the second management entity to add part of the feedback information in the first feedback report.

As an example but not a limitation, the feedback request message may be a Feedback request operation.

In this application, the feedback request message can be sent through an existing operation or notification message, or a newly defined operation Operation or notification message sending, this application is not limited here.

In a possible implementation manner, the feedback request message includes second feedback information. That is, the first management entity is requested to allow the second management entity to add the second feedback information in the first feedback report.

S730. The first management entity sends a second response message to the second management entity.

Specifically, the first management entity sends the second response message to the second management entity, and correspondingly, the second management entity receives the second response message from the first management entity.

As an example but not a limitation, the second response message may be a Feedback response operation.

In the present application, the second response message is used to notify the feedback that the second management entity is allowed to report according to the second feedback information.

S740. The second management entity receives the second response message, verifies the MDA report and/or the ML training report, and generates a first feedback report.

In this application, after receiving the second response message, the second management entity can confirm that a feedback report can be generated according to the second feedback information, where the feedback includes a feedback report for scene analysis.

S750. The second management entity sends the first feedback report to the first management entity.

According to the technical solution of the embodiment of the present application, the second management entity triggers the management and control configuration of the feedback report, and the second management entity can give feedback to the MDA report and/or ML report of the first management entity based on the feedback information, so that targeted Further, a feedback report can also be generated for a specific scenario, so that the MDA function can analyze the specific scenario more accurately, and output more accurate analysis results for use by operators.

Fig. 8 shows a schematic structural diagram of a communication device applicable to the embodiment of the present application. As shown in FIG. 8 , the communication device 800 includes a sending unit 810 , a receiving unit 820 and a processing unit 830 . The sending unit 810 and the receiving unit 820 may implement corresponding communication functions, and the processing unit 830 is configured to perform data processing, so that the communication device implements the aforementioned method embodiments. The sending unit 810 and the receiving unit 820 may also be referred to as communication interfaces or communication units.

Optionally, the communication device 800 may also include a storage unit, which may be used to store instructions and/or data, and the processing unit 830 may read the instructions and/or data in the storage unit, so that the communication device implements the aforementioned Method Example.

The communication device 800 can be used to execute the actions performed by the first management entity in the above method embodiments. At this time, the communication device 800 can be the first management entity or a component that can be configured in the first management entity. The sending unit 810 The receiving unit 820 is used to perform operations related to sending and receiving on the side of the first management entity in the above method embodiments, and the storage unit is used to perform operations related to data or instruction storage on the side of the first management entity in the above method embodiments, processing The unit 830 is configured to perform processing-related operations on the first management entity side in the above method embodiments.

Alternatively, the communication device 800 can be used to execute the actions performed by the second management entity in the above method embodiments. At this time, the communication device 800 can be the second management entity or a component that can be configured in the second management entity, sending The unit 810 and the receiving unit 820 are used to perform operations related to sending and receiving on the side of the second management entity in the above method embodiments, and the storage unit is used to perform operations related to data or instruction storage on the side of the second management entity in the above method embodiments , the processing unit 830 is configured to perform processing-related operations on the second management entity side in the above method embodiments.

In a possible design, the communication device 800 may correspond to the first management entity and the second management entity in the methods 400, 500, 60, and 700 according to the embodiments of the present application. The communication device 800 may include a unit for executing the methods performed by the first management entity and the second management entity in the methods 400 to 700 in FIGS. 4 to 7 . Moreover, the units in the communication device 800 and the above-mentioned other operations and/or functions are respectively intended to implement the corresponding processes in the method 400 to the method 700 in FIG. 4 to FIG. 7 .

Exemplarily, when the communication device 800 is used as the first management entity in the method 300, the following steps may be performed: a sending unit, configured to send first information, and the first information is used by the second management entity to execute the MDA report and/or or verification of the ML training report and generating a first feedback report; a receiving unit configured to receive the first feedback report, and the first feedback report is used to give feedback on the verification of the MDA report and/or the ML training report.

In this application, for the first management entity, the second management entity, the first information, and the first feedback report, reference may be made to the detailed description in the method 300, and details are not repeated here.

In a possible implementation manner, the first information includes first feedback information, where the first feedback information is information determined by the first management entity that the second management entity needs to feed back.

In a possible implementation manner, the receiving unit is further configured to receive a first request message, where the first request message includes second feedback information, and the second feedback information is the required feedback determined by the second management entity. information; the sending unit is further configured to send the first information according to the first request message.

In a possible implementation manner, the first feedback information or the second feedback information includes at least one of a feedback type, a feedback range, and a feedback state, where the feedback type includes an MDA type and/or an ML training type , the feedback range includes feedback time accuracy, and the feedback status includes the status of the MDA report and/or ML report.

In a possible implementation manner, the feedback range includes feedback accuracy and a suggested measure, the feedback accuracy includes feedback period accuracy and time accuracy, and the suggested measure includes a data source measure.

Exemplarily, when the communication device 800 is used as the second management entity in the method 400, the following steps may be performed: the receiving unit is used to receive the first information; the processing unit is used to perform verification of the MDA report and/or the ML training report And generate a first feedback report; a sending unit, configured to send the first feedback report, where the first feedback report is used to give feedback on the verification of the MDA report and/or the ML training report.

In a possible implementation manner, the processing unit is further configured to determine second feedback information, where the second feedback information is information that needs to be fed back determined by the second management entity; the sending unit is further configured to send the second feedback information. A request message, the first request message includes the second feedback information.

It should be understood that the specific process for each unit to perform the above corresponding steps has been described in detail in the above method embodiments, and for the sake of brevity, details are not repeated here. The processing unit 830 in the above embodiments may be implemented by at least one processor or processor-related circuits. The sending unit 810 and the receiving unit 820 may be implemented by transceivers or transceiver-related circuits. The sending unit 810 and the receiving unit 820 may also be referred to as communication units or communication interfaces. The storage unit can be realized by at least one memory.

FIG. 9 is a schematic block diagram of a communication device 900 provided by an embodiment of the present application. As shown in the figure, the apparatus 900 includes: at least one processor 920 . The processor 920 is coupled with the memory for executing instructions stored in the memory to send signals and/or receive signals. Optionally, the device 900 further includes a memory 930 for storing instructions. Optionally, the apparatus 900 further includes a transceiver 910, and the processor 920 controls the transceiver 910 to send signals and/or receive signals.

It should be understood that the above-mentioned processor 920 and memory 930 may be combined into one processing device, and the processor 920 is used to execute The program codes stored in the memory 930 realize the above functions. During specific implementation, the memory 930 may also be integrated in the processor 920 , or be independent of the processor 920 .

It should also be understood that the transceiver 910 may include a transceiver (or called a receiver) and a transmitter (or called a transmitter). The transceiver may further include antennas, and the number of antennas may be one or more. The transceiver 910 may be a communication interface or an interface circuit.

For example, the transceiver 910 in the apparatus 900 may correspond to the transceiver unit in the foregoing embodiments, and the processor 920 in the apparatus 900 may correspond to the processing unit in the foregoing embodiments. It should be understood that the specific process of each transceiver processor performing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, details are not repeated here.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of software. The computer software product is stored in a storage medium, including several The instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

Claims

A communication method, characterized in that, comprising:

The first management entity sends first information, and the first information is used for the second management entity to perform verification of the MDA report and/or ML training report and generate a first feedback report;

The first management entity receives the first feedback report, and the first feedback report is used to feedback the verification of the MDA report and/or ML training report.
The method according to claim 1, wherein the first information includes first feedback information, and the first feedback information is information determined by the first management entity that the second management entity needs to feed back.
The method according to claim 1, wherein the sending of the first information by the first management entity includes:

The first management entity receives a first request message, where the first request message includes second feedback information, where the second feedback information is information that needs to be fed back determined by the second management entity;

The first management entity sends the first information according to the first request message.
The method according to claim 3, wherein the first request message is feedback instance request information, and the feedback instance request information is used to request the first management entity to create a feedback instance.
The method according to claim 4, wherein the first management entity creates the feedback instance according to the first request message.
The method according to any one of claims 3-5, wherein the first information is a first response message of the first request message.
The method according to any one of claims 3-6, wherein the method further comprises:

The first management entity sends the first feedback information.
The method according to any one of claims 1-7, wherein the first feedback information or the second feedback information includes at least one of a feedback type, a feedback range, and a feedback state.
The method according to claim 8, wherein the feedback type includes MDA type and/or ML training type, and the MDA type includes coverage problem analysis type, slice coverage problem analysis type, paging optimization analysis type, failure At least one of the analysis types, fault prediction analysis types, end-to-end delay analysis types, energy saving analysis types, mobility analysis types, network slice load analysis types, network slice throughput analysis types, KPI exception analysis types, and software upgrade analysis types One, the ML training type includes coverage problem analysis model training type, slice coverage problem analysis model training type, paging optimization analysis model training type, fault analysis model training type, fault prediction analysis model training type, end-to-end delay analysis At least one of the model training type, energy saving analysis model training type, mobility analysis model training type, network slice load analysis model training type, network slice throughput analysis model training type, KPI anomaly analysis model training type, and software upgrade analysis model training type one.
The method according to claim 8, wherein the feedback range includes at least one of feedback accuracy and suggested measures, the feedback accuracy includes feedback cycle accuracy and/or time accuracy, and the suggested measures include Data source measures.
The method according to claim 8, wherein the status of the feedback includes whether the MDA report is corrected or not corrected based on feedback, or whether the ML training report is corrected or not corrected based on feedback.
The method according to any one of claims 1-8, wherein the first feedback report includes A first type report and a second type report, the first type report includes at least one of the feedback report type, feedback report status, feedback report accuracy, feedback report timestamp and feedback report suggestion, and the second type report includes coverage At least one of problem analysis, failure event analysis, mobility management analysis, KPI anomaly analysis and energy saving analysis.
The method according to any one of claims 1-12, wherein the first feedback information is the same as the second feedback information.
A communication method, characterized in that, comprising:

the second management entity receives the first information;

said second management entity performs validation of MDA reports and/or ML training reports and generates first feedback reports;

The second management entity sends the first feedback report, and the first feedback report is used to give feedback on the verification of the MDA report and/or ML training report.
The method according to claim 14, wherein the first information includes first feedback information, and the first feedback information is information determined by the first management entity that the second management entity needs to feed back.
The method according to claim 14, wherein the receiving of the first information by the second management entity comprises:

The second management entity determines second feedback information, where the second feedback information is information that needs to be fed back determined by the second management entity;

The second management entity sends a first request message, where the first request message includes second feedback information;

The second management entity receives the first information.
The method according to claim 16, wherein the first request message is feedback instance request information, and the feedback instance request information is used to request the first management entity to create a feedback instance.
The method according to claims 16-17, wherein the first information is a first response message of the first request message.
The method according to any one of claims 16-18, wherein the method further comprises:

The second management entity receives the first feedback information.
The method according to any one of claims 14-19, wherein the first feedback information or the second feedback information includes at least one of a feedback type, a feedback range, and a feedback state.
The method according to claim 20, wherein the feedback type includes MDA type and/or ML training type, and the MDA type includes coverage problem analysis type, slice coverage problem analysis type, paging optimization analysis type, failure At least one of the analysis types, fault prediction analysis types, end-to-end delay analysis types, energy saving analysis types, mobility analysis types, network slice load analysis types, network slice throughput analysis types, KPI exception analysis types, and software upgrade analysis types One, the ML training type includes coverage problem analysis model training type, slice coverage problem analysis model training type, paging optimization analysis model training type, fault analysis model training type, fault prediction analysis model training type, end-to-end delay analysis At least one of the model training type, energy saving analysis model training type, mobility analysis model training type, network slice load analysis model training type, network slice throughput analysis model training type, KPI anomaly analysis model training type, and software upgrade analysis model training type one.
The method according to claim 20, wherein the feedback range includes at least one of feedback accuracy and suggested measures, the feedback accuracy includes feedback cycle accuracy and/or time accuracy, and the suggested measures include Data source measures.
The method according to claim 20, wherein the status of the feedback comprises the MDA report is corrected or uncorrected based on feedback, or the ML training report is corrected or uncorrected based on feedback.
The method according to any one of claims 14-19, wherein the first feedback report includes a first type report and a second type report, and the first type report includes a feedback report type, a feedback report At least one of status, feedback report accuracy, feedback report time stamp and feedback report suggestion, the second type of report includes at least one of coverage problem analysis, fault event analysis, mobility management analysis, KPI anomaly analysis and energy saving analysis.
The method according to any one of claims 14-24, wherein the first feedback information is the same as the second feedback information.
A communication device, characterized in that, comprising:

A module or unit for implementing the method of any one of claims 1 to 13; or

A module or unit for implementing the method of any one of claims 14-25.
A communication system, characterized by comprising a module or unit for executing the communication method as claimed in any one of claims 1 to 25, or comprising the communication device as claimed in claim 26.
A communication device, characterized by comprising:

A processor, configured to execute the computer program stored in the memory, so that the communication device executes the communication method according to any one of claims 1 to 25.
A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is run on a computer, the computer is made to perform any one of claims 1 to 25. A method of communication as described.
A computer program product, characterized in that the computer program product includes instructions for executing the communication method according to any one of claims 1 to 25.