CN116112945A

CN116112945A - Communication method and device

Info

Publication number: CN116112945A
Application number: CN202111325389.3A
Authority: CN
Inventors: 李卓明; 时书锋
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2021-11-10
Filing date: 2021-11-10
Publication date: 2023-05-12
Also published as: WO2023082877A1

Abstract

A communication method and apparatus for enabling an analysis service of a data analysis network element to satisfy the requirement of an analysis request network element. The method comprises the following steps: the data analysis network element receives a request message from the analysis request network element, wherein the request message is used for requesting recommended network parameters, and the request message comprises the network parameters required by the analysis request network element and network indexes expected by the analysis request network element. The data analysis network element may also determine recommended network parameters based on the required network parameters and the desired network metrics. The data analysis network element may also send recommended network parameters to the analysis request network element. Wherein the recommended network parameters correspond to the network parameters required by the analysis request network element and the desired network index, so that the analysis result of the data analysis network element meets the requirement of the analysis request network element.

Description

Communication method and device

Technical Field

The present disclosure relates to the field of communications technologies, and in particular, to a communications method and apparatus.

Background

The rapid development of artificial intelligence and big data analysis provides a basic technology for network intelligence. In order to achieve 5G mobile network intelligence, network data analysis functions (network data analytics function, NWDAF) network elements are defined, as well as management data analysis systems (management data analytics system, MDAS). The NWDAF or MDAS may be used to provide intelligent analysis services for the network for supporting anomaly analysis, optimization tuning and service level agreement guarantees for the network. The NWDAF and/or MDAS may be referred to herein as data analysis network elements.

Taking NWDAF performing analysis as an example, NWDAF may predict a trend of a network index (i.e. an index representing a network operation state) through intelligent analysis service, and a service network element for processing a service performs network adjustment according to the trend of the network index. However, the analysis service of the data analysis network element cannot meet the service requirement at present.

Disclosure of Invention

The embodiment of the application provides a communication method and a communication device, so that analysis service of a data analysis network element meets business requirements.

In a first aspect, embodiments of the present application provide a communication method, which may be performed by a data analysis network element or a module (e.g. a chip) applied in the data analysis network element. Taking the data analysis network element as an example, the method comprises the following steps: the data analysis network element receives a request message from an analysis request network element, wherein the request message is used for requesting recommended network parameters, and the request message comprises the network parameters required by the analysis request network element and network indexes expected by the analysis request network element. The data analysis network element may also determine the recommended network parameter based on the required network parameter and the desired network indicator. The data analysis network element may also send the recommended network parameters to the analysis request network element.

According to the scheme, the data analysis network element can determine recommended network parameters according to the required network parameters and the expected network indexes from the analysis request network element, and send the recommended network parameters to the analysis request network element to realize the recommendation of the network parameters, wherein the recommended network parameters correspond to the network parameters required by the analysis request network element and the expected network indexes, so that the analysis service of the data analysis network element can meet the service requirements of the analysis request network element.

In one possible design, the recommended network parameter is within the range of the required network parameter, and the predicted network index corresponding to the recommended network parameter is not within the range of the desired network index. By adopting the design, the efficiency of recommending network parameters can be improved. For example, if no predicted network indicator corresponding to a network parameter is within an acceptable range of network parameters, then a recommended network parameter is determined from within a range of required network parameters, the value of the predicted network indicator corresponding to the recommended network parameter being within an acceptable range of network indicators, the acceptable range being greater than the range of the desired network indicator.

In one possible design, the data analysis network element may further send a predicted network indicator corresponding to the recommended network parameter to the analysis request network element. If the predicted network indicator corresponding to the recommended network parameter is not within the range of the desired network indicator, the data analysis network element may send the predicted network indicator corresponding to the recommended network parameter in order to analyze the requesting network element to decide whether to receive the recommended network parameter according to the network indicator.

In one possible design, the recommended network parameter is not within the range of the required network parameter, and the predicted network index corresponding to the recommended network parameter is within the range of the desired network index. By adopting the design, the efficiency of recommending network parameters can be improved. For example, if no predicted network indicator corresponding to a network parameter is within a desired network indicator, within a range of required network parameters, a recommended network parameter whose value is within the desired network indicator is determined from within an acceptable range of the network parameter.

In one possible design, the data analysis network element may further send indication information to the analysis request network element, where the indication information is used by the analysis request network element to decide whether to accept the recommended network parameter. By adopting the design, the data analysis network element can trigger the decision of analyzing whether the request network element accepts the recommended network parameters, thereby improving the system cooperativity. In one possible implementation, if the analysis request network element accepts the recommended network parameter, a response message may also be sent to the data analysis network element indicating that the recommended network parameter is accepted.

In one possible design, the recommended network parameter is within the range of the required network parameter and the predicted network indicator corresponding to the recommended network parameter is within the range of the desired network indicator. By adopting the design, the recommended network parameters meet the requirements of the analysis request network element on the network parameters and the expectations of the network indexes, so that the analysis service of the data analysis network element can further meet the requirements of the analysis request network element.

In one possible design, the data analysis network element may also send a tolerance range for the network parameters to the analysis request network element, the recommended network parameters belonging to the tolerance range. By adopting the design, the analysis service of the data analysis network element can further meet the requirement of the analysis request network element. The tolerance range is an acceptable numerical range of the recommended network parameters, the service request network element can adjust the network parameters according to the tolerance range, and the network index corresponding to the adjusted network parameters can meet the expectations.

In one possible design, the data analysis network element may further send a guarantee rate to the analysis request network element, where the guarantee rate is a probability that a predicted network indicator corresponding to the network parameter in the tolerance range can meet the predicted network indicator corresponding to the recommended network parameter. By adopting the design, the analysis request network element can determine whether to adjust network parameters within a tolerance range according to the guarantee rate, so that the analysis service of the data analysis network element further meets the requirement of the analysis request network element. For example, the analysis requesting network element may refuse to adjust the network parameters in a still range if the assurance rate is too low, at which time the analysis requesting network element may adjust the network parameters according to recommended network parameters or adjust the network parameters in a range less than the tolerance range and including the recommended network parameters.

In one possible design, the request message further includes requirement information for indicating the recommended network parameter, and the data analysis network element may further determine the recommended network parameter from a range of the required network parameter and/or a range of the network parameter corresponding to the desired network index according to the requirement information. By adopting the design, the recommended network parameters better meet the requirements of the service request network element on the network parameters, and the analysis service of the data analysis network element can further meet the requirements of the analysis request network element.

In one possible design, the requirement information includes a cost function. For example, the cost function may be a destination function that finds an optimal solution using a training model, and the requirement information may be used to indicate that the cost function of the recommended network parameter is the smallest, and the system overhead corresponding to the recommended network parameter is the smallest at this time, so as to achieve overhead minimization.

In one possible design, the requirement information indicates that the recommended network parameter is a maximum or minimum value within a range of the required network parameter, or the requirement information indicates that the recommended network parameter is a maximum or minimum value within a range of network parameters corresponding to meet the desired network index.

In a second aspect, embodiments of the present application provide a communication method that may be performed by an analysis request network element or a module (e.g., a chip) that is applied in an analysis request. Taking the analysis request as an example, the method includes: the analysis request network element sends a request message to the data analysis network element, wherein the request message is used for requesting recommended network parameters, and the request message comprises the network parameters required by the analysis request network element and network indexes expected by the analysis request network element. The analysis request network element may also receive recommended network parameters from the data analysis network element, the recommended network parameters being determined from the required network parameters and the network metrics desired by the analysis request network element. The analysis requesting network element may also adjust network parameters according to the recommended network parameters.

In one possible design, the recommended network parameter is within the range of the required network parameter, and the predicted network index corresponding to the recommended network parameter is not within the range of the desired network index.

In one possible design, the recommended network parameter is not within the range of the required network parameter, and the predicted network index corresponding to the recommended network parameter is within the range of the desired network index.

In one possible design, the analysis request network element may also receive indication information from the data analysis network element; the analysis requesting network element may also determine whether to accept the recommended network parameter based on the indication information.

In one possible design, the recommended network parameter is within the range of the required network parameter, the predicted network indicator corresponding to the recommended network parameter is not within the range of the desired network indicator, and the analysis requesting network element may further receive the predicted network indicator corresponding to the recommended network parameter from the data analysis network element. The analysis request network element may determine whether to accept the recommended network parameter according to the predicted network index corresponding to the recommended network parameter and the indication information.

In one possible design, the recommended network parameter is within the range of the required network parameter and the predicted network indicator corresponding to the recommended network parameter is within the range of the desired network indicator.

In one possible design, the analysis requesting network element may also receive a tolerance range for the network parameters from the data analysis network element, the recommended network parameters belonging to the tolerance range. The analysis requesting network element may specifically adjust the network parameters within the tolerance range.

In one possible design, the analysis request network element may further receive a tolerance range of the network parameter from the data analysis network element, the recommended network parameter belongs to the tolerance range, and the analysis request network element may further receive a guarantee rate from the data analysis network element, where the guarantee rate is a probability that a predicted network indicator corresponding to the network parameter within the tolerance range can satisfy the predicted network indicator corresponding to the recommended network parameter. The analysis request network element can specifically determine whether to adjust the network parameters within the tolerance range according to the guarantee rate.

In one possible design, the request message may further include requirement information for indicating the recommended network parameters.

In one possible design, the requirement information includes a cost function.

In a third aspect, embodiments of the present application provide a communication device, which may be a data analysis network element or a module (e.g. a chip) applied in the data analysis network element. The device has the function of realizing the above-described first aspect and any of its possible designs. The functions can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above.

In a fourth aspect, embodiments of the present application provide a communication device, which may be an analysis request network element or a module (e.g. a chip) applied in the analysis request network element. The device has the function of realizing the above-described second aspect and any possible designs thereof. The functions can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above.

In a fifth aspect, embodiments of the present application provide a communication device comprising a processor and a memory; the memory is configured to store computer instructions that, when executed by the apparatus, cause the apparatus to perform any implementation of the first aspect to the second aspect and any of their possible designs.

In a sixth aspect, embodiments of the present application provide a communication device comprising means for performing the steps of the first to second aspects and any possible designs thereof described above.

In a seventh aspect, embodiments of the present application provide a communication device comprising a processor and an interface circuit, the processor being configured to communicate with other devices via the interface circuit and to perform the method of the first aspect to the second aspect and any possible designs thereof. The processor includes one or more.

In an eighth aspect, embodiments of the present application provide a communication device comprising a processor coupled to a memory, the processor being configured to invoke a program stored in the memory to perform the method of the first aspect to the second aspect and any possible designs thereof. The memory may be located within the device or may be located external to the device. And the processor may be one or more.

In a ninth aspect, embodiments of the present application also provide a computer readable storage medium having instructions stored therein which, when run on a communications device, cause the method of the above first to second aspects and any possible designs thereof to be performed.

In a tenth aspect, embodiments of the present application also provide a computer program product comprising a computer program or instructions which, when executed by a communication device, cause the method of any of the above first to second aspects and any possible designs thereof to be performed.

In an eleventh aspect, embodiments of the present application further provide a chip system, including: a processor for performing the method of the first to second aspects and any possible designs thereof.

In a twelfth aspect, embodiments of the present application further provide a communication system, including a data analysis network element for performing the method in the first aspect and any possible designs thereof, and an analysis request network element for performing the method in the second aspect and any possible designs thereof.

The advantages of the above second to twelfth aspects and any possible designs thereof can be seen from the description of the advantages of the first aspect and any possible designs thereof, and are not specifically expanded.

Drawings

Fig. 1 is a schematic architecture diagram of a communication system according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a machine learning model according to an embodiment of the present disclosure;

Fig. 3 is a schematic architecture diagram of another communication system according to an embodiment of the present application;

fig. 4 is a flow chart of a communication method according to an embodiment of the present application;

FIG. 5 is a flow chart illustrating another communication method according to an embodiment of the present application;

FIG. 6 is a flow chart illustrating another communication method according to an embodiment of the present application;

FIG. 7 is a flow chart illustrating another communication method according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a communication device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of another communication device according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings.

Fig. 1 is a schematic diagram of a 5G network architecture based on a servitization architecture. The 5G network architecture shown in fig. 1 may include a terminal device, AN Access Network (AN) device, and a core network device. The terminal device accesses a Data Network (DN) through the access network device and the core network device. Wherein the core network device includes some or all Network Functions (NF) in the following network elements: unified data management (unified data management, UDM) network elements, network opening function (network exposure function, NEF) network elements (not shown in the figure), application function (application function, AF) network elements, policy control function (policy control function, PCF) network elements, access and mobility management function (access and mobility management function, AMF) network elements, network slice selection function (network slice selection function, NSSF) network elements, session management function (session management function, SMF) network elements, user plane function (user plane function, UPF) network elements, network data analysis function (network data analytics function, NWDAF) network elements, and network storage function (network repository function, NRF) network elements (not shown in the figure), etc.

The access network device may be a radio access network (radio access network, RAN) device. For example: base station (base station), evolved NodeB (eNodeB), transmission and reception point (transmission reception point, TRP), next generation base station (gNB) in 5G mobile communication system, next generation base station in sixth generation (the 6th generation,6G) mobile communication system, base station in future mobile communication system, or access node in wireless fidelity (wireless fidelity, wiFi) system, etc.; the present invention may also be a module or unit that performs a function of a base station part, for example, a Central Unit (CU) or a Distributed Unit (DU). The radio access network device may be a macro base station, a micro base station, an indoor station, a relay node, a donor node, or the like. The embodiment of the application does not limit the specific technology and the specific equipment form adopted by the wireless access network equipment.

The terminal device may be a User Equipment (UE), a mobile station, a mobile terminal, or the like. The terminal device may be widely applied to various scenes, for example, device-to-device (D2D), vehicle-to-device (vehicle to everything, V2X) communication, machine-type communication (MTC), internet of things (internet of things, IOT), virtual reality, augmented reality, industrial control, autopilot, telemedicine, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city, and the like. The terminal equipment can be a mobile phone, a tablet personal computer, a computer with a wireless receiving and transmitting function, a wearable device, a vehicle, an urban air vehicle (such as an unmanned aerial vehicle, a helicopter and the like), a ship, a robot, a mechanical arm, intelligent household equipment and the like.

The access network device and the terminal device may be fixed in location or may be mobile. The access network equipment and the terminal equipment can be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; the device can be deployed on the water surface; but also on aerial planes, balloons and satellites. The application scene of the access network equipment and the terminal equipment is not limited in the embodiment of the application.

An access management network element, which is mainly used for performing functions of mobility management, access authentication/authorization and the like, such as attachment of terminals in a mobile network, mobility management, tracking area update flow, and terminates non-access stratum (non access stratum, NAS) messages, completes registration management, connection management and reachability management, distributes tracking area list (tlist), mobility management and the like, and transparently routes session management (session management, SM) messages to session management network elements. In the 5th generation (5th generation,5G) communication system, the access management network element may be an AMF network element (hereinafter, abbreviated as AMF). In addition, the access management network element is responsible for delivering user policies between the terminal device and the PCF.

The session management network element is mainly used for session management in the mobile network, such as session establishment, modification and release. Specific functions are for example assigning an internet protocol (internet protocol, IP) address to the terminal, selecting a user plane network element providing a message forwarding function, etc. In the 5G communication system, the session management network element may be an SMF network element (hereinafter referred to as SMF).

The network slice selection network element is mainly used for selecting proper network slices for the service of the terminal. In a 5G communication system, the network slice selection network element may be an NSSF network element.

The user plane network element is mainly responsible for processing user messages, such as forwarding, charging, legal monitoring and the like. The user plane network element may act as a protocol data unit (protocol data unit, PDU) session anchor (PDU session anchor, PSA). In the 5G communication system, the user plane network element may be a UPF network element (hereinafter referred to as UPF). The UPF may communicate with the NWDAF directly through a similarly serviced interface, or may communicate with the NWDAF through other means, such as through a proprietary or internal interface between the SMF or with the NWDAF.

Unified data management network element: is responsible for managing subscription information of the terminal. In the 5G communication system, the unified data management network element may be a UDM network element (hereinafter referred to as UDM).

Network capability open network elements to support the opening of capabilities and events. In the 5G communication system, the network capability opening network element may be a NEF network element (hereinafter, simply referred to as NEF).

An application function network element is used for transmitting the requirement of the application side to the network side, such as QoS requirement or user state event subscription. The application function network element may be a third party function entity or an application server deployed by an operator. In the 5G communication system, the application function network element may be an AF network element (hereinafter, abbreviated as AF).

Policy control network elements including subscriber subscription data management functions, policy control functions, charging policy control functions, quality of service (quality of service, qoS) control, etc. In a 5G communication system, the policy control network element may be a PCF network element (hereinafter, abbreviated as PCF). It should be noted that in an actual network, the PCF may also be hierarchically or functionally divided into a plurality of entities, e.g. a global PCF and a PCF within a slice, or a session management PCF (session management PCF, SM-PCF) and an access management PCF (access management PCF, AM-PCF).

The network warehouse network element can be used for providing a network element discovery function and providing network element information corresponding to the network element type based on the requests of other network elements. The network warehouse network element also provides network element management services such as network element registration, updating, deregistration, network element state subscription, pushing and the like. In the 5G communication system, the network repository network element may be an NRF network element (hereinafter referred to as NRF).

And the data analysis network element can be used for collecting data and analyzing and predicting. Wherein collecting data includes, but is not limited to: at least one of collecting data from other individual NFs, such as through AMF, SMF, PCF, collecting data from NEF or directly from AF, or collecting data from an operations, administration, and maintenance (OAM) system. The data may be data of a terminal device, an access network device, a core network element or a third party application device, or data of the terminal device on the access network device, the core network element or the third party application device, and then intelligently analyze according to the collected data, and output an analysis result. In the 5G communication system, the data analysis network element may be an NWDAF network element (hereinafter, abbreviated as NWDAF). The intelligent analysis refers to analysis of collected data by means of intelligent technologies such as artificial intelligence (artificial intelligence, AI). In this application, intelligent analysis includes, but is not limited to, predicting network metrics and recommending network parameters.

In this application, NWDAF may utilize a machine learning model for intelligent analysis. The NWDAF may also output recommended values to each NF, AF, or OAM as described above for each NF, AF, or OAM to execute policy decisions. The training function and the reasoning (reference) function of the NWDAF are split in the third generation partnership project (3rd generation partnership project,3GPP) release 17, and one NWDAF may support only the model training function, only the data reasoning function, or both the model training function and the data reasoning function. The NWDAF supporting the model training function may be referred to as a training NWDAF, or an NWDAF (abbreviated as NWDAF (MTLF)) supporting the model training logic function (model training logical function, MTLF). The training NWDAF may perform model training according to the acquired data, to obtain a trained model. The NWDAF supporting the data reasoning function may also be referred to as a reasoning NWDAF or as NWDAF supporting the analysis logic function (analytics logical function, anLF) (simply NWDAF (AnLF)). The inference NWDAF may input the input data to the trained model to obtain an analysis result or inference data. In the embodiment of the present application, training NWDAF refers to NWDAF that at least supports model training functions. As one possible implementation, training NWDAF may also support data reasoning functions. The inferential NWDAF refers to NWDAF that supports at least a data inference function. As one possible implementation approach, the inference NWDAF may also support a model training function. If an NWDAF supports both model training functions and data reasoning functions, the NWDAF may be referred to as a training NWDAF, a reasoning NWDAF, or a training reasoning NWDAF or NWDAF. In this embodiment of the present application, an NWDAF may be a single network element, or may be combined with other network elements, for example, the NWDAF is set in a PCF network element or an AMF network element.

The DN is a network outside the operator network, the operator network can be accessed to a plurality of DNs, a plurality of services can be deployed on the DNs, and services such as data and/or voice can be provided for the terminal equipment. For example, the DN is a private network of an intelligent plant, the sensors installed in the plant of the intelligent plant may be terminal devices, a control server of the sensors is disposed in the DN, and the control server may serve the sensors. The sensor may communicate with the control server, obtain instructions from the control server, transmit collected sensor data to the control server, etc., according to the instructions. For another example, DN is an internal office network of a company, where a mobile phone or a computer of an employee of the company may be a terminal device, and the mobile phone or the computer of the employee may access information, data resources, etc. on the internal office network of the company.

Npcf, nnef, namf, nudm, nsmf, naf, nnssf and Nnwdaf in fig. 1 are service interfaces provided for PCF, NEF, AMF, UDM, SMF, AF, NSSF and NWDAF, respectively, above, for invoking corresponding service operations. N1, N2, N3, N4, and N6 are interface serial numbers, and the meaning of these interface serial numbers is as follows:

1) N1: the interface between the AMF and the terminal device may be used to communicate non-access stratum (non access stratum, NAS) signaling (e.g., including QoS rules from the AMF) etc. to the terminal device.

2) N2: the interface between the AMF and the access network device may be used to transfer radio bearer control information from the core network side to the access network device, etc.

3) N3: the interface between the access network equipment and the UPF is mainly used for transferring uplink and downlink user plane data between the access network equipment and the UPF.

4) N4: the interface between SMF and UPF can be used to transfer information between control plane and user plane, including control plane-oriented forwarding rule, qoS rule, flow statistics rule, etc. issuing and user plane information reporting.

5) N6: and the interface of the UPF and the DN is used for transmitting uplink and downlink user data streams between the UPF and the DN.

The service architecture shown in fig. 1 enables the 5G core network to form a flattened architecture, and through the signaling bus of the control plane, the control plane network functional entities of the same network slice can find each other through NRF to obtain the access address information of the opposite party, and then can directly communicate with each other through the signaling bus of the control plane.

It will be appreciated that the network elements or functions described above may be either network elements in a hardware device, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform). As a possible implementation method, the network element or the function may be implemented by one device, or may be implemented by a plurality of devices together, or may be a functional module in one device, which is not specifically limited in this embodiment of the present application.

As an implementation method, the data analysis network element in the embodiment of the present application may be the NWDAF, or may be a network element with a function of the NWDAF in future communications, for example, in a 6G network. The data analysis network element may also be an MDAS. The MDAS is a data analysis system deployed on a network management plane, and can be used for collecting management data such as performance statistics, alarms, operation configuration and the like, analyzing and predicting, and outputting suggestions of resource allocation or configuration optimization. MDAS also has training and reasoning functions. In contrast to NWDAF, MDAS is part of a network management system, often running off-line and non-real time, providing operators with resource and deployment tuning optimization suggestions, trend analysis and optimization suggestions for longer periods. For convenience of description, the data analysis network element is described below as an NWDAF, and the actions performed by the NWDAF in the present application may also be performed by the MDAS.

The process of intelligent analysis by NWDAF is described below. The NWDAF may collect data in multiple dimensions from multiple sources, perform correlation analysis, output historical statistics, or train and fit a model, and output predicted values of network metrics according to the model, so as to instruct the service network element to adjust network parameters to optimize the network metrics. It should be appreciated that different network metrics correspond to different network parameters, and that network metrics are related to network operating conditions. The network parameters may include time, UE location, application location, bit rate of traffic flow, packet delay, number of transmitted and retransmitted messages, and the like.

Taking the process of intelligent analysis (hereinafter referred to as service experience analysis) using a network index as a service experience, where the service experience refers to the experience evaluation of a user for accessing a service process through a network, the network index may be a quantitative evaluation performed by the user, and the process may include the following steps:

step 1, nwdaf first collects the following data:

(1) Collect experience scores for traffic from AF, percentage of UEs that reach the experience scores (e.g. the quality of traffic experience is excellent in proportion of no less than 90%), IP address of UEs, location information of applications (e.g. data network access identity (data network access identify, DNAI). Where experience scores are e.g. average subjective rating (mean opinion score, MOS).

(2) Collecting location information of the UE (e.g., global cell identity (global cell identifier, GCI)) from the subscriber permanent identity (subscription permanent identifier, SUPI) of the UE through the AMF;

(3) Collecting from the SMF the SUPI of the UE, a network slice identity of the PDU session (e.g., single-network slice selection assistance information (S-nsai)), information of the UPF (e.g., UPF Identity (ID)), IP filtering information, and traffic flow identity (QoS flow identifier, QFI);

(4) The parameters of bit rate, end-to-end delay (or packet delay), number of transmitted and retransmitted messages, etc. of the traffic flow are collected from the UPF.

Step 2, the nwdaf uses the IP filtering information and the IP address of the UE to associate the data collected from the AF of one UE with the data collected from the SMF of the same UE, and then associates the location data collected from the AMF of the same UE with the session data from the SMF according to the SUPI. The data collected from the UPF for the same UE is further correlated with the above data by QFI. Similarly, NWDAF further performs association analysis on data of a large number of UEs.

And 3, training and fitting a model by the NWDAF according to the data. For example, training a deep learning network using the data. Such as shown in fig. 2.

The training process uses a training function, for example, NWDAF uses network parameters such as a location of a UE, a location of an application, a time, a bit rate of QoS Flow, a packet delay, a number of transmission and retransmission packets, etc. as an argument (independent variables), uses network indexes such as a service experience and a UE duty ratio reaching a corresponding service experience as an argument (dependent variables), and trains the deep learning network using the data after the correlation processing, so as to obtain a deep learning model (deep learning model). That is, during the training process, the independent variable is a network parameter and the dependent variable is a network indicator.

And 4, setting a deep learning model obtained by training as an inference mode (namely using an inference function) by the NWDAF, predicting the most probable value range of each independent variable in the future according to the historical statistical variation trend of each independent variable, and calculating and outputting the predicted result of the dependent variable in the future according to the deep learning model obtained by training and the predicted value of each independent variable.

Accordingly, through the business experience analysis process, the NWDAF can predict the predicted value of the network index corresponding to the network parameter. The NWDAF may also send the predicted value to a service network element (or referred to as a service processing network element) for the service network element to adjust the network parameter according to the predicted value, so that the network index after adjusting the network parameter is optimized.

In particular, during the business experience analysis process, the business network element may include SMF, the network parameter may include QoS parameter, and the network index may include experience score. NWDAF may output the predicted value of experience score to SMF. The SMF may determine an adjusted QoS parameter based on the predicted value of the experience score, which may include, in particular, an adjusted bit rate and/or an adjusted packet delay. The SMF may also perform the adjusted QoS parameters through the UPF to improve traffic scoring through optimization of the QoS parameters.

However, in the above process of analyzing the service experience, the NWDAF outputs a predicted network index, and the service network element refers to the predicted value to adjust the network parameter, but in some cases, the adjustment manner of the network parameter determined by the service network element according to the predicted value may not meet the requirement of the service network element on the adjustment of the network parameter. Still taking the service experience analysis process as an example, if the adjustment manner of the network parameter corresponding to the predicted value output by the NWDAF is to adjust the end-to-end delay of the network slice, but the SMF may not support the adjustment or does not wish to make the adjustment, or wishes to adjust other network parameters, such as the bit rate, at this time, the SMF may not be able to adjust the network parameter according to the predicted value, so the predicted value has no practical value. Therefore, the NWDAF needs to analyze according to the requirements of the service network element, so that the analysis service of the data analysis network element meets the requirements of the analysis request network element.

In order to enable analysis services of a data analysis network element to meet requirements of an analysis request network element, the embodiment of the application provides a communication method. The communication method may be performed by a data analysis network element and an analysis request network element. As shown in fig. 3, the data analysis network element may be configured to perform intelligent analysis for a network according to a request message (or referred to as an analysis request) from an analysis request network element, and send an analysis result (or referred to as a response message corresponding to the request message) to the analysis request network element, where the data analysis network element includes NWDAF or MDAS, for example. The analysis request network element may be a network element in the network to be analyzed, or may be a network element other than the network. The analysis request network element may include a service network element for adjusting a network parameter of the network according to an analysis result, or may include other network elements other than the service network element, for example, the analysis request network element may be, for example, an AMF or an SMF, and is not particularly limited. The network may include at least one network element, for example, including at least one NF in the architecture shown in fig. 1.

A communication method according to an embodiment of the present application is described below with reference to fig. 4, and the communication method may include the following steps:

s101: the analysis requesting network element sends a request message to the data analysis network element, the request message being usable to request recommended network parameters. Wherein, the request message may include at least one of analyzing network parameters required by the requesting network element and analyzing network indexes expected by the requesting network element.

In the application, at least one of the network parameters required by the analysis request network element and the network indexes expected by the analysis request network element can be used for determining the analysis result, so that the number of the analysis results can meet the requirement of the analysis request network element. The analysis result may include recommended network parameters, so that the analysis request network element can adjust the network parameters according to the recommended network parameters, so as to obtain a better network optimization effect.

In particular, analyzing the network parameters required by the requesting network element may comprise analyzing the type of network parameters required by the requesting network element, or comprise the type and value of the required network parameters. The network parameters required by the analysis request network element may be acceptable adjustment ranges of the network parameters for the analysis request network element, so that the data analysis network element determines recommended network parameters according to the acceptable adjustment ranges of the network parameters, and the recommended network parameters determined by the data analysis network element are prevented from exceeding the acceptance range of the analysis request network element. For example, taking the example of the network parameter being a bit rate and an end-to-end delay, the required network parameter may indicate an acceptable bit rate of less than or equal to 20 megabits per second (Mbps) and an acceptable end-to-end delay of greater than or equal to 20 milliseconds (ms). It should be appreciated that the request message may carry a network parameter list comprising at least one required network parameter.

Analyzing the network metrics desired by the requesting network element may include analyzing the type of network metrics desired by the requesting network element, or include the type and value (or range of values) of the desired network metrics. The network index desired by the analysis requesting network element may be a value that the analysis requesting network element wishes the network index to be able to reach. For example, if the analysis request network element wishes to adjust the network parameters so that the network index can reach a certain value, the value may be sent to the data analysis network element so that the data analysis network element can predict the recommended network parameters that enable the network index to reach the value. The data analysis network element may thus determine network parameters that bring the network metrics to the desired network metrics for determining recommended network parameters. Taking the network index as an example of MOS, if the MOS expected by the analysis request network element is not lower than 4.5, the data analysis network element may analyze network parameters that make the MOS not lower than 4.5, and determine recommended network parameters according to the network parameters, where 0.ltoreq.mos.ltoreq.5.

In one possible implementation, the request message may further include requirement information of recommended network parameters. Wherein the requirement information is used for indicating that the recommended network parameters are determined from the range of network parameters required by the analysis request network element and/or from the range of network parameters corresponding to the network index expected by the analysis request network element. In particular, the requirement information may be used to indicate as recommended network parameters a maximum or minimum network parameter within a range of required network parameters and/or within a range of network parameters corresponding to a network index expected by the analysis requesting network element, or the requirement information may be used to indicate as recommended network parameters a network parameter corresponding to a maximum or minimum value of the predicted network index. In addition, the requirement information may also be used for the cost function. The cost function is a target function for finding an optimal solution by using a training model, and is used for determining an optimal network parameter from a plurality of network parameters corresponding to network indexes expected by the analysis request network element as a recommended value. Specifically, the requirement information may be used to indicate that the cost function of the recommended network parameter is minimum, and at this time, the system overhead corresponding to the recommended network parameter is minimum.

In one possible implementation, if the request message includes a network indicator that is expected by the analysis requesting network element, the request message may further include a desired proportion of the network indicator to reach the expected network indicator. Taking the network indicator as an example of MOS, the desired ratio may indicate that after the network parameter is adjusted according to the analysis result corresponding to the data request message, the MOS of the user desired by the analysis request network element reaches the desired ratio of the desired MOS, for example, the desired ratio is not less than 90%.

In a possible implementation manner, the request message may further include an analysis type identifier for analyzing the analysis type requested by the requesting network element, for example, carrying analysis of service experience.

In this application, the request message shown in S101 may be a request for requesting the data analysis network element to provide the intelligent analysis service, or may be a subscription request for requesting to subscribe to the analysis service. If the request is a request for providing intelligent analysis service, the data analysis network element outputs an analysis result to the analysis request network element at one time according to the request. If the subscription request is the subscription request of the analysis service, the data analysis network element outputs analysis results to the analysis request network element for a plurality of times according to the request, timing or event triggering until the analysis request network element cancels the subscription. If the request message is a subscription request, the request message may further include a subscription identifier, where the subscription identifier is used to identify the subscription, and the analysis request network element may distinguish different analysis subscriptions through the subscription identifier.

Accordingly, the data analysis network element receives a request message from the analysis request network element.

S102: after receiving the request message, the data analysis network element may determine recommended network parameters according to network parameters required by the analysis request network element and/or network indexes expected by the analysis request network element. In one possible implementation, the recommended network parameter determined in S102 is within the range of the network parameter required by the analysis requesting network element and/or the predicted network index corresponding to the recommended network parameter is within the range of the desired network index.

In S102, the data analysis network element may determine recommended network parameters through the trained model. If no trained model exists, the data analysis network element needs to enter a model training stage first, and a trained model is obtained in the training stage. In the model training stage, input data are data collected by the data analysis network element, including independent variables (i.e. network parameters) and corresponding dependent variables (i.e. network indexes) of the model, and the structure and internal parameters of the network model, i.e. the trained model, are output, and at this time, the data analysis network element obtains the trained model. If the data analysis network element already has a trained model, for example, obtained through a previous training phase, or received from other network elements or devices, the data analysis network element may use the trained model for reasoning, prediction, or recommendation. When the model is used for reasoning and prediction, the input data of the model may include independent variables and the output results of the model may include dependent variables. When the trained model is used to determine recommended arguments, the input data of the model may include predicted dependent variables of the model (i.e., one or more network metrics predicted to be achieved, which may be specifically the network metrics expected by the analysis requesting network element in S102), and the output results of the model may include at least one type of recommended argument (i.e., one or more network parameters).

Further, the data analysis network element may determine, according to the request message, a type of network parameter required by the analysis request network element, and determine, according to the type of network parameter required, one or more types of independent variables that need to output recommended values from the plurality of types of independent variables of the trained model, as recommended network parameters. The data analysis network element may furthermore determine other types of recommended network parameters than the type of required network parameters (hereinafter called non-required network parameters), which may take the current or historical average of the type of network parameters, or may also take a predicted value of the future maximum probability of occurrence of the type of network parameters. And then the data analysis network element analyzes and outputs the recommended value of the corresponding one or more network parameters according to the model and the one or more predicted network indexes, wherein the recommended value of the network parameter comprises the recommended value of the required network parameter and can also comprise the recommended value of the un-required network parameter. For example, the type of network parameter required is a bit rate, the data analysis network element may determine a recommended bit rate, and may also determine a recommended value for the recommended end-to-end delay, and send the recommended bit rate and the recommended end-to-end delay to the analysis requesting network element.

In one possible implementation manner, the output result of the data analysis network element may further include a predicted ratio of the network index reaching the predicted network index, where the predicted ratio may indicate a ratio of the actual network index reaching the predicted network index corresponding to the network parameter after the adjustment performed by using a certain network parameter, and the data analysis network element may further send the predicted ratio corresponding to the recommended network parameter to the analysis request network element. Wherein the predicted ratio may be equal to or greater than the desired ratio in the request message or may be less than the desired ratio in the request message. The predicted proportions may help the analysis requesting network element determine whether to accept recommended network parameters and make adjustments.

It should be understood that the training process of the model described herein may be performed in the data analysis network element, or the trained model may be obtained by other network elements through training and then sent to the data analysis network element. If the model is determined by the data analysis network element, the data analysis network element may collect data and train the model at certain periods, thus eliminating the need to retrain the model each time a network intelligence analysis is performed.

In the implementation of S102, the data analysis network element may determine, by using the model, a network parameter and a predicted value of a predicted network indicator corresponding to the network parameter, and determine a network parameter (hereinafter referred to as an alternative network parameter) with a better predicted value of the corresponding predicted network indicator, where the alternative network parameter may be used to determine the recommended network parameter. The predicted network index corresponding to the network parameter is a network index that is an output result of the model when the network parameter is input data of the model (or is a part of the input data). In one possible implementation, the alternative network parameter is within the range of network parameters required by the analysis requesting network element and/or the predicted network index corresponding to the alternative network parameter is within the range of desired network index.

Taking the service experience analysis as an example, if the network index is MOS, the data analysis network element may determine a network parameter that makes the MOS not lower than a threshold (e.g. 4.5) as an alternative network parameter, and further determine the recommended network parameter according to the alternative network parameter. In one possible implementation, the threshold is a network index desired by the analysis requesting network element.

In a possible implementation manner, in determining the recommended network parameter, if the network parameter required by the analysis request network element is included in the request message, in S102, the recommended network parameter determined by the data analysis network element is within the range of the required network parameter. For example, the data analysis network element uses the required network parameter as given input data to determine an output result, determines an output result with a higher value in the range of the obtained output result, and uses the network parameter corresponding to the output result with the higher value as an alternative network parameter. Taking service experience analysis as an example, the network parameters required by the analysis request network element are, for example, bit rate less than or equal to 20Mbps and end-to-end delay greater than or equal to 20ms, the recommended network parameters determined by the data analysis network element include bit rate and end-to-end delay, the bit rate is not higher than 20Mbps, and the end-to-end delay is not lower than 20ms.

In addition, if the request message includes the network index expected by the analysis request network element, in determining the candidate network parameter, the data analysis network element may determine a range of the network parameter corresponding to the expected network index according to the model, for example, the data analysis network element determines the input data with the expected network index as a given output result, and the obtained range of the input data, that is, the range of the network parameter corresponding to the expected network index, and then the data analysis network element may determine the candidate network parameter from the range of the network parameter corresponding to the expected network index, and then determine the recommended network parameter according to the candidate network parameter. Still taking the service experience analysis as an example, if the network index expected by the analysis request network element is, for example, MOS not lower than 4.5, the MOS corresponding to the recommended network parameter determined by the data analysis network element is not lower than 4.5.

If the request message includes a desired proportion of network metrics that reach the desired network metrics, the output result of the model may further include a predicted proportion of network metrics that reach predicted network metrics, and in determining the alternative network parameters, the data analysis network element may determine, as the alternative network parameters, network parameters such that the output result includes a predicted proportion that is not lower than the desired proportion. For example, the desired ratio is not less than 95%, and the data analysis network element may determine a network parameter such that the predicted ratio is not less than 95% as an alternative network parameter, and further determine a recommended network parameter from the alternative network parameters.

In one possible implementation manner, if the output result of the model includes that the network index reaches the predicted ratio of the predicted network index, the data analysis network element may further determine the predicted ratio corresponding to the recommended network parameter, where the input data of the model includes the recommended network parameter, and the output result of the model includes the predicted ratio corresponding to the recommended network parameter. The data analysis network element may also send a predicted ratio corresponding to the recommended network parameter to the analysis request network element, where the predicted ratio is used to indicate that the actual network index reaches the predicted ratio of the network index after the adjustment is performed using the recommended network index.

In one possible implementation, the data analysis network element may also determine a tolerance range for the network parameters to which the recommended network parameters belong. The data analysis network element may also send the tolerance range to the analysis request network element. The tolerance range may be a range of values including recommended network parameters, the range of values representing values of acceptable actual network parameters. It should be understood that, after the analysis request network element or other service network element adjusts the network parameters according to the analysis result, the network index corresponding to the actual network parameter has a certain deviation from the predicted network index corresponding to the recommended network parameter, and the data analysis network element may determine and indicate the range of the numerical value of the acceptable actual network parameter, that is, the tolerance range, to the analysis request network element, so that the analysis request network element adjusts the network parameters within the range. For example, the analysis requesting network element may ensure that the actual value of the adjusted network parameter is not outside of this tolerance range. In the present application, the tolerance range may be represented by a distance between a center value of the tolerance range and a boundary value of the tolerance range. Wherein the central value of the tolerance range may be the recommended network parameter. Taking the example that the network parameter is a bit rate, if the recommended bit rate is 20Mbps and the tolerance range is 19Mbps to 21Mbps, the tolerance range can be represented by 20±1Mbps, and 1Mbps is the radius of the tolerance range. The network index corresponding to the actual bit rate may deviate from the predicted network index corresponding to the recommended network parameter by a certain degree.

In one possible implementation, the data analysis network element may determine the tolerance range of the network parameter according to the desired proportion of the network indicator. For example, if the expected proportion in the request message is not less than 95%, the data analysis network element may determine some values of the network parameter, and if the values are greater than or smaller than the values, the following conditions may be satisfied: compared with the predicted value of the network index corresponding to the recommended network parameter, the predicted value of the corresponding network index is controlled within the deviation range of not more than 5 percent. The data analysis network element takes the value as the boundary value of the tolerance range of the network parameter.

When the desired proportion of the network index is not specified in the request message, the data analysis network element can also push back the tolerance range of the network parameter according to the preconfigured guarantee rate or the guarantee rate indicated by other network elements or devices. For example, when the preconfigured guarantee rate is not lower than 90%, the data analysis network element may determine that the value deviation between the value range of the corresponding predicted network index and the value of the network index of the recommended network parameter is not more than 10%, and use the value as the boundary value of the tolerance range of the network parameter.

In addition, the data analysis network element may also determine a guaranteed rate, which is a probability that an actual network indicator (or predicted network indicator) corresponding to a network parameter within the tolerance range can meet a predicted network indicator corresponding to a recommended network parameter. For example, the data analysis network element may determine that the assurance rate is not less than 90% according to the pre-configuration, and then determine the corresponding tolerance range of the network parameters according to this assurance rate. That is, according to the model, when the network parameters are within the tolerance range, the predicted network metrics can be achieved with a 90% probability. For example, when the actual bit rate is 20Mbps, the predicted MOS value is equal to or greater than 4.5, and when the network parameter is within the tolerance range of 20±1Mbps, the predicted MOS value can be equal to or greater than 4.5 with a 90% probability. The analysis request network element can decide whether to strictly adjust according to recommended network parameters or to relatively loosely control the value of the network parameters within a tolerance range according to the guarantee rate.

It should be appreciated that the above tolerance ranges and assurance rates are determined for one type of network parameter. For example, the recommended network parameters include a recommended bit rate and a recommended end-to-end delay, and the tolerance range and the assurance rate may be determined for the recommended bit rate and for the recommended end-to-end delay, respectively.

In one possible implementation, if the number of the alternative network parameters is plural, and the request message further includes requirement information, the data analysis network element may determine the recommended network parameter from the plural alternative network parameters according to the requirement information. The requirement information can be referred to the explanation in S101. For example, the data analysis network element may determine recommended network parameters from among the alternative network parameters based on the requirement information. For example, the data analysis network element may determine, based on the requirement information, a maximum or minimum network parameter from among the candidate network parameters as a recommended network parameter (e.g., the recommended network parameter is the network parameter that requires the lowest), or determine, from among the candidate network parameters, a network parameter that corresponds to the predicted network index that is the maximum or minimum as the recommended network parameter (e.g., the recommended network parameter is the network parameter that corresponds to the predicted network index that is optimal). For another example, when the requirement information includes a cost function, a recommended network parameter is determined according to the cost function, wherein if the requirement information requires that the cost function of the recommended network parameter is minimum, the data analysis network element can determine the network parameter with the minimum cost function from the candidate network parameters as the recommended network parameter.

Specifically, the cost function may be an expression for calculating network overhead according to a network parameter recommended by a requirement, and the data analysis network element may determine, according to the expression, a network parameter capable of minimizing the value of the network overhead expression from a plurality of candidate network parameters as the recommended network parameter. The cost function may also be an expression for calculating a service rate according to the required network parameter, and the data analysis network element may determine, as the recommended network parameter, a network parameter capable of minimizing the value of the charging rate from a plurality of alternative network parameters according to the expression.

It should be understood that the alternative network parameters described herein may also be replaced by network parameters within the range of the network parameters required by the analysis request network element and/or within the range of the network parameters corresponding to the network index desired by the analysis request network element, that is, the data analysis network element may determine the recommended network parameters from the range of the network parameters required by the analysis request network element and/or within the range of the network parameters corresponding to the network index desired by the analysis request network element according to the requirement information, and the specific manner of determining the recommended network parameters according to the requirement information is not expanded any more, which may be referred to in the description of determining the recommended network parameters from the alternative network parameters according to the requirement information.

S103: the data analysis network element sends recommended network parameters to the analysis request network element.

In one possible implementation, the data analysis network element may send an analysis result to the analysis request network element, where the analysis result may include recommended network parameters. In addition, the analysis result may further include at least one of analyzing a network parameter required by the requesting network element, analyzing a network index expected by the requesting network element, a predicted network index corresponding to the recommended network parameter, a predicted ratio corresponding to the recommended network parameter, a tolerance range of the network parameter, or a guarantee rate corresponding to the tolerance range of the network parameter.

Accordingly, the analysis requesting network element receives the recommended network parameters (or analysis results containing the recommended network parameters) from the data analysis network element. If the analysis request network element is a service network element, the analysis request network element can adjust network parameters according to recommended network parameters to optimize the network, so that the network index is improved. If the analysis request network element does not belong to the service network element, the analysis request network element may send the recommended network parameter to the service network element, or send a network adjustment policy determined according to the recommended network parameter, so that the service network element can adjust the network parameter. Taking service experience analysis as an example, the recommended network parameters include a recommended bit rate and/or a recommended end-to-end delay, the analysis request network element may be an SMF, the service network element may be a UPF, the SMF may determine an adjusted QoS parameter according to the recommended bit rate and/or the recommended end-to-end delay after receiving the analysis result, the adjusted QoS parameter may include the adjusted bit rate and/or the adjusted end-to-end delay, and the SMF may further send the adjusted QoS parameter to the UPF, so that the UPF executes the adjusted QoS parameter.

It can be seen that the communication method provided in the embodiment of the present application may send, by the analysis request network element, the required network parameters and the desired network index to the data analysis network element, so that an analysis process of the data analysis network element is performed according to the network parameters and the desired network index required by the analysis request network element, and an analysis result is obtained, where the analysis result may include recommended network parameters. The analysis result meets the requirement of the analysis request network element on network parameters and the expectation of network indexes, so that the analysis service of the data analysis network element can meet the requirement of the analysis request network element.

Several implementations of S103 are described below based on the relationship between the recommended network parameter and the range of the required network parameter, and the relationship between the predicted network index corresponding to the recommended network parameter and the range of the desired network index.

Mode 1

The recommended network parameters are within the range of network parameters required by the analysis requesting network element, and the predicted network index corresponding to the recommended network parameters is within the range of desired network indexes. In mode 1, the data analysis network element may send recommended network parameters to the analysis requesting network element.

Taking the service experience analysis process with NWDAF as the data analysis network element and SMF as the analysis request network element as an example, the communication method implemented in mode 1 provided by the embodiment of the present application includes the following steps shown in fig. 5:

s201: the SMF sends a request message to the NWDAF.

The request message includes a type identifier of the service experience analysis, a network parameter required by the SMF, an expected network index of the SMF and an expected proportion of the network index to the expected network index. Wherein the network parameters required by the SMF are used for indicating that the required bit rate is less than or equal to 20Mbps and the required end-to-end delay is greater than or equal to 20ms, and the network index expected by the SMF is used for indicating that the MOS is not lower than 4.5.

One possible implementation manner may further include requirement information in the request message, where the requirement information may be referred to as description in S101.

Accordingly, the NWDAF receives the request message.

S202: the NWDAF may determine an analysis result according to the request message after identifying the type identifier carried in the request message, where the analysis result includes recommended network parameters. For example, the recommended network parameters include a recommended bit rate and a recommended end-to-end delay, e.g., 15Mbps for the recommended bit rate and 30ms for the recommended end-to-end delay.

In practice, the NWDAF may use the network index desired by the SMF as a dependent variable of the model, and determine an independent variable of the model from the dependent variable and use it as a network parameter that satisfies the network index desired by the SMF. The NWDAF may obtain alternative network parameters from an intersection of network parameters meeting the network index desired by the SMF and network parameters required by the SMF. Further, when the candidate network parameters are plural and the request message includes the requirement information, the NWDAF may further determine the recommended network parameters from the candidate network parameters according to the requirement information, and the implementation manner may refer to the description when determining the recommended network parameters according to the requirement information in S102.

In addition, the analysis result can also include the tolerance range of the recommended network parameters or include the tolerance range and the guarantee rate of the recommended network parameters. The meaning and determination of the tolerance and assurance can be found in the description in S102. For example, the analysis results may indicate that the recommended bit rate corresponds to a tolerance range of 1Mbps with a corresponding assurance rate of 90%, and that the recommended end-to-end delay corresponds to a tolerance range of 5ms with a corresponding assurance rate of 95%. The central value of the tolerance range corresponding to the recommended bit rate may be the recommended bit rate by default, and the central value of the tolerance range corresponding to the recommended end-to-end delay is the recommended end-to-end delay.

S203: the NWDAF sends the analysis result to the SMF.

In one possible implementation, the analysis result may further include network parameters required by the SMF and/or network metrics expected by the SMF.

Accordingly, the SMF receives the analysis result.

S204: and the SMF determines the adjusted QoS parameters according to the analysis result.

S205: the SMF sends the adjusted QoS parameters to the UPF.

Accordingly, the UPF receives and performs the adjusted QoS parameters.

Mode 2

The recommended network parameters are within the range of network parameters required by the analysis requesting network element, and the predicted network index corresponding to the recommended network parameters is not within the range of the desired network index. In mode 2, if the data analysis network element determines that no network parameter is within the range of the required network parameters, but at least one network parameter is within the range of the required network parameters such that the corresponding predicted network index does not differ greatly from the range of the desired network index, or the network parameters are such that the corresponding predicted network index approaches the range of the desired network index, the data analysis network element may use the at least one network parameter as a recommended network parameter, and the data analysis network element may send the recommended network parameter to the analysis request network element in S103. In addition, the data analysis network element may further send a predicted network index corresponding to the recommended network parameter to the analysis request network element, where the analysis request network element determines whether to accept the recommended network parameter according to the predicted network index corresponding to the recommended network parameter. For example, the analysis request network element considers that the predicted network index corresponding to the recommended network parameter does not meet the requirement, for example, the predicted network index is far away from the expected network index, and then the decision is made not to accept the recommended network parameter; if the analysis requesting network element considers that the predicted network indicator corresponding to the recommended network parameter is acceptable, it may decide to accept the recommended network parameter.

The predicted network index corresponding to the network parameter does not differ much from the expected network index range, which means that the distance between the predicted network index corresponding to the network parameter and the expected network index range is within a first threshold. In one possible implementation, the first threshold may be determined according to a range of desired network metrics, e.g., in proportion to or in size according to the range of desired network metrics. Alternatively, the first threshold may be preconfigured in the data analysis network element or indicated by the analysis requesting network element, other network element or device.

In a possible implementation manner, in mode 2, the data analysis network element may further send indication information to the analysis request network element, where the first indication information may be used to indicate whether the analysis request network element decides to accept the recommended network parameter. In particular, the indication information may be used to indicate that the recommended network parameter cannot meet the range of the desired network index, or information used to indicate whether the recommended network parameter is received or not by the service request network element. For example, the indication information may be an identifier carried in a specific bit.

If the analysis request network element accepts the recommended network parameter, that is, adjusts the network parameter by adopting the recommended network parameter, the analysis request network element may send response information corresponding to the indication information to the data analysis network element, so as to indicate that the analysis request network element accepts the recommended network parameter.

Taking the service experience analysis procedure with NWDAF as the data analysis network element and SMF as the analysis request network element as an example, the communication method implemented in manner 2 provided in the embodiment of the present application includes the following steps shown in fig. 6:

s301: the SMF sends a request message to the NWDAF, the request message being a subscription request. The request message may carry a subscription identification.

The request message includes a type identifier of the service experience analysis, a network parameter required by the SMF, an expected network index of the SMF and an expected proportion of the network index to the expected network index. Wherein, the network parameter required by the SMF is used for indicating that the bit rate is less than or equal to 10Mbps, and the network index expected by the SMF is used for indicating that the MOS is not lower than 4.5.

Accordingly, the NWDAF receives the request message.

S302: the NWDAF sends a response message to the SMF to subscribe to the request.

Wherein the response message may be used to indicate that the subscription was successful. The subscription identification in S301 may be included in the response message to the subscription request.

Accordingly, the SMF receives a response message to the subscription request.

S303: the NWDAF may determine an analysis result according to the request message after identifying the type identifier carried in the request message, where the analysis result includes the recommended network parameter and a predicted network indicator corresponding to the recommended network parameter. Wherein the recommended network parameters cannot meet the range of desired network metrics. The NWDAF takes as recommended network parameters network parameter values that enable the predicted network index to be closest to the range of desired network indexes within the range of required network parameters.

In implementations, the NWDAF may determine that within the range of required network parameters, no network parameters can bring the predicted dependent variable (i.e., network index) within the range of desired network indices, using the network parameters required by the SMF as the independent variables of the model, and using the network index desired by the SMF as the dependent variable of the model. For example, the recommended network parameters include a recommended bit rate, e.g., 10Mbps, which is a bit rate that does not exist within the range of less than or equal to 10Mbps required by the SMF to meet the desired MOS value of 4.5 or more, but the MOS value is optimal (e.g., equal to 4.3) when the bit rate is equal to 10 Mbps. The NWDAF will then take the 10Mbps bit rate as the recommended network parameter. And meanwhile, taking MOS equal to 4.3 as a predicted network index corresponding to the recommended network parameter.

The NWDAF may determine the recommended network parameters from the alternative network parameters, which is not further developed herein, see the description in the present application.

In addition, the analysis result can also include the tolerance range of the recommended network parameters or include the tolerance range and the guarantee rate of the recommended network parameters. The meaning and determination of the tolerance and assurance can be found in the description in S102. For example, the analysis results may indicate that the recommended bit rate corresponds to a tolerance range radius of 1Mbps and a corresponding assurance rate of 90%. Wherein the center value of the tolerance range corresponding to the recommended bit rate may be defaulted to the recommended bit rate.

In one possible implementation, the analysis result includes indication information for indicating whether the SMF decides to accept the recommended network parameter.

S304: the NWDAF sends the analysis result to the SMF. The analysis result may include the subscription identification in S301.

Accordingly, the SMF receives the analysis result.

If the SMF accepts the recommended network parameter, S305 is performed, otherwise if the SMF does not accept the recommended network parameter, the present flow is ended, or response information indicating that the recommended network parameter is refused to be accepted is transmitted to the NWDAF, after which the recommended network parameter may be re-determined by the NWDAF.

S305: the SMF sends response information to the NWDAF indicating the network parameters that accepted the recommendation. The subscription identification in S301 may be included in the response information. The subscription identification in S301 may be included in the response information.

After that, S306-S307 are performed, and S306-S307 are shown with reference to S204-S205.

Accordingly, the NWDAF receives the response information.

S308: NWDAF stores the current recommendation. The recommended result includes, but is not limited to, an analysis result, and may further include a result that the SMF indicated by the response information in S305 accepts or does not accept the recommended network parameter. In a subsequent time, the NWDAF may use these stored recommendations to determine whether the actual network metrics agree with the predicted network metrics, further training the model, enhancing the accuracy of the predictions and recommendations. It should be understood that the execution timing of S308 and S306 is not limited in this application.

The flow shown in fig. 6 differs from the flow shown in fig. 5 mainly in that: the NWDAF determines that the recommended network parameter is within the range of the network parameter required by the analysis request network element, and the predicted network index corresponding to the recommended network parameter is not within the range of the expected network index, so that the analysis request network element can determine whether to accept the recommended network parameter according to the predicted network index corresponding to the recommended network parameter. If the recommended network parameters are accepted, the steps S305 to S308 may be continued, and the adjustment of the network parameters is performed according to the recommended network parameters.

Mode 3

The recommended network parameters are not within the range of network parameters required by the analysis requesting network element, and the predicted network index corresponding to the recommended network parameters is within the range of desired network indexes. In mode 3, if it is determined that no network parameter can make the predicted network index within the range of the desired network index, but at least one network parameter outside the range of the required network parameter can make the corresponding predicted network index within the range of the desired network index, the data analysis network element may use the at least one network parameter as a recommended network parameter if the at least one network parameter does not differ greatly from the range of the required network parameter, and the data analysis network element may send the recommended network parameter to the analysis request network element in S103 and send the predicted network index corresponding to the recommended network parameter. Wherein the predicted network indicator corresponding to the recommended network parameter is not within the range of the desired network indicator.

Wherein the network parameter does not differ much from the range of the required network parameter, meaning that the distance between the network parameter and the range of the required network parameter is within a second threshold. In one possible implementation, the second threshold may be determined according to a range of desired network parameters, e.g., according to a certain ratio or size of the range of desired network parameters. Alternatively, the second threshold may be preconfigured in the data analysis network element or indicated by the analysis requesting network element, other network element or device.

In a possible implementation manner, in mode 3, the data analysis network element may further send indication information to the analysis request network element, where the first indication information may be used to indicate whether the analysis request network element decides to accept the recommended network parameter. In particular, the indication information may be used to indicate a range of network parameters for which the recommended network parameter cannot meet the requirement, or information for indicating whether the recommended network parameter is received or not decided by the service request network element. For example, the indication information may be an identifier carried in a specific bit.

Taking the service experience analysis procedure with NWDAF as the data analysis network element and SMF as the analysis request network element as an example, a communication method implemented in accordance with mode 3 provided in the embodiment of the present application includes the following steps shown in fig. 7:

s401: the SMF sends a request message to the NWDAF, the request message being a subscription request. The request message may carry a subscription identification.

Accordingly, the NWDAF receives the request message.

S402: the NWDAF sends a response message to the SMF to subscribe to the request.

Wherein the response message may be used to indicate that the subscription was successful. The subscription identification in S401 may be included in the response message of the subscription request.

Accordingly, the SMF receives a response message to the subscription request.

S403: the NWDAF may determine an analysis result according to the request message after identifying the type identifier carried in the request message, where the analysis result includes recommended network parameters, and the recommended network parameters are not within the range of the required network parameters. The NWDAF may determine, from the desired network index, network parameters for which the corresponding predicted network index is within the range of the desired network index, and take as recommended network parameters in which the range of the required network parameters does not differ much.

In implementations, the NWDAF may determine that within the range of required network parameters, no network parameters can bring the predicted dependent variable (i.e., network index) within the range of the desired network index, using the network index desired by the SMF as the dependent variable of the model, and using the network parameter required by the SMF as the independent variable of the model. For example, the recommended network parameters include a recommended bit rate, for example, 10Mbps, which is a bit rate that does not exist within a range of 10Mbps or less required by the SMF and satisfies a desired MOS value of 4.5 or more, but the MOS is 4.5 when the bit rate is 12Mbps, and thus the MOS value is 4.5 or more when the bit rate is 12 Mbps. At this point the NWDAF will take the bit rate of 12Mbps as the recommended network parameter.

S404: the NWDAF sends the analysis result to the SMF. The analysis result may include the subscription identification in S401.

Accordingly, the SMF receives the analysis result.

If the SMF accepts the recommended network parameter, S405 is performed, otherwise if the SMF does not accept the recommended network parameter, the present flow is ended, or response information indicating that the recommended network parameter is refused to be accepted is transmitted to the NWDAF, after which the recommended network parameter may be re-determined by the NWDAF.

S405: the SMF may send response information to the NWDAF indicating the network parameters that accepted the recommendation. The subscription identification in S401 may be included in the response information. The subscription identification in S401 may be included in the response information. After that, S406 to S407 are performed, and S406 to S407 are shown with reference to S204 to S205.

Accordingly, the NWDAF receives the response information.

S408: NWDAF stores the current recommendation.

The implementation of S408 can be seen from the description of S306.

The flow shown in fig. 7 differs from the flow shown in fig. 6 mainly in that: the NWDAF determines that the recommended network parameter is not in the range of the network parameter required by the SMF, and the predicted network index corresponding to the recommended network parameter is in the range of the expected network index, at this time, the analysis result carries the recommended network parameter, and the analysis request network element decides whether to accept the recommended network parameter. If the recommended network parameters are accepted, the steps S405 to S408 may be continued, and the adjustment of the network parameters is performed according to the recommended network parameters.

Fig. 8 and 9 are schematic structural diagrams of possible communication devices according to embodiments of the present application. These communication devices may be used to implement the functions of the data analysis network element or the analysis request network element in the above method embodiments, so that the beneficial effects of the above method embodiments may also be implemented. In the embodiment of the present application, the communication device may be a data analysis network element or an analysis request network element, or may be a module (such as a chip) applied to the data analysis network element or the analysis request network element.

As shown in fig. 8, the communication apparatus 800 includes a processing unit 810 and a transceiving unit 820. The communication device 800 is configured to implement the functions of the data analysis network element or the analysis request network element in the above-described method embodiment.

In a first embodiment, the communication device is configured to implement the functions of the data analysis network element in the foregoing method embodiment, and the transceiver unit 820 is configured to receive a request message from an analysis request network element, where the request message is used to request recommended network parameters, and the request message includes the network parameters required by the analysis request network element and the network indexes expected by the analysis request network element. The processing unit 810 may be operative to determine the recommended network parameter based on the required network parameter and the desired network indicator. The transceiver unit 820 may be further configured to send the recommended network parameters to the analysis requesting network element.

As a possible implementation method, the recommended network parameter is within the range of the required network parameter, and the predicted network index corresponding to the recommended network parameter is not within the range of the desired network index.

As a possible implementation method, the transceiver unit 820 may be further configured to send, to the analysis requesting network element, a predicted network indicator corresponding to the recommended network parameter.

As a possible implementation method, the recommended network parameter is not within the range of the required network parameter, and the predicted network index corresponding to the recommended network parameter is within the range of the desired network index.

As a possible implementation method, the transceiver unit 820 may be further configured to send indication information to the analysis request network element, where the indication information is used by the analysis request network element to decide whether to accept the recommended network parameter.

As one possible implementation method, the recommended network parameter is within the range of the required network parameter, and the predicted network index corresponding to the recommended network parameter is within the range of the desired network index.

As a possible implementation method, the transceiver unit 820 may be further configured to send a tolerance range of the network parameter to the analysis requesting network element, where the recommended network parameter belongs to the tolerance range.

As a possible implementation method, the transceiver unit 820 may be further configured to send a guarantee rate to the analysis request network element, where the guarantee rate is a probability that the predicted network index corresponding to the network parameter in the tolerance range can meet the predicted network index corresponding to the recommended network parameter.

As a possible implementation method, the request message further includes requirement information for indicating the recommended network parameter, and the data analysis network element may further determine the recommended network parameter from a range of the required network parameter and/or a range of the network parameter corresponding to the desired network index according to the requirement information. For example, the requirement information includes a cost function. As another example, the requirement information indicates that the recommended network parameter is a maximum value or a minimum value within a range of the required network parameter, or the requirement information indicates that the recommended network parameter is a maximum value or a minimum value within a range of network parameters corresponding to meet the desired network index.

In a second embodiment, the communication device is configured to implement the function of the analysis request network element in the above embodiment of the method, and the transceiver unit 820 is configured to send a request message to the data analysis network element, where the request message is used to request recommended network parameters, and the request message includes the network parameters required by the analysis request network element and the network indexes expected by the analysis request network element. The transceiver unit 820 may be further configured to receive recommended network parameters from the data analysis network element, where the recommended network parameters are determined according to the required network parameters and the network metrics expected by the analysis request network element. The processing unit 810 may be configured to adjust the network parameters according to the recommended network parameters.

In one possible design, the transceiver unit 820 may be further configured to receive indication information from the data analysis network element; the processing unit 810 may also be configured to determine whether to accept the recommended network parameter based on the indication information.

In one possible design, the recommended network parameter is within the range of the required network parameter, and the predicted network indicator corresponding to the recommended network parameter is not within the range of the desired network indicator, and the transceiver unit 820 is further configured to receive the predicted network indicator corresponding to the recommended network parameter from the data analysis network element. The processing unit 810 may determine whether to accept the recommended network parameter according to the predicted network index corresponding to the recommended network parameter and the indication information.

In one possible design, the transceiver unit 820 may be further configured to receive a tolerance range of the network parameters from the data analysis network element, where the recommended network parameters belong to the tolerance range. The processing unit 810 is specifically configured to adjust the network parameters within the tolerance range.

In one possible design, the transceiver unit 820 may be further configured to receive a tolerance range of the network parameters from the data analysis network element, where the recommended network parameters belong to the tolerance range. The transceiver unit 820 may be further configured to receive a guarantee rate from the data analysis network element, where the guarantee rate is a probability that a predicted network indicator corresponding to a network parameter in the tolerance range can meet the predicted network indicator corresponding to the recommended network parameter. Processing unit 810 is specifically operable to determine whether to adjust the network parameters within the tolerance range based on the assurance rate.

In one possible design, the request message may further include requirement information for indicating the recommended network parameters. For example, the requirement information includes a cost function. As another example, the requirement information indicates that the recommended network parameter is a maximum value or a minimum value within a range of the required network parameter, or the requirement information indicates that the recommended network parameter is a maximum value or a minimum value within a range of network parameters corresponding to meet the desired network index.

The more detailed descriptions of the processing unit 810 and the transceiver unit 820 may be directly obtained by referring to the related descriptions in the above method embodiments, and are not repeated herein.

As shown in fig. 9, the communication device 900 includes a processor 910. As an implementation method, the communication device 900 further includes an interface circuit 920, where the processor 910 and the interface circuit 920 are coupled to each other. It is understood that the interface circuit 920 may be a transceiver or an input-output interface. As an implementation method, the communication apparatus 900 may further include a memory 930, configured to store instructions executed by the processor 910 or input data required for the processor 910 to execute the instructions or data generated after the processor 910 executes the instructions.

When the communication device 900 is used to implement the above-mentioned method embodiments, the processor 910 is used to implement the functions of the above-mentioned processing unit 810, and the interface circuit 920 is used to implement the functions of the above-mentioned transceiver unit 820.

It is to be appreciated that the processor in embodiments of the present application may be a central processing unit (central processing unit, CPU), but may also be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), field programmable gate arrays (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general purpose processor may be a microprocessor, but in the alternative, it may be any conventional processor.

The method steps in the embodiments of the present application may be implemented by hardware, or may be implemented by a processor executing software instructions. The software instructions may be comprised of corresponding software modules that may be stored in random access memory, flash memory, read only memory, programmable read only memory, erasable programmable read only memory, electrically erasable programmable read only memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. In addition, the ASIC may reside in a base station or terminal. The processor and the storage medium may reside as discrete components in a base station or terminal.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a base station, a user equipment, or other programmable apparatus. The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, e.g., floppy disk, hard disk, tape; but also optical media such as digital video discs; but also semiconductor media such as solid state disks. The computer readable storage medium may be volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage medium.

In the various embodiments of the application, if there is no specific description or logical conflict, terms and/or descriptions between the various embodiments are consistent and may reference each other, and features of the various embodiments may be combined to form new embodiments according to their inherent logical relationships.

In the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. In the text description of the present application, the character "/", generally indicates that the associated object is an or relationship; in the formulas of the present application, the character "/" indicates that the front and rear associated objects are a "division" relationship.

It will be appreciated that the various numerical numbers referred to in the embodiments of the present application are merely for ease of description and are not intended to limit the scope of the embodiments of the present application. The sequence number of each process does not mean the sequence of the execution sequence, and the execution sequence of each process should be determined according to the function and the internal logic.

Claims

1. A method of communication, comprising:

the data analysis network element receives a request message from an analysis request network element, wherein the request message is used for requesting recommended network parameters, and the request message comprises the network parameters required by the analysis request network element and network indexes expected by the analysis request network element;

the data analysis network element determines the recommended network parameters according to the required network parameters and the expected network indexes;

the data analysis network element sends the recommended network parameters to the analysis request network element.

2. The method of claim 1, wherein the recommended network parameter is within the range of the required network parameter, and the predicted network indicator corresponding to the recommended network parameter is not within the range of the desired network indicator.

3. The method of claim 2, wherein the method further comprises:

and the data analysis network element sends the predicted network index corresponding to the recommended network parameter to the analysis request network element.

4. The method of claim 1, wherein the recommended network parameter is not within the range of the required network parameter, and the predicted network indicator corresponding to the recommended network parameter is within the range of the desired network indicator.

5. The method of any one of claims 2-4, wherein the method further comprises:

the data analysis network element sends indication information to the analysis request network element, wherein the indication information is used for the analysis request network element to decide whether to accept the recommended network parameters.

6. The method of claim 1, wherein the recommended network parameter is within the range of the required network parameter and the predicted network indicator corresponding to the recommended network parameter is within the range of the desired network indicator.

7. The method of claim 6, wherein the method further comprises:

and the data analysis network element sends the tolerance range of the network parameters to the analysis request network element, and the recommended network parameters belong to the tolerance range.

8. The method of claim 7, wherein the method further comprises:

the data analysis network element sends a guarantee rate to the analysis request network element, wherein the guarantee rate is the probability that the predicted network index corresponding to the network parameter in the tolerance range can meet the predicted network index corresponding to the recommended network parameter.

9. The method of any of claims 1 to 8, wherein the request message further comprises requirement information for indicating the recommended network parameter, the data analysis network element determining the recommended network parameter from the required network parameter and the desired network indicator, comprising:

and the data analysis network element determines the recommended network parameters from the range of the required network parameters and/or the range of the network parameters corresponding to the expected network indexes according to the requirement information.

10. The method of claim 9, wherein the requirement information comprises a cost function.

11. The method of claim 9, wherein the requirement information indicates that the recommended network parameter is a maximum or minimum value within a range of the required network parameter, or wherein the requirement information indicates that the recommended network parameter is a maximum or minimum value within a range of network parameters corresponding to meet the desired network metric.

12. A method of communication, comprising:

the analysis request network element sends a request message to the data analysis network element, wherein the request message is used for requesting recommended network parameters, and the request message comprises the network parameters required by the analysis request network element and network indexes expected by the analysis request network element;

The analysis request network element receives recommended network parameters from the data analysis network element, wherein the recommended network parameters are determined according to the required network parameters and network indexes expected by the analysis request network element;

and the analysis request network element adjusts network parameters according to the recommended network parameters.

13. The method of claim 12, wherein the recommended network parameter is within the range of the required network parameter, and the predicted network indicator corresponding to the recommended network parameter is not within the range of the desired network indicator.

14. The method of claim 12, wherein the recommended network parameter is not within the range of the required network parameter, and the predicted network indicator corresponding to the recommended network parameter is within the range of the desired network indicator.

15. The method of claim 13 or 14, wherein the method further comprises:

the analysis request network element receives the indication information from the data analysis network element;

and the analysis request network element determines whether to accept the recommended network parameters according to the indication information.

16. The method of claim 15, wherein the recommended network parameter is within the range of the required network parameter, the predicted network indicator corresponding to the recommended network parameter is not within the range of the desired network indicator, the method further comprising:

The analysis request network element receives predicted network indexes corresponding to the recommended network parameters from the data analysis network element;

the analysis request network element determines whether to accept the recommended network parameters according to the indication information, and the analysis request network element comprises:

and the analysis request network element determines whether to accept the recommended network parameters according to the predicted network indexes corresponding to the recommended network parameters and the indication information.

17. The method of claim 12, wherein the recommended network parameter is within the range of the required network parameter and the predicted network indicator corresponding to the recommended network parameter is within the range of the desired network indicator.

18. The method of claim 17, wherein the method further comprises:

the analysis request network element receives the tolerance range of the network parameters from the data analysis network element, and the recommended network parameters belong to the tolerance range;

the analyzing the network element according to the recommended network parameters to adjust the network parameters includes:

the analysis requests the network element to adjust the network parameters within the tolerance range.

19. The method of claim 17, wherein the method further comprises:

the analysis request network element receives a guarantee rate from the data analysis network element, wherein the guarantee rate is the probability that a predicted network index corresponding to the network parameter in the tolerance range can meet the predicted network index corresponding to the recommended network parameter;

and the analysis request network element determines whether to adjust the network parameters within the tolerance range according to the guarantee rate.

20. The method of any of claims 12-19, wherein the request message further comprises requirement information for indicating the recommended network parameter.

21. The method of claim 20, wherein the requirement information comprises a cost function.

22. The method of claim 20, wherein the requirement information indicates that the recommended network parameter is a maximum or minimum value within a range of the required network parameter, or wherein the requirement information indicates that the recommended network parameter is a maximum or minimum value within a range of network parameters corresponding to meet the desired network metric.

23. A communication device comprising a processor and a memory; the memory is configured to store computer instructions that the processor executes to cause the apparatus to perform the method of any one of the preceding claims 1 to 22.

24. A communication system, comprising:

a data analysis network element for performing the method of any of the preceding claims 1 to 11; and

and the analysis request network element is used for receiving the recommended network parameters from the data analysis network element and adjusting the network parameters according to the recommended network parameters.

25. A computer readable storage medium, characterized in that the storage medium has stored therein a computer program or instructions which, when executed by a communication device, implement the method of any of claims 1 to 22.