WO2023082878A1 - 一种通信方法及装置 - Google Patents

一种通信方法及装置 Download PDF

Info

Publication number
WO2023082878A1
WO2023082878A1 PCT/CN2022/121651 CN2022121651W WO2023082878A1 WO 2023082878 A1 WO2023082878 A1 WO 2023082878A1 CN 2022121651 W CN2022121651 W CN 2022121651W WO 2023082878 A1 WO2023082878 A1 WO 2023082878A1
Authority
WO
WIPO (PCT)
Prior art keywords
network
analysis
parameter
network element
index
Prior art date
Application number
PCT/CN2022/121651
Other languages
English (en)
French (fr)
Inventor
李卓明
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023082878A1 publication Critical patent/WO2023082878A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition

Definitions

  • the present application relates to the technical field of communication, and in particular to a communication method and device.
  • NWDAF network data analytics function
  • MDAS management data analysis system
  • NWDAF can predict the change trend of network indicators (that is, the indicators that represent the network operation status) through intelligent analysis services, and the service network elements that process services make network adjustments according to the change trends of network indicators.
  • the current data analysis network element does not support the analysis of analysis requests for relevant network parameters from multiple network elements, which cannot meet the requirements of multiple network elements for analysis services.
  • the embodiments of the present application provide a communication method and device, so that the analysis service of the data analysis network element meets the requirements of multiple network elements for the analysis service.
  • the embodiment of the present application provides a communication method, and the method may be executed by a data analysis network element or a module (such as a chip) applied to the data analysis network element.
  • the method includes: the data analysis device receives a first request message and a second request message, the first request message comes from the first analysis request network element, and the first request message is used to request a recommendation
  • the first network parameter the first request message includes the first network parameter and the first network index required by the first analysis requesting network element, the first network index is the network index expected by the first analysis requesting network element
  • the second request message comes from
  • the second request message is used to request a recommended second network parameter
  • the second request message includes the second network parameter and the second network index required by the second analysis requesting network element
  • the second network index is The second analysis requests the expected network index of the network element.
  • the data analysis network element may also determine a third network index according to the first network index and the second network index, and the third network index is a network index jointly expected by the first analysis requesting network element and the second analysis network element.
  • the data analysis network element may also determine the recommended third network parameter and the recommended fourth network parameter according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element. Network parameters.
  • the data analysis network element may also send the recommended third network parameter and the recommended fourth network parameter.
  • the data analysis network element can determine the recommended network parameters according to the common expected network index of the first analysis request network element and the second analysis request network element, so that the recommended network parameters meet the requirements of the first analysis request network element and the second analysis request network element.
  • the analysis requests the network element's requirements for the analysis service.
  • the predicted network index corresponding to the recommended third network parameter and the recommended fourth network parameter is within the range of the third network index.
  • the recommended network parameters can be more in line with the expectations of the first analysis requesting network element and the second analysis requesting network element for network indicators.
  • the data analysis network element may also send a first message to the first analysis requesting network element and/or the second analysis requesting network element, the first message is used to modify the expected network index to the third network index.
  • the network element for data analysis can use the network index expected by the network element for the first analysis request and the network index expected by the second analysis request The second is to analyze the expected network index of the requesting network element to determine the common expected network index, so as to realize the accurate determination of the third network index.
  • the data analysis network element may also send the first analysis request network element
  • the recommended third network parameter is sent, and the data analysis network element may also send the recommended fourth network parameter to the second analysis requesting network element.
  • the data analysis network element may also send a second message to the first analysis requesting network element, and the second message is used for the first analysis requesting network element to modify the required network parameter to the third network parameter.
  • the data analysis network element may also Sending the recommended third network parameter and the recommended fourth network parameter to the first analysis requesting network element.
  • the first analysis requesting network element can send a recommended The third network parameter avoids repeated adjustments.
  • the data analysis network element can also send a third message to the second analysis requesting network element, and the third message is used to cancel the network parameter obtained according to the second network parameter required by the second analysis requesting network element .
  • the data analysis network element may send the recommended third network parameter to the first analysis requesting network element, and send the recommended fourth network parameter to the second analysis requesting network element, the recommended third network parameter Corresponding to the first network parameter, the recommended fourth network parameter corresponds to the second network parameter.
  • the data analysis network element may also receive a fourth message sent by the first analysis requesting network element, the fourth message is used to indicate that the recommended third network parameter is not accepted, and the data analysis network element may further According to the fourth message, according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element, determine the recommended fifth network parameter and the recommended sixth network parameters, the recommended fifth network parameter corresponds to the first network parameter, the recommended sixth network parameter corresponds to the second network parameter, and the value of the recommended fifth network parameter is different from the value of the recommended third network parameter.
  • the data analysis requesting network element may also send the recommended fifth network parameter to the first analysis requesting network element, and send the recommended sixth network parameter to the second analysis requesting network element.
  • the data analysis network element needs to re-determine the recommended network parameters corresponding to all the analysis requesting network elements, so as to improve analysis reliability.
  • the embodiment of the present application provides a communication method, and the method may be executed by a network element of the first analysis request or a module (such as a chip) applied to the first analysis request.
  • the method includes: the first analysis requesting network element may determine a first request message, the first request message is used to request a recommended first network parameter, and the first request message includes the first analysis A first network parameter and a first network index required by the network element are requested, and the first network index is a network index expected by the first analysis requesting network element.
  • the first analysis requesting network element may also send a first request message to the data analysis network element.
  • the first analysis requesting network element may also receive the recommended third network parameter from the data analysis network element.
  • the recommended third network parameter is determined according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element, and the third network index is the first analysis request
  • the third network index is determined according to the first network index and the second network index
  • the second network index is the network index expected by the second analysis requesting network element.
  • the first analysis requesting network element may also receive a first message from the data analysis network element, where the first message is used to modify the expected network index to the third network index.
  • the first analysis requesting network element may also determine whether to modify the network index expected by the first analysis requesting network element to the third network index according to the first message.
  • the first analysis requesting network element can also receive a second message from the data analysis network element, and the second message is used for the first analysis requesting network element to modify the required network parameter to the third network parameter .
  • the first analysis requesting network element may also receive the recommended third network parameter and the recommended The fourth network parameter, the recommended third network parameter and the recommended fourth network parameter are based on the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element It is determined that the third network index is the network index jointly expected by the first analysis requesting network element and the second analysis requesting network element, the third network index is determined according to the first network index and the second network index, and the second network index is the second analysis request Request the network index expected by the network element.
  • the predicted network index corresponding to the recommended third network parameter and the recommended fourth network parameter is within the range of the third network index, and the recommended fourth network parameter is based on the third The network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element are determined, and the fourth network parameter corresponds to the second network parameter.
  • the first analysis requesting network element may also receive a recommended third network parameter from the data analysis network element.
  • the first analysis requesting network element may also send a fourth message to the data analysis network element, where the fourth message is used to indicate that the recommended third network parameter is not accepted.
  • the first analysis requesting network element may also receive a recommended fifth network parameter from the data analysis network element, the recommended fifth network parameter corresponds to the first network parameter, and the recommended fifth network parameter is based on the third network index, the first The first network parameter required by the analysis requesting network element and the second network parameter required by the second analysis requesting network element are determined, the third network index is the network index jointly expected by the first analysis requesting network element and the second analysis requesting network element, the first The three network indicators are determined according to the first network indicator and the second network indicator, and the second network indicator is a network indicator expected by the second analysis requesting network element.
  • the embodiment of the present application provides a communication method, and the method may be executed by a second analysis request network element or a module (such as a chip) applied to the second analysis request.
  • the method includes: the second analysis requesting network element may determine a second request message, the second request message is used to request a recommended second network parameter, and the second request message includes the second analysis A second network parameter and a second network index required by the network element are requested, and the second network index is a network index expected by the second analysis requesting network element.
  • the second analysis requesting network element may also send a second request message to the data analysis network element.
  • the second analysis requesting network element may also receive a recommended fourth network parameter from the data analysis network element.
  • the recommended fourth network parameter is determined according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element
  • the third network index is the first analysis request
  • the third network index is determined according to the second network index and the first network index
  • the first network index is the network index expected by the first analysis requesting network element.
  • the second analysis requesting network element may also receive a first message from the data analysis network element, where the first message is used to modify the expected network index to the third network index.
  • the second analysis requesting network element may also determine whether to modify the network index expected by the second analysis requesting network element to the third network index according to the first message.
  • the second analysis requesting network element may also receive a third message from the data analysis network element, and the third message is used to cancel the request for obtaining the recommendation based on the second network parameter required by the second analysis requesting network element.
  • Network parameters may also be used to cancel the request for obtaining the recommendation based on the second network parameter required by the second analysis requesting network element.
  • the second analysis requesting network element may also receive a recommended fourth network parameter from the data analysis network element.
  • the recommended fourth network parameter is determined according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element
  • the third network index is the first analysis request
  • the third network index is determined according to the second network index and the first network index
  • the first network index is the network index expected by the first analysis requesting network element.
  • the second analysis request network element can also receive a recommended sixth network parameter from the data analysis network element, the recommended sixth network parameter corresponds to the second network parameter, and the recommended sixth network parameter is based on the third network index, the first The first network parameter required by the analysis requesting network element and the second network parameter required by the second analysis requesting network element are determined.
  • the embodiment of the present application provides a communication device, which may be a data analysis network element or a module (such as a chip) applied to the data analysis network element.
  • the device has the function of realizing the above-mentioned first aspect and any possible design thereof. This function may be implemented by hardware, or may be implemented by executing corresponding software on the hardware.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • the embodiment of the present application provides a communication device, which may be an analysis requesting network element or a module (such as a chip) applied to the analysis requesting network element.
  • the device has the function of realizing the above-mentioned second aspect and any possible design thereof. This function may be implemented by hardware, or may be implemented by executing corresponding software on the hardware.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • the embodiment of the present application provides a communication device, which may be an analysis requesting network element or a module (such as a chip) applied to the analysis requesting network element.
  • the device has the function of realizing the above third aspect and any possible design thereof. This function may be implemented by hardware, or may be implemented by executing corresponding software on the hardware.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • the embodiment of the present application provides a communication device, including a processor and a memory; the memory is used to store computer instructions required by the processor, and when the device is running, the processor executes the computer instructions stored in the memory to The device is made to execute any implementation method in the first aspect to the third aspect and any possible design thereof.
  • the embodiment of the present application provides a communication device, including a unit or means (means) for performing each step in the first aspect to the third aspect and any possible design thereof.
  • the embodiment of the present application provides a communication device, including a processor and an interface circuit, the processor is used to communicate with other devices through the interface circuit, and implement the above-mentioned first to third aspects and any possible designs thereof method in .
  • the processor includes one or more.
  • an embodiment of the present application provides a communication device, including a processor coupled to a memory, and the processor is used to call a program stored in the memory to execute the above-mentioned first to third aspects and any possible method in design.
  • the memory may be located within the device or external to the device. And there may be one or more processors.
  • the embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores instructions, and when it is run on a communication device, the above-mentioned first to third aspects and Methods in any possible design thereof are implemented.
  • the embodiment of the present application also provides a computer program product, the computer program product includes a computer program or instruction, when the computer program or instruction is run by the communication device, the above-mentioned first to third aspects and any of them The method in the possible design is implemented.
  • an embodiment of the present application further provides a chip system, including: a processor, configured to execute the methods in the above first to third aspects and any possible designs thereof.
  • the embodiment of the present application also provides a communication system, including a data analysis network element used to implement the method in the above first aspect and any possible design thereof, and used to implement the above second aspect and any possible design thereof.
  • FIG. 1 is a schematic structural diagram of a communication system provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a machine learning model provided in an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of another communication system provided by an embodiment of the present application.
  • FIG. 4 is a flow diagram of a communication method provided by an embodiment of the present application.
  • FIG. 5 is a flow diagram of another communication method provided by the embodiment of the present application.
  • FIG. 6 is a flow diagram of another communication method provided by the embodiment of the present application.
  • FIG. 7 is a flowchart of another communication method provided by the embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of another communication device provided by an embodiment of the present application.
  • FIG. 1 is a schematic diagram of a 5G network architecture based on a service-based architecture.
  • the 5G network architecture shown in FIG. 1 may include terminal equipment, access network (access network, AN) equipment, and core network equipment.
  • the terminal device accesses the data network (data network, DN) through the access network device and the core network device.
  • the core network equipment includes some or all of the network functions (network function, NF) in the following network elements: unified data management (unified data management, UDM) network elements, network exposure function (network exposure function, NEF) network elements (Fig.
  • application function application function, AF
  • policy control function policy control function, PCF
  • access and mobility management function access and mobility management function, AMF
  • network Slice selection function network slice selection function, NSSF
  • session management function session management function, SMF
  • user plane function user plane function, UPF
  • network data analysis function network data analytics function, NWDAF
  • network repository function network repository function, NRF
  • the access network device may be a radio access network (radio access network, RAN) device.
  • radio access network radio access network
  • base station base station
  • evolved base station evolved NodeB, eNodeB
  • transmission reception point transmission reception point
  • TRP transmission reception point
  • next generation base station next generation NodeB, gNB
  • a unit for example, can be a centralized unit (central unit, CU) or a distributed unit (distributed unit, DU).
  • the radio access network equipment may be a macro base station, a micro base station or an indoor station, or a relay node or a donor node.
  • the embodiment of the present application does not limit the specific technology and specific equipment form adopted by the radio access network equipment.
  • the terminal device may be a user equipment (user equipment, UE), a mobile station, a mobile terminal, and the like.
  • Terminal devices can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (internet of things, IOT), virtual reality, augmented reality, industrial control, automatic driving, telemedicine, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc.
  • Terminal devices can be mobile phones, tablet computers, computers with wireless transceiver functions, wearable devices, vehicles, urban air vehicles (such as drones, helicopters, etc.), ships, robots, robotic arms, smart home devices, etc.
  • Access network equipment and terminal equipment can be fixed or mobile. Access network equipment and terminal equipment can be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed on aircraft, balloons and artificial satellites in the air.
  • the embodiments of the present application do not limit the application scenarios of the access network device and the terminal device.
  • the access management network element includes the functions of mobility management, access authentication/authorization, etc. It is mainly used for the attachment, mobility management, and tracking area update process of terminals in the mobile network. Incoming layer (non access stratum, NAS) message, complete registration management, connection management and reachability management, allocation tracking area list (track area list, TA list) and mobility management, etc., and transparent routing session management (session management, SM) message to the session management network element.
  • the access management network element may be an AMF network element (hereinafter referred to as AMF).
  • AMF AMF network element
  • the access management network element is also responsible for transferring user policies between the terminal equipment 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 include assigning an Internet protocol (internet protocol, IP) address to the terminal, selecting a user plane network element that provides a packet forwarding function, and the like.
  • IP Internet protocol
  • the session management network element may be an SMF network element (hereinafter referred to as SMF).
  • the selection of network elements for network slicing is mainly used to select a suitable network slice for terminal services.
  • the network element selected for network slicing may be an NSSF network element.
  • the user plane network element is mainly responsible for processing user packets, such as forwarding, charging, and lawful interception.
  • the user plane network element can serve as a protocol data unit (protocol data unit, PDU) session anchor (PDU session anchor, PSA).
  • PDU protocol data unit
  • PSA protocol data unit
  • the user plane network element may be a UPF network element (hereinafter referred to as UPF).
  • UPF can directly communicate with NWDAF through a service-like interface, or communicate with NWDAF through other channels, such as SMF or a private interface or internal interface with NWDAF.
  • Unified data management network element responsible for managing terminal subscription information.
  • the unified data management network element may be a UDM network element (hereinafter referred to as UDM).
  • Network capability opening network element is used to support the opening of capabilities and events.
  • the network element of network capability exposure may be a NEF network element (hereinafter referred to as NEF).
  • the application function network element is used to transmit the requirements from the application side to the network side, for example, QoS requirements or user status event subscription.
  • the application function network element can be a third-party functional entity, or an application server deployed by an operator.
  • the application function network element may be an AF network element (hereinafter referred to as AF).
  • the policy control network element may be a PCF network element (hereinafter referred to as PCF).
  • PCF PCF network element
  • the PCF in the actual network may also be divided into multiple entities according to the level or function, such as the global PCF and the PCF in the slice, or the session management PCF (session management PCF, SM-PCF) and the access management PCF (access management PCF). , AM-PCF).
  • the network element in the network warehouse can be used to provide the network element discovery function, and provide the network element information corresponding to the network element type based on the request of other network elements.
  • the network element of the network warehouse also provides network element management services, such as network element registration, update, de-registration, and network element status subscription and push.
  • the network element of the network warehouse may be an NRF network element (hereinafter referred to as NRF).
  • the data analysis network element can be used to collect data and perform analysis and prediction.
  • collecting data includes but is not limited to: collecting data from other NFs, such as collecting data through AMF, SMF, PCF, collecting data through NEF or directly from AF, or from operation, administration, and maintenance (OAM) systems
  • At least one of the data is collected.
  • these data can be the data of terminal equipment, access network equipment, core network elements or third-party application equipment, or the data of terminal equipment on the access network equipment, the core network network elements or the third-party application equipment.
  • data and then perform intelligent analysis based on the collected data, and output the analysis results.
  • the data analysis network element may be a NWDAF network element (hereinafter referred to as NWDAF).
  • NWDAF NWDAF network element
  • intelligent analysis refers to the analysis of collected data with the help of artificial intelligence (AI) and other intelligent technologies.
  • intelligent analysis includes but is not limited to predicting network indicators and recommending network parameters.
  • NWDAF can use machine learning models for intelligent analysis.
  • the NWDAF can also output recommended values to the above-mentioned NFs, AFs or OAMs, for use by the NFs, AFs or OAMs in implementing policy decisions.
  • 3GPP 3rd generation partnership project
  • the training function and inference function of NWDAF are split.
  • One NWDAF can only support model training function, or only support data inference function. , or support both model training and data inference functions.
  • the NWDAF supporting the model training function may also be called the training NWDAF, or the NWDAF supporting the model training logical function (model training logical function, MTLF) (NWDAF (MTLF) for short).
  • Training NWDAF can perform model training based on the acquired data to obtain the trained model.
  • the NWDAF that supports the data reasoning function may also be called the reasoning NWDAF, or the NWDAF that supports the analysis logic function (analytics logical function, AnLF) (referred to as NWDAF (AnLF) for short).
  • Inference NWDAF can input the input data into the trained model to get analysis results or inference data.
  • the training NWDAF refers to an NWDAF that supports at least a model training function.
  • training NWDAF can also support data reasoning functions.
  • An inference NWDAF refers to an NWDAF that supports at least a data inference function.
  • inference NWDAF can also support the model training function. If an NWDAF supports both the model training function and the data reasoning function, the NWDAF may be called a training NWDAF, an inference NWDAF, or a training and reasoning NWDAF or NWDAF.
  • a NWDAF can be a single network element, or can be set up together with other network elements, for example, the NWDAF is set in a PCF network element or an AMF network element.
  • DN is a network outside the operator's network.
  • the operator's network can access multiple DNs, and various services can be deployed on the DN, which can provide data and/or voice services for terminal equipment.
  • DN is a private network of a smart factory.
  • the sensors installed in the workshop of the smart factory can be terminal devices.
  • the control server of the sensor is deployed in the DN, and the control server can provide services for the sensor.
  • the sensor can communicate with the control server, obtain instructions from the control server, and transmit the collected sensor data to the control server according to the instructions.
  • DN is a company's internal office network, and the mobile phone or computer of the company's employees can be a terminal device, and the employee's mobile phone or computer can access information and data resources on the company's internal office network.
  • Npcf, Nnef, Namf, Nudm, Nsmf, Naf, Nnssf, and Nnwdaf are the service interfaces provided by the above-mentioned PCF, NEF, AMF, UDM, SMF, AF, NSSF, and NWDAF, respectively, and are used to call corresponding service operations .
  • N1, N2, N3, N4, and N6 are interface serial numbers. The meanings of these interface serial numbers are as follows:
  • N1 the interface between the AMF and the terminal device, which can be used to transmit non-access stratum (non access stratum, NAS) signaling (such as including QoS rules from the AMF) to the terminal device.
  • non-access stratum non access stratum, NAS
  • N2 the interface between the AMF and the access network device, which can be used to transfer radio bearer control information from the core network side to the access network device.
  • N3 the interface between the access network device and the UPF, mainly used to transfer the uplink and downlink user plane data between the access network device and the UPF.
  • N4 The interface between SMF and UPF, which can be used to transfer information between the control plane and the user plane, including controlling the delivery of forwarding rules, QoS rules, traffic statistics rules, etc. for the user plane, as well as user plane information report.
  • N6 interface between UPF and DN, used to transmit uplink and downlink user data flow between UPF and DN.
  • the service-oriented architecture shown in Figure 1 enables the 5G core network to form a flat architecture.
  • the network function entities of the control plane of the same network slice can discover each other through NRF and obtain each other’s information. access address information and can then directly communicate with each other over the control plane signaling bus.
  • the above-mentioned network element or function may be a network element in a hardware device, or a software function running on dedicated hardware, or a virtualization function instantiated on a platform (for example, a cloud platform).
  • a platform for example, a cloud platform.
  • the foregoing network element or function may be implemented by one device, or jointly implemented by multiple devices, or may be a functional module in one device, which is not specifically limited in this embodiment of the present application.
  • the data analysis network element in the embodiment of the present application may be the above-mentioned NWDAF, or may be a network element having the above-mentioned NWDAF function in a future communication such as a 6G network.
  • the data analysis network element may also be an MDAS.
  • MDAS is a data analysis system deployed on the network management plane, which can be used to collect management data such as performance statistics, alarms, and operation configurations for analysis and prediction, and can also output suggestions for resource allocation or configuration optimization. MDAS also has training and reasoning functions. Compared with NWDAF, MDAS is a part of the network management system, which often runs offline and in non-real time. It provides operators with resource and deployment adjustment and optimization suggestions, and trends analysis and optimization suggestions for a longer period.
  • the data analysis network element is NWDAF as an example for description below, and the actions performed by NWDAF in this application can also be performed by MDAS.
  • NWDAF can collect data of multiple dimensions from multiple sources, perform correlation analysis, output historical statistics, or train and fit a model, and output the predicted value of network indicators according to the model to guide service network elements to adjust network parameters to Optimize network indicators.
  • network indicators correspond to different network parameters, and network indicators are related to network operation status.
  • network indicators such as network service evaluation value (hereinafter referred to as service experience), network key performance indicator value or network overhead indicator, etc.
  • network parameters may include time, UE location, application location, bit rate of service flow, packet time factors such as delay, number of transmitted and retransmitted packets, etc.
  • the intelligent analysis (hereinafter referred to as service experience analysis) process in which the network index is the service experience is taken as an example.
  • the service experience refers to the user's evaluation of the user's experience in accessing the service process through the network.
  • the network index can be quantified by the user. assessment, the process may include the following steps:
  • Step 1 NWDAF first collects the following data:
  • the service experience score is, for example, an average subjective evaluation (mean opinion score, MOS).
  • SUPI subscription permanent identifier
  • GCI global cell identifier
  • UE's SUPI such as single-network slice selection assistance information (single-network slice selection assistance information, S-NSSAI)), UPF information (such as UPF identifier (identifier, ID)) from SMF )), IP filtering information and service flow identifier (QoS flow identifier, QFI);
  • network slice identifier of PDU session such as single-network slice selection assistance information (single-network slice selection assistance information, S-NSSAI)
  • UPF information such as UPF identifier (identifier, ID)) from SMF
  • IP filtering information such as IP filtering information and service flow identifier (QoS flow identifier, QFI);
  • Step 2 NWDAF associates the data collected from AF of a UE with the data collected from SMF of the same UE by using the IP filtering information and the IP address of the UE, and then associates the location data collected from AMF of the same UE with the data collected from AMF according to SUPI Associated with session data from SMF.
  • the data collected from the UPF of the same UE is further associated with the above data through QFI.
  • the NWDAF further performs association analysis on the data of a large number of UEs.
  • Step 3 NWDAF trains and fits the model according to the above data. For example, train a deep learning network using the above data.
  • the deep learning network is shown in Figure 2, for example.
  • NWDAF uses the training function to take network parameters such as UE location, application location, time, QoS Flow bit rate, packet delay, number of transmitted and retransmitted packets as independent variables (independent variables), and Network indicators such as the experience and the proportion of UEs that achieve the corresponding service experience are used as dependent variables.
  • the data after the above-mentioned correlation processing is used to train the deep learning network to obtain a deep learning model. That is, during training, the independent variable is the network parameter and the dependent variable is the network index.
  • Step 4 NWDAF sets the trained deep learning model to inference mode (that is, uses inference function), predicts the most likely value range of each independent variable in the future according to the historical statistical change trend of each independent variable, and then According to the deep learning model obtained through training, the predicted results of the output dependent variable in the future are calculated through the predicted values of each independent variable.
  • inference mode that is, uses inference function
  • the NWDAF can predict the predicted value of the network index corresponding to the network parameter.
  • the NWDAF can also send the predicted value to the service network element (or called the service processing network element), so that the service network element can adjust the network parameters according to the predicted value, so that the network index after adjusting the network parameters can be optimized.
  • the service network element may include the SMF
  • the network parameters may include the QoS parameters
  • the network indicators may include the experience score.
  • the NWDAF can output the predicted value of the experience score to the SMF.
  • the SMF may determine an adjusted QoS parameter according to the predicted value of the experience score, and the adjusted QoS parameter may specifically include an adjusted bit rate and/or an adjusted packet delay.
  • the SMF can also implement the adjusted QoS parameters through the UPF, so as to improve the service score through the optimization of the QoS parameters.
  • NWDAF cannot analyze the request messages from multiple analysis requesting network elements, and only analyzes each service request separately, which may cause conflicts between the analyzes performed by NWDAF for different requests. Therefore, the analysis result cannot meet the requirements of all analysis requesting network elements at the same time.
  • the network indicator expected by the first analysis requesting network element is of the same type as the network indicator expected by the second analyzing network element, but with different values, this may cause a conflict.
  • SMF and AF request recommended network parameters from NWDAF respectively.
  • the range of MOS expected by SMF is not less than 4.5
  • the range of MOS expected by AF is not less than 4.
  • NWDAF responds to the request of SMF and AF respectively.
  • the request determines the recommended network parameters corresponding to the SMF and the recommended network parameters corresponding to the AF, and the SMF adjusts according to the corresponding recommended network parameters, and the AF adjusts according to the corresponding recommended network parameters.
  • the recommended network parameters corresponding to AF can only meet the requirement of MOS not lower than 4, and may not meet the requirement of MOS not lower than 4.5. Therefore, after AF is adjusted according to the recommended network parameters, the network MOS will not be able to reach 4.5, causing the network indicators expected by SMF to be unsatisfied.
  • the first analysis requesting network element and the second analysis requesting network element respectively request the recommended value of the same network parameter from NWDAF. If both analysis requesting network elements adjust the network parameters, it may also cause The actual network metrics do not match the expected network metrics.
  • this embodiment of the present application provides a communication method.
  • the communication method can be executed by a data analysis network element and a plurality of analysis requesting network elements.
  • the data analysis network element can be used to perform intelligent analysis for the network according to the request message (or analysis request) from multiple analysis requesting network elements, and send the analysis results to multiple analysis requesting network elements (or
  • the response message corresponding to the request message is referred to as the response message for short), for example, the data analysis network element includes NWDAF or MDAS.
  • the multiple analysis requesting network elements may be network elements in the network to be analyzed, or network elements outside the network.
  • the analysis request network element may include a service network element for adjusting the network parameters of the network according to the 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, AMF, SMF or AF etc., not specifically limited.
  • the network may include at least one network element, for example, at least one NF in the architecture shown in FIG. 1 .
  • the communication method may include the following steps:
  • the data analysis device receives a first request message from a first analysis requesting network element and a second request message from a second analysis requesting network element.
  • the first request message is used to request the recommended first network parameter, and the first request message includes the first network parameter required by the first analysis requesting network element (hereinafter referred to as the required first network parameter) and the first network index,
  • the first network index is the network index expected by the first analysis requesting network element;
  • the second request message is used to request the recommended second network parameter, and the second request message includes the second network parameter required by the second analysis requesting network element (hereinafter referred to as is the required second network parameter) and the second network index, the second network index is the network index expected by the second analysis requesting network element.
  • the first network parameter may be an adjustable network parameter of the first analysis requesting network element (or the service network element corresponding to the first analysis requesting network element), and the second network parameter may be the second analysis requesting network element (or the service network element corresponding to the first analysis requesting network element).
  • the second analysis requests adjustable network parameters of the service network element corresponding to the network element.
  • the required type of the second network parameter may be the same as or different from the required type of the first network parameter.
  • the first analysis request network element can be SMF
  • the first required network parameter at this time can be bit rate and end-to-end delay
  • the first required network parameter can indicate that the acceptable bit rate is less than or equal to 20 megabits per second (Mbps), and an indication of acceptable end-to-end latency greater than or equal to 20 milliseconds (ms).
  • the second analysis requesting network element may be AF
  • the second network parameter required at this time may be DNAI
  • the type of the first network parameter required at this time is different from the type of the second network parameter required.
  • the second analysis request network element can be UPF
  • the type of the second network parameter required at this time can be bit rate and end-to-end delay
  • the type of the first network parameter required at this time is the same as the required second network parameter
  • the parameters are of the same type.
  • the value of the required first network parameter and the value of the required second network parameter may be the same or different.
  • the network parameters required by the analysis requesting network element can be used to determine the analysis result, so that the number of analysis results can be accepted by the analysis requesting network element, so as to improve the reliability of the intelligent analysis process.
  • the analysis result may include recommended network parameters, so that the analysis requesting network element can adjust the network parameters according to the recommended network parameters, so as to obtain a better network optimization effect.
  • the first network parameters required by the first analysis requesting network element and the first network index expected by the first analysis requesting network element can be used to determine the recommended network parameters corresponding to the first analysis requesting network element
  • the second analysis requesting The second network parameter required by the network element and the second network index expected by the second analysis requesting network element may be used to determine a recommended network parameter corresponding to the second analysis requesting network element.
  • analyzing the network parameter required by the requesting network element may include analyzing the type of the network parameter required by the requesting network element, or including the type and value of the required network parameter.
  • the network parameters required by the analysis requesting network element may be an acceptable adjustment range of the network parameters for the analysis requesting network element, so that the data analysis network element determines the recommended network parameters according to the acceptable adjustment range of the network parameters, avoiding data analysis network
  • the recommended network parameters determined by the element are outside the acceptable range of the analysis requesting network element.
  • the request message may carry a network parameter list including at least one required network parameter.
  • Analyzing the expected network index of the requesting network element may include analyzing the type of the expected network index of the requesting network element, or including the type and value (or value range) of the expected network index.
  • the network index expected by the analysis requesting network element may be a value that the analysis requesting network element expects the network index to achieve. For example, if the analysis request network element hopes to adjust the network parameters so that the network index can reach a certain value, it can send this value to the data analysis network element, so that the data analysis network element can predict the recommendation that makes the network index reach the value. Network parameters. Therefore, the data analysis network element can determine the network parameters that make the network index reach the expected network index, and use it to determine the recommended network parameters.
  • the type of the network index expected by the first analysis requesting network element is the same as the type of the network index expected by the second analysis requesting network element.
  • the first analysis The type of the network index expected by the requesting network element and the type of the network index expected by the second analysis requesting network element are both experience scores, such as MOS.
  • the type of the network index expected by the first analysis requesting network element may be different from the type of the network index expected by the second analysis requesting network element.
  • the first The type of network index expected by the first analysis requesting network element is experience score (such as MOS), and the expected network index of the second analysis requesting network element is the proportion of service experience quality meeting the standard.
  • the network index can be MOS, if the MOS expected by the first analysis request network element is not lower than 4.5, then the data analysis network element can make the network parameter of MOS not lower than 4.5, and according to these The network parameters determine the recommended first network parameters, where 0 ⁇ MOS ⁇ 5.
  • the MOS expected by the second analysis requesting network element may be the same as or different from the value of the MOS expected by the first analysis requesting network element.
  • the request message may further include requirement information of recommended network parameters.
  • the requirement information may be used to indicate recommended network parameters determined within the range of network parameters required by the analysis requesting network element and/or within the range of network parameters corresponding to network indicators expected by the analysis requesting network element.
  • the requirement information may be used to indicate the maximum or minimum network parameter within the range of the required network parameter and/or within the range of the network parameter corresponding to the expected network index of the analysis requesting network element as the recommended network parameter, or, The requirement information may be used to indicate that the network parameter corresponding to the predicted maximum or minimum value of the network index is used as the recommended network parameter.
  • the required information can also be used in the cost function.
  • the cost function is an objective function for finding the optimal solution by using the training model, and is used to determine the optimal network parameter as a recommended value from a plurality of network parameters corresponding to the network index satisfying the network element expectation of the analysis request.
  • the requirement information can be used to indicate that the cost function of the recommended network parameters is the smallest, and the system overhead corresponding to the recommended network parameters is the smallest.
  • the requirement information of the first analysis requesting network element may also be included in the first request message, and the requirement information may be used to determine the recommended network parameters corresponding to the first analysis requesting network element; and/or, in the second request message It may also include requirement information of the second analysis requesting network element, and the requirement information may be used to determine recommended network parameters corresponding to the second analysis requesting network element.
  • the request message may further include an expected ratio of the network index reaching the expected network index.
  • the expected ratio may indicate the expected ratio of the user's MOS expected by the analysis requesting network element to reach the expected MOS after the network parameters are adjusted according to the analysis result corresponding to the data request message.
  • the expected ratio is not less than 90%.
  • the first request message may further include the expected ratio of the first analysis requesting network element, and/or the second request message may further include the expected ratio of the second analysis requesting network element.
  • the request message may further include the analysis type requested by the analysis requesting network element, for example, both the first request message and the second request message carry the analysis type identifier corresponding to the service experience analysis.
  • the request message shown in S101 may be a message for requesting the data analysis network element to provide the analysis service, or may be a subscription request for requesting to subscribe to the analysis service. If it is a message for requesting an analysis service, the data analysis network element outputs the analysis result to the analysis requesting network element at one time according to the request message. If it is a subscription message for the analysis service, the data analysis network element outputs analysis results to the analysis requesting network element multiple times according to the request message, timing or event triggering, until the analysis requesting network element cancels the subscription.
  • the request message may further include a subscription identifier for identifying the current subscription, and the analysis requesting network element may distinguish different analysis subscriptions through the subscription identifier.
  • the first request message from the first analysis requesting network element may carry the subscription identifier #1
  • the second request message from the second analysis requesting network element may carry the subscription identifier #2
  • the data analysis network element After receiving the subscription, each message transmitted between the first analysis request network element and the data analysis network element may carry the subscription identifier #1, and the message transmitted between the second analysis request network element and the data analysis network element Each message can carry subscription identifier #2.
  • the data analysis network element determines a third network index according to the first network index and the second network index, where the third network index is a network index jointly expected by the first analysis requesting network element and the second analysis network element.
  • the third network index may be the first network index or the second network index.
  • the third network indicator may have an MOS of not less than 4.5.
  • the third network index may be determined according to the first network index and/or the second network index.
  • the third network index may be the intersection of the first network index and the second network index.
  • the third network index can also be a compromise value between the first network index and the second network index, for example, the first network index is MOS not lower than 4.5, the second network index is MOS not lower than 4 and the third network The indicator is MOS not lower than 4.3.
  • the data analysis network element may use the union of the first network index and the second network index as the third network parameter.
  • satisfying the intersection of the first network index and the second network index means that the independent variable of the trained model includes any network parameter within the range of the network parameter required by the first analysis request network element and any network parameter in the second analysis request network element.
  • the dependent variable of the model cannot be within the range of the intersection of the first network index and the second network index.
  • the data analyzing network element may send the first message to the first analysis requesting network element. Wherein, the first message is used to modify the expected network index to the third network index. Similarly, if the third network index is different from the second network index, the data analysis network element may send a message for modifying the desired network index to the third network index (or the first message, or another message).
  • the type of the third network indicator may be the same as one of the first network indicator and the second network indicator, or the third network indicator includes the first Network Indicators and Secondary Network Indicators.
  • the network index expected by the first analysis request network element is not less than 4.5
  • the second analysis requests that the network index expected by the network element is that the proportion of service experience quality is not less than 90%
  • the proportion of the third network indicator that the MOS is not lower than 4.5 is greater than or equal to 90%.
  • the data analysis network element determines the recommended third network parameter and the recommended fourth network parameter according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element.
  • Network parameters the recommended third network parameter corresponds to the first network parameter, that is, the recommended third network parameter is determined according to the first network parameter;
  • the recommended fourth network parameter corresponds to the second network parameter, that is, That is, the recommended fourth network parameter is determined according to the second network parameter.
  • the data analysis network element can determine the recommended Network parameters. Among them, if there is no trained model, the data analysis network element needs to enter the model training phase first, and obtain the trained model in the training phase.
  • the input data is the data collected by the data analysis network element, including the independent variables of the model (including network parameters) and the corresponding dependent variables (including network indicators), and the structure and internal parameters of the output network model, that is, after training 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, the model is obtained through the previous training stage, or the model is received from other network elements or devices, the data analysis network element can use the trained model for inference, prediction or recommendation.
  • the input data of the model may include independent variables, and the output of the model may include dependent variables.
  • the input data of the model may include the dependent variable of the predicted model (including one or more predicted network indicators to be achieved, and specifically may include the third network indicator in S103 ), the output result of the model may include at least one type of recommended independent variable (for example, including a recommended third network parameter and a fourth recommended network parameter).
  • the data analysis network element can determine the type of network parameters required by the analysis request network element according to the request message, and determine the required network parameters from multiple types of recommended independent variables of the trained model according to the type of the required network parameters. One or more network parameters of the same type as the recommended network parameters.
  • the data analysis network element can also determine other types of recommended network parameters (hereinafter referred to as unrequired network parameters) other than the type of required network parameters. These unrequired network parameters can take the current value of this type of network parameter Value or historical average value, or the predicted value of the maximum probability of future occurrence of this type of network parameter.
  • the first analysis request network element is SMF
  • the network parameters required by SMF include bit rate and end-to-end delay, that is, the first network parameter includes bit rate and end-to-end delay
  • the second analysis The requesting network element is AF
  • the network parameters required by AF include DNAI, that is, the second network parameter includes DNAI
  • the data analysis network element can determine at least one set of network parameters that meet the third network index, and each set of network parameters includes at least DNAI, bit rate and end-to-end delay.
  • the data analysis network element analyzes and outputs the recommended value of one or more corresponding network parameters according to the model and the network index expected by the one or more analysis requesting network elements, where the recommended value of the network parameter includes the required network
  • the recommended values of parameters may also include recommended values of network parameters that are not required.
  • the type of network parameter required by SMF is bit rate
  • the data analysis network element can determine the recommended bit rate and the recommended end-to-end delay, and send the recommended bit rate and recommended end-to-end latency.
  • the data analysis network element can further base on the value of bit rate and end-to-end delay required by SMF, and the DNAI required by AF
  • a set of network parameters is determined from at least one set of network parameters, the bit rate and end-to-end delay in the set of network parameters are the recommended third network parameters, and the DNAI in the set of network parameters is the recommended first Four network parameters.
  • the value of the bit rate is within the range of the bit rate required by the SMF
  • the value of the end-to-end delay is within the range of the end-to-end delay required by the SMF
  • the DNAI is within the range of DNAI required by AF.
  • the dependent variable of the data analysis network element may also include a predicted ratio of the network index reaching the third network index, and the predicted ratio may indicate that the recommended third network parameter and the fourth network parameter are adopted at the same time After the adjustment, it is estimated that the actual network index can reach the ratio of the third network index, and the data analysis network element may also send the third network index and the predicted ratio.
  • the predicted ratio may be equal to or greater than the expected ratio carried in the first request message, or may be smaller than the expected ratio carried in the first request message; or, the predicted ratio may be equal to or greater than the expected ratio carried in the second request message
  • the expected proportion of may also be smaller than the expected proportion in the second request message.
  • the prediction ratio can help the analysis requesting network element to determine whether to accept and adjust the recommended network parameters.
  • the training process of the model described here may be performed in the data analysis network element, or other network elements may obtain a trained model through training and send the model to the data analysis network element. If the model is determined by the data analysis network element, the data analysis network element can collect data and train the model according to a certain period, so it is not necessary to retrain the model every time the intelligent network analysis is performed.
  • S104 The data analysis network element sends the recommended third network parameter and the recommended fourth network parameter.
  • the data analysis network element may send the first analysis result to the first analysis requesting network element or the second analysis requesting network element, and the first analysis result may include a recommended third network parameter and/or or the recommended fourth network parameter.
  • the first analysis result may further include at least one of the required third network parameter or fourth network parameter, the third network index, and the predicted ratio.
  • the two can be determined according to the important network index of one of the service analysis request network elements.
  • Network parameters recommended by each analysis requesting network element avoiding network performance degradation or service interruption caused by multiple analysis requesting network elements adjusting network parameters according to different network index targets, so as to improve the reliability of intelligent analysis.
  • the data analysis network element as NWDAF
  • the first analysis requesting network element as SMF
  • the second analysis requesting network element as AF
  • a communication method provided by the embodiment of the present application will be described with reference to FIG. 5 .
  • the method may include the following steps:
  • S201 The SMF sends a subscription request to the NWDAF.
  • the subscription request may carry the analysis type identifier corresponding to the service experience analysis, the network index expected by the SMF, and the network parameters required by the SMF.
  • the network index expected by the SMF is MOS greater than 4.0
  • the network parameters required by the SMF include the bit rate.
  • the subscription message may further carry a subscription identifier.
  • NWDAF receives the request message.
  • S202 The NWDAF sends a response message to the subscription request to the SMF.
  • the response message may be used to indicate that the subscription is successful.
  • the subscription identifier in S201 may be included in the response message of the subscription request.
  • the NWDAF may execute S202 after determining to accept the subscription request.
  • NWDAF can also store the subscription content of the SMF after accepting the subscription request of the SMF.
  • the subscription content includes but is not limited to the service type identifier in the subscription request, the network index expected by the SMF, and the network index required by the SMF. parameters and subscription ID.
  • the SMF receives the response message of the subscription request.
  • S203 The AF sends a subscription request to the NWDAF through the NEF.
  • the subscription request may carry the analysis type identifier corresponding to the service experience analysis, the network index expected by the AF, and the network parameters required by the AF.
  • the network index expected by AF is MOS greater than 4.5
  • the network parameters required by AF include DNAI.
  • the subscription message may further carry a subscription identifier.
  • the NWDAF receives the request message, and stores the subscription content corresponding to the AF, including but not limited to storing the service type identifier, the network parameters required by the AF, the network indicators expected by the AF, and the subscription identifier.
  • the NWDAF determines that the service type requested by the SMF for analysis is the same as the service type requested by the AF, but the network index expected by the SMF is inconsistent with the network index expected by the AF.
  • the NWDAF further determines that the network index jointly expected by the SMF and the AF is MOS greater than 4.0.
  • NWDAF may determine that the analysis type identifier stored in the subscription request of S201 is the same as the analysis type identifier of the subscription request of S203, and the network index expected by SMF in the subscribe request stored in S201 is different from the network index expected by AF in S203 , the NWDAF may determine that the analysis types requested by the SMF and the AF are the same and the expected network indicators are inconsistent.
  • the NWDAF sends a first message to the AF through the NEF, where the first message is used to modify the expected network index to make the MOS greater than 4.0.
  • the first message may also carry the subscription identifier in S204.
  • the AF receives the first message.
  • S206 The AF sends an updated subscription request to the NWDAF through the NEF, where the expected network index carried indicates that the MOS is greater than 4.0.
  • the subscription identifier shown in S204 may be carried in the updated subscription request.
  • the NWDAF receives the updated subscription request, and updates the subscription content of the AF according to the updated subscription request.
  • the subscription content of the AF includes the service type identifier, the network indicator expected by the AF (the value in the subscription request updated for S206), Network parameters and subscription identifiers required by AF.
  • the NWDAF determines that the subscription of the SMF and the subscription of the AF have the same expected network index, and determines recommended network parameters according to the expected network index, the network parameters required by the SMF, and the network parameters required by the AF.
  • the recommended network parameters include: the recommended bit rate is 14 Mbps, and the recommended DNAI ID is DNAI#1.
  • the NWDAF may associate the recommended bit rate with the identifier of the SMF and the subscription identifier in S201, and associate the recommended DNAI with the identifier of the AF and the subscription identifier in S204.
  • the NWDAF may send the recommended bit rate and the subscription identifier in S201 to the SMF.
  • the SMF receives the recommended bit rate.
  • S209 The NWDAF sends the recommended DNAI to the AF through the NEF.
  • the NWDAF may send the recommended DNAI and the subscription identifier in S204 to the AF through the NEF.
  • AF receives recommended DNAI.
  • NWDAF when receiving analysis requests from multiple analysis requesting network elements, if NWDAF determines that the service type identifiers of the multiple analysis requests are the same, but the values of the expected network indicators are different, then NWDAF can Determining a common expected network index of multiple analysis requesting network elements, and determining recommended network parameters according to the common expected network index can avoid conflicts when different analysis requesting network elements adjust network parameters.
  • the data analysis network element may send recommended network parameters to the first analysis request network element and/or the second analysis request network element, at this time
  • the type of the recommended network parameter obtained by an analysis requesting network element may be different from the type of the first network parameter, and/or the type of the recommended network parameter obtained by the second analysis requesting network element may be different from the type of the second network parameter .
  • S104 will be illustrated below in combination with different situations of whether the type of the first network parameter and the type of the second network parameter overlap.
  • the data analysis network element may report to the second network parameter
  • An analysis requesting network element sends a recommended third network parameter, and sends a recommended fourth network parameter to a second analysis requesting network element.
  • network parameter A corresponds to the network parameter B
  • the network parameter A and the network parameter B may include at least one type of network parameter.
  • network parameter A and network parameter B both include these two kinds of network parameters a and b, then it can be said that network parameter A corresponds to network parameter B, and/or, network parameter A (or network parameter B) corresponds to a and b These two network parameters.
  • the first network parameter corresponds to the third network parameter and the fourth network parameter
  • the second network parameter corresponds to the fourth network parameter
  • the third network parameter and The fourth network parameters do not overlap.
  • the data analysis network element can implement network parameter recommendation in any of the following ways:
  • the data analysis network element may send the recommended third network parameter and the recommended fourth network parameter to the first analysis requesting network element. At this time, it is not necessary to send the recommended third network parameter and the recommended Four network parameters.
  • the first analysis request network element is SMF
  • the first network parameter required by SMF includes bit rate
  • the second analysis request network element is UPF
  • the second network parameter required by UPF includes bit rate and end-to-end delay
  • SMF Both the first required network parameter and the second network parameter required by the UPF include a bit rate.
  • the data analysis network element may send the recommended bit rate and the recommended end-to-end delay to the SMF, and send the recommended bit rate to the UPF.
  • the network parameters recommended by the data analysis network element to the first analysis request network element and the second analysis request network element are respectively different from the network parameters required by the first analysis request network element and the network parameters required by the second analysis request network element.
  • the types of the parameters are the same, so that the recommended network parameters can meet the requirements of the analysis request network element.
  • the data analysis network element may send the recommended third network parameter to the first analysis requesting network element, and send the recommended fourth network parameter to the second analysis requesting network element.
  • the first analysis requesting network element is UPF
  • the first network parameter required by UPF includes bit rate and end-to-end delay
  • the second analysis requesting network element is SMF
  • the second network parameter required by SMF includes bit rate
  • UPF Both the first required network parameter and the second network parameter required by the SMF include a bit rate.
  • the data analysis network element can send the recommended end-to-end delay to the UPF, and send the recommended bit rate to the SMF.
  • the data analysis network element may send a second message to the first analysis requesting network element at this time,
  • the second message can be used to cancel the request (or subscription) of the first analysis requesting network element for the required fourth network parameter, or the second message can be used to modify the network parameter required by the first analysis requesting network element to the third network parameter parameter, or the second message is used to indicate that the recommended fourth network parameter has been sent to the second analysis requesting network element, or the second message may be used to indicate that the second analysis requesting network element performs the analysis according to the recommended fourth network parameter Adjustment of network parameters.
  • the data analysis network element may also send a second message to the UPF to indicate to cancel the request of the UPF for the recommended bit rate.
  • the data analysis network element can send the recommended third network parameter and the recommended fourth network parameter to the first analysis requesting network element, and at this time it is not necessary to send the recommended third network parameter and recommended network element to the second analysis requesting network element The fourth network parameter of .
  • the first analysis requesting network element is UPF
  • the first network parameter required by UPF includes bit rate and end-to-end delay
  • the second analysis requesting network element is SMF
  • the second network parameter required by SMF includes bit rate
  • UPF Both the first required network parameter and the second network parameter required by the SMF include a bit rate.
  • the data analysis network element can send the recommended bit rate and the recommended end-to-end delay to the UPF. At this time, the data analysis network element does not need to send the recommended bit rate to the SMF.
  • the data analysis network element can send the data analysis network element to the second analysis requesting network element.
  • the third message may be used to cancel the request (or subscription) of the second analysis requesting network element for the recommended fourth network parameter, or the third message is used to indicate that the required fourth network parameter has been sent to the second An analysis requesting network element, or, the third message may be used to instruct the first analysis requesting network element to adjust the network parameter according to the recommended fourth network parameter.
  • the data analysis network element may also send a third message to the SMF to indicate to cancel the SMF's request for the recommended bit rate.
  • the data analysis network element when it determines that there is overlap between the first network parameter and the second network parameter, it will not send the recommended overlapping network parameters to the two analysis requesting network elements, but The recommended overlapping network parameters are sent to one of the analysis requesting network elements, so as to prevent the two analysis requesting network elements from adjusting according to the recommended network parameters, resulting in excessive adjustment of network parameters.
  • the method may include the following steps:
  • S301 The SMF sends a subscription request to the NWDAF.
  • the subscription request may carry the analysis type identifier corresponding to the service experience analysis, the network index expected by the SMF, and the network parameters required by the SMF.
  • the network index expected by the SMF is MOS greater than 4.0
  • the network parameters required by the SMF include the bit rate.
  • the subscription message may further carry a subscription identifier.
  • NWDAF receives the request message.
  • S302 The NWDAF sends a response message of the subscription request to the SMF.
  • the response message may be used to indicate that the subscription is successful.
  • the subscription identifier in S301 may be included in the response message of the subscription request.
  • the NWDAF may execute S302 after determining to accept the subscription request.
  • NWDAF can also store the subscription content of the SMF after accepting the subscription request of the SMF.
  • the subscription content includes but is not limited to the service type identifier in the subscription request, the network index expected by the SMF, and the network index required by the SMF. parameters and subscription ID.
  • the SMF receives the response message of the subscription request.
  • the subscription request may carry the analysis type identifier corresponding to the service experience analysis, the network index expected by the UPF, and the network parameters required by the AF.
  • the network index expected by UPF is MOS greater than 4.0
  • the network parameters required by UPF include bit rate and end-to-end delay.
  • the subscription message may further carry a subscription identifier.
  • NWDAF receives the request message, and stores the subscription content corresponding to the UPF, including but not limited to storing service type identifiers, network parameters required by UPF, network indicators expected by UPF, and subscription identifiers.
  • the NWDAF determines that the service type requested by the SMF to be analyzed is the same as the service type requested by the UPF, and the network parameters required by the SMF overlap with those required by the AF.
  • the overlapping network parameter is the bit rate.
  • the NWDAF may determine that the analysis type identifier in the stored subscription request of S301 is the same as the analysis type identifier of the subscription request in S303, and the network parameters required by the SMF in the stored subscription request of S301 and the network parameters required by the UPF in S303 are the same. Including the same type of network parameters (here, the bit rate), the NWDAF can determine that the service type requested by the SMF to be analyzed is the same as that requested by the UPF, and the network parameters required by the SMF overlap with those required by the AF.
  • the NWDAF may determine that the analysis type identifier in the stored subscription request of S301 is the same as the analysis type identifier of the subscription request in S303, and the network parameters required by the SMF in the same. Including the same type of network parameters (here, the bit rate), the NWDAF can determine that the service type requested by the SMF to be analyzed is the same as that requested by the UPF, and the network parameters required by the SMF overlap with those required by the AF.
  • S305 The NWDAF sends a second message to the UPF, where the second message is used for the UPF to modify the required network parameter to an end-to-end delay.
  • the third message may be used to instruct the SMF to adjust the bit rate according to the recommendation.
  • the third message may include the subscription identifier in S304, the identifier used to indicate that there is something to be confirmed (that is, the network parameter of the modified requirement needs to be confirmed), and the information of modifying the network parameter to end-to-end delay and at least one of the identity of the SMF.
  • the UPF receives the first message.
  • the UPF sends an updated subscription request to the NWDAF, where the required network index carried indicates that the MOS is greater than 4.0.
  • the subscription identifier shown in S204 may be carried in the updated subscription request.
  • the NWDAF receives the updated subscription request, and updates the subscription content of the UPF according to the updated subscription request.
  • the subscription content of the UPF includes the service type identifier, the network index expected by the UPF (the value in the subscription request updated for S206), Network parameters and subscription identifiers required by UPF.
  • the NWDAF may also send a notification of the required network parameter conflict to the SMF, which may carry the subscription identifier in S301, the conflicting transmission (here, the bit rate) and the identifier of the UPF. At least one, it is up to the SMF to decide whether to change the required network parameters. If the SMF decides not to change the network parameters required by the SMF, the SMF may notify the UPF that the recommended bit rate is no longer requested by the UPF, and the UPF may execute S306, and S305 does not need to be executed at this time.
  • the SMF may notify the UPF that the recommended bit rate is no longer requested by the UPF, and the UPF may execute S306, and S305 does not need to be executed at this time.
  • the SMF can send a message to the NWDAF to cancel the subscription to the recommended bit rate, and at this time, the NWDAF can send the recommended bit rate to the UPF, so that the The UPF adjusts the bit rate.
  • S305 and S306 do not need to be executed.
  • the NWDAF determines that the required network parameters in the subscription of the SMF and the subscription of the UPF do not overlap, and determines the recommended network parameters according to the expected network indicators, the network parameters required by the SMF, and the network parameters required by the UPF.
  • the NWDAF may associate the recommended bit rate with the identity of the SMF and the subscription identity in S301, and associate the recommended end-to-end delay with the identity of the UPF and the subscription identity in S304.
  • the NWDAF may send the recommended bit rate and the subscription identifier in S201 to the SMF.
  • the SMF receives the recommended bit rate.
  • S309 The NWDAF sends the recommended end-to-end delay and the subscription identifier in S304 to the UPF.
  • the UPF receives the recommended end-to-end delay.
  • the NWDAF can decide that one of the SMF or the UPF will obtain the recommended bit rate when both the SMF and the UPF request the recommended bit rate, so as to avoid recommendation conflicts.
  • the data analysis network element may re-determine the recommended network parameters corresponding to the first analysis requesting network element (hereinafter referred to as recommended The fifth network parameter) and the recommended network parameter corresponding to the second analysis requesting network element (hereinafter referred to as the recommended sixth network parameter).
  • the recommended fifth network parameter corresponds to the first network parameter, that is, the recommended fifth network parameter is determined according to the first network parameter;
  • the recommended sixth network parameter corresponds to the second network parameter, that is, The recommended sixth network parameter is determined according to the second network parameter.
  • the data analysis network element can determine according to the fourth message from the first analysis requesting network element that the first analysis requesting network element does not accept the recommended third network parameter, for example, the fourth message can be used to indicate that the first analysis request The network element does not accept the recommended third network parameter, or, the fourth message may be used to indicate that the first analysis request network element requests to re-determine the recommended network parameter (such as re-determining the recommended third network parameter or the recommended first network parameter) .
  • the analysis requesting network element determines that the network parameter cannot be adjusted according to the type or value of the recommended network parameter, it may determine not to accept the recommended network parameter.
  • the data analysis network element may re-determine the recommended network parameters according to the fourth information.
  • the data analysis network element can use the historical average value or maximum likelihood probability value of the unaccepted network parameter as the recommended fifth network parameter, and determine the recommended fifth network parameter according to the recommended fifth network parameter.
  • the sixth network parameter of For example, a network parameter belonging to the same group as the recommended network parameter and having the same type as the second network parameter is used as the recommended sixth network parameter, wherein the recommended fifth network parameter and the recommended sixth network parameter belong to a group Network parameters that can meet the third network index.
  • the data analysis network element may also determine a set of network parameters from at least one set of network parameters satisfying the third network index, and use the network parameters of the same type as the first network parameter included in the set of network parameters as the recommended fifth A network parameter, and a network parameter of the same type as the second network parameter included in the set of network parameters is used as a recommended sixth network parameter.
  • the data analysis network element may determine the updated third network index according to the first network index and the second network index, and then determine the recommended fifth network parameter and the recommended sixth network parameter according to the updated third network index, For a specific implementation manner, refer to the description of determining the recommended third network parameter and the recommended fourth network parameter according to the third network index.
  • the second analysis requesting network element may send a message indicating that the recommended fourth network parameter is not accepted to the data analysis network element, and the data analysis network The unit may re-determine recommended network parameters according to the message.
  • the communication method provided by the embodiment of the present application may include the following steps:
  • the NWDAF sends the recommended end-to-end delay to the UPF, and sends the recommended bit rate to the SMF.
  • the recommended end-to-end delay and the recommended bit rate meet the common expectations of UPF and SMF network indicators, for example, the recommended end-to-end delay is 10ms, and the recommended bit rate is 5Mbps.
  • the implementation manner of S401 may refer to the description in FIG. 6 .
  • the UPF cannot adjust the end-to-end delay to the recommended value according to the current network operating conditions. , so it is determined that the end-to-end delay is unacceptable.
  • the UPF may determine that the recommended end-to-end delay is not acceptable.
  • S403 The UPF sends a fourth message to the NWDAF, where the fourth message is used to indicate that the UPF does not accept the recommended end-to-end delay.
  • the NWDAF receives the fourth information.
  • the NWDAF takes the historical average value of the recommended bit rate as the updated end-to-end delay, and determines an updated bit rate that meets the network index according to the updated end-to-end delay.
  • S405 The NWDAF sends the updated end-to-end delay to the UPF.
  • the UPF receives the updated end-to-end delay.
  • the NWDAF sends the updated bit rate to the SMF.
  • the SMF receives the updated bit rate.
  • NWDAF can re-determine the recommended bit rate and end-to-end delay when the UPF does not accept the recommended end-to-end delay, and indicate the recommended bit rate and recommended bit rate to the SMF and UPF respectively.
  • the end-to-end delay can avoid network parameter adjustment and results that cannot meet the expected network indicators.
  • FIG. 8 and FIG. 9 are schematic structural diagrams of possible communication devices provided by the embodiments of the present application. These communication devices can be used to implement the functions of the data analysis network element or the analysis request network element in the above method embodiments, and thus can also realize the beneficial effects of the above method embodiments.
  • the communication device may be a data analysis network element or an analysis request network element, or a module (such as a chip) applied to a data analysis network element or an analysis request network element.
  • a communication device 800 includes a processing unit 810 and a transceiver 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 foregoing method embodiments.
  • the communication device is used to realize the function of the data analysis network element in the above method embodiment
  • the transceiver unit 820 can be used to receive the first request message and the second request message, the first request message comes from the first The analysis request network element, the first request message is used to request the recommended first network parameter, the first request message includes the first network parameter and the first network index required by the first analysis requesting network element, the first network index is the first analysis The network index expected by the network element is requested.
  • the second request message comes from the second analysis request network element.
  • the second request message is used to request the recommended second network parameters.
  • the second request message includes the second analysis request network element required by the second request message.
  • a network parameter and a second network index where the second network index is a network index expected by the second analysis requesting network element.
  • the data analysis network element may also determine a third network index according to the first network index and the second network index, and the third network index is a network index jointly expected by the first analysis requesting network element and the second analysis network element.
  • the processing unit 810 may be configured to determine a recommended third network parameter and a recommended fourth network parameter according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element parameter.
  • the transceiving unit 820 is further configured to send the recommended third network parameter and the recommended fourth network parameter.
  • the predicted network index corresponding to the recommended third network parameter and the recommended fourth network parameter is within the range of the third network index.
  • the transceiver unit 820 can also be configured to send a first message to the first analysis requesting network element and/or the second analysis requesting network element, the first message is used to modify the expected network index to the third network index.
  • the transceiver unit 820 can also be used to request the first analysis request network element
  • the recommended third network parameter is sent, and the transceiver unit 820 is further configured to send the recommended fourth network parameter to the second analysis requesting network element.
  • the transceiving unit 820 is further configured to send a second message to the first analysis requesting network element, and the second message is used for the first analysis requesting network element to modify the required network parameter to a third network parameter.
  • the transceiver unit 820 can also be used to Sending the recommended third network parameter and the recommended fourth network parameter to the first analysis requesting network element.
  • the transceiver unit 820 may also be configured to send a third message to the second analysis requesting network element, and the third message is used to cancel obtaining the recommended network parameters according to the second network parameters required by the second analysis requesting network element .
  • the transceiver unit 820 can also be configured to send the recommended third network parameter to the first analysis requesting network element, and send the recommended fourth network parameter to the second analysis requesting network element.
  • the recommended third network parameter The parameter corresponds to the first network parameter, and the recommended fourth network parameter corresponds to the second network parameter.
  • the transceiving unit 820 may also receive a fourth message sent from the first analysis requesting network element, where the fourth message is used to indicate that the recommended third network parameter is not accepted.
  • the processing unit 810 may further determine the recommended fifth network parameter and The recommended sixth network parameter, the recommended fifth network parameter corresponds to the first network parameter, the recommended sixth network parameter corresponds to the second network parameter, the value of the recommended fifth network parameter and the value of the recommended third network parameter different.
  • the transceiving unit 820 is further configured to send the recommended fifth network parameter to the first analysis requesting network element, and send the recommended sixth network parameter to the second analysis requesting network element.
  • the communication device is used to implement the function of the first analysis request network element in the above method embodiment, and the processing unit 810 can be used to determine the first request message, and the first request message is used to request a recommendation
  • the first network parameter, the first request message includes the first network parameter and the first network index required by the first analysis requesting network element, and the first network index is the first analysis requesting network element Desired network metrics.
  • the transceiving unit 820 is further configured to send the first request message to the data analysis network element.
  • the transceiver unit 820 is further configured to receive the third network parameter recommended by the data analysis network element.
  • Network parameters are determined according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element, the first The third network index is a network index expected by the first analysis requesting network element and the second analysis requesting network element, the third network index is determined according to the first network index and the second network index, and the third network index is determined according to the first network index and the second network index.
  • the second network index is a network index expected by the second analysis requesting network element.
  • the transceiving unit 820 is further configured to receive a first message from the data analysis network element, where the first message is used to modify the expected network index to the third network index.
  • the processing unit 810 may also determine whether to modify the expected network index to the third network index according to the first message.
  • the transceiver unit 820 is further configured to receive a second message from the data analysis network element, and the second message is used for the first analysis request network element to modify the required network parameters to The third network parameter.
  • the transceiver unit 820 is further configured to receive the third network parameter recommended by the data analysis network element.
  • the predicted network index corresponding to the recommended third network parameter and the recommended fourth network parameter is within the range of the third network index.
  • the transceiver unit 820 is further configured to receive a recommended third network parameter from the data analysis network element.
  • the transceiving unit 820 is further configured to send a fourth message to the data analysis network element, where the fourth message is used to indicate that the recommended third network parameter is not accepted.
  • the transceiver unit 820 is further configured to receive a recommended fifth network parameter from the data analysis network element, the recommended fifth network parameter corresponds to the first network parameter, and the recommended fifth network parameter is based on the first network parameter Three network indicators, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element are determined, and the third network indicator is the first analysis requesting network element A network index expected jointly with the second analysis requesting network element, the third network index is determined according to the first network index and the second network index, and the second network index is the second network index for the second analysis requesting network element Desired network metrics.
  • the communication device is used to realize the function of the second analysis requesting network element in the method embodiment above, and the processing unit 810 can be used to determine the second request message, and the second request message is used to request the recommended first Two network parameters, the second request message includes a second network parameter and a second network index required by the second analysis requesting network element, and the second network index is a network index expected by the second analysis requesting network element.
  • the transceiver unit 820 may be configured to send the second request message to the data analysis network element.
  • the transceiver unit 820 is further configured to receive a recommended fourth network parameter from the data analysis network element.
  • the recommended fourth network parameter is determined according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element, and the third network index is the first analysis request
  • the transceiver unit 820 is further configured to receive a first message from the data analysis network element, where the first message is used to modify the expected network index to the third network index.
  • the processing unit 810 may be configured to determine whether to modify the expected network index to the third network index according to the first message.
  • the transceiver unit 820 is also configured to receive a third message from the data analysis network element, and the third message is used to cancel the network parameter obtained according to the second network parameter required by the second analysis requesting network element. .
  • the transceiver unit 820 is further configured to receive a recommended fourth network parameter from the data analysis network element.
  • the recommended fourth network parameter is determined according to the third network index, the first network parameter required by the first analysis requesting network element, and the second network parameter required by the second analysis requesting network element, and the third network index is the first analysis request
  • the transceiver unit 820 can also be configured to receive a recommended sixth network parameter from the data analysis network element, the recommended sixth network parameter corresponds to the second network parameter, and the recommended sixth network parameter is based on the third network indicator, the first analysis request The first network parameter required by the network element and the second analysis request are determined by the second network parameter required by the network element.
  • processing unit 810 and the transceiver unit 820 can be directly obtained by referring to related descriptions in the above method embodiments, and details are not repeated here.
  • the communication device 900 includes a processor 910 .
  • the communication device 900 further includes an interface circuit 920, and the processor 910 and the interface circuit 920 are coupled to each other.
  • the interface circuit 920 may be a transceiver or an input-output interface.
  • the communication device 900 may further include a memory 930 for storing instructions executed by the processor 910 or storing input data required by the processor 910 to execute the instructions or storing data generated after the processor 910 executes the instructions.
  • the processor 910 is used to implement the functions of the processing unit 810
  • the interface circuit 920 is used to implement the functions of the transceiver unit 820 .
  • processor in the embodiments of the present application may be a central processing unit (central processing unit, CPU), and may also be other general processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.
  • CPU central processing unit
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • a general-purpose processor can be a microprocessor, or any conventional processor.
  • the method steps in the embodiments of the present application may be implemented by means of hardware, or may be implemented by means of a processor executing software instructions.
  • Software instructions can be composed of corresponding software modules, and software modules can 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 hard 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.
  • the storage medium may also be a component of the processor.
  • the processor and storage medium can be located in the ASIC.
  • the ASIC can be located in the base station or the terminal.
  • the processor and the storage medium may also exist in the base station or the terminal as discrete components.
  • all or part of them may be implemented by software, hardware, firmware or any combination thereof.
  • software When implemented using software, it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product comprises one or more computer programs or instructions. When the computer program or instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are executed in whole or in part.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, a base station, user equipment or other programmable devices.
  • the computer program or instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instructions may be downloaded from a website, computer, A server or data center transmits 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 or a data center integrating one or more available media.
  • the available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disk; or it may be a semiconductor medium, such as a solid state disk.
  • the computer readable storage medium may be a volatile or a nonvolatile storage medium, or may include both volatile and nonvolatile types of storage media.
  • “at least one” means one or more, and “multiple” means two or more.
  • “And/or” describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and/or B, which can mean: A exists alone, A and B exist at the same time, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the contextual objects are an “or” relationship; in the formulas of this application, the character “/” indicates that the contextual objects are a "division” Relationship.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

一种通信方法及装置，用以使得数据分析网元的分析服务满足多个分析请求网元的要求。该方法包括：数据分析网元接收第一请求消息和第二请求消息，第一请求消息来自于第一分析请求网元，第一请求消息用于请求推荐的第一网络参数，数据分析网元还可根据第一分析请求网元期望的第一网络指标和第二分析请求网元期望的第二网络指标确定第三网络指标，第三网络指标为第一分析请求网元和第二分析请求网元共同期望的网络指标。数据分析网元根据第三网络指标确定推荐的网络参数，因此使得推荐的网络参数满足第一分析请求网元和第二分析请求网元对于分析业务的要求。

Description

一种通信方法及装置
相关申请的交叉引用
本申请要求在2021年11月10日提交中华人民共和国知识产权局、申请号为202111325483.9、申请名称为“一种通信方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种通信方法及装置。
背景技术
人工智能和大数据分析的快速发展为网络智能化提供了基础技术。为了实现5G移动网络智能化，定义了网络数据分析功能(network data analytics function，NWDAF)网元，以及管理数据分析系统(management data analytics system，MDAS)。NWDAF或MDAS可用于提供网络的智能分析服务，用于支持网络的异常分析、优化调整和服务等级协议保障，因此可称NWDAF和/或MDAS为数据分析网元。
以NWDAF执行分析为例，NWDAF可通过智能分析服务预测网络指标(即表征网络运行状态的指标)的变化趋势，处理业务的业务网元根据网络指标的变化趋势进行网络调整。然而目前的数据分析网元并不支持针对来自于多个网元的相关网络参数的分析请求进行分析，不能满足多网元对分析业务的需求。
发明内容
本申请实施例提供一种通信方法及装置，使得数据分析网元的分析服务满足多个网元对于分析业务的要求。
第一方面，本申请实施例提供一种通信方法，该方法可以由数据分析网元或应用于数据分析网元中的模块(如芯片)来执行。以数据分析网元执行该方法为例，该方法包括：数据分析设备接收第一请求消息和第二请求消息，第一请求消息来自于第一分析请求网元，第一请求消息用于请求推荐的第一网络参数，第一请求消息包括第一分析请求网元要求的第一网络参数和第一网络指标，第一网络指标为第一分析请求网元期望的网络指标，第二请求消息来自于第二分析请求网元，第二请求消息用于请求推荐的第二网络参数，第二请求消息包括第二分析请求网元要求的第二网络参数和第二网络指标，第二网络指标为第二分析请求网元期望的网络指标。数据分析网元还可根据第一网络指标和第二网络指标确定第三网络指标，第三网络指标为第一分析请求网元和第二分析网元共同期望的网络指标。数据分析网元还可根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数，确定推荐的第三网络参数和推荐的第四网络参数。数据分析网元还可发送推荐的第三网络参数和推荐的第四网络参数。
根据上述方案，数据分析网元可根据第一分析请求网元和第二分析请求网元共同的期望的网络指标确定推荐的网络参数，使得推荐的网络参数满足第一分析请求网元和第二分 析请求网元对于分析业务的要求。
在一种可能的设计中，对应于推荐的第三网络参数和推荐的第四网络参数的预测的网络指标在第三网络指标的范围内。采用该设计，可使得推荐的网络参数更加符合第一分析请求网元和第二分析请求网元对于网络指标的期望。
在一种可能的设计中，数据分析网元还可向第一分析请求网元和/或第二分析请求网元发送第一消息，第一消息用于将期望的网络指标修改为第三网络指标。采用该设计，在第一分析请求网元期望的网络指标的数值与第二分析请求网元期望的指标的数值不同时，数据分析网元可根据第一分析请求网元期望的网络指标和第二分析请求网元期望的网络指标确定共同期望的网络指标，实现第三网络指标的准确定。
在一种可能的设计中，如果第一网络参数对应于第三网络参数和第四网络参数，第二网络参数对应于第四网络参数，则数据分析网元还可向第一分析请求网元发送推荐的第三网络参数，以及，数据分析网元还可向第二分析请求网元发送推荐的第四网络参数。采用该设计，在第一分析请求网元要求的网络传输与第二分析请求网元要求的网络参数均包括第三网络参数时，第一分析请求网元可以向其中一个请求网元发送推荐的第三网络参数，避免重复调整。
在一种可能的设计中，数据分析网元还可向第一分析请求网元发送第二消息，第二消息用于第一分析请求网元将要求的网络参数修改为第三网络参数。
在一种可能的设计中，如果第一网络参数对应于第三网络参数和第四网络参数，第二网络参数对应于第三网络参数和/或第四网络参数，则数据分析网元还可向第一分析请求网元发送推荐的第三网络参数和推荐的第四网络参数。采用该设计，在第一分析请求网元要求的网络传输与第二分析请求网元要求的网络参数均包括第三网络参数时，第一分析请求网元可以向其中一个请求网元发送推荐的第三网络参数，避免重复调整。
在一种可能的设计中，数据分析网元还可向第二分析请求网元发送第三消息，第三消息用于取消根据第二分析请求网元要求的第二网络参数获得推荐的网络参数。
在一种可能的设计中，数据分析网元可向第一分析请求网元发送推荐的第三网络参数，并向第二分析请求网元发送推荐的第四网络参数，推荐的第三网络参数对应于第一网络参数，推荐的第四网络参数对应于第二网络参数。
在一种可能的设计中，数据分析网元还可接收来自于第一分析请求网元发送的第四消息，第四消息用于指示不接受推荐的第三网络参数，数据分析网元进一步可根据第四消息，根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数，确定推荐的第五网络参数和推荐的第六网络参数，推荐的第五网络参数对应于第一网络参数，推荐的第六网络参数对应于第二网络参数，推荐的第五网络参数的数值与推荐的第三网络参数的数值不同。数据分析请求网元还可向第一分析请求网元发送推荐的第五网络参数，并向第二分析请求网元发送推荐的所述第六网络参数。采用该设计，在多个分析请求网元中的一个分析请求网元拒绝推荐的网络参数时，数据分析网元需要重新确定全部分析请求网元对应的推荐的网络参数，以提高分析可靠性。
第二方面，本申请实施例提供一种通信方法，该方法可以由第一分析请求网元或应用于第一分析请求中的模块(如芯片)来执行。以第一分析请求执行该方法为例，该方法包括：第一分析请求网元可确定第一请求消息，第一请求消息用于请求推荐的第一网络参数，第一请求消息包括第一分析请求网元要求的第一网络参数和第一网络指标，第一网络指标 为第一分析请求网元期望的网络指标。第一分析请求网元还可向数据分析网元发送第一请求消息。
在一种可能的设计中，如果第一网络参数对应于第三网络参数和第四网络参数，则第一分析请求网元还可接收来自于数据分析网元的推荐的第三网络参数。其中，推荐的第三网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定，第三网络指标为第一分析请求网元和第二分析请求网元共同期望的网络指标，第三网络指标根据第一网络指标和第二网络指标确定，第二网络指标为第二分析请求网元期望的网络指标。
在一种可能的设计中，第一分析请求网元还可接收来自于数据分析网元的第一消息，第一消息用于将期望的网络指标修改为第三网络指标。第一分析请求网元还可根据第一消息确定是否将第一分析请求网元期望的网络指标修改为第三网络指标。
在一种可能的设计中，第一分析请求网元还可接收来自于数据分析网元的第二消息，第二消息用于第一分析请求网元将要求的网络参数修改为第三网络参数。
在一种可能的设计中，如果第一网络参数对应于第三网络参数和第四网络参数，则第一分析请求网元还可接收来自于数据分析网元的推荐的第三网络参数和推荐的第四网络参数，推荐的第三网络参数和推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定，第三网络指标为第一分析请求网元和第二分析请求网元共同期望的网络指标，第三网络指标根据第一网络指标和第二网络指标确定，第二网络指标为第二分析请求网元期望的网络指标。
在一种可能的设计中，对应于推荐的第三网络参数和推荐的第四网络参数的预测的网络指标在第三网络指标的范围内，所述推荐的第四网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第四网络参数对应于所述第二网络参数。
在一种可能的设计中，第一分析请求网元还可接收来自于数据分析网元的推荐的第三网络参数。第一分析请求网元还可向数据分析网元发送第四消息，第四消息用于指示不接受推荐的第三网络参数。第一分析请求网元还可接收来自于数据分析网元的推荐的第五网络参数，推荐的第五网络参数对应于第一网络参数，推荐的第五网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定，第三网络指标为第一分析请求网元和第二分析请求网元共同期望的网络指标，第三网络指标根据第一网络指标和第二网络指标确定，第二网络指标为第二分析请求网元期望的网络指标。
第三方面，本申请实施例提供一种通信方法，该方法可以由第二分析请求网元或应用于第二分析请求中的模块(如芯片)来执行。以第二分析请求执行该方法为例，该方法包括：第二分析请求网元可确定第二请求消息，第二请求消息用于请求推荐的第二网络参数，第二请求消息包括第二分析请求网元要求的第二网络参数和第二网络指标，第二网络指标为第二分析请求网元期望的网络指标。第二分析请求网元还可向数据分析网元发送第二请求消息。
在一种可能的设计中，第二分析请求网元还可接收来自于数据分析网元的推荐的第四网络参数。其中，推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定，第三网络指标为第一分析请求网 元和第二分析请求网元共同期望的网络指标，第三网络指标根据第二网络指标和第一网络指标确定，第一网络指标为第一分析请求网元期望的网络指标。
在一种可能的设计中，第二分析请求网元还可接收来自于数据分析网元的第一消息，第一消息用于将期望的网络指标修改为第三网络指标。第二分析请求网元还可根据所述第一消息确定是否将第二分析请求网元期望的网络指标修改为所述第三网络指标。
在一种可能的设计中，第二分析请求网元还可接收来自于数据分析网元的第三消息，第三消息用于取消根据第二分析请求网元要求的第二网络参数获得推荐的网络参数。
在一种可能的设计中，第二分析请求网元还可接收来自于数据分析网元的推荐的第四网络参数。其中，推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定，第三网络指标为第一分析请求网元和第二分析请求网元共同期望的网络指标，第三网络指标根据第二网络指标和第一网络指标确定，第一网络指标为第一分析请求网元期望的网络指标。第二分析请求网元还可接收来自于数据分析网元的推荐的第六网络参数，推荐的第六网络参数对应于第二网络参数，推荐的第六网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定。
第四方面，本申请实施例提供一种通信装置，该装置可以是数据分析网元或应用于数据分析网元中的模块(如芯片)。该装置具有实现上述第一方面及其任意可能的设计的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。
第五方面，本申请实施例提供一种通信装置，该装置可以是分析请求网元或应用于分析请求网元中的模块(如芯片)。该装置具有实现上述第二方面及其任意可能的设计的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。
第六方面，本申请实施例提供一种通信装置，该装置可以是分析请求网元或应用于分析请求网元中的模块(如芯片)。该装置具有实现上述第三方面及其任意可能的设计的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。
第七方面，本申请实施例提供一种通信装置，包括处理器和存储器；该存储器用于存储处理器需要的计算机指令，当该装置运行时，该处理器执行该存储器存储的计算机指令，以使该装置执行上述第一方面至第三方面及其任意可能的设计中的任意实现方法。
第八方面，本申请实施例提供一种通信装置，包括用于执行上述第一方面至第三方面及其任意可能的设计中的各个步骤的单元或手段(means)。
第九方面，本申请实施例提供一种通信装置，包括处理器和接口电路，所述处理器用于通过接口电路与其它装置通信，并执行上述第一方面至第三方面及其任意可能的设计中的方法。该处理器包括一个或多个。
第十方面，本申请实施例提供一种通信装置，包括与存储器耦合的处理器，该处理器用于调用所述存储器中存储的程序，以执行上述第一方面至第三方面及其任意可能的设计中的方法。该存储器可以位于该装置之内，也可以位于该装置之外。且该处理器可以是一个或多个。
第十一方面，本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介 质中存储有指令，当其在通信装置上运行时，使得上述第一方面至第三方面及其任意可能的设计中的方法被执行。
第十二方面，本申请实施例还提供一种计算机程序产品，该计算机程序产品包括计算机程序或指令，当计算机程序或指令被通信装置运行时，使得上述第一方面至第三方面及其任意可能的设计中的方法被执行。
第十三方面，本申请实施例还提供一种芯片系统，包括：处理器，用于执行上述第一方面至第三方面及其任意可能的设计中的方法。
第十四方面，本申请实施例还提供一种通信系统，包括用于实现上述第一方面及其任意可能的设计中的方法的数据分析网元、用于实现上述第二方面及其任意可能的设计中的方法的第一分析请求网元，和用于实现上述第三方面及其任意可能的设计中的方法的第二分析请求网元。
以上第二方面至第十四方面中任一方面中任一可能设计所带来的技术效果可参见上述第一方面中任一可能设计所带技术效果的描述，此处不再赘述。
附图说明
图1为本申请实施例提供的一种通信系统的架构示意图；
图2为本申请实施例提供的一种机器学习模型的示意图；
图3为本申请实施例提供的另一种通信系统的架构示意图；
图4为本申请实施例提供的一种通信方法的流程意图；
图5为本申请实施例提供的另一种通信方法的流程意图；
图6为本申请实施例提供的另一种通信方法的流程意图；
图7为本申请实施例提供的另一种通信方法的流程意图；
图8为本申请实施例提供的一种通信装置的结构示意图；
图9为本申请实施例提供的另一种通信装置的结构示意图。
具体实施方式
为了使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请作进一步地详细描述。
图1为基于服务化架构的5G网络架构示意图。图1所示的5G网络架构中可包括终端设备、接入网(access network，AN)设备以及核心网设备。终端设备通过接入网设备和核心网设备接入数据网络(data network，DN)。其中，核心网设备包括以下网元中的部分或者全部网络功能(network function，NF)：统一数据管理(unified data management，UDM)网元、网络开放功能(network exposure function，NEF)网元(图中未示出)、应用功能(application function，AF)网元、策略控制功能(policy control function，PCF)网元、接入与移动性管理功能(access and mobility management function，AMF)网元、网络切片选择功能(network slice selection function，NSSF)网元、会话管理功能(session management function，SMF)网元、用户面功能(user plane function，UPF)网元、网络数据分析功能(network data analytics function，NWDAF)网元和网络存储功能(network repository function，NRF)网元(图中未示出)等。
接入网设备可以是无线接入网(radio access network，RAN)设备。例如：基站(base station)、演进型基站(evolved NodeB，eNodeB)、发送接收点(transmission reception point，TRP)、5G移动通信系统中的下一代基站(next generation NodeB，gNB)、第六代(the 6th generation，6G)移动通信系统中的下一代基站、未来移动通信系统中的基站或无线保真(wireless fidelity，WiFi)系统中的接入节点等；也可以是完成基站部分功能的模块或单元，例如，可以是集中式单元(central unit，CU)，也可以是分布式单元(distributed unit，DU)。无线接入网设备可以是宏基站，也可以是微基站或室内站，还可以是中继节点或施主节点等。本申请的实施例对无线接入网设备所采用的具体技术和具体设备形态不做限定。
终端设备可以是用户设备(user equipment，UE)、移动台、移动终端等。终端设备可以广泛应用于各种场景，例如，设备到设备(device-to-device，D2D)、车物(vehicle to everything，V2X)通信、机器类通信(machine-type communication，MTC)、物联网(internet of things，IOT)、虚拟现实、增强现实、工业控制、自动驾驶、远程医疗、智能电网、智能家具、智能办公、智能穿戴、智能交通、智慧城市等。终端设备可以是手机、平板电脑、带无线收发功能的电脑、可穿戴设备、车辆、城市空中交通工具(如无人驾驶机、直升机等)、轮船、机器人、机械臂、智能家居设备等。
接入网设备和终端设备可以是固定位置的，也可以是可移动的。接入网设备和终端设备可以部署在陆地上，包括室内或室外、手持或车载；也可以部署在水面上；还可以部署在空中的飞机、气球和人造卫星上。本申请的实施例对接入网设备和终端设备的应用场景不做限定。
接入管理网元，包含执行移动性管理、接入鉴权/授权等功能，主要用于移动网络中的终端的附着、移动性管理、跟踪区更新流程，接入管理网元终结了非接入层(non access stratum，NAS)消息、完成注册管理、连接管理以及可达性管理、分配跟踪区域列表(track area list，TA list)以及移动性管理等，并且透明路由会话管理(session management，SM)消息到会话管理网元。在第5代(5th generation，5G)通信系统中，接入管理网元可以是AMF网元(以下简称为AMF)。此外，接入管理网元还负责在终端设备与PCF间传递用户策略。
会话管理网元，主要用于移动网络中的会话管理，如会话建立、修改、释放。具体功能如为终端分配互联网协议(internet protocol，IP)地址、选择提供报文转发功能的用户面网元等。在5G通信系统中，会话管理网元可以是SMF网元(以下简称为SMF)。
网络切片选择网元，主要用于为终端的业务选择合适的网络切片。在5G通信系统中，网络切片选择网元可以是NSSF网元。
用户面网元，主要负责对用户报文进行处理，如转发、计费、合法监听等。用户面网元可以作为协议数据单元(protocol data unit，PDU)会话锚点(PDU session anchor，PSA)。在5G通信系统中，用户面网元可以是UPF网元(以下简称为UPF)。UPF可以通过类似服务化的接口直接和NWDAF通信，也可以通过其他途径，例如通过SMF或者和NWDAF之间的私有接口或内部接口，和NWDAF通信。
统一数据管理网元：负责管理终端的签约信息。在5G通信系统中，统一数据管理网元可以是UDM网元(以下简称为UDM)。
网络能力开放网元，用于支持能力和事件的开放。在5G通信系统中，网络能力开放网元可以是NEF网元(以下简称为NEF)。
应用功能网元，用于传递应用侧对网络侧的需求，例如，QoS需求或用户状态事件订阅等。应用功能网元可以是第三方功能实体，也可以是运营商部署的应用服务器。在5G通信系统中，应用功能网元可以是AF网元(以下简称为AF)。
策略控制网元，包含用户签约数据管理功能、策略控制功能、计费策略控制功能、服务质量(quality of service，QoS)控制等。在5G通信系统中，策略控制网元可以是PCF网元(以下简称为PCF)。需要指出实际网络中PCF还可能按照层次或按功能分为多个实体，例如全局PCF和切片内的PCF，或者会话管理PCF(session management PCF，SM-PCF)和接入管理PCF(access management PCF，AM-PCF)。
网络仓库网元，可用于提供网元发现功能，基于其他网元的请求，提供网元类型对应的网元信息。网络仓库网元还提供网元管理服务，如网元注册、更新、去注册以及网元状态订阅和推送等。在5G通信系统中，网络仓库网元可以是NRF网元(以下简称为NRF)。
数据分析网元，可用于收集数据并进行分析和预测。其中，收集数据包括但不限于：从其他各个NF，如通过AMF、SMF、PCF收集数据、通过NEF或直接从AF收集数据，或从运行管理和维护(operation,administration,and maintenance，OAM)系统收集数据中的至少一种。其中，这些数据可以是终端设备、接入网设备、核心网网元或第三方应用设备的数据，也可以是终端设备在该接入网设备、该核心网网元或该第三方应用设备上的数据，然后根据收集的数据进行智能分析，并输出分析结果。在5G通信系统中，数据分析网元可以是NWDAF网元(以下简称为NWDAF)。其中，智能分析是指借助人工智能(artificial intelligence，AI)等智能化技术对于收集的数据进行的分析。本申请中，智能分析包括但不限于对网络指标进行预测和对网络参数进行推荐。
本申请中，NWDAF可以利用机器学习模型进行智能分析。NWDAF还可以向上述各个NF、AF或OAM输出推荐值，供各个NF、AF或OAM执行策略决策使用。第三代合作伙伴计划(3rd generation partnership project，3GPP)版本(release)17中将NWDAF的训练功能和推理(inference)功能进行拆分，一个NWDAF可以仅支持模型训练功能，或仅支持数据推理功能，或同时支持模型训练功能和数据推理功能。其中，支持模型训练功能的NWDAF也可以称为训练NWDAF，或称为支持模型训练逻辑功能(model training logical function，MTLF)的NWDAF(简称为NWDAF(MTLF))。训练NWDAF可以根据获取的数据进行模型训练，得到训练后的模型。支持数据推理功能的NWDAF也可以称为推理NWDAF，或称为支持分析逻辑功能(analytics logical function，AnLF)的NWDAF(简称为NWDAF(AnLF))。推理NWDAF可以将输入数据输入到训练后的模型，得到分析结果或推理数据。本申请实施例中，训练NWDAF指的是至少支持模型训练功能的NWDAF。作为一种可能的实现方法，训练NWDAF也可以支持数据推理功能。推理NWDAF指的是至少支持数据推理功能的NWDAF。作为一种可能的实现方法，推理NWDAF也可以支持模型训练功能。如果一个NWDAF同时支持模型训练功能和数据推理功能，则该NWDAF可以称为训练NWDAF、推理NWDAF或训练推理NWDAF或NWDAF。本申请实施例中，一个NWDAF可以是一个单独的网元，也可以与其他网元合设，例如将NWDAF设置到PCF网元或者AMF网元中。
DN，是位于运营商网络之外的网络，运营商网络可以接入多个DN，DN上可部署多种业务，可为终端设备提供数据和/或语音等服务。例如，DN是某智能工厂的私有网络，智能工厂安装在车间的传感器可为终端设备，DN中部署了传感器的控制服务器，控制服 务器可为传感器提供服务。传感器可与控制服务器通信，获取控制服务器的指令，根据指令将采集的传感器数据传送给控制服务器等。又例如，DN是某公司的内部办公网络，该公司员工的手机或者电脑可为终端设备，员工的手机或者电脑可以访问公司内部办公网络上的信息、数据资源等。
图1中Npcf、Nnef、Namf、Nudm、Nsmf、Naf、Nnssf和Nnwdaf分别为上述PCF、NEF、AMF、UDM、SMF、AF、NSSF和NWDAF提供的服务化接口，用于调用相应的服务化操作。N1、N2、N3、N4以及N6为接口序列号，这些接口序列号的含义如下：
1)、N1：AMF与终端设备之间的接口，可以用于向终端设备传递非接入层(non access stratum，NAS)信令(如包括来自AMF的QoS规则)等。
2)、N2：AMF与接入网设备之间的接口，可以用于传递核心网侧至接入网设备的无线承载控制信息等。
3)、N3：接入网设备与UPF之间的接口，主要用于传递接入网设备与UPF间的上下行用户面数据。
4)、N4：SMF与UPF之间的接口，可以用于控制面与用户面之间传递信息，包括控制面向用户面的转发规则、QoS规则、流量统计规则等的下发以及用户面的信息上报。
5)、N6：UPF与DN的接口，用于传递UPF与DN之间的上下行用户数据流。
图1所示的服务化架构，使得5G核心网形成一个扁平化的架构，通过控制面的信令总线，同一个网络切片的控制面网络功能实体之间可以通过NRF相互发现对方，获得对方的访问地址信息，然后可以通过控制面信令总线直接相互通信。
可以理解的是，上述网元或者功能既可以是硬件设备中的网络元件，也可以是在专用硬件上运行软件功能，或者是平台(例如，云平台)上实例化的虚拟化功能。作为一种可能的实现方法，上述网元或者功能可以由一个设备实现，也可以由多个设备共同实现，还可以是一个设备内的一个功能模块，本申请实施例对此不作具体限定。
作为一种实现方法，本申请实施例中的数据分析网元可以是上述NWDAF，也可以是未来通信如6G网络中具有上述NWDAF的功能的网元。数据分析网元还可以是MDAS。MDAS是部署在网络管理面的数据分析系统，可用于收集性能统计、告警、操作配置等管理数据并进行分析和预测，也可以输出资源分配或配置优化的建议。MDAS也具备训练功能和推理功能。和NWDAF相比，MDAS属于网络管理系统的一部分，常常离线和非实时运行，向运营商提供资源和部署调整优化建议，面向更长周期的趋势分析和优化建议。为便于说明，以下以数据分析网元是NWDAF为例进行说明，本申请中由NWDAF执行的动作也可由MDAS执行。
下面对NWDAF进行智能分析的过程进行说明。NWDAF可从多个来源收集多种维度的数据，进行关联分析，输出历史统计，或者训练拟合出模型，根据模型输出网络指标的预测值，用以指导业务网元对网络参数进行调整，以优化网络指标。应理解，不同的网络指标对应于不同的网络参数，而网络指标与网络运行状态相关。其中，网络指标比如网络业务评价值(以下简称为业务体验)、网络关键性能指标值或网络开销指标等，网络参数可包括时间、UE的位置、应用的位置、业务流的比特速率、包时延、传输和重传报文数量等因素。
这里以网络指标为业务体验的智能分析(以下称为业务体验分析)过程为例，其中，业务体验是指用户对于通过网络访问业务过程的体验评价，此时网络指标可以是由用户进 行的量化评估，该过程可包括以下步骤：
步骤1，NWDAF首先收集以下数据：
(1)从AF收集业务的体验评分、达到该体验评分的UE的百分比(例如业务体验质量为优秀的比例不低于90％)、UE的IP地址、应用的位置信息(如数据网络接入标识(data network access identify，DNAI)。其中，体验评分例如是平均主观评价(mean opinion score，MOS)。
(2)从通过AMF收集UE的签约用户永久标识(subscription permanent identifier，SUPI)，UE的位置信息(如全球小区标识(global cell identifier，GCI))；
(3)从SMF收集UE的SUPI、PDU会话的网络切片标识(如单一网络切片选择辅助信息(single-network slice selection assistance information，S-NSSAI))、UPF的信息(如UPF标识(identifier，ID))、IP过滤信息和业务流标识(QoS flow identifier，QFI)；
(4)从UPF收集业务流的比特速率、端到端时延(或包时延)、传输和重传报文数量等参数。
步骤2，NWDAF使用IP过滤信息和UE的IP地址将一个UE的从AF收集的数据和同一个UE的从SMF收集的数据关联起来，再根据SUPI将同一个UE的从AMF收集的位置数据和从SMF的会话数据关联起来。通过QFI进一步将同一个UE的从UPF收集的数据与以上数据关联进来。同理，NWDAF进一步将数量众多的UE的数据进行关联分析。
步骤3，NWDAF根据上述数据训练拟合出模型。例如使用上述数据训练一个深度学习网络。该深度学习网络例如图2所示。
训练过程例如，NWDAF使用训练功能，将UE的位置、应用的位置、时间、QoS Flow的比特速率、包时延、传输和重传报文数量等网络参数作为自变量(independent variables)，将业务体验和达到相应业务体验的UE占比等网络指标作为因变量(dependent variables)，使用上述关联处理后的数据训练这个深度学习网络，得到一个深度学习模型(deep learning model)。也就是说，在训练过程中，自变量是网络参数，因变量是网络指标。
步骤4，NWDAF将训练得到的深度学习模型设置为推理模式(inference mode)(即使用推理功能)，根据各个自变量的历史统计变化趋势，预测未来各个自变量最有可能的取值范围，然后根据训练得到的深度学习模型，通过各个自变量的预测值，计算输出因变量在未来的预测结果。
据此，通过业务体验分析过程，NWDAF可以预测网络参数所对应的网络指标的预测数值。NWDAF还可向业务网元(或称为业务处理网元)发送该预测数值，用于业务网元根据该预测数值调整网络参数，使得调整网络参数后的网络指标得到优化。
具体在业务体验分析过程中，业务网元可包括SMF，网络参数可包括QoS参数，网络指标可包括体验评分。NWDAF可以向SMF输出体验评分的预测数值。SMF可根据体验评分的预测数值确定调整后的QoS参数，该调整后的QoS参数具体可包括调整后的比特速率和/或调整后的包时延。SMF还可通过UPF执行调整后的QoS参数，从而通过QoS参数的优化来提高业务评分。
然而，目前的分析过程中，NWDAF无法根据来自于多个分析请求网元的请求消息进行分析，只会针对每个业务请求单独进行分析，导致NWDAF针对不同请求进行的分析之间可能存在冲突，因此分析结果不能同时符合全部分析请求网元的要求。
例如，如果第一分析请求网期望的网络指标与第二分析网元期望的网络指标的类型相 同，但是数值不同，这可能造成冲突。比如，SMF和AF分别向NWDAF请求推荐的网络参数，其中，SMF期望的MOS的范围是MOS不低于4.5，AF期望的MOS的范围是MOS不低于4，NWDAF分别针对SMF的请求和AF的请求确定SMF对应的推荐的网络参数和AF对应的推荐的网络参数，并由SMF根据其对应的推荐的网络参数进行调整，以及由AF根据其对应的推荐的网络参数进行调整。然而，AF对应的推荐的网络参数只能满足MOS不低于4，很可能不满足MOS不低于4.5的要求，因此在AF按照该推荐的网络参数进行调整后，会导致网络的MOS无法达到4.5，造成SMF期望的网络指标不能被满足。
又例如，第一分析请求网元和第二分析请求网元分别向NWDAF请求了同一种网络参数的推荐值，如果两个分析请求网元都对网络参数进行调整，也可能造成调整网络参数后实际的网络指标与期望网络指标不符。
为了使分析结果不符合全部分析请求网元的要求，本申请实施例提供一种通信方法。该通信方法可由数据分析网元和多个分析请求网元执行。如图3所示，数据分析网元可用于根据来自于多个分析请求网元的请求消息(或称分析请求)执行针对网络的智能分析，并向多个分析请求网元发送分析结果(或称请求消息对应的响应消息，简称为响应消息)，例如，数据分析网元包括NWDAF或MDAS。该多个分析请求网元可以是待分析的网络中的网元，也可以是该网络以外的网元。分析请求网元可以包括用于根据分析结果对该网络的网络参数进行调整的业务网元，或者可以包括业务网元以外的其他网元，例如，分析请求网元可例如是AMF、SMF或AF等，不具体限定。该网络可包括至少一个网元，例如，包括图1所示架构中的至少一个NF。
下面结合图4对本申请实施例提供的一种通信方法进行说明，该通信方法可包括以下步骤：
S101：数据分析设备接收来自于第一分析请求网元的第一请求消息和来自于第二分析请求网元的第二请求消息。
其中，第一请求消息用于请求推荐的第一网络参数，第一请求消息包括第一分析请求网元要求的第一网络参数(以下简称为要求的第一网络参数)和第一网络指标，第一网络指标为第一分析请求网元期望的网络指标；第二请求消息用于请求推荐的第二网络参数，第二请求消息包括第二分析请求网元要求的第二网络参数(以下简称为要求的第二网络参数)和第二网络指标，第二网络指标为第二分析请求网元期望的网络指标。应理解，第一网络参数可以是第一分析请求网元(或第一分析请求网元对应的业务网元)的可调整的网络参数，第二网络参数可以是第二分析请求网元(或第二分析请求网元对应的业务网元)的可调整的网络参数。
本申请中，要求的第二网络参数的类型可以与要求的第一网络参数的类型相同或不同。比如，业务体验分析中，第一分析请求网元可以是SMF，此时要求的第一网络参数可以是比特速率和端到端时延，要求的第一网络参数可以指示能够接受的比特速率小于或等于20兆比特每秒(Mbps)，以及指示可接受的端到端时延大于或等于20毫秒(ms)。第二分析请求网元可以是AF，此时要求的第二网络参数可以是DNAI，此时要求的第一网络参数的类型与要求的第二网络参数的类型不同。又如，第二分析请求网元可以是UPF，此时要求的第二网络参数的类型可以是比特速率和端到端时延，此时要求的第一网络参数的类型与要求的第二网络参数的类型相同。同理，要求的第一网络参数的数值与要求的第二网络参数的数值可以相同或不同。
本申请中，分析请求网元要求的网络参数(包括第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数)和分析请求网元期望的网络指标(包括第一网络指标和第二网络指标)中的至少一项可用于确定分析结果，使得分析结果数能够被分析请求网元所接受，以提高智能分析过程的可靠性。其中，该分析结果中可以包括推荐的网络参数，使得分析请求网元能够根据该推荐的网络参数对网络参数进行调整，以获得更好的网络优化效果。具体来说，第一分析请求网元所要求的第一网络参数和第一分析请求网元期望的第一网络指标可用于确定第一分析请求网元对应的推荐的网络参数，第二分析请求网元所要求的第二网络参数和第二分析请求网元期望的第二网络指标可用于确定第二分析请求网元对应的推荐的网络参数。
其中，分析请求网元要求的网络参数可包括分析请求网元要求的网络参数的类型，或包括要求的网络参数的类型和数值。分析请求网元要求的网络参数可以是对于分析请求网元来说网络参数的可接受的调整范围，使得数据分析网元根据网络参数的可接受的调整范围确定推荐的网络参数，避免数据分析网元所确定的推荐的网络参数超出分析请求网元的接受范围。应理解，请求消息可以携带包括至少一个要求的网络参数的网络参数列表。
分析请求网元期望的网络指标，可包括分析请求网元期望的网络指标的类型，或包括期望的网络指标的类型和数值(或数值范围)。分析请求网元期望的网络指标可以是分析请求网元希望网络指标能够达到的数值。比如，分析请求网元希望经过对网络参数的调整，使得网络指标能够达到一定的数值，则可以向数据分析网元发送该数值，使得数据分析网元能够预测使得网络指标达到该数值的推荐的网络参数。因此数据分析网元可确定使网络指标达到期望的网络指标的网络参数，用于确定推荐的网络参数。在一种可能的实现方式中，本申请中第一分析请求网元期望的网络指标的类型与第二分析请求网元期望的网络指标的类型相同，例如对于业务体验分析来说，第一分析请求网元期望的网络指标的类型与第二分析请求网元期望的网络指标的类型均为体验评分，如MOS。在另一种可能的实现方式中，本申请中第一分析请求网元期望的网络指标的类型与第二分析请求网元期望的网络指标的类型可以不同，例如对于业务体验分析来说，第一分析请求网元期望的网络指标的类型为体验评分(如MOS)，而第二分析请求网元期望的网络指标为业务体验质量达标的比例。
仍以第一请求消息为例，网络指标可以是MOS，如果第一分析请求网元期望的MOS不低于4.5，则数据分析网元可且令MOS不低于4.5的网络参数，并根据这些网络参数确定推荐的第一网络参数，其中，0≤MOS≤5。此外，第二分析请求网元期望的MOS可能与第一分析请求网元期望的MOS的数值相同或不同。
在一种可能的实现方式中，请求消息(例如第一请求消息和/或第二请求消息)中还可包括推荐的网络参数的要求信息。其中，该要求信息可用于指示从分析请求网元要求的网络参数的范围内和/或在分析请求网元期望的网络指标对应的网络参数的范围内，确定推荐的网络参数。具体的，要求信息可用于指示在要求的网络参数的范围内和/或在分析请求网元期望的网络指标对应的网络参数的范围内的最大或最小的网络参数作为推荐的网络参数，或者，要求信息可用于指示将预测的网络指标的最大值或最小值对应的网络参数作为推荐的网络参数。此外，要求信息还可用于代价函数。其中，代价函数是使用训练模型找到最优解的目的函数，用于从满足分析请求网元期望的网络指标所对应的多个网络参数中确定最优的网络参数作为推荐值。具体的，要求信息可用于指示推荐的网络参数的代价函 数最小，此时推荐的网络参数对应的系统开销最小。例如，在第一请求消息中还可包括第一分析请求网元的要求信息，该要求信息可用于确定第一分析请求网元对应的推荐的网络参数；和/或，在第二请求消息中还可包括第二分析请求网元的要求信息，该要求信息可用于确定第二分析请求网元对应的推荐的网络参数。
在一种可能的实现方式中，如果请求消息中包括分析请求网元期望的网络指标，请求消息中还可包括网络指标达到该期望的网络指标的期望比例。以网络指标是MOS为例，该期望比例可指示根据数据请求消息对应的分析结果调整网络参数后，分析请求网元希望的用户的MOS达到该期望的MOS的期望比例，例如，该期望比例不低于90％。例如，在第一请求消息中还可包括第一分析请求网元的期望比例，和/或，在第二请求消息中还可包括第二分析请求网元的期望比例。
在一种可能的实现方式中，该请求消息中还可包括分析请求网元所请求的分析类型，比如，第一请求消息和第二请求消息中均携带业务体验分析对应的分析类型标识。
本申请中，S101所示的请求消息可以是用于请求数据分析网元提供分析服务的消息，也可以是用于请求订阅分析服务的订阅请求。如果是用于请求提供分析服务的消息，则数据分析网元根据请求消息，一次性地向分析请求网元输出分析结果。如果是分析服务的订阅消息，则数据分析网元根据请求消息，定时或事件触发向分析请求网元多次输出分析结果，直到分析请求网元取消本次订阅。
其中，如果请求消息是订阅请求，则请求消息中还可包括订阅标识，用于标识本次订阅，则分析请求网元可通过订阅标识区分不同的分析订阅。
例如，来自于第一分析请求网元的第一请求消息中可携带订阅标识#1，来自于第二分析请求网元的第二请求消息中可携带订阅标识#2，则在数据分析网元接收订阅后，在第一分析请求网元与数据分析网元之间传输的每个消息中均可携带订阅标识#1，以及，在第二分析请求网元与数据分析网元之间传输的每个消息中均可携带订阅标识#2。
S102：数据分析网元根据第一网络指标和第二网络指标确定第三网络指标，第三网络指标为第一分析请求网元和第二分析网元共同期望的网络指标。
其中，如果第一网络指标和第二网络指标相同，则第三网络指标可以是第一网络指标或第二网络指标。例如，以业务体验分析为例，如果第一网元指标和第二网络指标均为MOS不低于4.5，则第三网络指标可以是MOS不低于4.5。
如果第一网络指标和第二网络指标不同，则第三网络指标可以是根据第一网络指标和/或第二网络指标确定的。比如，第三网络指标可以是第一网络指标和第二网络指标的交集。仍以业务体验分析为例，如果第一网络指标为MOS不低于4.5，第二网络指标为MOS不低于4，则第三网络指标可以是MOS不低于45。或者，第三网络指标也可以是第一网络指标和第二网络指标的折中数值等，例如，第一网络指标为MOS不低于4.5，第二网络指标为MOS不低于4第三网络指标为MOS不低于4.3。又如，在没有网络参数能够满足第一网络指标和第二网络指标的交集的情况下，数据分析网元可以将第一网络指标和第二网络指标的并集作为第三网络参数。其中，满足第一网络指标和第二网络指标的交集，是指训练后的模型的自变量包括在第一分析请求网元要求的网络参数的范围内的任意网络参数和在第二分析请求网元要求的网络参数的范围内的任意网络参数的情况下，均无法使模型的因变量在第一网络指标和第二网络指标的交集的范围内。
应理解，如果第三网络指标与第一网络指标不同，则数据分析网元可以向第一分析请 求网元发送第一消息。其中，该第一消息用于将期望的网络指标修改为第三网络指标。同理，如果第三网络指标与第二网络指标不同，则数据分析网元可以向第二分析请求网元发送用于将期望的网络指标修改为第三网络指标的消息(也可以是第一消息，或者是另外的消息)。
此外，如果第一网络指标的类型和第二网络指标的类型不同，则第三网络指标的类型可以与第一网络指标和第二网络指标中的一个相同，或者，第三网络指标包括第一网络指标和第二网络指标。例如，例如对于业务体验分析来说，第一分析请求网元期望的网络指标为MOS不低于4.5，而第二分析请求网元期望的网络指标为业务体验质量达标的比例不低于90％，则第三网络指标为MOS不低于4.5的比例大于等于90％。
S103：数据分析网元根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数，确定推荐的第三网络参数和推荐的第四网络参数，推荐的第三网络参数对应于第一网络参数，也就是说，推荐的第三网络参数是根据第一网络参数确定的；推荐的第四网络参数对应于第二网络参数，也就是说，推荐的第四网络参数是根据第二网络参数确定的。
在S103中，数据分析网元可以通过训练后的模型并根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数，确定推荐的网络参数。其中，如果没有已经训练好的模型时，数据分析网元需要首先进入模型训练阶段，在训练阶段获得训练好的模型。其中在模型训练阶段，输入数据为数据分析网元收集的数据，包括模型的自变量(包括网络参数)和对应的因变量(包括网络指标)，输出网络模型的结构和内部参数，即训练后的模型，这时数据分析网元获得了训练后的模型。如果数据分析网元已经有训练后的模型，比如，通过此前的训练阶段获得该模型，或者从其他网元或设备接收该模型，则数据分析网元可以使用该训练后的模型用于推理、预测或推荐。该模型用于推理和预测时，模型的输入数据可包括自变量，模型的输出结果可包括因变量。当该训练后的模型用于确定推荐的自变量时，模型的输入数据可包括预测的模型的因变量(包括一个或多个预测要达到的网络指标，在S103中具体可以包括第三网络指标)，模型的输出结果可包括至少一个类型的推荐的自变量(例如包括推荐的第三网络参数和第四推荐的网络参数)。
进一步的，数据分析网元可根据请求消息确定分析请求网元要求的网络参数的类型，根据要求的网络参数的类型从训练后的模型的多个类型的推荐的自变量中确定与要求的网络参数的类型相同的一个或多个类型的网络参数，作为推荐的网络参数。此外，数据分析网元还可确定要求的网络参数的类型以外的其他类型的推荐的网络参数(以下称为未要求的网络参数)，这些未要求的网络参数可以取该类型的网络参数的当前数值或历史平均值，或者还可以取该类型的网络参数未来最大概率出现的预测值。
以业务体验分析为例，如果第一分析请求网元为SMF，SMF要求的网络参数包括比特速率和端到端时延，即第一网络参数包括比特速率和端到端时延，第二分析请求网元为AF，AF要求的网络参数包括DNAI，即第二网络参数包括DNAI，则数据分析网元可确定满足第三网络指标的至少一组网络参数，每组网络参数至少包括DNAI、比特速率和端到端时延。
然后数据分析网元根据所述模型和所述一个或多个分析请求网元期望的网络指标，分析输出对应的一个或多个网络参数的推荐值，这里的网络参数的推荐值包括要求的网络参 数的推荐值，还可包括未要求的网络参数的推荐值。比如，SMF要求的网络参数的类型为比特速率，数据分析网元可确定推荐的比特速率，以及还可以确定推荐的端到端时延，并向分析请求网元发送推荐的比特速率和推荐的端到端时延。
例如，在数据分析网元可确定满足第三网络指标的至少一组网络参数后，数据分析网元进一步可根据SMF要求的比特速率的数值和端到端时延的数值，以及AF要求的DNAI的数值，从至少一组网络参数中，确定一组网络参数，该组网络参数中的比特速率和端到端时延为推荐的第三网络参数，该组网络参数中的DNAI为推荐的第四网络参数。示例性的，数据分析网元确定的该组网络参数中，比特速率的数值在SMF要求的比特速率的范围内、端到端时延的数值在SMF要求的端到端时延的范围内，且DNAI在AF要求的DNAI的范围内。
在一种可能的实现方式中，数据分析网元的因变量还可包括网络指标达到所述第三网络指标的预测比例，该预测比例可指示同时采用推荐的第三网络参数和第四网络参数进行调整后，预计实际的网络指标能够达到所述第三网络指标的比例，则数据分析网元还可发送所述第三网络指标和所述预测比例。其中，所述预测比例可以等于或大于第一请求消息中携带的期望比例，也可以小于第一请求消息中的所述期望比例；或者，所述预测比例可以等于或大于第二请求消息中携带的期望比例，也可以小于第二请求消息中的期望比例。所述预测比例可以帮助分析请求网元确定是否接受推荐的网络参数并进行调整。
应理解，这里所述的模型的训练过程可以在数据分析网元中进行，也可以由其他网元通过训练获得训练后的模型后将该模型发送给数据分析网元。如果由数据分析网元确定该模型，数据分析网元可以按照一定的周期收集数据并训练模型，因此不需要在每次执行网络智能分析时重新训练模型。
S104：数据分析网元发送推荐的第三网络参数和推荐的第四网络参数。
在一种可能的实现方式中，数据分析网元可向第一分析请求网元或第二分析请求网元发送第一分析结果，该第一分析结果中可包括推荐的第三网络参数和/或推荐的第四网络参数。此外，第一分析结果中还可包括要求的第三网络参数或第四网络参数、所述第三网络指标、所述预测比例中的至少一项。
采用图4所示方法，在数据分析网元分别接收到来自于多个分析请求网元的业务分析请求消息的情况下，可以根据其中一个业务分析请求网元权要的网络指标，确定这两个分析请求网元分别的推荐的网络参数，避免多个分析请求网元各自按照不同的网络指标的目标对网络参数进行调整而导致网络性能的降低或业务中断，以提高智能分析的可靠性。
下面以数据分析网元是NWDAF、第一分析请求网元是SMF，第二分析请求网元是AF为例，结合图5对本申请实施例提供的一种通信方法进行说明。
如图5所示，该方法可包括以下步骤：
S201：SMF向NWDAF发送订阅请求。
其中，该订阅请求中可携带业务体验分析对应的分析类型标识、SMF期望的网络指标、SMF要求的网络参数。例如，SMF期望的网络指标为MOS大于4.0，SMF要求的网络参数包括比特速率。
在一种可能的实现方式中，该订阅消息中还可携带订阅标识。
相应地，NWDAF接收该请求消息。
S202：NWDAF向SMF发送订阅请求的响应消息。
其中，该响应消息可用于指示订阅成功。订阅请求的响应消息中可包括S201中的订阅标识。
在S202之前NWDAF可以在确定接受该订阅请求后执行S202。
在一种可能的实现方式中，NWDAF还可在接受SMF的订阅请求后存储SMF的订阅内容，订阅内容包括但不限于该订阅请求中的业务类型标识、SMF期望的网络指标、SMF要求的网络参数和订阅标识。
相应地，SMF接收该订阅请求的响应消息。
S203：AF通过NEF向NWDAF发送订阅请求。
其中，该订阅请求中可携带业务体验分析对应的分析类型标识、AF期望的网络指标、AF要求的网络参数。例如，AF期望的网络指标为MOS大于4.5，AF要求的网络参数包括DNAI。
在一种可能的实现方式中，该订阅消息中还可携带订阅标识。
相应地，NWDAF接收该请求消息，并存储AF对应的订阅内容，包括但不限于存储业务类型标识、AF要求的网络参数、AF期望的网络指标和订阅标识。
S204：NWDAF确定SMF请求分析的业务类型与AF请求分析的业务类型相同，但是SMF期望的网络指标与AF期望的网络指标不一致，NWDAF进一步确定SMF和AF共同期望的网络指标为MOS大于4.0。
其中，NWDAF可确定存储的S201的订阅请求中的分析类型标识与S203的订阅请求的分析类型标识相同，且存储的S201的订阅请求中的SMF期望的网络指标与S203中AF期望的网络指标不同，则NWDAF可确定SMF与AF请求的分析类型相同且期望的网络指标不一致。
S205：NWDAF通过NEF向AF发送第一消息，该第一消息用于将期望的网络指标修改为MOS大于4.0。该第一消息中还可携带S204中的订阅标识。
相应地，AF接收第一消息。
S206：AF通过NEF向NWDAF发送更新的订阅请求，其中携带的期望的网络指标指示MOS大于4.0。更新的订阅请求中可携带S204所示的订阅标识。
相应地，NWDAF接收更新的订阅请求，并根据更新的订阅请求更新AF的订阅内容，更新后AF的订阅内容包括业务类型标识、AF期望的网络指标(为S206更新的订阅请求中的数值)、AF要求的网络参数和订阅标识。
S207：NWDAF确定SMF的订阅和AF的订阅期望的网络指标相同，根据该期望的网络指标、SMF要求的网络参数和AF要求的网络参数确定推荐的网络参数。
示例性的，该推荐的网络参数包括：推荐的比特速率为14Mbps，以及推荐的DNAI的标识为DNAI#1。
可选的，NWDAF可将推荐的比特速率与SMF的标识和S201中的订阅标识进行关联，以及将推荐的DNAI与AF的标识和S204中的订阅标识进行关联。
S208：NWDAF向SMF发送推荐的比特速率。
具体的，NWDAF可向SMF发送推荐的比特速率和S201中的订阅标识。
相应地，SMF接收推荐的比特速率。
S209：NWDAF通过NEF向AF发送推荐的DNAI。
具体的，NWDAF可通过NEF向AF发送推荐的DNAI和S204中的订阅标识。
相应地，AF接收推荐的DNAI。
基于图5所示流程，在接收到来自于多个分析请求网元的分析请求的情况下，如果NWDAF确定多个分析请求的业务类型标识相同，但是期望的网络指标的数值不同，则NWDAF可以确定多个分析请求网元共同期望的网络指标，根据该共同期望的网络指标确定推荐的网络参数可以避免不同的分析请求网元进行网络参数调整时产生冲突。
在一种可能的实现方式中，如果第一网络参数的类型与第二网络参数的类型重合，例如，第一网络参数(或第一网络参数包括的部分网络参数)的类型与第二网络参数(或第二网络参数包括的部分网络参数)的类型相同，则在S104中可由数据分析网元向第一分析请求网元和/或第二分析请求网元发送推荐的网络参数，此时第一分析请求网元获得的推荐的网络参数的类型可能与第一网络参数的类型不同，和/或，第二分析请求网元获得的推荐的网络参数的类型可能与第二网络参数的类型不同。
下面结合第一网络参数的类型和第二网络参数的类型是否重合的不同情况，对S104的实现方式进行举例说明。
情况1，第一网络参数对应于第三网络参数，第二网络参数对应于第四网络参数，且第一网络参数与第二网络参数之间不重合，S104中，数据分析网元可以向第一分析请求网元发送推荐的第三网络参数，并向第二分析请求网元发送推荐的第四网络参数。
应理解，当网络参数A与网络参数B相同时，为了方便说明，可称这网络参数A对应于网络参数B，其中，网络参数A和网络参数B可包括至少一种类型的网络参数。例如，网络参数A和网络参数B均包括a和b这两种网络参数，则可称网络参数A对应于网络参数B，和/或，网络参数A(或网络参数B)对应于a和b这两种网络参数。
情况2，第一网络参数对应于第三网络参数和第四网络参数，第二网络参数对应于第四网络参数，且第一网络参数与第二网络参数之间存在重合，第三网络参数和第四网络参数不重合。
在情况2中，在确定推荐的第三网络参数和推荐的第四网络参数后，数据分析网元可以通过以下方式中的任意一种实现网络参数的推荐：
方式1，数据分析网元可以向第一分析请求网元发送推荐的第三网络参数和推荐的第四网络参数，此时不需要向第二分析请求网元发送推荐的第三网络参数和第四网络参数。
例如，第一分析请求网元是SMF，SMF要求的第一网络参数包括比特速率，第二分析请求网元是UPF，UPF要求的第二网络参数包括比特速率和端到端时延，因此SMF要求的第一网络参数与UPF要求的第二网络参数均包括比特速率。在方式1中，数据分析网元可以向SMF发送推荐的比特速率和推荐的端到端时延，以及，向UPF发送推荐的比特速率。
可见在方式1中，数据分析网元向第一分析请求网元和第二分析请求网元推荐的网络参数分别与第一分析请求网元要求的网络参数和第二分析请求网元要求的网络参数的类型相同，使得推荐的网络参数能够满足分析请求网元的要求。
方式2，数据分析网元可以向第一分析请求网元发送推荐的第三网络参数，以及向第二分析请求网元发送推荐的第四网络参数。
例如，第一分析请求网元是UPF，UPF要求的第一网络参数包括比特速率和端到端时延，第二分析请求网元是SMF，SMF要求的第二网络参数包括比特速率，因此UPF要求的第一网络参数与SMF要求的第二网络参数均包括比特速率。在方式2中，数据分析网 元可以向UPF发送推荐的端到端时延，以及，向SMF发送推荐的比特速率。
此外在方式2中，由于方式2中没有根据第一分析请求向第一分析请求网元发送推荐的第四网络参数，此时数据分析网元可以向第一分析请求网元发送第二消息，该第二消息可用于取消第一分析请求网元对于要求的第四网络参数的请求(或订阅)，或者，第二消息可用于将第一分析请求网元要求的网络参数修改为第三网络参数，或者，第二消息用于指示已将推荐的第四网络参数发送至第二分析请求网元，或者，第二消息可用于指示由第二分析请求网元根据推荐的第四网络参数进行网络参数的调整。例如沿用上例，数据分析网元还可向UPF发送第二消息，以指示取消UPF对于推荐的比特速率的请求。
方式3，数据分析网元可以向第一分析请求网元发送推荐的第三网络参数和推荐的第四网络参数，此时不需要向第二分析请求网元发送推荐的第三网络参数和推荐的第四网络参数。
例如，第一分析请求网元是UPF，UPF要求的第一网络参数包括比特速率和端到端时延，第二分析请求网元是SMF，SMF要求的第二网络参数包括比特速率，因此UPF要求的第一网络参数与SMF要求的第二网络参数均包括比特速率。在方式3中，数据分析网元可以向UPF发送推荐的比特速率和推荐的端到端时延，此时，数据分析网元不需要向SMF发送推荐的比特速率。
此外在方式3中，由于方式3中没有根据第二分析请求向第二分析请求网元发送第二网络参数对应的推荐的网络参数，此时数据分析网元可以向第二分析请求网元发送第三消息，该第三消息可用于取消第二分析请求网元对于推荐的第四网络参数的请求(或订阅)，或者，第三消息用于指示已将要求的第四网络参数发送至第一分析请求网元，或者，第三消息可用于指示由第一分析请求网元根据推荐的第四网络参数进行网络参数的调整。例如沿用上例，数据分析网元还可向SMF发送第三消息，以指示取消SMF对于推荐的比特速率的请求。
根据方式2和方式3，数据分析网元在确定第一网络参数与第二网络参数之间存在重合的情况下，不会将推荐的重合的网络参数发送给两个分析请求网元，而是将推荐的重合的网络参数发送给其中一个分析请求网元，避免这两个分析请求网元都根据推荐的网络参数进行调整，造成网络参数的过度调整。
下面以数据分析网元是NWDAF、第一分析请求网元是UPF，第二分析请求网元是SMF为例，结合图6对本申请实施例提供的另一种通信方法进行说明。
如图6所示，该方法可包括以下步骤：
S301：SMF向NWDAF发送订阅请求。
其中，该订阅请求中可携带业务体验分析对应的分析类型标识、SMF期望的网络指标、SMF要求的网络参数。例如，SMF期望的网络指标为MOS大于4.0，SMF要求的网络参数包括比特速率。
在一种可能的实现方式中，该订阅消息中还可携带订阅标识。
相应地，NWDAF接收该请求消息。
S302：NWDAF向SMF发送订阅请求的响应消息。
其中，该响应消息可用于指示订阅成功。订阅请求的响应消息中可包括S301中的订阅标识。
在S302之前NWDAF可以在确定接受该订阅请求后执行S302。
在一种可能的实现方式中，NWDAF还可在接受SMF的订阅请求后存储SMF的订阅内容，订阅内容包括但不限于该订阅请求中的业务类型标识、SMF期望的网络指标、SMF要求的网络参数和订阅标识。
相应地，SMF接收该订阅请求的响应消息。
S303：UPF向NWDAF发送订阅请求。
其中，该订阅请求中可携带业务体验分析对应的分析类型标识、UPF期望的网络指标、AF要求的网络参数。例如，UPF期望的网络指标为MOS大于4.0，UPF要求的网络参数包括比特速率和端到端时延。
在一种可能的实现方式中，该订阅消息中还可携带订阅标识。
相应地，NWDAF接收该请求消息，并存储UPF对应的订阅内容，包括但不限于存储业务类型标识、UPF要求的网络参数、UPF期望的网络指标和订阅标识。
S304：NWDAF确定SMF请求分析的业务类型与UPF请求分析的业务类型相同，并且SMF要求的网络参数与AF要求的网络参数存在重合。其中，重合的网络参数为比特速率。
其中，NWDAF可确定存储的S301的订阅请求中的分析类型标识与S303的订阅请求的分析类型标识相同，且存储的S301的订阅请求中的SMF要求的网络参数与S303中UPF要求的网络参数均包括同一类型的网络参数(这里是比特速率)，则NWDAF可确定SMF请求分析的业务类型与UPF请求分析的业务类型相同，并且SMF要求的网络参数与AF要求的网络参数存在重合。
S305：NWDAF向UPF发送第二消息，该第二消息用于UPF将要求的网络参数修改为端到端时延。
或者，第三消息可用于指示由SMF根据推荐的对比特速率进行调整。
示例性的，第三消息中可包括S304中的订阅标识、用于指示有事项待确认(即需要确认修改后的要求的网络参数)的标识、将网络参数修改为端到端时延的信息和SMF的标识中的至少一项。
相应地，UPF接收第一消息。
S306：UPF向NWDAF发送更新的订阅请求，其中携带的要求的网络指标指示MOS大于4.0。更新的订阅请求中可携带S204所示的订阅标识。
相应地，NWDAF接收更新的订阅请求，并根据更新的订阅请求更新UPF的订阅内容，更新后UPF的订阅内容包括业务类型标识、UPF期望的网络指标(为S206更新的订阅请求中的数值)、UPF要求的网络参数和订阅标识。
在另一种可能的示例中，NWDAF还可向SMF发送要求的网络参数冲突的通知，该通知中可携带S301中的订阅标识、发生冲突的传输(这里即比特速率)和UPF的标识中的至少一项，可由SMF决定是否更改要求的网络参数。如果SMF决定不更改SMF要求的网络参数，SMF可向UPF通知不再由UPF请求推荐的比特速率，则UPF可以执行S306，此时不需要执行S305。
另一种可能的示例中，如果SMF决定更改SMF要求的网络参数，SMF可向NWDAF发送用于取消对于推荐的比特速率的订阅的消息，此时可由NWDAF向UPF发送推荐的比特速率，从而由UPF对比特速率进行调整。此时不需要执行S305和S306。
S307：NWDAF确定SMF的订阅和UPF的订阅中的要求的网络参数不重合，根据期 望的网络指标、SMF要求的网络参数和UPF要求的网络参数确定推荐的网络参数。
可选的，NWDAF可将推荐的比特速率与SMF的标识和S301中的订阅标识进行关联，以及将推荐的端到端时延与UPF的标识和S304中的订阅标识进行关联。
S308：NWDAF向SMF发送推荐的比特速率。
具体的，NWDAF可向SMF发送推荐的比特速率和S201中的订阅标识。
相应地，SMF接收推荐的比特速率。
S309：NWDAF向UPF发送推荐的端到端时延和S304中的订阅标识。
相应地，UPF接收推荐的端到端时延。
采用图6所示流程，NWDAF可以在SMF和UPF均请求推荐的比特速率的情况下，决定由SMF或UPF中的一个获得推荐的比特速率，避免推荐冲突。
在一种可能的实现方式中，在S104之后，如果推荐的第三网络参数和推荐的第四网络参数分别发送至第一分析请求网元和第二分析请求网元，则在第一分析请求网元或第二分析请求网元不接受来自于数据分析网元的推荐的网络参数的情况下，数据分析网元可以重新确定第一分析请求网元对应的推荐的网络参数(以下称为推荐的第五网络参数)和第二分析请求网元对应的推荐的网络参数(以下称为推荐的第六网络参数)。应理解，推荐的第五网络参数对应于第一网络参数，也就是说，推荐的第五网络参数根据第一网络参数确定；推荐的第六网络参数对应于第二网络参数，也就是说，推荐的第六网络参数根据第二网络参数确定。
具体来说，数据分析网元可根据来自于第一分析请求网元的第四消息确定第一分析请求网元不接受推荐的第三网络参数，例如，第四消息可用于指示第一分析请求网元不接受推荐的第三网络参数，或者，第四消息可用于指示第一分析请求网元请求重新确定推荐的网络参数(如重新确定推荐的第三网络参数或推荐的第一网络参数)。其中，如果分析请求网元确定无法根据推荐的网络参数的类型或数值对网络参数进行调整，则可确定不接受推荐的网络参数。
数据分析网元可根据第四信息重新确定推荐的网络参数。一种可能的实现方式中，数据分析网元可从该不被接受的网络参数的历史平均值或最大似然概率值作为推荐的第五网络参数，并根据该推荐的第五网络参数确定推荐的第六网络参数。例如，将与推荐的网络参数同属一组的且与第二网络参数的类型相同的网络参数作为推荐的第六网络参数，其中，推荐的第五网络参数和推荐的第六网络参数属于一组能够满足第三网络指标的网络参数。
此外，数据分析网元也可从满足第三网络指标的至少一组网络参数中确定一组网络参数，将该组网络参数包括的与第一网络参数的类型相同的网络参数作为推荐的第五网络参数，以及将该组网络参数包括的与第二网络参数的类型相同的网络参数作为推荐的第六网络参数。或者，数据分析网元可以根据重新根据第一网络指标和第二网络指标确定更新的第三网络指标，之后根据更新的第三网络指标确定推荐的第五网络参数和推荐的第六网络参数，具体实现方式可参见根据第三网络指标确定推荐的第三网络参数和推荐的第四网络参数的说明。
同理，如果第二分析请求网元不接受推荐的第四网络参数，则第二分析请求网元可向数据分析网元发送用于指示不接受推荐的第四网络参数的消息，数据分析网元可根据该消息重新确定推荐的网络参数。
下面以数据分析网元是NWDAF、第一分析请求网元是UPF，第二分析请求网元是SMF为例，结合图7对本申请实施例提供的另一种通信方法进行说明。
如图7所示，本申请实施例提供的通信方法可包括以下步骤：
S401：NWDAF向UPF发送推荐的端到端时延，以及向SMF发送推荐的比特速率。
其中，推荐的端到端时延和推荐的比特速率满足UPF和SMF共同期望的网络指标，例如，推荐的端到端时延为10ms，推荐的比特速率为5Mbps。
示例性的，S401的实现方式可参见图6中的说明。
S402：UPF接收到推荐的端到端时延后，确定该推荐的端到端时延是不可接受的。
在一种可能的实现方式中，虽然该推荐的端到端时延的数值在UPF要求的端到端时延的范围内，但是UPF根据当前网络运行情况无法将端到端时延调整到推荐的数值，于是确定该端到端时延是不可接受的。
例如，UPF当前不支持10ms的端到端时延，则UPF可确定推荐的端到端时延不可接受。
S403：UPF向NWDAF发送第四消息，第四消息用于指示UPF不接受推荐的端到端时延。
相应地，NWDAF接收第四信息。
S404：NWDAF将推荐的比特速率的历史平均值作为更新的端到端时延，以及根据更新的端到端时延确定满足网络指标的更新的比特速率。
S405：NWDAF向UPF发送更新的端到端时延。
相应地，UPF接收更新的端到端时延。
S406：NWDAF向SMF发送更新的比特速率。
相应地，SMF接收更新的比特速率。
采用图7所示流程，NWDAF可以在UPF不接受推荐的端到端时延的情况下，重新确定推荐的比特速率和端到端时延，并分别向SMF和UPF指示推荐的比特速率和推荐的端到端时延，避免网络参数调整和结果不能满足期望的网络指标。
图8和图9为本申请的实施例提供的可能的通信装置的结构示意图。这些通信装置可以用于实现上述方法实施例中数据分析网元或分析请求网元的功能，因此也能实现上述方法实施例所具备的有益效果。在本申请的实施例中，该通信装置可以是数据分析网元或分析请求网元，也可以是应用于数据分析网元或分析请求网元的模块(如芯片)。
如图8所示，通信装置800包括处理单元810和收发单元820。通信装置800用于实现上述方法实施例中数据分析网元或分析请求网元的功能。
在第一个实施例中，该通信装置用于实现上述方法实施例中数据分析网元的功能，收发单元820可用于接收第一请求消息和第二请求消息，第一请求消息来自于第一分析请求网元，第一请求消息用于请求推荐的第一网络参数，第一请求消息包括第一分析请求网元要求的第一网络参数和第一网络指标，第一网络指标为第一分析请求网元期望的网络指标，第二请求消息来自于第二分析请求网元，第二请求消息用于请求推荐的第二网络参数，第二请求消息包括第二分析请求网元要求的第二网络参数和第二网络指标，第二网络指标为第二分析请求网元期望的网络指标。数据分析网元还可根据第一网络指标和第二网络指标确定第三网络指标，第三网络指标为第一分析请求网元和第二分析网元共同期望的网络指标。处理单元810可用于根据第三网络指标、第一分析请求网元要求的第一网络参数和第 二分析请求网元要求的第二网络参数，确定推荐的第三网络参数和推荐的第四网络参数。收发单元820还可用于发送推荐的第三网络参数和推荐的第四网络参数。
作为一种可能的实现方法，对应于推荐的第三网络参数和推荐的第四网络参数的预测的网络指标在第三网络指标的范围内。
作为一种可能的实现方法，收发单元820还可用于向第一分析请求网元和/或第二分析请求网元发送第一消息，第一消息用于将期望的网络指标修改为第三网络指标。
在一种可能的设计中，如果第一网络参数对应于第三网络参数和第四网络参数，第二网络参数对应于第四网络参数，则收发单元820还可用于向第一分析请求网元发送推荐的第三网络参数，以及，收发单元820还可用于向第二分析请求网元发送推荐的第四网络参数。
在一种可能的设计中，收发单元820还可用于向第一分析请求网元发送第二消息，第二消息用于第一分析请求网元将要求的网络参数修改为第三网络参数。
在一种可能的设计中，如果第一网络参数对应于第三网络参数和第四网络参数，第二网络参数对应于第三网络参数和/或第四网络参数，则收发单元820还可用于向第一分析请求网元发送推荐的第三网络参数和推荐的第四网络参数。
在一种可能的设计中，收发单元820还可用于向第二分析请求网元发送第三消息，第三消息用于取消根据第二分析请求网元要求的第二网络参数获得推荐的网络参数。
在一种可能的设计中，收发单元820还可用于向第一分析请求网元发送推荐的第三网络参数，并向第二分析请求网元发送推荐的第四网络参数，推荐的第三网络参数对应于第一网络参数，推荐的第四网络参数对应于第二网络参数。
在一种可能的设计中，收发单元820还可接收来自于第一分析请求网元发送的第四消息，第四消息用于指示不接受推荐的第三网络参数。处理单元810进一步可根据第四消息，根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数，确定推荐的第五网络参数和推荐的第六网络参数，推荐的第五网络参数对应于第一网络参数，推荐的第六网络参数对应于第二网络参数，推荐的第五网络参数的数值与推荐的第三网络参数的数值不同。收发单元820还可用于向第一分析请求网元发送推荐的第五网络参数，并向第二分析请求网元发送推荐的所述第六网络参数。
在第二个实施例中，该通信装置用于实现上述方法实施例中第一分析请求网元的功能，则处理单元810可用于确定第一请求消息，所述第一请求消息用于请求推荐的第一网络参数，所述第一请求消息包括所述第一分析请求网元要求的所述第一网络参数和第一网络指标，所述第一网络指标为所述第一分析请求网元期望的网络指标。收发单元820还可用于向数据分析网元发送所述第一请求消息。
在一种可能的设计中，如果所述第一网络参数对应于第三网络参数和第四网络参数，则收发单元820还可用于接收来自于所述数据分析网元的推荐的所述第三网络参数。其中，所述推荐的第三网络参数根据第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为所述第二分析请求网元期望的网络指标。
在一种可能的设计中，收发单元820还可用于接收来自于所述数据分析网元的第一消息，所述第一消息用于将期望的网络指标修改为所述第三网络指标。处理单元810还可根 据所述第一消息确定是否将期望的网络指标修改为所述第三网络指标。
在一种可能的设计中，收发单元820还可用于接收来自于所述数据分析网元的第二消息，所述第二消息用于所述第一分析请求网元将要求的网络参数修改为所述第三网络参数。
在一种可能的设计中，如果所述第一网络参数对应于第三网络参数和第四网络参数，则收发单元820还可用于接收来自于所述数据分析网元的推荐的所述第三网络参数和所述推荐的所述第四网络参数，所述推荐的第三网络参数和所述推荐的第四网络参数根据第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为所述第二分析请求网元期望的网络指标。
在一种可能的设计中，对应于所述推荐的第三网络参数和所述推荐的第四网络参数的预测的网络指标在所述第三网络指标的范围内。
在一种可能的设计中，收发单元820还可用于接收来自于所述数据分析网元的推荐的第三网络参数。收发单元820还可用于向所述数据分析网元发送第四消息，所述第四消息用于指示不接受所述推荐的所述第三网络参数。收发单元820还可用于接收来自于所述数据分析网元的推荐的第五网络参数，所述推荐的第五网络参数对应于所述第一网络参数，所述推荐的第五网络参数根据第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为所述第二分析请求网元期望的网络指标。
在第三个实施例中，该通信装置用于实现上述方法实施例中第二分析请求网元的功能，则处理单元810可用于确定第二请求消息，第二请求消息用于请求推荐的第二网络参数，第二请求消息包括第二分析请求网元要求的第二网络参数和第二网络指标，第二网络指标为第二分析请求网元期望的网络指标。收发单元820可用于向数据分析网元发送第二请求消息。
在一种可能的设计中，收发单元820还可用于接收来自于数据分析网元的推荐的第四网络参数。其中，推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定，第三网络指标为第一分析请求网元和第二分析请求网元共同期望的网络指标，第三网络指标根据第二网络指标和第一网络指标确定，第一网络指标为第一分析请求网元期望的网络指标。
在一种可能的设计中，收发单元820还可用于接收来自于数据分析网元的第一消息，第一消息用于将期望的网络指标修改为所述第三网络指标。处理单元810可用于根据第一消息确定是否将期望的网络指标修改为所述第三网络指标。
在一种可能的设计中，收发单元820还可用于接收来自于数据分析网元的第三消息，第三消息用于取消根据第二分析请求网元要求的第二网络参数获得推荐的网络参数。
在一种可能的设计中，收发单元820还可用于接收来自于数据分析网元的推荐的第四网络参数。其中，推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定，第三网络指标为第一分析请求网元和第二分析请求网元共同期望的网络指标，第三网络指标根据第二网络指标和第一网络指标确定，第一网络指标为第一分析请求网元期望的网络指标。收发单元820还可用于接 收来自于数据分析网元的推荐的第六网络参数，推荐的第六网络参数对应于第二网络参数，推荐的第六网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和第二分析请求网元要求的第二网络参数确定。
有关上述处理单元810和收发单元820更详细的描述可以直接参考上述方法实施例中相关描述直接得到，这里不加赘述。
如图9所示，通信装置900包括处理器910。作为一种实现方法，该通信装置900还包括接口电路920，处理器910和接口电路920之间相互耦合。可以理解的是，接口电路920可以为收发器或输入输出接口。作为一种实现方法，通信装置900还可以包括存储器930，用于存储处理器910执行的指令或存储处理器910运行指令所需要的输入数据或存储处理器910运行指令后产生的数据。
当通信装置900用于实现上述方法实施例时，处理器910用于实现上述处理单元810的功能，接口电路920用于实现上述收发单元820的功能。
可以理解的是，本申请的实施例中的处理器可以是中央处理单元(central processing unit，CPU)，还可以是其它通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field programmable gate array，FPGA)或者其它可编程逻辑器件、晶体管逻辑器件，硬件部件或者其任意组合。通用处理器可以是微处理器，也可以是任何常规的处理器。
本申请的实施例中的方法步骤可以通过硬件的方式来实现，也可以由处理器执行软件指令的方式来实现。软件指令可以由相应的软件模块组成，软件模块可以被存放于随机存取存储器、闪存、只读存储器、可编程只读存储器、可擦除可编程只读存储器、电可擦除可编程只读存储器、寄存器、硬盘、移动硬盘、CD-ROM或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于基站或终端中。当然，处理器和存储介质也可以作为分立组件存在于基站或终端中。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序或指令。在计算机上加载和执行所述计算机程序或指令时，全部或部分地执行本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、基站、用户设备或者其它可编程装置。所述计算机程序或指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机程序或指令可以从一个网站站点、计算机、服务器或数据中心通过有线或无线方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是集成一个或多个可用介质的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，例如，软盘、硬盘、磁带；也可以是光介质，例如，数字视频光盘；还可以是半导体介质，例如，固态硬盘。该计算机可读存储介质可以是易失性或非易失性存储介质，或可包括易失性和非易失性两种类型的存储介质。
在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，不同的实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑 关系可以组合形成新的实施例。
本申请中，“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。在本申请的文字描述中，字符“/”，一般表示前后关联对象是一种“或”的关系；在本申请的公式中，字符“/”，表示前后关联对象是一种“相除”的关系。
可以理解的是，在本申请的实施例中涉及的各种数字编号仅为描述方便进行的区分，并不用来限制本申请的实施例的范围。上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定。

Claims (48)

  1. 一种通信方法，其特征在于，包括：
    数据分析网元接收第一请求消息和第二请求消息，所述第一请求消息来自于第一分析请求网元，所述第一请求消息用于请求推荐的第一网络参数，所述第一请求消息包括所述第一分析请求网元要求的所述第一网络参数和第一网络指标，所述第一网络指标为所述第一分析请求网元期望的网络指标，所述第二请求消息来自于第二分析请求网元，所述第二请求消息用于请求推荐的第二网络参数，所述第二请求消息包括所述第二分析请求网元要求的所述第二网络参数和第二网络指标，所述第二网络指标为所述第二分析请求网元期望的网络指标；
    所述数据分析网元根据所述第一网络指标和所述第二网络指标确定第三网络指标，所述第三网络指标为所述第一分析请求网元和所述第二分析网元共同期望的网络指标；
    所述数据分析网元根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和所述第二分析请求网元要求的所述第二网络参数，确定推荐的第三网络参数和推荐的第四网络参数；
    所述数据分析网元发送所述推荐的第三网络参数和所述推荐的第四网络参数。
  2. 如权利要求1所述的方法，其特征在于，对应于所述推荐的第三网络参数和所述推荐的第四网络参数的预测的网络指标在所述第三网络指标的范围内。
  3. 如权利要求1或2所述的方法，其特征在于，所述方法还包括：
    所述数据分析网元向所述第一分析请求网元和/或第二分析请求网元发送第一消息，所述第一消息用于将期望的网络指标修改为第三网络指标。
  4. 如权利要求1-3中任一所述的方法，其特征在于，所述第一网络参数对应于所述第三网络参数和所述第四网络参数，所述第二网络参数对应于所述第四网络参数；
    所述数据分析网元发送所述推荐的第三网络参数和所述推荐的第四网络参数，包括：
    所述数据分析网元向所述第一分析请求网元发送所述推荐的所述第三网络参数；
    所述数据分析网元向所述第二分析请求网元发送所述推荐的所述第四网络参数。
  5. 如权利要求4所述的方法，其特征在于，所述方法还包括：
    所述数据分析网元向所述第一分析请求网元发送第二消息，所述第二消息用于所述第一分析请求网元将要求的网络参数修改为所述第三网络参数。
  6. 如权利要求1-3中任一所述的方法，其特征在于，所述第一网络参数对应于所述第三网络参数和所述第四网络参数，所述第二网络参数对应于所述第三网络参数和/或所述第四网络参数；
    所述数据分析网元发送所述推荐的第三网络参数和所述推荐的第四网络参数，包括：
    所述数据分析网元向所述第一分析请求网元发送所述推荐的所述第三网络参数和所述推荐的所述第四网络参数。
  7. 如权利要求6所述的方法，其特征在于，所述方法还包括：
    所述数据分析网元向所述第二分析请求网元发送第三消息，所述第三消息用于取消根据所述第二分析请求网元要求的所述第二网络参数获得推荐的网络参数。
  8. 如权利要求1-5中任一所述的方法，其特征在于，所述数据分析网元发送所述推荐的第三网络参数和所述推荐的第四网络参数，包括:
    所述数据分析网元向所述第一分析请求网元发送所述推荐的所述第三网络参数；
    所述数据分析网元向所述第二分析请求网元发送所述推荐的所述第四网络参数；
    所述推荐的第三网络参数对应于所述第一网络参数，所述推荐的第四网络参数对应于所述第二网络参数。
  9. 如权利要求8所述的方法，其特征在于，所述方法还包括：
    所述数据分析网元接收来自于所述第一分析请求网元发送的第四消息，所述第四消息用于指示不接受所述推荐的所述第三网络参数；
    所述数据分析网元根据所述第四消息，根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和所述第二分析请求网元要求的所述第二网络参数，确定推荐的第五网络参数和推荐的第六网络参数，所述推荐的第五网络参数对应于所述第一网络参数，所述推荐的第六网络参数对应于所述第二网络参数，所述推荐的所述第五网络参数的数值与所述推荐的所述第三网络参数的数值不同；
    所述数据分析网元向所述第一分析请求网元发送所述推荐的所述第五网络参数；
    所述数据分析网元向所述第二分析请求网元发送所述推荐的所述第六网络参数。
  10. 一种通信方法，其特征在于，包括：
    第一分析请求网元确定第一请求消息，所述第一请求消息用于请求推荐的第一网络参数，所述第一请求消息包括所述第一分析请求网元要求的所述第一网络参数和第一网络指标，所述第一网络指标为所述第一分析请求网元期望的网络指标；
    所述第一分析请求网元向数据分析网元发送所述第一请求消息。
  11. 如权利要求10所述的方法，其特征在于，所述方法还包括：
    所述第一分析请求网元接收来自于所述数据分析网元的推荐的第三网络参数，所述推荐的第三网络参数对应于所述第一分析请求网元要求的所述第一网络参数，所述推荐的第三网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为所述第二分析请求网元期望的网络指标。
  12. 如权利要求11所述的方法，其特征在于，所述方法还包括：
    所述第一分析请求网元接收来自于所述数据分析网元的第一消息，所述第一消息用于将期望的网络指标修改为所述第三网络指标；
    所述第一分析请求网元根据所述第一消息确定是否将所述第一分析请求网元期望的网络指标修改为所述第三网络指标。
  13. 如权利要求11所述的方法，其特征在于，所述方法还包括：
    所述第一分析请求网元接收来自于所述数据分析网元的第二消息，所述第二消息用于所述第一分析请求网元将要求的网络参数修改为所述第三网络参数。
  14. 如权利要求11所述的方法，其特征在于，所述第一网络参数对应于所述第三网络参数和第四网络参数，所述方法还包括：
    所述第一分析请求网元接收来自于所述数据分析网元的推荐的第三网络参数和推荐的所述第四网络参数，推荐的第三网络参数和推荐的所述第四网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期 望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为第二分析请求网元期望的网络指标。
  15. 如权利要求13或14所述的方法，其特征在于，对应于所述推荐的第三网络参数和推荐的第四网络参数的预测的网络指标在所述第三网络指标的范围内，所述推荐的第四网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第四网络参数对应于所述第二网络参数。
  16. 如权利要求10-15中任一所述的方法，其特征在于，所述方法还包括：
    所述第一分析请求网元接收来自于所述数据分析网元的推荐的第三网络参数；
    所述第一分析请求网元向所述数据分析网元发送第四消息，所述第四消息用于指示不接受所述推荐的所述第三网络参数；
    所述第一分析请求网元接收来自于所述数据分析网元的推荐的第五网络参数，所述推荐的第五网络参数对应于所述第一网络参数，所述推荐的第五网络参数根据第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为所述第二分析请求网元期望的网络指标。
  17. 一种通信方法，其特征在于，包括：
    第二分析请求网元确定第二请求消息，所述第二请求消息用于请求推荐的第二网络参数，所述第二请求消息包括所述第二分析请求网元要求的所述第二网络参数和第二网络指标，所述第二网络指标为所述第二分析请求网元期望的网络指标；
    所述第二分析请求网元向数据分析网元发送所述第二请求消息。
  18. 如权利要求17所述的方法，其特征在于，所述方法还包括：
    所述第二分析请求网元接收来自于所述数据分析网元的推荐的第四网络参数，所述推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和所述第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据第一网络指标和所述第二网络指标确定，所述第一网络指标为所述第二分析请求网元期望的网络指标。
  19. 如权利要求18所述的方法，其特征在于，所述方法还包括：
    所述第二分析请求网元接收来自于所述数据分析网元的第一消息，所述第一消息用于将期望的网络指标修改为所述第三网络指标；
    所述第二分析请求网元根据所述第一消息确定是否将所述第二分析请求网元期望的网络指标修改为所述第三网络指标。
  20. 如权利要求17所述的方法，其特征在于，所述方法还包括：
    所述第二分析请求网元接收来自于所述数据分析网元的第三消息，所述第三消息用于取消根据所述第二分析请求网元要求的所述第二网络参数获得推荐的网络参数。
  21. 如权利要求17-20中任一所述的方法，其特征在于，所述方法还包括：
    所述第二分析请求网元接收来自于所述数据分析网元的推荐的第四网络参数，所述推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和所述第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第二网络指标和第 一网络指标确定，所述第一网络指标为所述第一分析请求网元期望的网络指标；
    所述第二分析请求网元接收来自于所述数据分析网元的推荐的第六网络参数，所述推荐的第六网络参数对应于所述第二网络参数，所述推荐的第六网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和所述第二分析请求网元要求的所述第二网络参数确定。
  22. 一种通信装置，其特征在于，包括：
    收发单元，用于接收第一请求消息和第二请求消息，所述第一请求消息来自于第一分析请求网元，所述第一请求消息用于请求推荐的第一网络参数，所述第一请求消息包括所述第一分析请求网元要求的所述第一网络参数和第一网络指标，所述第一网络指标为所述第一分析请求网元期望的网络指标，所述第二请求消息来自于第二分析请求网元，所述第二请求消息用于请求推荐的第二网络参数，所述第二请求消息包括所述第二分析请求网元要求的所述第二网络参数和第二网络指标，所述第二网络指标为所述第二分析请求网元期望的网络指标；
    处理单元，用于根据所述第一网络指标和所述第二网络指标确定第三网络指标，所述第三网络指标为所述第一分析请求网元和所述第二分析网元共同期望的网络指标；以及，根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和所述第二分析请求网元要求的所述第二网络参数，确定推荐的第三网络参数和推荐的第四网络参数；
    所述收发单元，还用于发送所述推荐的第三网络参数和所述推荐的第四网络参数。
  23. 如权利要求22所述的装置，其特征在于，对应于所述推荐的第三网络参数和所述推荐的第四网络参数的预测的网络指标在所述第三网络指标的范围内。
  24. 如权利要求22或23所述的装置，其特征在于，所述收发单元还用于：
    向所述第一分析请求网元和/或第二分析请求网元发送第一消息，所述第一消息用于将期望的网络指标修改为第三网络指标。
  25. 如权利要求22-24中任一所述的装置，其特征在于，所述第一网络参数对应于所述第三网络参数和所述第四网络参数，所述第二网络参数对应于所述第四网络参数；
    所述收发单元具体用于：
    向所述第一分析请求网元发送所述推荐的所述第三网络参数；
    向所述第二分析请求网元发送所述推荐的所述第四网络参数。
  26. 如权利要求25所述的装置，其特征在于，所述收发单元还用于：
    向所述第一分析请求网元发送第二消息，所述第二消息用于所述第一分析请求网元将要求的网络参数修改为所述第三网络参数。
  27. 如权利要求22-24中任一所述的装置，其特征在于，所述第一网络参数对应于所述第三网络参数和所述第四网络参数，所述第二网络参数对应于所述第三网络参数和/或所述第四网络参数；
    所述收发单元具体用于：
    向所述第一分析请求网元发送所述推荐的所述第三网络参数和所述推荐的所述第四网络参数。
  28. 如权利要求27所述的装置，其特征在于，所述收发单元还用于：
    向所述第二分析请求网元发送第三消息，所述第三消息用于取消根据所述第二分析请求网元要求的所述第二网络参数获得推荐的网络参数。
  29. 如权利要求22-26中任一所述的装置，其特征在于，所述收发单元具体用于：
    向所述第一分析请求网元发送所述推荐的所述第三网络参数；
    向所述第二分析请求网元发送所述推荐的所述第四网络参数；
    所述推荐的第三网络参数对应于所述第一网络参数，所述推荐的第四网络参数对应于所述第二网络参数。
  30. 如权利要求29所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述第一分析请求网元发送的第四消息，所述第四消息用于指示不接受所述推荐的所述第三网络参数；
    所述处理单元还用于：
    根据所述第四消息，根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和所述第二分析请求网元要求的所述第二网络参数，确定推荐的第五网络参数和推荐的第六网络参数，所述推荐的第五网络参数对应于所述第一网络参数，所述推荐的第六网络参数对应于所述第二网络参数，所述推荐的所述第五网络参数的数值与所述推荐的所述第三网络参数的数值不同；
    所述收发单元还用于：
    向所述第一分析请求网元发送所述推荐的所述第五网络参数；
    向所述第二分析请求网元发送所述推荐的所述第六网络参数。
  31. 一种通信装置，其特征在于，包括：
    处理单元，用于确定第一请求消息，所述第一请求消息用于请求推荐的第一网络参数，所述第一请求消息包括第一分析请求网元要求的所述第一网络参数和第一网络指标，所述第一网络指标为所述第一分析请求网元期望的网络指标；
    收发单元，用于向数据分析网元发送所述第一请求消息。
  32. 如权利要求31所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的推荐的第三网络参数，所述推荐的第三网络参数对应于所述第一分析请求网元要求的所述第一网络参数，所述推荐的第三网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为所述第二分析请求网元期望的网络指标。
  33. 如权利要求32所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的第一消息，所述第一消息用于将期望的网络指标修改为所述第三网络指标；
    所述收发处理还用于：
    根据所述第一消息确定是否将所述第一分析请求网元期望的网络指标修改为所述第三网络指标。
  34. 如权利要求32所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的第二消息，所述第二消息用于所述第一分析请求网元将要求的网络参数修改为所述第三网络参数。
  35. 如权利要求32所述的装置，其特征在于，所述第一网络参数对应于所述第三网络参数和第四网络参数，所述收发单元还用于：
    接收来自于所述数据分析网元的推荐的第三网络参数和推荐的所述第四网络参数，推荐的第三网络参数和推荐的所述第四网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为第二分析请求网元期望的网络指标。
  36. 如权利要求34或35所述的装置，其特征在于，对应于所述推荐的第三网络参数和推荐的第四网络参数的预测的网络指标在所述第三网络指标的范围内，所述推荐的第四网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第四网络参数对应于所述第二网络参数。
  37. 如权利要求31-36中任一所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的推荐的第三网络参数；
    向所述数据分析网元发送第四消息，所述第四消息用于指示不接受所述推荐的所述第三网络参数；
    接收来自于所述数据分析网元的推荐的第五网络参数，所述推荐的第五网络参数对应于所述第一网络参数，所述推荐的第五网络参数根据第三网络指标、所述第一分析请求网元要求的所述第一网络参数和第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第一网络指标和第二网络指标确定，所述第二网络指标为所述第二分析请求网元期望的网络指标。
  38. 一种通信装置，其特征在于，包括：
    处理单元，用于确定第二请求消息，所述第二请求消息用于请求推荐的第二网络参数，所述第二请求消息包括第二分析请求网元要求的所述第二网络参数和第二网络指标，所述第二网络指标为所述第二分析请求网元期望的网络指标；
    收发单元，用于向数据分析网元发送所述第二请求消息。
  39. 如权利要求38所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的推荐的第四网络参数，所述推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和所述第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据第一网络指标和所述第二网络指标确定，所述第一网络指标为所述第二分析请求网元期望的网络指标。
  40. 如权利要求39所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的第一消息，所述第一消息用于将期望的网络指标修改为所述第三网络指标；
    所述处理单元还用于：
    根据所述第一消息确定是否将所述第二分析请求网元期望的网络指标修改为所述第三网络指标。
  41. 如权利要求38所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的第三消息，所述第三消息用于取消根据所述第二分析请求网元要求的所述第二网络参数获得推荐的网络参数。
  42. 如权利要求38-41中任一所述的装置，其特征在于，所述收发单元还用于：
    接收来自于所述数据分析网元的推荐的第四网络参数，所述推荐的第四网络参数根据第三网络指标、第一分析请求网元要求的第一网络参数和所述第二分析请求网元要求的第二网络参数确定，所述第三网络指标为所述第一分析请求网元和所述第二分析请求网元共同期望的网络指标，所述第三网络指标根据所述第二网络指标和第一网络指标确定，所述第一网络指标为所述第一分析请求网元期望的网络指标；
    接收来自于所述数据分析网元的推荐的第六网络参数，所述推荐的第六网络参数对应于所述第二网络参数，所述推荐的第六网络参数根据所述第三网络指标、所述第一分析请求网元要求的所述第一网络参数和所述第二分析请求网元要求的所述第二网络参数确定。
  43. 一种通信装置，其特征在于，包括处理器，所述处理器执行存储器存储的所述计算机指令，以使所述装置执行上述权利要求1至21中任一项所述方法。
  44. 如权利要求43所述的通信装置，其特征在于，还包括接口电路和/或所述存储器。
  45. 一种通信系统，其特征在于，包括：
    数据分析网元，用于执行如权利要求1至9中任一项所述方法；以及
    第一分析请求网元，用于执行如权利要求10至16中任一项所述方法；以及
    第二分析请求网元，用于执行如权利要求17至21中任一项所述方法。
  46. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机程序或指令，当所述计算机程序或指令被通信装置执行时，实现如权利要求1至21中任一项所述的方法。
  47. 一种计算机程序产品，其特征在于，所述计算机程序产品中存储有计算机可读指令，当所述计算机可读指令运行时，如权利要求1至9中任一项所述的方法被执行，或如权利要求10至16中任一项所述的方法被执行，或如权利要求17至21中任一项所述的方法被执行。
  48. 一种芯片，其特征在于，所述芯片包括至少一个处理器，所述处理器被用以执行如权利要求1至9中任一项所述的方法，或被用以执行如权利要求10至16中任一项所述的方法，或被用以执行如权利要求17至21中任一项所述的方法。
PCT/CN2022/121651 2021-11-10 2022-09-27 一种通信方法及装置 WO2023082878A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111325483.9 2021-11-10
CN202111325483.9A CN116112946A (zh) 2021-11-10 2021-11-10 一种通信方法及装置

Publications (1)

Publication Number Publication Date
WO2023082878A1 true WO2023082878A1 (zh) 2023-05-19

Family

ID=86262472

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/121651 WO2023082878A1 (zh) 2021-11-10 2022-09-27 一种通信方法及装置

Country Status (2)

Country Link
CN (1) CN116112946A (zh)
WO (1) WO2023082878A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117572838A (zh) * 2024-01-17 2024-02-20 青岛创新奇智科技集团股份有限公司 一种基于工业大模型的自动调整生产线速度的方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116599862B (zh) * 2023-07-18 2023-09-29 中国电信股份有限公司 通信方法、分析网元和通信系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110519795A (zh) * 2018-05-21 2019-11-29 华为技术有限公司 一种确定背景流量传输策略的方法及装置
CN110972200A (zh) * 2018-09-30 2020-04-07 华为技术有限公司 通信方法和相关设备
CN112188533A (zh) * 2019-07-03 2021-01-05 华为技术有限公司 一种网络性能的上报方法及装置
US20210160147A1 (en) * 2018-08-06 2021-05-27 Apple Inc. Management data analytical kpis for 5g network traffic and resource
CN113596863A (zh) * 2020-04-30 2021-11-02 大唐移动通信设备有限公司 确定用户面功能及信息提供的方法、设备及介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110519795A (zh) * 2018-05-21 2019-11-29 华为技术有限公司 一种确定背景流量传输策略的方法及装置
US20210160147A1 (en) * 2018-08-06 2021-05-27 Apple Inc. Management data analytical kpis for 5g network traffic and resource
CN110972200A (zh) * 2018-09-30 2020-04-07 华为技术有限公司 通信方法和相关设备
CN112188533A (zh) * 2019-07-03 2021-01-05 华为技术有限公司 一种网络性能的上报方法及装置
CN113596863A (zh) * 2020-04-30 2021-11-02 大唐移动通信设备有限公司 确定用户面功能及信息提供的方法、设备及介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117572838A (zh) * 2024-01-17 2024-02-20 青岛创新奇智科技集团股份有限公司 一种基于工业大模型的自动调整生产线速度的方法
CN117572838B (zh) * 2024-01-17 2024-04-05 青岛创新奇智科技集团股份有限公司 一种基于工业大模型的自动调整生产线速度的方法

Also Published As

Publication number Publication date
CN116112946A (zh) 2023-05-12

Similar Documents

Publication Publication Date Title
US11647422B2 (en) Adaptable radio access network
US11588710B2 (en) Intelligent prioritized mobility of low-latency applications
US10827501B2 (en) Techniques for providing proximity services (ProSe) priority-related information to a base station in a wireless network
US10785674B2 (en) Allocation of data radio bearers for quality of service flows
US20230090022A1 (en) Method and device for selecting service in wireless communication system
WO2023082878A1 (zh) 一种通信方法及装置
WO2020143564A1 (zh) 一种通信方法和通信装置
US20220103990A1 (en) Communication Method, Apparatus, and System
US11212857B2 (en) Predictive bearer assignment for wireless networks
WO2022171051A1 (zh) 一种通信方法和通信装置
US20230164591A1 (en) Communication method and apparatus
KR20210054923A (ko) 이동통신 네트워크에서 rfsp 인덱스 선택을 위한 네트워크 분석 정보 제공하는 방법 및 장치
WO2023082877A1 (zh) 一种通信方法及装置
WO2023213177A1 (zh) 一种通信方法及装置
KR102172322B1 (ko) 이동통신 단말 및 이동통신 시스템
WO2016000165A1 (zh) 无线资源的指示方法和设备
EP4354999A1 (en) Communication method, apparatus, and system
WO2023185062A1 (zh) 一种备份方法、通信装置及通信系统
WO2023071320A1 (zh) 一种保障语音业务的方法及通信装置
WO2024032603A1 (zh) 一种通信方法及装置
WO2023078183A1 (zh) 一种数据收集方法及通信装置
WO2023061207A1 (zh) 一种通信方法、通信装置及通信系统
WO2023005440A1 (zh) 通信方法、通信装置及通信系统
WO2021081915A1 (zh) 通信方法、装置及系统
CN115915196A (zh) 一种链路状态检测方法、通信装置及通信系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22891680

Country of ref document: EP

Kind code of ref document: A1