Communication method and device

Abstract

Disclosed are a communication method and device, the method being applied to a first network element, the method comprising: receiving a first request from a second network element, the first request comprising an analysis identifier, the first request being used for requesting the first network element to provide an analysis service corresponding to the analysis identifier; the first information is sent to a third network element, the third network element is determined by the first network element based on the second information, the first information is used for requesting the third network element to execute the analysis service, and the second information comprises one or more of position information, capability information or load information of the third network element. In the application, the first network element selects the network element capable of executing the analysis service according to one or more of the position, the capability or the load of the network element, so that the selected third network element can better execute the analysis service, the analysis success rate is improved, and the analysis efficiency is also improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0002] With the development of communication technology, the 3rd generation partnership project (3GPP) introduced the network data analytics function (NWDAF) network element. A network function (NF) network element or an application function (AF) network element can request the NWDAF network element to perform an analysis service to obtain analysis results. Among them, the NF network element or the AF network element can determine the corresponding NWDAF network element based on the analytics identity (analytics ID) corresponding to the analysis service, and the NWDAF network element is used to perform the analysis service. The NWDAF network element can collect data from the NF network element or the AF network element; after performing the analysis service based on the collected data, the NWDAF network element can feed back the analysis results to the NF network element or the AF network element for subsequent processing.

[0003] However, the NWDAF network element determined based on the analysis identifier may not be able to perform the analysis service. For example, the NWDAF network element may be heavily loaded or have insufficient capacity, resulting in low analysis efficiency and even analysis failure. Summary of the invention

[0004] The embodiments of the present application provide a communication method and device for improving analysis efficiency.

[0005] In a first aspect, an embodiment of the present application provides a communication method, which can be applied to a first network element or a chip in the first network element. Taking the application of the method to the first network element as an example, the method includes: receiving a first request from a second network element, the first request includes an analysis identifier, and the first request is used to request the first network element to provide an analysis service corresponding to the analysis identifier; sending first information to a third network element, the third network element is determined by the first network element based on second information, the first information is used to request the third network element to perform the analysis service, and the second information includes one or more of location information, capability information or load information of the third network element.

[0006] In the implementation of the present application, after receiving the first request from the second network element, the first network element can select a network element for executing the analysis service according to the second information, for example, a third network element is selected. The second information may include one or more of the location information, capability information or load information of the third network element, which is equivalent to the first network element selecting a network element capable of executing the analysis service according to one or more of the location, capability or load of the network element, so that the selected third network element can perform the analysis service better, thereby improving the success rate of the analysis and the efficiency of the analysis.

[0007] In a possible implementation manner, the second information includes capability information of the third network element, wherein the capability information indicates that the third network element has the capability to perform the analysis service.

[0008] In this embodiment, when the first network element selects a third network element to perform an analysis service, it can select the third network element that has the ability to perform the analysis service based on the capability information of the third network element. For example, if the model used to perform the analysis service is model 1, and the third network element can train and deploy model 1, then the third network element has the ability to perform the analysis service. The first network element can select the third network element to perform the analysis service, thereby improving the success rate of the analysis.

[0009] In one possible implementation, the second information includes load information of the third network element, wherein the load information indicates that the load of the third network element is less than or equal to a first threshold, or the load information indicates that the load of the third network element is less than the load of at least one network element, and the at least one network element is an optional network element that supports executing the analysis service.

[0010] In this embodiment, when selecting a third network element to perform an analysis service, the first network element can select a third network element that supports the execution of the analysis service based on the load information of the third network element. For example, the first network element can select a network element (e.g., a third network element) whose load is less than or equal to the first threshold to execute the analysis service, wherein the ratio of the computing power resources used by a network element to the total computing power resources of the network element is the load of the network element, and the first threshold can be a default value, a value set by the first network element, or a value preconfigured in the first network element. The first threshold can be related to the analysis service, for example, different analysis services correspond to their own thresholds, and the thresholds corresponding to different analysis services can be the same or different; or, the first threshold can also be unrelated to the analysis service, for example, the thresholds corresponding to different analysis services are all the first threshold. The load of a network element is less than the first threshold, indicating that the computing power resources of the network element can support the execution of the analysis service, so this selection method is conducive to selecting a suitable network element. For example, if the first threshold is 60%, and the load of network element 1 is 50%, the first network element can select network element 1 to execute the analysis service. Optionally, if there are multiple optional network elements with a load less than the first threshold, the first network element may randomly select one from them to execute the analysis service, or the first network element may select the network element with the smallest load to execute the analysis service. Alternatively, no threshold may be set, and the first network element may select the network element with the smallest load from at least one optional network element to execute the analysis service. For example, the load of network element 1 is 50%, the load of network element 2 is 60%, and the load of network element 3 is 70%, then the first network element may select network element 1 to execute the analysis service. When the load of a network element is small, the efficiency of the network element in executing the analysis service may be higher, thereby improving the execution efficiency of the analysis service.

[0011] In a possible implementation manner, the first information is used to request the third network element to execute the analysis service, including: the first information includes a first identifier, and the first identifier indicates a model used to execute the analysis service.

[0012] In this embodiment, the first network element can select a model that matches the analysis service, and implicitly request the third network element to perform the analysis service by indicating the model that matches the analysis service to the third network element. Since there is no need to request the third network element to perform the analysis service through additional signaling, signaling overhead is reduced. In addition, the third network element can use the model that matches the analysis service to perform the analysis service, thereby improving analysis efficiency.

[0013] In a possible implementation, the first information includes information of a first transmission protocol for executing the analysis service, and the first transmission protocol is used to transmit data between the third network element and the second network element.

[0014] The first transmission protocol is, for example, selected by the first network element, that is, in this embodiment, the first network element can select the transmission protocol used when transmitting data between the third network element and the second network element. Compared with the scheme of transmitting data between the third network element and the second network element based on a fixed transmission protocol (such as the transmission control protocol (TCP)), when a fixed transmission protocol is adopted, due to the characteristics of the transmission protocol, there may be a large transmission delay when transmitting certain business-related data. For example, when transmitting machine learning-related data between the third network element and the second network element based on TCP, since the amount of machine learning-related data may be large, it is easy to cause network congestion. TCP will adjust the transmission rate according to the degree of network congestion. When the network congestion is more serious, the transmission rate may be lower, resulting in a larger transmission delay. The embodiments of the present application are more flexible and do not require a fixed transmission protocol. Instead, the first network element can select the transmission protocol. For example, when the first network element selects the transmission protocol used to transmit data between the third network element and the second network element, it can select a transmission protocol with a smaller transmission delay when transmitting the data to be transmitted between the third network element and the second network element (that is, a transmission protocol that does not reduce network congestion by adjusting the transmission rate), thereby improving data transmission efficiency.

[0015] In a possible implementation manner, the first transmission protocol is determined from transmission protocols supported by the third network element and the second network element based on the type of data to be transmitted between the third network element and the second network element.

[0016] In this implementation, due to the characteristics of the transmission protocol, there may be a large transmission delay when transmitting certain business-related data. The first network element can flexibly select the transmission protocol (e.g., the first transmission protocol) used to transmit data between the third network element and the second network element based on the type of data transmitted between the third network element and the second network element (e.g., artificial intelligence-related data, machine learning-related data, federated learning-related data, etc.). For example, when transmitting machine learning-related data (such as the analysis results obtained by the third network element performing the analysis service) between the third network element and the second network element, since the fast user datagram protocol (UDP) network connection (quick UDP internet connections, QUIC) transmits the analysis results, the network congestion will not be reduced by adjusting the transmission rate. Therefore, the transmission delay corresponding to the QUIC transmission analysis results is smaller than the transmission delay corresponding to the TCP transmission analysis results. Therefore, the first network element can select the QUIC transmission analysis results between the third network element and the second network element, thereby improving the data transmission efficiency.

[0017] In one possible implementation, the third network element includes multiple network elements; the first information includes information on at least two transmission protocols for executing the analysis service, one of the at least two transmission protocols is used to transmit data between any two network elements among the multiple network elements, and the other network elements belong to the multiple network elements.

[0018] At least one transmission protocol is selected by the first network element, for example, that is, in this embodiment, the first network element can select the transmission protocol used when transmitting data between any two network elements included in the third network element. Compared with the scheme of transmitting data based on a fixed transmission protocol (such as TCP) between any two network elements included in the third network element, due to the characteristics of the transmission protocol, there may be a large transmission delay when transmitting certain business-related data. For example, when data related to federated learning is transmitted based on TCP between any two network elements included in the third network element, since the amount of data related to federated learning may be large, it is easy to cause network congestion. TCP will adjust the transmission rate according to the degree of network congestion. When the network congestion is more serious, the transmission rate may be lower, resulting in a larger transmission delay. The embodiments of the present application are more flexible and do not require a fixed transmission protocol. Instead, the first network element can select the transmission protocol. For example, when the first network element selects the transmission protocol to be used for transmitting data between any two network elements included in the third network element, it can select a transmission protocol with a smaller transmission delay corresponding to the data to be transmitted between any two network elements included in the third network element (that is, a transmission protocol that will not reduce network congestion by adjusting the transmission rate), thereby improving data transmission efficiency.

[0019] In a possible implementation manner, the one transmission protocol is determined from transmission protocols supported by the any two network elements based on the type of data to be transmitted between the any two network elements.

[0020] In this implementation, due to the characteristics of the transmission protocol, there may be a large transmission delay when transmitting certain business-related data. The first network element can flexibly select a transmission protocol for transmitting data between any two network elements included in the third network element based on the type of data transmitted between any two network elements included in the third network element (for example, artificial intelligence-related data, machine learning-related data, federated learning-related data, etc.). For example, the third network element includes network element 1, network element 2, and network element 3. When transmitting federated learning-related data (such as data 1 generated by network element 1 and network element 2 in the process of training the model) between network element 1 and network element 2, due to the loss tolerant transmission protocol (loss tolerant transmission protocol), the transmission delay may be large. When QUIC transmits data 1, it will not reduce network congestion by adjusting the transmission rate. Therefore, the transmission delay corresponding to LTP transmitting data 1 is smaller than the transmission delay corresponding to TCP transmitting data 1, and partial data loss is allowed during the process of data 1. Therefore, the first network element can choose to transmit data 1 between network element 1 and network element 2 based on LTP, or, when transmitting federated learning related data (such as data 2 of the model trained by network element 1 and network element 2) between network element 2 and network element 3, since QUIC does not reduce network congestion by adjusting the transmission rate when transmitting data 2, the transmission delay corresponding to QUIC transmitting data 2 is smaller than the transmission delay corresponding to TCP transmitting data 2, and partial data loss is not allowed during the process of transmitting data 2. Therefore, the first network element can choose to transmit data 2 between network element 2 and network element 3 based on QUIC, thereby improving data transmission efficiency.

[0021] In a possible implementation, the first information is also used to indicate one or more of the following: training the model indicated by the first identifier; deploying the model trained by the third network element, and executing the analysis service based on the model trained by the third network element; or storing the model trained by the third network element.

[0022] In this embodiment, when the first network element selects a third network element to perform an analysis service, it can also determine relevant information of the third network element when executing the analysis service (for example, how to train a model used to execute the analysis service before executing the analysis service). This information matches the analysis service and the third network element, so that the third network element can execute the analysis service in combination with the information, thereby improving the efficiency of executing the analysis service.

[0023] In a possible implementation, the method further includes: receiving the second information from the network storage function network element. In this implementation, the first network element can obtain the second information by interacting with the network storage function network element without pre-storing the second information, thereby saving storage space of the first network element.

[0024] In a possible implementation manner, the second network element includes an application function network element and / or a network open function network element, and may also include other network elements in addition to this, which is not limited.

[0025] In a possible implementation, the third network element includes one or more of a network data analysis function network element, a data collection and coordination function network element, or an analysis and data storage function network element, and may also include other network elements in addition to these, without limitation. Optionally, if the third network element includes multiple network elements, the multiple network elements may be network elements of the same type, such as all being network data analysis function network elements; or, the multiple network elements may also include network elements of different types, such as network data analysis function network elements and data collection and coordination function network elements, without limitation.

[0026] In a second aspect, an embodiment of the present application provides a communication device, including a processor and a memory; the memory is used to store computer instructions, and when the device is running, the processor executes the computer instructions stored in the memory, so that the device executes any implementation method in the above-mentioned first aspect. The memory can be a volatile or non-volatile memory, such as a cache in a semiconductor chip.

[0027] In a third aspect, an embodiment of the present application provides a communication device, which may be a first network element, or a chip for the first network element. The device has the function of implementing any implementation method in the first aspect above. The function may be implemented by hardware, or by hardware executing corresponding software implementation. The hardware or software includes one or more modules corresponding to the above functions.

[0028] In a fourth aspect, an embodiment of the present application provides a communication device, comprising a unit or means for executing each step of any implementation method in the above-mentioned first aspect.

[0029] In a fifth aspect, an embodiment of the present application provides a communication device, including a processor and an interface circuit, wherein the processor is used to communicate with other devices through the interface circuit and execute any implementation method in the first aspect. The processor may be one or more processors.

[0030] In a sixth aspect, an embodiment of the present application provides a communication device, comprising a processor coupled to a memory, the processor being used to call a program stored in the memory to execute any implementation method in the first aspect above. The memory may be located inside the device or outside the device. The processor may also be one or more processors.

[0031] In a seventh aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, which, when executed on a communication device, enables any implementation method in the above-mentioned first aspect to be executed.

[0032] In an eighth aspect, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a communication device, any implementation method in the above-mentioned first aspect is executed.

[0033] In a ninth aspect, an embodiment of the present application further provides a chip system, comprising: a processor, configured to execute any implementation method in the above-mentioned first aspect.

[0034] In the tenth aspect, an embodiment of the present application further provides a communication system, the system comprising: a first network element, used to execute any implementation method executed by the first network element in the above-mentioned first aspect.

[0035] In a possible implementation, the system further includes: a second network element, used to execute any implementation method executed by the second network element in the above-mentioned first aspect; and a third network element, used to execute any implementation method executed by the third network element in the above-mentioned first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a schematic diagram of a possible communication system;

[0037] Figure 2 A schematic diagram of a NWDAF network element collecting data;

[0038] Figure 3 A schematic diagram of NWDAF network element model training and data analysis;

[0039] Figure 4 is a schematic diagram of another possible communication system;

[0040] Figure 5 is a flow chart of a communication method;

[0041] Figure 6 is a flow chart of another communication method;

[0042] Figure 7 is a flow chart of yet another communication method;

[0043] Figure 8 is a flow chart of yet another communication method;

[0044] Fig. 9 is a schematic diagram of network element interaction;

[0045] Fig.10is a schematic diagram of a communication device 1000;

[0046] Fig.11 is a schematic diagram of another communication device 1100 . DETAILED DESCRIPTION

[0047] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0048] The technical solution of the embodiment of the present application can be applied to various communication systems, such as: long term evolution (LTE) system, evolved LTE (LTE-advanced, LTE-A) system, universal mobile telecommunications system (UMTS), and fifth generation (5G) mobile communication system, beyond 5G (B5G) mobile communication system, or sixth generation (6G) and other communication systems evolved after 5G, etc. The communication system can also be a device-to-device (D2D) network, a wireless fidelity (WiFi) network, a machine-to-machine (M2M) network, an Internet of Things (IoT) network or other networks.

[0049] See also Figure 1 , a schematic diagram of a possible communication system. Figure 1 The communication system shown is a communication system based on a service-based architecture (SBA), which may include three parts, namely a user equipment (UE) part, a data network (DN) and an operator network part.

[0050] Among them, the operator network may include one or more of the following network elements: authentication server function (AUSF) network element, network exposure function (NEF) network element, policy control function (PCF) network element, unified data management (UDM) network element, unified data repository (UDR), network storage function (NRF) network element, AF network element, access and mobility management function (AMF) network element, policy control function (PCF), (radio) access network ((R)AN), user plane function (UPF) network element, NWDAF network element, data collection coordination function (DCCF) network element or analysis data storage function (ADRF) network element, etc.

[0051] The above-mentioned operator network includes a radio access network and a core network. The UE accesses the core network through the (R)AN, and the core network includes user plane network elements and control plane network elements. Among them, the user plane network elements of the core network include UPF network elements; the control plane network elements of the core network include at least one of AUSF, AMF, SMF, NSSF, NEF, NRF, UDM, PCF, AF, NWDAF, DCCF or ADRF network elements.

[0052] User plane network elements (such as UPF network elements) are mainly responsible for packet forwarding, quality of service (QoS) control, billing information statistics, etc. Control plane network elements are mainly responsible for business process interaction, sending packet forwarding strategies and QoS control strategies to the user plane.

[0053] The core network control plane can adopt a service-oriented architecture, that is, the interaction between control plane network elements adopts the service call method to replace the point-to-point communication method in the traditional architecture. In the service-oriented architecture, a control plane network element will open services to other control plane network elements for other control plane network elements to call; in point-to-point communication, there will be a set of specific messages on the communication interface between control plane network elements, which can only be used by the control plane network elements at both ends of the interface when communicating.

[0054] The functions of network elements in the core network are described as follows:

[0055] UPF supports all or part of the following functions: interconnecting protocol data unit (PDU) sessions with data networks, packet routing and forwarding (for example, supporting uplink classifier for forwarding traffic to the data network, supporting branching points to support multi-homed PDU sessions), or packet inspection.

[0056] AMF, UE access management and mobility management. Responsible for UE status maintenance, UE reachability management, non-mobility management (MM) non-access-stratum (NAS) message forwarding, session management (SM) N2 message forwarding.

[0057] SMF, UE session management, allocates resources for UE sessions and releases resources. The resources include session quality of service (QoS), session path, forwarding rules, etc. SMF is responsible for selecting or reselecting UPF, allocating Internet protocol (IP) addresses, and establishing, modifying, and releasing bearers.

[0058] NEF opens network functions to third parties in the form of northbound application programming interface (API).

[0059] NRF provides storage and selection functions for network function entity information for other network elements.

[0060] UDM, User Subscription Context Management, is responsible for managing the UE's subscription data and notifying the corresponding network element when the subscription data is modified.

[0061] UDR, a unified data repository function, is responsible for storing and retrieving contract data, policy data, and public architecture data, etc., which can be used by network elements such as UDM, PCF, or NEF to obtain relevant data. UDR can have different data access authentication mechanisms for different types of data (such as contract data, policy data, etc.) to ensure the security of data access. UDR should be able to return a failure response with an appropriate reason value for illegal service operations or data access requests.

[0062] PCF, user policy management, is used to generate and manage user, session, and QoS flow processing policies.

[0063] AF, application management, provides some application layer services to UE. When providing services to UE, AF has requirements for QoS (policy) and charging strategy, and needs to notify the network. In addition, AF also needs the core network to feedback application-related information.

[0064] NWDAF, an artificial intelligence (AI) data-related network element, collects data from NF (such as SMF, UPF, AMF, etc.), AF and the operator's network operation, administration, and maintenance (OAM) system, then analyzes the collected data and feeds back the analysis results to NF and AF for subsequent processing.

[0065] DCCF, as the network element for AI data collection coordination, data consumers (such as NWDAF) can send data requests to DCCF instead of directly sending data requests to NF. When performing data collection operations, DCCF will first go to ADRF or NWDAF to check whether historical data can be used. If not, it will arrange to subscribe to the collected data from NF.

[0066] ADRF, as a network element for AI data storage, provides an interface to NWDAF for storing collected data and analysis results, and can also interact with DCCF to store collected data.

[0067] The relevant interfaces between network element functions involved in the embodiments of the present application include:

[0068] N1: Interface between UE and core network control plane.

[0069] N2: Communication interface between (R)AN and core network control plane.

[0070] N3: Communication interface between (R)AN and UPF, used to transmit user plane data.

[0071] N4: Communication interface between SMF and UPF, used by SMF to configure policies for UPF, etc.

[0072] N6: Communication port between UPF and DN.

[0073] Above Figure 1 The NWDAF network element shown can implement data collection, model training and data analysis functions based on the service based inferface (SBI). Figure 2 , which is a schematic diagram of data collection by an NWDAF network element. The NWDAF network element collects data directly from the NF network element based on the service-oriented interface Nnf, or the NWDAF network element collects data from the NF through the DCCF based on the service-oriented interface Ndccf, or the NWDAF network element collects data from the NF through the messaging framework of the messaging framework adaptor function (MFAF) based on the service-oriented interface Nmfaf.

[0074] For example, see Figure 3 , is a schematic diagram of NWDAF network element model training and data analysis, Figure 3 The scenario shown is a federated learning (FL) scenario, where NWDAF network elements with server functions (i.e., server-NWDAF network elements) and NWDAF network elements with client functions (i.e., client-NWDAF network elements) are used to implement model training and data analysis. The specific steps are as follows:

[0075] Step 1: The AF network element sends a discovery request 1 to the NRF network element. The discovery request 1 is a Nnrf_NFDiscovery_Request message. The discovery request 2 includes an analysis identifier. The discovery request 1 is used to request the NRF network element to discover the server-NWDAF network element corresponding to the analysis identifier.

[0076] Step 2: The NRF network element sends a discovery response 1 to the AF network element. The discovery response 1 is a Nnrf_NFDiscovery_Response message. The discovery response 1 is used to indicate the server-NWDAF network element corresponding to the analysis identifier.

[0077] Step 3: The AF network element sends a service request to the server-NWDAF network element. The service request includes an analysis identifier. The service request is used to request the server-NWDAF network element to provide an analysis service corresponding to the analysis identifier.

[0078] Step 4: The server-NWDAF network element sends a discovery request 2 to the NRF network element. The discovery request 2 is a Nnrf_NFDiscovery_Request message. The discovery request 2 includes an analysis identifier. The discovery request 2 is used to request the NRF network element to discover the client-NWDAF network element corresponding to the analysis identifier.

[0079] Step 5: The NRF network element sends a discovery response 2 to the server-NWDAF network element. The discovery response 2 is a Nnrf_NFDiscovery_Response message. The discovery response 2 is used to indicate the client-NWDAF network element corresponding to the analysis identifier.

[0080] Step 6: The server-NWDAF network element sends a confirmation request to the client-NWDAF network element. The preparation request is used to request the client-NWDAF network element to confirm whether to perform model training.

[0081] Step 7: The client-NWDAF network element sends a confirmation response to the server-NWDAF network element, where the confirmation response is used to indicate that the client-NWDAF network element confirms the model training.

[0082] Step 8: The server-NWDAF network element and the client-NWDAF network element perform model training.

[0083] Step 9: The server-NWDAF network element executes the analysis service based on the trained model to obtain the analysis results and sends the analysis results to the AF network element.

[0084] Among them, for the large amount of data generated when the server-NWDAF network element and the client-NWDAF network element perform analysis services, the transmission control protocol (TCP) corresponding to the service interface can be used for transmission between the server-NWDAF network element and the client-NWDAF network element. However, due to the congestion control mechanism of TCP itself, that is, adjusting the transmission rate according to the degree of network congestion, the transmission delay is relatively large. And because the server-NWDAF network element and the client-NWDAF network element are determined by the NRF network element based on the analysis identifier provided by the AF network element, the server-NWDAF network element and the client-NWDAF network element may not be able to perform the analysis service. For example, the server-NWDAF network element and the client-NWDAF network element may be heavily loaded or insufficiently capable, resulting in low analysis efficiency and even analysis failure.

[0085] See also Figure 4 , is a schematic diagram of another possible communication system. Figure 1 Compared to the system shown, Figure 4 The system shown also includes the following network elements:

[0086] The artificial intelligence service control function (AISCF) network element is responsible for the control function of the AI ​​service and can perform data orchestration on network elements related to AI data (such as NWDAF network elements, DCCF network elements, and ADRF network elements). Among them, the orchestration includes the selection of network elements, the specific operations of network elements, the selection of transmission protocols, etc. In a specific implementation, the AISCF network element can be a type of service control function (SCF) network element. The AISCF network element can be independently deployed on a physical entity, and the AISCF network element can also be integrated with other network elements on the same physical entity, which is not limited in the embodiments of the present application.

[0087] It should be understood that the names of the above network elements are only examples, and this application does not exclude the situation where the network elements are named differently in the future, or the functions of the network elements are merged. With the evolution of technology, any device or network element that can realize the functions of the above network elements is within the protection scope of this application. In addition, in practical applications, the above communication system may also include other network elements, which is not limited by this application.

[0088] The following describes the method provided by the embodiments of the present application in conjunction with the accompanying drawings. The various embodiments of this article can be applied to Figure 4 For example, the AISCF network element described in each embodiment of this document may be Figure 4 The AISCF network element in the embodiment of the present invention may be Figure 4 The NRF network element in the embodiment of the present invention may be the AF network element Figure 4 The AF network element in the embodiment of the present invention may be Figure 4 The NEF network element in the various embodiments of this document may be Figure 4 The NWDAF network element in the embodiment of the present invention may be a DCCF network element. Figure 4 The DCCF network element in the embodiment of the present invention may be Figure 4 ADRF network element in.

[0089] In the drawings corresponding to the various embodiments of the present application, all steps indicated by dotted lines are optional steps.

[0090] This application embodiment provides a communication method, see Figure 5 , which is a flow chart of the method. This method can be applied to Figure 4 communication system. Figure 5 In the illustrated embodiment, it is taken as an example that the first network element includes an AISCF network element, the second network element includes an AF network element and / or an NEF network element, and the third network element includes one or more of an NWDAF network element, a DCCF network element, or an ADRF network element.

[0091] S501. A second network element sends a first request to a first network element. Correspondingly, the first network element receives the first request from the second network element.

[0092] In an embodiment of the present application, the first request may include an analysis identifier, and the first request may be used to request the first network element to provide an analysis service corresponding to the analysis identifier.

[0093] Specifically, the analysis identifier may indicate the type of the analysis service. For example, the first request may include identifier 1. Identifier 1 may indicate analysis service 1. Analysis service 1 may be used to predict the utilization rate of the central processing unit (CPU) of the network element.

[0094] Optionally, the first request may also include parameters indicating other information of the analysis service, such as parameters indicating the specific analysis scenario corresponding to the analysis service. For example, the first request may also include parameter 1, which may indicate the FL scenario. For another example, the first request may also include parameter 2, which may indicate a long short term memory (LSTM) model. For another example, the first request may also include parameter 3, which may indicate 5 minutes, indicating the maximum analysis time corresponding to the analysis service.

[0095] S502. The first network element sends first information to the third network element. Correspondingly, the third network element receives the first information from the first network element.

[0096] In an embodiment of the present application, the first information can be used to request a third network element to perform an analysis service.

[0097] Specifically, before the first network element sends the first information to the third network element, the first network element may also determine the third network element based on the second information, wherein the second information may include but is not limited to one or more of the location information of the third network element, the capability information of the third network element, or the load information of the third network element.

[0098] The capability information of the third network element may indicate that the third network element has the capability to perform the analysis service. Alternatively, the capability information of the third network element may indicate that the third network element is capable of performing the analysis service. Alternatively, the capability information of the third network element may indicate that the capability of the third network element satisfies the execution conditions of the analysis service. For example, if the model used to perform the analysis service is an LSTM model, and the third network element is capable of training and deploying the LSTM model, then the third network element has the capability to perform the analysis service, and the first network element may select the third network element to perform the analysis service, thereby improving the success rate of the analysis.

[0099] The load information of the third network element may indicate that the load of the third network element is less than or equal to the first threshold. Among them, the ratio of the computing power resources used by a network element to the total computing power resources of the network element is the load of the network element. The first threshold may be a default value, a value set by the first network element, or a value preconfigured in the first network element, and the embodiment of the present application does not specifically limit this. The first threshold may be related to the analysis service, for example, different analysis services correspond to their own thresholds, and the thresholds corresponding to different analysis services may be the same or different; or, the first threshold may also be unrelated to the analysis service, for example, the thresholds corresponding to different analysis services are all the first threshold. The load of a network element is less than the first threshold, indicating that the computing power resources of the network element can support the execution of the analysis service, so this selection method is conducive to selecting a suitable network element. For example, if the first threshold is 60% and the load of network element 1 is 50%, the first network element can select network element 1 to execute the analysis service (that is, network element 1 is the third network element). Optionally, if there are multiple optional network elements with a load less than the first threshold, the first network element may randomly select one from them to perform the analysis service, or the first network element may also select the network element with the smallest load to perform the analysis service. For example, the first threshold is 60%, and the load of network element 1 is 50%, the load of network element 2 is 40%, and the load of network element 3 is 70%. The first network element may select network element 1 or network element 2 to perform the analysis service (that is, network element 1 or network element 2 is the third network element). Alternatively, the load information of the third network element may indicate that the load of the third network element is less than the load of at least one network element. Among them, at least one network element is an optional network element that supports the execution of the analysis service. It can be understood that without setting a threshold, the first network element may select the network element with the smallest load from at least one optional network element to perform the analysis service. For example, if the load of network element 1 is 50%, the load of network element 2 is 60%, and the load of network element 3 is 70%, the first network element may select network element 1 to perform the analysis service (that is, network element 1 is the third network element). When the load of a network element is small, the efficiency of executing the analysis service by the network element may be higher, thereby improving the execution efficiency of the analysis service.

[0100] As an example, taking the third network element as an NWDAF network element, the second information may include but is not limited to one or more of the following information: location information of the NWDAF network element; capability information of the NWDAF network element, such as functions of the NWDAF network element, such as model training logical function (MTLF) and / or analysis logical function (AnLF), server function or client function in the FL scenario, etc., and models that can be trained or deployed by the NWDAF network element, such as LSTM model or large language model (LLM), etc., and transmission protocols that can be used by the NWDAF network element, such as quick UDP internet connections (QUIC), loss tolerant transmission protocol (LTP), TCP, etc.; load information of the NWDAF network element, such as the CPU load of the NWDAF network element.

[0101] If in the above S501, the first network element determines that the analysis service is used to predict the CPU utilization of the second network element, and determines the execution conditions of the analysis service as follows: the specific analysis model corresponding to the analysis service is the LSTM model, which can be understood as the first network element determining that the network element executing the analysis service needs to be able to train and deploy the LSTM model; the specific analysis scenario corresponding to the analysis service is the FL scenario, which can be understood as the first network element determining that the network element executing the analysis service needs to have server functions and client functions; the maximum analysis time corresponding to the analysis service is 5 minutes, which can be understood as the first network element sets the load of the network element executing the analysis service to be less than or equal to threshold 1 (for example, 50%) based on the maximum analysis time of 5 minutes so that the analysis time for the network element to execute the analysis service to obtain the analysis result is less than or equal to 5 minutes.

[0102] Further, the first network element may determine three NWDAF network elements from the multiple NWDAF network elements based on one or more of the location information, capability information or load information of the multiple NWDAF network elements. For example, NWDAF network element 1, NWDAF network element 2 and NWDAF network element 3. Among them, NWDAF network element 1 may have a model training logic function and an analysis logic function, NWDAF network element 1 may train or deploy an LSTM model, NWDAF network element 1 may have a server function in an FL scenario, and the CPU load of NWDAF network element 1 may be less than 50%. NWDAF network element 1 may be deployed as an AnLF-NWDAF network element to perform a model for performing the analysis service and perform the analysis service based on the model to obtain an analysis result, and may be used as a server-NWDAF network element to jointly train a model for performing the analysis service with a client-NWDAF network element. NWDAF network element 2 may have a model training logic function, NWDAF network element 2 may train an LSTM model, NWDAF network element 2 may have a client function in an FL scenario, and the CPU load of NWDAF network element 2 may be lower than 50%. NWDAF network element 3 has the model training logic function, NWDAF network element 3 can train LSTM model, NWDAF network element 3 has client function in FL scenario, and the CPU load of NWDAF network element 3 is less than 50%. NWDAF network element 2 and NWDAF network element 3 can be used as client-NWDAF network elements and server-NWDAF network elements to jointly train the model for executing the analysis service.

[0103] Alternatively, the first network element may also determine four NWDAF network elements from multiple NWDAF network elements based on one or more of the location information, capability information or load information of the multiple NWDAF network elements. For example, NWDAF network element 4, NWDAF network element 5, NWDAF network element 6 and NWDAF network element 7. Among them, NWDAF network element 4 has an analysis logic function, NWDAF network element 4 can deploy an LSTM model, and the CPU load of NWDAF network element 4 is less than 50%. NWDAF network element 4 can be deployed as an AnLF-NWDAF network element to perform a model for the analysis service and perform the analysis service based on the model to obtain an analysis result, and can be used as a server-NWDAF network element and client-NWDAF network element to jointly train a model for performing the analysis service. NWDAF network element 5 has a model training logic function, NWDAF network element 5 can train an LSTM model, NWDAF network element 5 has a server function in the FL scenario, and the CPU load of NWDAF network element 5 is less than 50%. NWDAF network element 5 can be used as a server-NWDAF network element to jointly train with the client-NWDAF network element for executing the model for the analysis service. NWDAF network element 6 has a model training logic function, NWDAF network element 6 can train an LSTM model, NWDAF network element 6 has a client function in the FL scenario, and the CPU load of NWDAF network element 6 is less than 50%. NWDAF network element 7 has a model training logic function, NWDAF network element 7 can train an LSTM model, NWDAF network element 7 has a client function in the FL scenario, and the CPU load of NWDAF network element 7 is less than 50%. NWDAF network element 6 and NWDAF network element 7 can be used as client-NWDAF network elements to jointly train with the server-NWDAF network element for executing the model for the analysis service.

[0104] As another example, taking the third network element as a DCCF network element, the second information may include but is not limited to one or more of the following information: location information of the DCCF network element; capability information of the DCCF network element, such as data that can be collected by the DCCF network element, such as load level information, service experience information, network performance information, user data congestion information, session management congestion control experience information, redundant transmission experience information, etc., and transmission protocols that can be used by the DCCF network element, such as QUIC, LTP, TCP, etc.; load information of the DCCF network element, such as the CPU load of the DCCF network element.

[0105] If in the above S501, the first network element determines that the analysis service is used to predict the CPU utilization of the second network element, and determines the execution condition of the analysis service as follows: the longest analysis time corresponding to the analysis service is 5 minutes, it can be understood that the load of the network element executing the analysis service needs to be less than or equal to threshold 1 (for example, 50%), so that the analysis time for the network element to execute the analysis service to obtain the analysis result is less than or equal to 5 minutes. The first network element can determine a DCCF network element from multiple DCCF network elements, such as DCCF network element 1, wherein DCCF network element 1 can collect load information, and the CPU load of DCCF network element 1 is less than 50%. DCCF network element 1 can provide the required data for the above client-NWDAF network element, the above server-NWDAF network element and the above AnLF-NWDAF network element.

[0106] As another example, taking the third network element as an ADRF network element, the second information may include but is not limited to one or more of the following information: location information of the ADRF network element; capability information of the ADRF network element, such as models that can be stored by the ADRF network element, such as LSTM models or LLMs, and data that can be stored by the ADRF network element, such as load information, service experience information, network performance information, user data congestion information, conference management congestion control experience information, redundant transmission experience information, and transmission protocols that can be used by the ADRF network element, such as QUIC, LTP, TCP, etc.; load information of the ADRF network element, such as the CPU load of the ADRF network element.

[0107] If in the above S501, the first network element determines that the analysis service is used to predict the CPU utilization of the second network element, and determines the execution conditions of the analysis service as follows: the specific analysis model corresponding to the analysis service is an LSTM model, which can be understood as the network element executing the analysis service needs to be able to train and deploy the LSTM model; the longest analysis time corresponding to the analysis service is 5 minutes, which can be understood as the load of the network element executing the analysis service needs to be less than or equal to threshold 1 (for example, 50%), so that the analysis time for the network element to execute the analysis service to obtain the analysis result is less than or equal to 5 minutes. The first network element can determine an ADRF network element from multiple ADRF network elements, such as ADRF network element 1, wherein ADRF network element 1 can store LSTM models and load information, and the CPU load of ADRF network element 1 is less than 50%. ADRF network element 1 can store the models trained by the client-NWDAF network element and the server-NWDAF network element for executing the analysis service, and store the analysis results obtained by the AnLF-NWDAF network element executing the analysis service. The ADRF network element 1 can also provide the required data for the above-mentioned client-NWDAF network element, server-NWDAF network element and AnLF-NWDAF network element.

[0108] Optionally, before the first network element determines the third network element based on the second information, the first network element may further obtain the second information.

[0109] For example, see Figure 6 As shown, before executing S502, the present application may also execute:

[0110] S502a, the third network element sends request 1 to the NRF network element, and correspondingly, the NRF network element receives request 1 from the third network element. Request 1 is also called a registration request, and request 1 may be a Nnrf_NFManagement_NFRegister Request message. Request 1 may include second information.

[0111] S502b, the NRF network element sends a response 1 to the third network element, and accordingly, the third network element receives the response 1 from the NRF network element. Response 1 is also called a registration response, and response 1 may be a Nnrf_NFManagement_NFRegister Response message. Response 1 may indicate that the NRF network element successfully stores the second information.

[0112] S502c: The first network element sends request 2 to the NRF network element. Correspondingly, the NRF network element receives request 2 from the first network element. Request 2 is also called a discovery request, and request 2 may be a Nnrf_NFDiscovery_Request message. Request 2 may be used to request the NRF network element to provide second information.

[0113] S502d: The NRF network element sends a response 2 to the first network element, and accordingly, the first network element receives the response 2 from the NRF network element. The response 2 is also called a discovery response, and the response 2 may be a Nnrf_NFDiscovery_Response message. The response 2 may include the second information.

[0114] Through the above scheme, the first network element selects a third network element that can perform the analysis service based on one or more of the location, capability or load of the third network element, so that the selected third network element can better perform the analysis service, thereby improving the analysis success rate and the analysis efficiency.

[0115] Specifically, when the first network element sends the first information to the third network element, the first information may include a first identifier, wherein the first identifier indicates a model used to perform the analysis service. It can be understood that the first network element requests the third network element to perform the analysis service by sending the first identifier to the third network element. For example, if in the above S501, the first network element determines that the specific analysis model corresponding to the analysis service is an LSTM model, then the first information sent by the first network element to the third network element may include identifier 2, and identifier 2 may indicate the LSTM model.

[0116] Optionally, the first information may also include information of a first transmission protocol for performing the analysis service. The first transmission protocol may be used to transmit data between the third network element and the second network element. The first transmission protocol may be determined by the first network element from the transmission protocols supported by the third network element and the second network element based on the type of data to be transmitted between the third network element and the second network element (e.g., artificial intelligence-related data, machine learning-related data, federated learning-related data, etc.).

[0117] For example, the transmission protocols supported by the third network element and the second network element include QUIC, LTP and TCP. Machine learning related data 1 (i.e., the analysis results obtained by the third network element performing the analysis service) are transmitted between the third network element and the second network element. Since the amount of data 1 may be large, network congestion is likely to occur when data 1 is transmitted. Different transmission protocols control network congestion in different ways. Some transmission protocols (such as TCP) will control network congestion by adjusting the transmission rate, so that the transmission delay is longer when the network congestion is heavier. Some transmission protocols (such as QUIC and LTP) will not control network congestion by adjusting the transmission rate, so that the transmission delay is shorter when the network congestion is heavier, but QUIC and LTP will control network congestion in other ways, such as LTP will control network congestion by packet loss. For example, the transmission delay corresponding to QUIC when transmitting data 1 is 3 seconds, the transmission delay corresponding to LTP when transmitting data 1 is 3 seconds, and the transmission delay corresponding to TCP when transmitting data 1 is 4 seconds. It can be seen that the transmission delays corresponding to QUIC and LTP when transmitting data 1 are smaller than the transmission delay corresponding to TCP when transmitting data 1. At this time, since partial data loss is not allowed when transmitting data 1, in order to reduce the transmission delay and improve transmission reliability, the first network element can determine that data 1 is transmitted between the third network element and the second network element based on QUIC, that is, the first transmission protocol is QUIC.

[0118] Further optionally, if the third network element includes multiple network elements, the first information may also include information of at least one transmission protocol or at least two transmission protocols for performing the analysis service. Among them, at least one transmission protocol or one of the at least two transmission protocols can be used to transmit data between any two network elements in the multiple network elements. The one transmission protocol can be determined by the first network element from the transmission protocols supported by the any two network elements based on the type of data to be transmitted between the any two network elements (e.g., artificial intelligence-related data, machine learning-related data, federated learning-related data, etc.).

[0119] For example, the third network element includes the above-mentioned NWDAF network element 4, NWDAF network element 5, NWDAF network element 6, NWDAF network element 7 and ADRF network element 1, and the transmission protocols supported by NWDAF network element 4, NWDAF network element 5, NWDAF network element 6 and ADRF network element 1 include QUIC, LTP and TCP.

[0120] Data 2 related to federated learning (i.e., data generated by NWDAF network element 7 and NWDAF network element 5 in the process of training the model for performing analysis services) is transmitted between NWDAF network element 7 and NWDAF network element 5. Data 3 related to federated learning (i.e., data generated by NWDAF network element 6 and NWDAF network element 5 in the process of training the model for performing analysis services) is transmitted between NWDAF network element 6 and NWDAF network element 5. Since the amount of data 2 and data 3 may be large, it is easy to cause network congestion when transmitting data 2 and data 3. Different transmission protocols control network congestion in different ways. Some transmission protocols (such as TCP) will control network congestion by adjusting the transmission rate, so that the transmission delay is longer when the network congestion is heavier. Some transmission protocols (such as QUIC and LTP) will not control network congestion by adjusting the transmission rate, so that the transmission delay is shorter when the network congestion is heavier, but QUIC and LTP will control network congestion in other ways, such as LTP will control network congestion by packet loss. For example, the transmission delay corresponding to QUIC when transmitting data 2 and data 3 is 8 seconds, the transmission delay corresponding to LTP when transmitting data 2 and data 3 is 7 seconds, and the transmission delay corresponding to TCP when transmitting data 2 and data 3 is 15 seconds. It can be seen that the transmission delays corresponding to QUIC and LTP when transmitting data 2 and data 3 are smaller than the transmission delay corresponding to TCP when transmitting data 2 and data 3. At this time, since some data loss is allowed when transmitting data 2 and data 3, in order to reduce the transmission delay, the first network element can determine that data 2 is transmitted based on LTP between NWDAF network element 7 and NWDAF network element 5, and data 3 is transmitted based on LTP between NWDAF network element 6 and NWDAF network element 5.

[0121] Data 4 related to machine learning (i.e., data of the model trained by NWDAF network element 6 and NWDAF network element 5 for executing analysis services) is transmitted between NWDAF network element 5 and ADRF network element 1. Since the amount of data 4 may be large, it is easy to cause network congestion when transmitting data 4. Different transmission protocols control network congestion in different ways. Some transmission protocols (such as TCP) will control network congestion by adjusting the transmission rate, so that the transmission delay is longer when the network congestion is heavier. Some transmission protocols (such as QUIC and LTP) will not control network congestion by adjusting the transmission rate, so that the transmission delay is shorter when the network congestion is heavier. However, QUIC and LTP will control network congestion in other ways. For example, LTP will control network congestion by packet loss. For example, the transmission delay corresponding to QUIC when transmitting data 4 is 3 seconds, the transmission delay corresponding to LTP when transmitting data 4 is 8 seconds, and the transmission delay corresponding to TCP when transmitting data 4 is 20 seconds. It can be seen that the transmission delays corresponding to QUIC and LTP when transmitting data 4 are smaller than the transmission delay corresponding to TCP when transmitting data 4. At this time, since partial data loss is not allowed when transmitting data 4, in order to reduce the transmission delay and improve transmission reliability, the first network element can determine that data 4 is transmitted based on QUIC between NWDAF network element 5 and NWDAF network element 4, and data 4 is transmitted based on QUIC between NWDAF network element 5 and ADRF network element 1.

[0122] Optionally, the first information may also be used to indicate one or more of the following: training the model indicated by the first identifier; deploying (or also called loading, or also called running) the model trained by the third network element and performing analysis services based on the model trained by the third network element; or storing the model trained by the third network element. Deploying the model trained by the third network element means opening a specific interface to call specific data or services through the interface to perform the analysis service, and storing the model trained by the third network element means not opening a specific interface and only saving the data of the model trained by the third network element.

[0123] For example, taking the third network element including the above-mentioned NWDAF network element 4, NWDAF network element 5, NWDAF network element 6, NWDAF network element 7 and ADRF network element 1 as an example, see Figure 7 As shown, S502 may specifically include the following steps:

[0124] S502e: The first network element sends indication information 1 to the NWDAF network element 7. Correspondingly, the NWDAF network element 7 receives the indication information 1 from the first network element.

[0125] Among them, the indication information 1 can indicate that the NWDAF network element 7 serves as a client-NWDAF network element in the FL scenario to train the model 1 of the LSTM identifier 2.

[0126] The indication information 1 may also indicate that data a (ie, data generated by the NWDAF network element 7 and the NWDAF network element 5 during the training of the LSTM model 1) is transmitted between the NWDAF network element 7 and the NWDAF network element 5 based on LTP.

[0127] S502f. The first network element sends indication information 1 to the NWDAF network element 6. Correspondingly, the NWDAF network element 6 receives indication information 2 from the first network element.

[0128] Among them, the indication information 2 can indicate that the NWDAF network element 6 is the LSTM model 1 indicated by the client-NWDAF network element training identifier 2 in the FL scenario.

[0129] The indication information 2 may also indicate that the NWDAF network element 6 and the NWDAF network element 5 transmit data b based on LTP (ie, the data generated by the NWDAF network element 6 and the NWDAF network element 5 during the process of training the LSTM model 1).

[0130] S502g: The first network element sends indication information 3 to the NWDAF network element 5. Correspondingly, the NWDAF network element 5 receives the indication information 3 from the first network element.

[0131] Among them, the indication information 2 can indicate that the NWDAF network element 5 is the LSTM model 1 indicated by the server-NWDAF network element training identifier 2 in the FL scenario.

[0132] Indication information 2 can also indicate data a transmitted based on LTP between NWDAF network element 5 and NWDAF network element 7, data b transmitted based on LTP between NWDAF network element 5 and NWDAF network element 6, data c transmitted based on QUIC between NWDAF network element 5 and NWDAF network element 4 (i.e., the data of LSTM model 2 trained by NWDAF network element 6, NWDAF network element 7 and NWDAF network element 5), and data c transmitted based on QUIC between NWDAF network element 5 and ADRF network element 1.

[0133] S502h: The first network element sends indication information 4 to the NWDAF network element 4. Correspondingly, the NWDAF network element 4 receives the indication information 4 from the first network element.

[0134] Among them, the indication information 4 can instruct NWDAF network element 4 to deploy LSTM model 2 trained by NWDAF network element 6, NWDAF network element 7 and NWDAF network element 5 as an AnLF-NWDAF network element, and perform analysis services based on LSTM model 2 trained by NWDAF network element 6, NWDAF network element 7 and NWDAF network element 5.

[0135] Indication information 4 can also indicate that data d is transmitted between NWDAF network element 4 and the second network element based on QUIC (that is, the analysis result obtained by NWDAF network element 4 performing analysis service based on LSTM model 2 trained by NWDAF network element 6, NWDAF network element 7 and NWDAF network element 5).

[0136] S502i. The first network element sends indication information 5 to the ADRF network element 1. Correspondingly, the ADRF network element 1 receives the indication information 5 from the first network element.

[0137] Among them, the indication information 5 can instruct the ADRF network element 1 to store the LSTM model 2 trained by the NWDAF network element 6, the NWDAF network element 7 and the NWDAF network element 5.

[0138] The indication information 5 may also indicate that data c is transmitted between the ADRF network element 1 and the NWDAF network element 5 based on QUIC.

[0139] It can be understood that the LSTM model 2 deployed by the NWDAF network element 4 in S502h can be obtained from the NWDAF network element 5 or from the ADRF network element 1, and this embodiment of the present application does not make any specific limitation on this.

[0140] Optionally, after receiving the first information from the first network element, the third network element may also perform an analysis service based on the first information.

[0141] For example, taking the third network element including the above-mentioned NWDAF network element 4, NWDAF network element 5, NWDAF network element 6, NWDAF network element 7 and ADRF network element 1 as an example, see Figure 8 As shown, after executing S502, the present application may also execute:

[0142] S502j, NWDAF network element 6, NWDAF network element 7 and NWDAF network element 5 train LSTM model 1 to obtain LSTM model 2, and transmit the data generated in the process of training LSTM model 1 based on LTP.

[0143] S502 k. NWDAF network element 5 sends data of LSTM model 2 to NWDAF network element 4 and ADRF network element 1 based on QUIC. Correspondingly, NWDAF network element 4 and ADRF network element 1 receive data of LSTM model 2 from NWDAF network element 5 based on QUIC.

[0144] S502 1. NWDAF network element 4 deploys LSTM model 2 and executes analysis service based on LSTM model 2 to obtain analysis results.

[0145] S502 m. ADRF network element 1 stores LSTM model 2.

[0146] S502n, NWDAF network element 4 sends the analysis results to the second network element based on QUIC, and correspondingly, the second network element receives the analysis results from NWDAF network element 4 based on QUIC.

[0147] It is understandable that the above Figure 7 and Figure 8 The numbers of the steps shown are only for distinguishing different steps, and are not used to limit the order of the steps. For example, S502e may occur before S502f, or may occur after S502f, or may occur at the same time as S502f.

[0148] For ease of understanding, the following further describes the interactions between the first network element, the second network element, the third network element, the NRF network element, and the DCCF network element. Fig. 9 As shown, it is taken as an example that the first network element includes the AISCF network element, the second network element includes the AF network element, and the third network element includes the above-mentioned NWDAF network element 4, NWDAF network element 5, NWDAF network element 6, NWDAF network element 7 and ADRF network element 1.

[0149] The interaction between network elements can be based on a service-based interface. For example, the AISCF network element can interact with the AF network element, NWDAF network element 4, NWDAF network element 5, NWDAF network element 6, NWDAF network element 7 and ADRF network element 1 based on the service-based interface Naiscf.

[0150] Alternatively, the interaction between network elements can also be based on a data interface. For example, tunnel 1 can be established based on LTP between NWDAF network element 6, NWDAF network element 7 and NWDAF network element 5 (for transmitting data generated during the training of LSTM model 1), tunnel 2 can be established based on QUIC between NWDAF network element 5 and NWDAF network element 4 (for transmitting data of LSTM model 2), tunnel 3 can be established based on QUIC between NWDAF network element 5 and ADRF network element 1 (for transmitting data of LSTM model 2), and tunnel 4 can be established based on QUIC between NWDAF network element 4 and AF network element (for transmitting analysis results).

[0151] It can be understood that the above-mentioned embodiments of the present application can be implemented separately or in combination with each other, and the embodiments of the present application are not limited.

[0152] The method provided by the embodiment of the present application is introduced above in combination with the accompanying drawings, and the device provided by the embodiment of the present application is introduced below in combination with the accompanying drawings.

[0153] Based on the same technical concept, the embodiment of the present application provides a communication device, which includes a module / unit / means for executing the method executed by the device in the above method embodiment. The module / unit / means can be implemented by software, or by hardware, or the corresponding software can be implemented by hardware.

[0154] For example, see Fig.10 , is a schematic diagram of a communication device 1000 , which includes a transceiver module 101 and a processing module 102 .

[0155] When the device 1000 is a first network element or is located in a first network element, the functions of each module of the device 1000 are as follows:

[0156] The transceiver module 101 is configured to receive a first request from a second network element, where the first request includes an analysis identifier, and the first request is used to request the first network element to provide an analysis service corresponding to the analysis identifier;

[0157] The transceiver module 101 is also used to send first information to a third network element, where the third network element is determined by the processing module 102 based on second information. The first information is used to request the third network element to perform the analysis service, and the second information includes one or more of location information, capability information or load information of the third network element.

[0158] In specific implementation, the above-mentioned device 1000 can have a variety of product forms. Several possible product forms are introduced below.

[0159] See also Fig.11, is a schematic diagram of a communication device 1100, the communication device 1100 includes a processor 1110 and an interface circuit 1120, the interface circuit 1120 is used to receive signals from other communication devices outside the communication device and transmit them to the processor 1110, or send signals from the processor 1110 to other communication devices outside the communication device, the processor 1110 is used to implement the method performed by any device or network element in the above method embodiments through logic circuits or execution instructions.

[0160] The processor 1110 and the interface circuit 1120 are coupled to each other. It is understood that the interface circuit 1120 may be a transceiver or an input / output interface. Optionally, the communication device 1100 may further include a memory 1130 for storing instructions executed by the processor 1110 or storing input data required by the processor 1110 to execute instructions or storing data generated after the processor 1110 executes instructions.

[0161] When the above-mentioned communication device is a module applied to the first network element, the module implements the function of the first network element in the above-mentioned method embodiment. The module receives information from other modules in the first network element (such as a radio frequency module or an antenna), and the information is sent by the second network element to the first network element; or, the module sends information to other modules in the first network element (such as a radio frequency module or an antenna), and the information is sent by the first network element to the third network element. The module here can be the baseband chip of the first network element, or it can be a DU or other module, and the DU here can be a DU under the open radio access network (O-RAN) architecture.

[0162] It should be understood that the processor mentioned in the embodiments of the present application can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented by software, the processor can be a general-purpose processor implemented by reading software code stored in a memory.

[0163] Exemplarily, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0164] It should be understood that the memory mentioned in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DirectRambus RAM, DR RAM).

[0165] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) can be integrated into the processor.

[0166] It should be noted that the memory described herein is intended to include but is not limited to these and any other suitable types of memory. Based on the same technical concept, an embodiment of the present application also provides a computer-readable storage medium, in which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the method performed by any device or network element in the above method embodiment is implemented.

[0167] Based on the same technical concept, an embodiment of the present application also provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed by a processor, the method executed by any device or network element in the above method embodiment is implemented.

[0168] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0169] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0170] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

Claims

1. A communication method, characterized in that: Applied to a first network element, the method includes: receiving a first request from a second network element, the first request including an analysis identifier, the first request being used to request the first network element to provide an analysis service corresponding to the analysis identifier; Sending first information to a third network element, where the third network element is determined by the first network element based on second information, wherein the first information is used to request the third network element to perform the analysis service, and the second information includes one or more of location information, capability information or load information of the third network element.

2. The method according to claim 1, characterized in that The second information includes capability information of the third network element, wherein the capability information indicates that the third network element has the capability to perform the analysis service.

3. The method according to claim 1 or 2, characterized in that The second information includes load information of the third network element, wherein the load information indicates that the load of the third network element is less than or equal to a first threshold, or the load information indicates that the load of the third network element is less than the load of at least one network element, and the at least one network element is an optional network element that supports executing the analysis service.

4. The method according to any one of claims 1 to 3, characterized in that: The first information is used to request the third network element to perform the analysis service, including: The first information includes a first identifier indicating a model used to execute the analysis service.

5. The method according to any one of claims 1 to 4, characterized in that: The first information includes information of a first transmission protocol used to execute the analysis service, and the first transmission protocol is used to transmit data between the third network element and the second network element.

6. The method according to claim 5, characterized in that The first transmission protocol is determined from transmission protocols supported by the third network element and the second network element based on the type of data to be transmitted between the third network element and the second network element.

7. The method according to any one of claims 1 to 6, characterized in that: The third network element includes multiple network elements; the first information includes information of at least two transmission protocols for executing the analysis service, and one transmission protocol among the at least two transmission protocols is used to transmit data between any two network elements among the multiple network elements.

8. The method according to claim 7, characterized in that The one transmission protocol is determined from transmission protocols supported by the any two network elements based on the type of data to be transmitted between the any two network elements.

9. The method according to any one of claims 1 to 8, characterized in that: The first information is further used to indicate one or more of the following: Training a model indicated by the first identifier; deploying the model trained by the third network element and executing the analysis service based on the model trained by the third network element; or, The model trained by the third network element is stored.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: Receive the second information from the network storage function network element.

11. The method according to any one of claims 1 to 10, characterized in that: The second network element includes an application function network element and / or a network open function network element.

12. The method according to any one of claims 1 to 11, characterized in that: The third network element includes one or more of a network data analysis network element, a data collection and coordination function network element, or an analysis and data storage function network element.

13. A communication device, characterized in that: Comprising modules for executing the method as claimed in any one of claims 1 to 12.

14. A communication device, characterized in that: It includes a processor and an interface circuit, wherein the interface circuit is used to receive signals from other communication devices outside the communication device and transmit them to the processor or send signals from the processor to other communication devices outside the communication device, and the processor implements the method as described in any one of claims 1 to 12 through a logic circuit or executing code instructions.

15. A communication device, characterized in that: include: Memory for storing computer programs; A processor, configured to call and execute the computer program from the memory to implement the method according to any one of claims 1 to 12.

16. A chip system, characterized in that: include: Memory for storing computer programs; A processor, configured to call and run the computer program from the memory, so that a device equipped with the chip system executes the method as claimed in any one of claims 1 to 12.

17. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a communication device, implements the method according to any one of claims 1 to 12.

18. A computer-readable storage medium, characterized in that: The storage medium stores a computer program or an instruction. When the computer program or the instruction is executed by the communication device, the method according to any one of claims 1 to 12 is implemented.

Images