Communication method, apparatus and system

Abstract

The embodiments of the present application relate to the technical field of communications. Disclosed are a communication method, apparatus and system; and provided is a solution of how a model provider completes, when a model of the model provider is not trained independently by the model provider, authorization for a network element that requests the model. The method comprises: a first network element receiving a first model from a third network element; the first network element then receiving a first request message from a second network element, wherein the first request message is used for requesting a model, and the first request message comprises manufacturer information of the second network element; and the first network element determining whether a model interoperation indication of the third network element comprises the manufacturer information of the second network element, and when it is determined that the model interoperation indication of the third network element comprises the manufacturer information of the second network element, the first network element sending information of the first model to the second network element.

Description

Communication method, device and system

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on March 22, 2024, with application number 202410341202.6 and application name “Communication Methods, Devices and Systems”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technologies, and in particular to communication methods, devices, and systems. Background Art

[0003] With the evolution of communications technology, the integration of artificial intelligence (AI) and communication networks is a growing trend. In a network architecture that integrates this technology, network elements (NEs) that support model training can train models based on collected data, while NEs that support inference can infer analytical results based on the output of trained models, assisting operators in adjusting network resources and formulating network policies.

[0004] Currently, when a network element that wants to obtain a model requests a model from another network element that already has a model, it must complete an authorization process. However, if a network element's model is not independently trained by the network element, there is currently no clear authorization process for another network element to obtain the model from the network element. Summary of the Invention

[0005] The embodiments of the present application provide a communication method, device, and system that can solve the problem of how to authorize another network element that requests a model when the model owned by the network element is not trained independently by itself.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, a communication method is provided, which can be executed by a first network element, or by a component of the first network element (such as a processor, a chip, or a chip system, etc.), or by a logic module or software that can implement all or part of the functions of the first network element. The following description takes the first network element as an example of the execution subject of the method, and the method includes: the first network element receives a first model from a third network element. Then, the first network element receives a first request message from the second network element, the first request message is used to request a model, and the first request message includes the manufacturer information of the second network element. The first network element determines whether the model interoperability indication of the third network element includes the manufacturer information of the second network element. If it is determined to be included, the first network element sends the information of the first model to the second network element.

[0008] Based on the communication method provided in the embodiments of the present application, if the second network element requests a model from the first network element, and the first network element has a model obtained from the first network element, the first network element can determine whether to authorize the second network element by verifying whether the model interoperability indication of the third network element includes the manufacturer information of the second network element. The embodiments of the present application provide a solution for how a model provider authorizes a network element requesting a model in a scenario where the model owned by the model provider comes from another network element and the model provider does not independently train the model.

[0009] In a possible implementation, the first model is obtained by aggregating local models of one or more network elements by the third network element.

[0010] Based on this solution, the model obtained by the first network element from the third network element can be obtained by the third network element aggregating the local models of one or more network elements. That is to say, the embodiment of the present application provides a solution for how the model provider authorizes the network element requesting the model in a scenario where the model owned by the model provider is a model jointly trained by other network elements (such as a federated learning scenario).

[0011] In one possible implementation, the method further includes: the first network element sending a second request message to the fourth network element, the second request message being used to request a model interoperability indication from the third network element; and the first network element receiving a first response message from the fourth network element, the first response message including the model interoperability indication from the third network element.

[0012] This solution provides an implementation method for a first network element to obtain a model interoperability indication of a third network element.

[0013] In a possible implementation manner, the method further includes: the first network element receiving a model interoperability indication of the third network element from the third network element.

[0014] This solution provides an implementation method for a first network element to obtain a model interoperability indication of a third network element.

[0015] In a possible implementation, the method further includes: the first network element sending first indication information to the third network element, where the first indication information is used to instruct the sending of a model interoperability indication of the third network element.

[0016] Based on this solution, the third network element can send its own model interoperability indication to the first network element based on the indication of the first network element.

[0017] In one possible implementation, when it is determined that the model interoperability indication of the third network element includes the manufacturer information of the second network element, the first network element sends information of the first model to the second network element, including: when it is determined that the model interoperability indication of the third network element and the model interoperability indication of the first network element both include the manufacturer information of the second network element, the first network element sends information of the first model to the second network element.

[0018] Based on this solution, opening the first model requires obtaining authorization from the first network element and the third network element.

[0019] In one possible implementation, when it is determined that the model interoperability indication of the third network element includes the manufacturer information of the second network element, the first network element sends the first model to the second network element, including: when it is determined that the model interoperability indication of the third network element and the model interoperability indication of one or more network elements both include the manufacturer information of the second network element, the first network element sends the information of the first model to the second network element.

[0020] This solution provides an authorization scheme for opening the first model for the scenario where the third network element and one or more other network elements jointly train to obtain the first model, ensuring that all network elements involved in training the first model support opening the first model to the second network element.

[0021] In a possible implementation manner, the method further includes: the first network element receiving a model interoperability indication from one or more network elements of the third network element.

[0022] Based on this solution, the first network element can obtain model interoperability indications of one or more network elements participating in training the first model from the third network element to authorize the second network element.

[0023] In one possible implementation, the method further includes: the first network element sending first information and second indication information to a third network element, the first information including the vendor information of the second network element and / or the identification information of the second network element, the second indication information being used to instruct the third network element to determine whether the model interoperability indication of the third network element and the model interoperability indications of multiple other network elements all include the vendor information of the second network element, wherein the identification information of the second network element is used to determine the vendor information of the second network element. Then, the first network element receives third indication information from the third network element, the third indication information being used to indicate whether the model interoperability indication of the third network element and the model interoperability indications of multiple network elements all include the vendor information of the second network element.

[0024] Based on this solution, the third network element can perform authorization verification on the second network element and inform the first network element of the verification result.

[0025] In a second aspect, another communication method is provided. The communication method can be executed by a fourth network element, or by a component of the fourth network element (such as a processor, a chip, or a chip system, etc.), or by a logic module or software that can implement all or part of the functions of the fourth network element. The following is an illustration of the fourth network element as the execution subject of the method. The method includes: the fourth network element receives a third request message from the third network element, the third request message is used to request the discovery of network elements, the third request message includes the vendor information of the second network element and / or the identification information of the second network element, and the identification information of the second network element is used to determine the vendor information of the second network element. The fourth network element determines one or more network elements based on the vendor information of the second network element, and the model interoperability indication of the one or more network elements includes the vendor information of the second network element. The fourth network element sends a second response message to the third network element, and the second response message includes information of the one or more network elements.

[0026] The one or more network elements may participate in training the model. If a second network element subsequently requests to obtain the model trained by the one or more network elements, the one or more network elements may support opening the model to the second network element.

[0027] Based on the communication method provided in the embodiment of the present application, a first network element that supports opening a model to a second network element can be discovered during the network element discovery stage. If a network element that subsequently supports opening the first model to the second network element is used to jointly train the model, authorization of the second network element can be completed during the network element discovery stage. This provides a solution for how a model provider authorizes a network element that requests a model in a scenario where the model owned by the model provider comes from other network elements and the model provider does not independently train the model.

[0028] In a third aspect, a communication device is provided for implementing the various methods described above. The communication device includes modules, units, or means corresponding to the methods described above. The modules, units, or means may be implemented in hardware, software, or by hardware executing corresponding software implementations. The hardware or software includes one or more modules or units corresponding to the functions described above.

[0029] In some possible designs, the communication device may include a transceiver module and a processing module. The transceiver module, which may also be referred to as a transceiver unit, is configured to implement the transmitting and / or receiving functions described in the first or second aspect and any possible implementation thereof. The transceiver module may be comprised of a transceiver circuit, a transceiver, a transceiver, or a communication interface. The processing module may be configured to implement the processing functions described in the first or second aspect and any possible implementation thereof.

[0030] In some possible designs, the transceiver module includes a sending module and a receiving module, which are respectively used to implement the sending and receiving functions in the above-mentioned first aspect or second aspect and any possible implementation methods thereof.

[0031] In a fourth aspect, a communication device is provided, comprising: a processor and a communication interface; the communication interface is used to communicate with a module outside the communication device; the processor is used to execute a computer program or instruction so that the communication device performs any of the methods described above.

[0032] In a fifth aspect, a communication device is provided, comprising: at least one processor; the processor is configured to execute a computer program or instruction stored in a memory, so that the communication device performs any of the methods described in the aforementioned aspects. In one possible implementation, the memory may be coupled to the processor, or may be independent of the processor. In another possible implementation, the communication device further includes the memory. Optionally, the memory and the processor are integrated.

[0033] In aspects 3 to 5, the communication device may be the first network element in the first aspect or any implementation of the first aspect, or a device including the first network element, or a device included in the first network element, such as a chip. Alternatively, the communication device may be the fourth network element in the second aspect or any implementation of the second aspect, or a device including the fourth network element, or a device included in the fourth network element, such as a chip.

[0034] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program or instruction. When the computer program or instruction is run on a communication device, the communication device can execute any of the above aspects or any of its implementation methods.

[0035] In a seventh aspect, a computer program product comprising instructions is provided, which, when executed on a communication device, enables the communication device to execute any of the above aspects or any of its implementation methods.

[0036] In an eighth aspect, a communication device is provided (for example, the communication device may be a chip or a chip system), which includes a processor for implementing the functions involved in any of the above aspects or any of its implementation methods.

[0037] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0038] In some possible designs, when the device is a chip system, it can be composed of a chip, or it can also include a chip and other discrete devices.

[0039] It can be understood that when the communication device provided in any one of the third to eighth aspects is a chip, the above-mentioned sending action / function can be understood as output, and the above-mentioned receiving action / function can be understood as input.

[0040] Among them, the technical effects brought about by any implementation method from the third aspect to the eighth aspect can refer to the technical effects brought about by the corresponding implementation methods from the first aspect to the second aspect, and will not be repeated here.

[0041] It should be noted that various possible implementations of any of the above aspects can be combined under the premise that the solutions are not contradictory.

[0042] In a ninth aspect, a communication system is provided, comprising a first network element, a second network element, and a third network element, wherein the first network element is configured to execute the method of the first aspect or any implementation of the first aspect.

[0043] In some possible designs, the communication system includes a fourth network element, wherein the fourth network element is configured to execute the method of the second aspect or any implementation of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a schematic diagram of the model training process in a horizontal federated learning scenario;

[0045] FIG2 is a schematic diagram of the architecture of a communication system applicable to an embodiment of the present application;

[0046] FIG3 is a schematic diagram of a network architecture applicable to an embodiment of the present application;

[0047] FIG4 is an interactive diagram of a communication method provided in an embodiment of the present application;

[0048] FIG5 is a schematic diagram of an exemplary process of a communication method provided in an embodiment of the present application;

[0049] FIG6 is a schematic diagram of another exemplary process of the communication method provided in an embodiment of the present application;

[0050] FIG7 is an interactive diagram of another communication method provided in an embodiment of the present application;

[0051] FIG8 is a schematic diagram of an exemplary process of another communication method provided in an embodiment of the present application;

[0052] FIG9 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0053] FIG10 is a schematic diagram of the structure of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to facilitate understanding of the technical solutions of the embodiments of the present application, a brief introduction to the relevant technologies of the present application is first given as follows.

[0055] 1. Intelligent network architecture

[0056] The 3rd Generation Partnership Project (3GPP) standard defines an intelligent network architecture based on a network data analytics function (NWDAF). Its purpose is to collect massive amounts of information from the network and leverage existing big data and artificial intelligence technologies to utilize this data, outputting valuable information to assist operators in developing strategies and adjusting network resources to improve user experience and reduce network load. For example, NWDAF can collect service-related information such as service identification and service experience from application functions (AF) or terminal devices, and information such as signal reception power and signal reception quality from operations, administration, and management (OAM). NWDAF can train AI models based on the collected data and then derive inference analysis results based on the AI ​​models, such as a predicted service experience for a certain time period in the future.

[0057] NWDAF can be divided into the following categories based on the functions it supports: NWDAF containing the analytics logical function (AnLF) (hereinafter referred to as AnLF), NWDAF containing the model training logical function (MTLF) (hereinafter referred to as MTLF), and NWDAF containing both the analytics logical function and the model training logical function (NWDAF containing AnLF and MTLF). AnLF primarily performs inference operations, deriving and publishing analysis results, while MTLF is primarily responsible for training ML models (a type of AI model) and providing the trained ML models to AnLF.

[0058] 2. Federated Learning (FL) Scenario:

[0059] Federated learning is a distributed machine learning framework. In a federated learning scenario, there are two roles: participants (clients) (also called FL clients) and servers (also called FL servers). There are typically multiple participants, while there is typically only one server. During the federated learning model training process, participants do not share training data, but instead train their own models based on local data. The server can transmit relevant information during the model training process to obtain the final model.

[0060] In combination with the above intelligent network architecture, the participant and the service provider can be MTLF, that is, the participant can also be called client NWDAF and the service provider can also be called server NWDAF.

[0061] Based on the characteristics of the data sources of the participants, federated learning can be divided into three categories: horizontal federated learning, vertical federated learning, and transfer learning. The embodiments of this application are applicable to horizontal federated learning, vertical federated learning, and transfer learning. The following uses horizontal federated learning as an example to introduce. In the horizontal federated learning scenario, the participants and the service provider can train the model based on the following steps:

[0062] Step 0: The user (consumer) (can be AnLF or MTLF) sends a subscription request to the FL server to request the ML model.

[0063] Step 1: The FL server determines that federated learning is required to train the ML model and triggers the selection of an FL client. Figure 1 illustrates the discovery of FL client 1 and FL client 2. In practice, the number of FL clients selected by the FL server varies.

[0064] Step 2: The FL server sends a model training subscription request to the FL client. The request message contains the initial ML model.

[0065] Step 3: The FL client collects the data required to train the local model and uses the data to train the local model.

[0066] Step 4: The FL client sends the trained local model to the FL server (the message carrying the trained local model by the FL client can be called a model training response message).

[0067] Step 5: The FL server performs model aggregation based on each FL client’s local model to obtain the global model.

[0068] Optionally, after step 5, the process may further include steps 6a-6c.

[0069] Steps 6a-6b: The FL server notifies the consumer of the model training status (such as global model accuracy) to assist the consumer in determining whether to terminate model training. The consumer determines whether to terminate the model training process and feeds back the result to the server.

[0070] Step 6c: The FL server determines whether to terminate the model training process.

[0071] Step 7: The FL server sends the aggregated global model obtained in step 5 to the FL client.

[0072] Step 8: FL client updates the local model based on the global model.

[0073] If the FL server decides to continue model training in steps 6a-6c, steps 3-8 are repeated iteratively until, during a model iteration, the FL server terminates model training in steps 6a-6c and sends the global model for that iteration to the FL client in step 7. The FL server and FL client then store the global model. If the FL server terminates model training in steps 6a-6c, the global model obtained in step 5 is the completed model, and the FL server and FL client store the global model.

[0074] 3. Model open authorization mechanism:

[0075] When AnLF requests MTLF to obtain a model, AnLF needs to obtain the corresponding authorization. In the current authorization process, the ownership of the default model belongs to the model provider (i.e., the MTLF that trained the model). When authorizing, the model provider needs to check whether the vendor identifier (Vendor ID) of the user requesting the model (i.e., the AnLF that requested the model) is in the model interoperability indicator of the model provider. The model interoperability indicator of MTLF includes one or more Vendor IDs. If MTLF determines that AnLF's Vendor ID is in the MTLF's model interoperability indicator, MTLF can authorize AnLF and send the model information to AnLF. If MTLF determines that AnLF's Vendor ID is not in the MTLF's model interoperability indicator, MTLF refuses to authorize AnLF.

[0076] However, the above-mentioned existing authorization process is based on the fact that the model is trained by a separate MTLF and the default model belongs to the MTLF, so only the MTLF needs to authorize it. At present, for scenarios where the model may not completely belong to the model provider, such as when the model owned by the model provider comes from other network elements, there is no clear solution on how to authorize the network element requesting the model. For example, when AnLF requests a network element from the FL client in a federated learning scenario, the network element owned by the FL client comes from the server. At this time, there is no clear solution on how the FL client authorizes AnLF. Based on this problem, the present application provides a communication method, device and system that can solve the problem of how to authorize the network element requesting the model in scenarios such as federated learning where the model may not completely belong to the model provider.

[0077] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0078] In the embodiment of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the first indication information or the second indication information below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein the other information and the information to be indicated have an association relationship. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can be achieved by means of the arrangement order of each piece of information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each piece of information can also be identified and indicated uniformly to reduce the indication overhead caused by indicating the same information separately.

[0079] In addition, the specific indication method can also be various existing indication methods, such as but not limited to the above-mentioned indication methods and various combinations thereof. The specific details of the various indication methods can be referred to the prior art and will not be repeated herein. As can be seen from the above, for example, when it is necessary to indicate multiple information of the same type, there may be a situation where the indication methods for different information are different. In the specific implementation process, the required indication method can be selected according to specific needs. The embodiment of the present application does not limit the selected indication method. In this way, the indication method involved in the embodiment of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0080] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited in the embodiments of this application. The sending period and / or sending time of these sub-information can be predefined, for example, predefined according to a protocol, or can be configured by the transmitting device by sending configuration information to the receiving device.

[0081] In an embodiment of the present application, "pre-definition", "pre-defined", "pre-configured" or "pre-configured" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the device. For example, it can be burned into the device when the device leaves the factory. The embodiment of the present application does not limit its specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, which is not limited by the embodiment of the present application.

[0082] The "protocol" involved in the embodiments of the present application may refer to a protocol family in the communication field, a standard protocol with a similar protocol family frame structure, or a related protocol used in future communication systems. The embodiments of the present application do not make specific limitations on this.

[0083] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if" and "if" all mean that the device will perform corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the device to perform judgment actions when implemented, nor does it mean that there are other limitations.

[0084] In the embodiment of the present application, "sending information to... (taking the first network element as an example)" can be understood as the destination end of the information being the first network element. This can include sending information to the first network element directly or indirectly. "Receiving information from... (taking the second network element as an example)" can be understood as the source end of the information being the second network element, which can include receiving information from the second network element directly or indirectly. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, etc., but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be repeated here.

[0085] The technical solution provided in this application can be used in various communication systems, which may be 3GPP communication systems, for example, 4th generation (4G) mobile communication systems, long term evolution (LTE) systems, 5th generation (5G) mobile communication systems and their evolution systems, non-terrestrial networks (NTN) systems, multiple-input multiple-output (MIMO) systems, vehicle to everything (V2X) systems, LTE and new radio (NR) hybrid networking systems, or device to device (D2D) systems, machine to machine (M2M) communication systems, Internet of Things (IoT), and other communication systems, such as future mobile communication systems. In addition, the term "system" and "network" can be used interchangeably.

[0086] It should be noted that the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0087] Figure 2 shows a communication system provided by the present application to which the communication method of the present application is applicable. The communication system may include a first network element, a second network element, and a third network element.

[0088] Optionally, FIG2 illustrates an example in which the number of the first network element, the second network element or the third network element is 1. In actual applications, the number of the first network element, the second network element or the third network element may also be multiple.

[0089] The first network element and the third network element can communicate with each other. Optionally, the second network element and the first network element can communicate with each other. Alternatively, the second network element and the third network element can communicate with each other.

[0090] Optionally, in a 5G communication system, the first network element, the second network element, or the third network element may be an NWDAF network element. In future communication systems, the first network element, the second network element, or the third network element may still be an NWDAF network element, or may have other names, which is not limited in this embodiment of the present application.

[0091] Optionally, if the first network element, the second network element or the third network element is an NWDAF network element, the second network element may be an AnLF, and the first network element or the third network element may be an MTLF.

[0092] Optionally, in a federated learning scenario, the first network element may be a FL client, and the third network element may be a FL server.

[0093] Optionally, as shown in FIG2 , the communication system may further include a fourth network element, etc. Optionally, the fourth network element and the first network element may communicate with each other. Alternatively, the fourth network element and the third network element may communicate with each other.

[0094] Optionally, in a 5G communication system, the fourth network element may be a network repository function (NRF) network element. In future communication systems, the fourth network element may still be an NRF network element, or may have other names, which is not limited in the embodiments of the present application.

[0095] Optionally, the communication system may also include terminal equipment or access network equipment, etc.

[0096] Figure 3 is a schematic diagram of a 5G network architecture based on a service-oriented interface applicable to the present application. As shown in Figure 3, the network architecture mainly includes the following network functions and entities: terminal equipment, access network equipment, user plane function (UPF) network element, data network (DN), access and mobility management function (AMF) network element, session management function (SMF) network element, binding support function (BSF) network element, policy control function (PCF) network element, application function (AF) network element, network exposure function (NEF) network element, NWDAF network element, NRF network element, unified data management function (UDM) network element, unified data repository (UDR) network element, etc. Optionally, it may also include an OAM network element.

[0097] The following is a brief introduction to the network elements mainly included in the network architecture shown in Figure 3.

[0098] Terminal equipment can refer to a user-side device with wireless transceiver capabilities. Terminal equipment can also be called user equipment (UE), terminal, access terminal, subscriber unit, subscriber station, mobile station (MS), remote station, remote terminal, mobile terminal (MT), user terminal, wireless communication device, user agent, or user device.

[0099] Exemplarily, the terminal device may be a drone, an Internet of Things (IoT) device (e.g., a sensor, an electricity meter, a water meter, etc.), a V2X device, a station (ST) in a wireless local area network (WLAN), a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device (also referred to as a wearable smart device), a tablet computer or a computer with wireless transceiver capabilities, a virtual reality (VR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a smart home, or a similar device. The present application does not specifically limit the terminals to mobile or fixed devices.

[0100] Access network equipment: Access network equipment can be a device deployed in the access network to provide communication functions for terminals. Access network equipment can be radio access network (RAN) equipment, wired access network equipment, non-3GPP access network equipment, 3GPP access network equipment, etc. Access network equipment can include various types of base stations (BS), such as various forms of macro base stations, micro base stations, pico base stations, femto base stations, relay stations, access points (AP), etc. In systems using different wireless access technologies, the names of access network equipment may be different, such as NodeB (NB) in 3G networks, evolved NodeB (eNB or eNodeB) in long term evolution (LTE) networks, and the next generation NodeB (gNB or gNodeB) or / new radio NodeB (NR NB) in 5G networks, etc.

[0101] In addition, in some network architectures, multiple access network devices collaborate to assist terminal devices in achieving wireless access, and different access network devices respectively implement part of the functions of the base station. For example, the access network device can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or they can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0102] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open access network (open RAN, O-RAN or ORAN), CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0103] The NWDAF network element is mainly responsible for data collection, model training, data analysis, model reasoning and other functions. It can be used to collect relevant data from network elements, third-party service servers, terminal devices or network management systems, perform data analysis or model training based on the relevant data, and provide data analysis results to network elements, third-party service servers, terminal devices or network management systems, or provide trained models to other data analysis function network elements.

[0104] The NRF network element is mainly responsible for network function service registration and status monitoring, realizing the automated management, selection and scalability of network function services, and allowing each network function to discover the services provided by other network functions.

[0105] The main functions of other network elements in the architecture shown in Figure 3, such as AMF network element, SMF network element, PCF network element, AF network element, UPF network element, NEF network element, OAM network element, UDM network element, UDR network element or BSF network element, can be referred to the existing protocols and will not be expanded here.

[0106] In addition, Figure 3 also shows the interaction relationship between various network functions and entities and the corresponding interfaces. As shown in Figure 3, the terminal device accesses the 5G network through the access network device; the access network device communicates with the AMF network element through the N2 interface (referred to as N2); the access network device communicates with the UPF network element through the N3 interface (referred to as N3); the SMF network element communicates with the UPF network element through the N4 interface (referred to as N4), and the UPF network element accesses the DN through the N6 interface (referred to as N6). In addition, the network functions such as the AMF network element, SMF network element, NEF network element, NRF network element, PCF network element, UDM network element, UDR network element, or AF network element shown in Figure 3 use service-oriented interfaces to interact. For example, the service interface provided by the AMF network element to the outside is Namf; the service interface provided by the SMF network element to the outside is Nsmf; the service interface provided by the NEF network element to the outside is Nnef; the service interface provided by the NRF network element to the outside is Nnrf; the service interface provided by the PCF network element to the outside is Npcf; the service interface provided by the UDM network element to the outside is Nudm; the service interface provided by the UDR network element to the outside is Nudr; the service interface provided by the AF network element to the outside is Naf; the service interface provided by the NWDAF network element to the outside is Nnwdaf; and the service interface provided by the BSF network element to the outside is Nbsf.

[0107] All or part of the functions of the network element in this application may also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (such as a cloud platform). The network element in this application may also be a logical node, logical module or software that can implement all or part of the network element functions.

[0108] In the embodiment of the present application, a network element may also be referred to as an entity or a functional entity. For example, an MME network element may also be referred to as an MME entity or an MME functional entity.

[0109] The communication method provided in the embodiment of the present application is described below in conjunction with Figures 2 to 3.

[0110] It can be understood that in the embodiment of the present application, the message names, the names of the parameters, or the names of the information between the network elements are only examples. In other embodiments, they may also be other names. The method provided in this application does not make specific limitations on this.

[0111] It is understood that in the embodiments of the present application, each network element or entity may perform some or all of the steps in the embodiments of the present application. These steps or operations are merely examples, and the embodiments of the present application may also perform other operations or variations of various operations. In addition, the steps may be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be performed.

[0112] For example, the method provided in the following embodiments of this application can be applied to a scenario where a model provider performs authorization verification on a network element requesting a model. Of course, this is only an example of an application scenario of this application, and this application scenario does not impose any limitation on this application. This application also does not specifically limit the application scenario of the method provided below.

[0113] As shown in Figure 4, a communication method is provided for an embodiment of the present application. Figure 4 takes the first network element, the second network element and the third network element as examples of the execution subjects of the interaction diagram to illustrate the method, but the present application does not limit the execution subjects of the interaction diagram. For example, the first network element in Figure 4 can also be a module such as a chip, a chip system, or a processor applied to the first network element, and can also be a logical node, a logical module or software that can realize all or part of the functions of the first network element; the second network element in Figure 4 can also be a module such as a chip, a chip system, or a processor applied to the second network element, and can also be a logical node, a logical module or software that can realize all or part of the functions of the second network element; the third network element in Figure 4 can also be a module such as a chip, a chip system, or a processor applied to the third network element, and can also be a logical node, a logical module or software that can realize all or part of the functions of the third network element;

[0114] As shown in FIG4 , the communication method includes steps S401 to S403:

[0115] S401. The third network element sends a first model to the first network element. Correspondingly, the first network element receives the first model from the third network element.

[0116] S402: The first network element receives a first request message from the second network element. The first request message is used to request a model (or to subscribe to a model). The first request message includes manufacturer information of the second network element.

[0117] S403: When it is determined that the model interoperability indication of the third network element includes the vendor information of the second network element, the first network element sends information of the first model to the second network element.

[0118] Based on the communication method provided in the embodiments of the present application, if a second network element requests a model from a first network element, and the first network element has a model obtained from the first network element, the first network element can determine whether to authorize the second network element by verifying whether the model interoperability indication of the third network element includes the manufacturer information of the second network element. The embodiments of the present application provide a solution for how a model provider authorizes a network element requesting a model in a scenario where the model owned by the model provider comes from another network element and the model provider does not independently train the model.

[0119] The following is an introduction to S401-S403.

[0120] In S401, the first model can be any AI model.

[0121] Optionally, the first model may be trained by a third network element. Alternatively, the first model may be jointly trained by the third network element and one or more network elements. The one or more network elements jointly trained with the third network element for the first model may include the first network element, or may not include the first network element.

[0122] Regarding the third network element and one or more network elements jointly training to obtain the first model, in one possible implementation, the first model can be obtained by the third network element aggregating local models of one or more network elements.

[0123] For example, assume that a first network element, a third network element, and one or more other network elements jointly train a first model. The first network element may be a FL client in a federated learning scenario, and the third network element may be a FL server in the federated learning scenario. The third network element may aggregate the model trained locally by the first network element and the models trained locally by the other FL clients to obtain the first model. In a federated learning scenario, the process by which the FL server aggregates the local models of the FL clients to obtain the final global model can be found in the above description of the federated learning scenario.

[0124] The embodiments of the present application do not limit the specific implementation of the third network element sending the first model to the first network element. Optionally, the third network element may send the model file of the first model to the first network element, and the first network element may directly obtain the first model based on the model file of the first model. Alternatively, the third network element may send the model file address of the first model to the first network element, such as a uniform resource locator (URL) address or a fully qualified domain name (FQDN) address, and the first network element may download the first model through the model file address. Alternatively, the third network element may send the identification information of the first model (such as a model ID) and the identification information of the analytics data repository function (ADRF) network element (such as ADRFID) to the first network element. The first network element may obtain the first model from the ADRF network element identified by the ADRFID through the model ID of the first model.

[0125] In S402, the manufacturer information of the second network element may indicate the manufacturer of the second network element, for example, may be the Vendor ID of the second network element.

[0126] Optionally, the second network element may directly send the first request message to the first network element to request the model. Alternatively, another network element may replace the second network element and send the first request message to the first network element to request the model.

[0127] For example, if the second network element is an AnLF, the AnLF can directly request the model from the first network element, with the request message sent by the AnLF including the AnLF's vendor ID. Alternatively, the AnLF can request the model from a MTLF, which, upon receiving the request, sends a first request message to the first network element to request the model.

[0128] Optionally, in addition to the manufacturer information of the second network element, the first request message may also include at least one of the following information: information indicating the second network element's requirements for the model, a token of the second network element, or an analytics ID. The analytics ID is used to identify the analysis type corresponding to the model requested by the second network element, for example, Analytics ID = "Service Experience", indicating that the second network element requests a model for analyzing service experience. For another example, Analytics ID = "UE Mobility", indicating that the second network element requests a model for analyzing terminal device mobility. The token of the second network element is used by the first network element to verify the identity of the second network element and decide whether to allow the second network element to obtain the model. The information indicating the requirements for the model is used to indicate the requirements for the model, and may include, for example, at least one of the following: single network slice selection assistance information (S-NSSAI) or an area of ​​interest, wherein S-NSSAI is used to indicate the slice to which the model is applicable, and the area of ​​interest is used to indicate the area to which the model is applicable.

[0129] In S403, the first network element determines whether to open the first model to the second network element, or in other words, whether to authorize the second network element to obtain the first model, by determining whether the model interoperability indicator of the third network element includes the vendor information of the second network element. If it is determined that the model interoperability indicator of the third network element includes the vendor information of the second network element, the first network element opens the first model to the second network element, that is, sends information about the first model to the second network element. If it is determined that the model interoperability indicator of the third network element does not include the vendor information of the second network element, the first network element refuses to open the first model to the second network element, that is, does not send information about the first model to the second network element.

[0130] Correspondingly, if the second network element receives the information of the first model, the second network element can obtain the first model based on the information of the first model. The information of the first model can be specifically referred to the above description of the specific implementation of the third network element sending the first model to the first network element, which will not be elaborated here.

[0131] Regarding determining whether the model interoperability indication of the third network element includes the vendor information of the second network element, in one possible implementation method, the first network element may determine whether the model interoperability indication of the third network element includes the vendor information of the second network element based on the model interoperability indication of the third network element.

[0132] In this implementation, the first network element needs to obtain the model interoperability indication of the third network element. The embodiment of the present application does not limit the manner in which the first network element obtains the model interoperability indication of the third network element. The following describes several possible methods provided by the embodiment of the present application.

[0133] Method 1: A first network element sends a second request message to a fourth network element, where the second request message is used to request a model interoperability indication from a third network element. After receiving the second request message, the fourth network element sends a first response message to the first network element in response to the second request message, where the first response message includes the model interoperability indication from the third network element. Accordingly, after receiving the first response message, the first network element obtains the model interoperability indication from the third network element.

[0134] Wherein, illustratively, the fourth network element may be an NRF network element.

[0135] Optionally, the second request message may include identification information of the third network element.

[0136] Method 2: The third network element sends a model interoperability indication of the third network element to the first network element, and correspondingly, the first network element receives the model interoperability indication of the third network element.

[0137] In the second method, optionally, the third network element may proactively send a model interoperability indication of the third network element to the first network element.

[0138] Among them, the third network element can send the model interoperability indication of the third network element to the first network element during the model training process, or it can send the model interoperability indication of the first model and the third network element to the first network element after the first model is trained.

[0139] Exemplarily, assuming that the first network element is a FL client in a federated learning scenario, and the third network element is a FL server in the federated learning scenario, the third network element may send a model interoperation indication to the first network element during the model training process. For example, the third network element may carry the model interoperation indication of the third network element in the model training subscription request sent to the first network element. The model training subscription request carrying the model interoperation indication of the third network element may be a model training subscription request carrying the initial model during the model training process, or a model training subscription request carrying the aggregated model during the subsequent model iteration process. For another example, the third network element may carry the model interoperation indication of the third network element in a message carrying the final aggregated model (i.e., the first model) (the message may also be referred to as a model training subscription request). For another example, the third network element may send the model interoperation indication of the third network element to the first network element through an independent new message.

[0140] Exemplarily, assuming that the first network element subscribes to a model from the third network element, the third network element may send a model interoperability indication of the first model and the third network element to the first network element after completing training of the first model.

[0141] In the second method, the first network element may optionally send first indication information to the third network element, where the first indication information is used to instruct the sending of the model interoperability indication of the third network element. After receiving the first indication information, the third network element sends the model interoperability indication of the third network element to the first network element according to the first indication information.

[0142] Exemplarily, assuming that the first network element is a FL client in a federated learning scenario, and the third network element is a FL server in the federated learning scenario, the first network element may send first indication information to the third network element during the model training process. For example, the first network element may carry the first indication information in a model training response message. After the third network element receives the model training response message, in the next round of model training, the model training subscription request sent to the first network element carries the model interoperability indication of the third network element. For another example, the first network element may send the first indication information to the third network element through an independent new message. For another example, the third network element may send the model interoperability indication of the third network element to the first network element through an independent new message.

[0143] Regarding determining whether the model interoperability indication of the third network element includes the vendor information of the second network element, in another possible implementation, the third network element may determine whether the model interoperability indication of the third network element includes the vendor information of the second network element.

[0144] In this implementation, the first network element may send the vendor information of the second network element and / or the identification information of the second network element (for example, if the second network element is AnLF, the identification information of the second network element may be AnLF ID) and indication information to the third network element, wherein the indication information instructs the third network element to determine whether the model interoperability indication of the third network element includes the vendor information of the second network element. If the third network element receives the vendor information of the second network element and the indication information, the third network element may determine whether the model interoperability indication of the third network element includes the vendor information of the second network element based on the indication of the indication information. If the third network element receives the identification information of the second network element and the indication information, the third network element may determine the vendor information of the second network element based on the identification information of the second network element, and then determine whether the model interoperability indication of the third network element includes the vendor information of the second network element. For example, the third network element may pre-configure a mapping relationship between the identification information of the second network element and the vendor information of the second network element, so that the vendor information of the second network element can be determined based on the identification information of the second network element. For another example, the third network element may obtain the manufacturer information of the second network element corresponding to the identification information of the second network element from the fourth network element based on the identification information of the second network element. The fourth network element may be, for example, an NRF.

[0145] Furthermore, the third network element sends indication information indicating whether the model interoperability indication of the third network element includes the vendor information of the second network element to the first network element. The first network element may determine whether to send the first model to the second network element based on the indication information.

[0146] In one possible scenario, in S403, in addition to determining whether the model interoperability indication of the third network element includes the vendor information of the second network element, it may also be determined whether the model interoperability indication of the first network element includes the vendor information of the second network element. If it is determined that both the model interoperability indication of the third network element and the model interoperability indication of the first network element include the vendor information of the second network element, the first network element sends the information of the first model to the second network element. Otherwise, the first network element does not send the information of the first model to the second network element.

[0147] Among them, the first network element can directly determine whether the model interoperability indication of the first network element includes the manufacturer information of the second network element. For determining whether the model interoperability indication of the third network element includes the manufacturer information of the second network element, please refer to the above introduction for details and will not be elaborated here.

[0148] In another possible scenario, if the first model is jointly trained by the third network element and one or more network elements, in S403, in addition to determining whether the model interoperability indication of the third network element includes the vendor information of the second network element, it may also be determined whether the model interoperability indication of the one or more network elements includes the vendor information of the second network element. If it is determined that the model interoperability indication of the third network element and the model interoperability indication of the one or more network elements both include the vendor information of the second network element, the first network element sends information about the first model to the second network element.

[0149] Regarding determining whether the model interoperability indication of the third network element includes the vendor information of the second network element, please refer to the above introduction for details, which will not be elaborated here.

[0150] For determining whether the model interoperability indication of one or more network elements that jointly train the first model with the third network element includes the vendor information of the second network element, in one possible implementation, the first network element can determine whether the model interoperability indication of the one or more network elements includes the vendor information of the second network element based on the model interoperability indication of the one or more network elements.

[0151] In this implementation, if the first network element is included in one or more network elements that jointly train the first model with the third network element, the first network element can directly determine whether the model interoperability indication of the first network element includes the manufacturer information of the second network element. If other network elements different from the first network element are included in the network elements that jointly train the first model with the third network element, the third network element can send the model interoperability indication of the other network element to the first network element, and the first network element accordingly receives the model interoperability indication of the other network element.

[0152] Optionally, if the network elements that jointly train the first model with the third network element include the first network element and other network elements, the first network element may first determine whether its own model interoperability indication includes the vendor information of the second network element. If so, the first network element may further determine whether the interoperability indications of the third network element and the other network elements jointly trained include the vendor information of the second network element.

[0153] Optionally, the third network element may proactively send model interoperability indications of other network elements to the first network element.

[0154] Among them, the third network element can send model interoperability indications of other network elements to the first network element during the model training process, or can send model interoperability indications of the first model and other network elements to the first network element after the first model is trained.

[0155] Exemplarily, assuming that the third network element is an FL server in a federated learning scenario, and the first network element is an FL client in the federated learning scenario, the third network element may send a model interoperability indication of each FL client that jointly trains the first model to the first network element during the model training process (or, may send a model interoperability indication of each FL client except the first network element). For example, the third network element may carry the model interoperability indication of the FL client in a model training subscription request sent to the first network element. The model training subscription request carrying the model interoperability indication of the FL client may be a model training subscription request carrying the initial model during the model training process, or may be a model training subscription request carrying the aggregated model during a subsequent model iteration process. For another example, the third network element may carry the model interoperability indication of the FL client in a message carrying the final aggregated model (i.e., the first model). For another example, the third network element may send the model interoperability indication of the FL client to the first network element through an independent new message.

[0156] For example, assuming that the first network element subscribes to a model from the third network element, and the third network element jointly trains the model with other network elements, the third network element can send the model interoperability indication of the first model and each network element that jointly trained the first model to the first network element after completing the training of the first model.

[0157] Optionally, the third network element may also send a model interoperability indication of other network elements to the first network element under the instruction of the first network element.

[0158] Exemplarily, assuming that the first network element is a FL client in a federated learning scenario, and the third network element is a FL server in the federated learning scenario, the first network element may send indication information to the third network element during the model training process, where the indication information instructs the third network element to send a model interoperability indication for each FL client that jointly trains the first model (or instructs the sending of a model interoperability indication for each FL client except the first network element). For example, the first network element may carry the indication information in a model training response message. After the third network element receives the model training response message, in the next round of model training, the third network element carries the model interoperability indication of the FL client in the model training subscription request sent to the first network element. For another example, the first network element may send the indication information to the third network element through an independent new message. For another example, the third network element may send the model interoperability indication of the FL client to the first network element through an independent new message.

[0159] Regarding determining whether the model interoperability indication of one or more network elements that jointly train the first model with the third network element includes the vendor information of the second network element, in another possible implementation, the third network element may determine whether the model interoperability indication of the one or more network elements includes the vendor information of the second network element based on the model interoperability indication of the one or more network elements.

[0160] Optionally, in this implementation, the third network element may, under the instruction of the first network element, determine whether the model interoperability indication of one or more network elements that jointly train the first model includes the manufacturer information of the second network element.

[0161] Optionally, in this implementation, the third network element may, under the instruction of the first network element, determine whether the model interoperability indication of the third network element and the model interoperability indication of one or more network elements that jointly train the first model include the manufacturer information of the second network element. The first network element may send first information and second indication information to the third network element, the first information including the manufacturer information of the second network element and / or the identification information of the second network element, the second indication information being used to instruct the third network element to determine whether the model interoperability indication of the third network element and the model interoperability indication of one or more network elements that jointly train the first model both include the manufacturer information of the second network element, and the identification information of the second network element being used by the third network element to determine the manufacturer information of the second network element. After receiving the first information and the second indication information, the third network element determines whether the model interoperability indication of the third network element and the model interoperability indication of one or more network elements that jointly train the first model include the manufacturer information of the second network element.

[0162] Optionally, if the first network element is one of one or more network elements that jointly train the first model, the second indication information can instruct the third network element to determine the model interoperability indication of the third network element, and whether the model interoperability indications of one or more network elements other than the first network element that jointly train the first model include the manufacturer information of the second network element.

[0163] Furthermore, after verification, the third network element sends third indication information to the first network element, where the third indication information is used to indicate whether the model interoperability indication of the third network element and the model interoperability indication of one or more network elements that jointly train the first model (or one or more network elements other than the first network element that jointly train the first model) both include the manufacturer information of the second network element. After receiving the third indication information, the first network element can determine whether to send the first model to the second network element based on the third indication information.

[0164] Assume that the above embodiment of S401-S403 is applied to a 5G system, the second network element is AnLF, the first network element is an FL client in a federated learning scenario, and the third network element is an FL server in a federated learning scenario. An exemplary process of the above embodiment can be shown in Figure 5, including the following steps:

[0165] S501: The MTLF determines that an ML model needs to be trained based on the local configuration. The MTLF determines that the federated learning mechanism needs to be used to train the ML model, and the MTLF determines that it cannot serve as the FL server.

[0166] S502: The MTLF discovers the FL server and sends a model subscription request to the FL server.

[0167] S503: The FL server selects a FL client. The MTLF may or may not be one of the FL clients selected by the FL server.

[0168] S504. The FL server carries the model interoperability indication of the FL server in the model training subscription request.

[0169] In S504, the FL server may proactively include its model interoperability indicator in the model training subscription request. Alternatively, if the FL server's first model training subscription request does not include its model interoperability indicator, the FL client, upon receiving the model training subscription request, may include first indicator information in a model training response message. This first indicator information is used to instruct the FL server to provide its model interoperability indicator. After receiving the model training response message, the FL server may include its model interoperability indicator in the model training subscription request sent to the FL client in the next round of model training.

[0170] S505: The FL server and the FL client perform a model training process. After the model training is completed, the FL client saves the final aggregated ML model, i.e., the first model.

[0171] S506: The FL server sends information of the first model to the MTLF.

[0172] Optionally, if the FL client does not obtain the model interoperability indication from the FL server during the model training phase, the FL client may request the model interoperability indication from the FL server from the NRF network element.

[0173] S507 : AnLF requests the FL client for the ML model. The request message includes AnLF's Vendor ID information.

[0174] Optionally, the request message also includes the analytics ID, AnLF token, and AnLF's requirements for the ML model.

[0175] S508: The FL client determines that the saved first model meets the requirements of AnLF and further decides whether to authorize AnLF to obtain the first model. The specific authorization verification process includes:

[0176] The FL client verifies whether AnLF's vendor ID is included in its own model interoperability indication. Furthermore, the FL client verifies whether AnLF's vendor ID is included in the FL server's model interoperability indication. If the FL client determines that both its own model interoperability indication and the FL server's model interoperability indication include AnLF's vendor ID, the FL client authorizes AnLF to obtain the first model, i.e., determines that the first model can be sent to AnLF.

[0177] S509: The FL client sends information of the first model to AnLF.

[0178] Assume that the above embodiment of S401-S403 is applied to a 5G system, the second network element is AnLF, and the first network element is an FL client in a federated learning scenario. Alternatively, the first network element may be MTLF, and the third network element is an FL server in a federated learning scenario. Another exemplary process of the above embodiment can be shown in Figure 6, including the following steps:

[0179] S601: The MTLF determines that an ML model needs to be trained based on the local configuration. The MTLF determines that the federated learning mechanism needs to be used to train the ML model, and the MTLF determines that it cannot serve as the FL server.

[0180] S602: The MTLF discovers the FL server and sends a model subscription request to the FL server.

[0181] S603: The FL server selects a FL client. The MTLF may or may not be one of the FL clients selected by the FL server.

[0182] S604: The FL server and the FL client perform a model training process. After the model training is completed, the FL server sends the final aggregated ML model, i.e., the first model, to the MTLF and the FL client.

[0183] Furthermore, after model training is completed, the FL server may send a model interoperability indication between the FL server and each FL client to the MTLF. The FL server may also send a model interoperability indication between the FL server and each FL client to the FL client during or after model training. Alternatively, for any FL client, the FL server may send the FL server's model interoperability indication and the model interoperability indication of each FL client except the FL client to the FL client. For details, please refer to the above description of S403 and will not be elaborated here.

[0184] S605. AnLF sends a model subscription request to the FL client / MTLF. The request message includes AnLF's verdor ID.

[0185] In FIG6 , S605 and subsequent steps S606 - S607 are illustrated by taking as an example that AnLF sends a model subscription request to FL client, FL client performs authorization verification, and sends information of the first model to AnLF if the authorization verification passes.

[0186] S606: After receiving the model subscription request from AnLF, the FL client / MTLF determines whether the stored first model can meet the requirements of AnLF, and further decides whether to authorize AnLF to obtain the first model.

[0187] As shown in S606a, if the FL client / MTLF has the model interoperability indication of the FL server and the model interoperability indication of each FL client participating in training the first model, a specific authorization verification process includes:

[0188] The FL client / MTLF verifies whether AnLF's vendor ID is included in the model interoperability indication of the FL server and also verifies whether AnLF's vendor ID is included in the model interoperability indication of each FL client. If the FL client / MTLF determines that the model interoperability indications of the FL server and each FL client both include AnLF's vendor ID, the FL client / MTLF authorizes AnLF to obtain the first model, i.e., determines that the first model can be sent to AnLF.

[0189] Alternatively, as shown in S606b, another specific authorization process includes:

[0190] The FL client / MTLF verifies whether the Vendor ID of AnLF is included in its own model interoperability indication. If it is determined to be included, the FL client / MTLF further sends a request message to the FL server. The request message includes the AnLF ID and / or the AnLF Vendor ID, as well as second indication information. The second indication information is used to instruct the FL server to verify whether the Vendor ID of AnLF is included in the model interoperability indication of the FL server and each FL client participating in training the first model (if the FL client sends the second indication information, the second indication information may also instruct to verify whether the Vendor ID of AnLF is included in the model interoperability indication of the FL server and other FL clients participating in training the first model). After receiving the request message, the FL server performs verification and returns the verification result (i.e., the third indication information) to the FL client / MTLF. Based on the verification result, the FL client / MTLF determines whether the first model can be sent to AnLF.

[0191] S607: The FL client / MTLF sends information of the first model to the AnLF.

[0192] Alternatively, in another possible implementation, in S601, the MTLF may also determine that it can serve as the FL server (this implementation is not shown in FIG6 ). In this implementation, subsequent steps include: the FL server (i.e., the MTLF) selects the FL client. The FL server and the FL client perform a model training process. After the model training is completed, the FL server sends the final aggregated ML model, i.e., the first model, to the FL client. In addition, the FL server may also send a model interoperability indication of the FL server and the FL client to the FL client during or after the model training is completed. For details, please refer to the above description of S804. In this implementation, the first network element may be the FL client.

[0193] In addition, the embodiment of the present application also provides another communication method. Referring to Figure 7, the another communication method provided by the embodiment of the present application includes steps S701-S703:

[0194] S701: A third network element sends a third request message to a fourth network element. Accordingly, the fourth network element receives the third request message from the third network element. The third request message is used to request network element discovery and includes vendor information and / or identification information of a second network element.

[0195] In S701 , the third network element requests the fourth network element to discover a network element that is to train a model together with the third network element.

[0196] Optionally, before S701, the third network element may receive a request message from the second network element, where the request message is used to request a model (also referred to as a model subscription message), including the manufacturer information of the second network element and / or the identification information of the second network element. Alternatively, the second network element may request a model from another network element. After receiving the request from the second network element, the third network element may send a request message for requesting a model to the third network element on behalf of the second network element, where the request message includes the manufacturer information of the second network element and / or the identification information of the second network element.

[0197] Accordingly, after receiving the request message for the model, the third network element determines, based on the request message, that the model needs to be trained and that it needs to be trained jointly with one or more network elements. For example, the third network element determines that the model needs to be trained using a federated learning mechanism. In this case, the third network element can be an FL server. Based on this, the third network element determines to select a network element with which to jointly train the model and decides to request network element discovery from the fourth network element, i.e., decides to send a third request message to the fourth network element.

[0198] Optionally, after receiving the request message for requesting the model, the third network element may determine whether its own model interoperability indication includes the vendor information of the second network element. If the third network element determines that its own model interoperability indication includes the vendor information of the second network element, the third network element sends a third request message to the fourth network element; if it determines that its own model interoperability indication does not include the vendor information of the second network element, the third network element does not send the third request message to the fourth network element.

[0199] If the request message for requesting a model received by the third network element includes identification information of the second network element, the third network element may determine the vendor information of the second network element based on the identification information of the second network element. For example, the third network element may pre-configure a mapping relationship between the identification information of the second network element and the vendor information of the second network element.

[0200] Optionally, the request message for requesting the model received by the third network element may further include at least one of the following information: information indicating the second network element's requirement for the model, a token of the second network element, or an analysis identifier.

[0201] Optionally, the third request message may further include at least one of the following information: an analysis identifier, a model interoperability indication of the third network element, manufacturer information of the third network element, or identification information of the third network element.

[0202] For details about the token, analysis identifier and other information, please refer to the above description of the information included in the first request message in S402, which will not be elaborated here.

[0203] S702: The fourth network element determines one or more first network elements according to the vendor information of the second network element, where the model interoperability indication of the first network element includes the vendor information of the second network element.

[0204] In S702, after the fourth network element receives the third request message, if the third request message includes the identification information of the second network element, the fourth network element may determine the vendor information of the second network element based on the identification information of the second network element. In other words, the identification information of the second network element is used to determine the vendor information of the second network element. For example, the fourth network element may pre-configure a mapping relationship between the identification information of the second network element and the vendor information of the second network element. For another example, the network element registration request sent by the second network element to the fourth network element includes a mapping relationship between the identification information of the second network element and the vendor information of the second network element.

[0205] Optionally, the fourth network element may further select the first network element based on at least one of the following conditions:

[0206] Condition 1: The vendor information of the third network element is included in the model interoperability indication of the first network element.

[0207] Condition 2: The vendor information of the first network element is included in the model interoperability indication of the third network element.

[0208] If the fourth network element selects the first network element using condition 1, the embodiment of the present application does not limit the manner in which the fourth network element obtains the vendor information of the third network element. For example, the third request message may include the vendor information of the third network element. For another example, if the third request message includes identification information of the third network element, the fourth network element may pre-configure a mapping relationship between the identification information of the third network element and the vendor information of the third network element, thereby determining the vendor information of the third network element based on the identification information of the third network element.

[0209] S703. The fourth network element sends a second response message to the third network element for the third request message, where the second response message includes information about one or more first network elements.

[0210] Optionally, the information of the first network element in the second response message may include identification information of the first network element and / or address information of the first network element.

[0211] Based on the communication method provided in the embodiment of the present application, when selecting a network element for training a model, the third network element can directly discover, through the fourth network element, a first network element whose model interoperability indication includes the manufacturer information of the second network element. That is, it can directly discover the first network element that supports opening the model to the second network element, thereby ensuring that when the trained model is opened to the second network element, it is authorized by the first network element that participated in training the model. In other words, the embodiment of the present application provides a method for determining whether to open a model to a second network element, which can complete the authorization of the second network element in the network element discovery phase before training the model.

[0212] Furthermore, after receiving the second response message, the third network element can determine the first network element based on the information of the first network element therein, and thus train the model together with the first network element. After the model training is completed, the third network element can send information about the trained model (which can be called the first model) to the second network element. For example, the third network element can directly send information about the first model to the second network element based on the identifier and / or address information of the second network element included in the request message for requesting the model. Alternatively, if before S701, other network elements request a model from the third network element on behalf of the second network element, the third network element can also send information about the first model to the network element that requested the model on behalf of the second network element, and the network element will pass the information about the first model to the second network element. Specifically, the information about the first model can refer to the above introduction to the information about the first model in S401.

[0213] Optionally, the third network element may aggregate one or more models trained locally by the first network element to obtain the first model. Exemplarily, the third network element may be an FL server in a federated learning scenario, and the first network element may be an FL client in the federated learning scenario.

[0214] Assuming that the above embodiments of S701-S703 are applied to a 5G system, the second network element is an AnLF, the fourth network element is an NRF network element, the first network element is an FL client in a federated learning scenario, and the third network element is an FL server in a federated learning scenario, an exemplary process of the above embodiment can be shown in FIG8, including the following steps:

[0215] S801. AnLF subscribes to an ML model from an FL server. The subscription message includes the AnLF identifier (AnLF ID) and / or the AnLF vendor ID.

[0216] Alternatively, in another possible implementation (not shown in FIG8 ), S1001 may be as follows: AnLF subscribes to the MTLF for an ML model. MTLF determines that the federated learning mechanism is required to train the ML model, but the MTLF cannot serve as a FL server. Based on this, the MTLF further discovers an FL server to train the model. The MTLF subscribes to the ML model from the FL server, and the subscription message includes the AnLF ID and / or the AnLF vendor ID.

[0217] S802: The FL server determines that a federated learning mechanism is required to train an ML model, triggering the FL client selection process. The FL server sends a third request message to the NRF network element to request network element discovery. The third request message includes the AnLF ID and / or AnLF vendor ID, as well as the following information: the FL server's vendor ID and / or FL server ID, an analysis identifier, and the FL server's model interoperability indicator.

[0218] S803: The NRF network element determines one or more FL clients. Each FL client meets the following conditions:

[0219] The FL server's Vendor ID is included in the FL client's Model Interoperability Instruction. The FL client's Vendor ID is included in the FL server's Model Interoperability Instruction. The AnLF Vendor ID is included in the FL client's Model Interoperability Instruction.

[0220] If the third request message does not include the Vendor ID of AnLF, the NRF network element may retrieve the Vendor ID of AnLF based on the AnLF ID. If the third request message does not include the Vendor ID of FL server, the NRF network element may retrieve the Vendor ID of FL server based on the FL server ID.

[0221] S804. The NRF network element sends a second response message to the FL server. The second response message includes one or more FL client instances (including identification information of the FL client's ID and / or address) that meet the conditions and are discovered by the NRF network element.

[0222] S805 : The FL server selects a FL client based on the second response message, and trains a model with the FL client using a federated learning mechanism to obtain a final aggregated model, i.e., a first model.

[0223] S806. The FL server sends information of the first model to AnLF.

[0224] The above mainly introduces the solutions provided by the embodiments of the present application from the perspective of interaction between network elements. Accordingly, the embodiments of the present application also provide a communication device, which is used to implement the various methods described above. The communication device can be various network elements in the above method embodiments, such as the first network element, the second network element, the third network element, or the fourth network element, or a device including the above network elements, or a component that can be used for the above network elements.

[0225] It is understandable that, in order to realize the above functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0226] In the embodiment of the present application, the functional modules of the communication device can be divided according to the above method embodiment. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0227] Figure 9 shows a schematic diagram of the structure of a communication device 900. The communication device 900 includes a processing module 901 and a transceiver module 902. Optionally, the communication device 900 may also include a storage module 903. The transceiver module 902, also known as a transceiver unit, is used to implement transceiver functions and may be, for example, a transceiver circuit, a transceiver, a transceiver, or a communication interface.

[0228] Taking the communication device 900 as the first network element in the above embodiment as an example, in a possible implementation manner:

[0229] Transceiver module 902 is configured to receive a first model from a third network element. Transceiver module 902 is further configured to receive a first request message from a second network element, the first request message being used to request a model and including the vendor information of the second network element. Processing module 901 is configured to determine whether the model interoperability indication from the third network element includes the vendor information of the second network element. Transceiver module 902 is further configured to send information about the first model to the second network element if the model interoperability indication from the third network element includes the vendor information of the second network element.

[0230] Optionally, the transceiver module 902 is further configured to send a second request message to the fourth network element, the second request message being used to request a model interoperability indication from the third network element. The transceiver module 902 is further configured to receive a first response message from the fourth network element, the first response message including the model interoperability indication from the third network element.

[0231] Optionally, the transceiver module 902 is further configured to receive a model interoperability indication from a third network element.

[0232] Optionally, the transceiver module 902 is further used to send first indication information to the third network element, where the first indication information is used to indicate sending a model interoperability indication of the third network element.

[0233] Optionally, the processing module 901 is further configured to determine whether the model interoperability indication of the third network element includes the vendor information of the second network element. The transceiver module sends the information of the first model to the second network element when the model interoperability indication of the third network element includes the vendor information of the second network element, including: sending the information of the first model to the second network element when both the model interoperability indication of the third network element and the model interoperability indication of the first network element include the vendor information of the second network element.

[0234] Optionally, the processing module 901 is further configured to determine whether the model interoperability indication of one or more network elements includes the vendor information of the second network element. The transceiver module sends the first model to the second network element when the model interoperability indication of the third network element includes the vendor information of the second network element, including: when the model interoperability indication of the third network element and the model interoperability indication of the one or more network elements both include the vendor information of the second network element, sending information of the first model to the second network element.

[0235] Optionally, the transceiver module 902 is further configured to receive a model interoperability indication from one or more network elements of the third network element.

[0236] Optionally, the transceiver module 902 is further configured to send first information and second indication information to a third network element, where the first information includes the vendor information of the second network element and / or the identification information of the second network element, and the second indication information is configured to instruct the third network element to determine whether the model interoperability indication of the third network element and the model interoperability indications of multiple other network elements all include the vendor information of the second network element, wherein the identification information of the second network element is used to determine the vendor information of the second network element. The first network element then receives third indication information from the third network element, where the third indication information is configured to indicate whether the model interoperability indication of the third network element and the model interoperability indications of multiple network elements all include the vendor information of the second network element.

[0237] Taking the communication device 900 as the fourth network element in the above embodiment as an example, in a possible implementation manner:

[0238] Transceiver module 902 is configured to receive a third request message from a third network element, the third request message being used to request network element discovery and including vendor information and / or identification information of a second network element. The identification information of the second network element is used to determine the vendor information of the second network element. Processing module 901 is configured to determine one or more network elements based on the vendor information of the second network element, wherein the model interoperability indication of the one or more network elements includes the vendor information of the second network element. Transceiver module 902 is further configured to send a second response message to the third network element, the second response message including information of the one or more network elements.

[0239] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0240] Alternatively, the modules in FIG9 may also be referred to as units. For example, the processing module may be referred to as a processing unit, and the transceiver module may be referred to as a transceiver unit. In addition, in the communication device shown in FIG9 , the names of the various units may not be those shown in the figure. For example, the transceiver module may also be referred to as a communication module or a communication unit.

[0241] If the various units in Figure 9 are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The storage medium for storing computer software products includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0242] In the embodiment of the present application, the communication device 900 is presented in the form of various functional modules divided in an integrated manner. The "module" here can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions.

[0243] In a simple embodiment, those skilled in the art may appreciate that the communication device 900 may take the form of the communication device shown in FIG. 10 .

[0244] As shown in Figure 10, the communication device 1000 includes one or more processors 1001, a communication line 1002, and at least one communication interface (Figure 10 is only an example of including a communication interface 1004 and a processor 1001 for illustration), and may optionally also include a memory 1003.

[0245] The processor 1001 may be a general-purpose central processing unit (CPU), a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0246] The communication line 1002 may include a path for connecting different components.

[0247] Communication interface 1004 may be a transceiver module for communicating with other devices or communication networks, such as Ethernet, RAN, terminals, and wireless local area networks (WLANs). For example, the transceiver module may be a device such as a transceiver or a transceiver. Alternatively, communication interface 1004 may be a transceiver circuit or input / output interface within processor 1001, used to implement signal input and output to the processor.

[0248] The memory 1003 may be a device having a storage function. For example, it may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be independent and connected to the processor via a communication line 1002. The memory may also be integrated with the processor.

[0249] The memory 1003 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 1001. The processor 1001 is used to execute the computer-executable instructions stored in the memory 1003, thereby implementing the communication method provided in the embodiment of the present application.

[0250] Alternatively, optionally, in an embodiment of the present application, the processor 1001 may also perform processing-related functions in the communication method provided in the following embodiments of the present application, and the communication interface 1004 is responsible for communicating with other devices or communication networks, which is not specifically limited in the embodiments of the present application.

[0251] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.

[0252] In a specific implementation, as an embodiment, the processor 1001 may include one or more CPUs, such as CPU0 and CPU1 in FIG10 .

[0253] In a specific implementation, as an embodiment, the communication device 1000 may include multiple processors, such as the processor 1001 and the processor 1007 in Figure 10. Each of these processors may be a single-core processor or a multi-core processor. The processor here may include but is not limited to at least one of the following: a CPU, a microprocessor, a digital signal processing (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., and each computing device may include one or more cores for executing software instructions to perform calculations or processing.

[0254] In a specific implementation, as an embodiment, the communication device 1000 may further include an output device 1005 and an input device 1006. The output device 1005 communicates with the processor 1001 and can display information in a variety of ways. For example, the output device 1005 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 1006 communicates with the processor 1001 and can receive user input in a variety of ways. For example, the input device 1006 can be a mouse, a keyboard, a touch screen device, or a sensor device.

[0255] The communication device 1000 described above may sometimes also be referred to as a communication device, which may be a general-purpose device or a dedicated device. For example, the communication device 1000 may be the first network element, the second network element, or a device having a similar structure as shown in FIG10 . The embodiments of the present application do not limit the type of the communication device 1000.

[0256] In addition, the composition structure shown in Figure 10 does not constitute a limitation on the communication device. In addition to the components shown in Figure 10, the communication device 1000 may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0257] Optionally, the functions / implementation processes of the transceiver module 902 and the processing module 901 in FIG9 can be implemented by the processor 1001 in the communication device 1000 shown in FIG10 calling computer-executable instructions stored in the memory 1003. Alternatively, the functions / implementation processes of the processing module 901 in FIG9 can be implemented by the processor 1001 in the communication device 1000 shown in FIG10 calling computer-executable instructions stored in the memory 1003, and the functions / implementation processes of the transceiver module 902 in FIG9 can be implemented by the communication interface 1004 in the communication device 1000 shown in FIG10.

[0258] It should be understood that one or more of the above modules or units can be implemented by software, hardware, or a combination of the two. When any of the above modules or units is implemented in software, the software exists in the form of computer program instructions and is stored in a memory, and a processor can be used to execute the program instructions and implement the above method flow. The processor can be built into an SoC or ASIC, or it can be an independent semiconductor chip. In addition to the core used to execute software instructions to perform calculations or processing within the processor, it can further include necessary hardware accelerators, such as FPGAs, programmable logic devices (PLDs), or logic circuits that implement dedicated logic operations.

[0259] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a CPU, a microprocessor, a DSP chip, an MCU, an artificial intelligence processor, an ASIC, a SoC, an FPGA, a PLD, a dedicated digital circuit, a hardware accelerator or a non-integrated discrete device, which can run the necessary software or not rely on the software to execute the above method flow.

[0260] Optionally, an embodiment of the present application further provides a communication device (for example, the communication device may be a chip or a chip system), which includes a processor for implementing the method in any of the above method embodiments. In one possible design, the communication device also includes a memory. The memory is used to store necessary program instructions and data, and the processor can call the program code stored in the memory to instruct the communication device to execute the method in any of the above method embodiments. Of course, the memory may not be in the communication device. When the communication device is a chip system, it may be composed of a chip, or it may include a chip and other discrete devices, which is not specifically limited in the embodiment of the present application.

[0261] Optionally, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer program or instruction. When the computer program or instruction is run on a communication device, the communication device can execute the method described in any of the above method embodiments or any of its implementation methods.

[0262] Optionally, an embodiment of the present application further provides a communication system, which includes the first network element, the second network element and the third network element described in the above method embodiment.

[0263] Optionally, the communication system may further include the fourth network element described in the above method embodiment.

[0264] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more media integrated therein. The available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state drives (SSDs)).

[0265] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0266] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, the present application is intended to encompass such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

Claims

1. A communication method, characterized in that: The method comprises: The first network element receives the first model from the third network element; The first network element receives a first request message from a second network element, where the first request message is used to request a model and includes manufacturer information of the second network element; In a case where it is determined that the model interoperability indication of the third network element includes the vendor information of the second network element, the first network element sends the information of the first model to the second network element.

2. The method according to claim 1, characterized in that The first model is obtained by the third network element aggregating local models of one or more network elements.

3. The method according to claim 1 or 2, characterized in that The method further comprises: The first network element sends a second request message to the fourth network element, where the second request message is used to request a model interoperability indication from the third network element; The first network element receives a first response message from the fourth network element, where the first response message includes a model interoperability indication of the third network element.

4. The method according to claim 1 or 2, characterized in that The method further comprises: The first network element receives a model interoperability indication of the third network element from the third network element.

5. The method according to claim 4, characterized in that The method further comprises: The first network element sends first indication information to the third network element, where the first indication information is used to instruct the sending of a model interoperability indication of the third network element.

6. The method according to any one of claims 1 to 5, characterized in that When it is determined that the model interoperability indication of the third network element includes the vendor information of the second network element, the first network element sending information of the first model to the second network element includes: When it is determined that the model interoperability indication of the third network element and the model interoperability indication of the first network element both include the vendor information of the second network element, the first network element sends the information of the first model to the second network element.

7. The method according to claim 2, characterized in that When it is determined that the model interoperability indication of the third network element includes the vendor information of the second network element, the first network element sends the first model to the second network element, including: When it is determined that the model interoperability indication of the third network element and the model interoperability indication of the one or more network elements both include the vendor information of the second network element, the first network element sends the information of the first model to the second network element.

8. The method according to claim 7, characterized in that The method further comprises: The first network element receives a model interoperability indication of the one or more network elements from the third network element.

9. The method according to claim 7, characterized in that The method further comprises: The first network element sends first information and second indication information to the third network element, where the first information includes vendor information of the second network element and / or identification information of the second network element, the second indication information is used to instruct the third network element to determine whether the model interoperability indication of the third network element and the model interoperability indications of the other multiple network elements all include the vendor information of the second network element, and the identification information of the second network element is used to determine the vendor information of the second network element; The first network element receives third indication information from the third network element, where the third indication information is used to indicate whether the model interoperability indication of the third network element and the model interoperability indications of the multiple network elements both include the vendor information of the second network element.

10. The method according to claim 2, characterized in that The method further comprises: The fourth network element receives a third request message from the third network element, where the third request message is used to request network element discovery, and the third request message includes vendor information of the second network element and / or identification information of the second network element, where the identification information of the second network element is used to determine the vendor information of the second network element; The fourth network element determines the one or more network elements according to the vendor information of the second network element, where the model interoperability indication of the one or more network elements includes the vendor information of the second network element; The fourth network element sends a second response message to the third network element, where the second response message includes information of the one or more network elements.

11. A communication device, characterized in that: The device includes: a processing module and a transceiver module; The transceiver module is configured to receive the first model from the third network element; The transceiver module is further configured to receive a first request message from a second network element, where the first request message is used to request a model, and the first request message includes manufacturer information of the second network element; The processing module is configured to determine whether the model interoperability indication of the third network element includes the vendor information of the second network element; The transceiver module is further configured to send information of the first model to the second network element when the model interoperability indication of the third network element includes the manufacturer information of the second network element.

12. The device according to claim 11, characterized in that The first model is obtained by the third network element aggregating local models of one or more network elements.

13. The device according to claim 11 or 12, characterized in that The transceiver module is further configured to send a second request message to the fourth network element, where the second request message is used to request a model interoperability indication from the third network element; The transceiver module is further configured to receive a first response message from the fourth network element, where the first response message includes a model interoperability indication of the third network element.

14. The device according to claim 11 or 12, characterized in that The transceiver module is further configured to receive a model interoperability indication of the third network element from the third network element.

15. The device according to claim 14, characterized in that The transceiver module is further used to send first indication information to the third network element, where the first indication information is used to indicate sending a model interoperability indication of the third network element.

16. The device according to any one of claims 11 to 15, characterized in that The processing module is further configured to determine whether the model interoperability indication of the communication device includes the vendor information of the second network element; The transceiver module sends information of the first model to the second network element when the model interoperability indication of the third network element includes the vendor information of the second network element, including: In a case where the model interoperability indication of the third network element and the model interoperability indication of the first network element both include the vendor information of the second network element, information of the first model is sent to the second network element.

17. The device according to claim 12, characterized in that The processing module is further configured to determine whether the model interoperability indication of the one or more network elements includes the vendor information of the second network element; The transceiver module sends the first model to the second network element when the model interoperability indication of the third network element includes the vendor information of the second network element, including: In a case where the model interoperability indication of the third network element and the model interoperability indication of the one or more network elements both include the vendor information of the second network element, information of the first model is sent to the second network element.

18. The device according to claim 17, characterized in that The transceiver module is further configured to receive model interoperability indications of the one or more network elements from the third network element.

19. The device according to claim 17, characterized in that The transceiver module is further configured to send first information and second indication information to the third network element, where the first information includes the vendor information of the second network element and / or the identification information of the second network element, the second indication information is used to instruct the third network element to determine whether the model interoperability indication of the third network element and the model interoperability indications of the other multiple network elements all include the vendor information of the second network element, and the identification information of the second network element is used to determine the vendor information of the second network element; The transceiver module is further used to receive third indication information from the third network element, and the third indication information is used to indicate whether the model interoperability indication of the third network element and the model interoperability indications of the multiple network elements both include the manufacturer information of the second network element.

20. A communication device, characterized in that: The device includes: a processing module and a transceiver module; The transceiver module is configured to receive a third request message from the third network element, where the third request message is used to request discovery of a network element, the third request message including vendor information of the second network element and / or identification information of the second network element, where the identification information of the second network element is used to determine the vendor information of the second network element; The processing module is configured to determine the one or more network elements based on the vendor information of the second network element, wherein the model interoperability indication of the one or more network elements includes the vendor information of the second network element; The transceiver module is further configured to send a second response message to the third network element, where the second response message includes information about the one or more network elements.

21. A communication device, characterized in that: The communication device comprises: a processor; the processor is configured to execute a computer program or instruction stored in a memory, so that the communication device performs the method according to any one of claims 1 to 10.

22. A chip system, characterized in that: include: processor and interface circuits; The interface circuit is used to receive computer execution instructions and transmit them to the processor; The processor is configured to execute the computer-executable instructions so as to enable the communication device to perform the method according to any one of claims 1 to 10.

23. A computer-readable storage medium, characterized in that A computer program or instruction is stored thereon, which, when executed by a computer, enables the computer to perform the method according to any one of claims 1 to 10.

24. A communication system, characterized in that: The communication system includes a first network element, a second network element and a third network element; wherein the first network element is used to execute the method according to any one of claims 1 to 9.

25. The system according to claim 24, wherein: The communication system further includes a fourth network element, configured to execute the method according to claim 10.

Images