Communication method and communication apparatus

Abstract

The present application provides a communication method, comprising: a third network element sends a registration message to a second network element, wherein the registration message comprises capability information which is used for indicating that the third network element has the capabilities of storing attribute information of a model and sending the model to a device that requests the model; and the first network element sends attribute information of at least one model to the third network element, wherein the attribute information of the model comprises at least one of the following information: input parameter information of the model, output parameter information of the model, application scenario information of the model, or required resource information of the model. In a communication system, a third network element is deployed, and specific information of models is stored in the third network element, so that a consumer can obtain an appropriate model from the third network element on the basis of the specific information of the required model, and resource waste caused by unnecessary model training performed by network elements that train the models in the system can be reduced to a certain extent.

Description

Communication method and communication device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on December 29, 2023, with application number 202311871701.8 and application name “Communication Method and Communication Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communications, and more particularly, to a communication method and a communication device. Background Art

[0003] Consumers in the network can request artificial intelligence (AI) models based on analytics identify. The same analysis ID can correspond to multiple AI models, where the AI ​​model can be used for data reasoning. Specifically, the consumer can obtain information about the network data analytics function (NWDAF) that supports the analysis ID through the analysis ID, and thus select a certain NWDAF to request the AI ​​model. When there are multiple NWDAFs in the same area, and different NWDAFs can support the same analysis ID, but the AI ​​models stored in different NWDAFs are different, when the consumer obtains the candidate list of NWDAFs, it cannot be determined which NWDAF contains the requested AI model (such as AI model #1). Therefore, the consumer is likely to select an NWDAF that does not currently have AI model #1 to send a model subscription request to it. When the NWDAF receives the model subscription request, it will retrain to obtain AI model #1, resulting in a waste of network resources. Therefore, in the process of consumer requesting AI models, how to reduce the possibility of wasting network resources becomes an urgent problem to be solved. Summary of the Invention

[0004] The present application provides a communication method to achieve model management while reducing the possibility of wasting network resources.

[0005] In a first aspect, a communication method is provided, the communication method comprising: a third network element sending a registration message to a second network element, the registration message including capability information, the capability information being used to indicate that the third network element has a first capability and a second capability, the first capability being the capability of storing attribute information of a model, and the second capability being the capability of sending a model. The first network element obtains an identifier of the third network element from the second network element, the first network element sending attribute information of at least one model to the third network element, the attribute information of the model including at least one of the following information: input parameter information of the model, output parameter information of the model, scenario information of the model application, or required resource information of the model, wherein the first network element is used to obtain a model based on data training, and the second network element is used to manage network elements in the communication system.

[0006] Based on the above technical solution, a third network element capable of storing the attribute information of the model and sending the model to the device requesting the model is arranged in the communication system, so that the first network element that trains the model in the communication system stores the attribute information of the trained model in the third network element, and the stored attribute information of the model is the specific information of the model, rather than the analysis ID corresponding to the model. Therefore, when the device requesting the model (such as a consumer) requests the model, it can request the third network element to obtain the model based on the specific information of the required model, so as to obtain the appropriate model. To a certain extent, it can reduce the waste of resources caused by unnecessary model training by the network element training the model in the system.

[0007] For example, when a consumer requests a model, the request message carries the specific information of the required model (such as the attribute information of the model). The third network element locally stores the attribute information of at least one model. If the third network element locally stores the attribute information of the model required by the consumer, the third network element can provide a suitable model to the consumer instead of providing multiple NWDAF identifiers of the training model based on the analysis ID, resulting in the consumer selecting an NWDAF that currently does not have a model and sending a model subscription request to it. When the NWDAF receives the model subscription request, it will retrain the model, resulting in a waste of network resources.

[0008] In combination with the first aspect, in some implementations of the first aspect, the method also includes: the first device sends a first request message to the third network element, the first request message is used to request to obtain the first model, and the first request message includes attribute information of the first model.

[0009] Based on the above technical solution, when the first device requests a model, it carries the specific information of the required first model (such as the input parameter information of the first model, the output parameter information of the first model, the scenario information of the application of the first model, or the required resource information of the first model, etc.), so that the third network element can obtain the model required by the first device.

[0010] In combination with the first aspect, in some implementations of the first aspect, the method also includes: the third network element determines the first model based on the attribute information of the first model and the attribute information of at least one model; the third network element sends a first response message to the first device, and the first response message includes the first model or first indication information, and the first indication information is used to indicate a refusal to provide the first model.

[0011] In combination with the first aspect, in some implementations of the first aspect, the method also includes: the third network element sends a first message to the first network element, the first message includes information of the first device and first information, the first information includes an identifier of the first model and / or attribute information of the first model; the first network element determines whether the first model is authorized to the first device based on the information of the first device and the first information; the first network element sends a first confirmation message to the third network element, and the first confirmation message is used to indicate whether the first model is authorized to the first device.

[0012] Based on the above technical solution, before providing the first model to the first device, the third network element can send a first message to the first network element that trained the first model to authenticate whether the first model is authorized to the first device, thereby avoiding providing the first model to the first device without authorization.

[0013] In conjunction with the first aspect, in certain implementations of the first aspect, the registration message further includes an identifier of at least one network element, and the identifier of the at least one network element indicates the network element that stores the attribute information of the model in the third network element. The at least one network element may store the attribute information of the trained model in the third network element.

[0014] In combination with the first aspect, in some implementations of the first aspect, the registration message further includes model type information, where the model type information is used to indicate the type of the model stored in the third network element.

[0015] In a second aspect, a communication method is provided. The method may be performed by a third network element, or by a component of the third network element (eg, a chip, circuit, or chip system). This application does not limit this.

[0016] The communication method includes: sending a registration message, the registration message including capability information, the capability information being used to indicate a first capability and a second capability, the first capability being the capability of storing attribute information of a model, and the second capability being the capability of sending a model; receiving attribute information of at least one model, the attribute information of the model including at least one of the following information: input parameter information of the model, output parameter information of the model, scenario information of the model application, or required resource information of the model.

[0017] In combination with the second aspect, in some implementations of the second aspect, the method includes: receiving a first request message, the first request message is used to request acquisition of the first model, the first request message including attribute information of the first model; determining the first model based on the attribute information of the first model and attribute information of at least one model; sending a first response message, the first response message including the first model or a rejection indication, the rejection indication being used to indicate a refusal to provide the first model.

[0018] In combination with the second aspect, in some implementations of the second aspect, the method also includes: sending a first message, the first message including information of the first device and first information, the first information including an identifier of the first model and / or attribute information of the first model, the information of the first device and the first information are used to confirm whether the first model is authorized to the first device; receiving first confirmation information, the first confirmation information is used to indicate whether the first model is authorized to the first device.

[0019] In conjunction with the second aspect, in certain implementations of the second aspect, the registration message further includes an identifier of at least one network element, where the identifier of the at least one network element indicates the network element that stores the attribute information of the model in the third network element. The at least one network element may store the attribute information of the trained model in the third network element.

[0020] In combination with the second aspect, in some implementations of the second aspect, the registration message also includes model type information, and the model type information is used to indicate the type of the model stored in the third network element.

[0021] The technical effects of the method shown in the above second aspect and its possible design can refer to the technical effects in the first aspect and its possible design.

[0022] In a third aspect, a communication method is provided. The method may be performed by a first network element, or by a component of the first network element (eg, a chip, a circuit, or a chip system). This application does not limit this.

[0023] The communication method includes: receiving a first message, the first message including information of a first device and first information, the first information including an identifier of a first model and / or attribute information of the first model, the first device being a device requesting to obtain the first model, the attribute information of the first model including at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model; determining whether the first model is authorized to the first device based on the information of the first device and the first information; and sending a first confirmation message, the first confirmation message being used to indicate whether the first model is authorized to the first device.

[0024] The technical effects of the method shown in the third aspect and its possible design above can refer to the technical effects in the first aspect and its possible design.

[0025] In a fourth aspect, a communication method is provided. The method may be performed by a first device or by a component of the first device (e.g., a chip, circuit, or chip system). This application does not limit this.

[0026] The communication method includes: sending a first request message, the first request message is used to request to obtain a first model, the first request message includes attribute information of the first model, the attribute information of the first model includes at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information of the application of the first model, or required resource information of the first model; receiving a first response message, the first response message includes the first model or first indication information, the first indication information is used to indicate a refusal to provide the first model.

[0027] In combination with the fourth aspect, in certain implementations of the fourth aspect, the method further includes: sending a second request message, the second request message is used to request to obtain the identifier of the third network element, the second request message carries capability information, the capability information is used to indicate the acquisition of the third network element having a first capability and a second capability, the first capability is the capability to store model attribute information, and the second capability is the capability to send the model; receiving the identifier of the third network element.

[0028] The technical effects of the method shown in the above fourth aspect and its possible design can refer to the technical effects in the first aspect and its possible design.

[0029] In a fifth aspect, a communication method is provided, which includes: a fourth network element sends a second message to a fifth network element, wherein the second message includes attribute information of a first model, and the attribute information of the first model includes at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model; the fifth network element determines the first model based on the attribute information of the first model and attribute information of at least one model stored locally; the fifth network element sends a third message to the first network element, wherein the third message includes information of the first device and first information, and the first information includes an identifier of the first model and / or attribute information of the first model, the first device is a device requesting to obtain the first model, and the first network element is a training The network element of the first model; the first network element determines whether the first model is authorized to the first device based on the information of the first device and the first information; the first network element sends a second confirmation message to the fifth network element, and the second confirmation message is used to indicate whether the first model is authorized to the first device; if the second confirmation information indicates that the first model is not authorized to the first device, the fifth network element sends a second indication information to the fourth network element, and the second indication information is used to indicate a refusal to provide the first model; or, if the second confirmation information indicates that the first model is authorized to the first device, the fifth network element sends the first model to the fourth network element, wherein the first network element is used to obtain a model based on data training, the fourth network element is used to send the model to the device requesting the model, and the fifth network element is used to store attribute information of the model.

[0030] Based on the above technical solution, when the fourth network element requests the first model from the fifth network element, it carries the specific information of the first model (such as the input parameter information of the first model, the output parameter information of the first model, the scenario information of the application of the first model, or the required resource information of the first model, etc.), so that the fifth network element can know the specific model requested and provide a suitable model, instead of providing multiple NWDAF identifiers of the training model based on the analysis ID, which causes the consumer to select an NWDAF that currently does not have a model and send a model subscription request to it. When the NWDAF receives the model subscription request, it will retrain the model, resulting in a waste of network resources.

[0031] In addition, the fifth network element can authenticate to the first network element that trained the first model through the third message whether the first model is authorized to the first device, so as to avoid providing the first model to the first device without authorization.

[0032] A sixth aspect provides a communication method,

[0033] The communication method includes: a fourth network element sends a second message to a fifth network element, wherein the second message includes attribute information of a first model, and the attribute information of the first model includes at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model; the fifth network element determines the first model according to the attribute information of the first model and attribute information of at least one model stored locally; the fifth network element sends information of the first network element to the fourth network element, and the first network element is the network element for training the first model; the fourth network element sends a fourth message to the first network element, and the fourth message includes information of the first device information and first information, the first information including the identifier of the first model and / or the attribute information of the first model, the first device is a device requesting to obtain the first model; the first network element determines whether the first model is authorized to the first device based on the information of the first device and the first information; the first network element sends the first model, the address information of the first model, or the third indication information to the fourth network element, the third indication information is used to indicate the refusal to provide the first model, and the address information of the first model is used to obtain the first model, wherein the first network element is used to obtain the model based on data training, the fourth network element is used to send the model to the device requesting the model, and the fifth network element is used to store the attribute information of the model.

[0034] Based on the above technical solution, when the fourth network element requests the first model from the fifth network element, it carries the specific information of the first model (such as the input parameter information of the first model, the output parameter information of the first model, the scenario information of the application of the first model, or the required resource information of the first model, etc.), so that the fifth network element can know the specific model requested and provide a suitable model, instead of providing multiple NWDAF identifiers of the training model based on the analysis ID, which causes the consumer to select an NWDAF that currently does not have a model and send a model subscription request to it. When the NWDAF receives the model subscription request, it will retrain the model, resulting in a waste of network resources.

[0035] In addition, the fifth network element provides the fourth network element with information about the first network element that trained the first model, so that the fourth network element can authenticate to the first network element that trained the first model through a fourth message whether the first model is authorized to the first device, thereby avoiding providing the first model to the first device without authorization.

[0036] In combination with the fifth aspect or the sixth aspect, in some implementations of the fifth aspect or the sixth aspect, the fourth network element and the first device are jointly arranged, or the communication system also includes the first device, and the method further includes: the first device sends a third request message to the fourth network element, the third request message is used to request to obtain the first model, and the third request message includes attribute information of the first model; the fourth network element sends a second response message to the first device, and the second response message includes the first model or information indicating a refusal to provide the first model.

[0037] Based on the above technical solution, if the first device and the fourth network element are not installed together, the first device carries the specific information of the required first model (such as the input parameter information of the first model, the output parameter information of the first model, the scenario information of the application of the first model, or the required resource information of the first model, etc.) during the process of requesting the model, so that subsequent network elements can obtain the model required by the first device.

[0038] In a seventh aspect, a communication method is provided. The method can be performed by a fourth network element, or by a component of the fourth network element (eg, a chip, a circuit, or a chip system). This application does not limit this.

[0039] The communication method includes: sending a second message, wherein the second message includes attribute information of the first model, and the attribute information of the first model includes at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model; receiving a fifth message, wherein the fifth message includes the first model, address information of the first model, or information indicating a refusal to provide the first model, and the address information of the first model is used to obtain the first model.

[0040] In combination with the seventh aspect, in certain implementations of the seventh aspect, receiving the fifth message specifically includes: receiving information of the first network element, the first network element is the network element for training the first model; sending a fourth message to the first network element, the fourth message including information of the first device and the first information, the first information including an identifier of the first model and / or attribute information of the first model, the first device is a device requesting to obtain the first model; receiving the fifth message from the first network element.

[0041] In combination with the seventh aspect, in some implementations of the seventh aspect, the method further includes: receiving a third request message, the third request message being used to request acquisition of the first model, the third request message including attribute information of the first model; and sending a second response message, the second response message including the first model or information indicating a refusal to provide the first model.

[0042] In combination with the seventh aspect, in certain implementations of the seventh aspect, when the fifth message includes the address information of the first model, the method also includes: receiving fourth indication information; sending the fourth indication information to the fifth network element indicated by the address information of the first model, and the fourth indication information is used to verify the acquisition of the first model.

[0043] The technical effects of the method shown in the above seventh aspect and its possible design can refer to the technical effects in the fifth aspect or sixth aspect and its possible design.

[0044] In an eighth aspect, a communication method is provided. The method may be performed by a fifth network element, or by a component of the fifth network element (eg, a chip, a circuit, or a chip system). This application does not limit this.

[0045] The communication method includes: receiving a second message, wherein the second message includes attribute information of a first model, the attribute information of the first model includes at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model; determining the first model based on the attribute information of the first model and attribute information of at least one model stored locally.

[0046] In combination with the eighth aspect, in some implementations of the eighth aspect, the method also includes: sending a third message, the third message including information of the first device and first information, the first information including an identifier of the first model and / or attribute information of the first model, the first device is a device requesting to obtain the first model, and the first network element is a network element for training the first model; receiving a second confirmation message, the second confirmation message is used to indicate whether the first model is authorized to the first device; if the second confirmation information indicates that the first model is not authorized to the first device, sending second indication information, the second indication information is used to indicate a refusal to provide the first model; or, if the second confirmation information indicates that the first model is authorized to the first device, sending the first model.

[0047] The technical effects of the method shown in the above eighth aspect and its possible design can refer to the technical effects in the fifth aspect or sixth aspect and its possible design.

[0048] In a ninth aspect, a communication device is provided. The communication device is configured to execute the second aspect and any one of its embodiments. Specifically, the communication device includes a processor and a memory, the memory being configured to store a computer program; the processor being configured to retrieve and execute the computer program from the memory, causing the communication device to execute the first aspect and any one of its embodiments.

[0049] In one implementation, when the communication device is a third network element, the transceiver unit may be a transceiver or an input / output interface. The processing unit may be at least one processor. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0050] In another implementation, the communication device may be a chip, chip system, or circuit in a third network element. In this case, the transceiver unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; and the processing unit may be at least one processor, processing circuit, or logic circuit.

[0051] In a tenth aspect, a communication device is provided. The communication device is configured to execute the third aspect and any one of its embodiments. Specifically, the communication device includes a processor and a memory, the memory being configured to store a computer program; the processor being configured to retrieve and execute the computer program from the memory, causing the network device to execute the third aspect and any one of its embodiments.

[0052] In one implementation, when the communication device is a first network element, the transceiver unit may be a transceiver or an input / output interface. The processing unit may be at least one processor. Optionally, the transceiver may be a transceiver circuit. Optionally, the input / output interface may be an input / output circuit.

[0053] In another implementation, the communication device may be a chip, chip system, or circuit in the first network element. In this case, the transceiver unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; and the processing unit may be at least one processor, processing circuit, or logic circuit.

[0054] In an eleventh aspect, a communication device is provided. The communication device is configured to implement the fourth aspect and any one of its embodiments. Specifically, the communication device includes a processor and a memory, the memory being configured to store a computer program; the processor being configured to retrieve and execute the computer program from the memory, causing the network device to implement the fourth aspect and any one of its embodiments.

[0055] In one implementation, when the communication apparatus is a first device, the transceiver unit may be a transceiver or an input / output interface. The processing unit may be at least one processor. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0056] In another implementation, the communication device may be a chip, chip system, or circuit in the first device. In this case, the transceiver unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; and the processing unit may be at least one processor, processing circuit, or logic circuit.

[0057] In a twelfth aspect, a communication device is provided. The communication device is configured to implement the seventh aspect and any one of its embodiments. Specifically, the communication device includes a processor and a memory, the memory being configured to store a computer program; the processor being configured to retrieve and execute the computer program from the memory, causing the network device to implement the seventh aspect and any one of its embodiments.

[0058] In one implementation, when the communication device is a fourth network element, the transceiver unit may be a transceiver or an input / output interface. The processing unit may be at least one processor. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0059] In another implementation, the communication device may be a chip, chip system, or circuit in the fourth network element. In this case, the transceiver unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; and the processing unit may be at least one processor, processing circuit, or logic circuit.

[0060] In a thirteenth aspect, a communication device is provided. The communication device is configured to implement the eighth aspect and any one of its embodiments. Specifically, the communication device includes a processor and a memory, the memory being configured to store a computer program; the processor being configured to retrieve and execute the computer program from the memory, causing the network device to implement the eighth aspect and any one of its embodiments.

[0061] In one implementation, when the communication device is a fifth network element, the transceiver unit may be a transceiver or an input / output interface. The processing unit may be at least one processor. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0062] In another implementation, the communication device may be a chip, chip system, or circuit in the fifth network element. In this case, the transceiver unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; and the processing unit may be at least one processor, processing circuit, or logic circuit.

[0063] In a fourteenth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed, the method of any one of the implementation modes of the first to eighth aspects is executed.

[0064] In a fifteenth aspect, a computer program product comprising instructions is provided, which, when executed, causes the method provided in any one of the implementations of the first to eighth aspects to be executed.

[0065] In the sixteenth aspect, a chip is provided, which includes a processor and a communication interface. The processor reads instructions through the communication interface and executes the method provided by any one of the implementation methods of the first to eighth aspects above.

[0066] Optionally, as an implementation method, the chip also includes a memory, the memory stores a computer program or instructions, and the processor is used to execute the computer program or instructions stored in the memory. When the computer program or instructions are executed, the processor is used to execute the method provided in any one of the implementation methods of the first to eighth aspects above.

[0067] In the seventeenth aspect, a communication system is provided, comprising a first network element, a second network element and a third network element.

[0068] In an eighteenth aspect, a communication system is provided, comprising a first network element, a fourth network element and a fifth network element.

[0069] In a nineteenth aspect, a computer program is provided. When the computer program is executed, the method provided in any one of the implementations of the first to eighth aspects is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] FIG1 is a schematic diagram of a network architecture 100 provided in this application.

[0071] FIG2 is a schematic flowchart of a communication method provided in an embodiment of the present application.

[0072] FIG3 is a schematic flowchart of another communication method provided in an embodiment of the present application.

[0073] FIG4 is a schematic flowchart of another communication method provided in an embodiment of the present application.

[0074] FIG5 is a schematic block diagram of a communication device 10 provided in an embodiment of the present application.

[0075] FIG6 is a schematic diagram of another communication device 20 provided in an embodiment of the present application.

[0076] FIG7 is a schematic diagram of a chip system 30 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] In order to facilitate understanding of the embodiments of the present application, the following points are first explained.

[0078] First, in this application, "used to indicate" can include being used for direct indication and being used for indirect indication. When describing that a certain indication information is used to indicate A, it can include that the indication information directly indicates A or indirectly indicates A, but it does not mean that the indication information must carry A.

[0079] The information indicated by the indication information is called the 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, directly indicating the information to be 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 there is an association between the other information and the information to be indicated. 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, it is also possible to use the arrangement order of each piece of information agreed in advance (such as specified in the protocol) to achieve the indication of specific information, thereby reducing the indication overhead to a certain extent. At the same time, it is also possible to identify the common parts of each piece of information and indicate them uniformly to reduce the indication overhead caused by indicating the same information separately.

[0080] Second, "at least one" shown in the present application refers to one or more, and "a plurality of" refers to two or more. In addition, in the embodiments of the present application, "first", "second" and various digital numbers (for example, "#1", "#2", etc.) are only for the convenience of description and are not used to limit the scope of the embodiments of the present application. The size of the sequence number of each process below does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. It should be understood that the objects described in this way can be interchanged where appropriate, so as to be able to describe solutions other than the embodiments of the present application. In addition, in the embodiments of the present application, words such as "S210" are only for the convenience of description and are not used to limit the order of execution of steps.

[0081] Third, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0082] Fourth, the term "storage" used in the embodiments of this application may refer to storage in one or more memories. The one or more memories may be provided separately or integrated into an encoder or decoder, a processor, or a communication device. The one or more memories may also be partially provided separately and partially integrated into a decoder, a processor, or a communication device. The type of memory may be any form of storage medium, and this application is not limited thereto.

[0083] Fifth, in the implementation of this application, "protocol" may refer to a standard protocol in the field of communications, for example, it may include the NR protocol and related protocols used in future communication systems, and this application does not limit this.

[0084] Sixth, in the embodiments of the present application, the terms “of”, “corresponding, relevant”, “corresponding” and “associate” can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings they intend to express are consistent.

[0085] Seventh, in the embodiments of the present application, "under the circumstances", "when", and "if" can sometimes be used interchangeably. It should be pointed out that when the distinction between them is not emphasized, the meanings they intend to express are consistent.

[0086] Eighth, the term "and / or" in this document simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0087] The technical solution in this application will be described below with reference to the accompanying drawings.

[0088] The technical solutions provided in this application can be applied to various communication systems, such as new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0089] In a communication system, the part operated by an operator may be referred to as a public land mobile network (PLMN), or an operator network, etc. PLMN is a network established and operated by the government or an operator approved by it for the purpose of providing land mobile communication services to the public. It is mainly a public network in which mobile network operators (MNOs) provide mobile broadband access services to users. The PLMN described in the embodiments of the present application may specifically be a network that complies with the requirements of the 3GPP standard, referred to as a 3GPP network. 3GPP networks generally include but are not limited to 5G networks, fourth-generation mobile communication (4G) networks, and other future communication systems, such as next-generation communication networks.

[0090] For the convenience of description, the embodiments of the present application will be described using PLMN or 5G network as an example.

[0091] Figure 1 is a schematic diagram of a network architecture 100 provided in this application, taking the 5G network architecture based on a service-oriented architecture in a non-roaming scenario as defined in the 3GPP standardization process as an example. As shown in the figure, the network architecture can be composed of three parts: a terminal device part (such as the user equipment (UE) shown in Figure 1), a data network (DN), and a carrier network (PLMN). The functions of the network elements in each part are briefly described below.

[0092] The terminal device part may include a terminal device, which may also be referred to as a UE. The terminal device in this application is a device with wireless transceiver functions, which can communicate with one or more core network (CN) devices via an access network device (or also referred to as an access device) in a radio access network (RAN). The terminal device may also be referred to as an access terminal, terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, user agent or user device, etc. The terminal device may be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it may also be deployed on the water (such as a ship, etc.); it may also be deployed in the air (such as an airplane, balloon and satellite, etc.). The terminal device may be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a smart phone, a mobile phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), etc. Alternatively, the terminal device may also be a handheld device with wireless communication capabilities, a computing device, or other device connected to a wireless modem, an in-vehicle device, a wearable device, a drone device, or a terminal in the Internet of Things, the Internet of Vehicles, a terminal of any form in a 5G network and future networks, a relay user device, or a terminal in a future evolved communication network, etc. Among them, the relay user device may be, for example, a 5G residential gateway (RG). For example, the terminal device may be a virtual reality (VR) terminal, an augmented reality (AR) 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 wireless terminal in a smart home, etc. The terminal device here refers to a 3GPP terminal. The embodiments of the present application do not limit the type or category of the terminal device. For ease of explanation, this application will be described below using UE as an example to refer to a terminal device.

[0093] The operator network PLMN part may include but is not limited to the (radio) access network ((R)AN) and the core network (CN).

[0094] (R)AN can be regarded as a sub-network of the operator network, and is an implementation system between the service node and the terminal device in the operator network. To access the operator network, the terminal device must first pass through the (R)AN, and then connect to the service node of the operator network through the (R)AN. The access network device (RAN device) in the embodiment of the present application is a device that provides wireless communication functions for the terminal device, and can also be called a network device. The RAN device includes but is not limited to: the next generation node base station (gNB) in the 5G system, the evolved node B (eNB) in the long term evolution (LTE), the radio network controller (RNC), the node B (NB), the base station controller (BSC), the base transceiver station (BTS), the home base station (for example, home evolved node B, or home node B, HNB), the base band unit (BBU), the transmission point (TRP), the transmitting point (TP), the small base station device (pico), the mobile switching center, or the network equipment in the future network. In systems using different wireless access technologies, the names of devices that function as access network devices may vary. For ease of description, in all embodiments of this application, the aforementioned devices that provide wireless communication functions for terminal devices are collectively referred to as access network devices, or simply RAN or AN. It should be understood that this document does not limit the specific types of access network devices.

[0095] In some deployments, the (R)AN may include a centralized unit (CU) and a distributed unit (DU). The CU implements some of the gNB's functionality, while the DU implements some of the gNB's functionality. For example, the CU is responsible for processing non-real-time protocols and services, implementing the functions of the radio resource control (RRC) and packet data convergence protocol (PDCP) layers. The DU is responsible for processing physical layer protocols and real-time services, implementing the functions of the radio link control (RLC), media access control (MAC), and physical (PHY) layers. It is understood that the (R)AN 120 may include one or more of the following: a CU node and a DU node.

[0096] In addition, the CU may be classified as a network device in an access network (radio access network, RAN), or may be classified as a network device in a core network (core network, CN), which is not limited in this application.

[0097] 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, the radio access network may also be an open radio access network (O-RAN) architecture. In the ORAN system, 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. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0098] The CN part may include but is not limited to the following NFs: user plane function (UPF), network exposure function (NEF), network function repository function (NRF), policy control function (PCF), unified data management function (UDM), unified data repository function (UDR), network data analytics function (NWDAF), access and mobility management function (AMF), session management function (SMF), analytics data repository function (ADRF), or operations, administration and management (OAM) equipment (i.e., network management).

[0099] A DN, also known as a packet data network (PDN), is typically a network located outside of a carrier network, such as a third-party network. Of course, in some implementations, a DN can also be deployed by a carrier, meaning that the DN is part of a PLMN. This application does not restrict whether a DN is a PLMN. A carrier network PLMN can access multiple data network DNs, on which multiple services can be deployed, providing data and / or voice services to terminal devices. For example, a data network DN can be the private network of a smart factory. Sensors installed in the workshop of the smart factory can be terminal devices. A control server for the sensors is deployed in the data network DN, and the control server can provide services to the sensors. The sensors can communicate with the control server, receive instructions from the control server, and transmit collected sensor data to the control server according to the instructions. For another example, a data network DN can be a company's internal office network. The company's employees' mobile phones or computers can be terminal devices, allowing them to access information and data resources on the company's internal office network. Terminal devices can establish a connection to the carrier network through interfaces provided by the carrier network (such as N1) and use the data and / or voice services provided by the carrier network. The terminal device can also access the data network DN through the operator network, use the operator services deployed on the data network DN, and / or services provided by a third party.

[0100] The following is a brief description of the NF functions included in the network architecture 100.

[0101] 1. The UPF is a gateway provided by the operator, serving as the gateway for communication between the operator network and the data network (DN). UPF network functions include packet routing and transmission, packet inspection, service usage reporting, Quality of Service (QoS) processing, lawful interception, uplink packet inspection, downlink packet storage, and other user-plane-related functions.

[0102] 2. NEF is a control plane function provided by the operator. It mainly enables third parties to use the services provided by the network, supports the network to open its capabilities, event and data analysis, provides PLMN security configuration information from external applications, and converts interactive information inside and outside the PLMN. It provides an API interface open to the operator network and provides interaction between external servers and internal operator networks.

[0103] 3. NRF is a control plane function provided by the operator, which can be used to maintain real-time information about network functions and services in the network. For example, it supports network service discovery, maintains the services supported by the NF profile of the NF instance, supports service discovery of the service communication proxy (SCP), maintains the SCP profile of the SCP instance, sends notifications about newly registered, deregistered, and updated NFs and SCPs, and maintains the health status of NF and SCP operations.

[0104] In this application, NRF can provide the certificate management network element with the number of available network elements corresponding to different network element types in a certain area through network service discovery or network service subscription process. The functions of NRF will be explained with specific examples below, which will not be repeated here.

[0105] 4. PCF is a control plane function provided by the operator. It supports a unified policy framework to govern network behavior, provide policy rules to other control functions, and provide contract information related to policy decisions.

[0106] 5. The UDM is a control plane function provided by the operator and is responsible for storing information such as the subscriber permanent identifier (SUPI), the generic public subscription identifier (GPSI), and credentials of subscribers in the operator network. The SUPI is first encrypted during transmission, and the encrypted SUPI is called the hidden subscriber subscription identifier (SUCI). This information stored by the UDM network function 134 can be used to authenticate and authorize the terminal device 110 to access the operator network. The subscribers of the operator network can specifically be users who use services provided by the operator network, such as users who use China Telecom's subscriber identity module (SIM) cards or China Mobile's SIM cards. The subscriber's credentials can be a small file storing long-term keys stored in the SIM card or information related to SIM card encryption, used for authentication and / or authorization. It should be noted that the permanent identifier, credentials, security context, authentication data (cookie), and token are equivalent to information related to verification / authentication and authorization. For the sake of convenience in the embodiments of this application, no distinction or limitation is made.

[0107] 6. UDR is a control plane function provided by the operator. It provides the UDM with the function of storing and retrieving subscription data, the PCF with the function of storing and retrieving policy data, and the user's NF group ID information.

[0108] 7. NWDAF is a network data analysis function provided by operators. Its main function is to collect data from NF, external application function AF, and OAM equipment, analyze the data, and provide data analysis results to NF and AF.

[0109] In this application, the NWDAF provides data analysis for the 5G core network (5G core, 5GC) NF and OAM. For example, the 5GC NF or OAM can request network data analysis results from the NWDAF. After receiving the request, the NWDAF collects data from relevant network elements and trains an AI model. Finally, the AI ​​model is used to perform data inference and feedback the inference results to the corresponding 5GC NF or OAM.

[0110] Specifically, NWDAF can be divided into NWDAF that supports model training logical function (MTLF) (which can be abbreviated as NWDAF (MTLF) or MTLF) and NWDAF that supports analysis logical function (AnLF) reasoning (which can be abbreviated as NWDAF (AnLF) or AnLF). Among them, AnLF can request AI model information from MTLF for data reasoning.

[0111] In addition, one or more NWDAFs can be deployed in the same PLMN domain.

[0112] 8. OAM refers to the division of network management tasks into three categories based on the actual needs of carrier network operations: operations, administration, and maintenance. Operations primarily involve the analysis, forecasting, planning, and configuration of daily network and service operations; maintenance primarily involves daily operational activities such as testing and troubleshooting the network and its services.

[0113] 9. AMF is a control plane network function provided by the operator network, responsible for access control and mobility management of terminal devices accessing the operator network, such as mobile state management, allocation of user temporary identity, authentication and authorization of users, etc.

[0114] 10. SMF is a control plane network function provided by the operator network, responsible for managing the PDU session of the terminal device. A PDU session is a channel for transmitting PDUs. The terminal device needs to transmit PDUs to and from the data network DN through the PDU session. The SMF is responsible for establishing, maintaining, and deleting PDU sessions. The SMF includes session management (such as session establishment, modification, and release, including tunnel maintenance between the user plane function UPF and the (R)AN), selection and control of the UPF network function 130, service and session continuity (SSC) mode selection, roaming, and other session-related functions.

[0115] 11. AF is a control plane network function provided by the operator network. It is used to provide application layer information. It can interact with the policy framework through network open function elements or directly interact with the policy framework to make policy decision requests. It can be located inside or outside the operator network.

[0116] 12. ADRF provides services that allow consumers to store and retrieve historical data (from various network elements) and analysis results (from NWDAF). Users can request or subscribe to the data storage (retrieval) services provided by ADRF through interfaces (such as Nadrf). When a user uses the request operation, ADRF directly responds with the corresponding results. When a user uses the subscription operation, if the corresponding purpose is to store data, ADRF subscribes to the analysis results or data from NWDAF and provides a notification address. Otherwise, ADRF continuously responds to the consumer network element notification address included in the subscription.

[0117] It is understood that the above network elements or functions can be physical entities in hardware devices, software instances running on dedicated hardware, or virtualized functions instantiated on a shared platform (e.g., a cloud platform). Simply put, an NF can be implemented by hardware or software.

[0118] In Figure 1, Nnef, Nnrf, Npcf, Nudm, Nudr, Nnwdaf, Namf, Nsmf, N2, N3, N4, and N6 are interface serial numbers. For example, the meaning of the above interface serial numbers can be found in the meaning defined in the 3GPP standard protocol, and this application does not limit the meaning of the above interface serial numbers. It should be noted that the interface name between the various network functions in the figure is only an example. In a specific implementation, the interface name of the system architecture may also be other names, which is not limited by this application. In addition, the name of the message (or signaling) transmitted between the above network elements is only an example and does not constitute any limitation on the function of the message itself.

[0119] For ease of explanation, in the embodiments of this application, network functions (such as NEFs...SMFs) are collectively referred to as NFs. That is, the NFs described later in the embodiments of this application can be replaced with any network function. Furthermore, Figure 1 only schematically illustrates some network functions, and the NFs described later are not limited to the network functions shown in Figure 1.

[0120] It should be understood that the above-mentioned network architecture applied to the embodiment of the present application is only a network architecture described from the perspective of service-oriented architecture. The network architecture applicable to the embodiment of the present application is not limited to this. Any network architecture that can realize the functions of the above-mentioned network elements is applicable to the embodiment of the present application.

[0121] It should also be understood that the AMF, SMF, UPF, NEF, NWDAF, NRF, PCF, UDM, etc. shown in the figure can be understood as network elements for implementing different functions, for example, they can be combined into network slices as needed. These core network elements can be independent devices or integrated into the same device to implement different functions. This application does not limit the specific form of the above network elements.

[0122] The network element types involved in the following embodiments may be: network elements may be divided into different network element types according to functions, deployment locations, or home domains. For example, division by service function may include division into the aforementioned SMF, AMF, UPF, NWDAF, and other network element types; division by deployment location may include division into access network elements or non-access network elements; and division by home domain may include division into visited network elements or home network elements.

[0123] For example, network elements belonging to different network element types provide different services. For example, network elements belonging to AMF are responsible for access control and mobility management of terminal devices accessing the operator network; for example, network elements belonging to SMF are responsible for managing PDU sessions of terminal devices.

[0124] It should be understood that during the service certificate update process, a large number of certificates may be updated simultaneously, and the certificate update process may cause the corresponding network elements to be unavailable. In particular, if network elements providing the same service in the network update their certificates at the same time, the network will be unable to provide the corresponding service. For example, if all AMFs in the network perform service certificate updates, there will be no available AMFs in the network.

[0125] It should also be understood that the above naming is defined only to facilitate the distinction between different functions and should not constitute any limitation to this application. This application does not exclude the possibility of adopting other naming in 5G networks and other future networks. For example, in future communication networks, some or all of the above network elements may continue to use 5G terminology, or may adopt other names.

[0126] To facilitate understanding of the embodiments of the present application, some basic concepts involved in the present application are briefly explained.

[0127] 1. AI Model: AI is an interdisciplinary and emerging discipline based on computer science, integrating multiple disciplines such as computer science, psychology, and philosophy. It studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. It attempts to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. The AI ​​models involved in this application can be understood as models that can implement different functions through AI technology. For example, AI models can be used for data reasoning, including but not limited to signal processing, signal generation, or channel estimation.

[0128] The "model" referred to below in this application includes an AI model or other model that can implement data analysis or data reasoning. This application does not impose any restrictions on the name of the model.

[0129] 2. Analytics Identification: This can be referred to as an analytics ID. The same analytics ID can correspond to multiple models. For example, a consumer on the network can request a model based on the analytics ID.

[0130] For example, analysis ID #1 corresponds to model #1, and analysis ID #2 corresponds to models #2 and #3. If a consumer requests the model corresponding to analysis ID #2, it can be understood that the model required by the consumer is model #2 or model #3.

[0131] 3. Model Attribute Information: In this application, model attribute information refers to information used to identify a model, specifically specific information about the model. For example, the attribute information of model #1 indicates model #1, and the attribute information of model #2 indicates model #2. Model attribute information may also be referred to as model parameter information, model selection information, or other terms, which are not detailed here.

[0132] As an example and not a limitation, the attribute information of the model in this application includes the following aspects:

[0133] 1) ML model filter information, for example, the model filter information includes at least one of an area of ​​interest (AOI), single network slice selection assistance information (S-NSSAI), or a network element type (NF type), wherein AOI indicates the area of ​​interest corresponding to the model, S-NSSAI indicates the network slice information corresponding to the model, and NF type indicates the network element type to which the network element corresponding to the model belongs.

[0134] 2) Model accuracy requirement information (ML model accuracy threshold), which is used to indicate the accuracy requirement of the model. For example, the accuracy requirement information of model #1 indicates that the accuracy of data analysis based on model #1 is 60%.

[0135] 3) ML model target period information, which indicates the time period during which the model can be applied. For example, the ML model target period information indicates that the target time period for model #1 application is T1 to T2.

[0136] 4) ML model target area information, which indicates the area where the model can be applied. For example, the target area information of model #1 indicates that the target area of ​​model #1 is urban area A.

[0137] 5) Model interoperability information (ML model interoperability information), used to indicate whether the model supports interoperability. Mainly used in model or operation sharing scenarios, model interoperability information includes model format, model execution environment and other information. For example, different manufacturers' models are trained on different model platforms and in different model formats. When manufacturer 1 requests a model from manufacturer 2, it needs to carry this information to inform manufacturer 2 of the model information it needs.

[0138] 6) Model input parameter information, used to indicate the model's input parameters. For example, when the model's input parameter types are used in the same application scenario for different models (such as positioning models), they can all be used for positioning in the same area or slice. However, due to different model input parameters, different models are used. Therefore, this parameter is used to determine the required model.

[0139] 7) Model output parameter information, used to indicate the model's output parameters. For example, the model's output parameter type. Similar to the model input information described above, different models may have different outputs in the same scenario.

[0140] 8) Model resource requirements: This refers to the resource requirements (e.g., required hardware and software resources) of the model requested by the consumer. This can also be referred to as model size information. For example, if a consumer determines that it can only run models under 1GB (i.e., models requiring less than 1GB of resources) based on the platform's model capabilities, this parameter can prevent the requested model from being unable to run on the consumer's platform.

[0141] 9) Model application scenario information, used to indicate the scenarios in which the model can be applied.

[0142] It should be understood that the above 1) to 9) are merely examples of possible forms of model attribute information in this application and do not constitute any limitation on the scope of protection of this application. Other information that can indicate a specific model is also within the scope of protection of this application. For example, the attribute information of the model also includes information about the analysis object corresponding to the model.

[0143] Specifically, different models have different attribute information. For example, the attribute information for AI model #1 includes usage time #1, analysis object #1, or accuracy #1, while the attribute information for AI model #2 includes usage time #2, analysis object #2, or accuracy #2. Usage time #1 and usage time #2 are different, analysis object #1 and analysis object #2 are different, and accuracy #1 and accuracy #2 are different.

[0144] 4. Model Management: NWDAF (e.g., NWDAF(MTLF)) manages models based on analysis IDs. Specifically, current model management technologies support model management at the analysis ID level. For example, when multiple NWDAFs exist within the same area and each supports the same analysis ID, the model information stored in each NWDAF may differ.

[0145] As an example and not a limitation, when NWDAF manages models based on analysis IDs, it stores the following information associated with the AI ​​model:

[0146] Analysis ID, model filtering information, model interoperability indicator, etc.

[0147] 5. Model Configuration Management Function (MCMF): This is a logical function used to configure and manage AI models. MCMF can be set up as a single network element or in conjunction with other network elements (e.g., with the consumer, NWDAF (AnLF), AMF, ADRF, etc.). This application does not limit this.

[0148] The above briefly introduces the application scenarios of the communication method provided in the embodiment of the present application in conjunction with Figure 1, and introduces the basic concepts that may be involved in the embodiment of the present application. In the basic concepts, the AI ​​model and analysis ID are introduced. One way for a user to request an AI model is to request an AI model from the NRF based on the analysis ID. The way for a user to request an AI model includes the following steps:

[0149] Step 1: The user sends a network element discovery request message to the NRF. The network element discovery request message includes an analysis ID and at least one of the following information:

[0150] Model filtering information, model interoperability instructions, user information, or NWDAF capability information, etc.

[0151] Among them, the filtering information of the model includes the area of ​​interest (AOI) and / or single network slice selection assistance information (S-NSSAI), AOI indicates the area of ​​interest of the requested analysis ID, and S-NSSAI indicates the network slice information corresponding to the requested analysis ID; the model interoperability indication is used to indicate whether the interoperability scenario is supported; user information is mainly used for the model interoperability request scenario; NWDAF capability information is used to indicate the capabilities of NWDAF, such as whether federated learning (FL), accuracy check, or roaming exchange capability are supported.

[0152] Step 2: After receiving the network element discovery request, the NRF can check the NWDAF that supports the analysis ID.

[0153] However, in this implementation, NRF cannot view the specific model information under the analysis ID.

[0154] Step 3: NRF sends the list of candidate NWDAFs corresponding to the analysis ID to the user.

[0155] It should be understood that under this implementation, the user cannot find the information of the NWDAF that stores the required model during the network element discovery phase. There is a possibility of selecting an NWDAF that does not have the model but supports the analysis ID, which causes the NWDAF to initiate repeated training of the model and thus waste network resources.

[0156] Another way for a user to request an AI model is to request an AI model from ADRF based on the analysis ID. This method includes the following steps:

[0157] Step 1: The user sends a model retrieval request message to ADRF. The model retrieval request message includes the analysis ID and at least one of the following information:

[0158] Filter information of the model or information about the target NWDAF that subscribes to the model.

[0159] Step 2: ADRF confirms whether the model is stored in ADRF.

[0160] If the ADRF confirms that the model is not stored in the ADRF, the ADRF sends a network element discovery request to the NRF, requesting to discover the NWDAF (MTLF), and sends a model subscription request or model retraining request to the NWDAF (MTLF). The NWDAF (MTLF) sends the trained model to the ADRF.

[0161] Step 3: ADRF then sends the obtained model to the user.

[0162] In addition, in this implementation, the user can also obtain the updated model. For example, the method in which the user requests the AI ​​model also includes the following steps:

[0163] Step 4: The user subscribes to model updates from ADRF, and ADRF returns the updated model.

[0164] Furthermore, in this implementation, the user may cancel the process of obtaining the subscription model. For example, the method of requesting the AI ​​model by the user further includes the following steps:

[0165] Step 5: The user notifies ADRF to cancel the model subscription.

[0166] It should be understood that in this implementation, the consumer bypasses MTLF and directly requests the model from ADRF, which will lead to model authorization issues, because ADRF is only a model storage network element, not the model's owning network element. The current protocol stipulates that the model trainer MTLF should decide whether to assign the model to the consumer. ADRF cannot directly pass the model to the consumer instead of NWDAF.

[0167] In order to solve the problems existing in the above-mentioned two methods of requesting AI models, the present application provides a communication method to achieve the management of AI models while reducing the possibility of wasting network resources.

[0168] The technical solutions provided by this application will be described in detail below with reference to the accompanying drawings. The embodiments of this application can be applied to a variety of different scenarios, including the scenario shown in FIG1 , but are not limited to this scenario. For example, they can also be applied to 5G, next-generation communication systems, or future communication systems.

[0169] It should be understood that the embodiments shown below do not particularly limit the specific structure of the execution subject of the method provided by the embodiments of the present application. As long as it is possible to communicate according to the method provided by the embodiments of the present application by running a program that records the code of the method provided by the embodiments of the present application, for example, the execution subject of the method provided by the embodiments of the present application can be a receiving device or a sending device, or a functional module in the receiving device or the sending device that can call and execute the program.

[0170] Below, without loss of generality, the communication method provided in the embodiment of the present application is described in detail by taking the interaction between network elements as an example.

[0171] FIG2 is a schematic flow chart of a communication method provided by the present application, comprising the following steps:

[0172] S210, the third network element sends a registration message to the second network element, and correspondingly, the second network element receives the registration message from the third network element.

[0173] In this embodiment, the third network element is a network element that stores model attribute information and sends the model to the device requesting the model, such as the MCMF described above; the second network element is a network element that has network element management functions, such as the NRF described above. It should be understood that in this embodiment, there is no limitation on the names of the network elements, and any network element that can implement the corresponding functions is within the scope of protection of this application.

[0174] Specifically, the registration information includes capability information, where the capability information is used to indicate that the third network element has a first capability and a second capability, where the first capability is the ability to store attribute information of the model, and the second capability is the ability to send the model (e.g., the ability to send the model to the device requesting the model). For example, the capability information is used to indicate that the third network element has a model management capability (ML model management capability).

[0175] Exemplarily, the registration information may further include an identifier of at least one network element, the identifier of the at least one network element being used to indicate that the attribute information of the model is stored in at least one third network element, i.e., the third network element is used to manage the model trained by the at least one network element. Optionally, the registration information includes a supported MTLF identifier (supported NWDAF (MTLF) ID), indicating which MTLFs the third network element supports the management of models trained in. When multiple MTLFs train models in the system, and only some of the MTLFs register the attribute information of their trained models with the third network element, the third network element supports the configuration and management of the models in these MTLFs. For example, the registration information includes the ID of MTLF#1 and the ID of MTLF#2. If the models trained by MTLF#1 include Model#1 and Model#2, and the models trained by MTLF#2 include Model#3 and Model#4, the third network element supports the configuration and management of the models trained by MTLF#1 and MTLF#2 (e.g., Model#1, Model#2, Model#3, and Model#4).

[0176] Exemplarily, the registration information may further include model type information (ML model category), which is used to indicate the type of model managed by the third network element. For example, the model type information indicates that the categories of models supported by the third network element include but are not limited to positioning models, perception models, etc.

[0177] As a possible implementation method, the third network element in this embodiment can be a network element independently deployed in the communication system, and can communicate with other network elements in the system (such as the second network element, the third network element, etc.) through a service interface.

[0178] As another possible implementation, the third network element in this embodiment can be integrated with existing network elements in the communication system, so that the existing network elements in the system can implement the functions of the third network element in this embodiment, which is equivalent to enhancing the performance of the existing network elements. For example, the third network element can be integrated with a localization management function (LMF) network element; for another example, the third network element can also be integrated with an AMF / SMF network element, etc., which will not be explained here one by one.

[0179] When the third network element and the existing network element are jointly set up, the third network element sending a registration message can be understood as the process of the existing network element sending a registration message. The difference is that the registration message includes information indicating the newly added functions of the existing network element, that is, the above-mentioned capability information.

[0180] Furthermore, the second network element sends a registration success message to the third network element, and the method flow shown in FIG2 further includes:

[0181] S220, the second network element sends a registration success message to the third network element, and correspondingly, the third network element receives the registration success message from the second network element.

[0182] It should be understood that the third network element in this embodiment is capable of storing the attribute information of the model and sending the model to the device requesting the model. Therefore, after the network element for training the model in the communication system in this embodiment (such as the first network element) trains the model, the attribute information of the model can be stored in the third network element.

[0183] It should be noted that, in this embodiment, the third network element can store the attribute information of the model trained by one or more network elements used to train the model. For example, the above-mentioned registration message carries the identifier of at least one network element, indicating that the third network element can store the attribute information of the model trained by the at least one network element; or, for example, the above-mentioned registration message does not carry the identifier of the network element, indicating that the third network element can store the attribute information of the model trained by all network elements in the system.

[0184] For ease of description, the following description is given by taking the example of the first network element storing the attribute information of the trained model in the third network element. The method flow shown in FIG2 also includes:

[0185] S230: The first network element sends attribute information of at least one model to the third network element. Correspondingly, the third network element receives attribute information of at least one model from the first network element.

[0186] Specifically, the first network element may train at least one model, and attribute information of the at least one model may be stored in the third network element. The first network element then sends the attribute information of each of the at least one model to (or registers with) the third network element. For example, the first network element uses a model management registration service to store the attribute information of each of the at least one model trained by the first network element in the third network element.

[0187] The attribute information of each model can refer to the description of the attribute information of the model in the basic concepts above, which will not be repeated here. For example, the attribute information of each model includes at least one of the following information: the input parameter information of the model, the output parameter information of the model, the scenario information of the model application, or the required resource information of the model.

[0188] In addition, it should be noted that if the registration message includes model type information, the first network element also needs to consider the model type when sending the model attribute information to the third network element. For example, the first network element uses the model management registration service to store the attribute information of at least one trained model corresponding to the model type indicated by the model type information in the third network element.

[0189] In this embodiment, the third network element locally stores attribute information of a model obtained by at least one network element, and in this embodiment, the third network element can send the model to the device requesting the model. Therefore, when the first device decides to request the model, the first device can obtain information about the third network element from the second network element in order to initiate a process of obtaining the model to the third network element. The method process shown in FIG2 further includes:

[0190] S231: The first device sends a second request message to the second network element. Correspondingly, the second network element receives the second request message from the first device.

[0191] Specifically, the second request message is used to request a network element that has the capability to store the attribute information of the model and send the model to the device requesting the model. For example, the second request message includes capability information (ML model management capability), and the capability information is used to indicate the acquisition of a third network element that has a first capability and a second capability, where the first capability is the capability to store the attribute information of the model and the second capability is the capability to send the model.

[0192] Optionally, the second request message may further include network element type information #1 and / or area information #1. The network element type information #1 indicates the network element type to which the network element requested by the first device belongs, such as if the network element type information #1 is MCMF; and the area information #1 indicates the area supported by the network element requested by the first device, such as if the area information #1 is AOI #1.

[0193] S232, the second network element sends the identifier of the third network element to the first device, and correspondingly, the first device receives the identifier of the third network element from the second network element.

[0194] Exemplarily, in this embodiment, after the second network element receives the second request message, the selected network elements that meet the requirements may include at least one, and the identifier of the third network element returned by the second network element to the first device may be identifiers of multiple third network elements.

[0195] For example, if the second network element determines that the third network elements that meet the requirements include third network element #1 and third network element #2, the second network element can provide both the identifier of third network element #1 and the identifier of third network element #2 to the first device. After the first device receives the identifiers of multiple third network elements, it can send a first request message to multiple different third network elements in sequence (or simultaneously, or in other ways) to obtain a first model.

[0196] For ease of description, this embodiment is described by taking an example in which the first device receives an identifier of a third network element from the second network element and sends a first request message to the third network element.

[0197] S240: The first device sends a first request message to the third network element. Correspondingly, the third network element receives the first request message from the first device.

[0198] Specifically, the first request message is used to request the acquisition of the first model. The first request message includes attribute information of the first model. For the attribute information of the first model, reference can be made to the description of the attribute information of the model in the basic concepts above, and no further description is given here. For example, the attribute information of the first model includes at least one of the following information:

[0199] Input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model.

[0200] Exemplarily, the first request message also includes indication information of the first device, where the indication information of the first device refers to information of the first device itself. For example, the indication information of the first device may be an identifier of the first device. For example, if the first device is a terminal device, the indication information of the first device may be identification information such as a globally unique temporary identifier (GUTI) or a subscription permanent identifier (SUPI) of the terminal device. For example, if the first device is an AnLF, the indication information of the first device may be identification information such as the operator information of the AnLF.

[0201] S250: The third network element determines the first model.

[0202] Specifically, the third network element determines the first model according to the attribute information of the first model and the attribute information of at least one model stored locally.

[0203] For example, the third network element locally stores attribute information of model #1, attribute information of model #2, attribute information of model #3, ..., attribute information of model #N. If the attribute information of the first model received by the third network element matches the attribute information of model #1 among the locally stored attribute information of at least one model, the third network element determines that the first model is model #1, wherein the attribute information of the first model matches the information of model #1, which can be understood as the attribute information of the first model being the same or substantially the same as the information of model #1.

[0204] S260, the third network element sends a first response message to the first device, and correspondingly, the first device receives the first response message from the third network element.

[0205] In this embodiment, after the third network element determines the first model, it may provide it to the first device through a first response message. Alternatively, if the third network element does not determine the first model, the first response message may include first indication information, which is used to indicate that the first model is rejected.

[0206] Optionally, when the first response message carries the first indication information, the first response message may further carry a reason value, where the reason value indicates that the first model has not been determined.

[0207] Furthermore, before providing the first model to the first device, the third network element may confirm with the first network element that trained the first model whether the first model can be provided to the first device. The method flow shown in FIG2 may further include:

[0208] S251, the third network element sends a first message to the first network element, and correspondingly, the first network element receives the first message from the third network element.

[0209] In this embodiment, the third network element can further determine that the network element that trains the first model is the first network element based on the determined first model. For example, the third network element locally stores information of the first network element that trains the first model. Therefore, after the third network element determines the first model, the third network element can determine that the network element that trains the first model is the first network element.

[0210] Specifically, the first message includes information of the first device and first information, the first information includes an identifier of the first model and / or attribute information of the first model, and the information of the first device and the first information are used by the first network element to confirm whether the first model is authorized to the first device.

[0211] Exemplarily, the information of the first device refers to the information of the first device itself. For example, the information of the first device can be an identifier of the first device. The third network element can send the indication information of the first device received from the first request message to the first network element through the first message, so that the first network element can determine that the device requesting the first model is the first device based on the indication information of the first device; or, the information of the first device can be information indicating the first device determined by the third network element based on the indication information of the first device carried in the first request message. In this embodiment, no limitation is imposed on the information of the first device, and all information that can be used to identify the first device is within the scope of protection of this application.

[0212] Exemplarily, the first information is information indicating the first model. For example, the third network element may send the attribute information of the first model received from the first request message to the first network element through the first message, so that the first network element may determine the first model required by the first device based on the attribute information of the first model; or, after determining the first model, the third network element may send the identifier (identify, ID) of the first model to the first network element through the first message, so that the first network element may determine the first model required by the first device based on the identifier of the first model.

[0213] Optionally, the first message is a model subscription request message.

[0214] S252: The first network element determines whether the first model is authorized to the first device.

[0215] Specifically, the first network element determines whether the first model is authorized to the first device according to the first information and the information of the first device included in the received first message.

[0216] For example, the first network element determines that the model required by the first device is the first model based on the first information, and the first model can be authorized to the first device (for example, the first network element determines the device that the first model can authorize during the process of training the first model); for another example, the first network element determines that the model required by the first device is the first model based on the first information, and the first model cannot be authorized to the first device.

[0217] S253, the first network element sends first confirmation information to the third network element, and correspondingly, the third network element receives the first confirmation information from the first network element.

[0218] The first confirmation information is used to indicate whether the first model is authorized to the first device.

[0219] When the first confirmation information received by the third network element indicates that the first model can be authorized to the first device, the third network element may provide the first model to the first device through the above-mentioned first response message; or,

[0220] When the first confirmation information received by the third network element indicates that the first model cannot be authorized to the first device, the third network element may send first indication information to the first device via the above-mentioned first response message, where the first indication information is used to indicate that provision of the first model is refused. Optionally, the first indication information may carry a reason value, where the reason value is used to indicate the reason for refusal to provide the first model, such as indicating that the first device is a device that cannot obtain the first model.

[0221] As can be seen from the above, in the communication method shown in Figure 2, a third network element with the ability to store model attribute information and send the model to the device requesting the model is deployed in the communication system, so that the first network element that trains the model in the communication system stores the attribute information of the trained model in the third network element, and the stored attribute information of the model is the specific information of the model, rather than the analysis ID corresponding to the model. Therefore, when the device requesting the model (such as a consumer) requests the model, it can request the third network element to obtain the model based on the specific information of the required model, so as to obtain the appropriate model. To a certain extent, it can reduce the waste of resources caused by unnecessary model training by the network element training the model in the system.

[0222] In addition, in the process of providing the first model, the third network element can request the first network element that trained the first model to determine whether to authorize the first model to the first device based on the information of the first model and the information of the first device, thereby improving security and preventing unauthorized devices from obtaining the model.

[0223] The present application also provides another communication method, which carries the specific information of the required model during the process of requesting the model, thereby avoiding, to a certain extent, the retraining of the model caused by the consumer selecting a network element that does not have the required model to request the model. The communication method will be described in detail below in conjunction with Figure 3.

[0224] FIG3 is a schematic flow chart of a communication method provided by the present application, comprising the following steps:

[0225] S310, the fourth network element sends a second message to the fifth network element, and correspondingly, the fifth network element receives the second message from the fourth network element.

[0226] In this embodiment, the fourth network element is a network element having a model management function (e.g., a function of sending a model to a device requesting a model), such as the MCMF described above; the second network element is a data analysis and storage network element, such as the ADRF described above. It should be understood that in this embodiment, there is no limitation on the names of the network elements, and network elements that can implement the corresponding functions are within the scope of protection of this application.

[0227] Specifically, the second message is used to request a query for the first model. The second message includes attribute information of the first model. For the attribute information of the first model, reference can be made to the description of the attribute information of the model in the basic concepts above, and will not be repeated here. For example, the attribute information of the first model includes at least one of the following information:

[0228] Input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model.

[0229] Exemplarily, the second message also includes information of the first device, where the first device is the device that actually requests to obtain the first model. In this embodiment, the fourth network element can be combined with the first network element. For example, the first device is AnLF, and the AnLF is functionally enhanced so that the AnLF has the function of the fourth network element in this embodiment; or,

[0230] The fourth network element is an independently deployed functional network element; or the fourth network element can be jointly set up with the AMF / SMF serving the first device.

[0231] The information of the first device refers to information about the first device. For example, the information of the first device may be an identifier of the first device. For example, if the first device is a terminal device, the information of the first device may be identifier information such as the GUTI or SUPI of the terminal device. For another example, if the first device is an AnLF, the information of the first device may be identifier information such as the AnLF operator information.

[0232] Optionally, the second message may be a model query request message (ML model search request).

[0233] In this embodiment, the premise that the fourth network element can send the second message to the fifth network element is that the fourth network element obtains the fifth network element information from the second network element. The method flow shown in FIG3 further includes:

[0234] S311, the fourth network element sends message #1 to the second network element, and correspondingly, the second network element receives message #1 from the fourth network element.

[0235] Exemplarily, the second network element is a functional network element for managing network element information, such as the NRF shown above.

[0236] Specifically, the message #1 is used to request the second network element to provide a fifth network element with model storage capability. The message #1 includes the following information:

[0237] Network element type information #2, capability information #2, and area information #2. Network element type information #2 indicates the network element type to which the fourth network element requests, e.g., network element type information #2 is ADRF; capability information 2 indicates the capabilities of the network element requested by the fourth network element, e.g., capability information #2 indicates a network element with ML model storage capability; and area information #2 indicates the area supported by the network element requested by the fourth network element, e.g., area information #2 is AOI #2.

[0238] Furthermore, in this embodiment, after receiving the above-mentioned message #1, the second network element selects a network element that meets the requirements and returns the identifier of the network element that meets the requirements to the fourth network element. The method flow shown in FIG3 further includes:

[0239] S312 , the second network element sends the identifier of the fifth network element to the fourth network element. Correspondingly, the fourth network element receives the identifier of the fifth network element from the second network element.

[0240] Exemplarily, in this embodiment, after the second network element receives message #1, the selected network elements that meet the requirements may include at least one, and the identifier of the fifth network element returned by the second network element to the fourth network element may be identifiers of multiple fifth network elements.

[0241] For example, if the second network element determines that the fifth network elements that meet the requirements include the fifth network element #1 and the fifth network element #2, the second network element can provide both the identifier of the fifth network element #1 and the identifier of the fifth network element #2 to the fourth network element. After the fourth network element receives the identifiers of multiple fifth network elements, it can send the above-mentioned second message to multiple different fifth network elements in sequence (or simultaneously, or in other ways) to obtain the first model.

[0242] For ease of description, this embodiment is described by taking an example in which the fourth network element receives an identifier of a fifth network element from the second network element and sends a first message to the fifth network element.

[0243] Furthermore, in this embodiment, after receiving the second message, the fifth network element may determine the first model based on the attribute information of the first model carried in the second message and the attribute information of at least one model stored locally. The method flow shown in FIG3 further includes:

[0244] S320: The fifth network element determines the first model.

[0245] Specifically, the fifth network element determines the first model according to the attribute information of the first model and the attribute information of at least one model stored locally.

[0246] For example, the fifth network element locally stores attribute information of model #1, attribute information of model #2, attribute information of model #3, ..., attribute information of model #N. If the attribute information of the first model received by the fifth network element matches the information of model #1 in the attribute information of at least one model stored locally, the fifth network element determines that the first model is model #1, wherein the attribute information of the first model matches the information of model #1, which can be understood as the attribute information of the first model being the same or substantially the same as the attribute information of model #1.

[0247] In this embodiment, after the fifth network element determines the first model, it may determine whether to provide the first model to the first device through the following two possible implementations:

[0248] As a possible implementation manner, the fifth network element determines, through the first network element, whether the first model can be provided to the first device.

[0249] In this implementation, the method shown in FIG3 further includes the following steps:

[0250] S321. The fifth network element sends a third message to the first network element. Correspondingly, the first network element receives the third message from the fifth network element.

[0251] In this embodiment, the first network element is the network element that trains the first model. For example, the first network element is NWDAF (MTLF). In this embodiment, the fifth network element can determine that the network element that trains the first model is the first network element based on the attribute information of at least one model stored locally. The specific method for determining the first network element is not detailed here.

[0252] Specifically, the third message includes information of the first device and the first information, the first information includes an identifier of the first model and / or information of the first model, and the information of the first device and the first information are used by the first network element to confirm whether the first model is authorized to the first device.

[0253] Optionally, the third message is a model subscription request message.

[0254] Optionally, the fifth network element may send the attribute information of the first model received from the second message to the first network element through a third message, so that the first network element may determine the first model required by the first device based on the information of the first model; or, after determining the first model, the fifth network element may send the identifier (identify, ID) of the first model to the first network element through a third message, so that the first network element may determine the first model required by the first device based on the identifier of the first model.

[0255] S322: The first network element determines whether the first model is authorized to the first device.

[0256] Specifically, the first network element may determine whether the first model is authorized to the first device based on the information of the first device and the first information. For example, the first network element determines, based on the first information, that the model required by the first device is the first model, and that the first model can be authorized to the first device (e.g., the first network element determines, during the process of training the first model, that the first model can be authorized to the device); for another example, the first network element determines, based on the first information, that the model required by the first device is the first model, and that the first model cannot be authorized to the first device.

[0257] S323, the first network element sends second confirmation information to the fifth network element, and correspondingly, the fifth network element receives the second confirmation information from the first network element.

[0258] The second confirmation information is used to indicate whether the first model is authorized to the first device.

[0259] S324. The fifth network element sends the first model or the second indication information to the fourth network element.

[0260] When the second confirmation information received by the fifth network element indicates that the first model can be authorized to the first device, the fifth network element may provide the first model to the fourth network element.

[0261] When the second confirmation information received by the fifth network element indicates that the first model cannot be authorized to the first device, the fifth network element may send second indication information to the fourth network element, where the second indication information is used to indicate that provision of the first model is refused. Optionally, the second indication information may carry a reason value, where the reason value is used to indicate a reason for refusal to provide the first model, such as indicating that the first device is a device that cannot obtain the first model.

[0262] As another possible implementation manner, the fourth network element determines, through the first network element, whether the first model can be provided to the first device.

[0263] In this implementation, the method shown in FIG3 further includes the following steps:

[0264] S331 , the fifth network element sends information of the first network element to the fourth network element. Correspondingly, the fourth network element receives information of the first network element from the fifth network element.

[0265] Optionally, the fifth network element may carry the information of the first network element (eg, the ID of the first network element) in a response message (eg, a model query result message) in response to the first message.

[0266] Exemplarily, the model query result message may further include an identifier of the first model and / or result information, where the identifier of the first model is used to indicate the first model determined by the fifth network element, and the result information is used to indicate whether the fifth network element has successfully determined the first model. For example, if the result information indicates success, it indicates that the fifth network element has successfully determined the first model; for example, if the result information indicates failure, it indicates that the fifth network element has failed to determine the first model.

[0267] S332, the fourth network element sends a fourth message to the first network element, and correspondingly, the first network element receives the fourth message from the fourth network element.

[0268] The fourth message is used to request the first model, and the fourth message includes information about the first device and the first information, where the first information includes an identifier of the first model and / or information about the first model. Optionally, if the model query result message received by the fourth network element from the fifth network element in step S331 includes the identifier of the first model, the first information may include the identifier of the first model.

[0269] S333: The first network element determines whether the first model is authorized to the first device.

[0270] Step S333 can refer to the description of the above step S322 and will not be repeated here.

[0271] S334, the first network element sends a response message #1 to the fourth network element. Correspondingly, the fourth network element receives the response message #1 from the first network element.

[0272] Response message #1 includes at least one of the following information:

[0273] The first model, the address information of the first model, or third indication information, wherein the third indication information is used to indicate a refusal to provide the first model, and the address information of the first model is used to obtain the first model.

[0274] When the first network element determines that the first model can be authorized to the first device, the response message #1 includes the first model or address information of the first model. The address information of the first model is used to obtain the first model. For example, the address information of the first model includes the address (Uniform Resource Locator (URL)) of the first model in the fifth network element.

[0275] When the first network element determines that the first model can be authorized for the first device, the response message #1 includes third indication information. Optionally, the third indication information may carry a reason value, where the reason value is used to indicate the reason for refusing to provide the first model, such as indicating that the first device is a device that cannot obtain the first model.

[0276] Exemplarily, if the first response message includes the address information of the first model including the URL of the first model in the fifth network element, the first response message may further include first indication information, where the first indication information is used to indicate whether the first model can be obtained from the fifth network element. For example, the first indication information is token information for obtaining the first model in the fifth network element, where the token information obtained in the fifth network element is allocated by the first network element when the model is stored, and is sent to the fifth network element when the model is stored, and is stored by the fifth network element as credential information for obtaining the model.

[0277] S335: The fourth network element obtains the first model.

[0278] As a possible implementation manner, if the response message #1 carries the first model, the fourth network element can directly obtain the first model from the response message #1.

[0279] As another possible implementation, if the response message #1 carries the address information of the first model, the fourth network element may obtain the first model based on the address information of the first model. For example, if the address information of the first model is a URL, the fourth network element may directly download the first model from the URL.

[0280] As can be seen from the above, the fourth network element can obtain the first model from the fifth network element or the first network element. In this embodiment, the fourth network element can be co-located with the first device, or the fourth network element can be deployed independently, or the fourth network element can be co-located with the AMF or SMF serving the first device.

[0281] As a possible implementation method, if the fourth network element and the first device are installed together, the steps performed by the fourth network element can be understood as steps performed by the first device, and the fourth network element can be understood as a functional enhancement of the first device.

[0282] As a possible implementation, if the fourth network element is deployed independently, then in this implementation, the method flow shown in FIG3 further includes:

[0283] S301: A first device sends a message #2 to a second network element. Correspondingly, the second network element receives the message #2 from the first device.

[0284] Specifically, the message #2 is used by the second network element to provide the fourth network element with model management capabilities. The message #2 includes the following information:

[0285] Network element type information #3, capability information #3, and area information #3. Network element type information #3 indicates the network element type to which the network element requested by the first device belongs, e.g., network element type information #3 is MCMF; capability information #3 indicates the capabilities of the network element requested by the first device, e.g., capability information #3 indicates a network element with model management capability (ML model management capability); and area information #3 indicates the area supported by the network element requested by the first device, e.g., area information #3 is AOI #3.

[0286] Furthermore, in this embodiment, after receiving the above-mentioned message #2, the second network element selects a network element that meets the requirements and returns the identifier of the network element that meets the requirements to the first device. The method flow shown in FIG3 further includes:

[0287] S302: The second network element sends an identifier of a fourth network element to the first device. Correspondingly, the first device receives the identifier of the fourth network element from the second network element.

[0288] Exemplarily, in this embodiment, after the second network element receives message #2, the selected network elements that meet the requirements may include at least one, and the identifier of the fourth network element returned by the second network element to the first device may be identifiers of multiple fourth network elements.

[0289] For example, if the second network element determines that the fourth network elements that meet the requirements include fourth network element #1 and fourth network element #2, the second network element can provide both the identifier of the fourth network element #1 and the identifier of the fourth network element #2 to the first device. After the first device receives the identifiers of multiple fourth network elements, it can send a third request message to multiple different fourth network elements in sequence (or simultaneously, or in other ways) to obtain the first model.

[0290] For ease of description, this embodiment is described by taking an example in which the first device receives an identifier of a fourth network element from the second network element and sends a third request message to the fourth network element.

[0291] S303: The first device sends a third request message to the fourth network element. Correspondingly, the fourth network element receives the third request message from the first device.

[0292] The third request message is used to request to obtain the first model. The third request message includes indication information of the first device and attribute information of the first model.

[0293] In addition, in this implementation, after the fourth network element obtains the above-mentioned first model, the address information of the first model, or the information indicating refusal to provide the first model, the obtained first model, the address information of the first model, or the information indicating refusal to provide the first model can be provided to the first device through a second response message. The method shown in Figure 3 further includes:

[0294] S304: The fourth network element sends a second response message to the first device. Correspondingly, the first device receives the second response message from the fourth network element.

[0295] Specifically, the second response message includes the first model or information indicating refusal to provide the first model (such as the second indication information or the third indication information mentioned above).

[0296] As another possible implementation, if the fourth network element and the AMF or SMF serving the first device are jointly set up, then in this implementation, the method flow shown in Figure 3 also includes the above-mentioned steps S303 and S304.

[0297] It should be noted that if the fourth network element is deployed independently or the fourth network element is jointly deployed with the AMF or SMF serving the first device, the fourth network element can request the fifth network element to obtain models for multiple devices that need to obtain models. For example, the second message includes information about at least one device, and the first device is one of the at least one devices.

[0298] Exemplarily, when the fourth network element and the AMF or SMF serving the first device are jointly established, when the first device requests the first model through the AMF or SMF serving the first device, the first device can send a third request message to the AMF or SMF through a registration request or a PDU session request message, and the AMF or SMF obtains the first model required by the first device by sending a model query request message to the fifth network element. It should be understood that the AMF or SMF can carry information of at least one device when sending a model query request message, which is used to indicate which devices the model query request is for. Among them, when the AMF or SMF receives model requests from multiple devices, it will merge, classify, etc. the multiple model requests, and carry information of multiple devices (such as UE ID list) in the model query request message sent to the fifth network element.

[0299] In addition, the fourth network element and the fifth network element mentioned above can also be combined into a sixth network element. For example, the fifth network element (such as ADRF) is functionally enhanced so that the fifth network element has the function of the fourth network element in this embodiment. When the fourth network element and the fifth network element are combined, the signaling interaction between the fourth network element and the fifth network element in the communication method shown in Figure 3 above can be omitted. The steps performed by the fourth network element and the fifth network element are implemented by the sixth network element. The specific process is shown in Figure 4 below:

[0300] FIG4 is a schematic flow chart of a communication method provided by the present application. The sixth network element is a network element formed by combining the fourth network element and the fifth network element in FIG3 , and has the functions of the fourth network element and the fifth network element. Specifically, the sixth network element includes the following steps:

[0301] S410, the first device sends message #3 to the second network element, and correspondingly, the second network element receives message #3 from the first device.

[0302] Specifically, the message #3 is used by the second network element to provide the sixth network element with model management capability and model storage capability. The message #3 includes the following information:

[0303] Network element type information #4, capability information #4, and area information #4. Network element type information #4 indicates the network element type to which the network element requested by the first device belongs, e.g., network element type information #4 is ADRF; capability information #4 indicates the capabilities possessed by the network element requested by the first device, e.g., capability information #4 indicates a network element with model management capability (ML model management capability) and model storage capability (ML model storage capability); and area information #4 indicates the area supported by the network element requested by the first device, e.g., area information #4 is AOI #4.

[0304] S420: The second network element sends the identifier of the sixth network element to the first device. Correspondingly, the first device receives the identifier of the sixth network element from the second network element.

[0305] Exemplarily, in this embodiment, after the second network element receives message #3, the selected network elements that meet the requirements may include at least one, and the identifier of the sixth network element returned by the second network element to the first device may be identifiers of multiple sixth network elements.

[0306] For example, if the second network element determines that the sixth network element that meets the requirements includes the sixth network element #1 and the sixth network element #2, the second network element can provide both the identifier of the sixth network element #1 and the identifier of the sixth network element #2 to the first device. After the first device receives the identifiers of multiple sixth network elements, it can send a third request message to multiple different sixth network elements in sequence (or simultaneously, or in other ways) to obtain the first model.

[0307] For ease of description, this embodiment is described by taking an example in which the first device receives an identifier of a sixth network element from the second network element and sends a third request message to the sixth network element.

[0308] S430: The first device sends a third request message to the sixth network element. Correspondingly, the sixth network element receives the third request message from the first device.

[0309] The third request message is used to request to obtain the first model. The third request message includes indication information of the first device and attribute information of the first model.

[0310] For example, the attribute information of the first model can refer to the description of the attribute information of the model in the basic concepts above, which will not be repeated here. For example, the attribute information of the first model includes at least one of the following information:

[0311] Input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model.

[0312] Exemplarily, the indication information of the first device refers to information of the first device. For example, the indication information of the first device may be an identifier of the first device. For example, if the first device is a terminal device, the indication information of the first device may be identifier information such as the GUTI or SUPI of the terminal device. For another example, if the first device is an AnLF, the indication information of the first device may be identifier information such as the operator information of the AnLF.

[0313] S440: The sixth network element determines the first model.

[0314] Specifically, the sixth network element determines the first model according to the attribute information of the first model and the attribute information of at least one model stored locally.

[0315] For example, the sixth network element locally stores attribute information of model #1, attribute information of model #2, attribute information of model #3, ..., attribute information of model #N. If the attribute information of the first model received by the sixth network element matches the information of model #1 in the locally stored attribute information of at least one model, the sixth network element determines that the first model is model #1, wherein the attribute information of the first model matches the information of model #1, which can be understood as the attribute information of the first model being the same or substantially the same as the attribute information of model #1.

[0316] S450, the sixth network element sends a third message to the first network element. Correspondingly, the first network element receives the third message from the sixth network element.

[0317] Refer to the description of step S321 above, which will not be repeated here. The difference is that in this embodiment, the sixth network element has the functions of the fourth network element and the fifth network element above.

[0318] S460: The first network element determines whether the first model is authorized to the first device.

[0319] Please refer to the description of step S322 above, which will not be repeated here.

[0320] S470 , the first network element sends second confirmation information to the sixth network element. Correspondingly, the sixth network element receives the second confirmation information from the first network element.

[0321] Please refer to the description of step S323 above, which will not be repeated here.

[0322] S480, the sixth network element sends a second response message to the first device, and correspondingly, the first device receives the second response message from the sixth network element.

[0323] Please refer to the description of step S304 above, which will not be repeated here.

[0324] In the communication method shown in Figures 3 and 4 above, in the process of requesting the first model, specific information of the first model (such as the input parameter information of the first model, the output parameter information of the first model, the scenario information of the application of the first model, or the required resource information of the first model, etc.) is carried so that the fifth network element can know the specific model requested and provide a suitable model, instead of providing multiple NWDAF identifiers of the training model based on the analysis ID, resulting in the consumer selecting an NWDAF that currently does not have a model and sending a model subscription request to it. When the NWDAF receives the model subscription request, it will retrain the model, resulting in a waste of network resources.

[0325] In addition, the first network element that trains the first model can be authenticated to determine whether the first model is authorized to the first device, thereby preventing the first model from being provided to the first device without authorization.

[0326] It should be understood that the size of the serial numbers of the above processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0327] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0328] It should also be understood that in some of the above embodiments, devices in existing network architectures are primarily used as examples for illustrative purposes. It should be understood that the present embodiments do not limit the specific form of the devices. For example, devices that can achieve the same functions in the future are applicable to the present embodiments.

[0329] It can be understood that in the above-mentioned method embodiments, the methods and operations implemented by the device (such as the first network element, the second network element, the third network element, the fourth network element, the fifth network element, or the sixth network element, etc.) can also be implemented by components that can be used in the device (such as chips or circuits).

[0330] It can also be understood that some optional features in the various embodiments of the present application may not depend on other features in certain scenarios, and may also be combined with other features in certain scenarios, without limitation.

[0331] The communication method provided in the embodiments of the present application is described in detail above with reference to Figures 2 to 4. The communication method is mainly described from the perspective of a network element. It is understood that in order to implement the above functions, the network element includes hardware structures and / or software modules corresponding to the execution of each function.

[0332] Those skilled in the art should be aware 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 performed 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.

[0333] The communication device provided in the embodiment of the present application is described in detail below with reference to Figures 5 to 7. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment. Therefore, for matters not described in detail, reference can be made to the method embodiment above. For the sake of brevity, some contents are not repeated here.

[0334] In the embodiment of the present application, the functional modules of the transmitting device or the receiving device can be divided according to the above method example. 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. There may be other division methods in actual implementation. The following is an example of dividing each functional module according to each function.

[0335] Figure 5 is a schematic block diagram of a communication device 10 provided in an embodiment of the present application. The device 10 includes a transceiver module 11 and a processing module 12. The transceiver module 11 can implement corresponding communication functions, and the processing module 12 is used to process data. In other words, the transceiver module 11 is used to perform operations related to receiving and sending, while the processing module 12 is used to perform operations other than receiving and sending. The transceiver module 11 can also be referred to as a communication interface or a communication unit.

[0336] Optionally, the device 10 may further include a storage module 13, which may be used to store instructions and / or data. The processing module 12 may read the instructions and / or data in the storage module so that the device implements the actions of the devices in the aforementioned method embodiments.

[0337] In one design, the apparatus 10 may correspond to the third network element in the above method embodiment, or be a component (such as a chip) of the third network element.

[0338] The device 10 can implement steps or processes corresponding to those executed by the third network element in the above method embodiment, wherein the transceiver module 11 can be used to perform operations related to transceiver transmission of the third network element in the above method embodiment, and the processing module 12 can be used to perform operations related to processing of the third network element in the above method embodiment.

[0339] In one possible implementation, transceiver module 11 is configured to send a registration message including capability information, where the capability information indicates a first capability and a second capability, where the first capability is the capability to store model attribute information, and the second capability is the capability to send models. Transceiver module 11 is configured to receive attribute information of at least one model, where the attribute information includes at least one of the following: input parameter information of the model, output parameter information of the model, scenario information for the model application, or required resource information for the model.

[0340] When the device 10 is used to execute the method in Figure 2, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S210, S220, S230, S240, S251, S253 and S260, and the processing module 12 can be used to execute the processing steps in the method, such as step S250.

[0341] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0342] In another design, the device 10 may correspond to the first network element in the above method embodiment, or a component (such as a chip) of the first network element.

[0343] The device 10 can implement the steps or processes corresponding to those executed by the first network element in the above method embodiment, wherein the transceiver module 11 can be used to perform operations related to transceiver transmission of the first network element in the above method embodiment, and the processing module 12 can be used to perform operations related to processing of the first network element in the above method embodiment.

[0344] In one possible implementation, processing module 12 is configured to obtain a predicted network transmission capability for data on the first terminal device and obtain predicted data characteristics for the data on the first terminal device. Processing module 12 is configured to determine control of current data on the first terminal device based on the predicted network transmission capability and the predicted data characteristics.

[0345] In another possible implementation, the transceiver module 11 is used to receive a first message, wherein the first message includes information about a first device and first information, wherein the first information includes an identifier of a first model and / or attribute information of the first model, the first device is a device requesting to obtain the first model, and the attribute information of the first model includes at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information of application of the first model, or required resource information of the first model. The processing module 12 is used to determine whether the first model is authorized to the first device based on the information about the first device and the first information. The transceiver module 11 is used to send a first confirmation message, wherein the first confirmation message is used to indicate whether the first model is authorized to the first device.

[0346] When the device 10 is used to execute the method in Figure 2, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S230, S251 and S253, and the processing module 12 can be used to execute the processing steps in the method, such as step S252.

[0347] When the device 10 is used to execute the method in Figure 3, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S321, S323, S332, and S334, and the processing module 12 can be used to execute the processing steps in the method, such as step S333.

[0348] When the device 10 is used to execute the method in FIG. 4 , the transceiver module 11 may be used to execute the steps of sending and receiving information in the method, such as steps S450 and S470 , and the processing module 12 may be used to execute the processing steps in the method, such as step S460 .

[0349] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0350] In yet another design, the apparatus 10 may correspond to the first device in the above method embodiment, or a component (such as a chip) of the first device.

[0351] The device 10 can implement the steps or processes corresponding to those executed by the first device in the above method embodiment, wherein the transceiver module 11 can be used to perform the transceiver-related operations of the first device in the above method embodiment, and the processing module 12 can be used to perform the processing-related operations of the first device in the above method embodiment.

[0352] In one possible implementation, the transceiver module 11 is configured to send a first request message, wherein the first request message is used to request acquisition of a first model, and the first request message includes attribute information of the first model, wherein the attribute information of the first model includes at least one of the following information: input parameter information of the first model, output parameter information of the first model, scenario information for application of the first model, or required resource information of the first model. The transceiver module 11 is configured to receive a first response message, wherein the first response message includes the first model or first indication information, and the first indication information is used to indicate a refusal to provide the first model.

[0353] When the device 10 is used to execute the method in FIG. 2 , the transceiver module 11 may be used to execute the steps of sending and receiving information in the method, such as steps S231 , S232 , S240 , and S260 , and the processing module 12 may be used to execute the processing steps in the method.

[0354] When the device 10 is used to execute the method in FIG3 , the transceiver module 11 may be used to execute the steps of sending and receiving information in the method, such as steps S301 , S302 , S303 and S304 , and the processing module 12 may be used to execute the processing steps in the method.

[0355] When the device 10 is used to execute the method in FIG4 , the transceiver module 11 may be used to execute the steps of sending and receiving information in the method, such as steps SS410 , S420 , S430 , and S480 , and the processing module 12 may be used to execute the processing steps in the method.

[0356] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0357] In yet another design, the apparatus 10 may correspond to the fourth network element in the above method embodiment, or be a component (such as a chip) of the fourth network element.

[0358] The device 10 can implement steps or processes corresponding to those executed by the fourth network element in the above method embodiment, wherein the transceiver module 11 can be used to perform operations related to transceiver transmission of the fourth network element in the above method embodiment, and the processing module 12 can be used to perform operations related to processing of the fourth network element in the above method embodiment.

[0359] In one possible implementation, the transceiver module 11 is configured to send a second message, where the second message includes attribute information of the first model, where the attribute information of the first model includes at least one of the following: input parameter information of the first model, output parameter information of the first model, scenario information for application of the first model, or resource information required by the first model. The transceiver module 11 is configured to receive a fifth message, where the fifth message includes the first model, address information of the first model, or information indicating a refusal to provide the first model, where the address information of the first model is used to obtain the first model.

[0360] When the device 10 is used to execute the method in Figure 3, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S311, S312, S310, S324, S331, S332, S334, and S304, and the processing module 12 can be used to execute the processing steps in the method, such as step S335.

[0361] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0362] In yet another design, the apparatus 10 may correspond to the fifth network element in the above method embodiment, or be a component (such as a chip) of the fifth network element.

[0363] The device 10 can implement the steps or processes corresponding to those executed by the fifth network element in the above method embodiment, wherein the transceiver module 11 can be used to perform the transceiver-related operations of the fifth network element in the above method embodiment, and the processing module 12 can be used to perform the processing-related operations of the fifth network element in the above method embodiment.

[0364] In one possible implementation, the transceiver module 11 is configured to receive a second message, where the second message includes attribute information of a first model, where the attribute information of the first model includes at least one of the following: input parameter information of the first model, output parameter information of the first model, scenario information for application of the first model, or resource information required by the first model. The processing module 12 is configured to determine the first model based on the attribute information of the first model and attribute information of at least one locally stored model.

[0365] When the device 10 is used to execute the method in Figure 3, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S310, S321, S323, S324, and S331, and the processing module 12 can be used to execute the processing steps in the method, such as step S320.

[0366] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0367] It should also be understood that the device 10 here is embodied in the form of a functional module. The term "module" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and memory for executing one or more software or firmware programs, a combined logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art will understand that the device 10 may be specifically the mobile management network element in the above-mentioned embodiment, and may be used to execute the various processes and / or steps corresponding to the mobile management network element in the above-mentioned method embodiments; or, the device 10 may be specifically the terminal device in the above-mentioned embodiment, and may be used to execute the various processes and / or steps corresponding to the terminal device in the above-mentioned method embodiments. To avoid repetition, it will not be described here.

[0368] The apparatus 10 of each of the above-mentioned solutions has the function of implementing the corresponding steps performed by the devices (such as the first network element, the second network element, the third network element, the fourth network element, the fifth network element, or the sixth network element) in the above-mentioned method. This function can be implemented by hardware, or it can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver module can be replaced by a transceiver (for example, the sending unit in the transceiver module can be replaced by a transmitter, and the receiving unit in the transceiver module can be replaced by a receiver), and other units, such as the processing module, can be replaced by a processor, respectively performing the sending and receiving operations and related processing operations in each method embodiment.

[0369] In addition, the transceiver module 11 may also be a transceiver circuit (for example, may include a receiving circuit and a sending circuit), and the processing module may be a processing circuit.

[0370] Figure 6 is a schematic diagram of another communication device 20 provided in an embodiment of the present application. Device 20 includes a processor 21, which is configured to execute computer programs or instructions stored in memory 22, or read data / signaling stored in memory 22, to perform the methods described in the above method embodiments. Optionally, there may be one or more processors 21.

[0371] Optionally, as shown in FIG6 , the apparatus 20 further includes a memory 22 for storing computer programs or instructions and / or data. The memory 22 may be integrated with the processor 21 or may be separately provided. Optionally, there may be one or more memories 22 .

[0372] Optionally, as shown in Figure 6, the device 20 further includes a transceiver 23, which is used to receive and / or send signals. For example, the processor 21 is used to control the transceiver 23 to receive and / or send signals.

[0373] As a solution, the device 20 is used to implement the operations performed by the first network element, the second network element, the third network element, the fourth network element, the fifth network element, or the sixth network element in the above method embodiments.

[0374] It should be understood that the processor mentioned in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0375] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory and / or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0376] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) can be integrated into the processor.

[0377] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0378] 7 is a schematic diagram of a chip system 30 provided in an embodiment of the present application. The chip system 30 (or also referred to as a processing system) includes a logic circuit 31 and an input / output interface 32.

[0379] The logic circuit 31 may be a processing circuit in the chip system 30. The logic circuit 31 may be coupled to a storage unit and call instructions in the storage unit so that the chip system 30 can implement the methods and functions of the various embodiments of the present application. The input / output interface 32 may be an input / output circuit in the chip system 30, outputting information processed by the chip system 30 or inputting data or signaling information to be processed into the chip system 30 for processing.

[0380] As a solution, the chip system 30 is used to implement the operations performed by the first network element, the second network element, the third network element, the fourth network element, the fifth network element, or the sixth network element in the above method embodiments.

[0381] For example, the logic circuit 31 is used to implement the processing-related operations performed by the first network element, the second network element, the third network element, the fourth network element, the fifth network element, or the sixth network element in the above method embodiments; the input / output interface 32 is used to implement the sending and / or receiving-related operations performed by the terminal device in the above method embodiments.

[0382] An embodiment of the present application further provides a computer-readable storage medium on which computer instructions for implementing the methods executed by the device in the above-mentioned method embodiments are stored.

[0383] For example, when the computer program is executed by a computer, the computer can implement the method performed by the first network element, the second network element, the third network element, the fourth network element, the fifth network element, or the sixth network element in each embodiment of the above method.

[0384] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed by a computer, implement the methods performed by the first network element, the second network element, the third network element, the fourth network element, the fifth network element, or the sixth network element in the above-mentioned method embodiments.

[0385] An embodiment of the present application also provides a communication system, including the aforementioned first network element, second network element and third network element.

[0386] An embodiment of the present application also provides a communication system, including the aforementioned first network element, fourth network element and fifth network element.

[0387] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.

[0388] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software 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 beyond the scope of this application.

[0389] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0390] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0391] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0392] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0393] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0394] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that, The method includes: A third network element sends a registration message to a second network element. The registration message includes capability information, which is used to indicate that the third network element has a first capability and a second capability. The first capability is the capability of storing attribute information of a model, and the second capability is the capability of sending a model. A first network element obtains the identifier of the third network element from the second network element. The first network element sends the attribute information of at least one model to the third network element. The attribute information of the model includes at least one of the following information: The input parameter information of the model, the output parameter information of the model, the scenario information to which the model is applied, or the resource information required by the model. Wherein, the first network element is used to obtain a model based on data training, and the second network element is used to manage network elements in a communication system.

2. The method according to claim 1, characterized in that, The method further includes: A first device sends a first request message to the third network element. The first request message is used to request to obtain a first model, and the first request message includes the attribute information of the first model.

3. The method according to claim 2, wherein The method further includes: The third network element determines the first model according to the attribute information of the first model and the attribute information of the at least one model. The third network element sends a first response message to the first device. The first response message includes the first model or a first indication information, and the first indication information is used to indicate a refusal to provide the first model.

4. The method according to claim 2 or 3, characterized in that, The method further includes: The third network element sends a first message to the first network element. The first message includes the information of the first device and a first piece of information, and the first piece of information includes the identifier of the first model and / or the attribute information of the first model. The first network element determines whether the first model is authorized for the first device according to the information of the first device and the first piece of information. The first network element sends a first confirmation message to the third network element. The first confirmation message is used to indicate whether the first model is authorized for the first device.

5. The method according to any one of claims 1 to 4, characterized in that, The registration message further includes the identifiers of at least one network element, and the identifiers of the at least one network element indicate the network element that stores the attribute information of the model to the third network element.

6. The method according to any one of claims 1 to 5, characterized in that, The registration message further includes model type information, and the model type information is used to indicate the type to which the model stored by the third network element belongs.

7. A communication method, characterized in that, It includes: Sending a registration message, where the registration message includes capability information, and the capability information is used to indicate having a first capability and a second capability. The first capability is the capability of storing model attribute information, and the second capability is the capability of sending a model. Receiving the attribute information of at least one model. The attribute information of the model includes at least one of the following information: The input parameter information of the model, the output parameter information of the model, the scenario information to which the model is applied, or the resource information required by the model.

8. The method according to claim 7, wherein The method includes: Receiving a first request message, where the first request message is used to request to obtain a first model, and the first request message includes the attribute information of the first model. Determining the first model according to the attribute information of the first model and the attribute information of the at least one model. Send a first response message, where the first response message includes the first model or a rejection indication for indicating a rejection of providing the first model.

9. The method according to claim 8, characterized in that, The method further includes: Sending a first message, where the first message includes information of a first device and first information, and the first information includes an identifier of a first model and / or attribute information of the first model, and the information of the first device and the first information are used to confirm whether the first model is authorized for the first device; Receiving a first confirmation message, where the first confirmation message is used to indicate whether the first model is authorized for the first device.

10. The method according to any one of claims 7 to 9, characterized in that The registration message further includes identifiers of at least one network element, and the identifiers of the at least one network element indicate the network element storing the attribute information of the model.

11. The method according to any one of claims 7 to 10, characterized in that The registration message further includes model type information, and the model type information is used to indicate the type to which the stored model belongs.

12. A communication method, characterized in that, Includes: Receiving a first message, where the first message includes information of a first device and first information, and the first information includes an identifier of a first model and / or attribute information of the first model, the first device is a device requesting to obtain the first model, and the attribute information of the first model includes at least one of the following information: Input parameter information of the first model, output parameter information of the first model, scenario information to which the first model is applied, or required resource information of the first model; Determining whether the first model is authorized for the first device according to the information of the first device and the first information; Sending a first confirmation message, where the first confirmation message is used to indicate whether the first model is authorized for the first device.

13. A communication method, characterized in that, Includes: Sending a first request message for requesting to obtain a first model, where the first request message includes attribute information of the first model, and the attribute information of the first model includes at least one of the following information: Input parameter information of the first model, output parameter information of the first model, scenario information to which the first model is applied, or required resource information of the first model; Receiving a first response message, where the first response message includes the first model or first indication information for indicating a rejection of providing the first model.

14. The method according to claim 13, wherein The method further includes: Sending a second request message for requesting to obtain an identifier of a third network element, where the second request message carries capability information for indicating obtaining the third network element having a first capability and a second capability, the first capability being the capability of storing model attribute information and the second capability being the capability of sending a model; Receiving the identifier of the third network element.

15. A communication method, characterized in that, The method includes: A fourth network element sends a second message to a fifth network element, where the second message includes attribute information of a first model, and the attribute information of the first model includes at least one of the following information: Input parameter information of the first model, output parameter information of the first model, scenario information to which the first model is applied, or required resource information of the first model; The fifth network element determines the first model according to the attribute information of the first model and the attribute information of at least one model stored locally; The fifth network element sends a third message to the first network element. The third message includes information of a first device and first information. The first information includes an identifier of the first model and / or the attribute information of the first model. The first device is a device that requests to obtain the first model, and the first network element is the network element that trains the first model; The first network element determines whether the first model is authorized for the first device according to the information of the first device and the first information; The first network element sends a second confirmation message to the fifth network element. The second confirmation message is used to indicate whether the first model is authorized for the first device; If the second confirmation information indicates that the first model is not authorized for the first device, the fifth network element sends second indication information to the fourth network element. The second indication information is used to indicate a refusal to provide the first model; or, if the second confirmation information indicates that the first model is authorized for the first device, the fifth network element sends the first model to the fourth network element; Wherein, the first network element is used to train a model based on data, the fourth network element is used to send the model to a device that requests the model, and the fifth network element is used to store the attribute information of the model.

16. A communication method, characterized in that, The method includes: The fourth network element sends a second message to the fifth network element. The second message includes the attribute information of a first model. The attribute information of the first model includes at least one of the following information: The input parameter information of the first model, the output parameter information of the first model, the scenario information to which the first model is applied, or the resource information required by the first model; The fifth network element determines the first model according to the attribute information of the first model and the attribute information of at least one model stored locally; The fifth network element sends information of the first network element to the fourth network element. The first network element is the network element that trains the first model; The fourth network element sends a fourth message to the first network element. The fourth message includes information of a first device and first information. The first information includes an identifier of the first model and / or the attribute information of the first model. The first device is a device that requests to obtain the first model; The first network element determines whether the first model is authorized for the first device according to the information of the first device and the first information; The first network element sends the first model, the address information of the first model, or third indication information to the fourth network element. The third indication information is used to indicate a refusal to provide the first model. The address information of the first model is used to obtain the first model; Wherein, the first network element is used to train a model based on data, the fourth network element is used to send the model to a device that requests the model, and the fifth network element is used to store the attribute information of the model.

17. The method according to claim 15 or 16, characterized in that, The fourth network element and the first device are co-located, or The communication system further includes the first device, and the method further includes: The first device sends a third request message to the fourth network element, where the third request message is used to request to obtain the first model, and the attribute information of the first model is included in the third request message; The fourth network element sends a second response message to the first device, where the first model or information indicating a refusal to provide the first model is included in the second response message.

18. A communication method, characterized in that, Including: Sending a second message, where the attribute information of the first model is included in the second message, and the attribute information of the first model includes at least one of the following information: The input parameter information of the first model, the output parameter information of the first model, the scenario information to which the first model is applied, or the resource information required by the first model; Receiving a fifth message, where the first model, the address information of the first model, or information indicating a refusal to provide the first model is included in the fifth message, and the address information of the first model is used to obtain the first model.

19. The method according to claim 18, characterized in that, The receiving the fifth message specifically includes: Receiving information of a first network element, where the first network element is the network element that trains the first model; Sending a fourth message to the first network element, where the information of the first device and first information are included in the fourth message, and the first information includes the identifier and / or the attribute information of the first model, and the first device is the device that requests to obtain the first model; Receiving the fifth message from the first network element.

20. The method according to claim 18 or 19, characterized in that The method further includes: Receiving a third request message, where the third request message is used to request to obtain the first model, and the attribute information of the first model is included in the third request message; Sending a second response message, where the first model or information indicating a refusal to provide the first model is included in the second response message.

21. The method according to any one of claims 18 to 20, characterized in that, When the address information of the first model is included in the fifth message, the method further includes: Receiving fourth indication information; Sending the fourth indication information to a fifth network element indicated by the address information of the first model, where the fourth indication information is used to verify the obtaining of the first model.

22. A communication method, characterized in that, Including: Receiving a second message, where the attribute information of the first model is included in the second message, and the attribute information of the first model includes at least one of the following information: The input parameter information of the first model, the output parameter information of the first model, the scenario information to which the first model is applied, or the resource information required by the first model; Determining the first model according to the attribute information of the first model and the attribute information of at least one model stored locally.

23. The method according to claim 22, characterized in that, The method further includes: Sending a third message, where the information of the first device and first information are included in the third message, and the first information includes the identifier and / or the attribute information of the first model, and the first device is the device that requests to obtain the first model; Receiving a second confirmation message, where the second confirmation message is used to indicate whether the first model is authorized to the first device; If the second confirmation information indicates that the first model is not authorized for the first device, send second indication information, where the second indication information is used to indicate refusal to provide the first model; or, if the second confirmation information indicates that the first model is authorized for the first device, send the first model.

24. A communication device, characterized in that, Comprising at least one module, where the at least one module is configured to execute the method according to any one of claims 1 to 23.

25. A computer-readable storage medium, characterized in that, A computer program or instruction is stored on the computer-readable storage medium, and when the computer program or the instruction runs on a computer, the method according to any one of claims 1 to 23 is executed.

26. A computer program product, characterized in that, Comprising computer program code, and when the computer program code runs, the method according to any one of claims 1 to 23 is implemented.

Images