Communication method and communication device

Abstract

Provided is a communication method, comprising: a third network element sending a registration message to a second network element, the registration message comprising capability information, the capability information being used for indicating that the third network element has attribute information of a storage model and a capability of sending a model to a device requesting the model, and the first network element sends attribute information of at least one model to a 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, scene information of model application or resource information required by the model. According to the embodiment of the invention, the third network element is arranged in the communication system, and the specific information of the model is stored in the third network element, so that the controller can obtain the appropriate model from the third network element based on the specific information of the required model, and resource waste caused by unnecessary model training of the network element for training the model in the system can be reduced to a certain extent.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly, to a communication method and a communication device. Background Art

[0002] Consumers in a network can request an artificial intelligence (AI) model based on an analytics identify. The same analytics ID can correspond to multiple AI models, where the AI models can be used for data inference. Specifically, a consumer can obtain information about a network data analytics function (NWDAF) that supports the analytics ID through the analytics ID, and thus select a certain NWDAF to request the AI model. When there are multiple NWDAs in the same area, and different NWDAs can support the same analytics ID, but the AI models stored in different NWDAs are different, when the consumer obtains a candidate list of NWDAs, it is impossible to determine which NWDA has the requested AI model (e.g., AI model #1). Therefore, the consumer is likely to select an NWDA that currently does not have AI model #1 and send a model subscription request to it. When this NWDA 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 a consumer requesting an AI model, how to reduce the possibility of network resource waste has become an urgent problem to be solved. Summary of the Invention

[0003] This application provides a communication method to manage a model while reducing the possibility of network resource waste.

[0004] In a first aspect, a communication method is provided. The communication method includes: a third network element sends a registration message to a second network element, where the registration message includes capability information for indicating 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 an identifier of the third network element from the second network element, and the first network element sends 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: input parameter information of the model, output parameter information of the model, scenario information to which the model is applied, or required resource information of the model, where 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.

[0005] Based on the above technical solution, by deploying a third network element with the ability to store the attribute information of the model and send the model to the device requesting the model in the communication system, 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. Thus, in the process of a device (such as a consumer) requesting a model, the specific information of the required model can be used to request the third network element to obtain the model, so as to obtain a suitable model, which can reduce the waste of resources caused by unnecessary model training by the network element that trains the model in the system to a certain extent.

[0006] For example, in the process of a consumer requesting a model, the specific information of the required model (such as the attribute information of the model) is carried in the request message. 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, rather than providing multiple NWDAF identifiers for training the model based on the analysis ID, which may cause the consumer to select an NWDAF that currently does not have a model and send a model subscription request to it. When this NWDAF receives the model subscription request, it will retrain to obtain the model, resulting in waste of network resources.

[0007] Combined with the first aspect, in some implementation manners of the first aspect, the method further includes: the first device sends a first request message to the third network element, 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.

[0008] Based on the above technical solution, when the first device requests a model, 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 applied by the first model, or the required resource information of the first model, etc.) is carried, so that the third network element can know the model required by the first device.

[0009] Combined with the first aspect, in some implementation manners of the first aspect, 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 at least one model; the third network element sends a first response message to the first device, where the first response message includes the first model or a first indication information, and the first indication information is used to indicate that the first model is refused to be provided.

[0010] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the third network element sends a first message to the first network element, where the first 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 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 first confirmation information to the third network element, and the first confirmation information is used to indicate whether the first model is authorized for the first device.

[0011] Based on the above technical solution, before the third network element provides the first model to the first device, it can send a first message to the first network element that trained the first model to authenticate whether the first model is authorized for the first device, so as to avoid providing the first model to the first device without authorization.

[0012] In combination with the first aspect, in some implementations of the first aspect, 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 that stores the attribute information of the model to the third network element. The at least one network element can store the attribute information of the trained model to the third network element.

[0013] In combination with the first aspect, in some implementations of the first aspect, 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.

[0014] In a second aspect, a communication method is provided. This method can be executed by the third network element, or by a component (such as a chip or a circuit or a chip system) of the third network element. This application does not limit this.

[0015] The communication method 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 being the capability to store the attribute information of the model, and the second capability being the capability to send the model; receiving the attribute information of at least one model, where 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 required resource information of the model.

[0016] In combination with the second aspect, in some implementations of the second aspect, the method includes: receiving a first request message for requesting to obtain the first model, where the first request message includes attribute information of 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; sending 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.

[0017] In combination with the second aspect, in some implementations of the second aspect, the method further includes: sending a first message that includes information of the first device and first information, where the first information includes an identifier of the first model and / or the 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 first confirmation information for indicating whether the first model is authorized for the first device.

[0018] In combination with the second aspect, in some implementations of the second aspect, the registration message further includes identifiers of at least one network element, where the identifiers of the at least one network element indicate the network element for storing the attribute information of the model to the third network element. The at least one network element may store the attribute information of the trained model to the third network element.

[0019] In combination with the second aspect, in some implementations of the second aspect, the registration message further includes model type information for indicating the type to which the model stored in the third network element belongs.

[0020] The technical effects of the method shown in the above second aspect and its possible designs may refer to the technical effects in the first aspect and its possible designs.

[0021] In a third aspect, a communication method is provided. This method may be executed by a first network element or by a component (such as a chip, a circuit, or a chip system) of the first network element. This application does not make a limitation in this regard.

[0022] The communication method includes: receiving a first message, where the first message includes information of a first device and first information, the first information includes an identifier of a first model and / or attribute information of the first model, the first device is a device that requests 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 where 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; and sending a first confirmation message, where the first confirmation message is used to indicate whether the first model is authorized for the first device.

[0023] For the technical effects of the method shown in the third aspect and its possible designs above, reference may be made to the technical effects in the first aspect and its possible designs.

[0024] In a fourth aspect, a communication method is provided. This method may be executed by a first device or by a component of the first device (such as a chip or a circuit or a chip system). This application does not limit this.

[0025] The communication method includes: sending 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, 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 where the first model is applied, or required resource information of the first model; and receiving a first response message, where 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.

[0026] In combination with the fourth aspect, in some implementation manners of the fourth aspect, the method further includes: sending a second request message, where the second request message is used to request to obtain an identifier of a third network element, and the second request message carries capability information, and the capability information is used to indicate obtaining the third network element with 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; and receiving the identifier of the third network element.

[0027] For the technical effects of the method shown in the fourth aspect and its possible designs above, reference may be made to the technical effects in the first aspect and its possible designs.

[0028] Fifth aspect, a communication method is provided, which 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 a first network element, where the third message includes information of a first device and first information, and 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 a 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, and 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, and 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, the fifth network element sends the first model to the fourth network element, where the first network element is used to train a model based on data, the fourth network element is used to send a model to a device that requests the model, and the fifth network element is used to store the attribute information of the model.

[0029] Based on the above technical solution, during the process of the fourth network element requesting the first model from the fifth network element, specific information of the first model (such as 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, etc.) is carried, so that the fifth network element can know the specific model being requested, thereby providing a suitable model, instead of providing multiple NWDAF identifiers for training the model based on analyzing the ID, which may cause the consumer to send a model subscription request to a NWDAF that currently does not have a model. When this NWDAF receives the model subscription request, it will retrain to obtain a model, resulting in waste of network resources.

[0030] In addition, the fifth network element can authenticate whether the first model is authorized for the first device through the third message to the first network element that trains the first model, avoiding providing the first model to the first device without authorization.

[0031] Sixth aspect, a communication method is provided,

[0032] The communication method includes: a fourth network element sending 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 determining 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 sending information of a first network element to the fourth network element, where the first network element is the network element that trains the first model; the fourth network element sending a fourth message to the first network element, where the fourth message includes information of a first device and first information, and the first information includes an identifier of the first model and / or the attribute information of the first model, and the first device is the device that requests to obtain the first model; the first network element determining 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 sending the first model, address information of the first model, or third indication information to the fourth network element, where 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. Herein, the first network element is used to obtain a model based on data training, the fourth network element is used to send a model to a device that requests a model, and the fifth network element is used to store the attribute information of the model.

[0033] Based on the above technical solution, during the process of the fourth network element requesting the first model from the fifth network element, specific information of the first model (such as 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, etc.) is carried, so that the fifth network element can know the specific model being requested, thereby providing a suitable model, instead of providing multiple NWDAF identifiers for training models based on analyzing the ID, which may cause the consumer to select a NWDAF that currently does not have a model and send a model subscription request to it. When this NWDAF receives the model subscription request, it will retrain to obtain a model, resulting in a waste of network resources.

[0034] In addition, the fifth network element provides information of the first network element that trains the first model to the fourth network element, so that the fourth network element can authenticate whether the first model is authorized for the first device through the fourth message to the first network element that trains the first model, avoiding providing the first model to the first device without authorization.

[0035] Combined 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 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 third request message includes the 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.

[0036] Based on the above technical solution, if the first device and the fourth network element are not co-located, when the first device requests a model, the specific information of the required first model is carried (for example, 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 required resource information of the first model, etc.), so that subsequent network elements can know the model required by the first device.

[0037] A seventh aspect provides a communication method. This method can be executed by the fourth network element or by a component (such as a chip or a circuit or a chip system) of the fourth network element. This application does not make a limitation in this regard.

[0038] This communication method includes: sending a second message, where the second message includes the attribute information of the first model, 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 required resource information of the first model; receiving a fifth message, where the fifth message includes the first model, the 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.

[0039] Combined with the seventh aspect, in some implementations of the seventh aspect, the receiving the fifth message specifically includes: receiving information of the 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 fourth message includes information of the first device and first information, and the first information includes the identifier of the first model 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.

[0040] In combination with the seventh aspect, in some implementations of the seventh aspect, the method further includes: receiving a third request message for requesting to obtain the first model, where the third request message includes attribute information of the first model; and sending a second response message, where the second response message includes the first model or information indicating a refusal to provide the first model.

[0041] In combination with the seventh aspect, in some implementations of the seventh aspect, when the fifth message includes the address information of the first model, the method further includes: receiving fourth indication information; and sending the fourth indication information to the fifth network element indicated by the address information of the first model, where the fourth indication information is used to verify the acquisition of the first model.

[0042] The technical effects of the method shown in the above seventh aspect and its possible designs can be referred to the technical effects in the fifth aspect or the sixth aspect and their possible designs.

[0043] The eighth aspect provides a communication method. This method can be executed by the fifth network element or by a component (such as a chip, a circuit, or a chip system) of the fifth network element. This application does not make any limitations in this regard.

[0044] The communication method includes: receiving a second message, 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; and determining the first model according to the attribute information of the first model and the attribute information of at least one model stored locally.

[0045] In combination with the eighth aspect, in some implementations of the eighth aspect, the method further includes: sending a third message, where the third message includes information of a 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 network element that trains the first model; receiving a second confirmation message for indicating 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 for indicating 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.

[0046] The technical effects of the method shown in the above eighth aspect and its possible designs can be referred to the technical effects in the fifth aspect or the sixth aspect and their possible designs.

[0047] In a ninth aspect, a communication device is provided. The communication device is used to implement the second aspect and any of its implementation manners described above. Specifically, the communication device includes a processor and a memory, where the memory is used to store a computer program; the processor is used to call and run the computer program from the memory, so that the communication device implements the first aspect and any of its implementation manners described above.

[0048] In one implementation manner, 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. Optionally, the transceiver may be a transceiver circuit. Optionally, the input / output interface may be an input / output circuit.

[0049] In another implementation manner, the communication device may be a chip, a chip system, or a circuit in the third network element. At this time, the transceiver unit may be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or a related circuit, etc. on the chip, the chip system, or the circuit; the processing unit may be at least one processor, a processing circuit, or a logic circuit, etc.

[0050] In a tenth aspect, a communication device is provided. The communication device is used to implement the third aspect and any of its implementation manners described above. Specifically, the communication device includes a processor and a memory, where the memory is used to store a computer program; the processor is used to call and run the computer program from the memory, so that the network device implements the third aspect and any of its implementation manners described above.

[0051] In one implementation manner, 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.

[0052] In another implementation manner, the communication device may be a chip, a chip system, or a circuit in the first network element. At this time, the transceiver unit may be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or a related circuit, etc. on the chip, the chip system, or the circuit; the processing unit may be at least one processor, a processing circuit, or a logic circuit, etc.

[0053] In an eleventh aspect, a communication device is provided. The communication device is used to implement the fourth aspect and any of its implementation manners described above. Specifically, the communication device includes a processor and a memory, where the memory is used to store a computer program; the processor is used to call and run the computer program from the memory, so that the network device implements the fourth aspect and any of its implementation manners described above.

[0054] In one implementation, when the communication device is the first device, the transceiver unit can be a transceiver or an input / output interface. The processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0055] In another implementation, the communication device can be a chip, a chip system or a circuit in the first device. At this time, the transceiver unit can be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin or a related circuit, etc. on the chip, the chip system or the circuit; the processing unit can be at least one processor, a processing circuit or a logic circuit, etc.

[0056] In a twelfth aspect, a communication device is provided. The communication device is used to execute the above seventh aspect and any one of its embodiments. Specifically, the communication device includes a processor and a memory, and the memory is used to store a computer program; the processor is used to call and run the computer program from the memory, so that the network device executes the above seventh aspect and any one of its embodiments.

[0057] In one implementation, when the communication device is the fourth network element, the transceiver unit can be a transceiver or an input / output interface. The processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0058] In another implementation, the communication device can be a chip, a chip system or a circuit in the fourth network element. At this time, the transceiver unit can be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin or a related circuit, etc. on the chip, the chip system or the circuit; the processing unit can be at least one processor, a processing circuit or a logic circuit, etc.

[0059] In a thirteenth aspect, a communication device is provided. The communication device is used to execute the above eighth aspect and any one of its embodiments. Specifically, the communication device includes a processor and a memory, and the memory is used to store a computer program; the processor is used to call and run the computer program from the memory, so that the network device executes the above eighth aspect and any one of its embodiments.

[0060] In one implementation, when the communication device is the fifth network element, the transceiver unit can be a transceiver or an input / output interface. The processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0061] In another implementation, the communication device may be a chip, a chip system, or a circuit in the fifth network element. At this time, the transceiver unit may be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or a related circuit on the chip, the chip system, or the circuit; the processing unit may be at least one processor, a processing circuit, or a logic circuit, etc.

[0062] In a fourteenth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is run, the method according to any one of the implementations of the first aspect to the eighth aspect is executed.

[0063] In a fifteenth aspect, a computer program product including instructions is provided. When the computer program product is run, the method provided by any one of the implementations of the first aspect to the eighth aspect is executed.

[0064] In a sixteenth aspect, a chip is provided. The chip 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 implementations of the first aspect to the eighth aspect.

[0065] Optionally, as an implementation, the chip further includes a memory. The memory stores a computer program or instructions. The processor is configured to execute the computer program or instructions stored on the memory. When the computer program or instructions are executed, the processor is configured to execute the method provided by any one of the implementations of the first aspect to the eighth aspect.

[0066] In a seventeenth aspect, a communication system is provided, including a first network element, a second network element, and a third network element.

[0067] In an eighteenth aspect, a communication system is provided, including a first network element, a fourth network element, and a fifth network element.

[0068] In a nineteenth aspect, a computer program is provided. When the computer program is run, the method provided by any one of the implementations of the first aspect to the eighth aspect is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 is a schematic diagram of the network architecture 100 provided by this application.

[0070] Figure 2 is a schematic flowchart of a communication method provided by an embodiment of this application.

[0071] Figure 3 is a schematic flowchart of another communication method provided by an embodiment of this application.

[0072] Figure 4It is a schematic flowchart of another communication method provided by an embodiment of the present application.

[0073] Figure 5 It is a schematic block diagram of a communication device 10 provided by an embodiment of the present application.

[0074] Figure 6 It is a schematic diagram of another communication device 20 provided by an embodiment of the present application.

[0075] Figure 7 It is a schematic diagram of a chip system 30 provided by an embodiment of the present application. Detailed implementation manners

[0076] For the convenience of understanding the embodiments of the present application, the following points are first explained.

[0077] First, in the present application, "for indicating" may include for directly indicating and for indirectly indicating. When it is described that a certain indication information is used to indicate A, it may include that the indication information directly indicates A or indirectly indicates A, and it does not mean that A must be carried in the indication information.

[0078] 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. For example, but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated, etc. It can also indirectly indicate the information to be indicated by indicating other information, where there is an association relationship between the other information and the information to be indicated. It can also only indicate a part of the information to be indicated, while the other parts of the information to be indicated are known or pre-agreed. For example, the indication of specific information can also be achieved by relying on the arrangement order of each information pre-agreed (such as protocol regulations), so as to reduce the indication overhead to a certain extent. At the same time, the common parts of each information can also be identified and indicated uniformly to reduce the indication overhead caused by separately indicating the same information.

[0079] Second, "at least one" shown in the present application means one or more, and "a plurality" means two or more. In addition, in the embodiments of the present application, "first", "second", and various numerical numbers (such as "#1", "#2", etc.) are only for the convenience of description for distinction, and do not limit the scope of the embodiments of the present application. The magnitudes of the serial numbers of the following processes do 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 to the implementation process of the embodiments of the present application. It should be understood that the objects described in this way can be interchanged under appropriate circumstances so as to be able to describe the solutions other than the embodiments of the present application. In addition, in the embodiments of the present application, the words such as "S210" are only identifiers made for the convenience of description, and do not limit the order of execution steps.

[0080] Third, in the embodiments of the present application, words such as "exemplary" or "for example" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the present application should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0081] Fourth, the "storage" involved in the embodiments of the present application may refer to storage in one or more memories. The one or more memories may be separately provided, or may be integrated in an encoder, a decoder, a processor, or a communication device. The one or more memories may also have a part separately provided and a part integrated in the decoder, the processor, or the communication device. The type of the memory may be any form of storage medium, and the present application does not limit this.

[0082] Fifth, in the implementation of the present application, the "protocol" may refer to standard protocols in the field of communication, for example, may include the NR protocol and related protocols applied to future communication systems, and the present application does not limit this.

[0083] Sixth, in the embodiments of the present application, "(of)", "corresponding", "corresponding", and "associated" may sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same.

[0084] Seventh, in the embodiments of the present application, "in the case of", "when", and "if" may sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same.

[0085] Eighth, the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0086] Next, the technical solutions in the present application will be described with reference to the accompanying drawings.

[0087] The technical solutions provided by 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 by 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.

[0088] In a communication system, the part operated by an operator can be referred to as a Public Land Mobile Network (PLMN), or it can also be called an operator network, etc. A PLMN is a network established and operated by a government or its approved operator for the purpose of providing public land mobile communication services, mainly a public network where a Mobile Network Operator (MNO) provides mobile broadband access services to users. The PLMN described in the embodiments of this application can specifically be a network that meets the requirements of the 3GPP standard, abbreviated as a 3GPP network. A 3GPP network generally includes but is not limited to 5G networks, Fourth Generation (4G) mobile communication networks, and future other communication systems, such as (6th Generation, 6G) networks, etc.

[0089] For ease of description, the embodiments of this application will be described by taking the PLMN or 5G network as an example.

[0090] Figure 1 It is a schematic diagram of the network architecture 100 provided by this application, taking the 5G network architecture based on the service-based architecture in the non-roaming scenario defined in the 3GPP standardization process as an example. As shown in the figure, this network architecture can include three parts, namely the terminal device part (such as Figure 1 the User Equipment (UE) shown in

[0091] 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 and 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 platform, remote station, remote terminal, mobile device, user terminal, user agent, or user device, etc. The terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on water (such as on a ship, etc.); it can also be deployed in the air (such as on an airplane, balloon, satellite, etc.). The terminal device can be a cellular phone, cordless phone, session initiation protocol (SIP) phone, smart phone, mobile phone, wireless local loop (WLL) station, personal digital assistant (PDA), etc. Or, the terminal device can also be a handheld device with wireless communication functions, a computing device, or other devices connected to a wireless modem, a vehicle-mounted device, a wearable device, a drone device, or a terminal in the Internet of Things, vehicle-to-everything network, any form of terminal in a 5G network and future networks, a relay user equipment, or a terminal in a future evolved 6G network, etc. Among them, the relay user equipment can be, for example, a 5G residential gateway (RG). For example, the terminal device can 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, 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 this application do not limit the type or category of the terminal device, etc. For ease of explanation, the following examples in this application use UE to represent the terminal device for illustration purposes.

[0092] The PLMN part of the operator network may include, but is not limited to, the (radio) access network ((R)AN) and the core network (CN) part.

[0093] (R)AN can be regarded as a sub-network of the operator network and is an implementation system between the service nodes and the terminal devices in the operator network. For a terminal device to access the operator network, it first passes through (R)AN and then can be connected to the service nodes of the operator network through (R)AN. The access network device (RAN device) in the embodiments of the present application is a device that provides wireless communication functions for terminal devices 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 transmitting and receiving point (TRP), the transmitting point (TP), the pico base station device, the mobile switching center, or the network device in the future network, etc. In systems using different radio access technologies, the names of the devices with the functions of access network devices may be different. For the convenience of description, in all embodiments of the present application, the above-mentioned devices that provide wireless communication functions for terminal devices are collectively referred to as access network devices or simply referred to as RAN or AN. It should be understood that the specific types of access network devices are not limited herein.

[0094] In some deployments, the (R)AN may include a centralized unit (CU) and a distributed unit (DU). The CU implements part of the functions of the gNB, and the DU implements part of the functions of the gNB. For example, the CU is responsible for processing non-real-time protocols and services, and 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, and implementing the functions of the radio link control (RLC) layer, media access control (MAC) layer, and physical (PHY) layer. It can be understood that the (R)AN 120 may be a device including one or more of the CU node and the DU node.

[0095] In addition, the CU may be classified as a network device in the radio access network (RAN), or may be classified as a network device in the core network (CN). This application does not make a limitation in this regard.

[0096] In different systems, the 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, the CU may also be referred to as O-CU (open CU), the DU may also be referred to as O-DU, the CU-CP may also be referred to as O-CU-CP, the CU-UP may also be referred to as O-CU-UP, and the RU may also be referred to as O-RU. Any one of the 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.

[0097] 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 (UDM), Unified Data Repository (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) device (i.e., network management).

[0098] The DN can also be referred to as a packet data network (PDN), which is usually a network outside the operator's network, such as a third-party network. Of course, in some implementation manners, the DN can also be deployed by the operator, that is, the DN belongs to a part of the PLMN. This application does not limit whether the DN belongs to the PLMN. The operator network PLMN can access multiple data networks DN, and various services can be deployed on the data network DN, providing services such as data and / or voice for terminal devices. For example, the data network DN can be a private network of a smart factory, and the 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 for the sensors. The sensors can communicate with the control server, obtain instructions from the control server, and transmit the collected sensor data to the control server according to the instructions, etc. Another example is that the data network DN can be an internal office network of a company. The mobile phones or computers of the company's employees can be terminal devices, and the mobile phones or computers of the employees can access information, data resources, etc. on the company's internal office network. The terminal device can establish a connection with the operator network through an interface provided by the operator network (such as N1, etc.) and use services such as data and / or voice provided by the operator network. The terminal device can also access the data network DN through the operator network and use the operator services deployed on the data network DN and / or services provided by third parties.

[0099] The NF functions included in the network architecture 100 are further briefly described below.

[0100] 1. The UPF is a gateway provided by the operator and is the gateway for communication between the operator network and the data network DN. The UPF network functions include user plane-related functions such as packet routing and transmission, packet detection, service usage reporting, quality of service (QoS) processing, lawful interception, uplink packet detection, and downlink packet storage.

[0101] 2. The NEF is a control plane function provided by the operator, mainly enabling third parties to use the services provided by the network, supporting the network to open its capabilities, events, and data analysis, equipping security information for the PLMN from external applications, converting information exchanged inside and outside the PLMN, providing an API interface for the operator network to open to the outside, and providing the interaction between the external server and the internal operator network.

[0102] 3. The NRF is a control plane function provided by the operator and 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 configuration data (NF profile) of the NF instance, supports service discovery of the service communication proxy (SCP), maintains the SCP configuration data (SCP profile) of the SCP instance, sends notifications about newly registered, deregistered, and updated NFs and SCPs, and maintains the health status of the running NFs and SCPs.

[0103] In this application, the NRF can provide the number of available network elements corresponding to different network element types in a certain area for the certificate management network element through the network service discovery or network service subscription process. The functions of the NRF will be described below in combination with specific examples and will not be elaborated here.

[0104] 4. The PCF is a control plane function provided by the operator. It supports a unified policy framework to govern network behavior, provides policy rules and subscription information related to policy decisions to other control functions, etc.

[0105] 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) of the subscribed users in the operator's network, the generic public subscription identifier (GPSI) of the subscribed users, and the credential. Among them, the SUPI will be encrypted first during the transmission process, and the encrypted SUPI is called the subscription concealed identifier (SUCI). The information stored by the UDM network function 134 can be used for the authentication and authorization of the terminal device 110 to access the operator's network. Among them, the subscribed users of the above operator's network can specifically be users who use the services provided by the operator's network, such as users who use the subscriber identity module (SIM) card of China Telecom, or users who use the SIM card of China Mobile, etc. The credential of the above subscribed users can be a long-term key stored in the SIM card or a small file storing information related to the encryption of the SIM card, etc., for authentication and / or authorization. It should be noted that information related to verification / authentication, authorization such as permanent identifiers, credentials, security contexts, authentication data (cookies), and tokens are not distinguished or restricted for the sake of convenience of description in the embodiments of this application.

[0106] 6. The UDR is a control plane function provided by the operator, which provides functions for the UDM to store and obtain subscription data, provides functions for the PCF to store and obtain policy data, and stores and obtains the NF group ID (group ID) information of users, etc.

[0107] 7. The NWDAF is a network data analysis function provided by the operator. Its main function is to collect data from NFs, external application functions (AFs), OAM devices, etc. for analysis, and provide data analysis results to NFs and AFs.

[0108] In this application, the NWDAF can provide data analysis for 5G core network (5G core, 5GC) NFs and OAMs. Exemplarily, a 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, and finally uses the AI model for data inference and feeds the inference results back to the corresponding 5GC NF or OAM.

[0109] Specifically, the NWDAF can be divided into two types according to different functions: the NWDAF that supports the model training logical function (MTLF) (which can be abbreviated as NWDAF(MTLF) or MTLF) and the NWDAF that supports the analytics logical function (AnLF) inference (which can be abbreviated as NWDAF(AnLF) or AnLF). Among them, the AnLF can request AI model information from the MTLF for data inference.

[0110] In addition, one or more NWDAFs can be deployed within the same PLMN domain.

[0111] 8. OAM refers to that according to the actual needs of the operator's network operation, the network management work is usually divided into three categories: operation, administration, and maintenance. Operation mainly completes the analysis, prediction, planning, and configuration work for daily networks and services; maintenance mainly conducts daily operation activities such as testing and fault management of the network and its services.

[0112] 9. The AMF is a control plane network function provided by the operator's network, responsible for access control and mobility management of terminal devices accessing the operator's network. For example, it includes functions such as mobile status management, allocation of user temporary identity identifiers, authentication and authorization of users, etc.

[0113] 10. The SMF is a control plane network function provided by the operator network and is responsible for managing the PDU sessions of the terminal devices. A PDU session is a channel for transmitting PDUs, and the terminal device needs to use the PDU session to transmit PDUs to and from the data network DN. The SMF is responsible for establishing, maintaining, and deleting the PDU sessions, etc. The SMF includes session management (such as session establishment, modification, and release, including the maintenance of the tunnel between the user plane function UPF and the (R)AN), the selection and control of the UPF network function 130, the selection of the service and session continuity (SSC) mode, roaming, and other session-related functions.

[0114] 11. The AF is a control plane network function provided by the operator network and is used to provide application layer information. It can interact with the policy framework through the network exposure function network element or directly interact with the policy framework for policy decision requests, etc. It can be located within the operator network or outside the operator network.

[0115] 12. The ADRF provides services that enable users (consumers) to store and retrieve historical data (from various network elements) and analysis results (from the NWDAF). Users can request or subscribe to the data storage (retrieval) services provided by the ADRF through interfaces (such as, Nadrf). When the user uses the request operation, the ADRF directly returns the corresponding result; when the user uses the subscription operation, if the corresponding purpose is to store data, the ADRF subscribes to the analysis results or data from the NWDAF and provides a notification address, otherwise the ADRF continuously returns data to the notification address of the consumer network element included in the subscription.

[0116] It can be understood that the above-mentioned network elements or functions can be either physical entities in hardware devices, software instances running on dedicated hardware, or virtualized functions instantiated on a shared platform (such as a cloud platform). Simply put, an NF can be implemented by hardware or by software.

[0117] Figure 1 Among them, Nnef, Nnrf, Npcf, Nudm, Nudr, Nnwdaf, Namf, Nsmf, N2, N3, N4, and N6 are interface sequence numbers. Exemplarily, the meanings of the above interface sequence numbers can be referred to the meanings defined in the 3GPP standard protocol, and this application does not limit the meanings of the above interface sequence numbers. It should be noted that the interface names between the various network functions in the figure are only examples. In specific implementations, the interface names of this system architecture may also be other names, and this application does not make any limitations in this regard. In addition, the names of the messages (or signaling) transmitted between the above-mentioned network elements are also only examples and do not impose any limitations on the functions of the messages themselves.

[0118] For ease of description, in the embodiments of the present application, network functions (such as NEF... SMF) are collectively referred to / simply called NF, that is, the NF described later in the embodiments of the present application can be replaced by any network function. Additionally, Figure 1 only some network functions are schematically described, and the NF described later is not limited to Figure 1 the network functions shown in

[0119] It should be understood that the network architecture applied to the embodiments of the present application is only described from the perspective of the service-based architecture, and the network architecture applicable to the embodiments of the present application is not limited thereto. Any network architecture capable of implementing the functions of the above-mentioned network elements is applicable to the embodiments of the present application.

[0120] 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 individual devices or integrated into the same device to implement different functions. The present application does not limit the specific form of the above-mentioned network elements.

[0121] The network element types involved in the following embodiments can be: network elements are divided into different network element types according to division methods such as functional division, deployment location division, or home domain division, etc. For example, when divided by service function, it can be divided into the above-mentioned network element types such as SMF, AMF, UPF, NWDAF, etc.; also for example, when divided by deployment location, it can be divided into access network elements or non-access network elements; and for another example, when divided by home domain, it can be divided into visited network elements or home network elements, etc.

[0122] Exemplarily, 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; also for example, network elements belonging to SMF are responsible for managing the PDU sessions of terminal devices.

[0123] It should be understood that in the service certificate update process, there may be a large number of certificates updated simultaneously, and during the certificate update process, the corresponding network elements cannot be used. In particular, if network elements providing the same service in the network update their certificates simultaneously, it will cause the network to be unable to provide the corresponding service. For example, if all AMFs in the network execute the service certificate update, then there will be no available AMFs in the network.

[0124] It should also be understood that the above naming is only defined for the convenience of distinguishing different functions and should not impose any limitations on this application. This application does not exclude the possibility of using other naming methods in 5G networks and other future networks. For example, in 6G networks, some or all of the above network elements may continue to use the terms in 5G, or other names may be adopted.

[0125] To facilitate the understanding of the embodiments of this application, some basic concepts related to this application are briefly described.

[0126] 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 is a new technical science that studies, develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence, attempting to understand the essence of intelligence and produce an intelligent machine that can respond in a way similar to human intelligence. The research in this field includes robots, speech recognition, image recognition, natural language processing, and expert systems, etc. The AI model involved in this application can be understood as a model that can achieve different functions through AI technology. For example, the AI model can be used for data reasoning, including but not limited to: signal processing, signal generation, or channel estimation, etc.

[0127] In this application, the "model" mentioned hereinafter includes an AI model or other models that can achieve data analysis or data reasoning. No specific limitations are imposed on the names of the models in this application.

[0128] 2. Analytics identify: It can be abbreviated as analytics ID. The same analytics ID can correspond to multiple models. For example, a consumer in the network can request a model based on the analytics ID.

[0129] Exemplarily, analytics ID #1 corresponds to model #1, and analytics ID #2 corresponds to model #2 and model #3. If a consumer requests the model corresponding to analytics ID #2, it can be understood that the model required by the consumer is model #2 or model #3.

[0130] 3. Attribute information of the model: In this application, the attribute information of the model is the relevant information used to determine the model, referring to the specific information of the model. For example, the attribute information of model #1 is used to indicate model #1, and the attribute information of model #2 is used to indicate model #2. The attribute information of the model can also be called other names such as parameter information of the model, selection information of the model, or information of the model, etc., which will not be elaborated here.

[0131] As an example rather than a limitation, the attribute information of the model in this application includes the following aspects of information:

[0132] 1) Filter information of a machine learning (ML) model, e.g., the filter information of the model includes at least one of information such as area of interest (AOI), single network slice selection assistance information (S-NSSAI), or network function (NF) type. Among them, 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 NF type to which the network function corresponding to the model belongs.

[0133] 2) Accuracy requirement information of the model (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%.

[0134] 3) Target time interval information of model application (ML model target period), which is used to indicate the time when the model can be applied. For example, the target time interval information of model #1 indicates that the target time interval for model #1 to be applied is from T1 to T2.

[0135] 4) Target area information of model application (ML model target area), which is used to indicate the area where the model can be applied. For example, the target area information of model #1 indicates that the target area for model #1 to be applied is City A.

[0136] 5) Interoperability information of the model (ML model interoperability information), which is used to indicate whether the model supports interoperability. It is mainly used in scenarios where the model is shared or operated. The interoperability information of the model includes information such as the format of the model and the model execution environment. Exemplarily, the platforms and formats of models used during training by different manufacturers are different. When Manufacturer 1 requests a model from Manufacturer 2, this information needs to be carried to inform Manufacturer 2 of the information of the model it needs.

[0137] 6) Input parameter information of the model, which is used to indicate the input parameters of the model. For example, when the input parameter types of the model are applied in the same application scenarios of different models (such as location models), they can all be used for location in the same area or slice. However, due to different input parameters of the models, different models are used. Therefore, this parameter is used to determine the required model.

[0138] 7) Output parameter information of the model, which is used to indicate the output parameters of the model. For example, the type of the output parameters of the model. Similar to the input information of the above-mentioned model. The outputs of different models in the same scenario may be different.

[0139] 8) Required resource information of the model: It refers to the amount of resources required for the model requested by the consumer (such as the required software and hardware resources, etc.), and can also be referred to as the size information of the model, or the dimension information (size) of the model, etc. For example, if the consumer determines based on the running ability of the model on the platform that it can only run models with a size of less than 1G (i.e., models with required resources less than 1G), this parameter can prevent the requested model from not being able to run on the consumer's platform.

[0140] 9) Scenario information of model application, which is used to indicate the scenarios where the model can be applied.

[0141] It should be understood that the above 1) to 9) are only examples to illustrate the possible forms of the attribute information of the model in this application, and do not constitute any limitation to the protection scope of this application. Other information that can indicate a certain model is also within the protection scope of this application. For example, the attribute information of the model also includes information about the analysis object corresponding to the model.

[0142] Specifically, the attribute information of different models is different. For example, the attribute information of AI model #1 includes usage time #1, analysis object #1, or accuracy #1, and the attribute information of AI model #2 includes usage time #2, analysis object #2, or accuracy #2, where 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.

[0143] 4. Model management: Model management is performed based on the analysis ID in NWDAF (such as NWDAF(MTLF)). Specifically, in the current model management technology, NWDAF supports model management at the analysis ID granularity. For example, when there are multiple NWDAFs in the same area, and different NWDAFs all support the same analysis ID, but the model information stored in different NWDAFs is different.

[0144] As an example but not a limitation, when NWDAF performs model management based on the analysis ID, the following information associated with the AI model is stored:

[0145] Analysis ID, filtering information of the model, model interoperability indicator (ML model interoperability indicator), etc.

[0146] 5. Model Configuration Management Function (MCMF): It is a logical function used to implement the configuration and management of AI models. Among them, MCMF can be set as a separate network element or co-located with other network elements (such as co-located with the consumer, co-located with network elements such as NWDAF (AnLF), AMF, ADRF, etc.). This application does not make any limitations in this regard.

[0147] The above Figure 1 briefly introduced the scenarios where the communication method provided by the embodiments of this application can be applied, and introduced the basic concepts that may be involved in the embodiments of this application. Among the basic concepts, an AI model and an analysis ID were introduced. A way for a user to request an AI model is: request the AI model from the NRF based on the analysis ID. This way for the user to request the AI model includes the following steps:

[0148] Step 1: The user sends a network element discovery request message to the NRF. The network element discovery request message includes the analysis ID and at least one of the following information:

[0149] Filtering information of the model, model interoperability indication, user information, or NWDAF capability information, etc.

[0150] Among them, the filtering information of the model includes the area of interest (AOI) and / or single network slice selection assistance information (S-NSSAI). The AOI indicates the area of interest of the requested analysis ID, and the 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; the user information is mainly used for the model interoperability request scenario; the NWDAF capability information is used to indicate the capabilities of the NWDAF, such as whether it supports federated learning (FL), accuracy check, or the ability to exchange analysis in the roaming scenario (roaming exchange capability).

[0151] Step 2: After receiving the network element discovery request, the NRF can view the NWDAF that supports the analysis ID.

[0152] However, in this implementation method, the NRF cannot view the specific model information under the analysis ID.

[0153] Step 3: The NRF sends the list of candidate NWDAFs corresponding to the analysis ID to the user.

[0154] It should be understood that in this implementation mode, the user cannot discover the information of the NWDAF storing the required model during the network element discovery phase. There is a situation where a NWDAF that does not have the model but supports the analysis ID is selected, resulting in repeated training of the model by this NWDAF and thus wasting network resources.

[0155] Another way for the user to request an AI model is: request the AI model from the ADRF based on the analysis ID. This way for the user to request the AI model includes the following steps:

[0156] Step 1: The user sends a model retrieval request message to the ADRF. The model retrieval request message includes the analysis ID and at least one of the following information:

[0157] Filtering information of the model or information of the target NWDAF subscribing to the model.

[0158] Step 2: The ADRF confirms whether the model is stored in the ADRF.

[0159] If the ADRF confirms that the model is not stored in the ADRF, the ADRF sends a network element discovery request to the NRF, requests to discover the NWDAF (MTLF), and sends a model subscription request or a model retraining request to this NWDAF (MTLF). The NWDAF (MTLF) sends the trained model to the ADRF.

[0160] Step 3: The ADRF then sends the obtained model to the user.

[0161] In addition, in this implementation mode, the user can also obtain an updated model. For example, this way for the user to request the AI model further includes the following steps:

[0162] Step 4: The user subscribes to model updates from the ADRF, and the ADRF returns the updated model.

[0163] Furthermore, in this implementation mode, the user can also cancel the process of obtaining the subscribed model. For example, this way for the user to request the AI model further includes the following steps:

[0164] Step 5: The user notifies the ADRF to cancel the model subscription.

[0165] It should be understood that in this implementation mode, the consumer bypasses the MTLF and directly requests the model from the ADRF, which will cause model authorization problems. Because the ADRF is only a model storage network element, not the model owner network element. The current protocol stipulates that it should be decided by the model trainer MTLF whether to allocate the model to the consumer, and the ADRF cannot directly pass the model to the consumer on behalf of the NWDAF.

[0166] To solve the problems existing in the two ways of requesting an AI model described above, the present application provides a communication method, aiming to manage the AI model on the premise of reducing the possibility of wasting network resources.

[0167] The technical solution provided by the present application will be described in detail below with reference to the accompanying drawings. The embodiments of the present application can be applied to multiple different scenarios, including Figure 1 the scenario shown, but not limited to this scenario. For example, it can also be applied to 5G, 6G or future communication systems.

[0168] It should be understood that the specific structure of the execution subject of the method provided by the embodiments of the present application is not particularly limited in the embodiments shown below. As long as it can communicate according to the method provided by the embodiments of the present application by running a program recording 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.

[0169] Hereinafter, without loss of generality, the communication method provided by the embodiments of the present application will be described in detail by taking the interaction between network elements as an example.

[0170] Figure 2 is a schematic flowchart of a communication method provided by the present application, including the following steps:

[0171] S210, the third network element sends a registration message to the second network element. Correspondingly, the second network element receives the registration message from the third network element.

[0172] In this embodiment, the third network element is a network element with the attribute information of the stored model and the function of sending the model to the device requesting the model, such as the MCMF shown above; the second network element is a network element with the network element management function, such as the NRF shown above. It should be understood that the names of the network elements are not limited in any way in this embodiment, and any network element that can implement the corresponding function is within the protection scope of the present application.

[0173] Specifically, the registration information 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 to store the attribute information of the model, and the second capability is the ability to send the model (such as the ability to send the model to the device requesting the model). For example, this capability information is used to indicate that the third network element has a model management capability (ML model management capability).

[0174] Exemplarily, the registration information may further include the identifier of at least one network element, and the identifier of the at least one network element is used to indicate at least one network element to which the attribute information of the model is stored in the third network element, that is, the third network element is used to manage the model trained by the at least one network element. Optionally, the registration information includes the supported NWDAF(MTLF) ID, indicating which models trained in MTLF the third network element supports. When there are multiple models trained in MTLF in the system and only some MTLF register the attribute information of their trained models to the third network element, the third network element supports the configuration and management of the models in these MTLF. 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 (such as Model#1, Model#2, Model#3, and Model#4).

[0175] Exemplarily, the registration information may further include the ML model category, and the ML model category is used to indicate the type to which the model managed by the third network element belongs. For example, the ML model category indicates that the categories of models supported by the third network element include, but are not limited to, positioning models, perception models, etc.

[0176] As a possible implementation, in this embodiment, the third network element may be a network element independently deployed in the communication system and may communicate with other network elements (such as the second network element, the third network element, etc.) in the system through a service-based interface.

[0177] As another possible implementation, in this embodiment, the third network element may be co-located with an existing network element in the communication system so that the existing network element 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 element. For example, the third network element may be co-located with the localization management function (LMF); also for example, the third network element may also be co-located with network elements such as AMF / SMF, and no further examples are given here.

[0178] In the case where the third network element is co-located with an existing network element, 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.

[0179] Further, when the second network element sends a registration success message to the third network element, then Figure 2 The method flow shown further includes:

[0180] S220, the second network element sends a registration success message to the third network element. Correspondingly, the third network element receives the registration success message from the second network element.

[0181] It should be understood that in this embodiment, the third network element can implement storing the attribute information of the model and the ability to send the model to the device requesting the model. Therefore, after a network element (such as the first network element) in the communication system trains a model, the attribute information of the model can be stored in the third network element.

[0182] It should be noted that in this embodiment, the third network element can store the attribute information of the models trained by one or more network elements for training the model. For example, the above registration message carries the identifiers of at least one network element, indicating that the third network element can store the attribute information of the models trained by the at least one network element; or, for another example, the above registration message does not carry the identifier of the network element, indicating that the third network element can store the attribute information of the models trained by all network elements in the system.

[0183] For the sake of convenience of description, hereinafter, an example will be given in which the first network element stores the attribute information of the trained model in the third network element.

[0184] Then Figure 2 The method flow shown further includes:

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

[0186] Specifically, the first network element can train at least one model, and the attribute information of the at least one model can be stored in the third network element. Then, the first network element sends (or registers) the attribute information of each model in the at least one model to the third network element. For example, the first network element uses the model management registration service to store the attribute information of each model in the at least one model it trains in the third network element.

[0187] Among them, the attribute information of each model can refer to the description of the attribute information of the model in the basic concept above, which will not be elaborated 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 to which the model is applied, or the required resource information of the model. Among them,

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

[0189] In this embodiment, the third network element locally stores the attribute information of the models obtained by at least one network element, and in this embodiment, the third network element can send models to the devices requesting models. Therefore, when the first device decides to request a model, the first device can obtain the information of the third network element from the second network element, with a view to initiating a process of obtaining the model from the third network element. Then Figure 2 The shown method flow 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 ability to store the attribute information of the model and send models to the devices requesting models. For example, the second request message includes capability information (ML model management capability), and the capability information is used to indicate obtaining a third network element with a first capability and a second capability. The first capability is the ability to store the attribute information of the model, and the second capability is the ability to send models.

[0192] Optionally, the second request message may further include network element type information #1 and / or area information #1. Among them, the network element type information #1 indicates the network element type to which the network element requested by the first device belongs. For example, the network element type information #1 is MCMF; the area information #1 indicates the area supported by the network element requested by the first device. For example, 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. 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. Then the identifier of the third network element returned by the second network element to the first device may be the identifiers of multiple third network elements.

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

[0196] For ease of description, in this embodiment, an example is given where the first device receives the identifier of a certain 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 to obtain the first model. The first request message includes the attribute information of the first model. Among them, the attribute information of the first model can refer to the description of the attribute information of the model in the basic concept above and will not be elaborated here. For example, the attribute information of the first model includes at least one of the following information:

[0199] The input parameter information of the first model, the output parameter information of the first model, the scenario information applied by the first model, or the required resource information of the first model.

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

[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 the attribute information of model #1, the attribute information of model #2, the attribute information of model #3, …, the 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 attribute information of at least one model stored locally, the third network element determines that the first model is model #1. Herein, the matching of the attribute information of the first model and the information of model #1 can be understood as that the attribute information of the first model is the same as 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. 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 can provide it to the first device through the first response message. Alternatively, if the third network element fails to determine the first model, the first response message may include first indication information for indicating a refusal to provide the first model.

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

[0207] Further, 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 it can provide the first model to the first device. Then Figure 2 The shown method flow may further include:

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

[0209] In this embodiment, the third network element may further determine that the network element that trained the first model is the first network element according to the determined first model. For example, the third network element locally stores the information of the first network element that trained the first model. Therefore, after the third network element determines the first model, the third network element may determine that the network element that trained the first model is the first network element.

[0210] Specifically, the first message includes the information of the first device and first information. The first information includes the identifier of the first model and / or the attribute information of the first model. The information of the first device and the first information are used for the first network element to confirm whether the first model is authorized for 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 the 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 the 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, there is no limitation on the information of the first device, and any information that can be used to identify the first device is within the protection scope of this application.

[0212] Exemplarily, the first information is the information indicating the first model. For example, the third network element can 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 can determine the first model required by the first device based on the attribute information of the first model; or, after the third network element determines the first model, it can send the identifier (ID) of the first model to the first network element through the first message, so that the first network element can 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 for the first device.

[0215] Specifically, the first network element determines whether the first model is authorized for 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 according to the first information, and the first model can be authorized for the first device (for example, the first network element determines the devices that the first model can be authorized for during the process of training the first model); also for example, the first network element determines that the model required by the first device is the first model according to the first information, and the first model cannot be authorized for the first device.

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

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

[0219] When the first confirmation information received by the third network element indicates that the first model can be authorized for the first device, the third network element can 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 through the above-mentioned first response message, where the first indication information is used to indicate the refusal to provide the first model. Optionally, a cause value may be carried in the first indication information, and the cause value is used to indicate the reason for refusing to provide the first model. For example, the cause value indicates that the first device is a device that cannot obtain the first model.

[0221] As can be seen from the above, Figure 2 In the communication method shown, by arranging a third network element with the ability to store the attribute information of the model and send the model to the device requesting the model in the communication system, 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. Thus, in the process of the device requesting the model (such as a consumer), the appropriate model can be requested from the third network element based on the specific information of the required model, so as to obtain the appropriate model, and to a certain extent, it can reduce the waste of resources caused by unnecessary model training by the network element that trains the model in the system.

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

[0223] This application also provides another communication method. By carrying the specific information of the required model in the process of requesting the model, it can, to a certain extent, prevent the consumer from selecting a network element that does not have the required model to request the model, resulting in retraining of the model. The following will be combined with Figure 3 This communication method will be introduced in detail.

[0224] Figure 3 FIG. is a schematic flowchart of a communication method provided by this application, including the following steps:

[0225] S310, the fourth network element sends a second message to the fifth network element. 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 with model management functions (such as the function of sending the model to the device requesting the model), such as the MCMF shown above; the second network element is a data analysis and storage network element, such as the ADRF shown above. It should be understood that in this embodiment, no specific limitations are imposed on the names of the network elements, and any network element that can implement the corresponding functions is within the protection scope of this application.

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

[0228] The input parameter information of the first model, the output parameter information of the first model, the scenario information applied by the first model, or the required resource information of the first model.

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

[0230] The fourth network element is a separately deployed functional network element; or the fourth network element can be co-located with the AMF / SMF serving the first device.

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

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

[0233] In this embodiment, the precondition for the fourth network element to be able to send the above second message to the fifth network element is that the fourth network element obtains the fifth network element information from the second network element. Then Figure 3 The shown method flow further includes:

[0234] S311, the fourth network element sends message #1 to the second network element. 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, this message #1 is used to request the second network element to provide a fifth network element with model storage capabilities. This message #1 includes the following information:

[0237] NE type information #2, capability information #2, and area information #2. Among them, the NE type information #2 indicates the NE type to which the NE requested by the fourth NE belongs. For example, the NE type information #2 is ADRF; the capability information 2 indicates the capabilities of the NE requested by the fourth NE. For example, the capability information #2 indicates an NE with model storage capability; the area information #2 indicates the area supported by the NE requested by the fourth NE. For example, the area information #2 is AOI#2.

[0238] Further, after receiving the above-mentioned message #1 in this embodiment, the second NE selects an NE that meets the requirements and returns the identifier of the NE that meets the requirements to the fourth NE. Then Figure 3 The method flow shown also includes:

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

[0240] Exemplarily, after receiving message #1 in this embodiment, the selected NEs that meet the requirements by the second NE may include at least one. Then the identifier of the fifth NE returned by the second NE to the fourth NE may be the identifiers of multiple fifth NEs.

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

[0242] For ease of description, in this embodiment, an example is given where the fourth NE receives the identifier of a certain fifth NE from the second NE and sends the first message to the fifth NE.

[0243] Further, after receiving the above-mentioned second message in this embodiment, the fifth NE 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. Then Figure 3 The method flow shown also includes:

[0244] S320, the fifth NE determines the first model.

[0245] Specifically, the fifth NE 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 the attribute information of Model #1, the attribute information of Model #2, the attribute information of Model #3, …, the 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. Herein, the matching of the attribute information of the first model and the information of Model #1 can be understood as the attribute information of the first model being the same as or substantially the same as the attribute information of Model #1.

[0247] After the fifth network element determines the first model in this embodiment, the following two possible implementation manners can be adopted to determine whether the first model can be provided to the first device:

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

[0249] In this implementation manner, Figure 3 The method shown 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 according to the attribute information of at least one model saved locally. The specific manner of determining the first network element will not be elaborated here.

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

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

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

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

[0257] S323. The first network element sends the second confirmation information to the fifth network element. 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 for 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 for 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 for the first device, the fifth network element may send the second indication information to the fourth network element. The second indication information is used to indicate the rejection of providing the first model. Optionally, a cause value may be carried in the second indication information, and the cause value is used to indicate the reason for rejecting to provide the first model. For example, the cause value indicates that the first device is a device that cannot obtain the first model.

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

[0263] In this implementation, Figure 3 The method shown further includes the following steps:

[0264] S331. The fifth network element sends the information of the first network element to the fourth network element. Correspondingly, the fourth network element receives the 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 (such as the ID of the first network element) in a response message (such as a model query result message) in response to the above first message.

[0266] Exemplarily, the model query result message may further include the identifier of the first model and / or result information. 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, the result information being "success" indicates that the fifth network element has successfully determined the first model; also for example, the result information being "failed" 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. Correspondingly, the first network element receives the fourth message from the fourth network element.

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

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

[0270] Step S333 may refer to the description of step S322 above and will not be elaborated 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] The 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. 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 for the first device, the response message #1 includes the first model or the address information of the first model. Among them, 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 of the first model in the fifth network element (Uniform Resource Locator (URL)).

[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, a cause value may be carried in the third indication information. The cause value is used to indicate the reason for refusing to provide the first model. For example, the cause value indicates that the first device is a device that cannot obtain the first model.

[0276] Exemplarily, if the address information of the first model included in the first response message includes the URL of the first model in the fifth network element, the first response message may further include first indication information, which is used to indicate whether it is possible to obtain the first model from the fifth network element. For example, the first indication information is the token information for obtaining the first model in the fifth network element. The token information for obtaining the model in the fifth network element is allocated by the first network element during model storage, sent to the fifth network element during model storage, and saved by the fifth network element as the credential information for obtaining the model.

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

[0278] As a possible implementation, if the first model is carried in response message #1, the fourth network element may directly obtain the first model from response message #1.

[0279] As another possible implementation, if the address information of the first model is carried in response message #1, the fourth network element may obtain the first model according to the address information of the first model. For example, when the address information of the first model is a URL, the fourth network element directly downloads the first model from the URL.

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

[0281] As a possible implementation, if the fourth network element is co-located with the first device, the steps performed by the above-mentioned fourth network element may be understood as the steps performed by the first device, and the fourth network element may be understood as the functional enhancement of the first device.

[0282] As a possible implementation, if the fourth network element is independently deployed, in this implementation, Figure 3 The shown method flow further includes:

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

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

[0285] NE type information #3, capability information #3, and area information #3. Among them, the NE type information #3 indicates the NE type to which the NE requested by the first device belongs. For example, the NE type information #3 is MCMF; the capability information #3 indicates the capabilities of the NE requested by the first device. For example, the capability information #3 indicates an NE with model management capability; the area information #3 indicates the area supported by the NE requested by the first device. For example, the area information #3 is AOI #3.

[0286] Further, after the second NE receives the above-mentioned message #2 in this embodiment, it selects an NE that meets the requirements and returns the identifier of the NE that meets the requirements to the first device. Then Figure 3 The method flow shown also includes:

[0287] S302, the second NE sends the identifier of the fourth NE to the first device. Correspondingly, the first device receives the identifier of the fourth NE from the second NE.

[0288] Exemplarily, after the second NE receives the message #2 in this embodiment, the selected NE that meets the requirements may include at least one. Then the identifier of the fourth NE returned by the second NE to the first device may be the identifiers of multiple fourth NEs.

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

[0290] For ease of description, in this embodiment, an example is given where the first device receives the identifier of a certain fourth NE from the second NE and sends the third request message to the fourth NE.

[0291] S303, the first device sends the third request message to the fourth NE. Correspondingly, the fourth NE 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 the indication information of the first device and the attribute information of the first model.

[0293] In addition, in this implementation manner, after the fourth NE obtains the above-mentioned first model, the address information of the first model, or the information indicating the refusal to provide the first model, it can provide the obtained first model, the address information of the first model, or the information indicating the refusal to provide the first model to the first device through the second response message. ThenFigure 3 The method shown also includes:

[0294] S304, the fourth network element sends a second response message to the first device, and 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 a refusal to provide the first model (e.g., the above-mentioned second indication information or third indication information).

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

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

[0298] Exemplarily, when the fourth network element is co-located with the AMF or SMF serving the first device, and the first device requests the first model through the AMF or SMF serving the first device, the first device can send the third request message to the AMF or SMF through a registration request or 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 the model query request message, for indicating which devices the model query request is for subscribing to the model. 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 (e.g., UE ID list) in the model query request message sent to the fifth network element.

[0299] In addition, the above-mentioned fourth network element and fifth network element can also be co-located as a sixth network element, such as enhancing the function of the fifth network element (e.g., ADRF) 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 co-located, Figure 3 the signaling interaction between the fourth network element and the fifth network element in the communication method shown can be omitted, and the steps performed by the fourth network element and the fifth network element are implemented by the sixth network element. The specific process is as follows Figure 4 shown:

[0300] Figure 4 is a schematic flowchart of a communication method provided by this application, and the sixth network element is the above-mentioned Figure 3The network element jointly established by the fourth network element and the fifth network element has the functions of the above-mentioned fourth network element and the fifth network element, and specifically includes the following steps:

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

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

[0303] Network element type information #4, capability information #4, and area information #4. Among them, the network element type information #4 indicates the network element type to which the network element requested by the first device belongs. For example, the network element type information #4 is ADRF; the capability information #4 indicates the capabilities of the network element requested by the first device. For example, the capability information #4 refers to a network element with model management capabilities (ML model management capability) and model storage capabilities (ML model storage capability); the area information #4 indicates the area supported by the network element requested by the first device. For example, the 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, there may be at least one network element that meets the requirements selected, so the identifier of the sixth network element returned by the second network element to the first device may be the identifiers of multiple sixth network elements.

[0306] For example, if the second network element determines that the sixth network elements that meet the requirements include 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 the third request message to multiple different sixth network elements in sequence (or simultaneously, or in other ways) to obtain the first model.

[0307] For the sake of convenience of description, in this embodiment, an example is given where the first device receives the identifier of a certain sixth network element from the second network element and sends the third request message to this sixth network element.

[0308] S430. The first device sends the 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, and the indication information of the first device and the attribute information of the first model are included in the third request message.

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

[0311] The input parameter information of the first model, the output parameter information of the first model, the scenario information applied by the first model, or the required resource information of the first model.

[0312] Exemplarily, the indication information of the first device refers to the information of the first device. For example, the indication information of the first device may be the 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; also, 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 stores locally the attribute information of model #1, the attribute information of model #2, the attribute information of model #3,..., the 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 among the attribute information of at least one model stored locally, the sixth network element determines that the first model is model #1. Here, the matching of the attribute information of the first model and the information of model #1 can be understood as that the attribute information of the first model is 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] Referring to the description of step S321 above, it will not be elaborated here. The difference is that in this embodiment, the sixth network element has the functions of the above fourth network element and fifth network element.

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

[0319] Referring to the description of step S322 above, it will not be elaborated here.

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

[0321] Referring to the description of step S323 above, it will not be elaborated here.

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

[0323] Referring to the description of step S304 above, it will not be elaborated here.

[0324] The above Figure 3 and Figure 4 In the communication method shown above, during the process of requesting the first model, specific information of the first model (such as input parameter information of the first model, output parameter information of the first model, scenario information applied by the first model, or required resource information of the first model, etc.) is carried, so that the fifth network element can know the specific model requested, thereby providing a suitable model, rather than providing multiple NWDAF identifiers for training models based on the analysis ID, which may cause the consumer to select a NWDAF that currently does not have a model and send a model subscription request to it. When this NWDAF receives the model subscription request, it will retrain to obtain a model, resulting in waste of network resources.

[0325] In addition, the first network element that trains the first model can authenticate whether the first model is authorized for the first device, so as to avoid providing the first model to the first device without authorization.

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

[0327] It should also be understood that in various embodiments of the present application, if there is no special description and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be mutually referred to, 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 the existing network architecture are mainly used as examples for illustrative purposes. It should be understood that the specific form of the device is not limited in the embodiments of the present application. For example, devices that can achieve the same functions in the future are applicable to the embodiments of the present application.

[0329] It can be understood that, in each of the above method embodiments, the methods and operations implemented by a 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 available for the device (such as a chip or a circuit).

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

[0331] As mentioned above, in combination with Figures 2 to 4 The communication method provided by the embodiments of the present application has been described in detail above. The above communication method has been mainly introduced from the perspective of network elements. It can be understood that, in order to implement the above functions, a network element includes corresponding hardware structures and / or software modules for executing each function.

[0332] Those skilled in the art should be able to realize 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 certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described function for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0333] As follows, in combination with Figures 5 to 7 The communication device provided by the embodiments of the present application will be described in detail. It should be understood that the description of the device embodiments corresponds to the description of the method embodiments. Therefore, for the content not described in detail, reference can be made to the above method embodiments. For the sake of brevity, some content will not be repeated.

[0334] The embodiments of the present application can perform function module division on the sending device or the receiving device according to the above method examples. For example, each function module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software function module. It should be noted that the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation. The following will be described by taking the example of dividing each function module corresponding to each function.

[0335] Figure 5It is a schematic block diagram of a communication device 10 provided by 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 for data processing. Or rather, the transceiver module 11 is used to perform operations related to reception and transmission, and the processing module 12 is used to perform other operations except reception and transmission. 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. The storage module 13 can be used to store instructions and / or data. The processing module 12 can read the instructions and / or data in the storage module so that the device can implement the actions of the device in the foregoing method embodiments.

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

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

[0339] In a possible implementation manner, the transceiver module 11 is used to send a registration message, and the registration message includes capability information. The capability information is used to indicate having 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. The transceiver module 11 is used to receive attribute information of at least one model. The attribute information of the model includes at least one of the following information: input parameter information of the model, output parameter information of the model, scenario information applied by the model, or required resource information of the model.

[0340] When the device 10 is used to execute Figure 2 the method in, the transceiver module 11 can be used to execute the steps of receiving and sending 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 processes of each unit executing the above corresponding steps have been described in detail in the foregoing method embodiments. For the sake of brevity, they will not be repeated here.

[0342] In another design, the device 10 may correspond to the first network element in the foregoing 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 performed by the first network element in the above method embodiments. Among them, the transceiver module 11 can be used to perform the operations related to the transceiver of the first network element in the above method embodiments, and the processing module 12 can be used to perform the operations related to the processing of the first network element in the above method embodiments.

[0344] In a possible implementation manner, the processing module 12 is configured to obtain the predicted network transmission capacity for the data of the first terminal device; obtain the predicted data characteristics for the data of the first terminal device. The processing module 12 is configured to determine the control of the current data of the first terminal device according to the predicted network transmission capacity and the predicted data characteristics.

[0345] In another possible implementation manner, the transceiver module 11 is configured to receive a first message, where the first message includes information of a first device and first information, the first information includes an identifier of a first model and / or attribute information of the first model, the first device is a device that requests 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. The processing module 12 is configured to determine whether the first model is authorized for the first device according to the information of the first device and the first information. The transceiver module 11 is configured to send a first confirmation message, and the first confirmation message is used to indicate whether the first model is authorized for the first device.

[0346] When the device 10 is used to execute Figure 2 the method in, 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 Figure 3 the method in, 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 Figure 4 the method in, the transceiver module 11 can 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 can be used to execute the processing steps in the method, such as step S460.

[0349] It should be understood that the specific processes for each unit to execute the above corresponding steps have been described in detail in the above method embodiments. For the sake of brevity, they will not be elaborated here.

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

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

[0352] In a possible implementation, the transceiver module 11 is used to send a first request message for requesting to obtain a first model. 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. The transceiver module 11 is used to receive a first response message, which includes the first model or a first indication information for indicating refusal to provide the first model.

[0353] When the device 10 is used to execute Figure 2 the method in, the transceiver module 11 may be used to execute the steps of transceiver 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 Figure 3 the method in, the transceiver module 11 may be used to execute the steps of transceiver 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 Figure 4 the method in, the transceiver module 11 may be used to execute the steps of transceiver 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 processes for each unit to execute the above corresponding steps have been described in detail in the above method embodiments. For the sake of brevity, they will not be repeated here.

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

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

[0359] In a possible implementation manner, the transceiver module 11 is used to send a second message, 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 transceiver module 11 is used 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, and the address information of the first model is used to obtain the first model.

[0360] When the device 10 is used to execute Figure 3 the method in, 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, 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 processes for each unit to execute the above corresponding steps have been described in detail in the above method embodiments. For the sake of brevity, they will not be repeated here.

[0362] In another design, the device 10 can correspond to the fifth network element in the above method embodiments, or 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 embodiments. Among them, the transceiver module 11 can be used to execute the operations related to the transceiver of the fifth network element in the above method embodiments, and the processing module 12 can be used to execute the operations related to the processing of the fifth network element in the above method embodiments.

[0364] In a possible implementation manner, the transceiver module 11 is used to receive a second message, 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 processing module 12 is used to determine the first model according to the attribute information of the first model and the attribute information of at least one model stored locally.

[0365] When the device 10 is used to executeFigure 3 When implementing the method in [description], 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, 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 processes of each unit executing the corresponding steps above have been described in detail in the above method embodiments. For the sake of brevity, they will not be repeated here.

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

[0368] The device 10 of each of the above solutions has the function of implementing the corresponding steps executed 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, etc.) in the above method. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above 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 to respectively execute the sending and receiving operations and related processing operations in each method embodiment.

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

[0370] Figure 6 It is a schematic diagram of another communication device 20 provided by an embodiment of the present application. The device 20 includes a processor 21, and the processor 21 is used to execute the computer program or instruction stored in the memory 22, or read the data / signaling stored in the memory 22 to execute the methods in the above method embodiments. Optionally, the processor 21 is one or more.

[0371] Optionally, as Figure 6 shown, 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 is one or more memories 22.

[0372] Optionally, as Figure 6 shown, the apparatus 20 further includes a transceiver 23 for receiving and / or transmitting signals. For example, the processor 21 is used to control the transceiver 23 to receive and / or transmit signals.

[0373] As a solution, the apparatus 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, etc. 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 also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be 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 ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). For example, the RAM can be used as an external cache. By way of example and not limitation, the RAM includes the following various forms: static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (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 devices, discrete gate or transistor logic devices, discrete hardware components, the memory (storage module) can be integrated in 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] Figure 7 It is a schematic diagram of a chip system 30 provided by an embodiment of the present application. The chip system 30 (or can also be referred to as a processing system) includes a logic circuit 31 and an input / output interface 32.

[0379] Among them, the logic circuit 31 can be the processing circuit in the chip system 30. The logic circuit 31 can be coupled to the storage unit and call the instructions in the storage unit, so that the chip system 30 can implement the methods and functions of the embodiments of the present application. The input / output interface 32 can be the input / output circuit in the chip system 30, output the information processed by the chip system 30, or input the 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 operations related to the processing 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 operations related to sending and / or receiving 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 performed by the devices in the above method embodiments are stored.

[0383] For example, when the computer program is executed by a computer, the computer can 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 method embodiments.

[0384] An embodiment of the present application further provides a computer program product, including 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 method embodiments.

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

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

[0387] The explanations and beneficial effects of the relevant content in any of the above-provided devices can refer to the corresponding method embodiments provided above, and will not be elaborated here.

[0388] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0389] Those skilled in the art can 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 foregoing method embodiments, and will not be elaborated here.

[0390] In several embodiments provided by the present 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 illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

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

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

[0393] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing 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 methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0394] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope 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 the attribute information of a model, and the second capability is the capability of sending the 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 through data training, and the second network element is used to manage the network elements in the 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. 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, which 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 the 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, and the rejection indication is used to indicate a rejection of providing the first model.

9. The method according to claim 8, wherein The method further includes: Send 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; Receive first confirmation information, where the first confirmation information 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: Receive 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 where the first model is applied, or required resource information of the first model; Determine whether the first model is authorized for the first device according to the information of the first device and the first information; Send first confirmation information, where the first confirmation information is used to indicate whether the first model is authorized for the first device.

13. A communication method, characterized in that, Includes: Send a first request message, where the first request message is used to request to obtain a first model, and 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 where the first model is applied, or required resource information of the first model; Receive a first response message, where the first response message includes the first model or first indication information, and the first indication information is used to indicate a rejection of providing the first model.

14. The method according to claim 13, wherein The method further includes: Send a second request message, where the second request message is used to request to obtain an identifier of a third network element, and the second request message carries capability information, and the capability information is used to indicate 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; Receive 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 where 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 about a first device and first information. The first information includes the identifier of the first model and / or the attribute information of the first model. The first device is the 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 the 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 about 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 about a first device and first information. The first information includes the identifier of the first model and / or the attribute information of the first model. The first device is the 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 required resource information of 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, wherein 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 required resource information of 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 for indicating 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, the at least one module being 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 which, when run, implements the method according to any one of claims 1 to 23.

Images