Communication method and apparatus

Abstract

The present application relates to the technical field of communications, and provides a communication method and apparatus, for use in acquiring a model. In the method, an AnLF function entity can determine to acquire a first model by determining that a first notification message carries first indication information. For example, when the first notification message is used for providing an updated model, the first notification message can carry first indication information used for indicating that the first model has been updated, so that on the basis of the first indication information, the AnLF function entity determines that the first model has been updated, i.e., determining to acquire the first model. For another example, when the first notification message is used for providing a new model or the updated model, the first notification message can carry first instruction information used for instructing an MTLF function entity to provide a model, so that the AnLF function entity determines, on the basis of the first instruction information, that the first model needs to be acquired, and acquires the first model. In this way, when determining that the first model needs to be acquired, the AnLF function entity acquires the first model.

Description

Communication method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on September 28, 2023, with application number 202311286458.3 and application name “Communication Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

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

[0003] Currently, the network architecture of fifth-generation (5G) mobile communication systems enables the provision of models (such as machine learning (ML) models) for data analysis and other operations. For example, in a perception scenario, models can be used to analyze perception data and generate perception results. These results can then be used to adjust and improve network operational efficiency and system performance.

[0004] However, how to obtain the model is a hot topic of discussion.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a communication method and apparatus for acquiring a model.

[0007] To achieve the above objectives, this application adopts the following technical solutions:

[0008] In a first aspect, a communication method is provided, which includes: an analysis logic function AnLF functional entity receives a first notification message from a model training logic function MTLF functional entity, and performs an operation for obtaining a first model when the first notification message also carries first indication information; wherein the first notification message carries a model identifier, the model identifier is used to indicate the first model, the first indication information is used to indicate that the first model is updated, or the first indication information is used to instruct the MTLF functional entity to provide the first model.

[0009] Based on the method described in the first aspect, it can be known that the AnLF functional entity can determine to obtain the first model and perform the operation for obtaining the first model by determining that the first notification message carries the first indication information. For example, when the first notification message is used to provide an updated model, the first notification message can carry the first indication information for indicating that the first model is updated, so that the AnLF functional entity can determine that the first model is updated according to the first indication information, that is, determine to obtain the first model. For another example, when the first notification message is used to provide a new model or an updated model, the first notification message can carry the first indication information for instructing the MTLF functional entity to provide the first model, so that the AnLF functional entity can determine that the first model needs to be obtained according to the first indication information, and obtain the first model. In this way, the first model can be obtained when the AnLF functional entity determines that the first model needs to be obtained.

[0010] In one possible design, the method described in the first aspect further includes: if the first notification message does not carry the first indication information, the AnLF functional entity does not perform the operation for obtaining the first model. It will be appreciated that the absence of the first indication information in the first notification message may indicate that the first model has not been updated, or that the first model has already been provided to the AnLF functional entity. In this case, the AnLF functional entity does not need to obtain the first model. This prevents the AnLF functional entity from repeatedly obtaining the first model, thereby ensuring that the AnLF functional entity's acquisition of the first model is effective and reducing the AnLF functional entity's overhead.

[0011] Optionally, when the first notification message does not carry the first indication information, the AnLF functional entity does not perform the operation for obtaining the first model, including: when the first notification message carries neither the first indication information nor the indication information indicating that the message type is a model delivery notification message, the AnLF functional entity does not perform the operation for obtaining the first model. The model delivery notification message can be understood as a message used to provide a model to the AnLF functional entity for the first time, that is, a message providing a new model. That is to say, when the first indication information is used to indicate that the first model is updated, the first notification message does not carry the first indication information and the indication information can indicate that the first notification message does not provide a new model or an updated model. At this time, the AnLF functional entity does not need to obtain the first model, that is, the operation for obtaining the first model is not performed. In this way, the AnLF functional entity can be prevented from repeatedly obtaining the first model, thereby making the behavior of the AnLF functional entity obtaining the first model effective and reducing the overhead of the AnLF functional entity.

[0012] In one possible design, the first indication information is used to indicate that the first model is updated, specifically including: the first indication information is used to indicate that the message type of the first notification message is a model update notification message. That is, the first indication information can indicate that the first model is updated by indicating the type of the first notification message.

[0013] Optionally, when the first notification message carries first indication information, the AnLF functional entity performs an operation for acquiring the first model, including: the AnLF functional entity determining, based on the first indication information, that the message type of the first notification message is a model update notification message; and the AnLF functional entity performing an operation for acquiring the first model based on the message type of the first notification message being a model update notification message and the model identifier. That is, when the first indication information indicates that the message type of the first notification message is a model update notification message, the AnLF functional entity may determine the type of the first notification message based on the first indication information carried in the first notification message; and upon determining that the message type of the first notification message is a model update notification message, determine that the first model has been updated and acquire the first model.

[0014] In one possible design, the method described in the first aspect further includes: the AnLF functional entity receiving a second notification message from the MTLF functional entity, the second notification message carrying a model identifier and second indication information, the second indication information being used to indicate that the second notification message is a model delivery notification message. In other words, the second notification message can be used to provide a model even if the AnLF functional entity has not yet acquired the model. Thus, upon receiving the second notification message, the AnLF functional entity can determine to acquire the model based on the second indication information and acquire the model.

[0015] Optionally, after the AnLF functional entity receives the second notification message from the MTLF functional entity, the method described in the first aspect further includes: the AnLF functional entity determining, based on the second indication information, that the message type of the second notification message is a model-delivered notification message; and the AnLF functional entity performing an operation for acquiring the first model based on the message type of the second notification message being a model-delivered notification message and the model identifier. That is, when the second indication information indicates that the message type of the second notification message is a model-delivered notification message, the AnLF functional entity may determine the type of the second notification message based on the second indication information carried in the second notification message; and upon determining that the message type of the second notification message is a model-delivered notification message, acquire the first model.

[0016] In a possible design scheme, the method described in the first aspect further includes: the AnLF functional entity receives a third notification message from the MTLF functional entity, the third notification message carries a model identifier and third indication information, the third indication information is used to indicate that the message type of the third notification message is a model accuracy notification message; the AnLF functional entity does not perform an operation for obtaining the first model according to the third indication information. It can be understood that the model accuracy notification message is used to notify the accuracy information of the model, that is, in this case, the first model has not been updated, and the AnLF functional entity does not need to obtain the first model. In other words, after receiving the third notification message, the AnLF functional entity can determine that the message type of the third notification message is a model accuracy notification message according to the third indication information, that is, it does not repeatedly obtain the first model, thereby avoiding the AnLF functional entity from repeatedly obtaining the first model, and further reducing the overhead of the AnLF functional entity.

[0017] In one possible design solution, the operation for obtaining the first model is sending a request message for obtaining the first model.

[0018] In one possible design scheme, the first model is a model obtained by updating the second model, the model identifier of the first model is the same as the model identifier of the second model, the first model is a model retrained based on the second model, or the first model is a regenerated model.

[0019] In one possible design scheme, the model identifier is the ID of the first model and / or the uniform resource locator URL. Different model identifiers can be selected according to actual conditions, and this embodiment of the present application does not impose any restrictions.

[0020] According to a second aspect, a communication method is provided, which includes: a model training logic function MTLF functional entity obtains a first notification message and sends a first notification message to an analysis logic function AnLF functional entity; wherein the first notification message carries a model identifier, and the model identifier is used to indicate a first model; when the first model is updated, the first notification message carries first indication information, and the first indication information is used to indicate that the first model is updated; or, when the MTLF functional entity provides the first model, the first notification message carries first indication information, and the first indication information is used to instruct the MTLF functional entity to provide the first model.

[0021] In a possible design scheme, when the first model is not updated, the second notification message does not carry the first indication information; or, when the MTLF functional entity does not provide the first model, the first notification message does not carry the first indication information.

[0022] In a possible design scheme, the first indication information is used to indicate that the first model is updated, specifically including: the first indication information is used to indicate that the message type of the first notification message is a model update notification message.

[0023] In a possible design scheme, the method described in the second aspect also includes: the MTLF functional entity sends a second notification message to the AnLF functional entity, the second notification message carries a model identifier and second indication information, and the second indication information is used to indicate that the message type of the second notification message is a model delivery notification message.

[0024] In a possible design scheme, the method described in the second aspect also includes: the MTLF functional entity sends a third notification message to the AnLF functional entity, the third notification message carries a model identifier and third indication information, and the third indication information is used to indicate that the message type of the third notification message is a model accuracy notification message.

[0025] In one possible design scheme, the first model is a model obtained by updating the second model, the model identifier of the first model is the same as the model identifier of the second model, the first model is a model retrained based on the second model, or the first model is a regenerated model.

[0026] In a possible design solution, the model identifier is the ID of the first model and / or the uniform resource locator URL.

[0027] In addition, the technical effects of the method described in the second aspect can also refer to the technical effects of the method described in the first aspect, and will not be repeated here.

[0028] According to a third aspect, a communication method is provided, which includes: an analysis logic function AnLF functional entity receives a first notification message from a model training logic function MTLF functional entity; when it is determined that a first model exists, the AnLF functional entity does not perform an operation for obtaining the first model; and / or, when it is determined that the first model does not exist, the AnLF functional entity performs an operation for obtaining the first model; wherein the first notification message carries a first model identifier, and the first model identifier is used to indicate the first model.

[0029] Based on the method described in the third aspect, it can be seen that the AnLF functional entity can determine whether to obtain the first model based on whether the first model corresponding to the first model identifier exists. That is, when the AnLF functional entity determines that the first model exists, the first notification message serves to provide accuracy information of the first model. In this case, the AnLF functional entity does not need to obtain the first model, that is, the AnLF functional entity does not perform the operation for obtaining the first model. Correspondingly, when the AnLF functional entity determines that the first model does not exist, the first notification message serves to provide a new or updated model. In this case, the AnLF functional entity needs to obtain the first model, that is, the AnLF functional entity performs the operation for obtaining the first model. It can be seen that after receiving the first notification message, the AnLF functional entity can obtain or not obtain the first model according to different circumstances. That is, the AnLF functional entity can obtain the first model when it is necessary to obtain the first model. In addition, when the first model exists, the AnLF functional entity can not obtain the first model. In this way, the AnLF functional entity can avoid repeatedly obtaining the first model, thereby reducing the overhead of the AnLF functional entity.

[0030] In a possible design scheme, the method described in the third aspect also includes: the AnLF functional entity receives a second notification message from the MTLF functional entity; when it is determined that the first model does not exist, the AnLF functional entity performs an operation for obtaining the first model; the AnLF functional entity stores the first model, and / or the first model identifier; wherein the second notification message carries the first model identifier. It can be understood that the AnLF functional entity can determine whether the model exists by whether the model or the model identifier of the model is stored. That is, after obtaining the first model, the AnLF functional entity can store the first model and / or the first model identifier so that after receiving the notification carrying the first model identifier again, it can determine that the first model has been obtained by determining that the first model and / or the first model identifier is stored. That is, at this time, the AnLF functional entity does not need to obtain the first model.

[0031] Optionally, determining the existence of the first model specifically includes: the AnLF functional entity determining the existence of the first model based on a stored first model or a first model identifier. That is, the AnLF functional entity may determine the existence of the first model by determining that the first model or the first model identifier is stored, that is, determining that the first model has been obtained.

[0032] In one possible design, the first notification message also carries the first accuracy information of the first model. In this way, after receiving the first notification message, the AnLF functional entity can directly obtain the first accuracy information without having to obtain it from other sources, thereby reducing the overhead of the AnLF functional entity.

[0033] Optionally, when it is determined that the first model does not exist, the method described in the third aspect further includes: the AnLF functional entity obtains first accuracy information.

[0034] Optionally, when it is determined that the first model exists, the method of the third aspect further includes: the AnLF functional entity determining that the first notification message is a message indicating accuracy information of the first model. In this manner, the AnLF functional entity may, based on the fact that the first notification message is a message indicating accuracy information of the first model, not obtain the first model, i.e., not perform an operation for obtaining the first model, thereby reducing overhead of the AnLF functional entity.

[0035] Furthermore, the AnLF functional entity determines that the first notification message is a message for indicating accuracy information of the first model, including: the AnLF functional entity only obtains the first accuracy information. In other words, in this case, the AnLF functional entity does not obtain the first model, that is, does not perform an operation for obtaining the first model, thereby reducing the overhead of the AnLF functional entity.

[0036] In a possible design solution, the first model identifier is a model ID and / or a uniform resource locator (URL) of the first model.

[0037] In a fourth aspect, a communication method is provided, which includes: an analysis logic function AnLF functional entity receives a first notification message from a model training logic function MTLF functional entity; the AnLF functional entity determines that the first model does not exist, and performs an operation for obtaining the first model; wherein the first notification message carries a first model identifier, and the first model identifier is used to indicate the first model.

[0038] Based on the method described in aspect 4, determining that the first model does not exist can indicate that the first model has not been acquired or is not stored. In other words, in this case, the first notification message is used to provide the first model. In other words, in this case, the AnLF functional entity needs to acquire the first model. Therefore, when the AnLF functional entity determines that the first model does not exist, the AnLF functional entity performs the operation for acquiring the first model to obtain the first model. In this way, the AnLF functional entity can acquire the model when it determines that the model needs to be acquired.

[0039] In a possible design solution, after the AnLF functional entity performs an operation for acquiring the first model, the method described in the fourth aspect further includes: the AnLF functional entity storing the first model and / or the first model identifier.

[0040] Optionally, the method described in the fourth aspect further includes: the AnLF functional entity receiving a second notification message from the MTLF functional entity; the AnLF functional entity determining the existence of the first model; and the AnLF functional entity not performing an operation for acquiring the first model; wherein the second notification message carries a first model identifier. It will be understood that determining the existence of the first model may indicate that the first model has already been acquired, that is, the second notification message is used to provide accuracy information for the first model. In other words, in this case, the AnLF functional entity does not need to repeatedly acquire the first model. Therefore, when the AnLF functional entity determines the existence of the first model, the AnLF functional entity does not perform an operation for acquiring the first model, thereby avoiding repeated acquisition of the first model and reducing the overhead of the AnLF functional entity.

[0041] Furthermore, the AnLF functional entity determines that the first model exists, including: the AnLF functional entity determines that the first model exists according to a stored first model or a first model identifier.

[0042] In a possible design solution, the first notification message also carries first accuracy information of the first model.

[0043] Optionally, when the AnLF functional entity determines that the first model does not exist, the method described in the fourth aspect further includes: the AnLF functional entity obtaining first accuracy information.

[0044] Optionally, when the AnLF functional entity determines that the first model exists, the method described in the fourth aspect further includes: the AnLF functional entity determining that the second notification message is a message for indicating accuracy information of the first model.

[0045] Further, the AnLF functional entity determines that the second notification message is a message for indicating accuracy information of the first model, including: the AnLF functional entity only obtains the first accuracy information.

[0046] In a possible design solution, the first model identifier is a model ID of the first model and / or a uniform resource locator (URL).

[0047] In addition, other technical effects of the method described in the fourth aspect can also refer to the technical effects of the method described in the third aspect, and will not be repeated here.

[0048] In a fifth aspect, a communication method is provided, which includes: a model training logic function MTLF functional entity sends a first notification message to an analysis logic function AnLF functional entity; the MTLF functional entity determines a second notification message and sends a second notification message to the AnLF functional entity; wherein the first notification message carries a first model identifier, and the first model identifier is used to indicate the first model; the second notification message carries a second model identifier, and the second model identifier is used to indicate the second model; when the second model is the updated first model, the second model identifier is different from the first model identifier.

[0049] Based on the method described in the fifth aspect, it can be seen that when the MTLF functional entity provides the updated model to the AnLF functional entity, it can carry a model identifier that is different from the previously provided model, so that after receiving the notification message, the AnLF functional entity can determine to obtain the model corresponding to the model identifier carried in the notification message based on the fact that the model identifier carried in the notification message is different from the previous model identifier. In this way, when the AnLF functional entity determines that a model needs to be obtained, the model can be obtained.

[0050] In one possible design, when the second model is the first model, the second model identifier is the same as the first model identifier. In other words, in this case, the second notification message is used to provide accuracy information for the first model, i.e., the second notification message is not used to provide the first model. By carrying the first model identifier in the second notification message, the AnLF functional entity, upon receiving the second notification message, can determine not to acquire the first model based on the model identifier carried in the notification message being identical to the previous model identifier. This prevents the AnLF functional entity from repeatedly acquiring the first model, thereby reducing its overhead.

[0051] In a possible design solution, the second model identifier is a model ID and / or a uniform resource locator (URL) of the second model.

[0052] In addition, other technical effects of the method described in the fifth aspect can also refer to the technical effects of the method described in the third aspect, and will not be repeated here.

[0053] In a sixth aspect, a communication method is provided, which includes: a data analysis and storage function ADRF functional entity receives a request from a model training logic function MTLF functional entity for requesting to configure a uniform resource locator URL for a second model; the ADRF functional entity configures a URL for the second model according to the request for requesting to configure a URL for the second model, the URL of the second model is different from the URL of the first model, and the second model is a model after the first model is updated.

[0054] Based on the method described in aspect 6, the ADRF functional entity can configure different URLs for different models, so that the AnLF functional entity can determine that model #m is the model to be obtained based on the difference between the URL of the model (denoted as model #m) carried in the received notification message and the URL of the previously obtained model, thereby obtaining model #m. In this way, when the AnLF functional entity determines that a model needs to be obtained, the model can be obtained.

[0055] In a seventh aspect, a communication device is provided. The communication device includes: a module for executing the method described in any possible implementation of aspects 1 to 6, such as a transceiver module and a processing module. For example, the transceiver module is configured to indicate the transceiver function of the communication device, and the processing module is configured to execute functions of the communication device other than the transceiver function.

[0056] Optionally, the transceiver module may include a sending module and a receiving module, wherein the sending module is used to implement the sending function of the communication device described in the seventh aspect, and the receiving module is used to implement the receiving function of the communication device described in the seventh aspect.

[0057] Optionally, the communication device described in the seventh aspect may further include a storage module, wherein the storage module stores a program or instruction. When the processing module executes the program or instruction, the communication device can execute the method described in any possible implementation of the first to sixth aspects.

[0058] It can be understood that the communication device described in the seventh aspect can be a network device, or a chip (system) or other parts or components that can be set in the network device, or a device that includes a network device. This application does not limit this.

[0059] In addition, the technical effects of the communication device described in the seventh aspect can refer to the technical effects of the method described in any possible implementation method of the first aspect to the sixth aspect, and will not be repeated here.

[0060] In an eighth aspect, a communication device is provided, comprising: a processor configured to execute the method as described in any possible implementation of the first to sixth aspects.

[0061] In one possible design solution, the communication device described in the eighth aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the communication device described in the eighth aspect to communicate with other communication devices.

[0062] In one possible design solution, the communication device described in aspect 8 may further include a memory. The memory may be integrated with the processor or provided separately. The memory may be used to store computer programs and / or data involved in the method described in any possible implementation of aspects 1 to 6.

[0063] In an embodiment of the present application, the communication device described in the eighth aspect may be a network device, or a chip (system) or other parts or components in the network device, or a device including the network device.

[0064] In addition, the technical effects of the communication device described in the eighth aspect can refer to the technical effects of the method described in any possible implementation method of the first aspect to the sixth aspect, and will not be repeated here.

[0065] In a ninth aspect, a communication device is provided. The communication device includes: a processor coupled to a memory, the processor configured to execute a computer program stored in the memory, so that the communication device performs the method described in any possible implementation of the first to sixth aspects.

[0066] In one possible design solution, the communication device described in aspect 9 may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the communication device described in aspect 9 to communicate with other communication devices.

[0067] In an embodiment of the present application, the communication device described in the ninth aspect may be a network device, or a chip (system) or other parts or components that can be set in the network device, or a device that includes the network device.

[0068] In addition, the technical effects of the communication device described in the ninth aspect can refer to the technical effects of the method described in any possible implementation method in the first to sixth aspects, and will not be repeated here.

[0069] In the tenth aspect, a communication device is provided, comprising: a processor and a memory; the memory is used to store a computer program, and when the processor executes the computer program, the communication device executes the method described in any possible implementation method of the first to sixth aspects.

[0070] In one possible design solution, the communication device described in the tenth aspect may further include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the communication device described in the tenth aspect to communicate with other communication devices.

[0071] In an embodiment of the present application, the communication device described in the tenth aspect may be a network device, or a chip (system) or other parts or components that can be set in the network device, or a device that includes the network device.

[0072] In addition, the technical effects of the communication device described in the tenth aspect can refer to the technical effects of the method described in any possible implementation method of the first aspect to the sixth aspect, and will not be repeated here.

[0073] In an eleventh aspect, a communication system is provided, which includes: an AnLF functional entity for executing the method described in the first aspect, and / or a model training logic function MTLF functional entity for executing the method described in the second aspect.

[0074] In a twelfth aspect, a communication chip is provided, in which instructions are stored. When the chip runs on a communication device, the method described in any one of the implementation methods of the first to sixth aspects is implemented.

[0075] In the thirteenth aspect, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are run on a computer, the computer executes the method described in any possible implementation method of the first to sixth aspects.

[0076] In the fourteenth aspect, a computer program product is provided, comprising a computer program or instructions, which, when executed on a computer, enables the computer to execute the method described in any one of the possible implementations of aspects one to six. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] FIG1 is a schematic diagram of the architecture of a fifth-generation mobile communication system 5GS provided in an embodiment of the present application;

[0078] FIG2 is a schematic diagram of a process for monitoring the accuracy of a machine learning ML model based on a model training logic function MTLF according to an embodiment of the present application;

[0079] FIG3 is a schematic diagram of a process for analyzing subscriptions or unsubscribing from a machine learning ML model according to an embodiment of the present application;

[0080] FIG4 is a schematic diagram of the architecture of a communication system provided in an embodiment of the present application;

[0081] FIG5 is a flow chart of a communication method according to an embodiment of the present application;

[0082] FIG6 is a second flow chart of the communication method provided in an embodiment of the present application;

[0083] FIG7 is a third flow chart of the communication method provided in an embodiment of the present application;

[0084] FIG8 is a fourth flow chart of a communication method according to an embodiment of the present application;

[0085] FIG9 is a fifth flow chart of a communication method according to an embodiment of the present application;

[0086] FIG10 is a sixth flow chart of a communication method according to an embodiment of the present application;

[0087] FIG11 is a seventh flow chart of a communication method according to an embodiment of the present application;

[0088] FIG12 is a first structural diagram of a communication device provided in an embodiment of the present application;

[0089] FIG13 is a second structural diagram of the communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0090] For ease of understanding, the technical terms involved in the embodiments of this application are first introduced below.

[0091] 1. Fifth-generation mobile communication system (5G system, 5GS):

[0092] Figure 1 is a schematic diagram of the 5GS architecture. As shown in Figure 1, 5GS includes: an access network (AN) and a core network (CN), and may also include: terminal equipment.

[0093] The terminal device may be a terminal device with transceiver functions, or a chip or chip system that can be provided in the terminal device. The terminal device may also be referred to as user equipment (UE), access terminal, subscriber unit, user station, mobile station (MS), mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal in the embodiments of the present application can be a mobile phone, a cellular phone, a smart phone, a tablet computer, a wireless data card, a personal digital assistant (PDA), a wireless modem, a handset, a laptop computer, a machine type communication (MTC) terminal, a computer with wireless transceiver function, 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 smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a vehicle-mounted terminal, a road side unit (RSU) with terminal function, etc. The terminal device of the present application may also be an on-board module, on-board module, on-board component, on-board chip or on-board unit built into the vehicle as one or more components or units.

[0094] The AN is used to implement access-related functions. It can provide network access for authorized users in a specific area and determine transmission links of varying quality to transmit user data based on user level and service requirements. The AN forwards control signals and user data between terminals and the CN. The AN may include access network equipment, also known as radio access network (RAN) equipment. The CN is primarily responsible for maintaining mobile network subscription data and providing terminal devices with functions such as session management, mobility management, policy management, and security authentication. CN mainly includes the following: user plane function (UPF), authentication server function (AUSF), access and mobility management function (AMF), session management function (SMF), network slice selection function (NSSF), network exposure function (NEF), network repository function (NRF), policy control function (PCF), unified data management (UDM), unified data repository (UDR), application function (AF), network data analytics function (NWDAF), and analytics data repository function (ADRF).

[0095] As shown in Figure 1, the UE accesses the 5G network through the RAN equipment. The UE communicates with the AMF through the N1 interface (referred to as N1); the RAN communicates with the AMF through the N2 interface (referred to as N2); the RAN communicates with the UPF through the N3 interface (referred to as N3); the SMF communicates with the UPF through the N4 interface (referred to as N4), and the UPF accesses the data network (DN) through the N6 interface (referred to as N6). In addition, the control plane functions shown in Figure 1, such as AUSF, AMF, SMF, NSSF, NEF, NRF, PCF, UDM, UDR, AF, NWDAF, and ADRF, interact using service-based interfaces. For example, the service-oriented interface provided by AUSF to the outside world includes Nausf; the service-oriented interface provided by AMF to the outside world includes Namf; the service-oriented interface provided by SMF to the outside world includes Nsmf; the service-oriented interface provided by NSSF to the outside world includes Nnssf; the service-oriented interface provided by NEF to the outside world includes Nnef; the service-oriented interface provided by NRF to the outside world includes Nnrf; the service-oriented interface provided by PCF to the outside world includes Npcf; the service-oriented interface provided by UDM to the outside world includes Nudm; the service-oriented interface provided by UDR to the outside world includes Nudr; the service-oriented interface provided by AF to the outside world includes Naf; the service-oriented interface provided by NWDAF to the outside world includes Nnwdaf; the service-oriented interface provided by ADRF to the outside world includes Nadrf.

[0096] RAN equipment can be equipment that provides access to terminal equipment. For example, the RAN equipment may include: a next-generation mobile communication system, such as an access network device of 6G, such as a 6G base station, or in the next-generation mobile communication system, the network equipment may also have other naming methods, which are all included in the protection scope of the embodiments of this application, and this application does not impose any restrictions on this. Alternatively, the RAN equipment may also include 5G, such as a gNB in ​​a new radio (NR) system, or one or a group of (including multiple antenna panels) antenna panels of a base station in 5G, or a network node constituting a gNB, a transmission point (TRP or transmission point, TP) or a transmission measurement function (TMF), such as a baseband unit (building base band unit, BBU), or a centralized unit (CU) or a distributed unit (DU), an RSU with base station function, or a wired access gateway, or a 5G core network. Alternatively, RAN devices may also include access points (APs) in wireless fidelity (WiFi) systems, wireless relay nodes, wireless backhaul nodes, various forms of macro base stations, micro base stations (also known as small stations), relay stations, access points, wearable devices, vehicle-mounted devices, and the like.

[0097] UPF is mainly responsible for user data processing (forwarding, receiving, billing, etc.).

[0098] AUSF is mainly used to perform security authentication of terminal devices.

[0099] AMF is mainly used for mobility management in mobile networks, such as user location update, user network registration, and user handover.

[0100] The SMF is primarily used for session management in mobile networks, such as session establishment, modification, and release. Specific functions include allocating Internet Protocol (IP) addresses to users and selecting the UPF that provides packet forwarding capabilities.

[0101] PCF primarily supports providing a unified policy framework to control network behavior, providing policy rules to the control layer network functions, and is responsible for obtaining user subscription information related to policy decisions. PCF can provide policies to AMF and SMF, such as quality of service (QoS) policies and slice selection policies.

[0102] NSSF is mainly used to select network slices for terminal devices.

[0103] NEF is mainly used to support the opening of capabilities and events. For example, NEF can open some capabilities of the 5G network to third-party applications through application program interfaces (APIs). Third-party applications can obtain some capabilities of the 5G network by calling the APIs provided by NEF through AF, allowing third-party applications to control certain behaviors of the 5G network and terminal devices.

[0104] UDM is mainly used to store user data, such as contract data, authentication / authorization data, etc.

[0105] UDR is mainly used to store structured data, including contract data and policy data, externally exposed structured data, and application-related data.

[0106] AF mainly supports interaction with CN to provide services, such as influencing data routing decisions, policy control functions, or providing some third-party services to the network side.

[0107] The NWDAF network element supports collecting data from other network functions and AF network elements; supports collecting data from operation administration and maintenance (OAM) network elements; and supports providing analysis information to other network functions and AF network elements. In other words, the NWDAF network element has the functions of data collection, model training, data analysis, and model reasoning, that is, it can be used to collect relevant data from network network elements, third-party service servers, terminal devices, or network management systems; perform data analysis based on the relevant data to obtain analysis results; and provide analysis results to network network elements, third-party service servers, terminal devices, or network management systems. The analysis results can assist the network in selecting service quality parameters for the service, or assist the network in executing traffic routing, or assist the network in selecting background data transmission strategies, etc. In addition, the NWDAF network element can also be used to collect relevant data from network network elements, third-party service servers, terminal devices, or network management systems, and perform model training based on the relevant data to obtain an AI model or ML model, and provide the AI ​​model or ML model to other NWDAF network elements. The AI ​​model or ML model can be used to assist the NWDAF network element in generating data analysis results based on the relevant data.

[0108] NWDAF, which includes analytics logical functions (AnLF), can be used to perform model inference, export analytical information (i.e., export statistics and / or predictions based on analytics consumer requests), and expose analytical services. NWDAF, which includes model training logical functions (MTLF), can be used to train ML models and expose new training services, such as providing trained ML models.

[0109] ADRF network elements can provide storage and retrieval services for data and analytics for consumers. For example, a consumer sends a Nadrf Data Management Storage Request to an ADRF network element containing the data or analytics to be stored; or a consumer sends a Nadrf Data Management Storage Subscription Request to an ADRF network element, requesting the ADRF network element to subscribe to receive data or analytics for storage. The ADRF network element then subscribes to an NWDAF network element or a data collection coordination function (DCCF) network element to obtain the data or analytics, providing the ADRF network element notification address or notification association ID. The analytics or data are then provided as notifications using the DCCF Data Management (Ndccf_DataManagement) service, the NWDAF Data Management (Nnwdaf_DataManagement) service, or the MFAF (messaging framework adaptor NF) Data Management (Nmfaf_3caDataManagement) service.

[0110] It can be understood that the functions mentioned in the embodiments of the present application can also be expressed as functional network elements or functional entities. For example, UPF can be expressed as UPF network element, AMF can be expressed as AMF network element, SMF can be expressed as SMF network element, PCF can be expressed as PCF network element, and so on, without limitation.

[0111] 2. Process of ML model accuracy monitoring based on MTLF:

[0112] Figure 2 illustrates the process of monitoring the accuracy of a configured ML model using newly collected data. The NWDAF with AnLF can provide inference data to the NWDAF with MTLF for model accuracy monitoring, and the NWDAF with MTLF can determine whether to retrain or reconfigure the ML model. The following details the MTLF-based ML model accuracy monitoring process.

[0113] S201: An analytics consumer initiates an analytics exposure service subscription (Nnwdaf_AnalyticsSubscription_subscribe) service operation to the NWDAF including the AnLF.

[0114] S202 , the NWDAF including the AnLF requests the ML model from the NWDAF including the MTLF using the ML model provision subscription (Nnwdaf_MLModelProvision_Subscribe) service operation.

[0115] NWDAFs with AnLF can include analysis accuracy thresholds as indicators for performing accuracy monitoring operations. NWDAFs with AnLF may include dataset tags (DataSetTag) and / or ADRFID for storing inference data and obtaining inference data from ADRF. Inference data is relevant for monitoring the accuracy of ML models, as well as for retraining or reconfiguring them. This inference data can include input data, prediction data, and ground truth data at the time of prediction.

[0116] S203 , the NWDAF including the MTLF provides the trained ML model to the NWDAF including the AnLF.

[0117] The NWDAF including the MTLF may include accuracy information indicating the accuracy of the ML model during training. The NWDAF including the MTLF may send the ML model to the NWDAF including the AnLF via the ML model provision notification (Nnwdaf_MLModelProvision_Notify) service operation.

[0118] S204 , the NWDAF including the AnLF registers the use of the ML model with the NWDAF including the MTLF to indicate its ability to send analysis feedback information and / or ML model accuracy information from analysis consumers.

[0119] NWDAF including AnLF can register the use of ML models with NWDAF including MTLF through the ML Model Monitor Registration (Nnwdaf_MLModelMonitor_Register) service operation.

[0120] S205, due to the registration in the previous step, if the NWDAF containing ANLF supports the service operation, the NWDAF containing MTLF can subscribe to the NWDAF containing ANLF by calling the ML model monitoring subscription (Nnwdaf_MLModelMonitor_Subscribe) service operation to obtain analysis feedback information and / or ML model accuracy information from the analysis consumer.

[0121] S206 , the analytics consumer may send analytics feedback information in an analytics subscription (Nnwdaf_AnalyticsSubscription_Subscribe) message, as described in Section 6.1.1.

[0122] In step S207, the NWDAF including the AnLF may send the analysis feedback information received from the analysis consumer and / or the provided ML model accuracy information by calling the ML model monitoring notification (Nnwdaf_MLModelMonitor_Notify) service operation according to the request in step S205. When the NWDAF including the MTLF receives the analysis feedback information or the ML model accuracy information, the NWDAF including the MTLF may trigger steps S208 to S2013 to improve the ML model accuracy.

[0123] S208a to S208f, the NWDAF including the MTLF determines whether to perform ML model accuracy monitoring and ML model retraining / reconfiguration based on requests from one or more NWDAFs including the AnLF or its local policy by collecting new data from various data sources:

[0124] 1) NWDAF with MTLF can collect new data for ML model accuracy monitoring, retraining, and reconfiguration from data sources NF and DCCF by calling the Data Exposure Subscription (Nnf_EventExposure_Subscribe) and Data Management Subscription (Ndccf_DataManagement_Susubscribe) service operations respectively.

[0125] 2) When S202 indicates an ADRFID and / or DataSetTag, the NWDAF with the MTLF can retrieve historical data from the ADRF indicated by the NWDAF with the AnLF in S202 by calling the Nadrf_DataManagementRetrievalRequest or Nadrf_DataManagementRetrieval_Subscribe service operations. Otherwise, the NWDAF with the MTLF can retrieve historical data from the DCCF or NWDAF with the AnLF by calling the Ndccf_DataManagement_Subscribe or Nnwdaf_DataManagement_Subsubscribe service operations, respectively.

[0126] 3) If the NWDAF containing AnLF in S202 does not include a DataSetTag with ADRFID, the NWDAF containing MLTF may use the procedure defined in Section 6.2B.3 to request the ADRF to subscribe to the collection of analytics and data corresponding to the analytics generated by the ML model provided in S203.

[0127] 4) The NWDAF including the MTLF may subscribe to the UDM by calling the SDM subscription (Nudm_SDM_subscribe) service operation of the UDM to obtain notifications of changes in subscription data of the target reported by the ML model, and the UDM may subscribe to the UDR by calling the DM subscription (Nudr_DM_subscribe) service operation of the UDR to obtain notifications of modifications of UE subscription data.

[0128] 5) NWDAF including MTLF can determine the status of data source NF by collecting fault prediction analysis data from MDAS using management data analytics (MDA) requests, thereby taking data quality into account in accuracy monitoring.

[0129] If the NWDAF containing MTLF has collected new test data and performed ML model accuracy monitoring and retraining triggered by other NWDAFs containing AnLF (for ML model accuracy monitoring and retraining), the NWDAF containing MTLF determines whether to use the data for subscription based on its internal logic.

[0130] S209a-S209f, the NWDAF including the MTLF receives the requested data from the various sources requested in S208a-S208f.

[0131] At S2010, based on the analysis and data collected from S209a-S209f, the NWDAF with MTLF uses the predictions and the actual measured data observed at the time of the prediction reference to calculate accuracy. If the data quality of a data source is detected to be poor, the NWDAF with MTLF may discard the data from that source. If only input data and ground truth data are available, the NWDAF with MTLF can generate predictions using the collected input data to calculate accuracy.

[0132] S2011: An accuracy report is sent to the NWDAF including the AnLF, for example, when the reporting threshold is reached by calling the NWDAF's ML Model Provision Notification (Nnwdaf_MLModelProvision_Notify) service operation.

[0133] S2012, based on the calculated accuracy, NWDAF including MTLF can decide to re-train or re-provision the ML model.

[0134] In step S2013, when the newly generated or retrained ML model is ready, the NWDAF including the MTLF sends the new or retrained ML model to the NWDAF including the AnLF by calling the NWDAF ML Model Provision Notification (Nnwdaf_MLModelProvision_Notify) service operation. The NWDAF including the MTLF can send an accuracy report of the new or retrained ML model to the NWDAF including the AnLF.

[0135] It can be understood that the above-mentioned process of MTLF-based ML model accuracy monitoring can refer to the relevant content in the 3rd Generation Partnership Project (3GPP) TS23.288V18.2.0, which will not be repeated here.

[0136] 3. Analyze the process of subscribing or unsubscribing to ML models:

[0137] As shown in Figure 3, Figure 3 shows the process of subscribing to or unsubscribing from an ML model for analysis provided in an embodiment of the present application. This process can be used by an NWDAF service consumer (i.e., an NWDAF containing AnLF) to subscribe / unsubscribe from another NWDAF (i.e., an NWDAF containing MTLF). When ML model information for related analysis is available, it will be notified using the Nnwdaf_MLModelProvision service defined in Clause 7.5. The ML model information is used by the NWDAF containing AnLF to derive analysis. The NWDAF also uses this service to modify existing ML model subscriptions. The NWDAF can be both a consumer of this service provided by other NWDAFs and a provider of this service provided by other NWDAFs.

[0138] S301, the NWDAF service consumer (i.e., the NWDAF including the AnLF) subscribes to, modifies, or cancels the subscription for (a set of) trained ML models associated with an analysis ID by calling ML model provision subscription (Nnwdaf_MLModelProvision_Subscribe) / ML model provision unsubscription (Nnwdaf_MLModelProvision_Unsubscribe). The parameters that the NWDAF service consumer can provide are listed in Section 6.2A.2. The service consumer can choose to indicate its support for multiple ML models (if available). When receiving a subscription for a trained ML model associated with an analysis ID, the NWDAF including the MTLF can: determine whether an existing trained ML model is available for subscription; or determine whether the subscription needs to trigger further training of the existing trained ML model.

[0139] If the NWDAF including the MTLF determines that further training is required, the NWDAF may initiate data collection from NFs (such as AMF, DCCF, or ADRF), UE applications (via AF), or OAM (as described in Section 6.2) to generate the ML model.

[0140] If the service call is for modifying or canceling a subscription, the NWDAF service consumer contains an identifier (subscription association ID) that needs to be modified when calling Nnwdaf_MLModelProvision_Subscribe.

[0141] S302, if the NWDAF service user subscribes to (a set of) trained ML models associated with (a set of) analysis IDs, the NWDAF including the MTLF notifies the NWDAF service user of the unique ML model identifier and ML model information associated with each analysis ID requested by the service user.

[0142] It should be noted that the structure and format of ML model identifiers and their uniqueness are before Phase 3. Parameters defined for multiple ML models are used to improve the accuracy of the analysis.

[0143] The content of the trained ML model information that the NWDAF including the MTLF can provide by calling the Nnwdaf_MLModelProvision_Notify service operation is specified in clause 6.2A.2.

[0144] When the NWDAF including the MTLF determines in step S301 that the previously provided training ML model needs to be retrained, the NWDAF including the MTLF also calls the Nnwdaf_MLModelProvision_Notify service operation to notify the available retrained ML model.

[0145] When step S301 is for subscription modification (i.e., including subscription association ID), the NWDAF including MTLF can provide a new trained ML model different from the previously provided one, or retrain the ML model by calling the Nnwdaf_MLModelProvision_Notify service operation.

[0146] 4.NWDAF model notification message element situation:

[0147] The NWDAF with MTLF provides the output information described in Sections 7.5 and 7.6 to the consumer of the ML Model Provisioning Service operation as follows:

[0148] (Applicable only to Nnwdaf_MLModelProvision_Notify) Notification related information.

[0149] For each analysis ID requested by the service consumer, a set of unique ML model identifier and ML model information pairs.

[0150] ML model information, including: ML model file address (such as URL or FQDN); or optional information as follows:

[0151] 1) ML model degradation indicator: Indicates whether the provided ML model is degraded.

[0152] 2) Validity period: Indicates the period of time during which the provided ML model information is applicable.

[0153] 3) Spatial validity: Indicates the area to which the provided ML model information is applicable.

[0154] 4) ML model representative ratio: When the target reported by the ML model is a group of UEs, it indicates the percentage of UEs in the group whose data was used in the ML model training.

[0155] 5) Training input data information: Contains information about the various settings used by MTLF during training, such as:

[0156] The “input data” used, each input data optionally accompanied by metrics showing the data characteristics and granularity of the use of this data (i.e. sampling ratio, the maximum number of input values ​​and / or the maximum time interval between samples of this input data, the data range including the maximum and minimum values, the mean and standard deviation and the data distribution (if applicable)) and the time when this data was obtained, i.e. timestamp and duration.

[0157] Data sources related to the "input data" used for ML model training.

[0158] ADRF (set) ID. When allocating ADRF (set) ID, you can also allocate storage transaction ID.

[0159] It will be appreciated that this may be a subset of the possible input data specified for a particular analysis type.

[0160] Already used as the data source for the list of NF instance (or NF set) identifiers.

[0161] It is understood that the spatial validity and validity period are determined by the MTLF internal logic and are a subset of the AOI if provided in the ML model filter information and ML model target period, respectively.

[0162] It is understood that the data source information enables ML model selection when different models are available for an analysis ID, or it enables a consumer to avoid selecting an ML model that uses data from a specific data source at a specific time or uses data with specific data characteristics.

[0163] 6) ML model accuracy information: If the analysis accuracy threshold is requested, the accuracy of the ML model is indicated, including: accuracy information of the ML model.

[0164] 7) ML model metrics (i.e., ML model accuracy).

[0165] It can be understood that the above-mentioned MTLF-based ML model accuracy monitoring process, the analysis and subscription or unsubscription process of the ML model, and the NWDAF model notification message element situation can all refer to the relevant content in 3GPP TS 23.288 V18.2.0, which will not be repeated here.

[0166] According to the above introduction, the ML model supply notification message can have many different functions, for example: in the aforementioned S203, the ML model supply notification message can be used to provide the AnLF functional entity with an ML model (denoted as model #ml). In this case, the AnLF functional entity can obtain model #ml based on the ML model supply notification message; or, in the aforementioned S2011, the ML model supply notification message can be used to provide accuracy information of model #ml. In this case, the AnLF functional entity can obtain accuracy information of model #ml based on the ML model supply notification message; or, in the aforementioned S2013, the ML model supply notification message can be used to provide the model after model #ml is updated. In this case, the AnLF functional entity can obtain the model after model #ml is updated based on the ML model supply notification message.

[0167] However, in the prior art, upon receiving an ML model provision notification message, the AnLF functional entity immediately retrieves the model corresponding to the model identifier carried in the message, thereby ensuring the real-time nature of the model. However, as previously mentioned, when the ML model provision notification message is used to provide model accuracy information, the AnLF functional entity updates the model accuracy information, but retrieves the same model. Therefore, how to improve the flexibility and effectiveness of the AnLF functional entity's ML model acquisition is currently a hot topic of discussion.

[0168] In response to the above technical problems, the embodiments of the present application propose the following technical solutions to improve the flexibility and effectiveness of AnLF functional entities in acquiring ML models.

[0169] The technical solution in this application will be described below with reference to the accompanying drawings.

[0170] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as wireless network (Wi-Fi) systems, vehicle to everything (V2X) communication systems, device-to-device (D2D) communication systems, Internet of Vehicles communication systems, fourth-generation (4G) mobile communication systems, such as long-term evolution (LTE) systems, world-wide interoperability for microwave access (WiMAX) communication systems, fifth-generation (5G) systems, such as new radio (NR) systems, and future communication systems.

[0171] This application will present various aspects, embodiments, or features in the context of systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that each system may include additional devices, components, modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in conjunction with the figures. Furthermore, combinations of these aspects may also be used.

[0172] Additionally, in the embodiments of this application, words such as "exemplary" and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner.

[0173] In the embodiments of the present application, "information", "signal", "message", "channel" and "signaling" can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings they intend to express are matched. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings they intend to express are matched. In addition, the " / " mentioned in this application can be used to express an "or" relationship.

[0174] The network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field will know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0175] To facilitate understanding of the embodiments of the present application, a communication system applicable to the embodiments of the present application is first described in detail using the communication system shown in Figure 4 as an example. For example, Figure 4 is a schematic diagram of the architecture of a communication system applicable to the communication method provided in the embodiments of the present application.

[0176] As shown in Figure 4, the communication system can be applied to the above-mentioned 5GS, including: AnLF functional entity and MTLF functional entity. The AnLF functional entity is carried on the NWDAF network element; and / or the MTLF functional entity is carried on the NWDAF network element.

[0177] AnLF functional entities can use models and provide external services. That is, they can provide input data for the model, use the model to obtain corresponding output data, and provide the output data to third parties. MTLF functional entities can provide models and can produce or train models or obtain models from other sources.

[0178] It can be understood that the AnLF functional entity and the MTLF functional entity can be set on the same NWDAF network element, that is, one NWDAF network element includes the AnLF functional entity and the MTLF functional entity; they can also be set separately on different NWDAF network elements, that is, different NWDAF network elements respectively include the AnLF functional entity and the MTLF functional entity, which is not limited in the embodiments of the present application.

[0179] It can also be understood that the "AnLF functional entity" and "MTLF functional entity" in the embodiment of the present application are only exemplary expressions, and the "AnLF functional entity" can also be replaced by any possible expression, such as "NWDAF including AnLF", "model consumer", etc., and the "MTLF functional entity" can also be replaced by any possible expression, such as "NWDAF including MTLF", "model provider", etc., and the embodiment of the present application does not limit this. In addition, the "AnLF functional entity" and "MTLF functional entity" can also be replaced by other network elements or network functions that have the same functions or include the functions of the AnLF functional entity or MTLF functional entity, and the embodiment of the present application does not limit this.

[0180] In a communication system, the AnLF functional entity can determine whether to obtain the first model, that is, whether to perform an operation for obtaining the first model (such as sending a request message for obtaining the first model) by whether the first notification message carries first indication information. The first indication information is used to indicate that the first model is updated, or the MTLF functional entity provides the first model. That is, when the first notification message carries the first indication information, the AnLF functional entity needs to obtain the first model; when the first notification message does not carry the first indication information, the AnLF functional entity does not need to obtain the first model. Therefore, the AnLF functional entity obtains the first model when the first notification message carries the first indication information; and does not obtain the first model when the first notification message does not carry the first indication information. This allows the AnLF functional entity to obtain the first model only when it needs to, thereby improving the flexibility and effectiveness of the AnLF functional entity in obtaining the first model.

[0181] For ease of understanding, the interaction process between the AnLF functional entity and the MTLF functional entity will be specifically described below through a method embodiment in conjunction with Figures 5 to 6 and 8.

[0182] Scenario 1:

[0183] For example, FIG5 is a flow chart of a communication method provided in an embodiment of the present application. This communication method can be applied to the communication between the AnLF functional entity and the MTLF functional entity in scenarios such as ML model accuracy monitoring in a 5G architecture. As shown in FIG5 , the flow of the communication method is as follows:

[0184] S501: The AnLF functional entity sends a request message (recorded as request message #1) to the MTLF functional entity. Correspondingly, the MTLF functional entity receives the request message from the AnLF functional entity.

[0185] Request message #1 is used to request an ML model. Sending request message #1 can be implemented by calling the MLModelProvision_Subscribe service operation or other operations, which are not limited in this embodiment of the application.

[0186] S502: The MTLF functional entity sends a first notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the first notification message from the MTLF functional entity.

[0187] The first notification message is used to provide a model, which may be a new model (described below). Sending the first notification message may be implemented by calling the ML model provision notification (Nnwdaf_MLModelMonitor_Notify) service operation. The first notification message carries a first model identifier and indication information.

[0188] The first model identifier is used to indicate the first model. The first model identifier can be at least one of the following: an identity identifier (ID) of the first model, a uniform resource locator (URL) of the first model, or a fully qualified domain name (FQDN) of the first model. The first model is an ML model, and the first model is a new model. The first model can be obtained by training the MTLF functional entity or by other means, without limitation.

[0189] The new model can be a model that the MTLF functional entity provides to the AnLF functional entity for the first time after receiving a request message from the AnLF functional entity, that is, the AnLF functional entity has never received the model before. For example: after receiving the request message, the MTLF functional entity provides model #1a to the AnLF functional entity, and the model #1a is a new model.

[0190] The indication information may be used to instruct the MTLF functional entity to provide a model, which may be a new model or an updated model. Alternatively, the indication information may be used to indicate that a new model or an updated model is provided, which may be a new model or an updated model. Alternatively, the indication information may be used to indicate that a model corresponding to a model identifier is provided, which may be a new model or an updated model.

[0191] The updated model may be a model that is not provided to the AnLF functional entity for the first time after the MTLF functional entity receives a request message from the AnLF functional entity. It is understood that the updated model may be a model obtained by the MTLF functional entity retraining an existing model, that is, the updated model is a model generated based on the existing model; or the updated model may be a model retrained by the MTLF functional entity. The existing model may be understood as a model stored locally by the MTLF functional entity, or a model that the MTLF functional entity has sent to the AnLF functional entity.

[0192] For example, after receiving the request message, the MTLF functional entity provides model #1a to the AnLF functional entity, where model #1a is a new model; the MTLF functional entity obtains model #1b after model #1a is updated, and provides model #1b to the AnLF functional entity, where model #1b is an updated model, that is, model #1b can be a model generated by the MTLF functional entity based on model #1a, or model #1b can be a model retrained by the MTLF functional entity.

[0193] It is understood that the indication information carried in the notification message can indicate that the model corresponding to the model identifier carried in the notification message has been provided, that is, the AnLF functional entity has not obtained the model, and that the AnLF functional entity needs to obtain the model. For example, if notification message #c carries the model #1c identifier and indication information, and the model #1c identifier is used to indicate model #1c, then the AnLF functional entity needs to obtain model #1c after receiving notification message #c.

[0194] After receiving the request message, the MTLF functional entity may provide the first model by sending a first notification message to the AnLF functional entity.

[0195] Optionally, the first notification message also carries first accuracy information of the first model. The first accuracy information is used to indicate the accuracy of the first model. The first accuracy information can be calculated based on relevant data using the first model (e.g., model test data). Calculating the model accuracy information can be implemented by reusing methods in the prior art, and this embodiment of the present application does not impose any restrictions on this.

[0196] S503: The AnLF functional entity performs an operation for acquiring the first model according to the first notification message.

[0197] After receiving the first notification message, the AnLF functional entity may obtain the first model according to the indication information carried in the first notification message, that is, perform an operation for obtaining the first model.

[0198] In a possible implementation, the operation for obtaining the first model may be sending a request message for obtaining the first model.

[0199] The request message for obtaining the first model can be implemented by calling the Nadrf_MLModelManagement_Retrieval service operation. The AnLF functional entity sending the request message for obtaining the first model can indicate that the AnLF functional entity is obtaining the first model.

[0200] It can be understood that the AnLF functional entity can send a request message for obtaining the first model to the ADRF functional entity. After receiving the request message, the ADRF functional entity returns the first model address (such as the URL or FQDN of the first model) to the AnLF functional entity. The AnLF functional entity can obtain the first ML model based on the first model address (such as the URL or the FQDN), such as obtaining the first model based on the hypertext transfer protocol (HTTP) technology.

[0201] In another possible implementation, the operation for obtaining the first model may be obtaining the first model from a first preset location. The first preset location may be a URL or FQDN of the first model, or other addresses, without limitation.

[0202] It is understood that in this case, the AnLF functional entity has already obtained the first preset position, such as pre-setting the first preset position in the AnLF functional entity. The first model is placed in the first preset position in advance, such as placing the first model in the first preset position before the AnLF functional entity receives the first notification message, so that the AnLF functional entity can directly obtain the first model at the first preset position.

[0203] S504: The MTLF functional entity obtains second accuracy information of the first model.

[0204] The second accuracy information is used to indicate the accuracy of the first model and may be the same as or different from the first accuracy information. The second accuracy information is the accuracy information of the first model determined based on data generated when the AnLF functional entity uses the first model. In other words, the second accuracy information is the most recent accuracy information of the first model.

[0205] It is understood that after the AnLF functional entity obtains the first model, it can use the first model. The MTLF functional entity can obtain an accuracy report of the first model based on the data generated during the use of the first model, that is, obtain second accuracy information of the first model. The MTLF functional entity can obtain the second accuracy information by reusing methods in the prior art, and this embodiment of the present application is not limited to this.

[0206] S505: The MTLF functional entity sends a second notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the second notification message from the MTLF functional entity.

[0207] The second notification message is used to indicate the second accuracy information of the first model. The second notification message is a notification message of the same type as the first notification message, and the information elements (IE) of the two are the same, that is, sending the second notification message can also be implemented by calling the ML model supply notification (Nnwdaf_MLModelMonitor_Notify) service operation. The second notification message carries the first model identifier and does not carry indication information. The fact that the second notification message does not carry indication information can indicate that the MTLF functional entity does not provide a model, such as a new model or an updated model. In this case, after receiving the second notification message, the AnLF functional entity does not need to repeatedly obtain the first model, that is, it does not need to perform the operation for obtaining the first model.

[0208] After acquiring the second accuracy information of the first model, the MTLF functional entity may send a second notification message to enable the AnLF functional entity to acquire the latest accuracy information of the first model, that is, the second accuracy information.

[0209] Optionally, the second notification message carries the second accuracy information. In this way, the AnLF functional entity can obtain the second accuracy information after receiving the second notification message without having to obtain it from other places, thereby reducing the overhead of the AnLF functional entity.

[0210] It can be understood that when the second notification message carries the second accuracy information, the MTLF functional entity can obtain the second accuracy information through the second notification message; when the second notification message does not carry the second accuracy information, the MTLF functional entity can obtain the second accuracy information from the second preset location.

[0211] S506: The AnLF functional entity does not perform an operation for acquiring the first model according to the second notification message.

[0212] Not performing the operation for obtaining the first model may indicate not obtaining the first model, and may specifically mean not sending a request message for obtaining the first model, or not obtaining the first model from the first predetermined location. The request message for obtaining the first model and obtaining the first model from the first predetermined location can be found in the aforementioned description of S503 and will not be repeated here.

[0213] After receiving the second notification message, the AnLF functional entity may not obtain the first model because the second notification message does not carry the indication information. In this case, the AnLF functional entity only obtains the second accuracy information. Furthermore, if the second notification message carries the second accuracy information, the AnLF functional entity obtains the second accuracy information by receiving the second notification message. Alternatively, if the second notification message does not carry the second accuracy information, the AnLF functional entity may obtain the second accuracy information from another location.

[0214] S507: The MTLF functional entity obtains the second model.

[0215] The second model is a model obtained by updating the first model, that is, the second model is an updated model. The second model can be a model retrained based on the first model, or the second model can be a regenerated model, without limitation.

[0216] It is understood that the MTLF functional entity can obtain the second model when the value corresponding to the second accuracy information is less than the accuracy threshold. The MTLF functional entity can obtain the second model by reusing the existing technology, and the embodiments of the present application are not limited to this. In this way, the MTLF functional entity can provide the AnLF functional entity with a model with higher accuracy or a model that is more consistent with the actual situation.

[0217] S508: The MTLF functional entity sends a third notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the third notification message from the MTLF functional entity.

[0218] The third notification message is used to provide the updated model, namely the second model described above. The third notification message is of the same type as the first and second notification messages, and contains the same information elements (IEs). This means that sending the third notification message can also be accomplished by invoking the ML Model Provisioning Notification (Nnwdaf_MLModelMonitor_Notify) service operation. The third notification message carries the second model identifier and indication information.

[0219] The second model identifier is used to indicate the second model. The second model identifier can be at least one of the following: an identity identifier (ID) of the second model, a uniform resource locator (URL) of the second model, or a fully qualified domain name (FQDN) of the second model.

[0220] It is understood that the second model identifier and the first model identifier can be the same or different. When the second model identifier and the first model identifier are the same, the same model identifier is used to indicate a different model. In this case, the second model can be referred to as the first model, that is, the first model is variable. Correspondingly, when the second model identifier and the first model identifier are different, different model identifiers are used to indicate different models. Whether the second model identifier and the first model identifier are the same can be selected accordingly based on actual circumstances and is not limited in the embodiments of the present application.

[0221] It can also be understood that when the model identifier is the model ID, the second model identifier can be the same as the first model identifier, which can be understood as the MTLF functional entity setting the same ID for different models; the second model identifier can be different from the first model identifier, which can be understood as the MTLF functional entity setting different IDs for different models. When the model identifier is the URL or FQDN of the model, the second model identifier can be the same as the first model identifier, which can be understood as the MTLF functional entity storing different models in the same location, that is, when the model is updated, the MTLF functional entity will replace the model before the update with the updated model; the second model identifier can be different from the first model identifier, which can be understood as the MTLF functional entity storing different models in different locations.

[0222] The instruction information can be referred to the above-mentioned S502 related introduction, which will not be repeated here.

[0223] After acquiring the second model, the MTLF functional entity may provide the second model by sending a third notification message to the AnLF functional entity.

[0224] Optionally, the third notification message also carries third accuracy information of the second model. The third accuracy information is used to indicate the accuracy of the second model. The third accuracy information can be calculated using relevant data of the second model. Calculating the model accuracy information can be achieved by reusing existing methods, which is not limited in this embodiment of the present application.

[0225] S509: The AnLF functional entity performs an operation for acquiring the second model according to the third notification message.

[0226] The operation for obtaining the second model is similar in principle to the operation for obtaining the first model in the aforementioned S503. For details, please refer to the relevant introduction of the aforementioned S503, which will not be repeated here.

[0227] The AnLF functional entity performing the operation for obtaining the second model can indicate that the AnLF functional entity obtains the second model. That is, after receiving the third notification message, the AnLF functional entity can obtain the second model corresponding to the second model identifier carried in the third notification message according to the indication information carried in the third notification message.

[0228] It can be understood that, according to the above S501-S509, the indication information for instructing the MTLF functional entity to provide a model can be understood as follows: upon receiving the request message #1 sent by the AnLF functional entity, the MTLF functional entity provides a new model to the AnLF functional entity; or, upon obtaining an updated model (such as the second model in S507), the MTLF functional entity provides the updated model to the AnLF functional entity. The indication information for instructing the MTLF functional entity to provide a model can also be understood as follows: upon providing a model to the AnLF functional entity for the first time, the MTLF functional entity provides a new model to the AnLF functional entity; or, upon not providing a model to the AnLF functional entity for the first time, the MTLF functional entity provides an updated model to the AnLF functional entity.

[0229] According to the technical solution introduced in Scenario 1, when the MTLF functional entity provides a model (such as a new model or an updated model) to the AnLF functional entity through a notification message (such as the first notification message or the third notification message mentioned above), indication information can be carried in the notification message so that after receiving the notification message, the AnLF functional entity can obtain the model corresponding to the model identifier carried in the notification message according to the indication information carried in the notification message. Correspondingly, when the MTLF functional entity provides the accuracy information of the model to the AnLF functional entity through a notification message (such as the second notification message mentioned above), indication information can be not carried in the notification message so that after receiving the notification message, the AnLF functional entity can not obtain the model corresponding to the model identifier carried in the notification message according to the indication information not carried in the notification message, that is, at this time, the AnLF functional entity only obtains the accuracy information of the model. In other words, by carrying or not carrying indication information in the notification message, the AnLF functional entity can obtain or not obtain the model after receiving the notification message. In this way, the AnLF functional entity can determine whether to obtain the model based on whether the notification message carries indication information, without having to obtain the model every time a notification message is received. In this way, the AnLF functional entity can improve the flexibility and effectiveness of obtaining the model and reduce the overhead of the AnLF functional entity.

[0230] Scenario 2:

[0231] For example, FIG6 is a flow chart of the communication method provided in an embodiment of the present application. The communication method can be applied to the communication between the AnLF functional entity and the MTLF functional entity in scenarios such as ML model accuracy monitoring in the 5G architecture. As shown in FIG6, the process of the communication method is as follows:

[0232] S601: AnLF functional entity sends a request message to MTLF functional entity. Correspondingly, MTLF functional entity receives the request message from AnLF functional entity.

[0233] The specific implementation principle of S601 can refer to the relevant introduction in the above S501 and will not be repeated here.

[0234] S602: The MTLF functional entity sends a first notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the first notification message from the MTLF functional entity.

[0235] The first notification message is used to instruct the MTLF functional entity to provide the ML model. The first notification message carries the first model identifier, and the first notification message does not carry the first indication information. For other contents of the first notification message, please refer to the relevant introduction of S502 above, which will not be repeated here.

[0236] The first model identifier is used to indicate the first model. The first model identifier and the first model can be referred to the related introduction of S502 above, which will not be repeated here.

[0237] The first indication information can be used to indicate that the model corresponding to the model identifier is updated. Alternatively, the first indication information can be used to instruct the MTLF functional entity to provide the updated model. It can be understood that the notification message carrying the first indication information can indicate that the model corresponding to the model identifier carried by the notification message is updated, or the MTLF functional entity provides the updated model; the notification message not carrying the first indication information can indicate that the model corresponding to the model identifier carried by the notification message is not updated, or the MTLF functional entity does not provide the updated model. The updated model can refer to the relevant introduction of S502 above, which will not be repeated here.

[0238] For example, notification message #2a carries a model #2a identifier and first indication information, where the model #2a identifier indicates model #2a. In this case, the first indication information may indicate that the model #2a corresponding to the model #2a identifier is updated, or that the MTLF functional entity provides the updated model, namely, model #2a.

[0239] It can be understood that in scenario 2, each model (such as a new model, an updated model) can use the same model identifier, for example: the new model is model #2b, the model identifier corresponding to model #2b is the first model identifier, and the first model identifier is used to indicate the first model, that is, the first model is model #2b at this time; the updated model is model #2c, and the model identifier corresponding to model #2c is also the first model identifier, that is, after the first model is updated, the first model is model #2c. It can be seen that in the embodiment of the present application, there is only one model and one model identifier, namely the first model and the first model identifier, and the first model can change, such as in step S602 the first model is a new model, and in S608 (described below) the first model is an updated model. It can also be understood that the updated model is used to replace the previous model, that is, the AnLF functional entity no longer uses the model before the update, and uses the updated model to replace the model before the update.

[0240] In one possible implementation, the first indication information can be used to indicate a model update notification message. That is, when the notification message carries the first indication information, it can indicate that the message type of the notification message is a model update notification message; correspondingly, when the notification message does not carry the first indication information, it can indicate that the notification message is not a model update notification message. The model update notification message can indicate that the model corresponding to the model identifier carried in the model notification message is updated, or the MTLF functional entity provides an updated model. It can be understood that when the notification message is a model update notification message, the functional entity that receives the notification message needs to obtain the model corresponding to the model identifier carried in the notification message, and the model is the updated model.

[0241] For example, notification message #2d carries a model #2d identifier and first indication information. The model #2d identifier is used to indicate model #2d. In this case, notification message #2d is a model update notification message, i.e., model #2d is the updated model. After receiving notification message #2d, the AnLF functional entity can determine that notification message #2d is a model update notification message based on the first indication information carried in notification message #2d, thereby obtaining model #2d.

[0242] After receiving the request message, the MTLF functional entity may provide the first model by sending a first notification message to the AnLF functional entity.

[0243] Optionally, the first notification message also carries second indication information. The second indication information is used to indicate the model sending notification message, that is, when the notification message carries the second indication information, it can be indicated that the notification message is a model sending notification message; correspondingly, when the notification message does not carry the second indication information, it can be indicated that the notification message is not a model sending notification message. The model sending notification message can indicate that the MTLF functional entity provides a new model. It can be understood that when the message type of the notification message is a model sending notification message, the functional entity that receives the notification message needs to obtain the model corresponding to the model identifier carried by the notification message.

[0244] For example, notification message #2e carries a model #2e identifier and second indication information. The model #2e identifier is used to indicate model #2e. In this case, notification message #2e is a model-delivered notification message, i.e., model #2e is a new model. After receiving notification message #2e, the AnLF functional entity can determine that notification message #2e is a model-delivered notification message based on the second indication information carried in notification message #2e, thereby obtaining model #2e.

[0245] Optionally, the first notification message also carries first accuracy information of the first model. For details, please refer to the above-mentioned S502 related introduction, which will not be repeated here.

[0246] S603: The AnLF functional entity performs an operation for acquiring the first model according to the first notification message.

[0247] The operation for obtaining the first model can refer to the related introduction of the aforementioned S503, which will not be repeated here.

[0248] After the AnLF functional entity receives the first notification message, if the first notification message does not carry the first indication information and the second indication information, the AnLF functional entity can obtain the first model when it determines that it is the first time to receive the first model identifier, that is, the first model does not exist in the AnLF functional entity at this time, and the AnLF functional entity needs to obtain the first model; if the first notification message carries the second indication information, the first notification message can be determined to be a model-sent notification message through the second indication information, and the first model can be obtained based on the first notification message and the model-sent notification message and the first model identifier.

[0249] S604: The MTLF functional entity obtains second accuracy information of the first model.

[0250] The specific implementation principle of S604 can refer to the relevant introduction in the above S504 and will not be repeated here.

[0251] S605: The MTLF functional entity sends a second notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the second notification message from the MTLF functional entity.

[0252] The second notification message is used to indicate the second accuracy information of the first model. The second notification message carries the first model identifier, and the second notification message does not carry the first indication information. For other contents of the second notification message, please refer to the relevant introduction of S505 above, which will not be repeated here.

[0253] Optionally, the second notification message also carries third indication information.

[0254] The third indication information may be used to instruct the MTLF functional entity to provide model accuracy information. It will be understood that carrying the third indication information in the notification message may indicate that the MTLF functional entity provides accuracy information of the model corresponding to the model identifier carried in the notification message. For example, carrying the third indication information in the second notification message may indicate that the MTLF functional entity provides accuracy information of the first model.

[0255] In one possible implementation, the third indication information is used to indicate that the message type is a model accuracy notification message. That is, when the notification message carries the third indication information, it can indicate that the notification message type is a model accuracy notification message. Conversely, when the notification message does not carry the third indication information, it can indicate that the notification message type is not a model accuracy notification message. A model accuracy notification message can be used to provide model accuracy information. It will be understood that when the notification message is a model accuracy notification message, the functional entity receiving the notification message only obtains the model accuracy information and does not need to obtain the model.

[0256] For example, notification message #2f carries a model #2f identifier and third indication information. The model #2f identifier is used to indicate model #2f. In this case, notification message #2f is a model accuracy notification message. After receiving notification message #2f, the AnLF functional entity can determine that notification message #2f is a model accuracy notification message based on the third indication information carried in notification message #2f. As a result, only the accuracy information of model #2e is obtained, i.e., model #2e is not obtained.

[0257] Optionally, the second notification message carries second accuracy information. For details, please refer to the relevant introduction of S505 above, which will not be repeated here.

[0258] S606: The AnLF functional entity does not perform an operation for acquiring the first model according to the second notification message.

[0259] For not performing the operation for obtaining the first model, please refer to the related introduction of the aforementioned S506, which will not be repeated here.

[0260] After the AnLF functional entity receives the second notification message, if the second notification message does not carry the first indication information and the third indication information, then the AnLF functional entity may, when determining that it is not the first time to receive the first model identifier, only obtain the accuracy information of the first model, that is, not perform the operation for obtaining the first model; if the second notification message carries the third indication information, then the AnLF functional entity may determine, based on the third indication information carried in the second notification message, that the second notification message is used to provide the accuracy information of the model, or determine that the message type of the second notification message is a model accuracy notification message, and based on the message type of the second notification message being a model accuracy notification message and the first model identifier, only obtain the accuracy information of the first model, that is, not perform the operation for obtaining the first model. That is, in this case, the AnLF functional entity only obtains the second accuracy information.

[0261] S607, the MTLF functional entity obtains the updated model.

[0262] The updated model is the model after the first model in S602 is updated. The updated model can be a model retrained based on the first model, or the updated model can be a newly generated model, without limitation. It is understood that since each model in the embodiment of the present application is the first model, the updated model is the first model.

[0263] It can be understood that the updated model can be the second model of the aforementioned S605. The specific implementation principle of S607 can refer to the relevant introduction in the above S507 and will not be repeated here.

[0264] S608: The MTLF functional entity sends a third notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the third notification message from the MTLF functional entity.

[0265] The third notification message is used to provide the updated model. The third notification message carries the first model identifier and the first indication information. For other contents of the third message and the first model identifier, refer to the aforementioned description of S508 and are not further described here. It will be understood that the inclusion of the first indication information in the third notification message indicates that the third notification message is a model update notification message. In other words, after receiving the third notification message, the AnLF functional entity needs to obtain the updated model, i.e., the first model.

[0266] Optionally, the second notification message also carries third accuracy information of the first model. For details, please refer to the relevant introduction of S508 above, which will not be repeated here.

[0267] After acquiring the first model, the MTLF functional entity may provide an updated model by sending a third notification message to the AnLF functional entity.

[0268] S609: The AnLF functional entity performs an operation for acquiring the first model according to the third notification message.

[0269] The operation for obtaining the first model may be performed by referring to the related introduction of S503 above, which will not be repeated here.

[0270] After receiving the first notification message, the AnLF functional entity can determine that the message type of the third notification message is a model update notification message according to the first indication information carried in the third notification message, thereby performing an operation for obtaining the first model, that is, obtaining the updated model.

[0271] It can be understood that the first indication information, the second indication information, and the third indication information can be the same information, that is, the three have the same IE, and different bits corresponding to the IE represent different indication information, for example, 00 represents the first indication information, 01 represents the second indication information, and 10 represents the third indication information. The first indication information, the second indication information, and the third indication information can also be different information, that is, each indication information is represented by different information, without limitation.

[0272] According to the technical solution introduced in Scenario 2, when the MTLF functional entity provides the updated model to the AnLF functional entity, the first indication information may be carried in the notification message for providing the updated model, that is, the first indication information is used to indicate that the notification message is a notification message for providing the updated model, so that after receiving the notification message, the AnLF functional entity can determine that the notification message provides the updated model based on the first indication information carried in the notification message, and obtain the model. Correspondingly, when the MTLF functional entity provides the model accuracy information to the AnLF functional entity, the first indication information may not be carried in the notification message for providing the model accuracy information, that is, the first indication information is not carried to indicate that the notification message does not provide the updated model, that is, at this time, the notification message provides the model accuracy information, so that after receiving the notification message, the AnLF functional entity can determine that the notification message is a model accuracy notification message based on the fact that the notification message does not carry the first indication information, thereby only obtaining the model accuracy information, that is, not obtaining the model. In this way, the AnLF functional entity can be prevented from obtaining the model when the notification message is a model accuracy notification message, thereby reducing the communication overhead of the AnLF functional entity and improving the accuracy of the obtained model.

[0273] In addition, the relevant technical effects of the technical solution of the above scenario 2 can refer to the relevant technical effects of the technical solution of the above scenario 1 and will not be repeated here.

[0274] It can be understood that Scenario 1 and Scenario 2 are merely examples, and some steps in Scenario 1 and Scenario 2 can be replaced or combined, for example, S502-S503 and S602-S603 can be replaced, and S508-S509 and S608-S609 can be replaced, without limitation. It can also be understood that when the steps in Scenario 1 and Scenario 2 are replaced or combined, the indication information used to indicate that the first model is updated (denoted as indication information #a) and the indication information used to indicate that the MTLF functional entity provides a model (denoted as indication information #b) can be the same information, that is, the two have the same IE, and different indication information is represented by different bits corresponding to the IE, for example, 0 is used to represent indication information #a, and 1 is used to represent indication information #b. Indication information #a and indication information #b can also be different information, that is, each indication information is represented by different information, without limitation.

[0275] The above describes the specific processes of the communication method provided by the embodiment of the present application in each scenario in combination with Scenario 1 and Scenario 2. The following describes the overall processes of the communication method provided by the embodiment of the present application in Scenario 1 and Scenario 2 in combination with FIG.

[0276] 7 is a flow chart of a communication method according to an embodiment of the present application. The communication method can be applied to the communication between the MTLF functional entity and the AnLF functional entity in the above communication system.

[0277] As shown in Figure 7, the process of the communication method is as follows:

[0278] S701: The MTLF functional entity obtains a first notification message.

[0279] The first notification message can have a variety of different functions. For example, the first notification message can be used to provide a model, such as a new model or an updated model, or the first notification message can be used to provide model accuracy information. In other words, the first notification message can be the first notification message (denoted as message #1), the second notification message (denoted as message #2), or the third notification message in the aforementioned scenario 1 or scenario 2. The new model and the updated model can be referred to the relevant description of S502 above and will not be repeated here.

[0280] The first notification message may carry a model identifier. The model identifier is used to indicate the first model and can be at least one of the following: the ID of the first model, the URL of the first model, or the Full Qualified Domain Name (FQDN) of the first model, without limitation. For details about the model identifier and the first model, refer to the description of the first model identifier and the first model, or the second model identifier and the second model, in Scenario 1 or Scenario 2 above, and will not be repeated here.

[0281] Optionally, the first notification message may also carry first indication information.

[0282] In a first possible implementation, the first indication information may be used to instruct the MTLF functional entity to provide the first model, or the first model is provided. For details, reference may be made to the related introduction of the indication information (S502) in the aforementioned scenario 1, which will not be repeated here.

[0283] In a second possible implementation, the first indication information may be used to indicate that the first model is updated. For details, please refer to the related introduction of the first indication information (S602) in the aforementioned scenario 2, which will not be repeated here.

[0284] Specifically, the first indication information used to indicate that the first model is updated may specifically include: the first indication information is used to indicate that the message type of the first notification message is a model update notification message. For details, please refer to the relevant introduction of the aforementioned S602, which will not be repeated here.

[0285] It is understandable that when the first notification message is a notification message with different functions, the first model corresponds to different models, and in this case the first notification message carries the first indication information or does not carry the first indication information.

[0286] Case 7.1: The first notification message is used to provide a new model.

[0287] In this case, the first model is a new model. For example, when the first notification message is message #1, the first model is a model provided by the MTLF functional entity to the AnLF functional entity after receiving a request message from the AnLF functional entity. In this case, the first notification message may carry first indication information, which is used to instruct the MTLF functional entity to provide the first model.

[0288] It can be understood that for situation 7.1, reference can be made to the relevant introduction of S502 in the aforementioned scenario 1 or S602 in scenario 2, which will not be repeated here.

[0289] Case 7.2: The first notification message is used to provide accuracy information of the model.

[0290] In this case, the first model is a model that the AnLF functional entity has already acquired. For example, when the first notification message is message #2, the AnLF functional entity has already acquired the first model, meaning that the first model already exists. In other words, in this case, the AnLF functional entity stores the first model and / or the first model identifier. In this case, the first notification message does not carry the first indication information.

[0291] It can be understood that if the communication method provided in the embodiment of the present application is applied to the above-mentioned scenario 1 or scenario 2, the first notification message in situation 7.2 is the second notification message in the above-mentioned scenario 1 or scenario 2. For details, please refer to the relevant introduction of S505 or S605, which will not be repeated here.

[0292] Case 7.3: The first notification message is used to provide the updated model.

[0293] In this case, the first model is an updated model. In other words, the first model has been updated. For example, the AnLF functional entity has acquired the second model, meaning that the second model already exists. In other words, the AnLF functional entity stores the second model and / or the second model identifier. The first model may be an updated version of the second model. In this case, the first notification message carries first indication information, which is used to instruct the MTLF functional entity to provide the first model, or to indicate that the first model has been updated.

[0294] It is understood that the first model can be the model after the second model is updated, the model identifier of the first model is the same as the model identifier of the second model, the first model is a model retrained based on the second model, or the first model is a regenerated model. It is understood that the model identifier of the first model is the same as the model identifier of the second model, which means that the model before the update and the model after the update use the same model identifier, that is, each model corresponds to a model identifier, that is, each model is the first model. In other words, in this case, the first model is changeable. For details, please refer to the relevant introduction in the aforementioned S602, which will not be repeated here.

[0295] In addition, if the communication method provided in the embodiment of the present application is applied to the above-mentioned scenario 1 or scenario 2, the first notification message in situation 7.3 is the third notification message in the above-mentioned scenario 1 or scenario 2. For details, please refer to the relevant introduction of S508 or S608, which will not be repeated here.

[0296] It can be seen that when the first model is updated, the first notification message may carry first indication information, where the first indication information is used to indicate that the first model is updated. Correspondingly, when the first model is not updated, the first notification message may not carry the first indication information.

[0297] Alternatively, when the MTLF functional entity provides the first model, the first notification message may carry first indication information, where the first indication information is used to instruct the MTLF functional entity to provide the first model. Accordingly, when the MTLF functional entity does not provide the first model, the second notification message may not carry the first indication information.

[0298] It can be understood that, when the MTLF functional entity requires the AnLF functional entity to obtain the first model, or the AnLF functional entity needs to obtain the first model, the first notification message may carry first indication information, where the first indication information is used to instruct the AnLF functional entity to obtain the first model. Correspondingly, when the MTLF functional entity does not require the AnLF functional entity to obtain the first model, or the AnLF functional entity does not need to obtain the first model, the first notification message may not carry the first indication information.

[0299] S702: The MTLF functional entity sends a first notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the first notification message from the MTLF functional entity.

[0300] The specific implementation principle of S702 can be referred to the relevant introduction in the aforementioned scenario 1 or scenario 2, and will not be repeated here.

[0301] S703: When the first notification message also carries the first indication information, the AnLF functional entity performs an operation for acquiring the first model.

[0302] The operation for obtaining the first model may be to send a request message for obtaining the first model, or to obtain the first model from a preset location. The specific operation is similar to the principle of the aforementioned operation for obtaining the first model. Please refer to the relevant introduction at S503 above for understanding, and will not be repeated here.

[0303] In one possible implementation, when the first notification message also carries the first indication information, the operation performed by the AnLF functional entity for obtaining the first model may specifically include: the AnLF functional entity determines, based on the first indication information, that the message type of the first notification message is a model update notification message; and the AnLF functional entity performs the operation for obtaining the first model based on the message type of the first notification message being a model update notification message and a model identifier. That is, the AnLF functional entity determines, based on the first indication information, the message type of the first notification message, and obtains the first model by determining that the message type of the first notification message is a model update notification message. If the communication method provided in the embodiment of the present application is applied to the above-mentioned scenario 2, the first notification message is the third notification message in the above-mentioned scenario 2. The specific implementation principle of the operation of the AnLF functional entity obtaining the first model based on the first indication information can be referred to the relevant introduction of S609 in the above-mentioned scenario 2, and will not be repeated here.

[0304] In one possible implementation, when the first notification message does not carry the first indication information, the AnLF functional entity does not perform the operation for obtaining the first model. The fact that the first notification message does not carry the first indication information may indicate that the first model has not been updated, or that the first model has been provided to the AnLF functional entity. In this case, the AnLF functional entity does not need to repeatedly obtain the first model. That is, at this time, the AnLF functional entity only obtains the accuracy information of the first model. In this way, the AnLF functional entity can be prevented from repeatedly obtaining the first model, thereby reducing the overhead of the AnLF functional entity. It can be understood that when the first notification message does not carry the first indication information, the first notification message can be the second notification message in the above-mentioned scenario 1 or scenario 2. For details, please refer to the relevant introduction of the above-mentioned scenario 1 and scenario 2, which will not be repeated here.

[0305] Optionally, when the first notification message does not carry the first indication information, the AnLF functional entity does not perform the operation for obtaining the first model, which can specifically include: when the first notification message carries neither the first indication information nor the indication information for indicating that the message type is a model-sent notification message (recorded as the fourth indication information), the AnLF functional entity does not perform the operation for obtaining the first model.

[0306] When the first indication information is used to indicate that the first model has been updated, the fact that the first notification message does not carry the first indication information may indicate that the first notification message does not provide the updated model. The fact that the first notification message does not carry the fourth indication information may indicate that the first notification message does not send a notification message for the model, that is, the first notification message does not provide a new model. The fourth indication information can refer to the second indication information in the aforementioned scenario 2 and will not be repeated here. That is, in this case, the first indication information does not provide a new model or an updated model. Therefore, the AnLF functional entity does not obtain the first model, that is, the operation for obtaining the first model is not performed. In this way, the AnLF functional entity can be prevented from repeatedly obtaining the first model, thereby reducing the overhead of the AnLF functional entity.

[0307] It can be understood that according to the foregoing content, in the embodiment of the present application, the first indication information for instructing the MTLF functional entity to provide a model can be understood as follows: when the MTLF functional entity receives a request message for obtaining a model sent from the AnLF functional entity (such as request message #1 in scenario 1), the MTLF functional entity provides a new model to the AnLF functional entity; or, when the MTLF functional entity obtains the updated model, the MTLF functional entity provides the updated model to the AnLF functional entity. The first indication information for instructing the MTLF functional entity to provide a model can also be understood as follows: when the MTLF functional entity provides a model to the AnLF functional entity for the first time, the MTLF functional entity provides a new model to the AnLF functional entity; or, when the MTLF functional entity provides a model to the AnLF functional entity for not the first time, the MTLF functional entity provides an updated model to the AnLF functional entity. For details, please refer to the relevant introduction of the aforementioned scenario 1, which will not be repeated here.

[0308] In summary, in this embodiment of the present application, the AnLF functional entity can determine whether to obtain the first model based on whether the received first notification message carries the first indication information. Specifically, if the first notification message carries the first indication information, the first model is obtained; if the first notification message does not carry the first indication information, the first model is not obtained. This allows the AnLF functional entity to obtain the first model only when it is needed, thereby improving the flexibility and effectiveness of the AnLF functional entity's model acquisition.

[0309] Optionally, in combination with the above embodiment, the communication method may further include: the MTLF functional entity sending a second notification message to the AnLF functional entity, and the AnLF functional entity correspondingly receiving the second notification message from the MTLF functional entity; wherein the second notification message carries a model identifier and second indication information, and the second indication information is used to indicate that the second notification message is a model delivery notification message. In other words, the second notification message used to provide a new model may carry the second indication information to indicate that the second notification message is used to provide a new model. In this manner, upon receiving the second notification message, the AnLF functional entity may obtain the model based on the second indication information carried in the second notification message.

[0310] Furthermore, after the AnLF functional entity receives the second notification message from the MTLF functional entity, the communication method may further include: the AnLF functional entity determining, based on the second indication information, that the message type of the second notification message is a model-delivered notification message; and the AnLF functional entity performing an operation for acquiring the first model based on the message type of the second notification message being a model-delivered notification message and a model identifier. If the communication method provided in the embodiment of the present application is applied to the above-mentioned scenario 2, the second notification message is the first notification message in the above-mentioned scenario 2. For details, please refer to the relevant descriptions of the above-mentioned scenarios 1 and 2, and will not be repeated here.

[0311] Optionally, in combination with the above embodiment, the communication method may further include: the MTLF functional entity sending a third notification message to the AnLF functional entity, and the AnLF functional entity correspondingly receiving the third notification message from the MTLF functional entity; and the AnLF functional entity, based on the third indication information, not performing an operation for obtaining the first model; wherein the third notification message carries a model identifier and third indication information, and the third indication information is used to indicate that the message type of the third notification message is a model accuracy notification message. The third notification message may be the second notification message in Scenario 2 above. For details, please refer to the relevant description of Scenario 2 above and will not be repeated here. It is understood that after receiving the third notification message, the AnLF functional entity only obtains the accuracy information of the first model.

[0312] Scenario 3:

[0313] For example, FIG8 is a flow chart of the communication method provided in an embodiment of the present application. This communication method can be applied to the communication between the AnLF functional entity and the MTLF functional entity in scenarios such as ML model accuracy monitoring in the 5G architecture. As shown in FIG8, the process of the communication method is as follows:

[0314] S801: AnLF functional entity sends a request message to MTLF functional entity. Correspondingly, MTLF functional entity receives the request message from AnLF functional entity.

[0315] The specific implementation principle of S801 can be found in the related introduction of S501 above and will not be elaborated here.

[0316] S802: The MTLF functional entity sends a first notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the first notification message from the MTLF functional entity.

[0317] The first notification message is used to provide the ML model. The first notification message carries a first model identifier, which is used to indicate the first model. The first model identifier and other contents of the first model can be referred to the relevant introduction of S502 and will not be repeated here.

[0318] After receiving the request message, the MTLF functional entity may provide the first model by sending a first notification message to the AnLF functional entity.

[0319] Optionally, the first notification message also carries first accuracy information of the first model. For details, please refer to the relevant introduction of S502, which will not be repeated here.

[0320] S803: The AnLF functional entity performs an operation for acquiring the first model according to the first notification message.

[0321] The operation for obtaining the first model can refer to the related introduction of the aforementioned S503, which will not be repeated here.

[0322] After receiving the first notification message, the AnLF functional entity may determine whether the first model exists, that is, whether the first model or the first model identifier is stored, based on the first model identifier carried in the first notification message. If the AnLF functional entity determines that the first model or the first model identifier does not exist, the AnLF functional entity performs an operation for obtaining the first model, that is, obtaining the first model.

[0323] S804: The MTLF functional entity obtains second accuracy information of the first model.

[0324] The specific implementation principle of S804 can refer to the relevant introduction in the above S504 and will not be repeated here.

[0325] S805: The MTLF functional entity sends a second notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the second notification message from the MTLF functional entity.

[0326] The second notification message is used to indicate the second accuracy information of the first model, and the second notification message carries the first model identifier. For other contents of the second notification message, please refer to the relevant introduction of S505 above, which will not be repeated here.

[0327] After acquiring the second accuracy information of the first model, the MTLF functional entity may send a second notification message to enable the AnLF functional entity to acquire the latest accuracy information of the first model.

[0328] Optionally, the second notification message carries second accuracy information. For details, please refer to the relevant introduction of S505 above, which will not be repeated here.

[0329] S806: The AnLF functional entity does not perform an operation for acquiring the first model according to the second notification message.

[0330] For not performing the operation for obtaining the first model, please refer to the related introduction of the aforementioned S506, which will not be repeated here.

[0331] After receiving the second notification message, the AnLF functional entity may determine the existence of the first model based on the first model identifier carried in the second notification message. In this case, the AnLF functional entity does not need to obtain the first model, that is, the AnLF functional entity only needs to obtain the second accuracy information of the first model. In this case, the AnLF functional entity does not send a request message for obtaining the first model, that is, it does not obtain the first model.

[0332] It is understood that the AnLF functional entity can determine whether the first model exists by determining whether it stores the first model or the first model identifier. That is, if the AnLF functional entity stores the first model or the first model identifier, the first model exists; if the AnLF functional entity does not store the first model or the first model identifier, the first model does not exist.

[0333] S807, the MTLF functional entity obtains the second model.

[0334] The specific implementation principle of S807 can refer to the relevant introduction in the above S507 and will not be repeated here.

[0335] It can be understood that when the model identifier includes the URL of the model, the MTLF functional entity can send a request for configuring the URL for the second model to the ADRF functional entity after obtaining the second model. Accordingly, the ADRF functional entity receives the request for configuring the URL for the second model from the MTLF functional entity, and the ADRF functional entity configures the URL for the second model according to the request for configuring the URL for the second model. The URL of the second model is different from the URL of the first model, and the second model is the model after the first model is updated. In other words, the ADRF functional entity can configure different URLs for different models, so that after receiving the notification message, the AnLF functional entity can determine whether the model exists, that is, whether to obtain the model, based on the URL of the model carried in the notification message.

[0336] S808: The MTLF functional entity sends a third notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the third notification message from the MTLF functional entity.

[0337] The third notification message is used to provide the updated model of the first model, that is, to provide the second model. The third notification message carries a second model identifier, which is different from the first model identifier. The third notification message and the second model identifier can be referred to the relevant description of S508 above and will not be repeated here.

[0338] Optionally, the second notification message also carries third accuracy information of the second model. For details, please refer to the relevant introduction of S508 above, which will not be repeated here.

[0339] After acquiring the second model, the MTLF functional entity may provide the second model by sending a third notification message to the AnLF functional entity.

[0340] S809: The AnLF functional entity performs an operation for acquiring the second model according to the third notification message.

[0341] The operation of obtaining the second model is similar to the second principle in the aforementioned S503. For details, please refer to the relevant introduction of the aforementioned S503, which will not be repeated here.

[0342] After receiving the third notification message, the AnLF functional entity can determine that the second model does not exist based on the second model identifier carried in the third notification message. In this case, the AnLF functional entity needs to obtain the second model, that is, the AnLF functional entity performs an operation for obtaining the second model to obtain the second model.

[0343] It is understood that the manner in which the AnLF functional entity determines whether the second model exists is the same as the manner in which it determines whether the first model exists, and the same parts can be referenced to each other and will not be repeated here. In addition, when the second notification message also carries the third accuracy information, the AnLF functional entity can also obtain the third accuracy information.

[0344] According to the technical solution described in Scenario 3, the AnLF functional entity can determine whether to acquire a model based on the model identifier carried in the notification message. Specifically, the AnLF functional entity can determine whether a model corresponding to the model identifier exists based on the model identifier carried in the notification message. If the model exists, the operation for acquiring the model is not performed, i.e., the model is not acquired. If the model does not exist, the operation for acquiring the model is performed, i.e., the model is acquired. This prevents the AnLF functional entity from acquiring a model immediately upon receiving a notification message, thereby reducing the AnLF functional entity's communication overhead and improving the flexibility and effectiveness of model acquisition.

[0345] In addition, the relevant technical effects of the technical solution of the above scenario 3 can refer to the relevant technical effects of the technical solution of the above scenario 1 and will not be repeated here.

[0346] The above describes the specific process of the communication method provided by the embodiment of the present application in scenario 3. The following describes the overall process of the communication method provided by the embodiment of the present application in scenario 3 in conjunction with Figures 9 to 11.

[0347] 9 is a flow chart of a communication method according to an embodiment of the present application. The communication method can be applied to the communication between the MTLF functional entity and the AnLF functional entity in the above communication system.

[0348] As shown in Figure 9, the process of the communication method is as follows:

[0349] S901: The MTLF functional entity sends a first notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the first notification message from the MTLF functional entity.

[0350] The first notification message can have a variety of different functions. For example, the first notification message can be used to provide a model, such as a new model or an updated model, or the first notification message can be used to provide model accuracy information. In other words, the first notification message can be the first notification message (denoted as message #1), the second notification message (denoted as message #2), or the third notification message (denoted as message #3) in the aforementioned scenario 3. The new model and the updated model can be referred to the relevant description of S502 above and will not be repeated here.

[0351] The first notification message carries a first model identifier. The first model identifier is used to indicate the first model, and the first model identifier can be at least one of the following: the ID of the first model, the URL of the first model, or the FQDN of the first model, without limitation. The first model identifier and the first model can refer to the related introduction of the first model identifier and the first model, or the second model identifier and the second model in the aforementioned scenario 3, and will not be repeated here. It can be understood that when the first notification message is a notification message with different functions, the first model is a different model. The following describes the different situations.

[0352] Case 9.1: The first notification message is used to provide a new model.

[0353] In this case, the first model is a new model. For example, when the first notification message is message #1, the first model is the first model provided by the MTLF functional entity to the AnLF functional entity.

[0354] Case 9.2: The first notification message is used to provide accuracy information of the model.

[0355] In this case, the first model is a model that the AnLF functional entity has acquired. For example, when the first notification message is message #2, the AnLF functional entity has acquired the first model, that is, the first model already exists, and the AnLF functional entity stores the first model and / or the first model identifier.

[0356] Case 9.3: The first notification message is used to provide the updated model.

[0357] In this case, the first model is an updated model, for example: the AnLF functional entity has acquired the second model, that is, the second model already exists, the AnLF functional entity stores the second model and / or the second model identifier, and the first model is the model after the second model is updated.

[0358] For example, when the first notification message is message #3, the first model is the model after the second model is updated. It is understandable that the second model can be a new model or an updated model, without limitation.

[0359] Optionally, before the AnLF functional entity receives the first notification message from the MTLF functional entity, the above communication method may further include: the MTLF functional entity sends a second notification message to the AnLF functional entity; accordingly, the AnLF functional entity receives the second notification message from the MTLF functional entity; when it is determined that the first model does not exist, the AnLF functional entity performs an operation for obtaining the first model; the AnLF functional entity stores the first model and / or the first model identifier.

[0360] The second notification message carries the first model identifier. It's understood that the second notification message can be used to provide a new model or an updated model. That is, the second notification message can be message #1 or message #3. For example, when the second notification message is used to provide a new model, the first model is the new model; when the second notification message is used to provide an updated model, the first model is the updated model. In this case, the first notification message can be used to provide accuracy information for the first model. That is, the first notification message can be message #2, corresponding to Scenario 2 above.

[0361] Determining that the first model does not exist may indicate that the AnLF functional entity has not yet acquired the first model. In other words, the AnLF functional entity does not store the first model and / or the first model identifier. In other words, in this case, the AnLF functional entity needs to acquire the first model. It is understood that in this case, the first model can be a new model or an updated model.

[0362] The operation for obtaining the first model may be performed by referring to the related introduction of S503 above, which will not be repeated here.

[0363] For example, after the AnLF functional entity sends a request message to the MTLF functional entity, the AnLF functional entity receives a second notification message from the MTLF functional entity. This second notification message carries the identifier of Model #1, meaning that this second notification message is used to provide a new model. After receiving the second notification message, the AnLF functional entity determines that Model #1 does not exist and then sends a request to obtain Model #1. After obtaining Model #1, the AnLF functional entity may store Model #1 and / or the identifier of Model #1 to facilitate subsequent searches for the existence of a specific model.

[0364] For another example, before the AnLF functional entity receives the second notification message from the MTLF functional entity, the AnLF functional entity has already acquired Model #2. The second notification message carries the identifier of Model #1, meaning that the second notification message provides the updated model. In other words, Model #1 is the updated version of Model #2. After receiving the second notification message, if the AnLF functional entity determines that Model #1 does not exist, it can send a request to acquire Model #1 to facilitate subsequent searches for the existence of the model.

[0365] After receiving the second notification message from the MTLF functional entity, the AnLF functional entity may determine whether a first model corresponding to the first model identifier carried in the second notification message exists. If the AnLF functional entity determines that the first model does not exist, the AnLF functional entity may obtain the first model and, after obtaining the first model, store the first model and / or the first model identifier.

[0366] It can be understood that the above-mentioned situation of determining that the first model does not exist may specifically include: the AnLF functional entity determining that the first model does not exist according to the first model and / or the first model identifier.

[0367] After obtaining the model, the AnLF functional entity stores the model and / or model identifier. When the AnLF function determines whether a certain model (e.g., model #A) exists, it can search whether model #A and / or the identifier of model #A are stored. If model #A and / or the identifier of model #A are not stored, it can be determined that model #A does not exist. In other words, the AnLF functional entity can independently determine whether the first model exists. When the AnLF functional entity determines that the first model does not exist, the AnLF functional entity sends a request message for obtaining the first model.

[0368] S902: When it is determined that the first model exists, the AnLF functional entity does not perform an operation for obtaining the first model; and / or when it is determined that the first model does not exist, the AnLF functional entity performs an operation for obtaining the first model.

[0369] Determining the presence of the first model indicates that the AnLF functional entity has already acquired the first model. In other words, the AnLF functional entity stores the first model and / or the first model identifier. In this case, the AnLF functional entity does not need to repeatedly acquire the first model; rather, it only needs to obtain the first accuracy information for the first model. In other words, the MTLF functional entity has already sent a notification message providing the first model. It will be understood that in this case, the first notification message is used to provide the model accuracy information, corresponding to the aforementioned scenario 2.

[0370] The operation for obtaining the first model can refer to the related introduction of the aforementioned S503, which will not be repeated here.

[0371] If the AnLF functional entity determines that the first model exists, it does not perform an operation for acquiring the first model, i.e., it does not acquire the first model, that is, it only acquires the first accuracy information of the first model. In this way, the AnLF functional entity does not acquire the first model when it does not need to, thereby reducing the communication overhead of the AnLF functional entity.

[0372] Optionally, determining the existence of the first model may specifically include: the AnLF functional entity determining the existence of the first model based on a stored first model or first model identifier. It is understood that after acquiring the model, the AnLF functional entity will store the model and / or model identifier. Therefore, when the AnLF functional entity determines that the first model or the first model identifier is stored based on the first model or the first model identifier, it can determine that it has already acquired the first model.

[0373] For determining the situation where the first model does not exist, reference may be made to the related introduction of the aforementioned S901, which will not be repeated here.

[0374] When the AnLF functional entity determines that the first model does not exist, it can execute an operation for obtaining the first model, that is, obtain the first model. In this way, the AnLF functional entity can obtain the first model only when it is needed, thereby improving the flexibility of obtaining the model.

[0375] In summary, in an embodiment of the present application, after receiving the first notification message, the AnLF functional entity can determine whether to obtain the first model based on whether the first model exists. For example, when the AnLF functional entity determines that the first model exists, the first notification message is used to provide accuracy information of the first model. In this case, the AnLF functional entity does not need to obtain the first model, that is, the AnLF functional entity does not perform the operation for obtaining the first model at this time; correspondingly, when the AnLF functional entity determines that the first model does not exist, the role of the first notification message is to provide a new model or an updated model. In this case, the AnLF functional entity needs to obtain the new model, that is, the AnLF functional entity performs the operation for obtaining the first model at this time. It can be seen that the AnLF functional entity can obtain or not obtain the first model according to different situations when receiving the first notification message, that is, the AnLF functional entity can obtain the first model only when it needs to obtain the first model. In this way, the flexibility and effectiveness of the AnLF functional entity in obtaining the model can be improved.

[0376] Optionally, in combination with the above embodiment, the first notification message also carries first accuracy information of the first model. The first accuracy information can be referred to the relevant introduction of the above S502 and will not be repeated here.

[0377] Furthermore, when it is determined that the first model does not exist, the communication method may further include: the AnLF functional entity obtaining first accuracy information. That is, in this case, the AnLF functional entity may not only obtain the first model but also obtain accuracy information of the first model, i.e., the first accuracy information.

[0378] Furthermore, when it is determined that the first model does not exist, the communication method may further include: the AnLF functional entity determining that the first notification message is a message for indicating accuracy information of the first model. That is, the first notification message may be used to provide accuracy information of the first model.

[0379] Furthermore, the AnLF functional entity determining that the first notification message is a message indicating the accuracy information of the first model may specifically include: the AnLF functional entity only obtaining the first accuracy information. In other words, in this case, the AnLF functional entity does not obtain the first model, i.e., does not perform operations for obtaining the first model. This avoids repeated acquisition of the first model, thereby reducing the overhead of the AnLF functional entity.

[0380] 10 is a sixth flow chart of a communication method according to an embodiment of the present application. The communication method may be applicable to communication between an MTLF functional entity and an AnLF functional entity in the above communication system.

[0381] As shown in Figure 10, the process of the communication method is as follows:

[0382] S1001: The MTLF functional entity sends a first notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the first notification message from the MTLF functional entity.

[0383] The first notification message can have various functions. For example, the first notification message can be used to provide a model, such as a new model or an updated model. In other words, the first notification message can be the first notification message (denoted as message #1) or the third notification message (denoted as message #3) in Scenario 3 described above. For details about the new model and the updated model, refer to the description of S502 above and will not be repeated here.

[0384] The first notification message carries a first model identifier. The first model identifier is used to indicate the first model and can be at least one of the following: the ID of the first model, the URL of the first model, or the Full Qualified Domain Name (FQDN) of the first model, without limitation. The first model identifier and the first model can refer to the description of the first model identifier and the first model, or the second model identifier and the second model, in Scenario 3 above, and will not be repeated here.

[0385] It can be understood that when the first notification message is a notification message with different functions, the first model is a different model. For example, when the first notification message is used to provide a new model, the first model is the new model. For example, when the first notification message is used to provide an updated model, the first model is the updated model, such as the first model is the model after the second model is updated.

[0386] S1002: The AnLF functional entity determines that the first model does not exist.

[0387] In a possible implementation, the AnLF functional entity determining that the first model does not exist may specifically include: the AnLF functional entity may search whether the first model exists in its stored models; if the first model does not exist in the stored models, the AnLF functional entity determines that the first model does not exist.

[0388] For example, the AnLF functional entity stores model #4 and model #5, and the first model is model #6, that is, the AnLF functional entity does not store model #6. When the AnLF functional entity does not store model #6, it determines that model #6 does not exist.

[0389] It can be understood that in this case, the AnLF functional entity needs to store the model each time after obtaining the model, so as to subsequently determine whether a certain model exists based on the stored model.

[0390] In another possible implementation, the AnLF functional entity determining that the first model does not exist may specifically include: the AnLF functional entity may search whether there is the first model identifier in its stored model identifiers; if the first model identifier does not exist in the stored model identifiers, the AnLF functional entity determines that the first model does not exist.

[0391] For example, the AnLF functional entity stores model #4 and model #5 identifiers, and the first model identifier is model #6 identifier, that is, the AnLF functional entity does not store model #6 identifier. When the AnLF functional entity does not store model #6 identifier, it determines that model #6 does not exist.

[0392] It can be understood that in this case, the AnLF functional entity needs to store the model identifier of the model each time after obtaining the model, so as to subsequently determine whether a certain model exists based on the stored model identifier.

[0393] S1003: The AnLF functional entity performs an operation for acquiring a first model.

[0394] The operation for obtaining the first model can refer to the related introduction of the aforementioned S503, which will not be repeated here.

[0395] Optionally, after the AnLF functional entity performs an operation for acquiring the first model, the communication method may further include: the AnLF functional entity storing the first model and / or the first model identifier. In this manner, upon receiving a notification message carrying the first model identifier, the AnLF functional entity can search stored models for the first model, or search stored model identifiers for the first model identifier. By finding the first model or the first model identifier, the AnLF functional entity can determine that the first model already exists, thereby avoiding repeated acquisition of the first model and reducing the AnLF functional entity's overhead.

[0396] Optionally, the communication method may further include: the MTLF functional entity sends a second notification message to the AnLF functional entity; accordingly, the AnLF functional entity receives the second notification message from the MTLF functional entity; the AnLF functional entity determines that the first model exists; and the AnLF functional entity does not perform an operation for acquiring the first model.

[0397] The second notification message carries the first model identifier and is used to provide accuracy information of the first model. For details, please refer to the relevant introduction of S805 above, which will not be repeated here.

[0398] After receiving the second notification message, if the AnLF functional entity determines that the first model exists, this indicates that the AnLF functional entity has already obtained the first model and does not need to obtain the first model again. In this case, the AnLF functional entity does not perform the operation to obtain the first model, that is, the AnLF functional entity does not obtain the first model. This reduces the overhead of the AnLF functional entity.

[0399] Furthermore, the AnLF functional entity determining the existence of the first model may specifically include: the AnLF functional entity determining the existence of the first model based on a stored first model or first model identifier. In other words, if the first model or first model identifier is stored, it can indicate that the AnLF functional entity has already obtained the first model, i.e., the existence of the first model can be determined. In this way, the existence of the first model can be accurately determined.

[0400] It is understood that if the AnLF functional entity does not store the first model or the first model identifier, it may indicate that the AnLF functional entity has not obtained the first model. In this case, the AnLF functional entity needs to obtain the first model, that is, the AnLF functional entity needs to perform an operation for obtaining the first model.

[0401] Optionally, the first notification message also carries first accuracy information of the first model. The first accuracy information can be referred to the relevant introduction of the aforementioned S802 and will not be repeated here.

[0402] Furthermore, when it is determined that the first model does not exist, the communication method may further include: the AnLF functional entity obtains first accuracy information. For details, reference may be made to the relevant content of the embodiment shown in FIG. 9 , which will not be repeated here.

[0403] Furthermore, when it is determined that the first model does not exist, the above-mentioned communication method may also include: the AnLF functional entity determines that the first notification message is a message for indicating the accuracy information of the first model. For details, please refer to the relevant content of the embodiment shown in Figure 9 above, which will not be repeated here.

[0404] Furthermore, the AnLF functional entity determining that the first notification message is a message for indicating the accuracy information of the first model may specifically include: the AnLF functional entity only obtains the first accuracy information. For details, please refer to the relevant content of the embodiment shown in Figure 9 above, which will not be repeated here.

[0405] In summary, in this embodiment of the present application, upon receiving the first notification message, the AnLF functional entity can determine whether to acquire the first model by determining whether the first model exists. For example, if the AnLF functional entity determines that the first model exists, it does not repeatedly acquire the first model; otherwise, it acquires the first model only if it determines that the first model does not exist. This improves the flexibility and effectiveness of the AnLF functional entity's model acquisition.

[0406] 11 is a flow chart of the seventh embodiment of the communication method provided in the present application. The communication method can be applied to the communication between the MTLF functional entity and the AnLF functional entity in the above communication system.

[0407] As shown in Figure 11, the process of the communication method is as follows:

[0408] S1101: The MTLF functional entity sends a first notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the first notification message from the MTLF functional entity.

[0409] The first notification message carries a first model identifier, and the first model identifier is used to indicate the first model.

[0410] The specific implementation principle of S1101 can refer to the relevant introduction in the above S901 and will not be repeated here.

[0411] S1102: The MTLF functional entity determines a second notification message.

[0412] The second notification message is used to provide the updated model, namely the second model (described below), or to provide accuracy information for the first model. The second notification message carries a second model identifier, which can be at least one of the following: the ID of the second model, the URL of the second model, or the Full Qualified Domain Name (FQDN) of the second model, without limitation. The second model identifier is used to indicate the second model. For details, please refer to the aforementioned related description and will not be repeated here.

[0413] The second model can be different from or the same as the first model. The similarity or difference between the two depends on the function of the second notification message. The following describes the different situations.

[0414] Case 11.1: The second model is different from the first model.

[0415] In this case, the second model is an updated model of the first model, that is, the second model can be a model retrained based on the first model, or the second model can be a regenerated model. That is, the second notification message is used to provide an updated model, that is, the second model. At this time, the second model identifier is different from the first model identifier, that is, the updated model is provided through different indications of the model identifier, that is, different model identifiers correspond to different models. In other words, after receiving the second notification message, the AnLF functional entity can determine that the second model is an updated model based on the fact that the second model identifier carried by the second notification message is different from the first model identifier, that is, the AnLF functional entity can obtain the second model at this time.

[0416] Case 11.2: The second model is identical to the first model.

[0417] In this case, the first model is not updated, and the second notification message is used to provide accuracy information for the first model. In this embodiment of the present application, different models correspond to different model identifiers, and the AnLF functional entity determines whether to acquire a model based on whether the model identifiers are the same or different. Therefore, in this case, the second model identifier is the same as the first model identifier.

[0418] After updating the first model, or after determining the accuracy of the first model, the MTLF functional entity may determine a second notification message. After updating the first model, the second notification message may carry the second model identifier; or after determining the accuracy of the first model, the second notification message may carry the first model identifier.

[0419] S1103: The MTLF functional entity sends a second notification message to the AnLF functional entity. Correspondingly, the AnLF functional entity receives the second notification message from the MTLF functional entity.

[0420] Optionally, in the case where the second model identifier is the URL of the second model, before the MTLF functional entity sends the second notification message to the AnLF functional entity, the above-mentioned communication method may also include: the MTLF functional entity sends a request to the ADRF functional entity for requesting to configure a URL for the second model, and accordingly, the ADRF functional entity receives the request from the MTLF functional entity for requesting to configure a URL for the second model; the ADRF functional entity configures the URL for the second model according to the request for requesting to configure the URL for the second model, the URL of the second model is different from the URL of the first model, and the second model is a model after the first model is updated.

[0421] It can be seen that when the model identifier is the URL of the model, the ADRF functional entity can configure different URLs for different models. In this way, the ADRF functional entity can determine whether the model corresponding to the model identifier is updated based on the model URL, that is, whether the model needs to be obtained.

[0422] S1104: When the second model identifier is different from the first model identifier, the AnLF functional entity performs an operation for acquiring the second model; or, when the second model identifier is the same as the first model identifier, the AnLF functional entity does not perform an operation for acquiring the first model.

[0423] After receiving the second notification message, the AnLF functional entity can determine whether the second model exists, that is, whether to obtain the second model, by checking whether the second model identifier is the same as the first model identifier. If the second model identifier is different from the first model identifier, it means that the second notification message provides an updated model, that is, the second model. In this case, the AnLF functional entity needs to obtain the second model, that is, the AnLF functional entity performs an operation for obtaining the second model. If the second model identifier is the same as the first model identifier, it means that the second notification message provides accuracy information of the first model. In this case, the AnLF functional entity does not need to repeatedly obtain the first model, that is, the AnLF functional entity does not perform an operation for obtaining the first model.

[0424] The principle of the AnLF functional entity determining whether the second model exists is similar to the principle of the AnLF functional entity determining whether the first model exists. For details, please refer to the relevant content of the embodiment shown in Figure 9 above, which will not be repeated here.

[0425] In summary, in this embodiment of the present application, different models can be indicated by different model identifiers. This allows the AnLF functional entity, upon receiving a model identifier carried in a notification message, to determine whether the model corresponding to the model identifier exists based on the model identifier and, therefore, to determine whether to acquire the model. This prevents the AnLF functional entity from repeatedly acquiring models when no model is needed, thereby increasing flexibility and efficiency in model acquisition and reducing the AnLF functional entity's overhead.

[0426] Figure 12 is a structural diagram of a communication device according to an embodiment of the present application. As shown in Figure 12, the communication device 1200 includes a transceiver module 1201 and a processing module 1202. For ease of illustration, Figure 12 only shows the main components of the communication device.

[0427] In some embodiments, the communication device 1200 may be applicable to the communication system shown in FIG. 4 , and execute the functions of the AnLF functional entity in the method shown in FIG. 7 .

[0428] The transceiver module 1201 is used to receive a first notification message from the MTLF functional entity, where the first notification message carries a model identifier, which is used to indicate the first model; the processing module 1202 is used to perform an operation for obtaining the first model when the first notification message also carries first indication information, where the first indication information is used to indicate that the first model is updated, or the first indication information is used to instruct the MTLF functional entity to provide the first model.

[0429] In a possible design scheme, the processing module 1202 is further configured to not perform an operation for obtaining the first model when the first notification message does not carry the first indication information.

[0430] In a possible design scheme, the processing module 1202 is specifically configured to: when the first notification message carries neither the first indication information nor the indication information for indicating that the message type is a model-delivered notification message, the AnLF functional entity does not perform an operation for obtaining the first model.

[0431] In a possible design scheme, the first indication information is used to indicate that the first model is updated, specifically including: the first indication information is used to indicate that the message type of the first notification message is a model update notification message.

[0432] Optionally, the processing module 1202 is specifically used to determine that the message type of the first notification message is a model update notification message according to the first indication information; and according to the message type of the first notification message being a model update notification message and a model identifier, perform an operation for obtaining the first model.

[0433] In one possible design, the transceiver module 1201 is further configured to receive a second notification message from the MTLF functional entity, where the second notification message carries a model identifier and second indication information, where the second indication information is configured to indicate that the message type of the second notification message is a model delivery notification message.

[0434] Optionally, after the AnLF functional entity receives the second notification message from the MTLF functional entity, the processing module 1202 is further used to determine, based on the second indication information, that the message type of the second notification message is a model delivery notification message; and based on the message type of the second notification message being a model delivery notification message and a model identifier, perform an operation for obtaining the first model.

[0435] In one possible design scheme, the transceiver module 1201 is also used to receive a third notification message from the MTLF functional entity, where the third notification message carries a model identifier and third indication information, and the third indication information is used to indicate that the message type of the third notification message is a model accuracy notification message; the processing module 1202 is also used to not perform an operation for obtaining the first model based on the third indication information.

[0436] In one possible design solution, the operation for obtaining the first model is sending a request message for obtaining the first model.

[0437] In one possible design scheme, the first model is a model obtained by updating the second model, the model identifier of the first model is the same as the model identifier of the second model, the first model is a model retrained based on the second model, or the first model is a regenerated model.

[0438] In a possible design solution, the model identifier is the ID and / or URL of the first model.

[0439] Optionally, the transceiver module 1201 may include a sending module (not shown in FIG12 ) and a receiving module (not shown in FIG12 ). The sending module is used to implement the sending function of the communication device 1200 , and the receiving module is used to implement the receiving function of the communication device 1200 .

[0440] Optionally, the communication device 1200 may further include a storage module (not shown in FIG12 ) storing a program or instruction. When the processing module 1202 executes the program or instruction, the communication device 1200 may perform the functions of the AnLF functional entity in the method shown in FIG7 in the above method.

[0441] It can be understood that the communication device 1200 can be a network device, a chip (system) or other parts or components that can be set in the network device, or a device that includes a network device. This application does not limit this.

[0442] In addition, the technical effects of the communication device 1200 can refer to the technical effects of the communication method shown in Figure 7, and will not be repeated here.

[0443] In some other embodiments, the communication device 1200 may be applicable to the communication system shown in FIG. 4 , and execute the functions of the MTLF functional entity in the method shown in FIG. 7 .

[0444] The processing module 1202 is used to obtain a first notification message, where the first notification message carries a model identifier, which is used to indicate the first model. The transceiver module 1201 is used to send a first notification message to the AnLF functional entity. When the first model is updated, the first notification message carries first indication information, which is used to indicate that the first model is updated. Alternatively, when the MTLF functional entity provides the first model, the first notification message carries first indication information, which is used to instruct the MTLF functional entity to provide the first model.

[0445] In a possible design scheme, when the first model is not updated, the second notification message does not carry the first indication information; or, when the MTLF functional entity does not provide the first model, the second notification message does not carry the first indication information.

[0446] In a possible design scheme, the first indication information is used to indicate that the first model is updated, specifically including: the first indication information is used to indicate that the message type of the first notification message is a model update notification message.

[0447] In a possible design scheme, the transceiver module 1201 is further used to send a second notification message to the AnLF functional entity, where the second notification message carries a model identifier and second indication information, and the second indication information is used to indicate that the message type of the second notification message is a model delivery notification message.

[0448] In one possible design scheme, the transceiver module 1201 is further used to send a third notification message to the AnLF functional entity, where the third notification message carries a model identifier and third indication information, and the third indication information is used to indicate that the message type of the third notification message is a model accuracy notification message.

[0449] In one possible design scheme, the first model is a model obtained by updating the second model, the model identifier of the first model is the same as the model identifier of the second model, the first model is a model retrained based on the second model, or the first model is a regenerated model.

[0450] In a possible design solution, the model identifier is the ID of the first model and / or the uniform resource locator URL.

[0451] Optionally, the transceiver module 1201 may include a sending module (not shown in FIG12 ) and a receiving module (not shown in FIG12 ). The sending module is used to implement the sending function of the communication device 1200 , and the receiving module is used to implement the receiving function of the communication device 1200 .

[0452] Optionally, the communication device 1200 may further include a storage module (not shown in FIG12 ) storing a program or instruction. When the processing module 1202 executes the program or instruction, the communication device 1200 may perform the functions of the MTLF functional entity in the method shown in FIG7 in the above method.

[0453] It can be understood that the communication device 1200 can be a network device, a chip (system) or other parts or components that can be set in the network device, or a device that includes a network device. This application does not limit this.

[0454] In addition, the technical effects of the communication device 1200 can refer to the technical effects of the communication method shown in Figure 7, and will not be repeated here.

[0455] Figure 13 is a second structural diagram of a communication device provided in an embodiment of the present application. Exemplarily, the communication device may be a terminal, or a chip (system) or other component or assembly that can be provided in a terminal. As shown in Figure 13, the communication device 1300 may include a processor 1301. Optionally, the communication device 1300 may further include a memory 1302 and / or a transceiver 1303. The processor 1301 is coupled to the memory 1302 and the transceiver 1303, such as by a communication bus.

[0456] The following is a detailed introduction to the various components of the communication device 1300 with reference to FIG13:

[0457] The processor 1301 is the control center of the communication device 1300 and can be a single processor or a collective term for multiple processing elements. For example, the processor 1301 can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0458] Optionally, the processor 1301 can execute various functions of the communication device 1300 by running or executing software programs stored in the memory 1302 and calling data stored in the memory 1302, such as executing the communication method shown in Figures 5 to 11 above.

[0459] In a specific implementation, as an embodiment, the processor 1301 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG13 .

[0460] In a specific implementation, as an embodiment, the communication device 1300 may also include multiple processors, such as the processor 1301 and the processor 1304 shown in FIG13 . Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0461] Among them, the memory 1302 is used to store the software program for executing the solution of this application, and the execution is controlled by the processor 1301. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0462] Alternatively, the memory 1302 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1302 may be integrated with the processor 1301 or exist independently and be coupled to the processor 1301 via an interface circuit (not shown in FIG. 13 ) of the communication device 1300. This embodiment of the present application does not specifically limit this.

[0463] Transceiver 1303 is used for communication with other communication devices. For example, if communication device 1300 is a terminal, transceiver 1303 can be used to communicate with a network device or another terminal device. For another example, if communication device 1300 is a network device, transceiver 1303 can be used to communicate with a terminal or another network device.

[0464] Optionally, the transceiver 1303 may include a receiver and a transmitter (not shown separately in FIG13 ), wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0465] Optionally, the transceiver 1303 can be integrated with the processor 1301, or can exist independently and be coupled to the processor 1301 through the interface circuit of the communication device 1300 (not shown in Figure 13). This embodiment of the present application does not specifically limit this.

[0466] It is understandable that the structure of the communication device 1300 shown in FIG13 does not constitute a limitation on the communication device, and an actual communication device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0467] In addition, the technical effects of the communication device 1300 can refer to the technical effects of the methods described in the above method embodiments, and will not be repeated here.

[0468] An embodiment of the present application also provides a communication chip having instructions stored therein. When the chip is run on a communication device, the method provided in the embodiment of the present application is implemented.

[0469] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0470] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0471] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a set of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0472] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0473] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0474] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0475] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0476] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0477] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0478] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0479] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0480] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0481] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: The method comprises: The analysis logic function AnLF functional entity receives a first notification message from the model training logic function MTLF functional entity, where the first notification message carries a model identifier, and the model identifier is used to indicate a first model; In a case where the first notification message also carries first indication information, the AnLF functional entity performs an operation for acquiring the first model, the first indication information is used to indicate that the first model is updated, or the first indication information is used to instruct the MTLF functional entity to provide the first model.

2. The method according to claim 1, characterized in that The first indication information is further used to instruct the MTLF functional entity to provide a new model or an updated model.

3. The method according to claim 1 or 2, characterized in that: Before the AnLF functional entity receives the first notification message from the MTLF functional entity, the method further includes: A second model is obtained, where a model identifier of the second model is provided by the MTLF functional entity.

4. The method according to claim 3, characterized in that The obtaining of the second model comprises: The AnLF functional entity receives a message carrying a model identifier indicating the second model from the MTLF functional entity; The AnLF functional entity acquires the second model based on the model identifier used to indicate the second model.

5. The method according to claim 3 or 4, characterized in that: The method further comprises: Receive model accuracy information of the second model from the MTLF functional entity.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Model accuracy information of the first model is received from the MTLF functional entity.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: In a case where the first notification message does not carry the first indication information, the AnLF functional entity does not perform an operation for acquiring the first model.

8. The method according to claim 7, characterized in that The step of, in a case where the first notification message does not carry the first indication information, the AnLF functional entity not performing an operation for acquiring the first model, includes: In a case where the first notification message carries neither the first indication information nor indication information used to indicate that the message type is a model-sent notification message, the AnLF functional entity does not perform an operation for acquiring the first model.

9. The method according to any one of claims 1 to 8, characterized in that The first indication information is used to indicate that the first model is updated and specifically includes: the first indication information is used to indicate that the message type of the first notification message is a model update notification message.

10. The method according to claim 9, characterized in that In a case where the first notification message carries the first indication information, the AnLF functional entity performs an operation for acquiring the first model, including: The AnLF functional entity determines, according to the first indication information, that the message type of the first notification message is the model update notification message; The AnLF functional entity performs an operation for acquiring the first model according to the message type of the first notification message being the model update notification message and the model identifier.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: The AnLF functional entity receives a second notification message from the MTLF functional entity, where the second notification message carries the model identifier and second indication information, where the second indication information is used to indicate that a message type of the second notification message is a model-delivered notification message.

12. The method according to claim 11, characterized in that After the AnLF functional entity receives the second notification message from the MTLF functional entity, the method further includes: The AnLF functional entity determines, according to the second indication information, that the message type of the second notification message is the model-sent notification message; The AnLF functional entity sends a notification message and the model identifier to the model according to the message type of the second notification message, and performs an operation for acquiring the first model.

13. The method according to any one of claims 1 to 12, characterized in that The method further comprises: The AnLF functional entity receives a third notification message from the MTLF functional entity, where the third notification message carries the model identifier and third indication information, where the third indication information is used to indicate that the message type of the third notification message is a model accuracy notification message. interest; The AnLF functional entity does not perform an operation for acquiring the first model according to the third indication information.

14. The method according to any one of claims 1 to 13, characterized in that The operation for obtaining the first model is sending a request message for obtaining the first model.

15. The method according to any one of claims 1 to 14, characterized in that The first model is a model obtained by updating the second model, the model identifier of the first model is the same as the model identifier of the second model, the first model is a model retrained based on the second model, or the first model is a regenerated model.

16. The method according to any one of claims 1 to 15, characterized in that The model identifier is the ID of the first model and / or the uniform resource locator URL.

17. A communication method, characterized in that: The method comprises: The model training logic function MTLF functional entity obtains a first notification message, where the first notification message carries a model identifier, and the model identifier is used to indicate a first model; The MTLF functional entity sends the first notification message to the analysis logic function AnLF functional entity; In which, when the first model is updated, the first notification message carries first indication information, and the first indication information is used to indicate that the first model is updated; or, when the MTLF functional entity provides the first model, the first notification message carries first indication information, and the first indication information is used to indicate that the MTLF functional entity provides the first model.

18. The method according to claim 17, characterized in that The first indication information is further used to instruct the MTLF functional entity to provide a new model or an updated model.

19. The method according to claim 17 or 18, characterized in that The method further comprises: A message carrying a model identifier indicating the second model is sent to the AnLF functional entity.

20. The method according to claim 19, characterized in that The method further comprises: Sending model accuracy information of the second model to the AnLF functional entity.

21. The method according to any one of claims 17 to 20, characterized in that The method further comprises: Sending model accuracy information of the first model to the AnLF functional entity.

22. The method according to any one of claims 17 to 21, characterized in that In the case where the first model is not updated, the first notification message does not carry the first indication information; or, In a case where the MTLF functional entity does not provide the first model, the first notification message does not carry the first indication information.

23. The method according to any one of claims 17 to 22, characterized in that The first indication information is used to indicate that the first model is updated and specifically includes: the first indication information is used to indicate that the message type of the first notification message is a model update notification message.

24. The method according to any one of claims 17 to 23, characterized in that The method further comprises: The MTLF functional entity sends a second notification message to the AnLF functional entity, where the second notification message carries the model identifier and second indication information, where the second indication information is used to indicate that a message type of the second notification message is a model-delivered notification message.

25. The method according to any one of claims 17 to 24, characterized in that The method further comprises: The MTLF functional entity sends a third notification message to the AnLF functional entity, where the third notification message carries the model identifier and third indication information, where the third indication information is used to indicate that a message type of the third notification message is a model accuracy notification message.

26. The method according to any one of claims 17 to 25, characterized in that The first model is a model obtained by updating the second model, the model identifier of the first model is the same as the model identifier of the second model, the first model is a model retrained based on the second model, or the first model is a regenerated model.

27. The method according to any one of claims 17 to 26, characterized in that The model identifier is the ID of the first model and / or the uniform resource locator URL.

28. A communication device, characterized in that: The apparatus comprises: a module for executing the method as claimed in any one of claims 1-27.

29. A communication device, characterized in that: The communication device comprises: a processor and a memory; the memory is used to store computer instructions, and when the processor executes the instructions, the communication device executes the method according to any one of claims 1-27.

30. A communication system, characterized in that: The communication system comprises at least one of the following: an analysis logic function AnLF functional entity for executing the method according to any one of claims 1 to 16, and a model training logic function MTLF functional entity for executing the method according to any one of claims 17 to 27.

31. A communication chip, characterized in that: Instructions are stored therein, and when the chip runs on a communication device, the method according to any one of claims 1 to 27 is implemented.

32. A computer-readable storage medium, characterized in that: The computer-readable storage medium comprises a computer program or instructions, and when the computer program or instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 27.

33. A computer program product, characterized in that The computer program product comprises a computer program or instructions, and when the computer program or instructions are executed by a communication device, the method according to any one of claims 1 to 27 is executed.

Images