Communication method and apparatus

Abstract

The present application belongs to the technical field of communications. Provided are a communication method and apparatus, which are used for preventing an AI / ML model identifier conflict. The method comprises: determining a first identifier and / or an identifier list, and sending the first identifier and / or the identifier list to a second device, wherein the first identifier is used for uniquely labeling a first AI / ML model in a cross-domain management system, and any identifier in the identifier list is used for uniquely labeling a corresponding AI / ML model in the cross-domain management system, the identifier list comprising at least two identifiers.

Description

Communication method and apparatus

[0001] The present application claims priority to the Chinese patent application No. 202411098178.4, filed on August 9, 2024, and entitled “Communication method and apparatus”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, in particular to a communication method and apparatus. BACKGROUND

[0003] The related applications of artificial intelligence (AI) and machine learning (ML) technologies are increasingly being adopted by a wider range of industries, and AI / ML models are used in various fields of the 5th generation (5G) mobile communication system, such as intelligent optimization use cases of radio access network (RAN), management data analysis services of network management, and network data analysis services of core network (CN).

[0004] In a network, an AI / ML model can be assigned an identifier to identify, but since the training of the AI / ML model can be performed on different network devices, the AI / ML model identifiers of different network devices can be repeated, and the AI / ML model identifiers can conflict, causing the network to be unable to distinguish the AI / ML model due to the identifier conflict, resulting in the failure of management and control of the training, inference, deployment, etc. of the AI / ML model. SUMMARY

[0005] Embodiments of the present application provide a communication method and apparatus to avoid the identifier conflict of the AI / ML model.

[0006] To achieve the above object, the present application adopts the following technical solutions:

[0007] In a first aspect, a communication method is provided. The method can be performed by a first device, a module (e.g., a processor, a chip, or a chip system) applied to the first device, or a logic node, a logic module, or software that can implement all or part of the functions of the first device. For the convenience of description, the method performed by the first device is taken as an example in the following description. The method includes determining a first identifier and / or a list of identifiers, and sending the first identifier and / or the list of identifiers to a second device. The first identifier is used to uniquely identify a first AI / ML model in a cross-domain management system, and any identifier in the list of identifiers is used to uniquely identify a corresponding AI / ML model in the cross-domain management system. The list of identifiers includes at least two identifiers.

[0008] Based on the above method, the first device can determine a first identifier for a specified AI / ML model, such as the first AI / ML model, to uniquely identify the first AI / ML model in the cross-domain management system. Alternatively, the first device can also determine a list of identifiers to select an identifier from the list of identifiers to uniquely identify an AI / ML model in the cross-domain management system, thereby avoiding identifier conflicts of AI / ML models in the cross-domain management system.

[0009] In a possible design, the first AI / ML model performs training on the second device. In this case, the first device can assign the first identifier to the second device for use, without the second device determining the identifier by itself, to reduce the overhead of the second device.

[0010] In a possible design, the first AI / ML model performs training on the third device. Similarly, the first device can also assign the first identifier to the third device for use, without the third device determining the identifier by itself, to reduce the overhead of the third device.

[0011] Optionally, the method of the first aspect further includes sending an identifier of a third device to the second device, the third device being an access network device or a network data analysis network element, so that the second device can forward the first identifier to the third device according to the identifier of the third device.

[0012] In a possible design, the method of the first aspect further includes sending a subnet identifier to the second device, the first AI / ML model being used in a subnet indicated by the subnet identifier, so that the second device can deploy the trained first AI / ML model to the corresponding subnet to provide services, to achieve targeted model deployment.

[0013] In a possible design, in the case of sending the identification list to the second device, the method of the first aspect further includes: receiving a second identification returned by the second device, the second identification being an identification in the identification list, that is, the second device / third device can select an identification (such as the second identification) from the identification list according to its own needs to identify the AI / ML model, and return the second identification to the first device, and the first device determines the first identification, and the freedom and flexibility of assigning the identification list are better.

[0014] In a possible design, the first device is a cross-domain management function unit, and the second device is a domain management function unit.

[0015] In a second aspect, a communication method is provided, and the method is applied to a second device. The method can be executed by the second device, a module (for example, a processor, a chip, or a chip system) applied to the second device, or a logic node, a logic module, or software that can realize all or part of the function of the second device. For convenience of description, the method is introduced below by taking the example of being executed by the second device. The method includes: determining a second identification, and sending the second identification to a first device. The second device and the first device are devices in a management domain, and the second identification is used to uniquely identify a first AI / ML model in a cross-domain management system.

[0016] Based on the above method, the second device can determine a second identification that is unique to a first AI / ML model, and the second device can avoid identification conflicts of AI / ML models in the cross-domain management system. The second device reports the second identification to the first device, and the first device can also manage the AI / ML model according to the second identification.

[0017] In a possible design, determining the second identification includes: receiving an identification list from the first device, and determining the second identification according to the identification list. The second identification is an identification in the identification list. Any identification in the identification list is used to uniquely identify a corresponding AI / ML model in the cross-domain management system, and the identification list includes at least two identifications.

[0018] In a possible design, determining the second identification includes: determining the second identification according to at least two of the following: an identification of the first AI / ML model, an identification determined by the second device, and a subnet identification associated with the second device. Multiple parameters are introduced to construct the second identification, which can guarantee the uniqueness of the second identification and avoid identification conflicts.

[0019] Optionally, the sending the second identifier to the first device comprises: sending the second identifier and an identifier of the first AI / ML model associated with the second identifier to the first device, so that the first device obtains the second identifier for identifying the first AI / ML model through the association relationship, and avoids AI / ML model management failure caused by the first device failing to identify the second identifier.

[0020] In a possible design, the first AI / ML model is trained on the second device.

[0021] In a possible design, the method of the second aspect further includes: sending the second identifier to a third device, and the first AI / ML model is trained on the third device, and the third device is a device of a service domain, that is, the second identifier is sent to the third device for use.

[0022] Optionally, the third device is an access network device or a data analysis network element.

[0023] In a possible design, the method of the second aspect further includes: receiving an identifier of the third device from the first device; and accordingly, the sending the second identifier to the third device comprises: sending the second identifier to the third device according to the identifier of the third device.

[0024] In a possible design, the method of the second aspect further includes: receiving a subnetwork identifier from the first device, and the first AI / ML model is used for a subnetwork indicated by the subnetwork identifier.

[0025] In a possible design, the first device is a cross-domain management function unit, and the second device is a domain management function unit.

[0026] It can be understood that other related technical effects of the method of the second aspect can also be referred to the related descriptions of the method of the first aspect, and details are not repeated.

[0027] In a third aspect, a communication method is provided, which can be executed by a third device, executed by a module (for example, a processor, a chip, or a chip system) applied to the third device, or executed by a logic node, a logic module, or software capable of realizing all or part of the functions of the third device. For the convenience of description, the method is introduced below by taking the third device as an example. The method includes: determining a second identifier, and sending the second identifier to a second device. The second identifier is used to uniquely identify a first AI / ML model in a cross-domain management system, the second device is a device of a management domain, and the third device is a device of a service domain.

[0028] In a possible design, determining the second identifier includes: receiving an identifier list from the second device, and determining the second identifier according to the identifier list, the second identifier being an identifier in the identifier list. Any identifier in the identifier list is used to uniquely identify a corresponding AI / ML model in the cross-domain management system, and the identifier list includes at least two identifiers.

[0029] Optionally, determining the second identifier includes: determining the second identifier according to at least two of the following: the identifier of the first AI / ML model, the identifier determined by the third device, and the identifier of the network in which the third device is located, that is, introducing multiple parameters to construct the second identifier can ensure its uniqueness and avoid identifier conflicts.

[0030] In a possible design, the first AI / ML model performs training on the third device.

[0031] In a possible design, the second device is a domain management function unit, and the third device is an access network device or a network analysis network element.

[0032] It can be understood that other related technical effects of the method of the second aspect can also be referred to the related descriptions of the method of the first aspect, and will not be repeated here.

[0033] In a fourth aspect, a communication apparatus is provided. The communication apparatus is configured to perform the communication method in any of the implementation manners of the first aspect or the third aspect.

[0034] In the present application, the communication apparatus of the fourth aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus containing the terminal device or the network device. The chip (system) or other components or assemblies can be arranged in the terminal device or the network device.

[0035] It should be understood that the communication apparatus of the fourth aspect includes modules, units, or means corresponding to the communication method of any of the first aspect or the third aspect, which can be implemented by hardware, software, or by executing corresponding software by hardware. The hardware or software includes one or more modules or units for performing functions involved in the communication method.

[0036] In a fifth aspect, a communication apparatus is provided. The communication apparatus includes a processor configured to perform the communication method in any of the implementation manners of the first aspect or the third aspect.

[0037] In a possible design, the communication apparatus of the fifth aspect can further include a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication apparatus of the fifth aspect and other communication apparatuses.

[0038] In an example, the communication apparatus in the fifth aspect can further include a memory. The memory can be integrated with the processor, or can be separately arranged. The memory can be configured to store the computer program and / or data related to the communication method in any of the first aspect or the third aspect.

[0039] In the present application, the communication apparatus in the fifth aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus including the terminal device or the network device. The chip (system) or other components or assemblies can be arranged in the terminal device or the network device.

[0040] In the sixth aspect, a communication apparatus is provided. The communication apparatus includes a processor coupled with a memory. The processor is configured to execute a computer program stored in the memory, so that the communication apparatus performs the communication method in any of the possible implementation manners of the first aspect or the third aspect.

[0041] In an example, the communication apparatus in the sixth aspect can further include a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be configured to enable the communication apparatus in the fifth aspect to communicate with other communication apparatuses.

[0042] In the present application, the communication apparatus in the sixth aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus including the terminal device or the network device. The chip (system) or other components or assemblies can be arranged in the terminal device or the network device.

[0043] In the seventh aspect, a communication apparatus is provided. The communication apparatus includes a processor and a memory. The memory is configured to store a computer program. When the processor executes the computer program, the communication apparatus performs the communication method in any of the implementation manners of the first aspect or the third aspect.

[0044] In an example, the communication apparatus in the seventh aspect can further include a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be configured to enable the communication apparatus in the sixth aspect to communicate with other communication apparatuses.

[0045] In the present application, the communication apparatus in the seventh aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus including the terminal device or the network device. The chip (system) or other components or assemblies can be arranged in the terminal device or the network device.

[0046] In an eighth aspect, a communication apparatus is provided, which comprises a processor; the processor is configured to couple with a memory, read a computer program in the memory, and execute the communication method according to any one of the implementation manners of the first aspect to the third aspect after the computer program is read.

[0047] In a possible design, the communication apparatus in the eighth aspect can further comprise a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be configured to enable the communication apparatus in the eighth aspect to communicate with other communication apparatuses.

[0048] In this application, the communication apparatus in the eighth aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus comprising the terminal device or the network device. The chip (system) or other components or assemblies can be arranged in the terminal device or the network device.

[0049] In a ninth aspect, a processor is provided, which is configured to execute the communication method according to any one of the implementation manners of the first aspect to the third aspect.

[0050] In a tenth aspect, a communication system is provided, which comprises at least two of the following: a first device configured to execute the method in the first aspect, a second device configured to execute the method in the second aspect, or a third device configured to execute the method in the third aspect.

[0051] In an eleventh aspect, a computer readable storage medium is provided, which comprises a computer program or instructions; when the computer program or instructions are run on a computer, the computer is caused to execute the communication method according to any one of the implementation manners of the first aspect to the third aspect.

[0052] In a twelfth aspect, a computer program product is provided, which comprises a computer program or instructions; when the computer program or instructions are run on a computer, the computer is caused to execute the communication method according to any one of the implementation manners of the first aspect to the third aspect. BRIEF DESCRIPTION OF DRAWINGS

[0053] FIG. 1 is a schematic diagram of a service-based management architecture;

[0054] FIG. 2 is a schematic diagram of a lifecycle management process of an AI / ML model;

[0055] FIG. 3 is a schematic diagram of a lifecycle deployment architecture of an AI / ML model;

[0056] FIG. 4 is a schematic diagram of a communication system according to an embodiment of the present application;

[0057] FIG. 5 is a schematic diagram of a communication method according to an embodiment of the present application;

[0058] Fig. 6 is a flow diagram of a communication method according to an embodiment of the present application;

[0059] Fig. 7 is a flow diagram of a communication method according to an embodiment of the present application;

[0060] Fig. 8 is a structural diagram of a communication apparatus according to an embodiment of the present application;

[0061] Fig. 9 is a structural diagram of a communication apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0062] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as a wireless network (Wi-Fi) system, a vehicle to everything (V2X) communication system, a device to device (D2D) communication system, a vehicle networking communication system, a 4th generation (4G) mobile communication system such as a long term evolution (LTE) system, a worldwide interoperability for microwave access (WiMAX) communication system, a 5th generation (5G) mobile communication system such as a new radio (NR) system, and a future communication system.

[0063] The technical terms and related technical solutions in the present application will be described below in conjunction with the accompanying drawings.

[0064] 1. Service-oriented management architecture:

[0065] Fig. 1 is a structural diagram of a service-oriented management architecture, which includes a business support system (BSS), a cross domain management function (CD-MnF), a domain management function (Domain-MnF), and an element.

[0066] The business support system is oriented to a communication service, and is used for providing charging, settlement, account, customer service, business, network monitoring, communication service life cycle management, service intent translation and the like.

[0067] The cross-domain management function unit, also referred to as a network management function (NMF), can be a network management system (NMS), a network function management service consumer (NFMS_C) or the like. The cross-domain management function unit provides one or more of the following management functions or management services: network life cycle management, network deployment, network fault management, network performance management, network configuration management, network assurance, network optimization function, and translation of an intent from a communication service provider (Intent-CSP).

[0068] The network referred to in the management functions or management services can include one or more network elements or sub-networks, or a network slice. That is, the network management function unit is a network slice management function (NSMF), a cross-domain management data analysis function (MDAF), a cross-domain self-organization network function (SON Function), or an intent driven management service (MnS).

[0069] Optionally, in some deployment scenarios, the cross-domain management function unit can also provide lifecycle management of sub-networks, deployment of sub-networks, fault management of sub-networks, performance management of sub-networks, configuration management of sub-networks, assurance of sub-networks, optimization function of sub-networks, translation of network intent from communication service producer (Intent-CSP) or network intent from communication service consumer (Intent-CSC) of sub-networks, etc. The sub-networks here are composed of multiple small sub-networks, which can be network slice sub-networks.

[0070] A domain management function unit (Domain-MnF), also called a network management function unit (NMF) or an element management function unit. For example, the domain management function unit can be a network element management entity such as a mobile broadband automation engine (MAE), an element management system (EMS), a network function management service provider (NFMS_P), etc.

[0071] The domain management function unit provides one or more of the following functions or management services: lifecycle management of sub-networks or network elements, deployment of sub-networks or network elements, fault management of sub-networks or network elements, performance management of sub-networks or network elements, assurance of sub-networks or network elements, optimization function of sub-networks or network elements, and translation of intent from network operator (Intent-NOP) of sub-networks or network elements, etc. The sub-networks here include one or more network elements. The sub-networks can also include sub-networks, i.e., one or more sub-networks form a larger sub-network.

[0072] Optionally, the sub-networks here can also be network slice sub-networks. The domain management system can be a network slice sub-network management function unit (NSSMF), a domain management data analysis function unit (Domain MDAF), a domain self-organization network function (SON Function), an intent driven MnS, etc.

[0073] The domain management function unit can be classified in the following ways, including:

[0074] The classification by network type can include a radio access network domain management function (RAN-Domain-MnF), a core network domain management function (CN-Domain-MnF), a transport network domain management function (TN-Domain-MnF), etc. It should be noted that the domain management function unit can also be a domain network management system, which can manage one or more of the access network, the core network, or the transport network.

[0075] The classification by administrative region can include a domain management function unit of a certain region, such as a Shanghai domain management function unit, a Beijing domain management function unit, etc.

[0076] A network element is an entity providing network services, including core network elements, access network elements, and the like. Among them, the core network elements include: access and mobility management function (AMF), session management function (SMF), policy control function (PCF), network data analysis unit (NWDAF), network repository unit (NRF), gateway, and the like. The access network elements include: base stations (such as gNB, eNB), central unit control plane (CUCP), central unit (CU), distribution unit (DU), central unit user plane (CU UP), and the like.

[0077] Among them, the network element can provide one or more of the following management functions or management services: lifecycle management of the network element, deployment of the network element, fault management of the network element, performance management of the network element, assurance of the network element, optimization function of the network element, and translation of the network element intent, and the like.

[0078] It can also be understood that the above-mentioned entities / units / network elements, etc. can also be divided according to the production role, for example, if the management service is provided by the cross-domain management function unit, the cross-domain management function unit is the management service producer (MnS producer), and the business support system is the management service consumer (MnS consumer). If the management service is provided by the domain management function unit, the domain management function unit is the management service producer, and the cross-domain management function unit is the management service consumer. If the management service is provided by the network element, the network element is the management service producer, and the domain management function unit is the management service consumer.

[0079] 2. Artificial intelligence (AI) / machine learning (ML):

[0080] Related applications of AI and ML technologies are increasingly being adopted by a wider range of industries, and AI / ML functions are being used in various areas of 5G mobile communication systems (5GS), including use cases for intelligent optimization of radio access network (RAN) (e.g., mobility load balancing (MLB), mobility robustness optimization (MRO), and energy saving (ES), see 3rd Generation Partnership Project (3GPP) Technical Standard (TS) 38.300, 3GPP Technical Report (TR) 37.817), management data analytics services for network management (e.g., management data analytics function (MDAF), see 3GPP TS 28.104), and network data analytics services for core network (e.g., network data analytics function (NWDAF), see 3GPP TS 23.288).

[0081] As shown in FIG. 2, the lifecycle management process of AI / ML models defined in TS 28.105 includes five main steps: training, testing, simulation, deployment, and inference, as follows:

[0082] Training: Training is the initial stage of the process, in which one or a set of AI / ML models are trained, including initial training and retraining. Training also includes validation of AI / ML models to assess the performance of AI / ML models on training data and validation data.

[0083] Testing: If the validation results are not as expected (e.g., variance is not acceptable), the AI / ML model needs to be retrained.

[0084] Simulation: Running AI / ML models for inference in a simulation environment. The purpose is to evaluate the inference performance of AI / ML models in a simulation environment before applying them to target networks or systems.

[0085] Deployment: Applying AI / ML models to target networks or systems, making trained AI / ML inference available to the process of target AI / ML inference functions.

[0086] Inference: The process of using AI / ML inference through AI / ML inference functions.

[0087] It can be seen that the above life cycle process is developed around the AI / ML model, and the identity of the AI / ML model is defined in TS28.105, which is a unique identifier within a single domain, such as a unique identifier within a producer.

[0088] The TS28.105 also defines the life cycle deployment architecture of the AI / ML model based on the service-oriented architecture (as shown in FIG. 1), taking the training function and the inference function as an example. As shown in (a) of FIG. 3, scenario 1: the training function and the inference function of the AI / ML model can be deployed in the domain management function unit. As shown in (b) of FIG. 3, scenario 2: the training function of the AI / ML model is deployed in the domain management function unit, and the inference function of the AI / ML model is deployed in the base station (such as gNB). As shown in (c) of FIG. 3, scenario 3: the training function and the inference function of the AI / ML model are deployed in the base station, and the domain management function unit manages the training function and the inference function of the AI / ML model. As shown in (d) of FIG. 3, scenario 4: the training function and the inference function of the AI / ML model can be deployed in the NWDAF, and the domain management function unit manages the training function and the inference function of the AI / ML model.

[0089] On this basis, according to the definition of TS28.105, the identity of the AI / ML model is unique within a single domain, and the identities of AI / ML models in different domains may conflict. The cross-domain management function unit may not be able to distinguish the AI / ML model when performing cross-domain model performance monitoring, resulting in management failure. In addition, for scenarios 3 and 4 described above, since the AI / ML model training is implemented in the network element (base station or NWDAF), the network element generates a model identifier when training the AI / ML model, but the identifier generated by the network element may not be recognized by the cross-domain management function unit, and the AI / ML model cannot be effectively managed.

[0090] To solve the above technical problems, the embodiments of the present application propose the following technical solutions. The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0091] The present application will present various aspects, embodiments or features around a system that can include multiple devices, components, modules, etc. It should be understood and appreciated that each system can include additional devices, components, modules, etc., and / or can not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. In addition, combinations of these solutions can also be used.

[0092] In addition, the terms "exemplary," "for example," and the like are used as adjectives to indicate certain examples or instances, but not necessarily as a determination or limitation as to the merits of the elements being described. In the present disclosure, any embodiment or design solution described as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or design solutions.

[0093] First, in the present disclosure, "for indicating" can include for directly indicating and for indirectly indicating. When describing that certain "information" is for indicating A, it can include that the information directly indicates A or indirectly indicates A, and it does not mean that A must be carried in the information.

[0094] When the information indicated by one information is referred to as to-be-indicated information, there are many ways to indicate the to-be-indicated information in the implementation process, for example but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be only indicated in part, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, specified by a protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common part of each information can be identified and uniformly indicated, so as to reduce the indication overhead caused by separately indicating the same information.

[0095] In addition, the specific indication manner can also be various existing indication manners, for example but not limited to, the above-mentioned indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, and will not be described herein. As can be known from the above, for example, when multiple information of the same type needs to be indicated, the indication manners of different information can not be the same. In the implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present disclosure, so that the indication manner involved in the embodiments of the present disclosure should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0096] The to-be-indicated information can be sent as a whole or can be divided into multiple sub-information and sent separately, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited in the present application. The sending period and / or sending occasion of the sub-information can be predefined, for example, predefined according to a protocol, or configured by the transmitting end device to the receiving end device through sending configuration information. The configuration information can include, for example but not limited to, one or a combination of at least two of radio resource control (RRC) signaling, medium access control (MAC) layer signaling and physical layer signaling. The MAC layer signaling can include, for example, MAC control element (CE), and the physical (PHY) layer signaling can include, for example, downlink control information (DCI).

[0097] Second, in the embodiments shown below, the first, second and various numbers are only distinguished for convenience of description, and do not limit the scope of the embodiments of the present application. For example, different indication information is distinguished.

[0098] Third, "preset" or "predefined" or "preconfigured" can be implemented by pre-saving corresponding codes, tables or other information indicating methods in devices (for example, including terminal devices and network devices), and can also be pre-defined in a protocol. The specific implementation method is not limited in the present application. The "saving" can mean saving in one or more memories. The one or more memories can be separately set or integrated in the encoder or decoder, processor or communication device. The one or more memories can be partially separately set and partially integrated in the decoder, processor or communication device. The type of memory can be any form of storage medium, which is not limited in the present application.

[0099] Fourth, the "protocol" involved in the embodiments of the present application can refer to a standard protocol in the communication field, which can include, for example, the LTE protocol (such as technical specification (TS) 36, i.e. the technical specification of TS36 series) of 3GPP, the NR protocol (such as the technical specification of TS38 series) and the related protocol applied to the future communication system, which is not limited in the present application.

[0100] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0101] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0102] To facilitate understanding of the embodiments of the present application, first, a communication system applicable to the embodiments of the present application is described in detail taking the communication system shown in FIG. 4 as an example. Exemplarily, FIG. 4 is a schematic diagram of an architecture of a communication system to which the method provided by the embodiments of the present application is applicable.

[0103] As shown in FIG. 4, the communication system can include a first device, and at least one of a second device and a third device.

[0104] The first device can be a device / network element / entity that manages a domain, which can be referred to as a network management device, such as the cross-domain management function unit described above. The cross-domain management function unit can be responsible for a cross-domain management system, such as managing multiple domains (or network domains / sub-networks). For multiple domains, they can be classified by network type or by administrative region, which can be referred to in the above description and will not be described here.

[0105] The second device can also be a device / network element / entity that manages a domain, which can also be referred to as a network management device, but is different from the first device. For example, the second device can be a domain management function unit described above, which is responsible for managing a specified domain, such as an access network (AN) domain management function unit responsible for managing access network elements, or a core network domain management function unit responsible for managing core network elements, etc., which can be referred to in the above description and will not be described here.

[0106] The third device can be a network element in a service domain, also referred to as a network device.

[0107] The network device can be a device with wireless transceiving function, or also can be a chip or chip system arranged in the device, located in an access network (AN) of a communication system, and used to provide access services for terminals. For example, the network device can be referred to as a radio access network (RAN) device, and specifically can be a future mobile communication system, or in the future mobile communication system, the network device can also have other naming manners, which are all covered in the protection scope of the embodiments of the present application, and the present application does not make any limitation on this. Alternatively, the network device can also include a gNB in a 5G, such as a new radio (NR) system, or one or a group (including multiple antenna panels) of antenna panels of a base station in the 5G, or can also be a network node constituting a gNB, a transmission and reception point (TRP or transmission point, TP), or a transmission measurement function (TMF), such as a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), an RSU with base station function, or a wired access gateway, or a core network element of the 5G, and the like. Alternatively, the network device can also include an access point (AP) in a WiFi system, a wireless relay node, a wireless backhaul node, various forms of macro base stations, micro base stations (also referred to as small stations), relay stations, access points, wearable devices, vehicle-mounted devices, and the like.

[0108] The CU and the DU can be separately arranged or can also be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH). It can be understood that the network device can be a CU node, or a DU node, or a device including a CU node and a DU node. In addition, the CU can be divided into a network device in an access network RAN, or the CU can be divided into a network device in a core network CN, which is not limited herein. In different systems, the CU (or CU-CP and CU-UP), the DU, or the RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, the CU-CP, the CU-UP, the DU, and the RU are taken as examples for description in this application. Any one of the CU (or the CU-CP, the CU-UP), the DU, and the RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module. In the embodiments of this application, the form of the network device is not limited, and the device for implementing the function of the network device can be the network device; or can be a device capable of supporting the network device to implement the function, such as a chip system. The device can be installed in the network device or used in combination with the network device.

[0109] Alternatively, the network device can also be a network element in a core network, such as a network data analysis function (NWDAF), or a function / entity on the network data analysis function, such as a model training logic function (MTLF), or other types of network elements, which are not limited in particular.

[0110] In the communication system, the first device can determine a first identifier for a specified AI / ML model, such as the first AI / ML model, which uniquely identifies the first AI / ML model in the cross-domain management system, and send the second device / third device. Alternatively, the first device can also determine a list of identifiers and send them to the second device / third device. Any identifier in the list of identifiers can uniquely identify a corresponding AI / ML model in the cross-domain management system, so that the second device / third device can select an identifier from the list of identifiers to uniquely identify an AI / ML model. In this way, the identification conflict of the AI / ML model in the cross-domain management system can be avoided.

[0111] Alternatively, the second device / third device can also determine a second identifier for the first AI / ML model to uniquely identify the first AI / ML model in the cross-domain management system, and send the second identifier to the first device. In this way, the identification conflict of the AI / ML model in the cross-domain management system can also be avoided.

[0112] It can be understood that the AI / ML model described in the embodiments of the present application can also be referred to as an ML model or an AI model.

[0113] The interaction process between the devices in the communication system will be described in detail below with reference to FIGS. 5-7 through method embodiments.

[0114] The communication method provided by the embodiments of the present application can be applied to the interaction between the first device and the second device, and the interaction between the second device and the third device in the communication system described above. The communication method will be described in detail below.

[0115] FIG. 5 is a flowchart of the communication method, please refer to FIG. 5. The communication method is applied to the interaction between the first device and the second device. The specific process is as follows:

[0116] S501, the first device determines a first identifier and / or a list of identifiers.

[0117] The first identifier can be used to uniquely identify a first AI / ML model in the cross-domain management system. For example, the first identifier can be an integer value in an integer range, such as any integer in the range of 0-500, or a string or bit string, or any other possible implementation. In the identification of AI / ML models in the cross-domain management system, the first identifier can be unique, and there is no other AI / ML model identifier that is the same as the first identifier to avoid conflict.

[0118] The cross-domain management system can be a system managed by the first device (such as a cross-domain management function unit), such as multiple domains, or alternatively, multiple network domains / multiple subnetworks, etc., without limitation. The details can be referred to the above related description, which will not be repeated here.

[0119] The first AI / ML model can be any possible type, or an AI / ML model for any possible function, without limitation. The first AI / ML model can perform training on the second device, or can also perform training on a third device.

[0120] The identification list can include at least two identifications. Any identification in the identification list can be used to uniquely identify a corresponding AI / ML model in the cross-domain management system, which can be understood similarly to the first identification, and will not be repeated here. The first identification can be an identification in the identification list, or can be independent of the identification list, without limitation. The identifications in the identification list are usually not used to identify AI / ML models, or have not been assigned to AI / ML models, or the identification list includes a part of the identifications that have been used to identify AI / ML models, and another part of the identifications have not been used to identify AI / ML models. In this case, the identification list can mark the identifications that have been used to identify AI / ML models, to distinguish which of the remaining identifications are available. For example, an exemplary implementation of the identification list is: identification #1-mark 1, identification #2-mark 1, identification #3-mark 0, identification #4-mark 0, where the mark can be a 1-bit (bit) information element, mark 1 means that the bit is 1, indicating that it has been used to identify an AI / ML model, and mark 0 means that the bit is 0, indicating that it has not been used to identify an AI / ML model. Therefore, it can be known that identification #1 and identification #2 have been used to identify AI / ML models, and the remaining identifications #3 and identification #4 have not been used to identify AI / ML models.

[0121] It can be understood that the first device determines the first identification, or determines the identification list, or both, which is not limited by embodiments of the present application, such as pre-configuration, or the first device flexibly selects according to actual conditions or actual needs.

[0122] S502, the first device sends the first identification and / or the identification list to the second device.

[0123] The first identification and / or the identification list described above can be carried in any possible signaling / message / information element, or the first identification and / or the identification list can be transmitted by a newly defined message, without limitation.

[0124] For example, the first device can carry the first identification (mLModelGlobleID) of the first AI / ML model in the operation of requesting the second device to create or pre-configure the object instance of the first AI / ML model, such as randomly selecting an integer value from the range of integers that has not been selected before, or randomly generating a string, or selecting an identification from the identification list. Alternatively, the first device carries the identification list (mLModelGlobleIDList) in the request operation, such as the first device can construct the list identification according to the identification that has not been used to identify the AI / ML model; or the identification list can be pre-configured or pre-constructed, and the first device can maintain it, such as adding new identification, deleting / releasing existing identification, or updating the label of the identification, such as whether the identification has been used to identify the AI / ML model, and in this case, the first device can obtain the latest identification list. After receiving the request operation, the first device creates the object instance of the first AI / ML model.

[0125] Optionally, the first device can carry the first identification or the identification list of the first AI / ML model in the operation of requesting the second device to create the object instance of the AI / ML model training.

[0126] For the second device, whether the first AI / ML model is trained on the second device or trained on the third device, the processing manner of the second device is different, which will be introduced respectively.

[0127] Case 1: The first AI / ML model is trained on the second device.

[0128] The second device can configure the identification for the first AI / ML model.

[0129] If the second device receives the first identification from the first device, the second device can configure the first identification for the first AI / ML model, such as configuring the first identification for the object instance of the first AI / ML model. Alternatively, if the second device receives the identification list from the first device, the second device can determine the second identification according to the identification list, and the second identification is an identification in the identification list. For example, in the case that all the identifications in the identification list have not been used to identify the AI / ML model, the second device can randomly select an identification, i.e., the second identification. Alternatively, in the case that some of the identifications in the identification list have been marked to identify the AI / ML model, the second device can randomly select an identification from the identifications that have not been marked, i.e., the identifications that have not been used to identify the AI / ML model, i.e., the second identification. The second device can configure the second identification for the first AI / ML model, such as configuring the second identification for the object instance of the first AI / ML model.

[0130] It should be understood that if the second device receives both the first identifier and the identifier list, the second device can select one of them to configure the identifier for the first AI / ML model by itself, without limitation.

[0131] Alternatively, the second device can also send a second identifier to the first device, and the first device can receive the second identifier from the second device. In this case, the first device can determine that the identifier selected by the second device for the first AI / ML model is the second identifier according to the sending of the identifier list and the receiving of the second identifier, so that the first device can also configure the second identifier for the first AI / ML model, such as configuring the second identifier for the object instance of the first AI / ML model, to align with the second device, so as to be able to use the second identifier to manage the first AI / ML model subsequently.

[0132] It can be seen that for the case that the first AI / ML model performs training on the second device, the first device can assign the first identifier to the second device for use, without the second device determining the identifier by itself, so as to reduce the overhead of the second device, or the second device selects an identifier (such as the second identifier) from the identifier list according to its own needs to identify the AI / ML model, which has better flexibility and better freedom of assigning the identifier list than the way that the first device determines the first identifier.

[0133] Case 2: The first AI / ML model performs training on the third device.

[0134] The second device can forward the received first identifier and / or identifier list to the third device. For example, the first device can send the identifier of the third device to the second device, to indicate that the third device is a device suitable for training the first AI / ML model, or that the first AI / ML model performs training on the third device, or that the first identifier and / or identifier list are suitable for the model trained by the third device. The identifier of the third device can be carried in the same message as the first identifier and / or identifier list, or can be transmitted separately, without limitation. The second device can receive the identifier of the third device from the first device, and send the first identifier and / or identifier list to the third device according to the identifier of the third device.

[0135] Therefore, the third device can receive the first identifier and / or identifier list from the second device. If the third device receives the first identifier from the first device, the third device can configure the first identifier for the first AI / ML model, or if the third device receives the identifier list from the second device, the third device can determine the second identifier according to the identifier list, and configure the second identifier for the first AI / ML model, the specific implementation principle is similar to that of the second device in the above "case 1", which can be understood by reference, and will not be described here.

[0136] It can be understood that the second identifier selected by the third device and the identifier selected by the second device, i.e., the second identifier, can be the same identifier, or can also be different identifiers. For the convenience of understanding, the embodiments of the present application are introduced along with the description of the second identifier, without being limited as the same.

[0137] Alternatively, the third device can also send the second identifier to the second device, and the second device can receive the second identifier from the third device. In this case, the second device can also determine that the identifier selected by the second device for the first AI / ML model is the second identifier according to the sending identifier list and receiving the second identifier, so that the first device can also configure the second identifier for the first AI / ML model. Similarly, the second device can also send the second identifier to the first device, and the first device can receive the second identifier from the first device. The specific implementation principle can be referred to the related introduction in the above "case 1", which will not be repeated here.

[0138] Similarly to the above case 1, for the case that the first AI / ML model performs training on the third device, the first device can assign the first identifier to the third device for use, without the third device determining the identifier by itself, so as to reduce the overhead of the third device, or the third device selects an identifier from the identifier list according to its own needs to identify the AI / ML model. Compared with the way of determining the first identifier by the first device, the degree of freedom and flexibility of assigning the identifier list is better.

[0139] It should also be understood that the above cases 1 and 2 are only an example. For example, for the case that the first AI / ML model performs training on the third device, the second device can also determine the second identifier and send it to the third device.

[0140] Alternatively, in combination with the above S501-S502, the method can further include that the first device can also send a subnet identifier to the second device. The subnet identifier can indicate a subnet / subnetwork applicable to the second device, which can also be understood as a domain / network domain served by the second device. The above first AI / ML model can be used in the subnet indicated by the subnet identifier, so that the second device can deploy the trained first AI / ML model to the corresponding subnet to provide services, so as to realize targeted model deployment. In addition, the subnet identifier can be carried in the same message as the above first identifier and / or identifier list, or can also be transmitted separately, which is not limited.

[0141] In summary, the first device can determine the first identifier for a specified AI / ML model, such as the first AI / ML model, to uniquely identify the first AI / ML model in the cross-domain management system. Alternatively, the first device can also determine a list of identifiers to select an identifier from the list of identifiers to uniquely identify an AI / ML model in the cross-domain management system, thereby avoiding identifier conflicts of AI / ML models in the cross-domain management system.

[0142] FIG. 6 is a flowchart of the communication method, which is applicable to the interaction between the first device and the second device. The specific process is as follows:

[0143] S601, the second device determines the second identifier.

[0144] The second identifier can be used to uniquely identify a first AI / ML model in the cross-domain management system, which can be understood with reference to the first identifier described above, and will not be described here.

[0145] In one possible implementation, the second device can receive the list of identifiers from the first device, and determine the second identifier according to the list of identifiers. In this case, the second identifier is an identifier in the list of identifiers, and the list of identifiers includes at least two identifiers. Any identifier in the list of identifiers is used to uniquely identify a corresponding AI / ML model in the cross-domain management system. The specific implementation principle can be referred to the related description of FIG. 5 above, and will not be described here.

[0146] In another possible implementation, the second device can construct the second identifier by itself. It should be noted that in this implementation, it can be understood that the model training is performed in the second device, and the model inference is also performed in the second device. For example, the second device determines the second identifier according to at least two of the following: the identifier of the first AI / ML model, the identifier determined by the second device, the identifier of the subnetwork associated with the second device, the identifier of the second device, and the identifier of the first AI / ML model object. That is, multiple parameters are introduced to construct the second identifier, which can guarantee its uniqueness and avoid identifier conflicts.

[0147] The identification of the first AI / ML model can be, for example, an ML model ID (mLModelID), which is used to uniquely identify the first AI / ML model in the domain / network domain / subnet / subnetwork where the second device is located, and is also an identification that the first device can recognize. The identification determined by the second device can be an identification autonomously assigned by the second device, such as a random number, a string, etc., which can be generated randomly or according to a specific rule / algorithm, and the specific implementation is not limited. It should be noted that the identification determined by the second device can also be the identification of the first AI / ML model described above. The subnet identification associated with the second device can be the identification of the domain / network domain / subnet / subnetwork where the second device is located. The identification of the second device can be the identification of the manufacturer where the second device is located, the identification of the management device of the manufacturer, etc. The identification of the first AI / ML model object can be generated when the second device creates the first AI / ML model object, such as a distinguish name (DN).

[0148] Specifically, the second identification can be obtained by adding the above-mentioned identifications, such as the identification of the first AI / ML model + the identification determined by the second device, or the identification of the first AI / ML model + the subnet identification associated with the second device, or the identification determined by the second device + the subnet identification associated with the second device, or the identification of the first AI / ML model + the identification determined by the second device + the subnet identification associated with the second device, or the identification of the first AI / ML model + the identification of the first AI / ML model object, or the identification of the first AI / ML model + the identification of the first AI / ML model object + the subnet identification associated with the second device. Alternatively, the second device can also hash the above-mentioned addition results, or obtain the second identification by using any other possible algorithm, and the specific implementation mode is not limited.

[0149] In another possible implementation, the second device can further obtain an identity from the third device, denoted as a third identity. It is to be noted that in this implementation, it can be understood that the model training is performed in the third device, and the model inference is also performed in the third device. The third identity can include one of the following identities: an identity determined by the third device, an identity of the third device, or an identity of a network in which the third device is located. The identity determined by the third device can be an identity autonomously allocated by the third device, such as a random number, a string, or the like generated randomly or according to a specific rule / algorithm, and the specific implementation is not limited. It is to be noted that the identity determined by the third device can also be an identity allocated by the third device for the trained AI / ML model, such as the first AI / ML model. For example, the third device is a core network element such as a NWDAF or an MLTF, and the identity allocated by the core network element for the trained first AI / ML model can be an ML model identifier (ML Model identifier). The specific definition of the ML Model identifier can refer to the definition in 3GPP TS 23.288, or the third device is an access network device, and the identity allocated by the access network device for the trained first AI / ML model can be an ML model identifier, such as a random number, a string, or the like generated randomly or according to a specific rule / algorithm, and the specific implementation is not limited. The identity of the third device can be an identity of an access network device, an identity of a core network entity, or the like, such as a gNB ID, an MTLF ID, a NWDAF ID, or an identity of a vendor in which the third device is located, an identity of a management device of the vendor, or the like. The identity of the network in which the third device is located can be an identity of an operator network, or in other words, an identity of a mobile communication network, such as an identity of a public land mobile network (PLMN) in which the third device is located (PLMN ID), and the third device is an access network device.

[0150] The second device can determine the second identity according to the identity obtained from the third device, i.e., the third identity. For example, the second device can combine the third identity with at least one of the following to obtain the second identity: an identity of the first AI / ML model, an identity determined by the second device, a subnet identity associated with the second device, an identity of the second device, or an identity of the first AI / ML model object, and the specific implementation can refer to the related description in the above another possible implementation, and will not be described in detail. For example, the second identity can be: the identity of the first AI / ML model + the third identity, or the identity of the first AI / ML model object + the third identity, or the identity of the first AI / ML model object + the subnet identity associated with the second device + the third identity, or the like, or there can be other combination manners, which can be understood with reference, and will not be described in detail. Alternatively, the second device can still determine the second identity in the manner in the above another possible implementation, and associate the second identity with the third identity.

[0151] Optionally, the second device can also directly send the third identity as the second identity.

[0152] S602, the second device sends the second identity to the first device.

[0153] If the second identity is an identity selected from the identity list allocated by the first device, the identity therein is also an identity that the first device can recognize, therefore, for this case, the second device can directly send the second identity to the first device, such as any possible message / signaling / information element carrying the second identity, without limitation of specific implementation.

[0154] It should be noted that the first device can manage the AI / ML model according to the received second identity, for example, manage and control the training of the AI / ML model, the testing of the AI / ML model, the deployment of the AI / ML model, the inference of the AI / ML model, and the performance monitoring of the AI / ML model in the training process, the testing process, and the inference process. For example, the first device can trigger the deployment of the AI / ML model according to the second identity, and start the inference function of the AI / ML model.

[0155] If the second identity is an identity constructed by the second device, generally, the first device cannot directly recognize the second identity, therefore, the second device can first associate the second identity with the identity of the first AI / ML model, such as configuring a certain information element to contain the second identity and the identity of the first AI / ML model to represent the association therebetween. In this way, the second device can send the second identity and the identity of the first AI / ML model associated with the second identity to the first device, such as any possible message / signaling / information element carrying the second identity and the associated identity of the first AI / ML model, without limitation of specific implementation. In this way, the first device can determine that the second identity is used to identify the first AI / ML model according to the association of the second identity to the identity of the first AI / ML model, thereby avoiding the failure of AI / ML model management due to the inability of the first device to recognize the second identity.

[0156] If the first AI / ML model performs training on the second device, the second device can configure the second identity for the first AI / ML model, and the specific implementation principle can refer to the above-mentioned related receiving in “Case 1”, which will not be repeated. If the first AI / ML model performs training on the third device, the second device can also send the second identity to the third device, such as receiving the identity of the third device from the first device, and sending the second identity to the third device according to the identity of the third device, so that the third device can configure the second identity for the first AI / ML model. The specific implementation principle can also refer to the above-mentioned related receiving in “Case 2”, which will not be repeated.

[0157] Optionally, in combination with S601-S602, the method can further include: the second device receives a subnet identifier from the first device, the first AI / ML model is used for a subnet indicated by the subnet identifier, so that the second device can deploy the trained first AI / ML model into the corresponding subnet to provide services, so as to realize targeted model deployment. For details, refer to the related description of FIG. 5 above, which will not be repeated here.

[0158] In summary, the second device can determine a second identifier for a first AI / ML model, which can avoid identifier conflict of the AI / ML model in the cross-domain management system. The second device reports the second identifier to the first device, which can also facilitate the first device to manage the AI / ML model according to the second identifier.

[0159] FIG. 7 is a flowchart of the communication method, which is applicable to the interaction between the second device and the third device. The specific process is as follows:

[0160] S701, the third device determines the second identifier.

[0161] The second identifier is used to uniquely identify a first AI / ML model in the cross-domain management system.

[0162] In one possible implementation, the third device can receive an identifier list from the second device, and determine the second identifier according to the identifier list. In this case, the second identifier is an identifier in the identifier list, and the identifier list includes at least two identifiers. Any identifier in the identifier list is used to uniquely identify a corresponding AI / ML model in the cross-domain management system. For details, refer to the related description of FIG. 5 above, which will not be repeated here.

[0163] In another possible implementation, the third device can determine the second identifier according to at least two of the following: an identifier of the first AI / ML model, an identifier determined by the third device, or an identifier of the third device, or an identifier of a network where the third device is located. That is, multiple parameters are introduced to construct the second identifier, which can guarantee its uniqueness and avoid identifier conflict.

[0164] The identification of the first AI / ML model can refer to the relevant description in FIG. 6 described above, and will not be repeated here. The identification determined by the third device can be an identification autonomously allocated by the third device, such as a random number, a string, etc. generated randomly or according to a specific rule / algorithm, which can be used by the third device as the identification of the AI / ML model. For example, the third device is a core network element such as NWDAF or MLTF, and the identification determined by the third device can be an ML model ID (ML Model identifier). The specific definition of the ML Model identifier can refer to the definition in 3GPP TS23.288. Alternatively, the third device is an access network device, and the identification determined by the third device can be an ML model ID, such as a random number, a string, etc. generated randomly or according to a specific rule / algorithm, and the specific implementation is not limited. The identification of the third device can be an identification of an access network device, an identification of a core network entity, etc., such as a gNB ID, an MTLF ID, a NWDAF ID, or an identification of a vendor where the third device is located, an identification of a management device of a vendor, etc. The identification of the network where the third device is located can be an operator network, or in other words, an indication of a mobile communication network, such as an identification (PLMN ID) of a public land mobile (communication) network (PLMN) where the access network device is located.

[0165] Specifically, the second identification can be obtained by adding the above-mentioned identifications, for example, the third device is an access network device, and the second identification can be the identification of the first AI / ML model + the identification determined by the third device, or the identification of the first AI / ML model + the identification of the network where the third device is located, or the identification determined by the third device + the identification of the network where the third device is located, or the identification of the first AI / ML model + the identification determined by the third device + the identification of the network where the third device is located; or the third device can also hash the result after the above-mentioned addition, or obtain the second identification by any other possible algorithm, and the specific implementation manner is not limited. Alternatively, the third device is a data analysis function network element, or more specifically, an MTLF, and the second identification can also be an identification pre-configured by the MTLF.

[0166] The first AI / ML model performs training on the third device, and the third device can also configure the second identification for the first AI / ML model. The specific implementation principle can refer to the relevant reception in the above-mentioned "case 2", and will not be repeated here.

[0167] S702, the third device sends the second identification to the second device.

[0168] The second identifier can carry any possible signaling / message / information element in which the third device interacts with the second device, and the specific implementation is not limited. The second device can return the received second identifier to the first device, and the specific implementation principle can refer to the description of S601 above, which will not be repeated here.

[0169] It can be understood that in the cross-domain management system of the embodiments of the present application, the first AI / ML model can have multiple identifiers, such as the first identifier or the second identifier of the embodiments of the present application, and the ML model ID, or it can also have only one identifier, such as the first identifier or the second identifier of the embodiments of the present application, in which case the ML model ID can be replaced or said to be modified as the first identifier or the second identifier.

[0170] In summary, the third device can determine the second identifier as a unique identifier for a first AI / ML model, which can avoid identifier conflicts of AI / ML models in the cross-domain management system. The third device reports the second identifier to the first device through the second device, which can also facilitate the first device to manage the AI / ML model according to the second identifier.

[0171] FIG. 8 is a structural schematic diagram of a communication apparatus according to an embodiment of the present application. As shown in FIG. 8, the communication apparatus 800 includes a transceiver module 802 and a processing module 801. For the convenience of description, FIG. 8 only shows the main components of the communication apparatus.

[0172] The communication apparatus 800 can be applied to the communication method of FIGS. 5-7, to realize the corresponding functions. For example, the transceiver module 802 can be used to realize the transceiving function in the communication method of FIGS. 5-7, and the processing module 801 can be used to realize other functions in the communication method of FIGS. 5-7, except for the transceiving function.

[0173] Optionally, the transceiver module 802 can include a sending module (not shown in FIG. 8) and a receiving module (not shown in FIG. 8). The sending module is used to realize the sending function of the communication apparatus 800, and the receiving module is used to realize the receiving function of the communication apparatus 800.

[0174] Optionally, the communication apparatus 800 can further include a storage module (not shown in FIG. 8), which stores programs or instructions. When the processing module 801 executes the programs or instructions, the communication apparatus 800 can execute the functions in the method shown in FIGS. 5-7.

[0175] It can be understood that the communication apparatus 800 can be a network device, or a chip (system) or other components or assemblies that can be arranged in a network device, or a device containing a network device, and the present application does not limit this.

[0176] In addition, the technical effects of the communication apparatus 800 can refer to the technical effects of the communication method described above, which will not be repeated here.

[0177] FIG. 9 is a schematic diagram of a communication apparatus according to an embodiment of the present application. The communication apparatus can be a terminal, a chip (system) or other components or assemblies that can be arranged in the terminal. As shown in FIG. 9, the communication apparatus 900 can include a processor 901. Optionally, the communication apparatus 900 can also include a memory 902 and / or a transceiver 903. The processor 901 is coupled to the memory 902 and the transceiver 903, for example, through a communication bus.

[0178] The various components of the communication apparatus 900 will be described below in detail with reference to FIG. 9.

[0179] The processor 901 is the control center of the communication apparatus 900, which can be one processor or a plurality of processing elements. For example, the processor 901 can be one or more central processing units (CPUs), application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement one or more embodiments of the present application, such as one or more microprocessors (digital signal processors (DSPs)), or one or more field programmable gate arrays (FPGAs).

[0180] Optionally, the processor 901 can perform various functions of the communication apparatus 900 by running or executing software programs stored in the memory 902 and calling data stored in the memory 902, such as the communication method shown in FIGS. 5-7.

[0181] In a specific implementation, as an embodiment, the processor 901 can include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 9.

[0182] In a specific implementation, as an embodiment, the communication apparatus 900 can also include a plurality of processors, such as the processor 901 and the processor 904 shown in FIG. 9. Each of these processors can be a single-CPU or a multi-CPU. The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0183] The memory 902 is configured to store software programs for implementing the solutions of the present application, and the processor 901 is configured to control the execution of the software programs. The specific implementation manners can refer to the methods in the above embodiments, and will not be described here.

[0184] Optionally, the memory 902 can 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, and can also be 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, a laser disc, an optical disc, a digital versatile disc, a 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 codes in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory 902 can be integrated with the processor 901 or exist independently, and is coupled with the processor 901 through an interface circuit (not shown in FIG. 9) of the communication device 900, and the embodiments of the present application are not limited in this regard.

[0185] The transceiver 903 is configured to communicate with other communication devices. For example, the communication device 900 is a terminal, and the transceiver 903 can be configured to communicate with a network device or another terminal device. For another example, the communication device 900 is a network device, and the transceiver 903 can be configured to communicate with a terminal or another network device.

[0186] Optionally, the transceiver 903 can include a receiver and a transmitter (not shown separately in FIG. 9). The receiver is configured to implement the receiving function, and the transmitter is configured to implement the transmitting function.

[0187] Optionally, the transceiver 903 can be integrated with the processor 901 or exist independently, and is coupled with the processor 901 through an interface circuit (not shown in FIG. 9) of the communication device 900, and the embodiments of the present application are not limited in this regard.

[0188] It can be understood that the structure of the communication device 900 shown in FIG. 9 does not constitute a limitation on the communication device, and the actual communication device can include more or fewer components than those shown, or combine certain components, or different component arrangements.

[0189] In addition, the technical effects of the communication apparatus 900 can refer to the technical effects of the methods described in the above method embodiments, which will not be repeated here.

[0190] It should be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and the processor can 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 gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0191] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0192] The above-described embodiments can be implemented in whole or in part by software, hardware (such as a circuit), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented 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 programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred 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 through a wired (such as infrared, wireless, microwave, etc.) manner. 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, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0193] The embodiments of the present application also provide a computer-readable storage medium storing a computer program, which can make a computer execute the above-described communication method when the computer program is executed by the computer. In other words, the computer program includes instructions for implementing the above-described communication.

[0194] The embodiments of the present application also provide a computer program product, which includes computer program code, and when the computer program code is executed on a computer, the computer can execute the above-described communication method.

[0195] The embodiments of the present application also provide a communication system, which includes a first device and a second device for executing the above-described communication method.

[0196] The embodiments of the present application also provide a chip, which can include a processor for executing the above-described communication method. Optionally, the chip further includes a memory coupled to the processor, and the memory stores a program for executing the above-described communication method.

[0197] It should be understood that the term "and / or" in this document is merely used to describe associated relationship, and it can mean three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " in this document generally means that the associated objects before and after the " / " are in an "or" relationship, but can also mean an "and / or" relationship, which can be understood according to the context before and after.

[0198] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0199] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0200] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0201] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-mentioned system, device and unit can be referred to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0202] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be realized by other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0203] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0204] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0205] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0206] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that, Applied to a first device, the method includes: Determine a first identifier and / or an identifier list, wherein the first identifier is used to uniquely identify a first AI / ML model in the cross-domain management system, and any identifier in the identifier list is used to uniquely identify a corresponding AI / ML model in the cross-domain management system, and the identifier list includes at least two identifiers; Send the first identifier and / or the list of identifiers to the second device.

2. The method according to claim 1, characterized in that, The first AI / ML model is trained on the second device.

3. The method according to claim 1, characterized in that, The first AI / ML model is trained on a third device.

4. The method according to claim 3, characterized in that, The method further includes; The identifier of the third device is sent to the second device, wherein the third device is an access network device or a network data analysis network element.

5. The method according to any one of claims 1-4, characterized in that, The method further includes; Send a subnet identifier to the second device, wherein the first AI / ML model is used for the subnet indicated by the subnet identifier.

6. The method according to any one of claims 1-5, characterized in that, When sending the identifier list to the second device, the method further includes: Receive a second identifier returned by the second device, wherein the second identifier is an identifier in the identifier list.

7. The method according to any one of claims 1-6, characterized in that, The first device is a cross-domain management function unit, and the second device is a domain management function unit.

8. A communication method, characterized in that, Applied to a second device, the method includes: A second identifier is determined, which is used to uniquely identify a first AI / ML model in the cross-domain management system; Send the second identifier to the first device, wherein the second device and the first device are devices in the management domain.

9. The method according to claim 8, characterized in that, Determining the second identifier includes: Receive an identifier list from the first device, wherein any identifier in the identifier list is used to uniquely identify a corresponding AI / ML model in the cross-domain management system, and the identifier list includes at least two identifiers; The second identifier is determined based on the identifier list, wherein the second identifier is an identifier in the identifier list.

10. The method according to claim 8, characterized in that, Determining the second identifier includes: The second identifier is determined based on at least two of the following: the identifier of the first AI / ML model, the identifier determined by the second device, and the identifier of the subnet associated with the second device.

11. The method according to claim 10, characterized in that, Sending the second identifier to the first device includes: Send the second identifier and the identifier of the first AI / ML model associated with the second identifier to the first device.

12. The method according to any one of claims 8-11, characterized in that, The first AI / ML model is trained on the second device.

13. The method according to any one of claims 8-11, characterized in that, The method further includes: The second identifier is sent to a third device, on which the first AI / ML model is trained, and the third device is a device in the business domain.

14. The method according to claim 13, characterized in that, The method further includes: Receive the identifier of the third device from the first device; Sending the second identifier to the third device includes: The second identifier is sent to the third device based on the identifier of the third device.

15. The method according to any one of claims 8-14, characterized in that, The method further includes; Receive a subnet identifier from the first device, and use the first AI / ML model for the subnet indicated by the subnet identifier.

16. The method according to any one of claims 8-15, characterized in that, The first device is a cross-domain management function unit, and the second device is a domain management function unit.

17. A communication method, characterized in that, Applied to a third device, the method includes: A second identifier is determined, which is used to uniquely identify a first AI / ML model in the cross-domain management system; The second identifier is sent to a second device, which is a device in the management domain, and the third device is a device in the service domain.

18. The method according to claim 17, characterized in that, Determining the second identifier includes: Receive an identifier list from the second device, wherein any identifier in the identifier list is used to uniquely identify a corresponding AI / ML model in the cross-domain management system, and the identifier list includes at least two identifiers; The second identifier is determined based on the identifier list, wherein the second identifier is an identifier in the identifier list.

19. The method according to claim 17, characterized in that, Determining the second identifier includes: The second identifier is determined based on at least two of the following: the identifier of the first AI / ML model, the identifier determined by the third device, and the identifier of the network where the third device is located.

20. The method according to any one of claims 17-19, characterized in that, The first AI / ML model is trained on the third device.

21. The method according to any one of claims 17-20, characterized in that, The second device is a domain management function unit, and the third device is an access network device or a network analysis network element.

22. A communication device, characterized in that, The communication device is used to perform the method as described in any one of claims 1-21.

23. A communication device, characterized in that, include: Processor and memory; The memory is used to store computer instructions, which, when executed by the processor, cause the communication device to perform the method as described in any one of claims 1-21.

24. A communication device, characterized in that, include: Processor and interface circuits; among which, The interface circuit is used to receive code instructions and transmit them to the processor; The processor is used to run the code instructions to perform the method as described in any one of claims 1-21.

25. A communication device, characterized in that, The communication device includes a processor and a transceiver, the transceiver being used for information exchange between the communication device and other communication devices, and the processor executing program instructions to perform the method as described in any one of claims 1-21.

26. The communication device according to any one of claims 22-25, characterized in that, The communication device is a chip.

27. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program or instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-21.

28. A computer program product, characterized in that, The computer program product includes: a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1-21.

Images