Machine model reasoning capability management and control method and device

Abstract

The present application relates to the technical field of wireless communications, and provides a machine model reasoning capability management and control method and device, for use in managing and controlling the reasoning capability of machine models. In the method, a second communication device sends first information to a first communication device, the first information comprising an AI / ML capability corresponding to AI / ML reasoning; and the second communication device receives a reasoning result of the AI / ML reasoning from the first communication device. According to the solution, on the basis of the first information, the second communication device can indicate to the first communication device the AI / ML capability corresponding to the AI / ML reasoning, thereby realizing management and control of the AI / ML capability, and enabling the first communication device to execute the AI / ML reasoning of the AI / ML capability on the basis of the first information.

Description

A method and device for controlling machine model reasoning capabilities

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on January 16, 2024, with application number 202410068001.3 and application name “A method and device for controlling machine model reasoning capabilities”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of wireless communication technology, and in particular to a method and device for managing and controlling machine model reasoning capabilities. Background Art

[0004] Currently, the Third Generation Partnership Project (3 rd The Third Generation Partnership Project (3GPP) defines the use of artificial intelligence / machine learning (AI / ML) technology to achieve radio access network (RAN) intelligence, specifically to support energy saving (ES), mobility load balancing (MLB), and mobility robustness optimization (MRO). The standard discussion also defines how to support and manage the reasoning type scenarios of RAN intelligence on the network management. The specific management information includes switch management and policy management of the reasoning type of RAN intelligence, that is, the cross-domain management node can set the switch for the use case and configure the execution policy. The standard also discusses how to support the reasoning type scenarios of management data analytics (MDA) of AI / ML.

[0005] However, the management of RAN intelligence's reasoning types in the standard only supports the management of switches and execution policies, and does not propose the management of RAN intelligence's AI / ML capabilities. Summary of the Invention

[0006] The present application provides a method and device for managing the reasoning capability of a machine model, which are used to manage the reasoning capability of a machine model.

[0007] In a first aspect, a method for managing and controlling machine model reasoning capabilities is provided. This method can be performed by a second communication device. The second communication device can be a second management device, or a chip / chip system. In this method, the second communication device sends first information to a first communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. The second communication device then receives the AI / ML reasoning results from the first communication device.

[0008] Based on the above scheme, the second communication device can indicate the AI / ML capability corresponding to the AI / ML reasoning to the first communication device through the first information, thereby realizing the management and control of the AI / ML capability and enabling the first communication device to perform AI / ML reasoning of the AI / ML capability according to the first information.

[0009] In one possible implementation, the first information is used to request the first communication device to perform AI / ML reasoning of the AI / ML capability. Based on this solution, the first information can request the execution of AI / ML reasoning of the AI / ML capability, that is, the second communication device can control the AI / ML capability based on the first information.

[0010] In one possible implementation, the second communication device receives AI / ML capability information supported by the first communication device. The AI / ML capability indicated by the AI / ML capability information includes AI / ML capability corresponding to AI / ML reasoning.

[0011] Based on the above solution, the second communication device can obtain the AI / ML capability information supported by the first communication device, so as to manage and control the AI / ML capabilities supported by the first communication device.

[0012] In one possible implementation, the second communication device sends second information to the first communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0013] Based on the above solution, the second communication device can request the first communication device to send supported AI / ML capability information, thereby obtaining the AI / ML capabilities supported by the first communication device.

[0014] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supporting one or more of management data analysis function, mobility optimization function, network energy saving function or load balancing function.

[0015] Based on the above scheme, the second communication device can instruct the first communication device to send AI / ML capability information supported by reasoning types such as management data analysis function, mobility optimization function, network energy saving function or load balancing function through the second information, thereby realizing the management and control of reasoning type instructions such as management data analysis function, mobility optimization function, network energy saving function or load balancing function from AI / ML capability information.

[0016] In one possible implementation, the second communication device sends an inference type of AI / ML capability, where the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0017] Based on the above solution, the second communication device can send the first information to the first communication device to indicate which reasoning types the AI / ML capabilities correspond to, thereby achieving management and control of AI / ML capabilities of specific reasoning types.

[0018] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0019] In a possible implementation manner, the second communication device receives one or more of the inference state and the inference time.

[0020] Based on the above scheme, the first communication device can also send one or more items of the inference status or inference time to the second communication device, so that the second communication device can understand one or more items of the inference status or inference time, which facilitates the second communication device to timely manage and control AI / ML inference.

[0021] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0022] Based on the above solution, the first communication device can send the inference type of the inference result to the second communication device, that is, send which inference types can use the inference result, so that the second communication device can perform corresponding functions through the inference result.

[0023] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0024] In a second aspect, a method for managing and controlling machine model reasoning capabilities is provided. This method can be performed by a first communication device. The first communication device can be a first management device, or a chip / chip system. In this method, the first communication device receives first information from a second communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. The first communication device performs AI / ML reasoning on the AI / ML capabilities and obtains an inference result. The first communication device then sends the inference result to the second communication device.

[0025] In one possible implementation, the first information is used to request the first communication device to perform AI / ML reasoning of the AI / ML capability.

[0026] In one possible implementation, the first communication device sends supported AI / ML capability information to the second communication device. The AI / ML capability indicated by the AI / ML capability information includes AI / ML capability corresponding to AI / ML reasoning.

[0027] In one possible implementation, a first communication device receives second information from a second communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0028] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supporting one or more of management data analysis function, mobility optimization function, network energy saving function or load balancing function.

[0029] In one possible implementation, the first communication device receives an inference type of AI / ML capability, where the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0030] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0031] In a possible implementation manner, the first communication device sends one or more of the inference state and the inference time.

[0032] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0033] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0034] In a third aspect, a method for managing and controlling machine model reasoning capabilities is provided. This method can be performed by a second communication device. The second communication device can be a second management device, or a chip / chip system. In this method, the second communication device receives AI / ML capability information supported by the first communication device. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control the one or more AI / ML capabilities.

[0035] Based on the above scheme, the second communication device can obtain the AI / ML capabilities supported by the first communication device, and thus can manage and control the AI / ML capabilities supported by the first communication device. In some embodiments, the AI / ML capability information is used to manage and control one or more AI / ML capabilities. It can be understood that the management and control can be based on the received AI / ML capability information, triggering the cross-domain management function unit to reason about the AI / ML capabilities of the domain management function unit, or triggering the reasoning of the AI / ML reasoning type of the domain management function unit. It should also be noted that the reasoning of AI / ML capabilities here can be understood as training an ML model based on the AI / ML capabilities, and then applying it to the reasoning type of AI / ML to complete the AI / ML reasoning function corresponding to the reasoning type of AI / ML.

[0036] In one possible implementation, the second communication device receives the AI / ML capability information from the first communication device and applies to the AI / ML reasoning type. Optionally, the AI / ML reasoning type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0037] Based on the above solution, the second communication device can obtain the AI / ML reasoning type applicable to the AI / ML capability information, and thus can manage the AI / ML capabilities of one or more AI / ML reasoning types of the first communication device.

[0038] In one possible implementation, the second communication device sends second information to the first communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0039] Based on the above solution, the second communication device can request the first communication device to send supported AI / ML capability information, thereby obtaining the AI / ML capabilities supported by the first communication device.

[0040] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supporting one or more of management data analysis function, mobility optimization function, network energy saving function or load balancing function.

[0041] Based on the above scheme, the second communication device can instruct the first communication device to send AI / ML capability information supported by reasoning types such as management data analysis function, mobility optimization function, network energy saving function or load balancing function through the second information, thereby realizing the management and control of reasoning type instructions such as management data analysis function, mobility optimization function, network energy saving function or load balancing function from AI / ML capability information.

[0042] In one possible implementation, a second communication device sends first information to a first communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. The one or more AI / ML capabilities indicated by the AI / ML capability information include the AI / ML capabilities indicated by the first information. The second communication device receives an inference result of the AI / ML reasoning from the first communication device.

[0043] Based on the above scheme, the second communication device can indicate the AI / ML capability corresponding to the AI / ML reasoning to the first communication device through the first information, thereby realizing the management and control of the AI / ML capability and enabling the first communication device to perform AI / ML reasoning of the AI / ML capability according to the first information.

[0044] In one possible implementation, the first information is used to request the first communication device to perform AI / ML inference of the AI / ML capability indicated by the first information. Based on this solution, the first information can request the execution of AI / ML inference of the AI / ML capability, that is, the second communication device can control the AI / ML capability based on the first information.

[0045] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0046] In one possible implementation, the second communication device receives one or more of the inference state or inference time. Based on the above solution, the first communication device may also send one or more of the inference state or inference time to the second communication device, thereby allowing the second communication device to understand the one or more of the inference state or inference time, thereby facilitating the second communication device to timely manage and control AI / ML inference.

[0047] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0048] Based on the above solution, the first communication device can send the inference type of the inference result to the second communication device, that is, send which inference types can use the inference result, so that the second communication device can perform corresponding functions through the inference result.

[0049] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0050] In a fourth aspect, a method for managing and controlling machine model reasoning capabilities is provided. This method can be performed by a first communication device. The first communication device can be a first management device, or a chip / chip system. In this method, the first communication device sends supported AI / ML capability information to a second communication device. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control one or more AI / ML capabilities.

[0051] In one possible implementation, the first communication device sends the AI / ML reasoning type applicable to the AI / ML capability information to the second communication device. Optionally, the AI / ML reasoning type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0052] In one possible implementation, a first communication device receives second information from a second communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0053] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supporting one or more of management data analysis function, mobility optimization function, network energy saving function or load balancing function.

[0054] In one possible implementation, a first communication device receives first information from a second communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. The AI / ML capabilities indicated by the AI / ML capability information include the AI / ML capabilities indicated by the first information. The first communication device sends an inference result of the AI / ML reasoning to the second communication device.

[0055] In one possible implementation, the first information is used to request the first communication device to perform AI / ML reasoning of the AI / ML capability.

[0056] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0057] In a possible implementation, the first communication device sends one or more of the inference state and the inference time to the second communication device.

[0058] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0059] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0060] In a fifth aspect, a communication device is provided, comprising a processing unit and a transceiver unit.

[0061] The processing unit is configured to generate first information, wherein the first information includes AI / ML capabilities corresponding to the AI / ML reasoning. The transceiver unit is configured to send the first information to the first communication device. The transceiver unit is further configured to receive an inference result of the AI / ML reasoning from the first communication device.

[0062] In one possible implementation, the first information is used to request the first communication device to perform AI / ML reasoning of the AI / ML capability.

[0063] In one possible implementation, the transceiver unit is further configured to receive AI / ML capability information supported by the first communication device. The AI / ML capability indicated by the AI / ML capability information includes AI / ML capability corresponding to AI / ML reasoning.

[0064] In one possible implementation, the transceiver unit is further configured to send second information to the first communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0065] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supporting one or more of management data analysis function, mobility optimization function, network energy saving function or load balancing function.

[0066] In one possible implementation, the transceiver unit is further used to send the inference type of the AI / ML capability, where the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0067] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0068] In one possible implementation, one or more of an inference state or an inference time is received.

[0069] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0070] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0071] In a sixth aspect, a communication device is provided, comprising a processing unit and a transceiver unit.

[0072] The transceiver unit is configured to receive first information from a second communication device, the first information including an AI / ML capability corresponding to the AI / ML reasoning. The processing unit is configured to perform the AI / ML reasoning based on the AI / ML capability and obtain an reasoning result. The transceiver unit is further configured to transmit the reasoning result to the second communication device.

[0073] In one possible implementation, the first information is used to request the first communication device to perform AI / ML reasoning of the AI / ML capability.

[0074] In one possible implementation, the transceiver unit is further configured to send supported AI / ML capability information to the second communication device. The AI / ML capability indicated by the AI / ML capability information includes AI / ML capability corresponding to AI / ML reasoning.

[0075] In one possible implementation, the transceiver unit is further configured to receive second information from the second communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0076] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supporting one or more of management data analysis function, mobility optimization function, network energy saving function or load balancing function.

[0077] In one possible implementation, an inference type of an AI / ML capability is received, where the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0078] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0079] In a possible implementation, the transceiver unit is further configured to send one or more items of the inference state or the inference time.

[0080] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0081] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0082] In a seventh aspect, a communication device is provided, comprising a processing unit and a transceiver unit.

[0083] A transceiver unit is configured to receive AI / ML capability information supported by the first communication device. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control the one or more AI / ML capabilities. A processing unit is configured to manage and control the one or more AI / ML capabilities.

[0084] In one possible implementation, the transceiver unit is further configured to receive an AI / ML reasoning type applicable to the AI / ML capability information from the first communication device. Optionally, the AI / ML reasoning type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0085] In one possible implementation, the transceiver unit is further configured to send second information to the first communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0086] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supporting one or more of management data analysis function, mobility optimization function, network energy saving function or load balancing function.

[0087] In one possible implementation, the transceiver unit is further configured to send first information to the first communication device, where the first information includes AI / ML capabilities corresponding to the AI / ML reasoning. The one or more AI / ML capabilities indicated by the AI / ML capability information include the AI / ML capability indicated by the first information. The transceiver unit is further configured to receive an inference result of the AI / ML reasoning from the first communication device.

[0088] In one possible implementation, the first information is used to request the first communication device to perform AI / ML reasoning of the AI / ML capability indicated by the first information.

[0089] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0090] In a possible implementation manner, the second communication device receives one or more of the inference state or the inference time capability.

[0091] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0092] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0093] In an eighth aspect, a communication device is provided, comprising a processing unit and a transceiver unit.

[0094] A processing unit is configured to determine supported AI / ML capability information. A transceiver unit is configured to send the supported AI / ML capability information to a second communication device. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control the one or more AI / ML capabilities.

[0095] In one possible implementation, the transceiver unit is further configured to send, to the second communication device, an AI / ML reasoning type applicable to the AI / ML capability information. Optionally, the AI / ML reasoning type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

[0096] In one possible implementation, the transceiver unit is further configured to receive second information from the second communication device, where the second information is used to request the first communication device to send AI / ML capability information.

[0097] In one possible implementation, the second information instructs the first communication device to send AI / ML capability information supported by one or more of the mobility optimization function, the network energy saving function, or the load balancing function.

[0098] In one possible implementation, the transceiver unit is further configured to receive first information from a second communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. The one or more AI / ML capabilities indicated by the AI / ML capability information include the AI / ML capabilities indicated by the first information. The transceiver unit is further configured to send an inference result of the AI / ML reasoning to the second communication device.

[0099] In one possible implementation, the first information is used to request the first communication device to perform AI / ML reasoning of the AI / ML capability indicated by the first information.

[0100] In one possible implementation, the AI / ML capability includes one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

[0101] In a possible implementation, the transceiver unit is further configured to send one or more of the inference state and the inference time to the second communication device.

[0102] In a possible implementation, the inference result further includes an inference type of the inference result, where the inference type includes one or more of a mobility optimization function, a network energy saving function, or a load balancing function.

[0103] In a possible implementation, the inference result includes one or more of the following: cell personality offset, cell identifier, network device identifier, time trigger, switching trigger, information of shutting down cells, information of shutting down carriers, or information of shutting down time slots.

[0104] In a ninth aspect, the present application provides a communication system, which may include a second communication device that executes the method described in the first aspect and a first communication device that executes the method described in the second aspect.

[0105] In a tenth aspect, the present application provides a communication system, which may include a second communication device that executes the method described in the third aspect and a first communication device that executes the method described in the fourth aspect.

[0106] In the eleventh aspect, the present application provides a computer-readable storage medium, in which computer-readable instructions are stored. When a computer reads and executes the computer-readable instructions, the computer executes the method in any possible implementation of any aspect from the first to the fourth aspects above.

[0107] In a twelfth aspect, the present application provides a computer program product. When a computer reads and executes the computer program product, the computer executes the method in any possible implementation of any aspect from the first to the fourth aspects above.

[0108] In a thirteenth aspect, the present application provides a chip, which is used to read a computer program stored in a memory to execute a method in any possible implementation of any one of the first to fourth aspects above.

[0109] The technical effects that can be achieved in any of the second to thirteenth aspects mentioned above can refer to the description of the technical effects that can be achieved in any possible implementation method of any of the first aspects mentioned above, and repetitions will not be discussed. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] FIG1 is a schematic diagram of a MnF entity provided in an embodiment of the present application;

[0111] FIG2 is a schematic diagram of a service-oriented management architecture provided in an embodiment of the present application;

[0112] FIG3A is a schematic diagram of the architecture of an AI / ML capability provided by this application;

[0113] FIG3B is a schematic diagram of the architecture of another AI / ML capability provided in an embodiment of the present application;

[0114] FIG4A is a schematic diagram of the architecture of another AI / ML capability provided in an embodiment of the present application;

[0115] FIG4B is a schematic diagram of the architecture of another AI / ML capability provided in an embodiment of the present application;

[0116] FIG4C is a schematic diagram of the architecture of another AI / ML capability provided in an embodiment of the present application;

[0117] FIG5A is a schematic diagram of the architecture of another AI / ML capability provided in an embodiment of the present application;

[0118] FIG5B is a schematic diagram of the architecture of another AI / ML capability provided in an embodiment of the present application;

[0119] FIG5C is a schematic diagram of the architecture of another AI / ML capability provided in an embodiment of the present application;

[0120] FIG6 is an exemplary flow chart of a method for managing and controlling machine model reasoning capabilities provided in an embodiment of the present application;

[0121] FIG7 is an exemplary flowchart of another method for managing and controlling machine model reasoning capabilities provided in an embodiment of the present application;

[0122] FIG8 is an exemplary flowchart of another method for managing and controlling machine model reasoning capabilities provided in an embodiment of the present application;

[0123] FIG9 is an exemplary flowchart of another method for managing and controlling machine model reasoning capabilities provided in an embodiment of the present application;

[0124] FIG10 is a block diagram of a communication device provided in an embodiment of the present application;

[0125] FIG11 is a block diagram of another communication device provided in an embodiment of the present application;

[0126] FIG12 is a block diagram of another communication device provided in an embodiment of the present application;

[0127] FIG13 is a block diagram of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0128] In order to facilitate understanding of the technical solutions provided by the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained and illustrated below.

[0129] 1) Use case is a technology that obtains requirements by using scenarios. It can also be called the reasoning type of AI / ML or the reasoning function of AI / ML, which is not specifically limited in this application. The use cases involved in the embodiments of the present application may include self-organizing network (SON) use cases or SON reasoning types. Among them, the reasoning type of SON may include at least one of mobility robustness optimization (MRO), distributed mobility robustness optimization (DMRO), energy saving (ES), distributed energy saving (DES), mobility load balancing (MLB) or distributed mobility load balancing (DMLB). The use cases involved in the embodiments of the present application may include radio access network intelligence (RAN intelligence) use cases or radio access network intelligence reasoning types. Among them, the reasoning type of radio access network intelligence may include mobility optimization (MRO), network energy saving (NES), and load balancing. The use cases involved in the embodiments of this application may also include management data analytics (MDA) use cases or MDA reasoning types, such as coverage problem analysis, etc., which can be referenced in Section 8.4 of 3GPP TS 28.104 V18.2.0. The MDA type type is not described in detail in this application. The use cases involved in the embodiments of this application may also include network data analytics function (NWDAF) use cases or NWDAF reasoning types, etc., which can be referenced in 3GPP TS 23.288. The use cases in this application are not described in detail.

[0130] The embodiments of the present application can be applied to various mobile communication systems, such as new radio (NR) systems, long term evolution (LTE) systems, advanced long term evolution (LTE-A) systems, future communication systems and other communication systems, but the embodiments of the present application are not limited thereto. For example, the various embodiments in the present application can be used in the network management architecture of NR. The network management architecture of NR may include a management function (MnF). MnF is a management entity defined by the 3rd Generation Partnership Project (3GPP), and its externally visible behavior and interface are defined as management services (MnS). In the management architecture for providing services, MnF can act as an MnS producer or an MnS consumer. The MnS produced by the MnS producer of MnF may have multiple MnS consumers. MnF can consume multiple management services from one or more management service producers.

[0131] As shown in Figure 1, the MnS provided by an MnF can be used to provide services to another MnF (e.g., MnF#A). In this case, the MnF can act as a MnS producer, and MnF#A can act as a MnS consumer. Furthermore, the MnF can also obtain services from another MnF (e.g., MnF#B, which can be the same as or different from MnF#A). In other words, the MnF shown in Figure 1 can act as a MnS consumer, while MnF#B can act as a MnS producer. In other words, the same MnF can act as both a MnS consumer and a MnS producer.

[0132] It should be understood that the circle graphic or arc graphic shown in FIG. 1 may represent a service-based interface.

[0133] Figure 2 is a schematic diagram of a service-oriented management architecture applicable to an embodiment of the present application. The service-oriented management architecture includes a business support system (BSS), a cross-domain management function (CD-MnF) unit, a domain management function (Domain-MnF), and a network element (NE). Figure 2 uses two domain management function units and four network elements as an example.

[0134] If the MnS is provided by a cross-domain management functional unit, the cross-domain management functional unit is the MnS producer, and the service support system is the MnS consumer. If the MnS is provided by a domain management functional unit, the domain management functional unit is the MnS producer, and the cross-domain management functional unit is the MnS consumer. If the MnS is provided by a network element, the network element is the MnS producer, and the domain management functional unit is the MnS consumer. It should be understood that the MnS producer and MnS consumer can also be deployed in the same entity, such as in a service support system, a cross-domain management functional unit, a domain management functional unit, or a network element.

[0135] In the embodiment of the present application, the cross-domain management function unit can be used to manage one or more domain management function units. The domain management function unit can be used to manage one or more network elements. The following is a brief introduction to each unit.

[0136] 1) Business support systems (BSSs) are systems for communication services, providing billing, settlement, accounting, customer service, sales operations, network monitoring, communication service lifecycle management, business intent translation, and other functions and MnS. BSSs can be either carrier operations systems or vertical industry operations systems (OT systems).

[0137] 2) Cross-domain management functional units, which can be network management entities such as network management function units (NMFs), network function management service consumers (NFMS_Cs), MnS producers, MnS consumers, or management data analytics (MDA) consumers. The cross-domain management functional units can provide one or more of the following management functions or MnSs: network lifecycle management, network deployment, network fault management, network performance management, network configuration management, network assurance, network optimization, and translation of service producer network intents (intent from communication service providers, intent-CSPs).

[0138] It should be understood that the "intention" in the embodiments of the present application can be understood as the expectation of the intention producer (such as a network element) and the system where the intention producer is located (such as a network or subnetwork, etc.), which may include requirements, goals or constraints, etc. The translation of intention refers to the process of determining the strategy of the intention. For example, the strategy may be a condition for indicating that the intention is not met. For example, when the intention is to save energy, strategy A may be: when the power consumption is greater than the first threshold, the power consumption is abnormal (i.e., no energy saving); strategy B may be: when the power consumption is greater than the second threshold, the power consumption is abnormal (i.e., no energy saving). It can be understood that even for the same intention, the solutions that can meet the intention determined by different strategies may be different.

[0139] The network referred to in the above-mentioned management function or MnS may include one or more network elements or subnetworks, or a network slice. That is, the network management function unit may be a network slice management function (NSMF) unit, a cross-domain management data analytical function (MDAF) unit, a cross-domain self-organization network function (SON Function), or a cross-domain intent driven management service (intent driven MnS) unit.

[0140] Optionally, in certain deployment scenarios, the cross-domain management functional unit can also provide sub-network lifecycle management, sub-network deployment, sub-network fault management, sub-network performance management, sub-network configuration management, sub-network assurance, sub-network optimization functions, and translation of the network intent of the sub-network service producer (intent-CSP) or the network intent of the sub-network service consumer (intent from communication service consumer, intent-CSC). The sub-network here consists of multiple small sub-networks and can be a network slice sub-network.

[0141] 3) Domain management functional unit, which can be a network element management entity such as NMF, element management system (EMS), network function management service provider (NFMS_P), make before break automation engine (MAE), MnS producer, MnS consumer, or MDA producer.

[0142] The domain management functional unit can provide one or more of the following management functions or MnS: sub-network or network element lifecycle management, sub-network or network element deployment, sub-network or network element fault management, sub-network or network element performance management, sub-network or network element assurance, sub-network or network element optimization, and sub-network or network element intent (intent from network operator, intent-NOP) translation. A sub-network here includes one or more network elements. A sub-network can also include sub-networks, i.e., one or more sub-networks form a larger sub-network.

[0143] Optionally, the subnetwork here can also be a network slice subnetwork. The domain management system can be a network slice subnet management function (NSSMF) unit, a domain management data analytical function (domain MDAF) unit, a domain self-organization network function (SON Function), a domain intent management function unit, etc.

[0144] The domain management functional units can be classified as follows:

[0145] By network type, they can be categorized as: radio access network (RAN) domain management function (RAN domain MnF), core network domain management function (CN domain MnF), transport network domain management function (TN domain MnF), etc. It should be noted that a domain management function unit can also be a domain network management system that can manage one or more of the access network, core network, or transport network. The transport network, which provides signal transmission and conversion, is the foundation of the switching network, data network, and support network.

[0146] According to administrative region classification, it can be divided into: domain management functional units of a certain area, such as domain management functional unit of city A, domain management functional unit of city B, etc.

[0147] 4) Network elements are entities that provide network services, including core network elements, radio access network elements, or transport network elements. For example, in the architecture shown in Figure 2, the domain management functional unit may include a radio access network domain management functional unit, a core network element domain management functional unit, or a transport network domain management functional unit. The radio access network domain management functional unit can be used to manage radio access network elements, the core network element domain management functional unit can be used to manage core network elements, and the transport network domain management functional unit can be used to manage transport network elements.

[0148] Exemplarily, core network network elements may include but are not limited to: access and mobility management function (AMF) network element, session management function (SMF) network element, policy control function (PCF) network element, network data analytical function (NWDAF) network element, network repository function (NRF) network element, and gateway, etc.

[0149] The network elements of the radio access network may include but are not limited to: various types of base stations (such as next-generation base stations (generation node B, gNB), evolved base stations (evolved Node B, eNB), etc.), centralized control units (central unit control panel, CUCP), centralized units (central unit, CU), distributed units (distributed unit, DU), centralized user plane units (central unit user panel, CUUP), etc.

[0150] It should be understood that the network function in the embodiments of the present application is also called a network element, or an entity, etc.

[0151] Among them, the network element can provide one or more of the following management functions or MnS: network element lifecycle management, network element deployment, network element fault management, network element performance management, network element assurance, network element optimization function and network element intent translation, etc.

[0152] AI / ML technologies and related applications are increasingly being adopted by a wider range of industries. AI / ML capabilities are also being used in various fields of 5GS, including intelligent optimization use cases in RAN base stations, such as mobility load balancing (MLB), mobility robustness optimization (MRO), and energy saving (ES), management data analysis services in network management, such as management data analytics (MDA), and network data analysis services in the core network, such as the network data analytics function (NWDAF).

[0153] Currently, the AI / ML management workflow is defined, including the training phase, simulation phase, deployment phase, and inference phase.

[0154] The training phase involves training one or a group of ML models, including initial training and retraining. It also includes validation of the ML entity to evaluate its performance on training and validation data. If the validation results do not meet expectations, such as unacceptable variance, the ML model associated with the ML entity needs to be retrained. The training phase is the initial stage of the AI / ML management workflow.

[0155] In the simulation phase, the ML entity used for reasoning is run in a simulation environment. Its purpose is to evaluate its reasoning performance in the simulation environment before applying the ML entity to the target network or system.

[0156] The deployment phase is the process of making the trained ML entities available for target AI / ML inference functions.

[0157] Inference phase: The process of using ML entities to perform reasoning through AI / ML reasoning functions.

[0158] Currently, TR 37.817 and TS 38.300 define the implementation of RAN intelligence through AI / ML technology, specifically for supporting NES (Network Energy Saving), LB (Load balancing) and MO (Mobility Optimization). The standard discussion also defines how to support and manage the scenarios of RAN intelligent reasoning types on the network management. In some embodiments, the reasoning types of RAN intelligence may include at least one of distributed MRO (Distributed Mobility Robustness Optimization, DMRO), distributed ES (Distributed Energy Saving, DES), distributed MLB (Distributed Mobility Load Balancing, DMLB), mobility optimization (MO), network energy saving (NES), and load balancing (LB). The specific management information includes switch management and policy management of the reasoning type of RAN intelligence, that is, the cross-domain management node can set the switch for the use case and configure the execution policy.

[0159] However, the management of RAN intelligence's reasoning types in the standard only supports the management of switches and execution policies, and does not propose the management of RAN intelligence's AI / ML capabilities.

[0160] In view of this, an embodiment of the present application provides a method for managing and controlling machine model reasoning capabilities. In this method, a first communication device can receive first information from a second communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. The first communication device can perform AI / ML reasoning of the AI / ML capability and obtain an inference result. The first communication device can send the inference result to the second communication device. Based on this solution, the first communication device can implement management and control of the AI / ML capability through the first information, enabling the second communication device to perform AI / ML reasoning of the AI / ML capability based on the first information.

[0161] It should be noted that the term "AI / ML" in this application can be replaced by "AI," "ML," or "AIML," etc. AI / ML can be understood as AI and ML, as AI or ML, or as AI and / or ML.

[0162] To facilitate understanding of the technical solutions provided in the embodiments of this application, the AI / ML capabilities are explained and illustrated below.

[0163] The AI / ML capabilities involved in the embodiments of the present application can be understood as the reasoning capabilities of AI / ML and the reasoning simulation capabilities of AI / ML.

[0164] It should be noted that this application does not limit the specific name of AI / ML reasoning capabilities. For example, AI / ML reasoning capabilities may also be referred to as ML reasoning capabilities, AI reasoning capabilities, or other names. AI / ML reasoning simulation capabilities may also be referred to as ML reasoning simulation capabilities, AI reasoning simulation capabilities, ML simulation capabilities, AI simulation capabilities, or other names.

[0165] In one possible scenario, the AI / ML capabilities involved in the embodiments of the present application may include one or more of the following: traffic analysis capability, coverage analysis capability, mobility analysis capability, load analysis capability, fault analysis capability, network slicing throughput analysis capability, slice load analysis capability, network slicing traffic prediction analysis capability, service experience analysis capability, energy efficiency analysis capability, or energy consumption analysis capability.

[0166] It should be noted that the AI / ML capabilities here can also be manufacturer-defined capabilities, and this application does not limit them here.

[0167] It should also be noted that the AI / ML capability here can be understood as the reasoning capability and / or simulation capability possessed by the reasoning type of AI / ML, that is, the second communication device can train an ML model based on the AI / ML capability, and then apply it to the reasoning type of AI / ML to complete the AI / ML reasoning function corresponding to the reasoning type of AI / ML. Taking the reasoning type of AI / ML as MRO in SON as an example, MRO as the reasoning function of AI / ML can use the mobility analysis ML model trained by the mobility analysis capability to perform reasoning, obtain the reasoning result, and then use the reasoning result to perform the MRO function. Similarly, the AI / ML capabilities of other reasoning types can refer to the above description and will not be repeated here.

[0168] It should also be noted that in the embodiments of the present application, the AI / ML reasoning simulation capability can be understood as simulating the AI / ML reasoning type or the AI / ML reasoning capability. Simulating the AI / ML reasoning capability involves running an ML model used for reasoning in a simulation environment. The ML model is the ML model corresponding to the AI / ML capability, or it can be understood as the ML model trained by the AI / ML capability. This allows evaluation of the analysis or optimization performance of the ML model in the simulation environment before applying the ML model to the target reasoning type and further to the live network. Simulating the AI / ML reasoning type involves running the reasoning type in the simulation environment, thereby evaluating the analysis or optimization performance of the reasoning type in the simulation environment before further application to the live network. For example, if the AI / ML reasoning type is MRO in SON, MRO, as an AI / ML reasoning function, can perform reasoning simulation using the mobility analysis ML model trained by the mobility analysis capability, obtain reasoning simulation results, and optionally continue to use the reasoning simulation results to perform simulation of the MRO function. Similarly, the AI / ML reasoning simulation capabilities for other reasoning types can be referred to above and will not be repeated here.

[0169] The following explains and illustrates the various AI / ML capabilities shown above.

[0170] Traffic analysis capabilities can be embodied as ML models with traffic analysis capabilities, or can be understood as being able to perform traffic analysis reasoning. This means that reasoning is performed using the ML model. The ML model with traffic analysis capabilities can analyze traffic metrics. Analysis of traffic metrics can include identifying traffic issues (such as traffic congestion), collecting statistics on traffic-related metrics, or predicting traffic-related metrics.

[0171] Coverage analysis capabilities can be embodied in an ML model with coverage analysis capabilities, or can be understood as being able to perform coverage analysis reasoning. This means that the ML model with coverage analysis capabilities can be used to perform reasoning and analyze coverage metrics. Analysis of coverage metrics can include identifying coverage issues (e.g., weak coverage, over-coverage, coverage holes, and out-of-area coverage), compiling statistics on coverage-related metrics, or even predicting coverage-related metrics.

[0172] Mobility analysis capabilities can be embodied as ML models with mobility analysis capabilities, or can be understood as being able to perform mobility analysis reasoning. This means that reasoning is performed using the ML model. The ML model with mobility analysis capabilities can analyze mobility indicators. The analysis of mobility indicators can include identifying mobility issues (e.g., premature handover, late handover, handover to the wrong cell, etc.), collecting statistics on mobility-related indicators, or predicting mobility-related indicators.

[0173] Load analysis capabilities can be embodied in ML models with load analysis capabilities, or can be understood as being able to perform load analysis reasoning. This means that the ML model with load analysis capabilities can be used to perform reasoning and analyze load metrics. Analysis of load metrics can include identifying load issues (e.g., high load, low load), compiling statistics on load-related metrics, or even predicting load-related metrics.

[0174] Fault analysis capabilities can be embodied as ML models with fault analysis capabilities, or can be understood as being able to perform fault analysis reasoning. This means using the ML model with fault analysis capabilities to perform reasoning and analyze fault indicators. This analysis of fault indicators can include fault problem identification (e.g., network alarms), statistics on fault-related indicators, or predictions of fault-related indicators.

[0175] - The network slicing throughput analysis capability can be embodied as an ML model with a network slicing throughput analysis function, which can also be understood as being able to perform reasoning for network slicing throughput analysis, i.e., using the ML model with the network slicing throughput analysis function to perform reasoning. The ML model with the network slicing throughput analysis function can analyze network slicing throughput indicators. The analysis of network slicing throughput indicators can include identifying network slicing throughput issues (e.g., a decrease in throughput), collecting statistics on network slicing throughput-related indicators, or predicting network slicing throughput-related indicators.

[0176] - The slice load analysis capability can be reflected in an ML model with slice load analysis functions, which can also be understood as being able to perform slice load analysis reasoning, that is, using the ML model with the slice load analysis function to perform reasoning, and the ML model with the slice load analysis function can analyze slice load indicators. The analysis of slice load indicators can include identifying problems with the slice load (such as a decrease in key performance indicators (KPIs)), statistics on negative slice load-related indicators, or predictions of slice load-related indicators.

[0177] - The network slicing traffic prediction and analysis capability can be embodied as an ML model with network slicing traffic prediction and analysis functions, which can also be understood as performing reasoning for network slicing traffic prediction and analysis, i.e., using the ML model with the network slicing traffic prediction and analysis functions to perform reasoning. The ML model with the network slicing traffic prediction and analysis functions can analyze indicators of network slicing traffic prediction. The analysis of indicators of network slicing traffic prediction can include identifying problems with network slicing traffic prediction, collecting statistics on indicators related to network slicing traffic prediction, or predicting indicators related to network slicing traffic prediction.

[0178] The service experience analysis capability can be embodied in an ML model with service experience analysis capabilities, or it can be understood as the ability to perform reasoning related to service experience analysis. This means that the ML model with this service experience analysis capability can perform reasoning and analyze service experience indicators. This analysis of service experience indicators can include identifying service experience issues, compiling statistics related to service experience indicators, or predicting service experience indicators.

[0179] Energy efficiency analysis capabilities can be embodied in ML models with energy efficiency analysis capabilities, or can be understood as being able to perform reasoning related to energy efficiency analysis. This means that reasoning is performed using ML models with this energy efficiency analysis capability, and the ML models with this energy efficiency analysis capability can analyze energy efficiency indicators. The analysis of energy efficiency indicators can include identifying energy efficiency issues (e.g., high energy efficiency, low energy efficiency, etc.), compiling statistics on energy efficiency-related indicators, or predicting energy efficiency-related indicators.

[0180] Energy consumption analysis capabilities can be embodied as ML models with energy consumption analysis capabilities, or can be understood as being able to perform energy consumption analysis reasoning. This means that the ML model with this energy consumption analysis capability can perform reasoning and analyze energy consumption indicators. This analysis of energy consumption indicators can include identifying energy consumption issues (e.g., high energy consumption, low energy consumption, etc.), compiling statistics on energy consumption-related indicators, or predicting energy consumption-related indicators.

[0181] In another possible scenario, the AI / ML capabilities involved in the embodiments of the present application can be defined as one or more of the AI / ML reasoning types included in the MDA. The AI / ML reasoning types can refer to the inference types (InferenceType) defined in section 7.5.1 of 3GPP TS 28.105 V18.2.0, such as coverage analysis, mobility analysis, etc., and can refer to the AI / ML reasoning types of MDA defined in section 8.4 of 3GPP TS 28.104 V18.2.0. This application does not describe them in detail. The AI / ML capabilities involved in the embodiments of the present application can also be defined as one or more of the reasoning types of SON, such as MRO, MLB, and ES, and can refer to the use cases defined in section 7 of 3GPP TS 28.313 V17.9.0 or the use cases defined in section 5.1 of TS 28.310 V18.4.0. This application does not describe them in detail. The AI / ML capabilities involved in the embodiments of this application can also be defined as one or more types of RAN intelligent reasoning, such as MO, MLB, and ES. Please refer to the use cases defined in 3GPP TS 38.300, which will not be described in detail in this application.

[0182] The AI / ML capabilities involved in the embodiments of the present application can also be defined as one or more of the AI / ML reasoning types included in NWDAF, such as slice load analysis and user data congestion analysis. For details, please refer to the use cases defined in Chapter 6 of 3GPP TS 23.288V 18.4.0. This application will not elaborate on this.

[0183] In the embodiments of this application, AI / ML capabilities can be universal, meaning they are available for all use cases, i.e., all AI / ML reasoning types can share one or more AI / ML capabilities. Alternatively, in the embodiments of this application, AI / ML capabilities can be use case-granular, meaning each AI / ML reasoning type has its own AI / ML capability. Each of these is described below.

[0184] For example, AI / ML capabilities are universal. In one example, universal AI / ML capabilities can be attached to various use cases, meaning that each use case can use the universal AI / ML capabilities to perform reasoning. See Figure 3A for an example of a SON use case. AI / ML capabilities and SON use cases can be coupled, and AI / ML capabilities can be attached to SON use cases. Each SON use case can use AI / ML capabilities to perform reasoning.

[0185] In another example, general AI / ML capabilities can be embedded in various use cases, and each use case with AI / ML capabilities can be used as a new use case. Refer to Figure 3B, which takes the use case of SON as an example for illustration. AI / ML capabilities and SON use cases are not coupled, and AI / ML capabilities can be embedded in various use cases as new use cases. As shown in Figure 3B, MRO, MLB, and ES are use cases of SON without AI / ML capabilities, and mobility optimization (MO), load balancing (LB), and network energy saving (NES) are use cases of SON with AI / ML capabilities. Among them, MO can be understood as MRO with AI / ML capabilities, LB can be understood as MLB with AI / ML capabilities, and NES can be understood as ES with AI / ML capabilities.

[0186] It should be noted that the use cases with AI / ML capabilities in FIG3B , such as MO, LB, and NES, are shown only as examples and do not constitute a limitation on the names of the use cases with AI / ML capabilities.

[0187] For example, general AI / ML capabilities can also be attached to MDA use cases, and MDA use cases can be deployed in domain management functional units.

[0188] Exemplarily, AI / ML capabilities are use case-specific. In one example, general AI / ML capabilities can be attached to individual use cases. See Figure 4A for an example of a SON use case. AI / ML capabilities and SON use cases can be coupled, and AI / ML capabilities can be attached to SON use cases. AI / ML capabilities are use case-specific.

[0189] For example, in a SON use case, MRO may support AI / ML capabilities. The AI / ML capabilities of MRO may include one or more of the following: traffic analysis capabilities or mobility analysis capabilities.

[0190] For example, in a SON use case, MLB may support AI / ML capabilities, and the AI / ML capabilities of MLB may include load analysis capabilities.

[0191] For example, in a SON use case, ES may support AI / ML capabilities, and the AI / ML capabilities of ES may include one or more of the following: energy efficiency analysis capability, energy consumption analysis capability, or traffic analysis capability.

[0192] The following describes how to deploy AI / ML capabilities for each use case.

[0193] Referring to Figure 4B , a distributed MRO (DMRO) use case is used as an example. Figure 4B illustrates the location of the training, inference, and DMRO functions. In Figure 4B , the cross-domain management function system serves as a service consumer of the domain management function system. The domain management function unit is illustrated using the RAN domain management function system as an example. The RAN domain management function system can include the gNB and the RAN domain management function. The AI / ML training function can be deployed in the RAN domain management function, while the DRMO function and AI / ML inference function can be deployed within the gNB. AI / ML capabilities can be deployed within the AI / ML inference function. The MnS interface between the cross-domain management function system and the domain management function system is an interface to be standardized and is referred to as the management service interface. Similarly, other optimization functions supported on the gNB, such as DMLB and DES, can be deployed in a similar manner.

[0194] Refer to Figure 4C, which uses the MDAF use case as an example for explanation. Figure 4C shows the location of the training function, reasoning function, and MDA function. The top box in the figure is the cross-domain management system (RAN / CN domain MnS consumer / Cross domain management), that is, the cross-domain management function system in Figure 4C serves as the service consumer of the domain management function system, and the domain management function unit is explained using the RAN domain management function system as an example. The RAN domain management function system may include gNB and RAN domain management functions. The AI / ML training function, AI / ML reasoning function, and MDA function are all deployed within the RAN domain management function, and the AI / ML capability is deployed within the AI / ML reasoning function. The MnS interface between the cross-domain management function system and the domain management function system is the interface to be standardized, referred to as the management service interface. Similarly, similar deployments can be made for other MDA functions, NWDAF functions, etc. supported in the RAN domain management function.

[0195] In another example, AI / ML capabilities are embedded in each use case. Refer to Figure 5A, which takes the use case of SON as an example for explanation. AI / ML capabilities and SON use cases are not coupled, and AI / ML capabilities are embedded in each use case. As shown in Figure 5A, MRO, MLB, and ES are use cases of SON that do not have AI / ML capabilities. Mobility optimization (MO), load balancing (LB), and network energy saving (NES) have AI / ML capabilities and can be used as new use cases or functions, coexisting with MRO, MLB, and ES in related technologies. Among them, MO can be understood as MRO with AI / ML capabilities, LB can be understood as MLB with AI / ML capabilities, and NES can be understood as ES with AI / ML capabilities. In Figure 5A, AI / ML capabilities are case specific.

[0196] It should be noted that the use cases with AI / ML capabilities in FIG5A , such as MO, LB, and NES, are shown only as examples and do not constitute a limitation on the names of the use cases with AI / ML capabilities.

[0197] The following describes how to deploy AI / ML capabilities embedded in various use cases.

[0198] Refer to Figure 5B, which uses MRO as an example for explanation. The difference between the deployment method in Figure 5B and the deployment method in Figure 4B is that the AI / ML capability is embedded in the MO, that is, the AI / ML DMRO capability (AIMLDMROCapability) is a new and independent capability, or it can be called a function, which coexists with the DMRO function in the relevant technology. It should be noted that this scenario can be understood as the MO embedded with the MO's unique AI / ML capability, the LB embedded with the LB's unique AI / ML capability, and the NES embedded with the NES's unique AI / ML capability.

[0199] Refer to Figure 5C, which takes the use case of MDA as an example for explanation. The difference between the deployment method in Figure 5C and the deployment method in Figure 4C is that the AIML capability is embedded in the MDA, that is, the AI / ML MDA capability (AIMLMDACapability) is a new independent capability, or it can be called a function, which coexists with the MDA function in the relevant technology. The AI / ML MDA capability (AIMLMDACapability) here can be one or more MDA types, and this application does not make specific limitations. For example, the AI / ML MDA capability (AIMLMDACapability) can be the AI / ML MDA coverage analysis capability (AIMLMDACoverageAnalysisCapabiltiy), and the MDA type can refer to the type definition in 3GPP TS 28.104, which is not described in detail in this application.

[0200] The following introduces a method for controlling the machine model reasoning capability provided by an embodiment of the present application. The embodiment of the present application can be applied to scenarios where both the training function and the reasoning function are deployed on a domain management function unit, such as MDA, and can also be applied to scenarios where the training function is deployed on a domain management function unit and the reasoning function is deployed on a base station, such as SON or RAN intelligence; it can also be applied to scenarios where both the training function and the reasoning function are deployed on a base station, such as SON, RAN intelligence; it can also be applied to scenarios where the training is in a cross-domain management function unit and the reasoning function is in a management function unit or a base station. You can refer to the function management scenario defined in 3GPP TS 28.105V18.2.0 4a.2, which will not be described in detail in this application. In the above scenarios, the cross-domain management function unit can act as a service consumer of the domain management function unit to manage and control the functions in the domain management function unit.

[0201] In an embodiment of the present application, the first communication device may be an AI / ML MnS consumer, or a component in an AI / ML MnS consumer (such as a chip or a chip system, etc.). The second communication device may be an AI / ML MnS producer, or a component in an AI / ML MnS producer (such as a chip or a chip system, etc.). The first communication device and the communication device may be deployed in different entities, or they may be deployed in the same entity, as shown in Figure 1. In order to facilitate understanding of the embodiment of the present application, the following text takes the first communication device and the second communication device as an example deployed in different entities. It can be understood that in an embodiment of the present application, the role of providing the management service (management service, MnS) of AI / ML capabilities is called a producer (producer), and the role of calling the AI / ML capability management service is called a consumer (consumer).

[0202] If the first communication device is the cross-domain management functional unit in Figure 2, then the second communication device may be the domain management functional unit in Figure 2. For descriptions of the cross-domain management functional unit and the domain management functional unit, please refer to the relevant content of Figure 2 and will not be repeated here.

[0203] Referring to FIG. 6 , which is an exemplary flowchart of a method for managing and controlling machine model reasoning capabilities provided in an embodiment of the present application, the method may include the following operations.

[0204] S601: The cross-domain management function unit sends second information to the domain management function unit.

[0205] S601 is an optional step, which is shown by a dotted line in FIG6 .

[0206] Correspondingly, the domain management function unit receives second information from the cross-domain management function unit.

[0207] The second information is used to request the AI / ML capability information of the domain management functional unit. It is understood that the AI / ML capability information of the domain management functional unit can be understood as information about the AI / ML capabilities that the domain management functional unit can support. In some embodiments, the AI / ML capability information of the domain management functional unit can also be understood as the types of AI / ML capabilities that the domain management functional unit can support.

[0208] In one possible scenario, the second information may request or instruct the domain management functional unit to send AI / ML capability information. It is understandable that in this case, the second information may be used to request AI / ML capability information supported by all AI / ML reasoning types.

[0209] In another possible scenario, the second information may request or instruct the domain management function unit to send AI / ML capability information supported by the reasoning type of the first AI / ML. It is understandable that the second information includes the reasoning type of the first AI / ML.

[0210] It should be noted that the first AI / ML reasoning type includes at least one of the following: MDA reasoning type, SON reasoning type, NWDAF reasoning type, or radio access network intelligence (RAN intelligence) reasoning type. The specific definition of the AI / ML reasoning type here can refer to the inference type (InferenceType) defined in section 7.5.1 of 3GPP TS 28.105 V18.2.0.

[0211] In some embodiments, the reasoning type of the MDA may include at least one of energy saving analysis, coverage problem analysis, fault analysis, network slice throughput analysis, slice load analysis, network slice traffic prediction analysis, service experience analysis, congestion traffic analysis, mobility performance analysis, or handover optimization analysis. The specific types can be referred to as defined in Section 8.4 of TS 28.104 and will not be repeated here.

[0212] In some embodiments, the reasoning type of SON may include at least one of MRO, DMRO, ES, DES, MLB, and DMLB. For specific types, please refer to the definition in Section 7 of TS 28.313, which will not be repeated here.

[0213] In some embodiments, the reasoning type of NWDAF may include at least one of slice load analysis, network performance analysis, user data congestion analysis, etc. The specific types can refer to the use cases defined in Chapters 6.5 to 6.21 of TS 23.288, which will not be repeated here.

[0214] In some embodiments, the reasoning type of RAN intelligence includes at least one of MO, NES, and LB types. For specific types, refer to the definition in the "Support of AI / ML for NG-RAN" section in TS 38.300 or the definition in Chapter 5 of TR 37.817, which will not be repeated here.

[0215] For example, the second information may request or instruct the domain management function unit to send AI / ML capability information supported by the SON reasoning type (such as MRO (MO), MLB (LB), or ES (NES)). For another example, the second information may request or instruct the domain management function unit to send AI / ML capability information supported by the MDA reasoning type (such as coverage problem analysis and fault analysis). For another example, the second information may request or instruct the domain management function unit to send AI / ML capability information supported by the NWDAF reasoning type.

[0216] S602: The domain management functional unit sends AI / ML capability information to the cross-domain management functional unit.

[0217] Correspondingly, the cross-domain management functional unit receives AI / ML capability information from the domain management functional unit.

[0218] It should be noted that the AI / ML capability information is used for the management and control of the one or more AI / ML capabilities. It can be understood that the management and control can be based on the received AI / ML capability information, triggering the cross-domain management function unit to reason or simulate the AI / ML capability of the domain management function unit, or triggering the reasoning or simulation of the AI / ML reasoning type of the domain management function unit. It should also be noted that the reasoning of AI / ML capabilities here can be understood as training an ML model based on the AI / ML capabilities, and then applying it to the AI / ML reasoning type to complete the AI / ML reasoning function corresponding to the AI / ML reasoning type.

[0219] The AI / ML capability information can be understood as information about the AI / ML capabilities supported or possessed by the domain management functional unit, that is, the domain management functional unit in S602 can indicate to the cross-domain management functional unit the AI / ML capabilities supported or possessed by the domain management functional unit. Alternatively, the AI / ML capability information can also be understood as information about the AI / ML capabilities supported or possessed by the AI / ML reasoning type in the domain management functional unit. It can be understood that the AI / ML capability can be universal for all AI / ML reasoning types or granular for each AI / ML reasoning type. Please refer to the previous relevant description and will not be repeated here. In some embodiments, the AI / ML capability information of the domain management functional unit can also be understood as the AI / ML capability type that the domain management functional unit can support.

[0220] It is understandable that AI / ML capability information includes AI / ML capability. In some embodiments, AI / ML capabilities include one or more of traffic analysis capability, coverage analysis capability, mobility analysis capability, load analysis capability, fault analysis capability, network slicing throughput analysis capability, slice load analysis capability, network slicing traffic prediction analysis capability, service experience analysis capability, energy efficiency analysis capability or energy consumption analysis capability. Optionally, the AI / ML capability can be represented by a character string, or it can be represented by a custom identifier, which is not limited in this application. It should also be noted that the AI / ML capability can also be customized by the manufacturer, which is not limited in this application. It should also be noted that the AI / ML capability can be used as the reasoning capability of AI / ML, or as the simulation capability of AI / ML.

[0221] Optionally, the AI / ML capability information may also include the reasoning type of AI / ML, where the reasoning type of AI / ML may also be understood as an applicable AI / ML reasoning function. In some embodiments, the reasoning type of AI / ML includes at least one of the following: the reasoning type of MDA, the reasoning type of SON, the reasoning type of NWDAF, or the reasoning type of radio access network intelligence (RAN intelligence). The specific definition of the reasoning type of AI / ML here can refer to the inference type (InferenceType) defined in section 7.5.1 of 3GPP TS 28.105 V18.2.0.

[0222] In one possible implementation, if FIG6 executes S601, and the second information requests the domain management function unit to send AI / ML capability information, that is, the second information does not carry the AI / ML reasoning type, then it can be considered that the cross-domain management function unit requests the AI / ML capability information supported by all AI / ML reasoning types of the domain management function unit. In this case, the domain management function unit can send all AI / ML capability information to the cross-domain management function unit, such as including all AI / ML capabilities. The AI / ML capabilities here can refer to the AI / ML capabilities mentioned above and will not be repeated here. Optionally, in this possible implementation, the domain management function unit can send the AI / ML reasoning type to which the AI / ML capability information is applicable to the cross-domain management function unit, that is, the domain management function unit can indicate to the cross-domain management function unit that the AI / ML capability in the sent AI / ML capability information can be used for the AI / ML reasoning type. The AI / ML reasoning type here can refer to the AI / ML reasoning type mentioned above and will not be repeated here. Exemplarily, the domain management functional unit sends AI / ML capabilities including load analysis capabilities to the cross-domain management functional unit. The domain management functional unit can send the AI / ML reasoning type applicable to the AI / ML capabilities to the cross-domain management functional unit, such as ES (NES). That is, the domain management functional unit can indicate to the cross-domain management functional unit that the load analysis capability can be used for ES (NES).

[0223] In another possible implementation, if FIG6 executes S601, the second message requests the domain management functional unit to send AI / ML capability information of the first AI / ML reasoning type. That is, the second message carries the reasoning type of the first AI / ML. Then, the domain management functional unit may send the AI / ML capability information of the first AI / ML reasoning type to the cross-domain management functional unit. It is understood that the reasoning type of the first AI / ML can be implemented with reference to S601 and will not be further described here.

[0224] In another possible implementation, if step S601 is not executed in FIG6 , then in S602 the domain management function unit may send all capability information, such as all AI / ML capabilities, to the cross-domain management function unit. The AI / ML capabilities here can refer to the AI / ML capabilities described above and are not further described here. Optionally, in this possible implementation, the domain management function unit may send the cross-domain management function unit the AI / ML reasoning type to which the AI / ML capability information applies. In other words, the domain management function unit may indicate to the cross-domain management function unit the AI / ML reasoning type that the AI / ML capability in the sent AI / ML capability information can be used. The AI / ML reasoning type here can refer to the AI / ML reasoning type described above and are not further described here. For example, the domain management function unit may send the cross-domain management function unit AI / ML capability type including load analysis capability. The domain management function unit may send the cross-domain management function unit the AI / ML reasoning type to which the AI / ML capability applies, such as ES (NES). In other words, the domain management function unit may indicate to the cross-domain management function unit that the load analysis capability can be used for ES (NES).

[0225] In one example, the request and reporting of the above-mentioned capability information shown in Figure 6 can be implemented through existing object classes (information object class, IOC), such as: DMRO function (DMROFunction), DLBO function (DLBOFunction), DES function (DESManagementFunction), AI / ML inference capability (AiMlInferenceCapability), ES's AI / ML capability (AiMlESCapability), MO's AI / ML capability (AiMlMOCapability), LB's AI / ML capability (AiMlLBCapability), MDA function (MDAFunction), MDS request (MDARequest), AnLF function (AnLFFunction), etc., or can also be implemented through a newly defined object class (such as SONFunction), or the capability information can be implemented through a newly defined data type (such as aIMLManagementInfomation), which is not limited in this application.

[0226] For example, the attributes of the above object classes are described below:

[0227] Table 1: A DMRO function (DMROFunction< <ioc>>) attributes:

[0228] Table 1 shows the relevant properties of the DMRO function.

[0229] Exemplarily, in S602, the domain management function unit may send the AI / ML capability information of the DMRO to the cross-domain management function unit through the attributes shown in Table 1. Exemplarily, the domain management function unit may indicate the AI / ML inference capabilities supported by the DMRO to the cross-domain management function unit through the attribute 'supportedMLInferenceCapabilityList'. Exemplarily, the domain management function unit may indicate the AI / ML simulation capabilities supported by the DMRO to the cross-domain management function unit through the attribute 'supportedMLEmulationCapabilityList'.

[0230] Similarly, the related attributes of DLBO function (DLBOFunction) and (DESManagementFunction) can also be implemented with reference to Table 1, which will not be described in detail in this application.

[0231] Through Table 1, the domain management functional unit can indicate AI / ML capability information of one or more reasoning types to the cross-domain management functional unit.

[0232] It should be noted that Table 1 shows the coexistence of AI / ML reasoning and AI / ML simulation capabilities. In reality, these capabilities can exist separately. In other words, the DMRO function may only support AI / ML reasoning or only support AI / ML simulation. Similarly, in the following tables, AI / ML reasoning and AI / ML simulation capabilities can exist simultaneously or separately, and this is not repeated here.

[0233] Table 2: AI / ML reasoning function of a SON (SONFunction< <ioc>>)

[0234] Table 2 shows the relevant attributes of SON.

[0235] For example, in S602, the domain management functional unit may indicate the AI / ML inference capabilities supported by the SON to the cross-domain management functional unit through the attribute 'supportedAIMLInferenceCapabilityList'. For example, the domain management functional unit may indicate the AI / ML simulation capabilities supported by the SON to the cross-domain management functional unit through the attribute 'supportedAIMLEmulationCapabilityList'.

[0236] Similarly, the related attributes of the MDA function and the AnLF function (AnLFFunction) can be implemented with reference to Table 2, which will not be described in detail in this application.

[0237] Through Table 2, the domain management functional unit can indicate one or more types of AI / ML capability information to the cross-domain management functional unit.

[0238] Table 3: An AI / ML inference capability (AiMlInferenceCapability< <ioc>>)

[0239] Table 3 shows the relevant attributes of AI / ML inference capability (AiMlInferenceCapability).

[0240] For example, in S602, the domain management function unit may indicate the AI / ML inference capabilities supported by the domain management function unit to the cross-domain management function unit through the attribute 'supported AI / ML inference capabilities (supportedMLInferenceCapabilityList)'. For example, the domain management function unit may indicate the AI / ML simulation capabilities supported by the domain management function unit to the cross-domain management function unit through the attribute 'supportedAI / ML simulation capabilities (supportedMLEmulationCapabilityList)'.

[0241] Through Table 3, the domain management functional unit can indicate all AI / ML capability information of the domain management functional unit to the cross-domain management functional unit.

[0242] Table 4: AI / ML reasoning capabilities of a MO (AiMlMOCapability< <ioc>>)'s related properties:

[0243] Table 4 shows the relevant attributes of the MO function.

[0244] For example, in S602, the domain management function unit may indicate the AI / ML inference capabilities supported by the MO to the cross-domain management function unit through the attribute 'MO supported AI / ML inference capabilities (supportedAMLInferenceCapabilityList)'. For example, the domain management function unit may indicate the AI / ML simulation capabilities supported by the MO to the cross-domain management function unit through the attribute 'MO supported AI / ML simulation capabilities (supportedMLEmulationCapabilityList').

[0245] Through Table 4, the domain management functional unit may indicate the AI / ML capability information of one or more reasoning types of the domain management functional unit to the cross-domain management functional unit.

[0246] The supported AI / ML inference capabilities (supportedMLInferenceCapabilityList) shown in Tables 1 to 4 above can be indicated by the related attributes in Table 5 below.

[0247] Table 5: A supported AI / ML reasoning capability (SupportedMLCapabilityList<<data type> >)

[0248] Related attributes of the supported AI / ML reasoning capabilities are shown in Table 5. That is, the supported AI / ML reasoning capabilities shown in Tables 1 to 4 can be indicated by the AI / ML capability type and AI / ML reasoning type in Table 5.

[0249] Similarly, the supported AI / ML simulation capabilities (supportedMLEmulationCapabilityList)' shown in Tables 1 to 4 can be indicated by the related attributes shown in Table 6.

[0250] Table 6: A supported AI / ML simulation capability (SupportedMLEmulationCapabilityList<<data type> >)

[0251] Related attributes of the supported AI / ML simulation capabilities are shown in Table 6. That is, the supported AI / ML simulation capabilities shown in Tables 1 to 4 can be indicated by the AI / ML capability type and AI / ML reasoning type in Table 5.

[0252] Based on the solution shown in Figure 6, the cross-domain management functional unit can obtain the AI / ML capability information of the domain management functional unit, thereby enabling management and control of the AI / ML capabilities of the domain management functional unit. In one possible scenario, the cross-domain management functional unit can obtain AI / ML capability information of one or more reasoning types, thereby enabling management and control of the AI / ML capabilities of one or more reasoning types.

[0253] The following describes a method for managing AI / ML capabilities by a cross-domain management functional unit in an embodiment of the present application in conjunction with Figure 7. Referring to Figure 7, an exemplary flow chart of a method for managing machine model reasoning capabilities provided in an embodiment of the present application may include the following operations.

[0254] S701: The cross-domain management function unit sends first information to the domain management function unit.

[0255] Correspondingly, the domain management function unit receives the first information from the cross-domain management function unit.

[0256] Optionally, the cross-domain management function unit may send the first information to the domain management function unit according to the AI / ML capability information of the domain management function unit in S602.

[0257] Among them, the first information may indicate the AI / ML capability corresponding to the AI / ML reasoning. In some embodiments, the AI / ML capability corresponding to the AI / ML reasoning can be understood as the AI / ML capability type corresponding to the AI / ML reasoning, that is, the first information may indicate the AI / ML capability type corresponding to the AI / ML reasoning. The domain management function unit may execute the AI / ML reasoning corresponding to the AI / ML capability type to obtain the reasoning result of the AI / ML capability. In one possible case, the first information may be carried in an inference request or a simulation request, or carried in an existing SON function object class, an MDArequest object class, an NWDAF information object class or an AIML reasoning function object class, or a newly defined object class, which is not limited in this application.

[0258] In some embodiments, the first information indicates AI / ML capabilities, and the AI / ML capabilities may include one or more of traffic analysis capabilities, coverage analysis capabilities, mobility analysis capabilities, load analysis capabilities, fault analysis capabilities, network slicing throughput analysis capabilities, slice load analysis capabilities, network slicing traffic prediction analysis capabilities, service experience analysis capabilities, congestion analysis capabilities, energy efficiency analysis capabilities, or energy consumption analysis capabilities.

[0259] Optionally, in the embodiment shown in Figure 7, the cross-domain management function unit may also send the AI / ML inference type of the above-mentioned AI / ML capability to the domain management function unit. It is understandable that the AI / ML inference type may be indicated in the same message as the AI / ML capability, or may be indicated in different messages. This application does not make specific limitations. Exemplarily, the first information may include the AI / ML capability and the AI / ML inference type. In some embodiments, the AI / ML inference type may include at least one of the following: the MDA inference type, the SON inference type, the NWDAF inference type, or the RAN intelligence inference type. The specific definition of the AI / ML inference type here can refer to the inference type (InferenceType) defined in section 7.5.1 of 3GPP TS 28.105 V18.2.0 version, and this application will not go into details here.

[0260] In some embodiments, the first information includes the AI / ML reasoning type and the AI / ML capabilities available for the AI / ML reasoning type. The domain management functional unit can then execute the function corresponding to the AI / ML reasoning type and perform AI / ML reasoning using the available AI / ML capabilities to obtain an inference result. It is understood that the inference result can be used to execute the function corresponding to the AI / ML reasoning type.

[0261] In one example, the indication of the AI / ML capability shown in FIG7 can be implemented through existing IOCs, such as: DMRO function (DMROFunction), DLBO function (DLBOFunction), DES function (DESManagementFunction), AI / ML reasoning capability (AiMlInferenceCapability), ES AI / ML capability (AiMlESCapability), MO AI / ML capability (AiMlMOCapability), LB AI / ML capability (AiMlLBCapability), MDA function (MDAFunction), MDS request (MDARequest), AnLF function (AnLFFunction), etc., or can also be implemented through newly defined object classes, which are not limited in this application. For example, the attributes of the above-mentioned object classes are described below:

[0262] Table 7: A DMRO function (DMROFunction< <ioc>>) attributes:

[0263] Table 7 shows the relevant attributes of the DMRO function.

[0264] Exemplarily, in S701, the cross-domain management functional unit may indicate the AI / ML capabilities of the DMRO to the domain management functional unit through some attributes shown in Table 7. Exemplarily, the first information may carry the attribute 'available AI / ML inference capabilities (availableMLinferenceCapabilityList)', send the AI / ML inference capabilities of the DMRO to the domain management functional unit, and instruct the domain management functional unit to perform AI / ML inference of the AI / ML inference capabilities of the DMRO. Exemplarily, the first information may carry the attribute 'available AI / ML simulation capabilities (availableMLEmulationCapabilityList)', send the AI / ML simulation capabilities of the DMRO to the domain management functional unit, and instruct the domain management functional unit to perform AI / ML inference simulation of the AI / ML simulation capabilities of the DMRO.

[0265] Similarly, the related attributes of the DLBO function (DLBOFunction) and the DES function (DESManagementFunction) can also be implemented with reference to Table 7, which will not be described in detail in this application.

[0266] Through Table 7, the cross-domain management functional unit can indicate one or more AI / ML capabilities of reasoning type to the domain management functional unit, and instruct the domain management functional unit to perform AI / ML reasoning of the one or more AI / ML capabilities of reasoning type.

[0267] It should be noted that Table 1 and Table 7 can be implemented as one table or as different tables, and this application does not make any specific limitations.

[0268] Table 8: A SON function (SONFunction< <ioc>Examples of attributes indicated by AI / ML capabilities:

[0269] Table 8 shows the relevant attributes of SON.

[0270] For example, in S701, the cross-domain management function unit may indicate the AI / ML inference capability of the SON to the domain management function unit through the attribute 'available AI / ML inference capability (availableMLInferenceCapabilityList)', and instruct the domain management function unit to perform AI / ML inference of the AI / ML inference capability of the SON. For example, the cross-domain management function unit may indicate the AI / ML simulation capability of the SON to the domain management function unit through the attribute 'availableMLEmulationCapabilityList', and instruct the domain management function unit to perform AI / ML inference simulation of the AI / ML simulation capability of the SON.

[0271] Similarly, the related attributes of the MDA function and the AnLF function (AnLFFunction) can be implemented with reference to Table 8, which will not be described in detail in this application.

[0272] Through Table 8, the cross-domain management functional unit can indicate one or more AI / ML capabilities of reasoning types to the domain management functional unit, instructing the domain management functional unit to perform AI / ML reasoning for one or more AI / ML capabilities of reasoning types. It should be noted that Table 2 and Table 8 can be implemented as a single table or as separate tables, and this application does not impose specific limitations.

[0273] Table 9: An AI / ML inference capability (AiMlInferenceCapability< <ioc>>)

[0274] Table 9 shows the relevant attributes of AI / ML inference capability (AiMlInferenceCapability).

[0275] Exemplarily, in S701, the cross-domain management function unit can indicate the AI / ML reasoning capability to the domain management function unit through the attribute 'available AI / ML inference capability (availableMLInferenceCapabilityList)', and instruct the domain management function unit to perform AI / ML reasoning of the AI / ML reasoning capability. Exemplarily, the cross-domain management function unit can indicate the AI / ML simulation capability to the domain management function unit through the attribute 'availableAI / ML simulation capability (availableMLEmulationCapabilityList)', and instruct the domain management function unit to perform AI / ML reasoning simulation of the AI / ML simulation capability. That is, the cross-domain management function unit can use these two attributes to instruct the domain management function unit to perform AI / ML reasoning of the AI / ML capability, rather than being limited to AI / ML reasoning of the AI / ML capability of a certain reasoning type.

[0276] Through Table 9, the cross-domain management functional unit can indicate AI / ML capabilities to the domain management functional unit, instructing the domain management functional unit to perform AI / ML reasoning of the AI / ML capabilities. In one possible scenario, through Table 9, the cross-domain management functional unit can also indicate one or more inference types of AI / ML capabilities to the domain management functional unit, instructing the domain management functional unit to perform AI / ML reasoning of one or more inference types of AI / ML capabilities.

[0277] It should be noted that Table 3 and Table 9 can be implemented as one table or as different tables, and this application does not make any specific limitations.

[0278] Table 10: A MO function (AiMlMOCapability< <ioc>Examples of attributes related to AI / ML capabilities:

[0279] Table 10 shows the relevant attributes of the MO function.

[0280] Exemplarily, in S701, the cross-domain management function unit may indicate the MO's AI / ML reasoning capabilities to the domain management function unit through the attribute 'availableMLInferenceCapabilityList', and instruct the domain management function unit to perform AI / ML reasoning of the MO's AI / ML reasoning capabilities. Exemplarily, the cross-domain management function unit may indicate the MO's AI / ML simulation capabilities to the domain management function unit through the attribute 'availableMLEmulationCapabilityList', and instruct the domain management function unit to perform AI / ML reasoning simulation of the MO's AI / ML simulation capabilities.

[0281] Through Table 10, the cross-domain management functional unit can indicate one or more AI / ML capabilities of reasoning types to the domain management functional unit, instructing the domain management functional unit to perform AI / ML reasoning for one or more AI / ML capabilities of reasoning types. It should be noted that Table 4 and Table 10 can be implemented as a single table or as separate tables, and this application does not impose specific limitations.

[0282] The available AI / ML inference capabilities (availableMLinferenceCapabilityList) shown in Tables 7 to 10 above can be indicated by the related attributes in Table 11 below.

[0283] Table 11: An available AI / ML inference capability (availableMLinferenceCapabilityList<<data type> >)

[0284] Related attributes of the usable AI / ML reasoning capabilities are shown in Table 11. That is, the usable AI / ML reasoning capabilities shown in Tables 7 to 10 can be indicated by the AI / ML capability type and AI / ML reasoning type in Table 5.

[0285] Similarly, the available AI / ML simulation capabilities (availableMLEmulationCapabilityList)' shown in Tables 7 to 10 can be indicated by the related attributes shown in Table 12.

[0286] Table 12: An available AI / ML simulation capability (availableMLEmulationCapabilityList<<data type> >)

[0287] Related attributes of the available AI / ML simulation capabilities are shown in Table 12. That is, the available AI / ML simulation capabilities shown in Tables 7 to 10 can be indicated by the AI / ML capability type and AI / ML reasoning type in Table 12.

[0288] It is understandable that the AI / ML capabilities mentioned in S701 can be general or use case-specific, and can be implemented with reference to the previous related descriptions, which will not be repeated here.

[0289] S702: The domain management functional unit performs AI / ML reasoning of AI / ML capabilities.

[0290] In S702, the domain management function unit performs AI / ML reasoning on the AI / ML capability and obtains a reasoning result of the AI / ML capability. It can be understood that the domain management function unit performs AI / ML reasoning on the AI / ML capability, which can be understood as the domain management function unit performs AI / ML reasoning on the AI / ML capability type and obtains a reasoning result of the AI / ML capability type. For example, the first information can indicate one or more of the aforementioned traffic analysis capability, coverage analysis capability, mobility analysis capability, load analysis capability, fault analysis capability, network slice throughput analysis capability, slice load analysis capability, network slice traffic prediction analysis capability, service experience analysis capability, energy efficiency analysis capability, or energy consumption analysis capability. Then, the domain management function unit can perform AI / ML reasoning on the first information indicating one or more of the aforementioned traffic analysis capability, coverage analysis capability, mobility analysis capability, load analysis capability, fault analysis capability, network slice throughput analysis capability, slice load analysis capability, network slice traffic prediction analysis capability, service experience analysis capability, energy efficiency analysis capability, or energy consumption analysis capability.

[0291] Optionally, the cross-domain management function unit in S701 may further send an AI / ML reasoning type corresponding to the AI / ML capability to the domain management function unit. For example, if the first information includes the AI / ML capability and the AI / ML reasoning type, the domain management function unit may execute the AI / ML capability of the AI / ML reasoning type. The AI / ML reasoning type here includes at least one of the following: an MDA reasoning type, a SON reasoning type, an NWDAF reasoning type, or a radio access network intelligence (RAN intelligence) reasoning type.

[0292] Exemplarily, the first information indicates the load analysis capability, and the cross-domain management function unit sends the AI / ML reasoning type corresponding to the load analysis capability to the domain management function unit. If the AI / ML reasoning type is ES (NES), the domain management function unit can perform AI / ML reasoning of the ES (NES) load analysis capability.

[0293] In some embodiments, the cross-domain management functional unit may trigger the activation of a function corresponding to an AI / ML reasoning type. For example, the cross-domain management functional unit may trigger the domain management functional unit to activate or execute a function corresponding to at least one of an MDA reasoning type, a SON reasoning type, an NWDAF reasoning type, or a radio access network intelligence (RAN intelligence) reasoning type.

[0294] It should be noted that the step of triggering the cross-domain management function unit to enable the function corresponding to the AI / ML reasoning type can be performed before S701, or after S701 and before S702, or can be performed together with S701, and this application does not make specific restrictions. Then, in S702, the domain management function unit can enable the function corresponding to the AI / ML reasoning type and perform AI / ML reasoning of the AI / ML capability indicated by the first information, thereby obtaining an inference result.

[0295] S703: The domain management function unit sends the inference result of AI / ML inference to the cross-domain management function unit.

[0296] Accordingly, the cross-domain management function unit receives the inference result from the domain management function unit. For example, the cross-domain management function unit may receive the inference result from the domain management function unit.

[0297] In one possible scenario, the inference result may be carried in an inference report. For example, the domain management functional unit may send an inference report of AI / ML inference to the cross-domain management functional unit, and the inference report may carry the inference result.

[0298] Optionally, the domain management functional unit may also send one or more of the reasoning status (such as one of success, in progress, or failure) and the reasoning time (such as one or more of the start time, end time, or duration) to the cross-domain management functional unit. It is understandable that one or more of the reasoning status or reasoning time may be sent in the same message as the reasoning result, such as being sent in a reasoning report. Alternatively, one or more of the reasoning status or reasoning time may be sent in different messages from the reasoning result, which is not specifically limited in this application.

[0299] In this embodiment of the present application, the inference result may be the inference result of the AI / ML capability indicated by the first information.

[0300] For example, if the first information indicates the AI / ML capability of the MRO (MO), the inference result may include one or more of a cell identifier, a base station identifier, a cell individual offset (CIO), a time trigger, or a handover trigger.

[0301] Exemplarily, if the first information indicates the AI / ML capability of the MLB (LB), the inference result may include one or more of a cell identifier, a base station identifier, or a CIO.

[0302] Exemplarily, if the first information indicates the AI / ML capability of the node ES (NES), the inference result may include one or more of a cell identifier, a base station identifier, or information of a shut-down cell, or information of a shut-down carrier, or information of a shut-down time slot.

[0303] The reasoning results of the MDA reasoning type can refer to one or more of the corresponding outputs in TS 28.104 section 8.4, which will not be described in detail in this application.

[0304] In one example, the domain management functional unit may also send the reasoning type of AI / ML to which the reasoning result is applicable to the cross-domain management functional unit, and the reasoning type of AI / ML includes at least one of the following: the reasoning type of MDA, the reasoning type of SON, the reasoning type of NWDAF, or the reasoning type of radio access network intelligence (RAN intelligence). It can be understood that the reasoning type of AI / ML can be understood as the reasoning type of AI / ML capability can use the reasoning result. It should be noted that the reasoning type of AI / ML can be carried in the same message as the reasoning result, such as in the reasoning report, or it can be carried in a different message from the reasoning result, and this application does not make specific limitations.

[0305] Optionally, before S703 , the cross-domain management function unit may send an inference result request to the domain management function unit, requesting or instructing the domain management function unit to send an inference result or an inference report.

[0306] The following describes a method for managing and controlling the machine model reasoning capabilities provided in an embodiment of the present application in conjunction with specific use cases.

[0307] Exemplarily, taking the mobility optimization capability use case as an example, AI / ML capabilities can be attached to MRO or distributed MRO. Referring to Figure 8, an exemplary flowchart of a method for controlling machine model reasoning capabilities provided in an embodiment of the present application may include the following operations. In the embodiment shown in Figure 8, the cross-domain management function unit is an NMS network management system (network management system, NMS), and the domain management function unit is a domain MnF as an example for description.

[0308] S801: The NMS turns on DMRO.

[0309] In S801, the NMS can trigger the DMRO to be enabled, that is, the NMS can trigger the DMRO function to be enabled.

[0310] It is understandable that the NMS may send an instruction to trigger the activation of DMRO to the domain MnF, and the domain MnF may instruct the base station to activate DMRO.

[0311] S802: The NMS sends second information to the domain MnF.

[0312] Correspondingly, the domain MnF receives the second information from the NMS. This step is optional.

[0313] The second information may be implemented with reference to S601. In one possible scenario, the second information may request the AI / ML capability information of the DMRO of the domain MnF. For example, the second information may be a request for the AI / ML reasoning capability of the DMRO.

[0314] S803: The domain MnF sends the AI / ML capability information of the DMRO to the NMS.

[0315] Correspondingly, the NMS receives the AI / ML capability information of the DMRO from the domain MnF.

[0316] In S803 , the domain MnF may respond to the second information and send the AI / ML capability information of the DMRO to the NMS.

[0317] In one possible scenario, when AI / ML capabilities are universal, the domain MnF can directly send capability indications, such as DMRO supports AIML reasoning capabilities or DMRO supports AIML reasoning simulation capabilities. For example, the domain MnF can send DMRO supports mobility analysis capabilities, traffic analysis capabilities, or coverage analysis capabilities.

[0318] In another possible scenario, when AI / ML capabilities are at the use case granularity, the domain MnF can send the AI / ML capabilities possessed by the DMRO to the NMS, such as coverage analysis capabilities, traffic analysis capabilities, and mobile performance analysis capabilities.

[0319] S804: The NMS sends first information to the domain MnF.

[0320] Correspondingly, the domain MnF receives the first information from the NMS, wherein the first information may be implemented with reference to S601.

[0321] In S804, the NMS may select which AI / ML capabilities to activate to perform AI / ML reasoning of the DMRO based on the AI / ML capability information of the DMRO, and indicate this to the domain MnF through the first information.

[0322] In one possible scenario, if the AI / ML capability is deployed in a base station, the domain MnF may send first information to the base station to instruct the base station to perform AI / ML reasoning of the AI / ML capability.

[0323] S805: The NMS requests the domain MnF for the AI / ML reasoning result.

[0324] For example, the NMS may send an inference result request to the domain MnF, thereby requesting the domain MnF to send the inference result of the AI / ML inference.

[0325] S806: The domain MnF sends the inference result to the NMS.

[0326] Correspondingly, the NMS receives the inference results from the domain MnF.

[0327] In S806, the domain MnF may respond to the inference result request in S805 and send the inference results, such as one or more of coverage analysis results, traffic analysis results, and mobility analysis results, to the NMS. In one possible scenario, if the AI / ML capability is deployed in the base station, the domain MnF may obtain the inference results from the base station and send them to the NMS.

[0328] Exemplarily, the domain MnF sends an inference report to the NMS, which may include the inference time, thrust status, and inference result. Optionally, the inference report also includes the inference type of the inference result, that is, DMRO.

[0329] In the embodiment shown in Figure 8, the NMS can turn on DMRO and then activate AI / ML reasoning. Below, in conjunction with Figure 9, the scenario in which the NMS first activates AI / ML reasoning and then turns on DMRO is introduced. Referring to Figure 9, an exemplary flowchart of a method for managing and controlling machine model reasoning capabilities provided in an embodiment of the present application may include the following operations. In the embodiment shown in Figure 9, the cross-domain management function unit is NMS, and the domain management function unit is domain MnF as an example for description.

[0330] S901: The NMS sends second information to the domain MnF.

[0331] Correspondingly, the domain MnF receives the second information from the NMS, wherein the second information may be implemented with reference to S601.

[0332] For example, the second information may request the AI / ML capability information of the domain MnF. It is understandable that the difference between the second information of S901 and the second information of S801 is that the second information of S901 may request the AI / ML capability information of the domain MnF and is not limited to the AI / ML capability information of the DMRO.

[0333] This step is optional.

[0334] S902: The domain MnF sends AI / ML capability information to the NMS.

[0335] Correspondingly, the NMS receives AI / ML capability information from the domain MnF.

[0336] S902 may be implemented with reference to S602. In S902, the domain MnF may send information about supported or available AI / ML capabilities to the NMS.

[0337] S903: The NMS activates AI / ML capabilities to perform AI / ML reasoning.

[0338] For example, the NMS can send an inference request to the domain MnF to perform AI / ML inference.

[0339] S903 may be implemented with reference to S601. In S903, the NMS may activate the AI / ML capability of the DMRO based on the AI / ML capability information acquired in S902 to perform AI / ML reasoning of the AI / ML capability.

[0340] In one possible scenario, if the AI / ML reasoning capability is deployed in the base station, the domain MnF may send first information to the base station to instruct the base station to perform AI / ML reasoning of the AI / ML capability.

[0341] S904: The NMS turns on DMRO and indicates the AI / ML capability.

[0342] In S904, the NMS may indicate to the domain MnF which AI / ML capabilities of the DMRO to use based on the acquired AI / ML capability information. In other words, in S904, the NMS may indicate to the domain MnF which AI / ML capabilities of the DMRO to use.

[0343] S905 to S906 may refer to S805 and S806.

[0344] Based on the concepts of the above embodiments, referring to FIG10 , an embodiment of the present application provides a communication device 1000, which includes a processing unit 1001 and a transceiver unit 1002. The device 1000 can be a communication device, or can be a device applied to a communication device and capable of supporting the communication device to execute a method for notifying a quality of service parameter.

[0345] The transceiver unit may also be referred to as a transceiver module, transceiver, transceiver, transceiver device, etc. The processing unit may also be referred to as a processor, processing board, processing unit, processing device, etc. Optionally, the device used to implement the receiving function in the transceiver unit may be considered a receiving unit. It should be understood that the transceiver unit is used to perform the sending and receiving operations of the communication device in the above method embodiments, and the device used to implement the sending function in the transceiver unit is considered a sending unit, that is, the transceiver unit includes a receiving unit and a sending unit.

[0346] In addition, it should be noted that if the device is implemented using a chip / chip circuit, the transceiver unit can be an input and output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operations) and output operations (corresponding to the aforementioned sending operations); the processing unit is an integrated processor or microprocessor or integrated circuit.

[0347] The following describes in detail an embodiment in which the apparatus 1000 is applied to a first communication apparatus and a second communication apparatus.

[0348] For example, when the apparatus 1000 is applied to the first communication apparatus, operations performed by each unit thereof are described in detail.

[0349] In an optional implementation, the communication device 1000 can be applied to a first communication device to execute the method executed by the first communication device, for example, the method executed by the terminal device in the embodiments shown in FIG. 6 to FIG. 9 .

[0350] For example, transceiver unit 1002 is configured to receive first information from a second communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. Processing unit 1001 is configured to perform AI / ML reasoning based on the AI / ML capabilities and obtain an inference result. Transceiver unit 1002 is further configured to transmit the inference result to the second communication device.

[0351] For another example, the processing unit 1001 is configured to determine supported AI / ML capability information. The transceiver unit 1002 is configured to send the supported AI / ML capability information to the second communication device. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control the one or more AI / ML capabilities.

[0352] For example, when the apparatus 1000 is applied to the second communication apparatus, operations performed by each unit thereof are described in detail.

[0353] In an optional implementation, the communication device 1000 may be applied to a second communication device to execute the method executed by the aforementioned second communication device, for example, the method executed by the second communication device in the embodiments shown in FIG. 6 to FIG. 9 .

[0354] For example, processing unit 1001 is configured to generate first information, the first information including the AI / ML capability corresponding to the AI / ML reasoning. Transceiver unit 1002 is configured to send the first information to a first communication device. Transceiver unit 1002 is also configured to receive an inference result of the AI / ML reasoning from the first communication device.

[0355] For another example, the transceiver unit 1002 is configured to receive AI / ML capability information supported by the first communication device. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control the one or more AI / ML capabilities. The processing unit 1001 is configured to manage and control the one or more AI / ML capabilities.

[0356] Based on the concepts of the embodiments, as shown in FIG11 , an embodiment of the present application provides a communication device 1100. The communication device 1100 includes a processor 1110. Optionally, the communication device 1100 may further include a memory 1120 for storing instructions executed by the processor 1110, or storing input data required by the processor 1110 to execute instructions, or storing data generated after the processor 1110 executes instructions. The processor 1110 can implement the method described in the above method embodiment using the instructions stored in the memory 1120.

[0357] Based on the concept of the embodiment, as shown in Figure 12, the embodiment of the present application provides a communication device 1200, which can be a chip or a chip system. Optionally, in the embodiment of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0358] Communication device 1200 may include at least one processor 1210 coupled to a memory. Optionally, the memory may be located within or outside the device. For example, communication device 1200 may also include at least one memory 1220. Memory 1220 stores the necessary computer programs, configuration information, computer programs or instructions, and / or data for implementing any of the aforementioned embodiments. Processor 1210 may execute the computer programs stored in memory 1220 to perform the methods of any of the aforementioned embodiments. Optionally, the memory may be integrated with the processor.

[0359] The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, and is used for information exchange between devices, units, or modules. The processor 1210 may operate in conjunction with the memory 1220. The specific connection medium between the transceiver 1230, the processor 1210, and the memory 1220 is not limited in the embodiments of the present application.

[0360] The communication device 1200 may also include a transceiver 1230, and the communication device 1200 can exchange information with other devices through the transceiver 1230. The transceiver 1230 can be a circuit, a bus, a transceiver or any other device that can be used for information exchange, or is called a signal transceiver unit. As shown in Figure 12, the transceiver 1230 includes a transmitter 1231, a receiver 1232 and an antenna 1233. In addition, when the communication device 1200 is a chip-type device or circuit, the transceiver in the communication device 1200 can also be an input and output circuit and / or a communication interface, which can input data (or receive data) and output data (or send data). The processor is an integrated processor or microprocessor or integrated circuit, and the processor can determine the output data based on the input data.

[0361] In one possible implementation, the communication device 1200 can be applied to a communication device. Specifically, the communication device 1200 can be a communication device, or a device capable of supporting a communication device to implement the functions of the first communication device or the second communication device in any of the above-mentioned embodiments. The memory 1220 stores the necessary computer programs, computer programs, instructions, and / or data to implement the functions of the first communication device or the second communication device in any of the above-mentioned embodiments. The processor 1210 can execute the computer program stored in the memory 1220 to perform the method performed by the first communication device or the second communication device in any of the above-mentioned embodiments.

[0362] In the embodiments of the present application, the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present application may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0363] In an embodiment of the present application, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., or a volatile memory (volatile memory), such as a random-access memory (RAM). The memory may also be any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in an embodiment of the present application may also be a circuit or any other device that can implement a storage function, for storing computer programs, computer programs or instructions and / or data.

[0364] Based on the above embodiments, referring to FIG13 , an embodiment of the present application also provides another communication device 1300, including: an input / output interface 1310 and a logic circuit 1320; the input / output interface 1310 is used to receive code instructions and transmit them to the logic circuit 1320; the logic circuit 1320 is used to run code instructions to execute the method executed by the first communication device or the second communication device in any of the above embodiments.

[0365] The following describes in detail the operations performed by the apparatus 1300 when applied to the first communication apparatus or the second communication apparatus.

[0366] In an optional implementation, the communication device 1300 may be applied to a first communication device to execute the method executed by the first communication device, for example, the method executed by the first communication device in the embodiments shown in FIG. 6 to FIG. 9 .

[0367] For example, input / output interface 1310 is configured to input first information from a second communication device, where the first information includes AI / ML capabilities corresponding to AI / ML reasoning. Logic circuit 1320 is configured to perform AI / ML reasoning based on the AI / ML capabilities and obtain reasoning results. Input / output interface 1310 is also configured to output the reasoning results.

[0368] For another example, logic circuit 1320 is configured to determine supported AI / ML capability information. Input / output interface 1310 is configured to output the supported AI / ML capability information. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control the one or more AI / ML capabilities.

[0369] Since the communication device 1300 provided in this embodiment can be applied to the first communication device and execute the method executed by the first communication device, the technical effects that can be obtained can refer to the above method embodiments and will not be described in detail here.

[0370] [Corrected 19.02.2025 according to Rule 91] In an optional implementation, the communication device 1300 can be applied to a second communication device to execute the method executed by the above-mentioned second communication device, specifically, for example, the method executed by the second communication device in the embodiments shown in Figures 6 to 9 above.

[0371] For example, logic circuit 1320 is configured to generate first information, including the AI / ML capability corresponding to the AI / ML reasoning. Input / output interface 1310 is configured to output the first information. Input / output interface 1310 is also configured to input the AI / ML reasoning result from the first communication device.

[0372] For another example, the input / output interface 1310 is configured to input AI / ML capability information supported by the first communication device. The AI / ML capability information indicates one or more AI / ML capabilities. The AI / ML capability information is used to manage and control the one or more AI / ML capabilities. The logic circuit 1320 is configured to manage and control the one or more AI / ML capabilities.

[0373] Since the communication device 1300 provided in this embodiment can be applied to a second communication device to execute the method executed by the aforementioned second communication device, the technical effects that can be obtained can be referred to the aforementioned method embodiment and will not be described in detail here.

[0374] Based on the above embodiments, embodiments of the present application further provide a communications system, comprising at least one first core network and at least one second core network. Optionally, the communications system further comprises at least one terminal device. The technical effects achieved can be referenced with reference to the above method embodiments and are not further elaborated here.

[0375] Based on the above embodiments, embodiments of the present application further provide a computer-readable storage medium storing a computer program or instructions. When the instructions are executed, the method performed by the communication device in any of the above embodiments is implemented. The computer-readable storage medium may include any medium capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0376] To implement the functions of the communication devices of Figures 9 to 13 above, embodiments of the present application further provide a chip including a processor for supporting the communication device in implementing the functions of the first or second communication devices in the above method embodiments. In one possible design, the chip is connected to or includes a memory, which is used to store computer programs, instructions, and data necessary for the terminal device or network device.

[0377] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0378] The present application is described with reference to the flow chart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by a computer program or instruction. These computer programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow chart flow or multiple flows and / or one box or multiple boxes of the block diagram.

[0379] These computer programs or instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0380] These computer programs or instructions may also be loaded onto a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes of the flowchart and / or one or more blocks of the block diagram. Obviously, those skilled in the art may make various changes and modifications to the embodiments of the present application without departing from the scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these changes and variations.< / ioc> < / ioc> < / ioc> < / ioc> < / ioc> < / ioc> < / ioc> < / ioc>

Claims

1. A method for controlling the reasoning capability of a machine model, characterized in that: include: receiving AI / ML capability information supported by the first communication device, the AI / ML capability information indicating one or more AI / ML capabilities; The AI / ML capability information is used for the management and control of the one or more AI / ML capabilities.

2. The method according to claim 1, characterized in that Also includes: Receive the AI / ML reasoning type applicable to the AI / ML capability information; the reasoning type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

3. The method according to claim 1 or 2, characterized in that Also includes: Sending second information to the first communication device, where the second information is used to request the first communication device to send the AI / ML capability information.

4. The method according to claim 3, characterized in that The second information instructs the first communication device to send AI / ML capability information supporting one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

5. The method according to any one of claims 1 to 4, characterized in that: The one or more AI / ML capabilities include one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

6. The method according to any one of claims 1 to 5, characterized in that: Also includes: Sending first information to the first communication device, the first information including an AI / ML capability corresponding to the AI / ML reasoning; wherein the one or more AI / ML capabilities include the AI / ML capability corresponding to the AI / ML reasoning; Receive an inference result of the AI / ML inference from the first communication device.

7. The method according to claim 6, characterized in that The first information is used to request the first communication device to perform the AI / ML reasoning of the AI / ML capability corresponding to the AI / ML reasoning.

8. The method according to claim 6 or 7, characterized in that Also includes: Sending the inference type of the AI / ML capability, where the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

9. The method according to any one of claims 6 to 8, characterized in that: Also includes: Receive one or more of inference status or inference time.

10. The method according to any one of claims 6 to 9, characterized in that: The inference result also includes an inference type of the inference result, and the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

11. The method according to any one of claims 6 to 10, characterized in that: The inference results include one or more of the following: Cell personality offset, cell identifier, network device identifier, time trigger, handover trigger, information about shutting down cells, shutting down carriers, or shutting down time slots.

12. A method for controlling the reasoning capability of a machine model, characterized in that: include: sending supported AI / ML capability information to the second communication device, the AI / ML capability information indicating one or more AI / ML capabilities; The AI / ML capability information is used for managing and controlling the one or more AI / ML capabilities of the second communication device.

13. The method according to claim 12, characterized in that Also includes: Sending the AI / ML reasoning type to which the AI / ML capability information is applicable to the second communication device; the reasoning type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

14. The method according to claim 12 or 13, characterized in that Also includes: Second information is received from the second communication device, where the second information is used to request the first communication device to send the AI / ML capability information.

15. The method according to claim 14, characterized in that The second information instructs the first communication device to send AI / ML capability information supporting one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

16. The method according to any one of claims 12 to 15, characterized in that: The one or more AI / ML capabilities include one or more of the following: traffic analysis capability, traffic prediction capability, mobility analysis capability, mobility prediction capability, load analysis capability, load prediction capability, energy consumption analysis capability, or energy consumption prediction capability.

17. The method according to any one of claims 12 to 16, characterized in that: Also includes: receiving first information from the second communication device, the first information including an AI / ML capability corresponding to the AI / ML reasoning; wherein the one or more AI / ML capabilities include the AI / ML capability corresponding to the AI / ML reasoning; Sending the inference result of the AI / ML inference to the second communication device.

18. The method according to claim 17, characterized in that The first information is used to request the first communication device to perform the AI / ML reasoning of the AI / ML capability corresponding to the AI / ML reasoning.

19. The method according to claim 17 or 18, characterized in that Also includes: Receive an inference type of the AI / ML capability, where the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

20. The method according to any one of claims 17 to 19, characterized in that: Also includes: Send one or more of the inference status or inference time.

21. The method according to any one of claims 17 to 20, characterized in that: The inference result also includes an inference type of the inference result, and the inference type includes one or more of a management data analysis function, a mobility optimization function, a network energy saving function, or a load balancing function.

22. The method according to any one of claims 17 to 21, characterized in that: The inference results include one or more of the following: Cell personality offset, cell identifier, network device identifier, time trigger, handover trigger, information about shutting down cells, shutting down carriers, or shutting down time slots.

23. A communication device, characterized in that: The method comprises a unit for executing the method according to any one of claims 1 to 11, or comprises a unit for executing the method according to any one of claims 12 to 22.

24. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when called by an electronic device, enable the electronic device to execute the method according to any one of claims 1 to 11, or enable the electronic device to execute the method according to any one of claims 12 to 22.

25. A communication system, characterized in that: The invention comprises an apparatus for executing the method according to any one of claims 1 to 11 and an apparatus for executing the method according to any one of claims 12 to 22.

26. A chip system, characterized in that: The chip system includes: Communication interface; A processor, configured to call and execute the instruction through the communication interface, so that the device equipped with the chip system executes the method as described in any one of claims 1 to 11, or so that the device equipped with the chip system executes the method as described in any one of claims 12 to 22.

27. A computer program product, characterized in that The method comprises computer-executable instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 11, or enable the electronic device to execute the method according to any one of claims 12 to 22.

Images