Communication method and communication apparatus

Abstract

The present application discloses a communication method and a communication apparatus. The method relates to the technical field of communications. The method comprises: a second node located on a network side sends an activation indication to a first node located on the network side; and after the first node receives the activation indication, the first node generates first information on the basis of an AI function, and then sends the first information. The activation indication is used for indicating activation of a first node, and the first node has an artificial intelligence (AI) function. In the described method, a first node has a built-in AI function, and other nodes, without a built-in AI function, can acquire an AI service by means of the first node. Moreover, in a scenario in which an AI function is limited, communication functions of other nodes without a built-in AI function can be prevented from being affected.

Description

Communication method and communication apparatus

[0001] This application claims priority to the Chinese Patent Application No. 202410970527.0, filed on July 18, 2024, entitled “Communication method and communication apparatus”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

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

[0003] Artificial intelligence (AI) is a technology that simulates human brain to perform complex calculations. AI is applied to wireless communication to improve network performance and user experience by intelligently collecting and analyzing data. For AI-based application scenarios in the air interface, the standard discusses UE-sided (user equipment-sided) models, NW-sided (network-sided) models, and two-sided models. For the UE-sided model, the model can be located at the modem on the UE side. For the NW-sided model, the model can be located at the network node on the side of the access network device such as the CU (central unit), DU (distributed unit), or RU (radio unit), or located at the network node on the side of the core network such as the NWDAF (network data analytics function), or located in the OAM (operations, administration and maintenance) system. For the two-sided model, the model can be located on the UE side or the network side, and the two-sided models cooperate to complete the requirements.

[0004] When each node in the network interacts with AI information, it needs to be based on a communication protocol stack. The AI information refers to information related to AI. AI and communication protocol stack are deeply bound to each other. It can be understood that the interaction of AI information needs to be based on a communication protocol stack, and the design of the communication protocol also needs to consider the management function of AI information or the specification of AI information interaction process, etc. Nowadays, the supervision of AI function in some areas is becoming more and more strict. In some areas, devices with AI function may be restricted from using AI function. For example, an access network device has AI function and is located in an area where AI function is restricted. Because AI and communication protocol stack are deeply bound to each other, the access network device will not be able to communicate normally based on the communication protocol stack. SUMMARY

[0005] The present application provides a communication method and a communication device. The first node has an AI function, and other nodes without an AI function can obtain AI services through the first node. In addition, the nodes without an AI function can avoid the impact on communication function in an area where AI function is restricted.

[0006] In a first aspect, the present application provides a communication method, which can be executed by a first node located at a network side. The first node can refer to the first node itself, or a processor, a module, a chip, or a chip system in the first node that implements the method. The method includes receiving an activation indication from a second node located at the network side, generating first information based on an artificial intelligence (AI) function, and sending the first information. The activation indication is used to indicate that the first node is activated, and the first node has an AI function.

[0007] Based on the method described in the first aspect, the first node has an AI function, and other nodes without an AI function can obtain AI services through the first node. In addition, in a scenario where AI function is restricted, the communication function of the other nodes without an AI function can be avoided.

[0008] In a possible implementation, the activation indication is used to indicate that the first node is activated, specifically: the activation indication is used to indicate that the following one or more of the first node is activated: all or part of the AI function, all or part of the protocol stack, all or part of the AI model, or all or part of the result inferred by AI that needs to be provided. By indicating the activation of specific AI function, protocol stack, AI model or result inferred by AI that needs to be provided in the first node through the activation indication, unnecessary items in the first node are avoided, which is beneficial to avoid waste of energy consumption.

[0009] In a possible implementation, the method further includes: closing the first node when a first condition is met; the first condition includes one or more of the following: receiving a first deactivation indication from the second node, the first deactivation indication being used to indicate to close the first node; or, an inference accuracy of the first node or an AI model or AI function of the first node is less than or equal to a first threshold; or, a performance gain of the first node or the AI model or AI function of the first node is less than or equal to a second threshold; or, a calculation overhead or a storage overhead of the first node or the AI model or AI function of the first node is greater than or equal to a third threshold. When the above-described condition is met, closing the first node helps to save energy consumption. Meanwhile, after the first node is closed, the other nodes can normally communicate.

[0010] In a possible implementation, the closing of the first node includes: closing one or more of the following of the first node: all or part of AI functions, all or part of protocol stacks, all or part of AI models, or all or part of results to be provided by AI inference.

[0011] In a possible implementation, the second node is an access network device or a central unit (CU).

[0012] In a possible implementation, the first information is generated based on the AI function, and specifically, the first information is generated through a first protocol layer having the AI function; and the first information is sent through the first protocol layer to a second protocol layer, and the first information is encapsulated by the second protocol layer to obtain a first data unit, and the first data unit is sent through the second protocol layer.

[0013] In a possible implementation, before receiving the activation indication from the second node located at a network side, the method further includes: sending first registration information to the second node, the first registration information including capability information of the first node, the capability information indicating that the first node has the AI function.

[0014] Optionally, the capability information indicates that the first node has an AI function, and the implementation is that the capability information indicates one or more of the following information: one or more AI use cases supported by the first node, a number of AI use cases supported by the first node, an algorithmic cost corresponding to each of the one or more AI use cases, an energy consumption corresponding to each of the one or more AI use cases, an input / output format corresponding to each of the one or more AI use cases, one or more AI functions supported by the first node, a number of AI functions supported by the first node, an algorithmic cost corresponding to each of the one or more AI functions, an energy consumption corresponding to each of the one or more AI functions, an input / output format corresponding to each of the one or more AI functions, one or more AI models supported by the first node, a number of AI models supported by the first node, an algorithmic cost corresponding to each of the one or more AI models, an energy consumption corresponding to each of the one or more AI models, an input / output format corresponding to each of the one or more AI models. Through the capability information, the node registered by the first node can determine the capability of the first node.

[0015] Optionally, the capability information is further used to indicate a total algorithmic cost supported by the first node and / or a total energy consumption supported by the first node.

[0016] In a possible implementation, the method further includes: sending, to one or more of a distributed unit (DU), a radio unit (RU), a core network device, an operations, administration and maintenance (OAM), or a RAN intelligent controller (RIC), second registration information including the capability information of the first node, or sending, through the second node, the second registration information to the one or more of the DU, the RU, the core network device, the OAM, or the RIC.

[0017] In a possible implementation, the method further includes: receiving indication information from the second node, the indication information being used to indicate that the registration with the one or more of the DU, the RU, the core network device, the OAM, or the RIC is completed.

[0018] In a possible implementation, before the first information is generated based on the AI function, the method further includes: receiving second information, the second information being used for model training or model inference; the second information including one or more of the following information: third information from the terminal device, fourth information from the core network device or the OAM, fifth information from the third node, and sixth information from the fourth node; the third node including one or more of the second node, the DU, or the RU; the fourth node having the AI function and being registered with the fifth node; the fifth node being one or more nodes other than the second node; the third information indicating one or more of the following information: AI capability information of the terminal device, computing capability of the terminal device, energy consumption of the terminal device, energy efficiency information of the terminal device, moving speed of the terminal device, moving path of the terminal device, number of antennas of the terminal device, beam weighting manner of the terminal device, service information of the terminal device, or measurement result of the terminal device; the fourth information indicating one or more of the following information: AI capability information of the core network device or the OAM, computing capability of the core network device or the OAM, or service requirement of the core network device or the OAM; the fifth information indicating one or more of the following information: AI capability information of the third node, computing capability of the third node, energy consumption of the third node, energy efficiency information of the third node, geographic location of the third node, number of antennas of the third node, beam weighting manner of the third node, resource information of the third node, or measurement result of the third node; and the sixth information indicating one or more of the following information: AI capability information of the fourth node, computing capability of the fourth node, energy consumption of the fourth node, or energy efficiency information of the fourth node. Based on this implementation, the first node can obtain more data for model training or model inference.

[0019] In a possible implementation, the first information is sent, specifically, the first information is sent by the second node to the terminal device, and the first information indicates one or more of the following: an AI use case of the terminal device, an AI function to be executed by the terminal device, or an AI model to be executed by the terminal device, an AI inference result to be provided by the terminal device, information related to lifecycle management of the AI use case of the terminal device, information related to lifecycle management of the AI function of the terminal device, or information related to lifecycle management of the AI model of the terminal device; or the first information is sent to a third node, the third node including one or more of the second node, a DU, or a RU, or the first information is sent by the second node to the third node, the third node including one or more of the DU or the RU, and the first information indicates one or more of the following: a recommended downlink beam weighting manner, a predicted optimal access beam index of the terminal device, positioning assistance information of the terminal device, location information of the terminal device, an execution manner of energy saving, an execution manner of load balancing, a path prediction result of the terminal device, a recommended execution strategy of terminal device switching, a transmission configuration of uplink and downlink data transmission, an antenna form adjustment, or a modulation and demodulation scheme configuration; or the first information is sent to a fourth node, or the first information is sent by the second node and a fifth node to the fourth node, the fourth node having an AI function, the fourth node being registered with the fifth node, and the fifth node being one or more nodes other than the second node, and the first information indicates one or more of the following: a prediction result or an execution strategy of the second node; or the first information is sent to a core network device or an OAM, or the first information is sent by the second node to the core network device or the OAM, and the first information indicates one or more of the following: a data transmission capability of the access network side, a switching state prediction of the terminal device, path prediction information of the terminal device, or a predicted service demand of the terminal device. Based on this implementation, other nodes can obtain AI services of the first node.

[0020] In a second aspect, a communication method is provided, which can be executed by a second node located at a network side. The second node can refer to the second node itself, a processor, a module, a chip, or a chip system in the second node that implements the method, and the like. The method includes sending an activation indication to a first node located at the network side, and then receiving first information from the first node. The activation indication is used to indicate to activate the first node, the first node has an AI function, and the first information is generated based on the AI function.

[0021] The beneficial effects of the second aspect can be referred to the method described in the first aspect, which will not be repeated here.

[0022] In a possible implementation, the activation indication is used to indicate activation of the first node, in particular, the activation indication is used to indicate activation of the first node in one or more of the following: all or part of AI functions, all or part of protocol stacks, all or part of AI models, or all or part of results inferred by AI that need to be provided.

[0023] In a possible implementation, the method further includes: sending a first deactivation indication to the first node, the first deactivation indication being used to indicate closing of the first node.

[0024] In a possible implementation, the first deactivation indication is sent to the first node, in particular, the first deactivation indication is sent to the first node when a second condition is met; the second condition includes one or more of the following: receiving a second deactivation indication from the OAM, the second deactivation indication being used to indicate closing of the first node; an inference accuracy of the first node or an AI model or AI function of the first node is less than or equal to a first threshold; or, a performance gain of the first node or the AI model or AI function of the first node is less than or equal to a second threshold; or, a calculation overhead or storage overhead of the first node or the AI model or AI function of the first node is greater than or equal to a third threshold.

[0025] In a possible implementation, the first node is closed, in particular, the following one or more of the first node is closed: all or part of AI functions, all or part of protocol stacks, all or part of AI models, or all or part of results inferred by AI that need to be provided.

[0026] In a possible implementation, the second node is an access network device or a CU.

[0027] In a possible implementation, the method further includes: receiving first registration information from the first node, the first registration information including capability information of the first node, the capability information indicating that the first node has AI functions.

[0028] Optionally, the capability information indicates that the first node is provided with an AI function, and the implementation is that the capability information indicates one or more of the following information: one or more AI use cases supported by the first node, a number of AI use cases supported by the first node, an algorithmic cost corresponding to each of the one or more AI use cases, an energy consumption corresponding to each of the one or more AI use cases, an input / output format corresponding to each of the one or more AI use cases, one or more AI functions supported by the first node, a number of AI functions supported by the first node, an algorithmic cost corresponding to each of the one or more AI functions, an energy consumption corresponding to each of the one or more AI functions, an input / output format corresponding to each of the one or more AI functions, one or more AI models supported by the first node, a number of AI models supported by the first node, an algorithmic cost corresponding to each of the one or more AI models, an energy consumption corresponding to each of the one or more AI models, an input / output format corresponding to each of the one or more AI models.

[0029] Optionally, the capability information is further used to indicate a total algorithmic cost supported by the first node and / or a total energy consumption supported by the first node.

[0030] In a possible implementation, the method further includes: receiving second registration information from the first node; and sending the second registration information to one or more of the DU, the RU, the core network device, the OAM, or the RIC, the second registration information being further used to indicate capability information of the first node.

[0031] In a possible implementation, before receiving the second registration information from the second node, the method further includes: sending indication information to the first node, the indication information being used to indicate completion of registration with one or more of the DU, the RU, the core network device, the OAM, or the RIC.

[0032] In a possible implementation, the method further includes: sending fifth information to the first node, the fifth information indicating one or more of the following information: AI capability information of the second node, computing capability of the second node, energy consumption of the second node, energy efficiency information of the second node, geographic location of the second node, number of antennas of the second node, beam weighting manner of the second node, resource information of the second node, or measurement result of the second node.

[0033] In a possible implementation, the first information indicates one or more of the following information: a recommended downlink beam weighting manner, a predicted optimal access beam index of the terminal device, positioning assistance information of the terminal device, location information of the terminal device, an execution manner of energy saving, an execution manner of load balancing, a path prediction result of the terminal device, an execution strategy of recommended terminal device switching, a transmission configuration of uplink / downlink data transmission, an antenna form adjustment, or a modulation and demodulation scheme configuration.

[0034] In a third aspect, the present application provides a communication system, wherein the communication system comprises a first node and a second node located at a network side:

[0035] The second node sends an activation indication to the first node, the activation indication being used to indicate activating the first node, the first node being provided with an AI function; the first node generates first information based on the AI function; and the first node sends the first information.

[0036] In a possible implementation, the activation indication is used to indicate activating the first node, specifically, the activation indication is used to indicate activating one or more of the following of the first node: all or part of the AI function, all or part of the protocol stack, all or part of the AI model, or all or part of the result inferred by the AI that needs to be provided.

[0037] In a possible implementation, the first node is closed when a first condition is met; the first condition comprises one or more of the following: the first node receives a first deactivation indication from the second node, the first deactivation indication being used to indicate closing the first node; or, an inference accuracy of the first node or an AI model or an AI function of the first node is less than or equal to a first threshold; or, a performance gain of the first node or the AI model or the AI function of the first node is less than or equal to a second threshold; or, a calculation overhead or a storage overhead of the first node or the AI model or the AI function of the first node is greater than or equal to a third threshold.

[0038] In a possible implementation, the second node sends the first deactivation indication to the first node when a second condition is met; the second condition comprises one or more of the following: the second node receives a second deactivation indication from an OAM, the second deactivation indication being used to indicate closing the first node; an inference accuracy of the first node or an AI model or an AI function of the first node is less than or equal to a first threshold; or, a performance gain of the first node or the AI model or the AI function of the first node is less than or equal to a second threshold; or, a calculation overhead or a storage overhead of the first node or the AI model or the AI function of the first node is greater than or equal to a third threshold.

[0039] In a possible implementation, the first node is closed, specifically, one or more of the following of the first node is closed: all or part of the AI function, all or part of the protocol stack, all or part of the AI model, or all or part of the result inferred by the AI that needs to be provided.

[0040] In a possible implementation, the second node is an access network device or a CU.

[0041] In a possible implementation, the first node generates the first information based on the AI function, specifically: the first node generates the first information through a first protocol layer, the first protocol layer having the AI function; and the first node sends the first information, specifically: the first node sends the first information to a second protocol layer through the first protocol layer; the first node encapsulates the first information to obtain a first data unit through the second protocol layer; and the first node sends the first data unit through the second protocol layer.

[0042] In a possible implementation, the second node receives the first data unit through the second protocol layer; the second node decapsulates the first data unit to obtain the first information through the second protocol layer; the second node sends the first information to the first protocol layer through the second protocol layer; and the second node reads the first information through the first protocol layer.

[0043] In a possible implementation, the second node receives the first data unit through the second protocol layer; the second node sends the first data unit to the terminal device through the second protocol layer; the terminal device decapsulates the first data unit to obtain the first information through the second protocol layer; the terminal device sends the first information to the first protocol layer through the second protocol layer; and the terminal device reads the first information through the first protocol layer.

[0044] In a possible implementation, the first node sends first registration information to the second node, the first registration information including capability information of the first node, the capability information indicating that the first node has the AI function.

[0045] Optionally, the capability information indicates that the first node has the AI function, and specifically indicates one or more of the following information: one or more AI use cases supported by the first node, a number of AI use cases supported by the first node, an algorithmic cost corresponding to each of the one or more AI use cases, an energy consumption corresponding to each of the one or more AI use cases, an input / output format corresponding to each of the one or more AI use cases, one or more AI functions supported by the first node, a number of AI functions supported by the first node, an algorithmic cost corresponding to each of the one or more AI functions, an energy consumption corresponding to each of the one or more AI functions, an input / output format corresponding to each of the one or more AI functions, one or more AI models supported by the first node, a number of AI models supported by the first node, an algorithmic cost corresponding to each of the one or more AI models, an energy consumption corresponding to each of the one or more AI models, and an input / output format corresponding to each of the one or more AI models.

[0046] Optionally, the capability information is further used to indicate a total algorithmic cost supported by the first node and / or a total energy consumption supported by the first node.

[0047] In a possible implementation, the communication system further includes one or more of the following nodes: a DU, a RU, a core network device, or an OAM; and the first node sends the second registration information to one or more of the following nodes: the meta-DU, the RU, the core network device, the OAM, or the RIC, or the first node sends the second registration information to one or more of the following nodes: the DU, the RU, the core network device, the OAM, or the RIC through the second node.

[0048] In a possible implementation, the second node sends indication information to the first node, and the indication information is used to indicate that the registration with one or more of the following nodes: the DU, the RU, the core network device, the OAM, or the RIC is completed.

[0049] In a possible implementation, the communication system further includes one or more of the following nodes: a terminal device, a DU, a RU, a core network device, an OAM, or a fourth node; and the first node receives second information, and the second information is used for AI model training or model inference; the second information includes one or more of the following information: third information sent by the terminal device, fourth information sent by the core network device or the OAM, fifth information sent by a third node, and sixth information sent by a fourth node; the third node includes one or more of the following nodes: the second node, the DU, or the RU; the fourth node has an AI function, is registered with a fifth node, and the fifth node is one or more nodes other than the second node; the third information indicates one or more of the following information: AI capability information of the terminal device, computing capability of the terminal device, energy consumption of the terminal device, energy efficiency information of the terminal device, moving speed of the terminal device, moving path of the terminal device, number of antennas of the terminal device, beam weighting manner of the terminal device, service information of the terminal device, or measurement result of the terminal device; the fourth information indicates one or more of the following information: AI capability information of the core network device or the OAM, computing capability of the core network device or the OAM, or service requirement of the core network device or the OAM; the fifth information indicates one or more of the following information: AI capability information of the third node, computing capability of the third node, energy consumption of the third node, energy efficiency information of the third node, geographic location of the third node, number of antennas of the third node, beam weighting manner of the third node, resource information of the third node, or measurement result of the third node; and the sixth information indicates one or more of the following information: AI capability information of the fourth node, computing capability of the fourth node, energy consumption of the fourth node, or energy efficiency information of the fourth node.

[0050] In a possible implementation, the communication system further includes one or more of the following nodes: a terminal device, a DU, a RU, a core network device, an OAM, or a fourth node; and the first node sends first information, and the first information is specifically:

[0051] The first node sends first information to the terminal device through the second node, and the first information indicates one or more of the following information: an AI use case of the terminal device, an AI function to be executed by the terminal device, or an AI model to be executed by the terminal device, an AI inference result to be provided by the terminal device, information related to lifecycle management of the AI use case of the terminal device, information related to lifecycle management of the AI function of the terminal device, or information related to lifecycle management of the AI model of the terminal device; or

[0052] The first node sends the first information to a third node, the third node including one or more of the second node, a DU, or a RU, or the first node sends the first information to the third node through the second node, the third node including one or more of the DU or the RU, and the first information indicates one or more of the following information: a recommended downlink beam weighting manner, a predicted optimal access beam index of the terminal device, positioning assistance information of the terminal device, location information of the terminal device, an execution manner of energy saving, an execution manner of load balancing, a path prediction result of the terminal device, a recommended execution strategy of terminal device switching, a transmission configuration of uplink and downlink data transmission, an antenna form adjustment, or a modulation and demodulation scheme configuration; or

[0053] The first node sends the first information to a fourth node, or the first node sends the first information to the fourth node through the second node and a fifth node, the fourth node having an AI function, the fourth node being registered with the fifth node, and the fifth node being one or more nodes other than the second node, and the first information indicates one or more of the following information: a prediction result or an execution strategy of the first node; or

[0054] The first node sends the first information to a core network device or an OAM, or the first node sends the first information to the core network device or the OAM through the second node, and the first information indicates one or more of the following information: a data transmission capability of the access network side, a switching state prediction of the terminal device, path prediction information of the terminal device, or a predicted service demand of the terminal device.

[0055] In a fourth aspect, a communication apparatus is provided. The communication apparatus can also be a chip system. The communication apparatus can perform the method in the first aspect and its possible implementation manners. The functions of the communication apparatus can be implemented by hardware, by corresponding software executed by hardware, or by a combination of hardware and software. The hardware or software includes one or more units or modules corresponding to the functions. The units or modules can be software and / or hardware. The operations and advantages of the communication apparatus can be derived from the method in the first aspect and its possible implementation manners, and will not be repeated here.

[0056] In a fifth aspect, the present application provides a communication apparatus, which can also be a chip system. The communication apparatus can perform the method in the second aspect and possible implementation manners thereof. The functions of the communication apparatus can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the functions described above. The units or modules can be software and / or hardware. The operations and beneficial effects of the communication apparatus can be referred to the method in the second aspect and possible implementation manners thereof, and the beneficial effects described above, and the repeated descriptions are omitted.

[0057] In a sixth aspect, the present application provides a communication apparatus, which includes a processor. When the processor invokes a computer program in a memory, the method in the first aspect or the second aspect and possible implementation manners thereof are performed.

[0058] In a possible implementation manner, the communication apparatus further includes a memory, which is coupled with the processor. Optionally, the memory is integrated with the processor.

[0059] In a possible implementation manner, the communication apparatus further includes a transceiver, which is configured to transceive data and / or signaling.

[0060] In a seventh aspect, the present application provides a communication apparatus, which includes a processor and an interface circuit. The interface circuit is configured to receive a signal from another communication apparatus outside the communication apparatus and transmit the signal to the processor, or send a signal from the processor to another communication apparatus outside the communication apparatus. The processor is configured to implement the method in the first aspect or the second aspect and possible implementation manners thereof by means of a logic circuit or executing code instructions.

[0061] In an eighth aspect, the present application provides a chip, which includes a processor and a communication interface. The processor is configured to cause the chip to perform the method in the first aspect or the second aspect and possible implementation manners thereof, or the processor is configured to cause the chip to perform the method in the first aspect or the second aspect and possible implementation manners thereof.

[0062] In a ninth aspect, the present application provides a computer readable storage medium, which stores a computer program or instructions. When the computer program or instructions are executed by a communication apparatus, the method in the first aspect or the second aspect and possible implementation manners thereof are implemented.

[0063] In a tenth aspect, the present application provides a computer program or computer program product, which includes code or instructions. When the code or instructions are run on a computer, the computer is caused to perform the method in the first aspect or the second aspect and possible implementation manners thereof. BRIEF DESCRIPTION OF DRAWINGS

[0064] Fig. 1 is a schematic diagram of an application framework in a communication system according to an embodiment of the present application;

[0065] Fig. 2 is a schematic diagram of another application framework in a communication system according to an embodiment of the present application;

[0066] Fig. 3 is a schematic diagram of an AI application framework in NR according to an embodiment of the present application;

[0067] Fig. 4 is a schematic diagram of a communication method according to an embodiment of the present application;

[0068] Fig. 5 is a schematic diagram of a protocol stack architecture between a second node and a first node according to an embodiment of the present application;

[0069] Fig. 6A is a schematic diagram of a protocol stack architecture between a terminal device and a first node according to an embodiment of the present application;

[0070] Fig. 6B is a schematic diagram of another protocol stack architecture between a terminal device and a first node according to an embodiment of the present application;

[0071] Fig. 6C is a schematic diagram of another protocol stack architecture between a terminal device and a first node according to an embodiment of the present application;

[0072] Fig. 7A is a schematic diagram of a protocol stack architecture between a DU and a first node according to an embodiment of the present application;

[0073] Fig. 7B is a schematic diagram of another protocol stack architecture between a DU and a first node according to an embodiment of the present application;

[0074] Fig. 8A is a schematic diagram of a protocol stack architecture between a fourth node and a first node according to an embodiment of the present application;

[0075] Fig. 8B is a schematic diagram of another protocol stack architecture between a fourth node and a first node according to an embodiment of the present application;

[0076] Fig. 9 is a schematic diagram of a structure of an apparatus according to an embodiment of the present application;

[0077] Fig. 10 is a schematic diagram of a structure of an apparatus according to an embodiment of the present application;

[0078] Fig. 11 is a schematic diagram of a structure of an apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0079] To make the technical solution of the present application more understandable, the present application will be further described below with reference to the accompanying drawings.

[0080] The terms "first" and "second," etc., used in the specification, claims, and drawings of this application are used only to distinguish different objects and not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0081] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0082] In this application, "at least one (item)" refers to one or more, "more than one" refers to two or more, "at least two (items)" refers to two or three or more, and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. "Or" indicates that there can be two relationships, such as only A exists and only B exists; when A and B are not mutually exclusive, it can also mean that there are three relationships, such as only A exists, only B exists, and both A and B exist simultaneously. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c".

[0083] In the present application, the information indicated by the indication information is referred to as to-be-indicated information. In the process of implementation, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be only indicated in part, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, the protocol stipulates), thereby reducing the indication overhead to a certain extent. In addition, the to-be-indicated information can be sent as a whole, or can be sent separately in multiple sub-information, and the sending period and / or sending time of these sub-information can be the same or different.

[0084] In the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending information to XX" can be understood as that the destination of the information is XX, which can include direct sending through the air interface, or indirect sending through the air interface by other units or modules. "Receiving information from YY" can be understood as that the source of the information is YY, which can include direct receiving from YY through the air interface, or indirect receiving from YY through the air interface by other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, sending and receiving can be carried out between devices, such as between network devices and terminal devices, or can be carried out within a device, such as between components, modules, chips, software modules or hardware modules within a device through a bus, wire or interface.

[0085] In addition, in the embodiments of the present application, "network element A sends information A to network element B" can be understood as that the destination of the information A or the intermediate network element in the transmission path between the destination is network element B, which can include direct or indirect sending of information to network element B. "Network element B receives information A from network element A" can be understood as that the source of the information A or the intermediate network element in the transmission path between the source is network element A, which can include direct or indirect receiving of information from network element A. The information can be processed as necessary between the source and the destination of the information transmission, such as format change, but the destination can understand the valid information from the source. Similar expressions in the present application can be understood similarly, and will not be described here.

[0086] It should be understood that, in this application, information C being used for determination of information D includes both information D being determined based on information C only and information D being determined based on information C and other information. In addition, information C being used for determination of information D also includes the case that information D is determined indirectly based on information C, such as the case that information D is determined based on information E, and information E is determined based on information C.

[0087] The following introduces a communication system related to embodiments of the present application.

[0088] The technical solutions provided in the present application can be applied to various communication systems, for example, a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system, or a fusion system of multiple systems, etc. The technical solutions provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and an internet of things (IoT) communication system or other communication systems.

[0089] A node in a communication system can send or receive a signal to or from another node. The signal can include information, signaling, or data, etc. The node can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a network element, a communication node, etc. The node is taken as an example for description in the present application. For example, the communication system can include at least one terminal device and at least one access network device. The access network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device.

[0090] In embodiments of the present application, the terminal device can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user apparatus.

[0091] The terminal device can be a device providing voice / data, for example, a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: mobile phone, tablet computer, notebook computer, palm computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication function, computing device or other processing device connected to a wireless modem, wearable device, terminal device in a 5G network, or terminal device in a future evolved public land mobile network (PLMN), etc. The embodiments of the present application are not limited thereto.

[0092] By way of example and not limitation, in the embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the user's clothes or accessories. The wearable device is not only a hardware device, but also a device that realizes powerful functions through software support and data interaction and cloud interaction. The general wearable smart device includes devices with full functions, large size, and the ability to realize complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, and devices that focus on a certain application function and need to be used in cooperation with other devices, such as smart phones, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0093] In the embodiments of the present application, the apparatus for implementing the function of the terminal device can be a terminal device, or can be an apparatus capable of supporting the terminal device to implement the function, for example, a chip system, which can be installed in the terminal device or used in matching with the terminal device. In the embodiments of the present application, the chip system can include a chip, or can include a chip and other discrete devices. In the embodiments of the present application, only the apparatus for implementing the function of the terminal device is taken as an example for description, and the scheme of the embodiments of the present application is not limited.

[0094] The access network device in the embodiments of the present application can be a device for communicating with a terminal device, and the access network device can also be referred to as a network device or a radio access network device, for example, the access network device can be a base station. The access network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) for accessing a terminal device to a wireless network. The base station can broadly cover various names in the following or be replaced by the following names, such as: Node B (NodeB), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), primary station, secondary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station can also refer to a communication module, modem or chip used in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device performing a base station function in D2D, V2X, M2M communication, a device performing a base station function in a future communication system, etc. The base station can support networks of the same or different access technologies. Optionally, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in the vehicle to everything (V2X) technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form of the access network device.

[0095] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station. In other examples, the helicopter or the drone can be configured to serve as a device communicating with another base station.

[0096] In some deployments, the access network device mentioned by embodiments of the present application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the access network device can include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0097] In some deployments, wireless access is assisted by multiple RAN nodes cooperating to assist a terminal, and different RAN nodes respectively implement part of the functions of a base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be separately arranged, or can also be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, an AAU, or an RRH.

[0098] The RAN node can support one or more types of fronthaul interfaces, different fronthaul interfaces respectively corresponding to DUs and RUs having different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more of baseband functions, and the RU is configured to implement one or more of radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, which, relative to the CPRI, moves one or more of partial baseband functions of the downlink and / or uplink, such as, for the downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / add cyclic prefix (CP), from the DU to the RU for implementation, and for the uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / remove cyclic prefix (CP), from the DU to the RU for implementation. In a possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting manner between the DU and the RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0099] Taking eCPRI Cat A as an example, for downlink transmission, with layer mapping as the cut, the DU is configured to implement layer mapping and one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, layer mapping) before layer mapping, while other functions (e.g., one or more of resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) after layer mapping are implemented in the RU. For uplink transmission, with de-RE mapping as the cut, the DU is configured to implement de-mapping and one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, de-modulation, inverse discrete Fourier transform (IDFT), channel equalization, de-RE mapping) before de-mapping, while other functions (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) after de-mapping are implemented in the RU. It can be understood that the function description of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which is not described here.

[0100] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit.

[0101] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. Any of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0102] In the embodiments of the present application, the device for implementing the function of the access network device can be the access network device, or can be a device capable of supporting the access network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The device can be installed in the access network device or used in combination with the access network device. In the embodiments of the present application, only the device for implementing the function of the access network device is taken as an example to illustrate the access network device, and the scheme of the embodiments of the present application is not limited.

[0103] The access network device and / or the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on the water surface; and can also be deployed on airplanes, balloons and satellites in the air. The scenarios in which the access network device and the terminal device are located are not limited in the embodiments of the present application. In addition, the terminal device and the access network device can be hardware devices, or software functions running on special hardware, software functions running on general hardware, such as virtualized functions instantiated on a platform (for example, a cloud platform), or entities including special or general hardware devices and software functions. The specific forms of the terminal device and the access network device are not limited in the present application.

[0104] In a wireless communication network, for example, in a mobile communication network, the services supported by the network are increasingly diverse, and therefore the needs to be met are increasingly diverse. For example, the network needs to be able to support ultra-high rates, ultra-low latencies, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as the functions of the network become increasingly powerful, for example, the network supports increasingly high frequency spectrums, supports high-order multiple input multiple output (MIMO) technology, supports beamforming, and / or supports new technologies such as beam management, network energy saving has become a hot research topic. These new needs, new scenarios and new features bring unprecedented challenges to network planning, operation and efficient operation. In order to meet this challenge, artificial intelligence (AI) technology can be introduced into the wireless communication network, thereby realizing network intelligentization.

[0105] In order to support AI technology in a wireless network, the embodiments of the present application propose that a first node can be introduced into a communication system, the first node is located at the network side, has an AI function, and can provide AI services for other nodes in the communication system except the first node, for example, one or more of the access network device, the terminal device, the core network device, or the operations, administration and maintenance (OAM).

[0106] It can be understood that the number of first nodes is not limited in the present application. For example, when there are multiple first nodes, the multiple first nodes can be divided based on functions, such as different first nodes being responsible for different AI functions.

[0107] It can also be understood that the first nodes can be independent devices, can be integrated into the same device to implement different functions, or can be network elements in a hardware device, or can be software functions running on dedicated hardware, or virtualized functions instantiated on a platform (for example, a cloud platform), and the specific form of the first nodes is not limited in the present application.

[0108] FIG. 1 is a schematic diagram of an application framework in a communication system. The communication system includes a core network device, an OAM, an access network device, a terminal and a first node. The first node shown in FIG. 1 is located inside the access network device, and it should be noted that the first node can also be located outside the access network device. When the first node is located inside the access network device, it can be understood that the first node is part of the access network device, that is, the first node is a unit, device or module in the access network device. Alternatively, the first node is a unit at the same level as the CU, DU or RU, that is, the first node, CU, DU and RU all belong to the inside of the access network device. When the first node is located outside the access network device, it means that the first node is a node independent of the access network device and does not belong to the access network device. Alternatively, the first node is a network node parallel to the access network device. The embodiments of the present application do not limit whether the first node is located inside or outside the access network device. In the communication system, the nodes are connected through interfaces or air interfaces. For example, the first node is connected to the CU through a first interface. Alternatively, the first node can be connected to the DU through a second interface, connected to the RU through a third interface, connected to the core network device through a fourth interface, and connected to the OAM through a fifth interface. Alternatively, the first node does not have an interface with one or more nodes in the DU, RU, core network device and OAM, and communicates through the CU. The access network device shown in FIG. 1 is a separation architecture of CU and DU. Of course, the access network device in the communication system can also be a non-separation architecture, and the embodiments of the present application do not limit whether the access network device is a separation architecture of CU and DU or a non-separation architecture.

[0109] One or more AI modules (only 1 is shown in FIG. 1 for clarity) are deployed in the first node. The AI modules are used to implement corresponding AI functions. The AI modules deployed in different network elements can be the same or different. The AI modules can implement different functions according to different parameter configurations. The model of an AI module can be configured based on one or more of the following parameters: a structural parameter (for example, at least one of the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of a neuron, the activation function of a neuron, or the bias in the activation function), an input parameter (for example, the type of the input parameter and / or the dimension of the input parameter), or an output parameter (for example, the type of the output parameter and / or the dimension of the output parameter). The bias in the activation function can also be referred to as the bias of the neural network.

[0110] One AI module can have one or more models. One model can infer an output, which includes one parameter or multiple parameters. The learning process, the training process, or the inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0111] In addition to the first node, one or more of the following nodes of the communication system, such as a core network device, an access network device, a terminal, or an OAM device, can or can not be provided with an AI module, and the embodiments of the present application do not limit this.

[0112] FIG. 2 is a schematic diagram of another application framework in a communication system. The communication system includes a core network device, a RIC, an access network device, a terminal and a first node. The access network device further includes a CU, a DU and a RU. The CU can also be referred to as an O-CU, the DU can also be referred to as an O-DU, and the RU can also be referred to as an O-RU. The first node in FIG. 2 is located inside the access network device, and it is to be noted that the first node can also be located outside the access network device, and the embodiments of the present application do not limit whether the first node is located inside or outside the access network device. For the definition of whether the first node is located inside or outside the access network device, refer to the above description, and details are not described herein. The nodes in the communication system are connected through interfaces or air interfaces, for example, the first node and the CU are connected through a first interface. Alternatively, the first node is connected with the DU through a second interface, connected with the RU through a third interface, connected with the core network device through a fourth interface, and connected with the RIC through a sixth interface. Alternatively, the first node does not have an interface with one or more nodes in the DU, the RU, the core network device and the RIC, and communicates through the CU. The CU can further include a CU-CP and / or a CU-UP. The RU is an intermediate node for interaction between the terminal and the CU-CP. The CU-CP is used to generate a configuration sent to the terminal, and sends the configuration to the terminal via the RU. On the other hand, the CU-CP can also be used to generate a decision method of the configuration to be sent to the terminal, and the decision method of the configuration can come from the RIC.

[0113] The RIC includes a near-real time RIC (near-RT RIC) and a non-real time RIC (Non-RT RIC). The non-real time RIC mainly processes non-real time information, such as data insensitive to delay, and the delay of the data can be seconds. The real-time RIC mainly processes near-real time information, such as data relatively sensitive to delay, and the delay of the data is tens of milliseconds.

[0114] The near-real time RIC is used for model training and inference. For example, an AI model is trained, and inference is performed by using the AI model. The near-real time RIC can obtain network side and / or terminal side information from the RAN node (such as the CU, the CU-CP, the CU-UP, the DU and / or the RU) and / or the terminal. The information can be used as training data or inference data. Alternatively, the near-real time RIC can submit the inference result to the RAN node and / or the terminal. Alternatively, the CU and the DU, and / or the DU and the RU can interact with the inference result. For example, the near-real time RIC submits the inference result to the DU, and the DU sends the inference result to the RU.

[0115] Non-real-time RIC is also used for model training and inference. For example, for training an AI model, inference is performed using the model. The non-real-time RIC can obtain network-side and / or terminal-side information from the RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or the terminal. The information can be used as training data or inference data, and the inference result can be delivered to the RAN node and / or the terminal. Alternatively, the inference result can be exchanged between the CU and the DU, and / or between the DU and the RU, for example, the non-real-time RIC delivers the inference result to the DU, which then sends it to the RU.

[0116] The near-real-time RIC and the non-real-time RIC can also be separately set as a network element, respectively. Alternatively, the near-real-time RIC and the non-real-time RIC can also be part of other devices, for example, the near-real-time RIC is set in the RAN node (e.g., CU, DU), and the non-real-time RIC is set in the OAM, the cloud server, the core network device, or other network devices.

[0117] To facilitate understanding of the scheme provided by the embodiments of the present application, the related concepts involved in the embodiments of the present application are introduced as follows:

[0118] 1、AI

[0119] AI is a technology that simulates the human brain to perform complex calculations. With the improvement of data storage and computing power, AI has been increasingly used. The R17 version of 3GPP has approved a study item (SI) to apply AI to NR, which collects and analyzes data intelligently to improve network performance and user experience. Based on the discussion of the RAN3 working group of 3GPP, the framework for applying AI in NR is preliminarily defined as shown in FIG. 3.

[0120] Among them, the data source can store data input from gNB, gNB-CU, gNB-DU, UE or other management entities, and the data source can serve as a database for AI model training and data analysis inference. For example, the data collection module in FIG. 3 can represent the data source. The model training module gives the optimal AI model by analyzing the training data provided by the data collection. The model inference module uses the AI model to give the AI-based reasonable prediction (i.e. prediction data) based on the inference data provided by the data collection, or to guide the network to make strategy adjustment. The relevant strategy adjustment is uniformly planned by the actor entity and sent to multiple network entities for operation. At the same time, after the network applies the relevant strategy, the specific performance of the network will be input again into the data source for storage.

[0121] 2. AI-based use case

[0122] Currently, 3GPP designs several basic application scenarios for AI application in RAN side from RAN3, RAN1 and other working groups, among which RAN3 includes energy saving, load balancing and mobility optimization, RAN1 includes channel state information-reference signal (CSI-RS) feedback enhancement, beam management enhancement and positioning accuracy enhancement. The basic principles of several use cases are briefly introduced as follows.

[0123] (1) Energy saving: by collecting the load, energy consumption, energy efficiency information of the base station itself and the neighboring area, as well as the trajectory information, measurement results, etc. of the UE, the trend of the load of the base station itself is predicted, and under the premise of not affecting the network coverage and user access, appropriate energy saving measures are taken in a timely manner. Exemplarily, the energy saving strategy can include directly deactivating the cell, other energy saving strategies include carrier shutdown, channel shutdown, time slot shutdown, transmission power reduction, etc. A more complex energy saving strategy also includes combining the above energy saving measures. When the network coverage is affected or the UE access and service demand cannot be met, the current energy saving strategy needs to be modified or directly returned to the normal working state, and the load needs to be re-predicted or the AI model used is changed for re-inference. In this application, if the collection of the trajectory information or historical trajectory information of the UE is involved, the collection has been authorized or agreed by the user.

[0124] (2) Load balancing: by collecting the load, energy consumption, energy efficiency information of the base station itself and the neighboring area, as well as the trajectory information, measurement results, etc. of the UE, the trend of the load of the base station itself is predicted, and combined with the cell usage, KPI requirements, etc., some UEs are reasonably selected to be handed over to the neighboring area or to receive UEs from the neighboring area, so that the load levels of the base stations in the whole cell are close, and the situation that some base stations are overloaded to affect normal business while some base station resources are idle is reduced. However, due to the inaccuracy of the prediction, it may lead to unreasonable selection of UEs or unreasonable selection of target cells for handover, resulting in handover failure or UE service being affected, or inaccurate load prediction leading to poor load balancing effect, or temporary load abnormal changes leading to the inapplicability of the original load balancing strategy, at which time the current load balancing strategy needs to be exited or modified, and the load needs to be re-predicted or the AI model used is changed for re-inference.

[0125] (3) Mobility optimization: by collecting the historical trajectory information of the UE by the base station, combined with the measurement information of the UE, the future trajectory of the UE is predicted. Based on the predicted trajectory, it is judged in advance whether the UE will be handed over, and the handover configuration is issued in advance and the target cell is informed to prepare for access resources, reducing the delay of the UE in the handover process and reducing the probability of handover and access failure. However, due to the inaccuracy of the trajectory prediction, when the predicted trajectory is wrong, it will lead to UE handover failure and service interruption. In view of this situation, it is necessary to consider retraining the model and inference in combination with abnormal situations, or consider replacing the model to avoid similar abnormal situations for subsequent UEs.

[0126] (4) CSI-RS feedback enhancement: The main process of current CSI-RS feedback enhancement is: first, a dictionary is exchanged between the base station and the UE, usually the base station trains a model in advance according to the UE capability and its own requirements, and then an encoder and a quantizer tool are issued to the UE; then, the UE compresses and quantizes the feedback matrix according to the existing dictionary according to the measured channel matrix result, and delivers the result to the base station side; finally, the base station side recovers the original channel matrix according to the dictionary and the data reported by the UE.

[0127] (5) Beam sweeping enhancement: The main process of current beam management enhancement is: first, the generation of the initial model, that is, the results of a certain number of UE full beam sweeping of the synchronized signal block (SSB) are reported, and a sparse scanning matrix is trained, which is usually unique to each cell; then, the base station issues the sparse model to the UE (it can be considered through the system information block (SIB) message, etc.), and the UE performs P1 stage beam sweeping according to the matrix; finally, the base station infers the optimal CSI-RS beam based on the sparse scanning result of the UE, and starts P2 scanning for the UE, and the UE feeds back the optimal CSI-RS beam ID.

[0128] (6) Positioning enhancement: The main process of current positioning accuracy enhancement is: first, use the operator-controlled reference UE to collect raw data; then, the location management function (LMF) and the base station train models respectively, the LMF model can infer the final positioning (latitude and longitude, etc.), and the base station model can infer the line of sight (LOS) path / non line of sight (NLOS) path judgment result.

[0129] Nowadays, the interaction between each network node and AI information is based on a communication protocol stack. The AI information can refer to information related to AI, such as data information used for AI model training, result information or decision information obtained by AI model inference, or feedback information obtained after a decision is made by performing AI model inference, and the like. AI and the communication protocol stack are deeply bound to each other. That is, the interaction of AI information needs to be based on the communication protocol stack, and the design of the communication protocol also needs to consider the management of AI information or the specification of the AI information interaction process, and the like. However, with the increasing regulation of AI functions in some regions, devices with AI functions may be restricted from use in some regions. For example, an access network device has an AI function and is located in an AI function restricted area. Because AI and the communication protocol stack are deeply bound to each other, the access network device will not be able to communicate normally based on the communication protocol stack.

[0130] To avoid the communication function of a node (such as an access network device, a terminal device, or a core network device) in a communication system being affected when the node is located in an AI function restricted area, embodiments of the present application propose a communication method. As shown in FIG. 4, the communication method includes steps 401-403. The method shown in FIG. 4 corresponds to a first node and a second node, or the method shown in FIG. 4 can be a chip or functional module in the first node and a chip or functional module in the second node.

[0131] The method can be applied to the network framework shown in FIG. 1 or FIG. 2, where the first node can be the first node shown in FIG. 1 or FIG. 2, and the second node can be the access network device shown in FIG. 1 or FIG. 2 or a communication unit (such as a CU) included in the access network device. FIG. 4 is described by taking the first node and the second node as an example. Embodiments of the present application do not limit the execution subject of the communication method. The method includes:

[0132] 401. The second node sends an activation indication, and the activation indication is used to indicate the activation of the first node.

[0133] Correspondingly, the first node receives the activation indication, such as receiving the activation indication from the second node.

[0134] The first node has an AI function, which means that the first node can be deployed with an AI model (or also referred to as an AI algorithm), and the AI use case can be implemented through the AI function. The AI use case, AI function, and AI model are introduced as follows: The AI use case refers to a function of network optimization implemented through the AI function. For example, the AI use case can refer to energy saving and load balancing, energy saving, load balancing, mobility optimization, CSI-RS feedback enhancement, beam sweeping enhancement, or positioning enhancement. The AI function refers to a specific function implemented through AI. For example, in the AI use case of energy saving and load balancing, the AI function is used for load prediction to determine the corresponding strategy of energy saving and load balancing, where the load prediction can be considered as an AI function. The AI model is a model used to implement a certain AI function. The types of models can include neural network models, linear models, deep learning models, etc. For example, in the AI function-based load prediction, a neural network model can be used for calculation to obtain a load prediction result.

[0135] The AI use case can correspond to one or more AI functions, one AI function can correspond to one or more AI models, one AI model can be used for one or more AI functions, and one AI function can be applied to one or more AI use cases.

[0136] The types of AI functions, AI use cases, and AI models described above are only examples, and there can be other types of AI functions, AI use cases, and AI models. The embodiments of the present application do not limit the types of AI functions, AI use cases, and AI models.

[0137] The first node is located at the network side. For example, the first node can be a network node located inside an access network device, or a network node located outside the access network device. The second node is also located at the network side. For example, the second node can be a RAN node, such as an access network device or a CU.

[0138] The first node can provide AI services for other nodes (such as one or more of the second node, DU, RU, core network device, OAM, or terminal device) based on the AI function. For example, the second node requests an energy saving strategy suitable for the second node through the first node. The second node can provide the first node with load, energy consumption, and energy efficiency information of the second node and the second node adjacent area, as well as trajectory information, measurement results, and other information of the terminal device, to request the first node to infer the energy saving strategy of the second node through the AI function. The first node can input the obtained information into the AI model to infer the energy saving strategy, and then send the energy saving strategy to the second node.

[0139] Optionally, one or more nodes in the communication system other than the first node can not have AI functions, for example, one or more of the second node, the DU, the RU, the core network device, the OAM, or the terminal device does not have AI functions, and these nodes can obtain corresponding AI services through the first node when AI functions are needed. In this way, the first node is built-in with AI functions, and other nodes without built-in AI functions can also obtain AI services through the first node, and in the scenario where AI functions are limited, the communication functions of other nodes without built-in AI functions can be avoided from being affected.

[0140] In one example, the activation indication is used to indicate the activation of the first node, specifically, the activation indication is used to indicate the activation of one or more of the following in the first node: all or part of the AI functions, all or part of the protocol stack, all or part of the AI model, or all or part of the results inferred by AI that need to be provided. Wherein, activating the results inferred by AI that need to be provided can be understood as activating the first node to perform AI inference, so as to obtain the results inferred by the first node through a specific AI function or a specific AI model.

[0141] Taking the activation indication indicating the activation of the AI function of the first node as an example, it can be understood that the activation indication can indicate the activation of all AI functions of the first node by default, or it can also indicate the activation of a part of specific AI functions in the all AI functions of the first node. For example, the first node has AI function 1 and AI function 2, when the activation indication activates all AI functions of the first node by default, that is, the first node activates AI function 1 and AI function 2; when the activation indication activates AI function 2 in the first node, the first node only activates AI function 2 and will not activate AI function 1. Optionally, when the activation indication is used to indicate the activation of part of the AI functions of the first node, the activation indication can also carry the identity of the part of the AI functions. By using the activation indication to indicate the activation of specific AI functions, protocol stacks, AI models, or results inferred by AI that need to be provided in the first node, unnecessary items in the first node can be avoided from being activated, which is beneficial to avoid wasting energy consumption.

[0142] When the activation indication is used to indicate the activation of the protocol stack, the AI model, or the results inferred by AI that need to be provided in the first node, the "AI function" described in the above examples can be replaced by "protocol stack", "AI model", or "results inferred by AI that need to be provided" for description, which will not be described here.

[0143] In one example, the second node sends the activation indication when one or more of the following conditions are met:

[0144] (1) The second node detects that one or more of the core network device, OAM, DU, RU, or terminal device has a demand for AI service. For example, the second node detects that the terminal device triggers a beam failure recovery (Beam Failure Recovery). Or, the second node detects that the terminal device triggers a radio link failure (Radio Link Failure, RLF) or a successful handover report (successful handover report, SHR) report due to handover failure.

[0145] (2) The second node receives an activation indication from one or more of the core network device, RIC, OAM, DU, RU, or terminal device, which indicates to activate the first node.

[0146] (3) The configuration of one or more of the core network device, RIC, OAM, DU, RU, or terminal device meets the trigger condition of activation, for example, one or more of the core network device, RIC, OAM, DU, RU, or terminal device enables a specific AI-based case.

[0147] (4) The second node detects that the performance indicator is greater than or less than the preset value. For example, the performance indicator can be the positioning error of the terminal device, such as the positioning error of more than a preset proportion of terminal devices in the cell exceeding a preset value. For example, the performance indicator can be the quality of the reference signal, which can be a demodulation reference signal (demodulation reference signal, DMRS) or a sounding reference signal (sounding reference signal, SRS), such as the quality of the reference signal being greater than a preset value. For example, the performance indicator is the throughput or the modulation and coding scheme (modulation and coding scheme, MCS) order, such as the throughput or the MCS order being lower than the preset value. For example, the performance indicator is the energy consumption or energy efficiency of the system, such as the energy consumption or energy efficiency of the system being lower than the preset value. For example, the performance indicator is the cell load level, such as the cell load level exceeding the preset value.

[0148] It should be further noted that in some cases, the first node can also activate by itself, in which case, step 401 can not need to be performed. For example, when the first node detects that a performance indicator is greater than or less than a preset value, the first node can activate by itself, for example, the performance indicator can be one or more of a positioning error of a terminal device, a quality of a reference signal, a throughput, an MCS order, an energy consumption or energy efficiency of a system, or a load level of a cell. Related examples of the performance indicator can be referred to the above description, which will not be repeated here. Or when the first node detects that one or more of a core network device, a RIC, an OAM, a second node, a DU, a RU, or a terminal device has a demand for activating an AI service, the first node can activate by itself, for example, the first node detects that a terminal device triggers a beam failure recovery. Alternatively, the first node detects that a terminal device triggers a radio link failure RLF or a SHR report due to a handover failure.

[0149] In a possible implementation, before the second node sends the activation indication, the first node sends first registration information, and correspondingly, the second node receives the first registration information, the first registration information including capability information of the first node, the capability information indicating that the first node has an AI function. After the second node receives the first registration information, the registration of the first node will be completed according to the first registration information. For example, the first node is connected to the second node through a first interface, and the first node can send the first registration information to the second node directly through the first interface, and correspondingly, the second node receives the first registration information from the first node through the first interface.

[0150] For example, when the capability information indicates that the first node has an AI function, the capability information can be implemented as indicating one or more of the following information:

[0151] (1) one or more AI use cases supported by the first node, a number of AI use cases supported by the first node, one or more respective computing power consumptions of the one or more AI use cases, one or more respective energy consumptions of the one or more AI use cases, or one or more respective input and output formats of the one or more AI use cases.

[0152] (2) one or more AI functions supported by the first node, a number of AI functions supported by the first node, one or more respective computing power consumptions of the one or more AI functions, one or more respective energy consumptions of the one or more AI functions, or one or more respective input and output formats of the one or more AI functions.

[0153] (3) one or more of the following: one or more AI models supported by the first node, a number of AI models supported by the first node, an amount of computing power respectively corresponding to the one or more AI models, an amount of energy consumption respectively corresponding to the one or more AI models, and an input / output format respectively corresponding to the one or more AI models.

[0154] In the above description, the example overhead or energy consumption refers to a predicted example overhead or energy consumption, i.e., a predicted example overhead or energy consumption required by the first node to support a certain AI use case, or AI function, or AI model. Alternatively, the example overhead or energy consumption can refer to a maximum overhead or maximum energy consumption, i.e., a maximum example overhead or maximum energy consumption of a certain AI use case, or AI function, or AI model supported by the first node.

[0155] It should be further noted that the indication described in the embodiments of the present application can include direct indication (also referred to as explicit indication) and implicit indication. The direct indication of information A means that the information A is included. The implicit indication of information A means that the information A is indicated by the corresponding relationship between the information A and information B and the direct indication of information B. The corresponding relationship between the information A and the information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0156] Taking the capability information described herein as an example, in the case of direct indication, the capability information includes information indicating one or more AI use cases supported by the first node. In the case of indirect indication, the capability information can include one or more indexes respectively corresponding to the one or more AI use cases. The one or more AI use cases supported by the first node can be determined based on the corresponding relationship between the one or more AI use cases and the indexes and the indexes included in the capability information.

[0157] For example, the capability information further indicates the total computing power supported by the first node and / or the total energy consumption supported by the first node.

[0158] Optionally, the first node can also be registered with other nodes in addition to the second node. For example, the first node sends second registration information, and one or more of the following nodes: a DU, a RU, a core network device, an OAM, or a RIC receives the second registration information. The second registration information includes the capability information of the first node.

[0159] Exemplarily, the first node and the DU can be connected through a second interface, in which case the first node sends the second registration information to the DU directly through the second interface, and correspondingly, the DU receives the second registration information from the first node through the second interface. Alternatively, there is no interface between the first node and the DU, in which case the first node can send the second registration information to the DU through the second node, it can be understood that the first node sends the second registration information to the second node first, and the second node forwards the second registration information to the DU after receiving the second registration information. After receiving the second registration information, the DU completes the registration of the first node according to the second registration information.

[0160] Exemplarily, the first node and the RU can be connected through a third interface, in which case the first node sends the second registration information to the RU directly through the third interface, and correspondingly, the RU receives the second registration information from the first node through the third interface. Alternatively, there is no interface between the first node and the RU, in which case the first node can send the second registration information to the RU through the second node, it can be understood that the first node sends the second registration information to the second node first, and the second node forwards the second registration information to the RU after receiving the second registration information. After receiving the second registration information, the RU completes the registration of the first node according to the second registration information.

[0161] Exemplarily, the first node and the core network device can be connected through a fourth interface, in which case the first node sends the second registration information to the core network device directly through the fourth interface, and correspondingly, the core network device receives the second registration information from the first node through the fourth interface. Alternatively, there is no interface between the first node and the core network device, in which case the first node can send the second registration information to the core network device through the second node, it can be understood that the first node sends the second registration information to the second node first, and the second node forwards the second registration information to the core network device after receiving the second registration information. After receiving the second registration information, the core network device completes the registration of the first node according to the second registration information.

[0162] Exemplarily, the first node and the OAM can be connected through a fifth interface, in which case the first node sends the second registration information to the OAM directly through the fifth interface, and correspondingly, the OAM receives the second registration information from the first node through the fifth interface. Alternatively, the first node and the OAM have no interface therebetween, in which case the first node can send the second registration information to the OAM through the second node. It can be understood that the first node sends the second registration information to the second node first, and the second node forwards the second registration information to the OAM after receiving the second registration information. The OAM completes the registration of the first node according to the second registration information after receiving the second registration information.

[0163] Exemplarily, the first node and the RIC can be connected through a sixth interface, in which case the first node sends the second registration information to the RIC directly through the sixth interface, and correspondingly, the RIC receives the second registration information from the first node through the sixth interface. Alternatively, the first node and the RIC have no interface therebetween, in which case the first node can send the second registration information to the RIC through the second node. It can be understood that the first node sends the second registration information to the second node first, and the second node forwards the second registration information to the RIC after receiving the second registration information. The RIC completes the registration of the first node according to the second registration information after receiving the second registration information.

[0164] Further optionally, the second node needs to instruct the first node to complete the registration with one or more of the DU, the RU, the core network device, the OAM or the RIC. Exemplarily, the second node sends instruction information to the first node before the first node sends the second registration information, and correspondingly, the first node receives the instruction information from the second node, which is used to instruct the first node to complete the registration with one or more of the DU, the RU, the core network device, the OAM or the RIC. Alternatively, the second node can also not need to instruct, and the first node can complete the registration with one or more of the DU, the RU, the core network device, the OAM or the RIC spontaneously.

[0165] Optionally, after the second node completes the registration of the first node, the terminal device can also be instructed to complete the registration with the first node. Exemplarily, the second node sends third registration information, and correspondingly, the terminal device receives the third registration information, which includes the capability information of the first node. The terminal device completes the registration between the first node and the terminal device through the third registration information. Further optionally, the second node can send the third registration information in one of the following ways:

[0166] Manner one: the second node sends a cell broadcast message, and the third registration information is carried in the cell broadcast message. It can be understood that the first node can be registered and the capability information of the first node is indicated through the cell broadcast message. The terminal device receiving the cell broadcast message can complete the registration with the first node based on the third registration information according to its own needs.

[0167] Manner two: the second node sends a radio resource control (RRC) message to the terminal device, and the third registration information is carried in the RRC message. It can be understood that when the terminal device receives the RRC message, the terminal device will complete the registration with the first node based on the third registration information carried in the RRC message.

[0168] In one example, after the first node completes the registration with one or more nodes described above, if the capability of the first node is updated, the first node can also provide the corresponding updated capability information to the registered nodes. Optionally, the capability update of the first node can mean that the first node supports a new AI function, or the performance of the AI function of the first node is improved. The first node can obtain a new AI model through model training or through OAM or a core network device. For example, the first node can periodically send capability information to the nodes it registers, or it can send capability information to the nodes it registers after meeting the corresponding conditions, for example, the conditions can be one or more of the following:

[0169] (1) The first node supports a new AI function, that is, the first node supports an AI function, AI model, or AI use case that it did not have or support before. For example, the OAM or core network device provides a new AI model to the first node, and the first node can implement a new AI function through the new AI model.

[0170] (2) The performance of the AI function, AI model, or AI use case supported by the first node improves by more than a preset value, for example, the performance can refer to one or more of accuracy, inference rate, or precision.

[0171] 402. The first node generates first information based on an AI function.

[0172] Generating first information based on an AI function can also be understood as the first node obtaining first information through inference by an AI model.

[0173] Optionally, the first information can be result information or strategy information obtained through AI model inference. For example, assuming that the AI model is applied to base station energy saving, the first node can input the load, energy consumption, energy efficiency information of the base station and the base station neighborhood, and the trajectory information, measurement results and the like of the terminal device into the AI model to obtain the first information, which can be the predicted future energy consumption of the base station, or can also be the energy saving strategy determined according to the future energy consumption of the base station.

[0174] In a possible implementation, before generating the first information based on the AI function, the first node also needs to obtain second information, which is used for model training or model inference, wherein the second information includes one or more of the following information: third information from the terminal device, fourth information from the core network device or OAM, fifth information from the third node, and sixth information from the fourth node. The third node is a RAN node, for example, the third node includes one or more of the second node, DU or RU. The fourth node has an AI function, and the fourth node is registered with the fifth node, which is one or more nodes other than the second node. Further optionally, the fifth node is a neighboring node of the second node. For example, when the second node is an access network device, the fifth node is a neighboring access network device of the second node; when the second node is a CU, the fifth node is a neighboring CU of the second node.

[0175] For example, the third information is sent by the terminal device to the first node through the second node, that is, the terminal device first sends the third information to the second node, and the second node sends the third information to the first node after receiving the third information.

[0176] Optionally, the third information indicates one or more of the following information:

[0177] (1) AI capability information of the terminal device. For example, the AI capability information can include one or more of the AI function, AI model or AI use case supported by the terminal device (or needed / being executed).

[0178] (2) One or more of the following information of the terminal device: computing capability, energy consumption, energy efficiency information, moving speed, moving path, number of antennas, and beam weighting mode.

[0179] (3) Service information of the terminal device. For example, the service information includes one or more of the following: Quality of Service (QoS) requirement, data radio bearer (DRB) configuration, and service type supported by the terminal device.

[0180] (4) Measurement result of the terminal device. For example, the measurement result includes measurement result of the terminal device on a reference signal.

[0181] For example, when the first node has an interface with the core network device or the OAM, the first node can directly receive the fourth information from the core network device or the OAM through the corresponding interface. When the first node does not have an interface with the core network device or the OAM, the first node can receive the fourth information from the core network device or the OAM through the second node. It can be understood that the core network device or the OAM sends the fourth information to the second node, and the second node forwards the fourth information to the first node after receiving the fourth information.

[0182] Optionally, the fourth information indicates one or more of the following information:

[0183] (1) AI capability information of the core network device or the OAM. For example, the AI capability information can include one or more of the AI functions, AI models or AI use cases supported by (or needed / being executed by) the core network device or the OAM.

[0184] (2) One or more of the computing capability, energy consumption, energy efficiency of the core network device or the OAM.

[0185] (3) Service requirement of the core network device or the OAM. For example, the service requirement includes one or more of the following: execution priority corresponding to one or more AI use cases respectively, execution priority corresponding to one or more AI functions respectively, execution priority corresponding to one or more AI models respectively, whether to prioritize network performance, whether to prioritize network energy efficiency, rate of data transmission needed to be performed to the terminal device, delay requirement, etc.

[0186] For example, when the first node has an interface with the third node, the first node can directly receive the fifth information from the third node through the corresponding interface, the third node including one or more of the second node, the DU or the RU. Alternatively, when the first node does not have an interface with the third node, the first node can receive the fifth information from the third node through the second node, the third node including one or more of the DU or the RU. It can be understood that the third node sends the fifth information to the second node, and the second node forwards the fifth information to the first node after receiving the fifth information.

[0187] Optionally, the fifth information indicates one or more of the following information:

[0188] (1) AI capability information of the third node. For example, the AI capability information can include one or more of AI functions, AI models, or AI use cases supported by (or needed / being executed by) the third node.

[0189] (2) One or more of computing capability of the third node, energy consumption of the third node, energy efficiency information of the third node, geographical location of the third node, number of antennas of the third node, antenna form of the third node, or beam weighting manner of the third node.

[0190] (3) Resource information of the third node, for example, the resource information includes current resource usage state of the third node or number of connected terminal devices.

[0191] (4) Measurement result of the third node. For example, the measurement result includes L1 or L3 measurement result for one or more terminal devices.

[0192] For example, when there is an interface between the first node and the fourth node, the first node can directly receive the sixth information from the fourth node through the corresponding interface. For another example, when there is no interface between the first node and the fourth node, the first node receives the sixth information from the fourth node through the fifth node and the second node. It can be understood that the fourth node can first send the sixth information to the fifth node, the fifth node forwards the sixth information to the second node after receiving the sixth information, and the second node forwards the sixth information to the first node after receiving the sixth information.

[0193] Optionally, the sixth information indicates one or more of the following information:

[0194] (1) AI capability information of the fourth node. For example, the AI capability information can include one or more of AI functions, AI models, or AI use cases supported by (or needed / being executed by) the fourth node.

[0195] (2) One or more of computing capability of the fourth node, energy consumption of the fourth node, or energy efficiency information of the fourth node.

[0196] In one example, before determining the first information, the second node determines whether the built-in AI model can meet the requirement of generating the first information, if the AI model can meet the requirement, the corresponding first information is determined. If not, data can be collected from other nodes, for example, as described above, the first node also obtains the second information, and then performs model training based on the second information. If the local model training cannot be completed, for example, due to the limited computing power of the first node, the first node can send a first request to the OAM or the core network device, the first request being used to request a new AI model. Optionally, the reason for requesting the AI model can also be indicated in the first request.

[0197] 403、The first node sends the first information.

[0198] For example, the terminal device receives the first information, for example, the terminal device receives the first information from the first node through the second node. It can be understood that the first node sends the first information to the second node, and the second node forwards the first information to the terminal device after receiving the first information. The first information indicates one or more of the following information:

[0199] (1) One or more of the AI use cases, AI functions, or AI models to be executed by the terminal device. Optionally, the AI use cases, AI functions, or AI models to be executed by the terminal device can be indicated by an identifier (ID) or an ID list, etc. For example, assuming that the terminal device supports AI use cases including AI use case 1 and AI use case 2, the identifier of AI use case 1 is identifier 1, and the identifier of AI use case 2 is identifier 2, the first information can indicate that the terminal device needs to execute AI use case 2 by carrying identifier 2.

[0200] (2) AI inference result required by the terminal device.

[0201] (3) One or more of the lifecycle management (LCM) related information of the AI use case of the terminal device, the LCM related information of the AI function of the terminal device, or the LCM related information of the AI model of the terminal device. Taking the LCM of the AI use case as an example, it can include activating, deactivating, switching, or reverting the AI use case, etc.

[0202] Exemplarily, the third node receives the first information. For example, the third node has an interface with the first node, the third node can receive the first information from the first node directly through the corresponding interface, the third node includes one or more of the second node, the DU or the RU. For another example, the third node has no interface with the first node, the third node can receive the first information from the first node through the second node, it can be understood that the first node sends the first information to the second node, the second node receives the first information and forwards the first information to the third node, the third node includes one or more of the DU or the RU. The first information includes one or more of the following information:

[0203] (1) Recommended downlink beam weighting mode; (2) Predicted optimal access beam index of the terminal device (further optionally, predicted Reference Signal Receiving Power (RSRP) corresponding to the terminal device can also be included); (3) Positioning assistance information of the terminal device (for example, predicted LOS and / or NLOS); (4) Position information of the terminal device; (5) Energy saving execution mode; (6) Load balancing execution mode; (7) Path prediction result of the terminal device; (8) Recommended execution strategy of terminal device switching; (9) Transmission configuration of uplink and downlink data transmission; (10) Antenna form adjustment; (11) Modulation and demodulation scheme configuration.

[0204] Exemplarily, the fourth node receives the first information, the fourth node is the same as described in the foregoing content, that is, the fourth node has an AI function, and the fourth node is registered in the neighboring node of the second node. For example, the fourth node has an interface with the first node, the fourth node can receive the first information from the first node directly through the corresponding interface. For another example, the fourth node has no interface with the first node, the fourth node receives the first information from the first node through the fifth node and the second node. The fifth node is the same as described in the foregoing content, the fifth node is one or more nodes except the second node, and the fourth node is registered in the fifth node. Further optionally, the fifth node is a neighboring node of the second node. It can be understood that the first node sends the first information to the second node, the second node receives the first information and forwards the first information to the fifth node, and the fifth node receives the first information and forwards the first information to the fourth node. The first information indicates one or more of the following information:

[0205] (1) The prediction result required by the fourth node. For example, the prediction result can include one or more of the load prediction of the fourth node, the energy consumption or energy efficiency prediction, and the path prediction result of the terminal device under the fifth node.

[0206] (2) the execution strategy of the fifth node. The execution strategy can include one or more of a power saving strategy, a handover strategy of the terminal device, or a coverage capacity adjustment strategy. Further optionally, the first information can also indicate the execution strategy of the second node.

[0207] For example, the core network device or the OAM has an interface with the first node, and the core network device or the OAM can directly receive the first information from the first node through the corresponding interface. When the core network device or the OAM does not have an interface with the first node, the core network device or the OAM can receive the first information from the first node through the second node. It can be understood that the first node sends the first information to the second node, and the second node forwards the first information to the core network device or the OAM after receiving the first information. The first information indicates one or more of the following information:

[0208] (1) one or more of the transmission capacity of the RAN side, the handover state prediction of the terminal device, the path prediction information of the terminal device, or the path prediction auxiliary information of the terminal device.

[0209] (2) predicting the service demand of the terminal device. For example, the service demand can be a transmission demand (such as data volume, transmission delay, or service type, etc.).

[0210] In a possible implementation, the first node is closed when a first condition is met. The first condition includes one or more of the following:

[0211] (1) the first node receives a first deactivation indication from the second node, the first deactivation indication being used to indicate to close the first node. Optionally, the second node sends the first deactivation indication to the first node when a second condition is met, and the second condition includes one or more of the following:

[0212] (1.1) the second node receives a second deactivation indication from an operation and maintenance (OAM), the second deactivation indication being used to indicate to close the first node.

[0213] (1.2) The inference accuracy of the first node or the AI model or AI function of the first node is less than or equal to a first threshold. The inference accuracy of the first node refers to the inference accuracy of the first node as a whole, which can be understood as the inference accuracy of all AI models or all AI functions of the first node. The inference accuracy of the AI model or AI function of the first node refers to the inference accuracy of a certain AI model or AI function of the first node. Optionally, the inference accuracy can be determined by the second node itself according to the inference result and the true result sent by the first node. Or the inference accuracy can be determined by the first node, for example, the first node sends the inference accuracy to the second node after determining the inference accuracy, and the second node determines whether to send the second deactivation instruction according to the inference accuracy. The inference accuracy can be the inference accuracy of the first node as a whole, or the inference accuracy of a certain AI model or AI function of the first node.

[0214] (1.3) The performance gain of the first node or the AI model or AI function of the first node is less than or equal to a second threshold. The performance gain of the first node refers to the performance gain of the first node as a whole, which can be understood as the performance gain of all AI models or all AI functions of the first node. The performance gain of the AI model or AI function of the first node refers to the performance gain of a certain AI model or AI function of the first node. For example, the first node sends the performance gain to the second node after determining the performance gain, and the second node determines whether to send the second deactivation instruction according to the performance gain. The performance gain can be the performance gain of the first node as a whole, or the performance gain of a certain AI model or AI function of the first node.

[0215] (1.4) The calculation overhead or storage overhead of the first node or the AI model or AI function of the first node is greater than a third threshold. The calculation overhead or storage overhead of the first node refers to the calculation overhead or storage overhead of the first node as a whole, which can be understood as the calculation overhead or storage overhead of all AI models or all AI functions of the first node. The calculation overhead or storage overhead of the AI model or AI function of the first node refers to the calculation overhead or storage overhead of a certain AI model or AI function of the first node. For example, the first node sends the calculation overhead or storage overhead to the second node after determining the calculation overhead or storage overhead, and the second node determines whether to send the second deactivation instruction according to the calculation overhead or storage overhead. The calculation overhead or storage overhead can be the calculation overhead or storage overhead of the first node as a whole, or the calculation overhead or storage overhead of a certain AI model or AI function of the first node.

[0216] (2) The inference accuracy of the first node or the AI model or AI function of the first node is less than or equal to a first threshold. For example, the first node determines first information according to the AI function, and the first information can include an inference result or an execution strategy corresponding to the inference result. After the first node sends the first information, the first node can receive feedback of a real result from one or more nodes such as a terminal device, a second node, a DU, a RU, a core network device, or an OAM. The first node can compare the real result with the inference result to determine the inference accuracy, and compare the inference accuracy with the first threshold to determine whether to shut down the first node.

[0217] (3) The performance gain of the first node or the AI model or AI function of the first node is less than or equal to a second threshold.

[0218] (4) The calculation overhead or storage overhead of the first node or the AI model or AI function of the first node is greater than or equal to a third threshold.

[0219] In the above-described scenarios, shutting down the first node is beneficial to save energy consumption. At the same time, shutting down the first node does not affect the normal communication between other nodes.

[0220] In an example, the first node is shut down, specifically, one or more of the following is shut down: all or part of the AI function, the protocol stack, the AI model, or the result provided by AI inference of the first node.

[0221] In a possible implementation, the first node can interact with AI-related information through a first protocol layer, or it can also be understood that the first protocol layer has an AI function.

[0222] Taking the first node sending first information as an example, the first node generates first information through the first protocol layer; then, the first node sends the first information to a second protocol layer through the first protocol layer; then, the first node encapsulates the first information to obtain a first data unit through the second protocol layer; finally, the first node sends the first data unit through the second protocol layer.

[0223] Taking the first node receiving second information as an example, the first node receives a second data unit through the second protocol layer; then, the first node decapsulates the second data unit to obtain second information through the second protocol layer; then, the second node sends the second information to the first protocol layer through the second protocol layer.

[0224] Optionally, the first data unit and / or the second data unit can be a container or signaling.

[0225] Optionally, the first protocol layer can be a newly defined protocol layer, or the first protocol layer can be one of the following protocol layers: a General Packet Radio Service tunneling protocol user plane (GTP-U) layer, a stream control transport protocol (SCTP) layer, an RRC layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, and a physical (PHY) layer. Further optionally, the information generated by the first protocol layer can be encapsulated via a second protocol layer, and the second protocol layer can be one of the following protocol layers: a GTP-U layer, an SCTP layer, a PDCP layer, an RLC layer, a MAC layer, or a PHY layer.

[0226] The process in which the first node interacts with other nodes via the first protocol layer can be seen from the following examples:

[0227] For example, a protocol stack architecture between the second node and the first node is shown in FIG. 5, and the second node side and the first node side include the first protocol layer and the second protocol layer, and the second protocol layer can be an SCTP layer or a GTP-U layer. The information exchanged between the first node and the second node can be a control plane message carried by an SCTP protocol, or a user plane message carried by a GTP-U protocol.

[0228] In this case, the specific process in which the first node sends the first information to the second node is as follows:

[0229] Step 1: The first node generates the first information via the first protocol layer.

[0230] Step 2: The first node sends the first information to the second protocol layer via the first protocol layer.

[0231] Step 3: The first node encapsulates the first information to obtain a first data unit via the second protocol layer.

[0232] Step 4: The first node sends the first data unit via the second protocol layer, and correspondingly, the second node receives the first data unit via the second protocol layer.

[0233] Step 5: The second node decapsulates the first data unit via the second protocol layer to obtain the first information.

[0234] Step 6, the second node sends the first information to the first protocol layer through the second protocol layer.

[0235] Step 7, the second node reads the first information through the first protocol layer.

[0236] For example, a protocol stack architecture between the terminal device and the first node is shown in FIG. 6A, the terminal device communicates with the first node through the second node, and the protocol layers between the terminal device and the first node are peer-to-peer, that is, the first protocol layer and the second protocol layer on the first node side are one-to-one corresponding to the first protocol layer and the second protocol layer on the terminal device side. Of course, the first node and the terminal device can also include other protocol layers, and are one-to-one corresponding, which are omitted in FIG. 6A for brevity.

[0237] In this case, the specific process in which the first node sends the first information to the terminal device is as follows:

[0238] Step 1, the first node generates the first information through the first protocol layer.

[0239] Step 2, the first node sends the first information to the second protocol layer through the first protocol layer.

[0240] Step 3, the first node encapsulates the first information to obtain a first data unit through the second protocol layer.

[0241] Step 4, the first node sends the first data unit through the second protocol layer, and correspondingly, the second node receives the first data unit through the second protocol layer.

[0242] Step 5, the second node sends the first data unit through the second protocol layer, and correspondingly, the terminal device receives the first data unit through the second protocol layer.

[0243] Step 6, the terminal device decapsulates the first data unit through the second protocol layer to obtain the first information.

[0244] Step 7, the terminal device sends the first information to the first protocol layer through the second protocol layer.

[0245] Step 8, the terminal device reads the first information through the first protocol layer.

[0246] For example, another protocol stack architecture between the terminal device and the first node is shown in FIG. 6B, and the protocol layers between the terminal device and the first node are not peer-to-peer. The terminal device side includes the first protocol layer, the PDCP layer, the RLC layer, the MAC layer, and the PHY layer. The first node side includes the first protocol layer and the second protocol layer. The second protocol layer is the SCTP layer or the GTP-U layer.

[0247] In this case, the specific process in which the first device sends the first information to the terminal device is as follows:

[0248] Step 1: The first node generates first information through the first protocol layer.

[0249] Step 2: The first node sends the first information to the SCTP layer or the GTP-U layer through the first protocol layer.

[0250] Step 3: The first node encapsulates the first information through the SCTP layer or the GTP-U layer to obtain a first data unit.

[0251] Step 4: The first node sends the first data unit through the SCTP layer or the GTP-U layer, and correspondingly, the second node receives the first data unit through the SCTP layer or the GTP-U layer.

[0252] Step 5: The second node encapsulates the first data unit through the PDCP layer, the RLC layer, the MAC layer, and the PHY layer to obtain a third data unit.

[0253] Step 6: The second node sends the third data unit through the PHY layer, and correspondingly, the terminal device receives the third data unit through the PHY layer.

[0254] Step 7: The terminal device decapsulates the third data unit through the PDCP layer, the RLC layer, the MAC layer, and the PHY layer to obtain the first information.

[0255] Step 8: The terminal device sends the first information to the first protocol layer through the PDCP layer.

[0256] Step 9: The terminal device reads the first information through the first protocol layer.

[0257] Another exemplary protocol stack architecture between the terminal device and the first node is shown in FIG. 6C, and the protocol layers between the terminal device and the first node are not equal. The protocol layers included on the terminal device side include the first protocol layer, the RRC layer, the PDCP layer, the RLC layer, the MAC layer, and the PHY layer. The protocol layers included on the first node side include the first protocol layer and the second protocol layer. The second protocol layer is the SCTP layer or the GTP-U layer.

[0258] Step 1: The first node generates first information through the first protocol layer.

[0259] Step 2: The first node sends the first information to the SCTP layer or the GTP-U layer through the first protocol layer.

[0260] Step 3: The first node encapsulates the first information through the SCTP layer or the GTP-U layer to obtain a first data unit.

[0261] Step 4, the first node sends the first data unit through the SCTP layer or the GTP-U layer, and correspondingly, the second node receives the first data unit through the SCTP layer or the GTP-U layer.

[0262] Step 5, the second node encapsulates the first data unit through the RRC layer, the PDCP layer, the RLC layer, the MAC layer and the PHY layer to obtain a third data unit.

[0263] Step 6, the second node sends the third data unit through the PHY layer, and correspondingly, the terminal device receives the third data unit through the PHY layer. The third data unit can also be understood as an RRC message, that is, the second node transmits the first information through the RRC message.

[0264] Step 7, the terminal device decapsulates the third data unit through the RRC layer, the PDCP layer, the RLC layer, the MAC layer and the PHY layer to obtain the first information.

[0265] Step 8, the terminal device sends the first information to the first protocol layer through the RRC layer.

[0266] Step 9, the terminal device reads the first information through the first protocol layer.

[0267] Exemplarily, a protocol stack architecture between the DU and the first node is shown in FIG. 7A. The DU and the first node have an interface and can directly communicate. The DU side and the first node side include a first protocol layer and a second protocol layer. The second protocol layer is a GTP-U layer.

[0268] In this case, the specific process in which the first node sends the first information to the DU is as follows:

[0269] Step 1, the first node generates the first information through the first protocol layer.

[0270] Step 2, the first node sends the first information to the second protocol layer through the first protocol layer.

[0271] Step 3, the first node encapsulates the first information through the second protocol layer to obtain a first data unit.

[0272] Step 4, the first node sends the first data unit through the second protocol layer, and correspondingly, the DU receives the first data unit through the second protocol layer.

[0273] Step 5, the DU decapsulates the first data unit through the second protocol layer to obtain the first information.

[0274] Step 6, the DU sends the first information to the first protocol layer through the second protocol layer.

[0275] Step 7, the DU reads the first information through the first protocol layer.

[0276] Exemplarily, another protocol stack architecture between the DU and the first node is shown in FIG. 7B, the DU communicates with the first node through the second node, and the DU side and the first node side include the first protocol layer and the second protocol layer, and the second protocol layer is an SCTP layer.

[0277] In this case, the specific process in which the first node sends the first information to the DU is as follows:

[0278] Step 1, the first node generates the first information through the first protocol layer.

[0279] Step 2, the first node sends the first information to the second protocol layer through the first protocol layer.

[0280] Step 3, the first node encapsulates the first information to obtain a first data unit through the second protocol layer.

[0281] Step 4, the first node sends the first data unit through the second protocol layer, and correspondingly, the second node receives the first data unit through the second protocol layer.

[0282] Step 5, the second node sends the first data unit through the second protocol layer, and correspondingly, the DU receives the first data unit through the second protocol layer.

[0283] Step 6, the DU decapsulates the first data unit through the second protocol layer to obtain the first information.

[0284] Step 7, the DU sends the first information to the first protocol layer through the second protocol layer.

[0285] Step 8, the DU reads the first information through the first protocol layer.

[0286] Exemplarily, one protocol stack architecture between the fourth node and the first node is shown in FIG. 8A, the fourth node and the first node both have AI functions, and the first node can be connected with the fourth node through an interface and can directly communicate. The fourth node side and the first node side include the first protocol layer and the second protocol layer, and the second protocol layer is a GTP-U layer.

[0287] In this case, the specific process in which the first node sends the first information to the fourth node is as follows:

[0288] Step 1, the first node generates the first information through the first protocol layer.

[0289] Step 2, the first node sends the first information to the second protocol layer through the first protocol layer.

[0290] Step 3, the first node encapsulates the first information to obtain a first data unit through the second protocol layer.

[0291] Step 4, the first node sends the first data unit through the second protocol layer, and correspondingly, the fourth node receives the first data unit through the second protocol layer.

[0292] Step 5, the fourth node decapsulates the first data unit through the second protocol layer to obtain the first information.

[0293] Step 6, the fourth node sends the first information to the first protocol layer through the second protocol layer.

[0294] Step 7, the fourth node reads the first information through the first protocol layer.

[0295] Exemplarily, another protocol stack architecture between the fourth node and the first node is shown in FIG. 8B, the first node and the fourth node communicate through the second node and the fifth node, the fifth node is a node registered by the fourth node, and the fifth node and the second node are adjacent nodes, and the fifth node and the second node can interact through the XN interface. The fourth node side and the first node side include the first protocol layer and the second protocol layer, and the second protocol layer is an SCTP layer.

[0296] In this case, the specific process in which the first node sends the first information to the fourth node is as follows:

[0297] Step 1, the first node generates the first information through the first protocol layer.

[0298] Step 2, the first node sends the first information to the second protocol layer through the first protocol layer.

[0299] Step 3, the first node encapsulates the first information through the second protocol layer to obtain the first data unit.

[0300] Step 4, the first node sends the first data unit through the second protocol layer, and correspondingly, the second node receives the first data unit through the second protocol layer.

[0301] Step 5, the second node sends the first data unit through the second protocol layer, and correspondingly, the fifth node receives the first data unit through the second protocol layer.

[0302] Step 6, the fifth node sends the first data unit through the second protocol layer, and correspondingly, the fourth node receives the first data unit through the second protocol layer.

[0303] Step 7, the fourth node decapsulates the first data unit through the second protocol layer to obtain the first information.

[0304] Step 8, the fourth node sends the first information to the first protocol layer through the second protocol layer.

[0305] Step 9, the fourth node reads the first information through the first protocol layer.

[0306] The device provided by the embodiment of the present application will be introduced below.

[0307] The device is divided into functional modules according to the method embodiments of the present application. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The integrated module can be realized in the form of hardware or in the form of a software functional module. It should be noted that the division of the modules in the present application is illustrative, and is only a logical functional division. In actual implementation, another division mode can be used. The device of the embodiment of the present application will be described in detail below with reference to FIGS. 9-11.

[0308] FIG. 9 is a structural schematic diagram of a device provided by an embodiment of the present application. As shown in FIG. 9, the device includes a processing module 901 and a transceiver module 902. The transceiver module 902 can realize corresponding communication functions, and the processing module 901 is used to realize corresponding processing functions. The transceiver module 902 can also be referred to as an interface, a communication interface, a communication module, or an input and output interface, etc.

[0309] In some embodiments of the present application, the device can be used to perform the actions performed by the first node in the above method embodiments. At this time, the first node can be the first node itself or a chip or functional module configured in the first node, etc. The transceiver module 902 is used to perform the transceiver-related operations or input and output-related operations of the first node in the above method embodiments, and the processing module 901 is used to perform the processing-related operations of the first node in the above method embodiments.

[0310] For example, the transceiver module 902 is configured to receive an activation indication from a second node located at a network side, the activation indication being used to indicate to activate the first node, and the first node having an artificial intelligence (AI) function; the processing module 901 is configured to generate first information based on the AI function; and the transceiver module 902 is further configured to send the first information.

[0311] For example, the processing module 901 is further configured to close the first node when a first condition is met.

[0312] For example, the transceiver module 902 is further configured to send first registration information to the second node, the first registration information including capability information of the first node, and the capability information indicating that the first node has the AI function.

[0313] For example, the transceiver module 902 is further configured to send second registration information to one or more nodes in a DU, an RU, a core network device, an OAM, or a RIC, or send the second registration information to the one or more nodes in the DU, the RU, the core network device, the OAM, or the RIC through the second node, the second registration information including the capability information of the first node.

[0314] The transceiver module 902 is configured to receive indication information from the second node, the indication information being used to indicate completion of registration with one or more of the DU, the RU, the core network device, the OAM, or the RIC.

[0315] In some embodiments of the present application, the apparatus of FIG. 9 can be configured to perform the actions performed by the second node in the above method embodiments. In this case, the apparatus can be the second node itself or a chip or functional module configured in the second node. The transceiver module 902 is configured to perform the transceiving-related operations of the second node in the above method embodiments, and the processing module 901 is configured to perform the processing-related operations of the second node in the above method embodiments.

[0316] The transceiver module 902 is configured to send an activation indication to the first node located at the network side, the activation indication being used to indicate activation of the first node, and the transceiver module 902 is further configured to receive first information from the first node, the first information being generated based on the AI function.

[0317] The transceiver module 902 is further configured to send a first deactivation indication to the first node, the first deactivation indication being used to indicate deactivation of the first node.

[0318] The transceiver module 902 is further configured to receive second registration information from the first node, and the transceiver module 902 is further configured to send the second registration information to one or more of the DU, the RU, the core network device, the OAM, or the RIC, the second registration information including capability information of the first node.

[0319] The transceiver module 902 is further configured to send fifth information to the first node, the fifth information indicating one or more of the following: AI capability information of the second node, computing capability of the second node, energy consumption of the second node, energy efficiency information of the second node, geographic location of the second node, number of antennas of the second node, beam weighting manner of the second node, resource information of the second node, or measurement result of the second node.

[0320] In the above embodiments, the specific descriptions of the terms or steps can refer to the descriptions in the above method embodiments, which will not be repeated here.

[0321] The specific descriptions of the transceiver module and the processing module in the above embodiments are only examples. For the specific functions or steps performed by the transceiver module and the processing module, refer to the above method embodiments, which will not be repeated here.

[0322] It can be understood that the division of the modules in the above apparatus is only a logical function division, each function can correspond to a function module, or two or more functions can be integrated in a function module. In actual implementation, all or part of the modules can be integrated into one physical entity, or can be distributed in different physical entities. In addition, the above function modules can be implemented in the form of hardware, or in the form of software, or in the form of hardware combined with software.

[0323] In one example, the functional units in any of the above apparatuses can be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0324] The above introduces the apparatus of the embodiments of the present application, and the following introduces the possible product form of the apparatus. Any form of product that has the functions of the apparatus described in FIG. 9 falls within the protection scope of the embodiments of the present application. The following introduction is only for example, and does not limit the product form of the apparatus of the embodiments of the present application.

[0325] In a possible implementation, in the apparatus shown in FIG. 9, the processing module 901 can be one or more processing circuits, and the transceiver module 902 can be a transceiver circuit, or the transceiver module 902 can also be a sending module and a receiving module, the sending module can be a sending circuit, and the receiving module can be a receiving circuit, which are integrated in one device, such as a transceiver circuit. In the embodiments of the present application, the processing circuit and the transceiver circuit can be coupled, and the connection mode of the processing circuit and the transceiver circuit is not limited in the embodiments of the present application. In the process of executing the above method, the process of sending information in the above method can be the process of outputting the above information by the processing circuit. When the above information is output, the processing circuit outputs the above information to the transceiver circuit, so as to be transmitted (or output) by the transceiver circuit. After the above information is output by the processing circuit, it can also need to be processed further, and then reach the transceiver circuit. Similarly, the process of receiving information in the above method can be the process of receiving the input above information by the processing circuit. When the processing circuit receives the input information, the transceiver circuit receives the above information and inputs it to the processing circuit. Further, after the transceiver circuit receives the above information, the above information can need to be processed further, and then input to the processing circuit.

[0326] FIG. 10 is a structural schematic diagram of an apparatus provided in the embodiments of the present application. As shown in FIG. 10, the apparatus 100 includes one or more processing circuits 1020 and a transceiver circuit 1010.

[0327] In some embodiments of the present application, the apparatus can be used to execute the steps or methods or functions executed by the first node, for example, the processing circuit 1020 can be used to execute the functions or steps implemented by the processing module 901 shown in FIG. 9, and the transceiver circuit 1010 can be used to execute the functions or steps implemented by the transceiver module 902 shown in FIG. 9. For specific description of the processing circuit 1020 and the transceiver circuit 1010, reference can be made to FIG. 9 or the method embodiments shown above, which will not be described in detail here.

[0328] In some embodiments of the present application, the apparatus can be used to execute the steps or methods or functions executed by the first node, for example, the processing circuit 1020 can be used to execute the functions or steps implemented by the processing module 901 shown in FIG. 9, and the transceiver circuit 1010 can be used to execute the functions or steps implemented by the transceiver module 902 shown in FIG. 9. For specific description of the processing circuit 1020 and the transceiver circuit 1010, reference can be made to FIG. 9 or the method embodiments shown above, which will not be described in detail here.

[0329] For example, the processing circuit can be one or more processors, or all or part of the circuit of one or more processors. The transceiver circuit can be a transceiver, or an input / output circuit, or an interface circuit, etc.

[0330] Exemplarily, in each implementation of the apparatus shown in FIG. 10, the transceiver circuitry can include a receiver configured to perform the functions (or operations) of receiving and a transmitter configured to perform the functions (or operations) of transmitting. The transceiver circuitry is configured to communicate with other devices / apparatuses via a transmission medium.

[0331] Optionally, the apparatus 100 can further include one or more memories 1030 configured to store program instructions and / or data. The memory 1030 is coupled to the processing circuitry 1020. The coupling between the apparatus, units or modules in embodiments of the present application can be indirect coupling or communication connection between the apparatus, units or modules, which can be electrical, mechanical or other form, for information interaction between the apparatus, units or modules. The processing circuitry 1020 can operate in cooperation with the memory 1030. The processing circuitry 1020 can execute program instructions stored in the memory 1030. Optionally, at least one of the one or more memories can be included in the processing circuitry.

[0332] The specific connection medium between the transceiver circuitry 1010, the processing circuitry 1020 and the memory 1030 in embodiments of the present application is not limited. In FIG. 10, the memory 1030, the processing circuitry 1020 and the transceiver circuitry 1010 are connected through the bus 1040, which is represented by a thick line in FIG. 10, and the connection mode between other components is only schematically illustrated and is not limited. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, only one thick line is used in FIG. 10, but it does not mean that there is only one bus or only one type of bus.

[0333] In embodiments of the present application, the processing circuitry can be a general-purpose processing circuitry, a digital signal processing circuitry, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in embodiments of the present application. The general-purpose processing circuitry can be a micro-processing circuitry or any conventional processing circuitry, etc. The steps of the methods disclosed in conjunction with the embodiments of the present application can be directly embodied as hardware processing circuitry executed, or a combination of hardware and software modules in the processing circuitry executed, etc.

[0334] The memory in the embodiments of the present application can include, but is not limited to, a non-volatile memory such as a hard disk drive (HDD) or a solid-state drive (SSD), a random access memory (RAM), an erasable programmable ROM (EPROM), a read-only memory (ROM), a compact disc read-only memory (CD-ROM), and the like. The memory is any storage medium that can be used to carry or store program codes in the form of instructions or data structures and can be read and / or written by a computer (such as the device shown in the present application and the like). The memory in the embodiments of the present application can also be a circuit or any other device capable of realizing a storage function, used for storing program instructions and / or data.

[0335] For example, the processing circuit 1020 is mainly used for processing communication protocols and communication data, and controlling the whole device, executing software programs, and processing data of the software programs. The memory 1030 is mainly used for storing software programs and data. The transceiver circuit 1010 can include a control circuit and an antenna, and the control circuit is mainly used for converting baseband signals and radio frequency signals and processing radio frequency signals. The antenna is mainly used for receiving and transmitting radio frequency signals in the form of electromagnetic waves. The input and output device, such as a touch screen, a display screen, a keyboard, and the like, is mainly used for receiving user input data and outputting data to the user.

[0336] When the device is powered on, the processing circuit 1020 can read the software program in the memory 1030, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processing circuit 1020 performs baseband processing on the data to be transmitted, and outputs the baseband signal to the radio frequency circuit. The radio frequency circuit converts the baseband signal into a radio frequency signal, and transmits the radio frequency signal in the form of electromagnetic waves through the antenna. When data is transmitted to the device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processing circuit 1020. The processing circuit 1020 converts the baseband signal into data and processes the data.

[0337] In another implementation, the radio frequency circuit and the antenna can be arranged independently of the processing circuit for baseband processing, for example, in a distributed scenario, the radio frequency circuit and the antenna can be arranged remotely from the device.

[0338] The apparatus shown in the embodiments of the present application can also have more components than those shown in FIG. 10, and the embodiments of the present application do not limit the apparatus. The method performed by the processing circuit and the transceiver circuit shown above is only an example, and the specific steps performed by the processing circuit and the transceiver circuit can refer to the method described above.

[0339] In another possible implementation, in the apparatus shown in FIG. 9, the processing module 901 can be one or more logic circuits, and the transceiving module 902 can be an input / output interface, also referred to as a communication interface, or an interface circuit, or an interface, etc. Alternatively, the transceiving module 902 can also be a sending module and a receiving module, the sending module can be an output interface, and the receiving module can be an input interface, and the sending module and the receiving module are integrated into one module, for example, an input / output interface.

[0340] FIG. 11 is a structural schematic diagram of an apparatus provided by an embodiment of the present application. As shown in FIG. 11, the apparatus shown in FIG. 11 includes a logic circuit 1101 and an interface circuit 1102. That is, the processing module 901 can be implemented by the logic circuit 1101, and the transceiving module 902 can be implemented by the interface circuit 1102. The logic circuit 1101 can be a chip, a processing circuit, an integrated circuit, or a system on chip (SoC) chip, etc., and the interface circuit 1102 can be a communication interface, an input / output interface, a pin, etc. For example, FIG. 11 is shown by taking the apparatus as a chip, and the chip includes the logic circuit 1101 and the interface circuit 1102.

[0341] In the embodiments of the present application, the logic circuit and the interface can also be coupled to each other. The embodiments of the present application do not limit the specific connection mode of the logic circuit and the interface. For example, the logic circuit 1101 can be used to perform the functions or steps implemented by the processing module 901 shown in FIG. 9, and the interface circuit 1102 can be used to perform the functions or steps implemented by the transceiving module 902 shown in FIG. 9. For specific descriptions of the logic circuit 1101 and the interface circuit 1102, refer to the method embodiments shown in FIG. 9 or the above description, which will not be described in detail here.

[0342] The apparatus shown in the embodiments of the present application can implement the method provided by the embodiments of the present application in the form of hardware, or implement the method provided by the embodiments of the present application in the form of software, etc., and the embodiments of the present application do not limit this.

[0343] The embodiments of the present application also provide a communication system, which includes a first node and a second node, and the first node and the second node can be used to perform the method in any of the preceding embodiments.

[0344] In addition, the present application also provides a computer program for implementing the operations and / or processes performed by each device in the method provided by the present application.

[0345] The present application also provides a computer readable storage medium having computer code stored therein, which, when executed on a computer, causes the computer to perform the operations and / or processes performed by each device in the method provided by the present application.

[0346] The present application also provides a computer program product comprising computer code or a computer program, which, when executed on a computer, causes the operations and / or processes performed by each device in the method provided by the present application to be performed.

[0347] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or modules, and can also be electrical, mechanical or other form of connection.

[0348] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical modules, that is, they can be located in one place, or can be distributed to multiple network modules. According to actual needs, part or all of the modules can be selected to achieve the technical effects of the scheme provided by the embodiments of the present application.

[0349] In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of software functional module.

[0350] The integrated module, if implemented in the form of a software function module and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art, or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a readable storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned readable storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0351] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: A method applied to a first node located at a network side, the method comprising: receiving an activation indication from a second node located at the network side, the activation indication being used to indicate to activate the first node, the first node being provided with an artificial intelligence (AI) function; generating first information based on the AI function; sending the first information.

2. The method of claim 1, wherein, The activation indication is used to indicate to activate the first node, comprising: The activation indication is used to indicate to activate one or more of the following of the first node: all or part of the AI function, all or part of a protocol stack, all or part of an AI model, or all or part of a result inferred by AI that needs to be provided.

3. The method according to claim 1 or 2, characterized in that, The method further comprises: deactivating the first node when a first condition is met; The first condition comprises one or more of the following: receiving a first deactivation indication from the second node, the first deactivation indication being used to indicate to deactivate the first node; or The inference accuracy of the first node or the AI model or the AI function of the first node is less than or equal to a first threshold; or The performance gain of the first node or the AI model or the AI function of the first node is less than or equal to a second threshold; or The calculation overhead or storage overhead of the first node or the AI model or the AI function of the first node is greater than or equal to a third threshold.

4. The method of claim 3, wherein, The deactivating the first node comprises deactivating one or more of the following of the first node: all or part of the AI function, all or part of the protocol stack, all or part of the AI model, or all or part of the result inferred by AI that needs to be provided.

5. The method according to any one of claims 1 to 4, characterized in that, The second node is an access network device or a centralized unit (CU).

6. The method of any one of claims 1-5, wherein: The generating first information based on the AI function comprises: generating first information through a first protocol layer, the first protocol layer having the AI function; The sending the first information comprises: sending the first information through the first protocol layer to a second protocol layer; encapsulating the first information through the second protocol layer to obtain a first data unit; sending the first data unit through the second protocol layer.

7. The method according to any one of claims 1 to 6, characterized in that, Before the receiving the activation indication from the second node located at the network side, the method further comprises: sending first registration information to the second node, the first registration information comprising capability information of the first node, the capability information indicating that the first node is provided with the AI function.

8. The method of claim 7, wherein, The capability information indicating that the first node is provided with the AI function comprises: The capability information indicates one or more of the following: one or more AI use cases supported by the first node, a number of AI use cases supported by the first node, an algorithmic cost corresponding to each of the one or more AI use cases, an energy consumption corresponding to each of the one or more AI use cases, an input / output format corresponding to each of the one or more AI use cases, one or more AI functions supported by the first node, a number of AI functions supported by the first node, an algorithmic cost corresponding to each of the one or more AI functions, an energy consumption corresponding to each of the one or more AI functions, an input / output format corresponding to each of the one or more AI functions, one or more AI models supported by the first node, a number of AI models supported by the first node, an algorithmic cost corresponding to each of the one or more AI models, an energy consumption corresponding to each of the one or more AI models, an input / output format corresponding to each of the one or more AI models.

9. The method according to claim 7 or 8, characterized in that, The capability information further indicates a total algorithmic cost supported by the first node and / or a total energy consumption supported by the first node.

10. The method according to any one of claims 7 to 9, characterized in that, The method further includes: sending, to one or more of a distributed unit (DU), a radio unit (RU), a core network device, an operation administration and maintenance (OAM), or a radio intelligent controller (RIC), or sending, by the second node, to one or more of the DU, the RU, the core network device, the OAM, or the RIC, second registration information including capability information of the first node.

11. The method of claim 10, wherein, Before sending the second registration information, the method further includes: receiving, from the second node, indication information indicating completion of registration with one or more of the DU, the RU, the core network device, the OAM, or the RIC.

12. The method according to any one of claims 1 to 10, characterized in that, Before generating the first information based on the AI function, the method further includes: receiving second information for model training or model inference; one or more of the following is included in the second information: third information from a terminal device, fourth information from a core network device or an OAM, fifth information from a third node, and sixth information from a fourth node; the third node includes one or more of the second node, a DU, or an RU; the fourth node has an AI function and is registered with a fifth node that is one or more nodes other than the second node; the third information indicates one or more of the following: AI capability information of the terminal device, computing capability of the terminal device, energy consumption of the terminal device, energy efficiency information of the terminal device, moving speed of the terminal device, moving path of the terminal device, number of antennas of the terminal device, beam weighting manner of the terminal device, service information of the terminal device, or measurement result of the terminal device. The fourth information indicates one or more of the following: AI capability information of the core network device or the OAM, computing capability of the core network device or the OAM, or service requirement of the core network device or the OAM; The fifth information indicates one or more of the following: AI capability information of the third node, computing capability of the third node, energy consumption of the third node, energy efficiency information of the third node, geographic location of the third node, number of antennas of the third node, beam weighting mode of the third node, resource information of the third node, or measurement result of the third node; The sixth information indicates one or more of the following: AI capability information of the fourth node, computing capability of the fourth node, energy consumption of the fourth node, or energy efficiency information of the fourth node.

13. The method according to any one of claims 1 to 12, characterized in that, The sending of the first information includes: sending, by the second node, the first information to a terminal device, the first information indicating one or more of the following: AI use case of the terminal device, AI function to be executed by the terminal device, or AI model to be executed by the terminal device, AI inference result to be provided by the terminal device, information related to lifecycle management of the AI use case of the terminal device, information related to lifecycle management of the AI function of the terminal device, or information related to lifecycle management of the AI model of the terminal device; or sending, by the second node, the first information to a third node, the third node including one or more of the second node, a DU, or a RU, or sending, by the second node, the first information to the third node, the third node including one or more of a RU or a DU; the first information indicating one or more of the following: recommended downlink beam weighting mode, predicted optimal access beam index of the terminal device, positioning assistance information of the terminal device, location information of the terminal device, execution mode of energy saving, execution mode of load balancing, path prediction result of the terminal device, recommended execution strategy of terminal device switching, transmission configuration of uplink and downlink data transmission, antenna form adjustment, or modulation and demodulation scheme configuration; or sending, by the second node, the first information to a fourth node, the fourth node having an AI function, the fourth node being registered with a fifth node, the fifth node being one or more nodes other than the second node; the first information indicating one or more of the following: prediction result required by the fourth node or execution strategy of the fifth node; or sending, by the second node, the first information to a core network device or an OAM, the first information indicating one or more of the following: data transmission capability on the access network side, switching state prediction of the terminal device, path prediction information of the terminal device, or predicted service requirement of the terminal device.

14. A communication method, comprising: The method is applied to a second node located at a network side, and the method comprises: sending an activation indication to a first node located at the network side, the activation indication being used to indicate to activate the first node, the first node being provided with an artificial intelligence (AI) function; receiving first information from the first node, the first information being generated based on the AI function.

15. The method of claim 14, wherein, The activation indication is used to indicate to activate the first node, and the activation indication comprises: The activation indication is used to indicate to activate one or more of the following in the first node: all or part of the AI function, all or part of a protocol stack, all or part of an AI model, or all or part of a result inferred by AI that needs to be provided.

16. The method according to claim 14 or 15, characterized in that The method further comprises: sending a first deactivation indication to the first node, the first deactivation indication being used to indicate to close the first node.

17. The method of claim 16, wherein, The sending of the first deactivation indication to the first node comprises: sending the first deactivation indication to the first node when a second condition is met; The second condition comprises one or more of the following: receiving a second deactivation indication from an operation administration and maintenance (OAM), the second deactivation indication being used to indicate to close the first node; an inference accuracy of the first node or an AI model or an AI function of the first node is less than or equal to a first threshold value; or a performance gain of the first node or the AI model or the AI function of the first node is less than or equal to a second threshold value; or a calculation overhead or a storage overhead of the first node or the AI model or the AI function of the first node is greater than or equal to a third threshold value.

18. The method according to claim 16 or 17, characterized in that, The closing of the first node comprises closing one or more of the following in the first node: all or part of the AI function, all or part of the protocol stack, all or part of the AI model, or all or part of the result inferred by AI that needs to be provided.

19. The method according to any one of claims 14 to 18, characterized in that, The second node is an access network device or a centralized unit (CU).

20. The method of any of claims 14-19, wherein, The method further comprises: receiving first registration information from the first node, the first registration information comprising capability information of the first node, the capability information indicating that the first node is provided with the AI function.

21. The method of claim 20, wherein, The capability information indicating that the first node is provided with the AI function comprises: total computing power supported by the first node, total energy consumption supported by the first node, one or more AI use cases supported by the first node, a number of AI use cases supported by the first node, computing power overheads corresponding to the one or more AI use cases respectively, energy consumption corresponding to the one or more AI use cases respectively, input and output formats corresponding to the one or more AI use cases respectively, one or more AI functions supported by the first node, a number of AI functions supported by the first node, computing power overheads corresponding to the one or more AI functions respectively, energy consumption corresponding to the one or more AI functions respectively, input and output formats corresponding to the one or more AI functions respectively, one or more AI models supported by the first node, a number of AI models supported by the first node, computing power overheads corresponding to the one or more AI models respectively, energy consumption corresponding to the one or more AI models respectively, input and output formats corresponding to the one or more AI models respectively.

22. The method of claim 20 or 21, wherein, The capability information further indicates total computing power supported by the first node and / or total energy consumption supported by the first node.

23. The method of any one of claims 20-22, wherein, The method further includes: receiving second registration information from the first node; sending, to one or more nodes of a distributed unit (DU), a radio unit (RU), a core network device, an operation administration and maintenance (OAM), or a radio intelligent controller (RIC), the second registration information including capability information of the first node.

24. The method of claim 23, wherein, Before the receiving the second registration information from the second node, the method further includes: sending, to the first node, indication information indicating completion of registration with one or more nodes of a DU, a RU, a core network device, an OAM, or a RIC.

25. The method of any of claims 14-24, wherein, The method further includes: sending, to the first node, fifth information indicating one or more of: AI capability information of the second node, computing capability of the second node, energy consumption of the second node, energy efficiency information of the second node, geographic location of the second node, number of antennas of the second node, beam weighting manner of the second node, resource information of the second node, or measurement result of the second node.

26. The method of any of claims 14-25, wherein, The first information indicates one or more of: recommended downlink beam weighting manner, predicted optimal access beam index of a terminal device, positioning assistance information of a terminal device, location information of a terminal device, execution manner of energy saving, execution manner of load balancing, path prediction result of a terminal device, recommended execution strategy of terminal device switching, transmission configuration of uplink and downlink data transmission, antenna form adjustment, or modulation and demodulation scheme configuration.

27. A communications device, characterized by The communication apparatus includes modules or units for performing the method of any of claims 1-13, or the communication apparatus includes modules or units for performing the method of any of claims 14-26.

28. A communications device, characterized by comprising a processor and an interface circuit for receiving signals from the other communication apparatus outside the communication apparatus and transmitting to the processor or transmitting the signals from the processor to the other communication apparatus outside the communication apparatus, the processor causes the method according to any one of claims 1 to 13 to be executed by a logic circuit or an execution instruction, or the processor causes the method according to any one of claims 14 to 26 to be executed by a logic circuit or an execution instruction.

29. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or an instruction, and when the computer program or the instruction is executed by the communication apparatus, the method according to any one of claims 1 to 13 is executed, or the method according to any one of claims 14 to 26 is executed.

Images