WO2024046113A1 - 一种无线通信方法及通信装置 - Google Patents

一种无线通信方法及通信装置 Download PDF

Info

Publication number
WO2024046113A1
WO2024046113A1 PCT/CN2023/113109 CN2023113109W WO2024046113A1 WO 2024046113 A1 WO2024046113 A1 WO 2024046113A1 CN 2023113109 W CN2023113109 W CN 2023113109W WO 2024046113 A1 WO2024046113 A1 WO 2024046113A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
capability information
terminal device
access network
capability
Prior art date
Application number
PCT/CN2023/113109
Other languages
English (en)
French (fr)
Inventor
耿婷婷
曾宇
陈君
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2024046113A1 publication Critical patent/WO2024046113A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/22—Processing or transfer of terminal data, e.g. status or physical capabilities
    • H04W8/24—Transfer of terminal data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/20—Control channels or signalling for resource management
    • H04W72/21—Control channels or signalling for resource management in the uplink direction of a wireless link, i.e. towards the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/22—Processing or transfer of terminal data, e.g. status or physical capabilities

Definitions

  • the present application relates to the field of wireless communication technology, and in particular, to a wireless communication method and communication device.
  • Artificial Intelligence is a technology that performs complex calculations by simulating the human brain. As data storage and computing capabilities improve, artificial intelligence is increasingly used.
  • the 3rd generation partnership project (3GPP) proposes to apply artificial intelligence to the fifth generation (5th generation, 5G) communication system to improve network performance and user experience through intelligent collection and data analysis.
  • the present application provides a wireless communication method and communication device to improve the collaboration efficiency between terminal equipment and wireless access network equipment.
  • embodiments of the present application provide a wireless communication method, which can be executed by a wireless access network device or a module (such as a chip) applied in a wireless access network device.
  • the method includes: a wireless access network device receiving first capability information of a terminal device, where the first capability information includes at least one set of AI capability information supported by the terminal device; and the wireless access network device based on the first capability information, Determine the AI resource demand information corresponding to the at least one set of AI capability information.
  • the terminal device reports one or more sets of AI capability information supported by the terminal device to the wireless access network device, and the wireless access network device determines the AI resource requirement information corresponding to the one or more sets of AI capability information, and then It can decide how to configure AI for terminal equipment based on AI resource demand information, so that terminal equipment can reasonably and effectively use AI functions, thereby improving the collaboration efficiency between terminal equipment and wireless access network equipment.
  • the radio access network device determines the AI resource requirement information respectively corresponding to the at least one set of AI capability information based on the first capability information, including: the radio access network device determines the AI resource requirement information corresponding to the at least one set of AI capability information based on the first capability information.
  • the information and the predefined correspondence determine the AI resource requirement information respectively corresponding to the at least one AI capability information, and the predefined correspondence includes the correspondence between the at least one AI capability information and the AI resource requirement information.
  • the above solution pre-defines the corresponding relationship between AI capability information and AI resource requirement information. Based on the corresponding relationship, the wireless access network device can quickly and accurately determine at least one set of AI capability information in the first capability information sent by the terminal device.
  • the corresponding AI resource demand information helps to accurately determine AI configuration information for the terminal device.
  • the radio access network device receives second capability information of the terminal device, and the second capability information is used to indicate information about AI resources that the terminal device can provide; the radio access network device is based on The AI resource demand information corresponding to the second capability information and the at least one set of AI capability information respectively determines the first AI configuration information, and the first AI configuration information corresponds to one or more groups of AI in the at least one set of AI capability information. Capability information; the wireless access network device sends the first AI configuration information to the terminal device.
  • the terminal device since the first AI configuration information is generated based on at least one set of AI capability information supported by the terminal device, the terminal device supports the first AI configuration information, which helps to implement correct AI configuration for the terminal device.
  • the radio access network device receives notification information from the terminal device.
  • the notification information includes information about AI resources occupied by the terminal device, information about remaining AI resources, and desired AI configuration information. at least one of.
  • the radio access network device determines second AI configuration information based on the notification information and the first capability information, and the second AI configuration information corresponds to one of the at least one set of AI capability information. or multiple sets of AI capability information; the radio access network device sends the second AI configuration information to the terminal device.
  • the above solution can update the AI configuration information for the terminal device, so that the terminal device can use the AI function more reasonably and effectively according to the updated AI configuration information, thereby meeting the communication needs between the terminal device and the wireless access network device and improving the terminal Equipment and None Collaboration efficiency between line access network equipment.
  • the radio access network device sends first indication information to the terminal device, where the first indication information indicates a trigger condition for reporting the notification information.
  • the radio access network device receives second instruction information from the terminal device, and the second instruction information instructs to deactivate the AI configuration information of the terminal device; the radio access network device according to the third 2. Instruction information to activate the AI configuration information of the terminal device.
  • the above solution can deactivate the AI configuration information of the terminal device when the terminal device does not need to use the AI function, which helps to save the energy consumption of the terminal device.
  • the radio access network device receiving the first capability information of the terminal device includes: the radio access network device receiving the first capability information from other radio access network devices, the terminal device or the core network device. Capability information.
  • the radio access network device receiving the second capability information of the terminal device includes: the radio access network device receiving the second capability information from other radio access network devices, the terminal device or the core network device. Capability information.
  • embodiments of the present application provide a wireless communication method, which can be executed by a terminal device or a module (such as a chip) applied in the terminal device.
  • the method includes: a terminal device determines first capability information, where the first capability information includes at least one set of AI capability information supported by the terminal device; and the terminal device sends the first capability information to a wireless access network device.
  • the terminal device reports one or more sets of AI capability information supported by the terminal device to the wireless access network device, and the wireless access network device can decide how to perform the function based on the one or more sets of AI capability information supported by the terminal device.
  • the terminal device performs AI configuration so that the terminal device can reasonably and effectively use the AI function, thereby improving the collaboration efficiency between the terminal device and the wireless access network device.
  • the terminal device sends second capability information to the wireless access network device, where the second capability information is used to indicate information about AI resources that the terminal device can provide; the terminal device receives information from the wireless access network device.
  • First AI configuration information of the access network device The first AI configuration information is determined based on the AI resource requirement information corresponding to the second capability information and the at least one set of AI capability information.
  • the first AI configuration information corresponds to the One or more sets of AI capability information in at least one set of AI capability information.
  • the terminal device since the first AI configuration information is generated based on at least one set of AI capability information supported by the terminal device, the terminal device supports the first AI configuration information, which helps to implement correct AI configuration for the terminal device.
  • the terminal device determines that the triggering condition is met and sends notification information to the radio access network device.
  • the notification information includes information about AI resources occupied by the terminal device, information about remaining AI resources, and expected At least one item of AI configuration information; wherein, the triggering condition includes: the information of AI resources occupied by the terminal device is greater than the first threshold, and/or the information of the remaining AI resources of the terminal device is less than the second threshold.
  • the terminal device receives second AI configuration information from the radio access network device.
  • the second AI configuration information is determined based on the notification information and the first capability information.
  • the second AI The configuration information corresponds to one or more sets of AI capability information in the at least one set of AI capability information.
  • the above solution can update the AI configuration information for the terminal device, so that the terminal device can use the AI function more reasonably and effectively according to the updated AI configuration information, thereby meeting the communication needs between the terminal device and the wireless access network device and improving the terminal Cooperation efficiency between equipment and radio access network equipment.
  • the terminal device receives first indication information from the radio access network device, the first indication information indicates the trigger condition for reporting the notification information, and the first indication information includes the first threshold. and/or the second threshold.
  • the terminal device sends second instruction information to the radio access network device, and the second instruction information instructs to deactivate the AI configuration information of the terminal device.
  • the above solution can deactivate the AI configuration information of the terminal device when the terminal device does not need to use the AI function, which helps to save the energy consumption of the terminal device.
  • each set of AI capability information includes at least one of AI functions, AI sub-functions, collaboration levels, AI models or AI algorithms supported by the terminal device.
  • each set of AI capability information includes at least two pieces of AI capability information, and there is a corresponding relationship between the at least two pieces of AI capability information.
  • the wireless access network device when the wireless access network device generates AI configuration information, it performs combined configuration based on the AI capability information in the same group to avoid generating configuration information that is not supported by the terminal device.
  • AI configuration helps reduce the occurrence of misconfiguration.
  • the first capability information also includes: AI resource requirement information corresponding to the at least one set of AI capability information, or index information of AI resource requirement information corresponding to the at least one set of AI capability information. .
  • the AI resource information that the terminal device can provide includes the maximum computing power information, the maximum storage capacity information, the maximum power information, the processing delay information, the supported AI model information or the supported AI resource information of the terminal device. At least one of the AI algorithm information.
  • embodiments of the present application provide a wireless communication method, which can be executed by a wireless access network device or a module (such as a chip) applied in a wireless access network device.
  • the method includes: a radio access network device receiving first capability information of a terminal device, where the first capability information includes a set of AI capability information or at least two sets of AI capability information supported by the terminal device within the range of AI resources indicated by the second capability information.
  • the combination information of AI capability information, the second capability information is used to indicate the information of AI resources that the terminal device can provide; the radio access network device determines the first AI configuration information based on the first capability information, the first AI The configuration information corresponds to one or more groups of AI capability information in the group of AI capability information or the combined information of the at least two groups of AI capability information; the radio access network device sends the first AI configuration information to the terminal device.
  • the terminal device since the first AI configuration information is generated based on the AI capability information supported by the terminal device, the terminal device supports the first AI configuration information, which helps to implement correct AI configuration for the terminal device, thereby improving the connection between the terminal device and Cooperation efficiency between wireless access network devices.
  • the radio access network device receives notification information from the terminal device.
  • the notification information includes information about AI resources occupied by the terminal device, information about remaining AI resources, and desired AI configuration information. at least one of.
  • the radio access network device determines second AI configuration information based on the notification information and the first capability information, and the second AI configuration information corresponds to the set of AI capability information or the at least two sets of AI capability information. One or more groups of AI capability information in the combined information of AI capability information; the radio access network device sends the second AI configuration information to the terminal device.
  • the above solution can update the AI configuration information for the terminal device, so that the terminal device can use the AI function more reasonably and effectively according to the updated AI configuration information, thereby meeting the communication needs between the terminal device and the wireless access network device and improving the terminal Cooperation efficiency between equipment and radio access network equipment.
  • the radio access network device sends first indication information to the terminal device, where the first indication information indicates a trigger condition for reporting the notification information.
  • the radio access network device receives second instruction information from the terminal device, and the second instruction information instructs to deactivate the AI configuration information of the terminal device; the radio access network device according to the third 2. Instruction information to activate the AI configuration information of the terminal device.
  • the radio access network device receiving the first capability information of the terminal device includes: the radio access network device receiving the first capability information from other radio access network devices, the terminal device or the core network device. Capability information.
  • embodiments of the present application provide a wireless communication method, which can be executed by a terminal device or a module (such as a chip) applied in the terminal device.
  • the method includes: the terminal device determines first capability information based on the second capability information.
  • the first capability information includes at least AI capability information or at least two groups of AI supported by the terminal device within the range of AI resources indicated by the second capability information.
  • Combination information of capability information, the second capability information is used to indicate information about AI resources that the terminal device can provide; the terminal device sends the first capability information to the radio access network device.
  • the terminal device reports the AI capability information supported by the terminal device to the wireless access network device, and the wireless access network device can decide how to configure AI for the terminal device based on the AI capability information supported by the terminal device, so that the terminal device can Reasonable and effective use of AI functions can improve the collaboration efficiency between terminal equipment and wireless access network equipment.
  • the AI resource information that the terminal device can provide includes the maximum computing power information, the maximum storage capacity information, the maximum power information, the processing delay information, the supported AI model information or the supported AI resource information of the terminal device. At least one of the AI algorithm information.
  • the terminal device determines that the triggering condition is met and sends notification information to the radio access network device.
  • the notification information includes information about AI resources occupied by the terminal device, information about remaining AI resources, and expected At least one item of AI configuration information; wherein, the triggering condition includes: the information of AI resources occupied by the terminal device is greater than the first threshold, and/or the information of the remaining AI resources of the terminal device is less than the second threshold.
  • the terminal device receives second AI configuration information from the radio access network device.
  • the second AI configuration information is determined based on the notification information and the first capability information.
  • the second AI The configuration information corresponds to one or more sets of AI capability information in the set of AI capability information or the combined information of at least two sets of AI capability information.
  • the above solution can update the AI configuration information for the terminal device, so that the terminal device can use the AI function more reasonably and effectively according to the updated AI configuration information, thereby meeting the communication needs between the terminal device and the wireless access network device and improving the terminal Cooperation efficiency between equipment and radio access network equipment.
  • the terminal device receives first indication information from the radio access network device, the first indication information indicates the trigger condition for reporting the notification information, and the first indication information includes the first threshold. and/or the second threshold.
  • the terminal device sends second instruction information to the radio access network device, and the second instruction information instructs to deactivate the AI configuration information of the terminal device.
  • each set of AI capability information includes at least one of AI functions, AI sub-functions, collaboration levels, AI models or AI algorithms supported by the terminal device.
  • each set of AI capability information includes at least two pieces of AI capability information, and there is a corresponding relationship between the at least two pieces of AI capability information.
  • the wireless access network device when the wireless access network device generates AI configuration information, it performs combined configuration based on the AI capability information in the same group to avoid generating configuration information that is not supported by the terminal device.
  • AI configuration helps reduce the occurrence of misconfiguration.
  • inventions of the present application provide a communication device.
  • the device may be a wireless access network device, or may be a module (such as a chip) for the wireless access network device.
  • the device has the function of implementing any implementation method of the above-mentioned first aspect or third aspect. This function can be implemented by hardware, or it can be implemented by hardware executing corresponding software.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • embodiments of the present application provide a communication device, which may be a terminal device or a module (such as a chip) for the terminal device.
  • the device has the function of implementing any implementation method of the above-mentioned second aspect or fourth aspect. This function can be implemented by hardware, or it can be implemented by hardware executing corresponding software.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • embodiments of the present application provide a communication device, including a processor and a memory; the memory is used to store computer instructions, and when the device is running, the processor executes the computer instructions stored in the memory to cause the device to execute Any implementation method in the above first to fourth aspects.
  • embodiments of the present application provide a communication device, including units or means for executing each step of any implementation method in the above first to fourth aspects.
  • embodiments of the present application provide a communication device, including a processor and an interface circuit.
  • the processor is configured to communicate with other devices through the interface circuit and execute any implementation method in the above first to fourth aspects.
  • the processor includes one or more.
  • embodiments of the present application provide a communication device, including a processor coupled to a memory.
  • the processor is configured to call a program stored in the memory to execute any implementation method in the first to fourth aspects.
  • the memory may be located within the device or external to the device.
  • the processor can be one or more.
  • embodiments of the present application further provide a computer-readable storage medium, in which instructions are stored, and when run on a communication device, the instructions in the above-mentioned first to fourth aspects are achieved. Any implementation method of is executed.
  • embodiments of the present application further provide a computer program product.
  • the computer program product includes a computer program or instructions.
  • the computer program or instructions are run by a communication device, any one of the above first to fourth aspects is enabled.
  • the implementation method is executed.
  • embodiments of the present application further provide a chip system, including: a processor configured to execute any implementation method of the first aspect or the third aspect.
  • embodiments of the present application further provide a chip system, including: a processor configured to execute any implementation method of the above-mentioned second or fourth aspect.
  • embodiments of the present application further provide a communication system, including: a radio access network device for performing any implementation method of the first aspect and a terminal device for performing any implementation method of the second aspect.
  • embodiments of the present application further provide a communication system, including: a radio access network device for performing any implementation method of the third aspect and a terminal device for performing any implementation method of the fourth aspect.
  • Figure 1 is a schematic diagram of the architecture of a communication system applied in an embodiment of the present application
  • Figure 2 is a schematic flow chart of a wireless communication method provided by an embodiment of the present application.
  • Figure 3 is a schematic flow chart of a wireless communication method provided by an embodiment of the present application.
  • Figure 4 is a schematic flow chart of a wireless communication method provided by an embodiment of the present application.
  • Figure 5 is a schematic flow chart of a wireless communication method provided by an embodiment of the present application.
  • Figure 6 is a schematic flow chart of a wireless communication method provided by an embodiment of the present application.
  • Figure 7 is a schematic flow chart of a wireless communication method provided by an embodiment of the present application.
  • Figure 8 is a schematic structural diagram of a possible communication device provided by an embodiment of the present application.
  • Figure 9 is a schematic structural diagram of a possible communication device provided by an embodiment of the present application.
  • Figure 1 is a schematic architectural diagram of a communication system applied in an embodiment of the present application.
  • the communication system includes terminal equipment and wireless access network equipment.
  • the communication system is suitable for 5G communication networks, non-terrestrial networks (non-terrestrial network, NTN) or future communication networks, such as sixth generation (6th generation, 6G) communication networks.
  • NTN non-terrestrial network
  • 6G sixth generation
  • Terminal equipment is a device with wireless transceiver functions.
  • the terminal equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as aircraft, balloons and satellites, etc.).
  • the terminal device may be a mobile phone (mobile phone), a tablet computer (pad), a computer with wireless transceiver functions, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, an industrial control ( Wireless terminal equipment in industrial control, wireless terminal equipment in self-driving, wireless terminal equipment in telemedicine, wireless terminal equipment in smart grid, transportation safety ), wireless terminal equipment in smart city (smart city), wireless terminals in smart home (smart home), and may also be user equipment (user equipment, UE), etc.
  • a mobile phone mobile phone
  • a tablet computer pad
  • AR augmented reality
  • an industrial control Wireless terminal equipment in industrial control, wireless terminal equipment in self-driving, wireless terminal equipment in telemedicine, wireless terminal equipment in smart grid, transportation safety ), wireless terminal equipment in smart city (smart city), wireless terminals in smart home (smart home), and may also be user equipment (user equipment, UE), etc.
  • Radio access network (RAN) equipment is a device that can connect terminal equipment to a wireless network.
  • Wireless access network equipment can be: next-generation node (gNodeB, gNB), transmission reception point (TRP), evolved node B (evolved Node B, eNB), radio network controller (radio network controller, RNC) ), Node B (Node B, NB), base station controller (BSC), base transceiver station (BTS), home base station (for example, home evolved NodeB, or home Node B, HNB), Baseband unit (BBU), or wireless fidelity (Wifi) access point (AP), integrated access and backhaul (IAB), etc.
  • gNodeB, gNB next-generation node
  • TRP transmission reception point
  • eNB evolved node B
  • RNC radio network controller
  • Node B Node B
  • BSC base station controller
  • BTS base transceiver station
  • home base station for example, home evolved NodeB, or home Node B, HNB
  • the radio access network device in the embodiment of this application may also be a centralized unit (central unit, CU) or a distributed unit (distributed unit, DU), or include a CU and a DU.
  • CU and DU can be understood as the division of wireless access network equipment from the perspective of logical functions.
  • the CU and the DU may be physically separated or deployed together, which is not specifically limited in the embodiments of this application.
  • One CU can be connected to one DU, or multiple DUs can share one CU.
  • CU and DU can be segmented according to the protocol stack.
  • RRC radio resource control
  • SDAP service data adaptation protocol
  • PDCP packet data convergence protocol
  • RLC wireless link control
  • MAC media access control
  • DU physical layer
  • the radio access network device in the embodiment of this application may also refer to a centralized unit control plane (CU-CP) node or a centralized unit user plane (CU-UP) node, or include CU-CP and CU-UP.
  • CU-CP is responsible for control plane functions, mainly including RRC and PDCP-C.
  • PDCP-C is mainly responsible for encryption and decryption of control plane data, integrity protection, data transmission, etc.
  • CU-UP is responsible for user plane functions, mainly including SDAP and PDCP-U.
  • SDAP is mainly responsible for processing core network data and mapping flows to bearers.
  • PDCP-U is mainly responsible for data plane encryption and decryption, integrity protection, header compression, serial number maintenance, data transmission, etc.
  • Wireless access network equipment and terminal equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed on aircraft, balloons and satellites in the sky.
  • the embodiments of this application do not limit the application scenarios of wireless access network equipment and terminal equipment.
  • the embodiments of the present application may be applicable to downlink signal transmission or uplink signal transmission.
  • the sending device is the wireless access network device, and the corresponding receiving device is the terminal device.
  • the sending device is the terminal device, and the corresponding receiving device is the wireless access network device.
  • the embodiments of the present application do not limit the transmission direction of the signal.
  • Wireless access network equipment and terminal equipment can communicate through licensed spectrum, unlicensed spectrum, or both at the same time.
  • Wireless access Network access equipment and terminal equipment can communicate through spectrum below 6 gigahertz (GHz) or above 6G, or they can communicate using spectrum below 6G and above 6G at the same time.
  • GHz gigahertz
  • the embodiments of the present application do not limit the spectrum resources used between the radio access network device and the terminal device.
  • AI functions are also called AI application scenarios.
  • AI functions include but are not limited to: channel status information reference signal (CSI-RS) feedback enhancement (CSI-RS feedback enhancement), beam management enhancement (beam management enhancement), and positioning accuracy enhancement (positioning accuracy enhancement). They are explained below.
  • CSI-RS channel status information reference signal
  • CSI-RS feedback enhancement beam management enhancement
  • positioning accuracy enhancement positioning accuracy enhancement
  • CSI-RS includes but is not limited to at least one of the following: channel quality indicator (chanel quality indicator, CQI), precoding matrix indicator (precoding matrix indicator, PMI), CSI-RS resource indicator (CSI-RS resource indicator, CRI), Layer indicator (LI), rank indicator (RI).
  • CSI-RS feedback enhancement may include at least one sub-function, such as: CSI compression, CSI prediction, and CSI-RS configuration signaling reduction.
  • CSI compression can be divided into CSI compression in at least one domain: spatial domain, time domain and frequency domain.
  • the beam management enhancement may include at least one sub-function, such as beam scanning matrix prediction and optimal beam prediction respectively.
  • Positioning enhancement is used to improve positioning accuracy.
  • Positioning enhancement may include at least one sub-function, such as: positioning enhancement based on the access network device, positioning enhancement based on the positioning management function network element, and positioning enhancement based on the terminal device.
  • Collaboration level 0 is also called No collaboration.
  • the AI model of the wireless access network device is completely invisible to the terminal device.
  • the training and inference of the AI model are completed within the wireless access network device, and no model information or information is sent to the terminal device over the air interface. Information about the model instance.
  • Collaboration level 1 is also called signaling-based collaboration without model transfer.
  • the wireless access network device sends an instance of the AI model, that is, a dictionary, to the terminal device.
  • the terminal device uses the dictionary to assist the wireless access network device in AI reasoning, and has Influence.
  • the terminal device performs channel compression coding according to the dictionary.
  • an AI model can also be deployed inside the terminal device.
  • the terminal device When the terminal device is deployed with an AI model, the terminal device performs channel compression coding based on the AI model and the dictionary received from the wireless access network device.
  • the terminal equipment and the radio access network equipment can jointly train the model, for example, through federated learning. Terminal equipment and wireless access network equipment will not directly transfer the model over the air interface, but they can transfer model parameters, weights, etc.
  • deploying an AI model on a terminal device or a wireless access network device can be understood as deploying a software module or hardware module for realizing the functions of the AI model.
  • collaboration level 1 can be divided into collaboration level 1A and collaboration level 1B, where:
  • Collaboration level 1A Signaling-based collaboration for single-sided model without model transfer, also known as single-sided node deployment model, that is, the wireless access network equipment is deployed with an AI model, and the terminal The device does not have an AI model deployed.
  • Collaboration level 1B Signaling-based collaboration for two-sided model without model transfer, also known as bilateral node deployment model, that is, both wireless access network equipment and terminal equipment are deployed with AI model.
  • Cooperation level 2 is also called signaling-based collaboration with model transfer.
  • both radio access network equipment and terminal equipment are deployed with AI models, both can perform inference, and can communicate over the air interface.
  • Information about mutual AI models The differences between collaboration level 2 and collaboration level 1 include: collaboration level 2 can transmit AI model information over the air interface.
  • this application proposes a wireless communication method. It can be understood that the method provided by this application can be executed by the terminal device and/or the radio access network device, or can be executed by a module (such as a chip) for the terminal device and/or the radio access network device.
  • the terminal device and The wireless access network device serves as the execution subject to introduce the wireless communication method provided by this application.
  • Figure 2 is a schematic flowchart of a wireless communication method provided by an embodiment of the present application. The method includes the following steps:
  • Step 201 The terminal device determines first capability information, where the first capability information includes at least one set of AI capability information supported by the terminal device.
  • Each set of AI capability information includes at least one piece of AI capability information.
  • each set of AI capability information includes at least one of AI functions, AI sub-functions, collaboration levels, AI models, or AI algorithms supported by the terminal device.
  • each set of AI capability information includes at least two pieces of AI capability information
  • the first capability information includes 6 groups of AI capability information, respectively as follows:
  • Group 1 AI capability information CSI compression, collaboration level 1.
  • Group 2 AI capability information CSI prediction, collaboration level 2.
  • Group 3 AI capability information CSI-RS configuration signaling reduction, cooperation level 2.
  • Group 4 AI capability information beam scanning matrix prediction, collaboration level 2.
  • Group 5 AI capability information optimal beam prediction, collaboration level 1.
  • Group 6 AI capability information terminal device-based positioning enhancement, collaboration level 1.
  • the AI sub-function is CSI compression
  • the corresponding collaboration level of this CSI compression is collaboration level 1.
  • the terminal device supports using collaboration level 1 to implement the AI sub-function of CSI compression, and there is a binding relationship or collaboration relationship between CSI compression and collaboration level 1. For example, if the AI model is not deployed in the terminal device, the wireless access network device can send an instance of the AI model to the terminal device, and then the terminal device performs CSI compression based on the instance of the AI model and sends the compressed data to the wireless access network device.
  • the latter CSI realizes CSI compression based on cooperation level 1 between the terminal device and the wireless access network device.
  • the second group of AI capability information it can be determined that there is a corresponding relationship between the CSI prediction and collaboration level 2. Furthermore, it can also be determined that there is a corresponding relationship between the CSI prediction and other collaboration levels less than collaboration level 2. For example, it can be determined that the CSI prediction There is a corresponding relationship with collaboration level 0 or collaboration level 1.
  • the first capability information can be used to indicate AI function information or AI sub-function information and its corresponding highest collaboration level information.
  • Step 202 The terminal device sends first capability information to the wireless access network device.
  • the radio access network device receives the first capability information.
  • Step 203 The radio access network device determines AI resource requirement information corresponding to at least one set of AI capability information based on the first capability information.
  • the AI resource requirement information is used to indicate the AI resource information of the terminal device required when activating a set of AI capability information of the terminal device.
  • the AI resource information here includes but is not limited to one or more of the following: required computing power information, required storage capacity information, required power information, required processing delay information, required AI model information, or required AI algorithm information.
  • the wireless access network device may also receive the first capability information of the terminal device from other wireless access network devices or core network devices.
  • the other radio access network equipment may be a base station, CU or DU adjacent to the radio access network equipment, which is not limited in the embodiment of this application.
  • the core network device may be an access and mobility management function (AMF) network element or a session management function (SMF) network element, etc., which are not limited in the embodiments of this application. It can be understood that in this implementation, step 201 and step 202 are optional steps.
  • the terminal device reports one or more sets of AI capability information supported by the terminal device to the wireless access network device, and the wireless access network device determines the AI resource requirement information corresponding to the one or more sets of AI capability information, and then It can decide how to configure AI for terminal equipment based on AI resource demand information, so that terminal equipment can reasonably and effectively use AI functions, thereby improving the collaboration efficiency between terminal equipment and wireless access network equipment.
  • Implementation method 1 the first capability information also includes at least one set of AI resource requirement information corresponding to the AI capability information.
  • the first capability information includes at least one set of AI capability information and AI resource requirement information corresponding to the at least one set of AI capability information. Therefore, the radio access network device can determine, based on the first capability information, at least one set of AI capability information corresponding to AI resource demand information.
  • the first capability information also includes at least one set of index information of AI resource requirement information corresponding to the AI capability information.
  • the first capability information includes at least one set of AI capability information and index information of AI resource requirement information corresponding to the at least one set of AI capability information. Therefore, the radio access network device can determine, based on the first capability information, the index information of the AI resource requirement information corresponding to at least one set of AI capability information, and further, based on the index information of the AI resource requirement information corresponding to the at least one set of AI capability information, Determine at least one set of AI resource demand information corresponding to each set of AI capability information.
  • At least one set of AI capability information in the first capability information includes AI sub-functions and collaboration levels respectively
  • the index information of the AI resource requirement information in the first capability information includes index information of required computing capabilities, required storage Index information of capabilities and index information of required AI models.
  • Table 1 is an example of the correspondence between the AI capability information and the index information of the AI resource requirement information.
  • the correspondence between the index information of the AI resource requirement information and the AI resource requirement information can be predefined by the protocol or the terminal device and the wireless access network Device interaction.
  • the above corresponding relationship can be stored in the radio access network device and/or the terminal device in the form of tables, functions, sequences, etc.
  • Table 2 is an example of the correspondence between index information of computing capabilities and computing capability information.
  • Table 3 is an example of the correspondence between the index information of the storage capacity and the storage capacity information.
  • Table 4 is an example of the correspondence between the index information of the AI model and the AI model information.
  • Tables 2 to 4 illustrate the correspondence between the index information of the AI resource requirement information and the AI resource requirement information. In practical applications, Tables 2 to 4 can also be combined into one table to define the correspondence between the index information of the AI resource requirement information and the AI resource requirement information. This application is not limited to this.
  • flops refers to the number of floating-point operations performed per second (floating-point operations per second).
  • the wireless The access network equipment can determine the AI resource demand information corresponding to the combination of (CSI compression, cooperation level 1) including: the required computing capability information is a1 ⁇ a2, the required storage capability information is 0 ⁇ 10M, and the required AI model information is AI model 1.
  • both the terminal device and the radio access network device store the Tables 2 to 4.
  • the terminal device determines at least one set of AI capability information that needs to be reported and the AI resource requirement information corresponding to the at least one set of AI capability information, it then determines the AI resource requirements corresponding to the at least one set of AI capability information according to the above Tables 2 to 4.
  • the index information of the information further includes in the first capability information index information of at least one set of AI capability information and the AI resource requirement information corresponding to the at least one set of AI capability information.
  • the radio access network device determines the AI resource requirement information corresponding to at least one set of AI capability information according to Table 2 to Table 4.
  • Implementation method three the radio access network device determines the AI resource requirement information corresponding to at least one AI capability information according to the first capability information and a predefined correspondence relationship.
  • the predefined correspondence relationship includes at least one AI capability information and AI resource. Correspondence between demand information.
  • the radio access network device can determine the AI resource requirement information corresponding to at least one piece of AI capability information in the first capability information by querying the predefined correspondence relationship.
  • the corresponding relationship may be a corresponding relationship between AI capability information and AI resource requirement information.
  • the first capability information includes AI capability information
  • the radio access network device can determine the AI resource requirement information corresponding to the AI capability information according to the correspondence between the AI capability information and the AI resource requirement information.
  • the corresponding relationship includes a corresponding relationship between the AI capability information and the index information of the AI resource requirement information, and a corresponding relationship between the index information of the AI resource requirement information and the AI resource requirement information.
  • the first capability information includes AI capability information.
  • the radio access network device can determine the index information of the AI resource requirement information corresponding to the AI capability information according to the above correspondence relationship. Further, the radio access network device can determine the index information of the AI resource requirement information according to the AI resource. The corresponding relationship between the index information of the demand information and the AI resource demand information determines the resource demand information corresponding to the AI capability.
  • the above corresponding relationship can be stored in the radio access network device and/or the terminal device in the form of tables, functions, sequences, etc.
  • the AI capability information includes AI sub-functions and collaboration levels
  • the AI resource requirement information includes required computing capability information, required storage capability information, and required AI model information.
  • the radio access network device receives the AI capability information of the terminal device, and determines the index of the AI resource requirement information corresponding to the AI capability information by querying the correspondence between the AI capability information and the index information of the AI resource requirement information shown in Table 1 above. Information, further, by querying the correspondence between the index information of the AI resource requirement information and the AI resource requirement information shown in Tables 2 to 4, the AI resource requirement information corresponding to the AI capability information can be determined.
  • the radio access network device can determine the index information of the corresponding AI resource requirement information as follows: the index information of the required computing capability is 1, and the index information of the required computing capability is 1.
  • the index information of the storage capacity is 1, and the index information of the required AI model is 1.
  • the wireless access network device can determine the AI resource requirement information corresponding to the AI function information: Required calculation
  • the capabilities are a1 ⁇ a2, the required storage capacity is 0 ⁇ 10M, and the required AI model is AI model 1.
  • the radio access network device stores the Tables 1 to 4.
  • the first capability information sent by the terminal device includes at least one set of AI capability information.
  • the wireless access network device receives the first capability information, according to Table 1 to Table 4, Determine at least one set of AI resource demand information corresponding to each set of AI capability information.
  • the wireless access network device can accurately determine the AI resource requirement information corresponding to a set of AI capability information, which helps to configure appropriate AI configuration for the terminal device.
  • the terminal device carries in the first capability information at least one set of AI capability information and at least one set of AI resource requirement information respectively corresponding to the AI capability information, so that the wireless access network device according to the first capability information is The AI resource demand information corresponding to at least one set of AI capability information can be quickly determined, which can reduce the overhead of wireless access network equipment.
  • the terminal device carries in the first capability information at least one set of AI capability information and at least one set of index information of AI resource requirement information corresponding to the AI capability information.
  • the terminal device Due to the overhead occupied by the index information of AI resource requirement information, It requires less than AI resource requirement information, so it can reduce the signaling overhead between the terminal device and the wireless access network device and improve communication efficiency.
  • the terminal device carries at least one set of AI capability information in the first capability information, because the terminal device does not need to determine the AI resource requirement information corresponding to the at least one set of AI capability information or the index of the corresponding AI resource requirement information. information, therefore the overhead of the terminal device can be reduced, and since there is no need to carry in the first capability information at least one set of AI resource requirement information corresponding to the AI capability information or index information of the corresponding AI resource requirement information, the terminal device can be reduced Signaling overhead with wireless access network equipment to improve communication efficiency.
  • the embodiment of FIG. 2 also includes one or more of the following steps 204 to 206.
  • Step 204 The terminal device sends the second capability information to the wireless access network device.
  • the radio access network device receives the second capability information.
  • the second capability information is used to indicate information about AI resources that the terminal device can provide.
  • the second capability information may include at least one of the terminal device's maximum computing power information, maximum storage capacity information, maximum power information, processing delay information, AI model information supported by the terminal device, or supported AI algorithm information.
  • Step 205 The radio access network device determines the first AI configuration information of the terminal device based on the second capability information and the AI resource requirement information corresponding to at least one set of AI capability information.
  • the wireless access network device may also receive the second capability information of the terminal device from other wireless access network devices or core network devices.
  • the other radio access network equipment may be a base station, CU or DU adjacent to the radio access network equipment, which is not limited in the embodiment of this application.
  • the core network device may be an AMF network element or an SMF network element, etc., which is not limited in the embodiment of this application. It can be understood that in this implementation, step 204 may not be executed.
  • the radio access network device selects one or more sets of AI capability information from the at least one set of AI capability information based on the AI resource requirement information respectively corresponding to the second capability information and the at least one set of AI capability information.
  • the AI resource demand information corresponding to the one or more sets of AI capability information can all be satisfied by the second capability information, or it can be understood that the AI resources corresponding to the one or more sets of AI capability information do not exceed the second capability information.
  • the indicated AI resource determines the first AI configuration information based on the one or more sets of AI capability information, so the first AI configuration information corresponds to the one or more sets of AI capability information.
  • the first capability information includes the aforementioned 6 groups of AI capability information, and it is assumed that the AI resource requirements corresponding to the 1st, 3rd to 5th groups of AI capability information can be satisfied by the AI resources indicated by the second capability information, and the 2nd and 6th groups The AI resource requirements corresponding to the AI capability information cannot be satisfied by the AI resources indicated by the second capability information, so the 1st, 3rd to 5th groups of AI capability information can be used as candidate AI capability information.
  • the wireless access network device generates the first AI configuration information based on one or more groups of AI capability information selected from the first, third to fifth groups of AI capability information. For example, the radio access network device selects the first and fourth groups of AI capability information to generate the first AI configuration information.
  • the embodiments of this application do not limit the specific implementation method for the radio access network device to select one or more sets of AI capability information from multiple sets of AI capability information. For example, it may be to randomly select a set of AI capability information, or to select based on history. , select AI capability information that is the same as or different from the AI capability information selected last time, or select all sets of AI capability information, etc.
  • the first AI configuration information consists of the first and fourth groups of AI capability information.
  • the first AI configuration information includes: ⁇ CSI compression, cooperation level 1 ⁇ and ⁇ beam scanning matrix prediction, cooperation level 2 ⁇ .
  • CSI compression and cooperation level 1 constitute one configuration
  • beam scanning matrix prediction and cooperation level 2 constitute another configuration.
  • the first AI configuration information is generated based on the first and fourth groups of AI capability information, but is not exactly the same as the first and fourth groups of AI capability information.
  • the first AI configuration information includes: ⁇ CSI compression, cooperation level 1, model 1 ⁇ and ⁇ beam scanning matrix prediction, cooperation level 1, model 1 ⁇ .
  • CSI compression, cooperation level 1 and model 1 constitute one configuration
  • beam scanning matrix prediction, cooperation level 1 and model 1 constitute another configuration.
  • the first group of AI capability information in the first capability information reported by the terminal device does not include model information, indicating that the first group of AI capability information supports any model, so the radio access network device generates a model based on the first group of AI capability information.
  • model 1 is selected to be combined with the first set of AI capability information.
  • model 1 here are only Taking model 1 as an example, in practical applications, there is no limit to the method of selecting a model. For example, it can be random selection, or a model with the smallest cost, etc.
  • the radio access network device when the radio access network device generates the first AI configuration information based on the fourth group of AI capability information, it selects model 1 for combination with the fourth group of AI capability information.
  • the collaboration level in the fourth group of AI capability information in the first capability information reported by the terminal device is 2, which can be understood as the terminal device supports beam scanning matrix prediction and any AI with a collaboration level less than and/or equal to collaboration level 2 Capability information.
  • the wireless access network device also supports the first AI configuration information. Specifically, the radio access network device supports the AI function, AI sub-function, collaboration level, AI model, or AI algorithm, etc. in the first AI configuration information.
  • Step 206 The wireless access network device sends the first AI configuration information to the terminal device.
  • the terminal device receives the first AI configuration information.
  • the terminal device After receiving the first AI configuration information, the terminal device executes the corresponding AI function or AI sub-function according to the first AI configuration information.
  • the terminal device since the first AI configuration information is generated based on at least one set of AI capability information supported by the terminal device, the terminal device supports the first AI configuration information, which helps to implement correct AI configuration for the terminal device. Moreover, there is a corresponding relationship between multiple AI capability information in the same group. Therefore, when the wireless access network device generates AI configuration information, it performs combined configuration based on the AI capability information in the same group to avoid generating AI that is not supported by the terminal device. configuration to help reduce the occurrence of misconfigurations.
  • the above-mentioned step 204 and the above-mentioned step 202 can be implemented in the same step, or can be implemented in two different steps, which is not limited by this application.
  • FIG. 3 is a schematic flowchart of a wireless communication method provided by an embodiment of the present application. The method includes the following steps:
  • Step 301 The terminal device determines first capability information based on the second capability information.
  • the first capability information includes a set of AI capability information or at least two sets of AI capability information supported by the terminal device within the range of AI resources indicated by the second capability information. combination information.
  • the second capability information is used to indicate a maximum value of AI resources supported by the terminal device.
  • the second capability information includes an index value, which can be mapped to the maximum value of AI resources supported by the terminal device; or the second capability information includes a specific value of the maximum value of AI resources supported by the terminal device.
  • the second capability information has the same meaning as the second capability information in the embodiment of FIG. 2, and reference may be made to the foregoing description.
  • the first capability information has a different meaning from the first capability information in the embodiment of FIG. 2 .
  • the AI resource or the sum of AI resources corresponding to the first capability information may exceed the range of AI resources that the terminal device indicated by the second capability information can provide; in the embodiment of Figure 2
  • the radio access network device determines the first AI configuration according to the second capability information, and ensures that the AI resources or the sum of AI resources required by the first AI configuration do not exceed the range of AI resources indicated by the second capability information.
  • the first capability information includes a set of AI capability information supported by the terminal device within the range of the AI resources indicated by the second capability information, or a combination of at least two sets of AI capability information.
  • the first capability The AI resources corresponding to the information will not exceed the range of AI resources that the terminal device indicated by the second capability information can provide. It can be understood that the terminal device determines the first capability information based on the second capability information, and ensures that the AI capability information indicated by the first capability information or the AI resources or the sum of AI resources required by the combination of AI capability information does not exceed the AI capability information indicated by the second capability information. The scope of AI resources.
  • the terminal device supports 6 sets of AI capability information, as follows:
  • Group 1 AI capability information CSI compression, collaboration level 1.
  • Group 2 AI capability information CSI prediction, collaboration level 2.
  • Group 3 AI capability information CSI-RS configuration signaling reduction, cooperation level 2.
  • Group 4 AI capability information beam scanning matrix prediction, collaboration level 2.
  • Group 5 AI capability information optimal beam prediction, collaboration level 1.
  • Group 6 AI capability information terminal device-based positioning enhancement, collaboration level 1.
  • the AI resources supported by the terminal device include the storage capacity that can be provided, and the maximum storage capacity that can be provided is 100M. That is, the maximum storage capacity that the terminal device indicated by the second capability information can provide is 100M.
  • the AI resources corresponding to the above-mentioned first group of AI capability information include: the required storage capacity is 30M
  • the AI resources corresponding to the above-mentioned second group of AI capability information include: the required storage capacity is 40M
  • the above-mentioned third group of AI capability information corresponds to AI resources include: the required storage capacity is 50M.
  • the AI resources corresponding to the above-mentioned 4th group of AI capability information include: the required storage capacity is 100M.
  • the AI resources corresponding to the above-mentioned 5th group of AI capability information include: the required storage capacity is 70M
  • the AI resources corresponding to the above-mentioned 6th group of AI capability information include: the required storage capacity is 50M.
  • the terminal device determines that the first capability information supported includes ⁇ the 1st group of AI capability information (30M); the 2nd group of AI capability information ( 40M) ⁇ , ⁇ The first group of AI capability information (30M); The third group of AI capability information (50M) ⁇ , ⁇ The first group of AI capability information (30M); Group 5 AI capability information (70M) ⁇ , ⁇ Group 1 AI capability information (30M); Group 6 AI capability information (50M) ⁇ , ⁇ Group 2 AI capability information (40M); Group 3 AI capability information (50M) ⁇ , ⁇ Group 2 AI capability information (30M); Group 6 AI capability information (50M) ⁇ , ⁇ Group 3 AI capability information (50M); Group 6 AI capability information (50M) ⁇ , ⁇ At least one of the 4th group of AI capability information (100M) ⁇ .
  • the AI resources corresponding to a set of AI capability information or a combination of multiple sets of AI capability information in the above-mentioned first capability information are all within the range of AI resources that can be provided by the terminal device indicated by the second capability information, that is, a set of The total storage capacity required for AI capability information or the combination of multiple sets of AI capability information is less than or equal to 100M.
  • Step 302 The terminal device sends the first capability information to the wireless access network device.
  • the radio access network device receives the first capability information.
  • Step 303 The radio access network device determines the first AI configuration information based on the first capability information.
  • the radio access network device selects a set of AI capability information or a combination of multiple sets of AI capability information from the first capability information to form the first AI configuration information, and the first AI configuration information is consistent with the selected set of AI capability information.
  • the capability information is the same, or is the same as the selected combination of multiple sets of AI capability information, or is the same as one or more sets of AI capability information in the selected combination of multiple sets of AI capability information.
  • the radio access network device can select one or two sets of AI capability information from ⁇ the first group of AI capability information (30M); the second group of AI capability information (40M) ⁇ to constitute the first AI Configuration information, or select one or two sets of AI capability information from ⁇ Group 1 AI capability information (30M); Group 3 AI capability information (50M) ⁇ to constitute the first AI configuration information, or select ⁇ Group 1 AI Capability information (30M); Group 5 AI capability information (70M) ⁇ one or two groups of AI capability information as the first AI configuration information, or select ⁇ Group 1 AI capability information (30M); Group 6 AI One or two sets of AI capability information in the capability information (50M) ⁇ constitute the first AI configuration information, or select one of the ⁇ 2nd group of AI capability information (40M); 3rd group of AI capability information (50M) ⁇ Either two sets of AI capability information constitute the first AI configuration information, or one or two sets of AI capability information are selected from ⁇ the 2nd group of AI capability information (30M); the 6th group of AI capability information (
  • the radio access network device selects a set of AI capability information or a combination of multiple sets of AI capability information from the first capability information, and based on the selected set of AI capability information or a combination of multiple sets of AI capability information, Generate first AI configuration information.
  • the first AI configuration information is not exactly the same as the selected AI capability information.
  • the first AI configuration information can be composed of the selected AI capability information and other information corresponding to the AI capability information. .
  • the wireless access network device selects ⁇ the first group of AI capability information (30M); the second group of AI capability information (40M) ⁇ from the first capability information.
  • the first AI configuration information determined by the network access device includes ⁇ CSI compression, collaboration level 1, AI model 1 ⁇ and ⁇ CSI prediction, collaboration level 2, AI model 2 ⁇ . It can be seen that the first AI configuration information includes in addition to the The first set of AI capability information and the second set of AI capability information also include the AI model 1 corresponding to the first set of AI capability information, and the AI model 2 corresponding to the second set of AI capability information. Among them, model 1 is selected for the first group of AI capability information, and model 2 is selected for the second group of AI capability information. This is just an example. In practical applications, there is no limit to the method of selecting models. For example, it can be random selection, or Choose the least expensive model and so on.
  • the wireless access network device also supports the first AI configuration information. Specifically, the radio access network device supports the AI function, AI sub-function, collaboration level, AI model, AI algorithm, etc. in the first AI configuration information.
  • the wireless access network device in addition to receiving the first capability information of the terminal device from the terminal device, can also receive the first capability information of the terminal device from other wireless access network devices or core network devices.
  • the core network equipment here can be an AMF network element or an SMF network element, etc. It can be understood that in this implementation, step 301 and step 302 may not be executed.
  • Step 304 The wireless access network device sends the first AI configuration information to the terminal device.
  • the terminal device receives the first AI configuration information.
  • the terminal device After receiving the first AI configuration information, the terminal device executes the corresponding AI function and AI sub-function according to the first AI configuration information.
  • the terminal device since the first AI configuration information is generated based on the AI capability information supported by the terminal device, the terminal device supports the first AI configuration information, which helps to implement correct AI configuration for the terminal device. Moreover, there is a corresponding relationship between multiple AI capability information in the same group, so that when the wireless access network device generates the first AI configuration information, it performs a combined configuration based on the AI capability information in the same group to avoid generating a configuration that is not supported by the terminal device. AI configuration helps reduce the occurrence of misconfiguration.
  • FIG 4 is a schematic flowchart of yet another wireless communication method provided by an embodiment of the present application. This method is used to send updates to the terminal device. New AI configuration information. This method can be implemented in combination with the above-mentioned embodiment of Figure 2 or Figure 3, or can be implemented independently. The method includes the following steps:
  • Step 401 The wireless access network device sends first indication information to the terminal device.
  • the first indication information indicates trigger configuration information for reporting notification information, and the first indication information includes a first threshold and/or a second threshold.
  • the values of the first threshold and/or the second threshold may be predefined by the protocol.
  • This step 401 is an optional step. If step 401 is not performed, the terminal device may be pre-configured with the first threshold and the second threshold.
  • Step 402 The terminal device determines that the trigger condition corresponding to the first indication information is met, and sends notification information to the wireless access network device.
  • the notification information includes at least one of information about AI resources occupied by the terminal device, information about remaining AI resources, and desired AI configuration information.
  • the information about the AI resources occupied by the terminal device includes but is not limited to one or more of the following: occupied computing resources, occupied storage resources, and used power.
  • Information about the remaining AI resources of the terminal device includes but is not limited to one or more of the following: remaining computing resources, remaining storage resources, and remaining power.
  • the desired AI configuration information includes, but is not limited to, one or more of the following: one or more of AI functions, AI sub-functions, collaboration levels, AI models, or AI algorithms.
  • the trigger condition includes: information on AI resources occupied by the terminal device is greater than or equal to a first threshold, and/or information on remaining AI resources of the terminal device is less than or equal to a second threshold.
  • the first threshold includes the threshold value of the occupied computing resources and the threshold value of the occupied storage resources.
  • the second threshold includes the threshold value of the remaining computing resources and the threshold value of the remaining storage resources.
  • Step 403 The radio access network device determines the second AI configuration information based on the notification information and the first capability information.
  • the second AI configuration information can be understood as updated AI configuration information.
  • historical AI configuration information is stored in the wireless access network device, and the historical AI configuration information may be the AI configuration information most recently configured for the terminal device.
  • the second AI configuration information can be determined based on the historical AI configuration information, notification information and first capability information.
  • the radio access network device gives priority to generating updated AI configuration information, that is, the second AI configuration information, for the terminal device based on the desired AI configuration information.
  • the second AI configuration information may correspond to one or more sets of AI capabilities in the above-mentioned first capability information.
  • Information that is, the second AI configuration information is generated based on one or more sets of AI capability information in the first capability information. Based on this method, it can be understood that the second AI configuration information is an update to the first AI configuration information in the embodiment of FIG. 2 or FIG. 3 .
  • Step 404 The wireless access network device sends the second AI configuration information to the terminal device.
  • the above solution can update the AI configuration information for the terminal device, so that the terminal device can use the AI function more reasonably and effectively according to the updated AI configuration information, thereby meeting the communication needs between the terminal device and the wireless access network device and improving the terminal Cooperation efficiency between equipment and radio access network equipment.
  • the wireless access network device can deactivate the AI configuration that has been configured on the terminal device. information.
  • the following introduces an implementation method for triggering and deactivating the AI configuration information of a terminal device. For example, when the terminal device determines that it needs to deactivate the AI configuration information, it sends second instruction information to the wireless access network device. The second instruction information instructs to deactivate the AI configuration information of the terminal device. The wireless access network device can activate the AI configuration information according to the second instruction. Information to activate the AI configuration information of the terminal device.
  • the second indication information may be used to indicate that the terminal device desires to deactivate the AI function, and the radio access network device may deactivate the corresponding AI function on the terminal device.
  • the method of deactivating the AI configuration information on the terminal device can be implemented independently, or can be implemented in combination with the above-mentioned embodiments of Figure 2, Figure 3 or Figure 4, which is not limited in this application.
  • the CU is responsible for exchanging radio resource control (RRC) messages with the terminal device
  • the DU is responsible for processing the information received from the terminal device. Processing is performed, and information can also be generated and sent to the terminal device through the CU.
  • RRC radio resource control
  • the embodiment of FIG. 2 may be implemented according to the embodiment of FIG. 5 .
  • step 202 in Figure 2 corresponds to step 202a and step 202b in Figure 5
  • step 204 in Figure 2 corresponds to step 204a and step 204b in Figure 5
  • step 206 in Figure 2 corresponds to step 206a in Figure 5 and step 206b
  • steps 203 and 205 in Figure 2 are performed by the DU in Figure 5 .
  • step 302 in Figure 3 corresponds to step 302a and step 302b in Figure 6
  • step 304 in Figure 3 corresponds to step 304a and step 304b in Figure 6
  • step 303 in Figure 3 is formed by DU in Figure 6 implement.
  • the embodiment of FIG. 4 may be implemented according to the embodiment of FIG. 7 .
  • step 401 in Figure 4 corresponds to step 401a and step 401b in Figure 7
  • step 402 in Figure 4 corresponds to step 402a and step 402b in Figure 7
  • step 404 in Figure 4 corresponds to step 404a in Figure 7 and step 404b
  • step 403 in FIG. 4 are performed by the DU in FIG. 7 .
  • the radio access network equipment (CU or DU) can be further divided into a first network element with an AI decision-making function and a second network element with an AI implementation function.
  • the first network element may be called an AI controller, or a near-real-time wireless access network intelligent controller.
  • the second network element is used to manage the sending or receiving of information between it and other access network equipment or terminal equipment, and forward relevant information to the first network element.
  • the first network element can make a decision based on the above information, and send the determined configuration information to the second network element, so that the second network element can perform subsequent operations based on the configuration information. For example, send the above configuration information to other access network equipment or terminal equipment.
  • the radio access network device when the radio access network device includes the above-mentioned first network element and the second network element, in the above embodiment, the radio access network device receives the first capability information, or receives the first capability information and the second capability information, And the operation of determining the AI resource demand information corresponding to at least one set of AI capability information, or determining the first AI configuration information, may include:
  • the second network element receives the first capability information, or receives the first capability information and the second capability information;
  • the second network element sends the received first capability information to the first network element, or receives part or all of the first capability information and the second capability information;
  • the first network element determines the AI resource requirement information corresponding to at least one set of AI capability information respectively, or determines the first AI configuration based on the received first capability information, or receives part or all of the first capability information and the second capability information. information;
  • the first network element sends the AI resource demand information respectively corresponding to the at least one set of AI capability information to the second network element, or determines the first AI configuration information.
  • the terminal device and/or the radio access network device can perform some or all of the steps in the embodiment of the present application. These steps or operations are only examples, and the embodiment of the present application can also perform other operations. Or variations of various operations. In addition, various steps may be performed in a different order than those presented in the embodiments of the present application, and it may not be necessary to perform all operations in the embodiments of the present application.
  • the radio access network device and the terminal device include corresponding hardware structures and/or software modules that perform each function.
  • the units and method steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software driving the hardware depends on the specific application scenarios and design constraints of the technical solution.
  • Figures 8 and 9 are schematic structural diagrams of possible communication devices provided by embodiments of the present application. These communication devices can be used to implement the functions of the terminal equipment or the radio access network equipment in the above method embodiments, and therefore can also achieve the beneficial effects of the above method embodiments.
  • the communication device may be the terminal equipment shown in Figure 1, or the wireless access network equipment shown in Figure 1, or may be a module applied to the terminal equipment or the radio access network equipment. (such as chips).
  • the communication device 800 shown in FIG. 8 includes a processing unit 810 and a transceiver unit 820.
  • the communication device 800 is used to implement the functions of the terminal device or the radio access network device in the above method embodiment.
  • the transceiver unit 820 is used to receive the first capability information of the terminal device.
  • a capability information includes at least one set of AI capability information supported by the terminal device; the processing unit 810 is configured to determine, based on the first capability information, the AI resource requirement information corresponding to the at least one set of AI capability information.
  • the processing unit 810 is specifically configured to determine the AI resource requirement information respectively corresponding to the at least one piece of AI capability information based on the first capability information and a predefined correspondence relationship.
  • the predefined correspondence relationship includes: Correspondence between the at least one AI capability information and the AI resource requirement information.
  • the transceiver unit 820 is also used to receive the second capability information of the terminal device, where the second capability information is used to indicate information about the AI resources that the terminal device can provide; the processing unit 810 is also used to Determine first AI configuration information based on the AI resource demand information corresponding to the second capability information and the at least one set of AI capability information, and the first AI configuration information corresponds to one or more of the at least one set of AI capability information. Group AI capability information; the wireless access network device sends the first AI configuration information to the terminal device.
  • the transceiver unit 820 is also used to receive notification information from the terminal device, where the notification information includes At least one of information on AI resources occupied by the terminal device, information on remaining AI resources, and desired AI configuration information.
  • the processing unit 810 is also configured to determine second AI configuration information based on the notification information and the first capability information.
  • the second AI configuration information corresponds to one of the at least one set of AI capability information.
  • One or more sets of AI capability information; the transceiver unit 820 is also used to send the second AI configuration information to the terminal device.
  • the transceiver unit 820 is also configured to send first indication information to the terminal device, where the first indication information indicates a trigger condition for reporting the notification information.
  • the transceiver unit 820 is also configured to receive second instruction information from the terminal device, the second instruction information instructs to deactivate the AI configuration information of the terminal device; the radio access network device according to the The second instruction information is to activate the AI configuration information of the terminal device.
  • the transceiver unit 820 is specifically configured to receive the first capability information from other radio access network equipment, the terminal equipment, or the core network equipment.
  • the transceiver unit 820 is specifically configured to receive the second capability information from other radio access network equipment, the terminal equipment, or the core network equipment.
  • the processing unit 810 is used to determine the first capability information
  • the first capability information includes the terminal device supports At least one set of the AI capability information
  • the transceiver unit 820 is configured to send the first capability information to the radio access network device.
  • the transceiver unit 820 is also configured to send second capability information to the radio access network device, where the second capability information is used to indicate information about AI resources that the terminal device can provide; receiving from the First AI configuration information of the radio access network device, the first AI configuration information is determined based on the AI resource requirement information corresponding to the second capability information and the at least one set of AI capability information, and the first AI configuration information is There should be at least one or more sets of AI capability information in one set of AI capability information.
  • the transceiver unit 820 is also configured to send notification information to the radio access network device when the processing unit 810 determines that the trigger condition is met.
  • the notification information includes information about the AI resources occupied by the terminal device, At least one of the remaining AI resource information and the desired AI configuration information; wherein the triggering condition includes: the information on the AI resources occupied by the terminal device is greater than the first threshold, and/or the remaining AI resources of the terminal device The information is less than the second threshold.
  • the transceiver unit 820 is also configured to receive second AI configuration information from the radio access network device, where the second AI configuration information is determined based on the notification information and the first capability information,
  • the second AI configuration information corresponds to one or more sets of AI capability information in the at least one set of AI capability information.
  • the transceiver unit 820 is also configured to receive first indication information from the radio access network device, where the first indication information indicates the triggering condition for reporting the notification information, and the first indication information includes the first threshold and/or the second threshold.
  • the transceiver unit 820 is also configured to send second instruction information to the radio access network device, where the second instruction information instructs to deactivate the AI configuration information of the terminal device.
  • the transceiver unit 820 is used to receive the first capability information of the terminal device.
  • One capability information includes a set of the AI capability information supported by the terminal device within the scope of the AI resource indicated by the second capability information, or the combination information of at least two sets of AI capability information.
  • the second capability information is used to indicate that the terminal device can Information about provided AI resources; the processing unit 810 is configured to determine first AI configuration information based on the first capability information, where the first AI configuration information corresponds to the set of AI capability information or a combination of the at least two sets of AI capability information.
  • One or more sets of AI capability information in the information; the transceiver unit 820 is also used to send the first AI configuration information to the terminal device.
  • the transceiver unit 820 is also used to receive notification information from the terminal device.
  • the notification information includes information about the AI resources occupied by the terminal device, information about the remaining AI resources, and desired AI configuration information. at least one of them.
  • the processing unit 810 is also configured to determine second AI configuration information based on the notification information and the first capability information.
  • the second AI configuration information corresponds to the set of AI capability information or the at least two AI capability information.
  • One or more groups of AI capability information in the combined information of the group of AI capability information; the transceiver unit 820 is also configured to send the second AI configuration information to the terminal device.
  • the transceiver unit 820 is also configured to send first indication information to the terminal device, where the first indication information indicates a trigger condition for reporting the notification information.
  • the transceiver unit 820 is also configured to receive second instruction information from the terminal device, the second instruction information instructs to deactivate the AI configuration information of the terminal device; the processing unit 810 is also configured to The second instruction information deactivates the AI configuration information of the terminal device.
  • the transceiver unit 820 is specifically used to receive data from other wireless access network equipment, the terminal equipment or the core network equipment.
  • the equipment receives the first capability information.
  • the processing unit 810 is used to determine the first capability information based on the second capability information.
  • the first capability The information includes a set of AI capability information supported by the terminal device within the scope of the AI resource indicated by the second capability information, or a combination of at least two sets of AI capability information.
  • the second capability information is used to indicate the AI that the terminal device can provide.
  • Resource information; the transceiver unit 820 is configured to send the first capability information to the radio access network device.
  • the transceiver unit 820 is also configured to send notification information to the radio access network device when the processing unit 810 determines that the trigger condition is met.
  • the notification information includes information about the AI resources occupied by the terminal device, At least one of the remaining AI resource information and the desired AI configuration information; wherein the triggering condition includes: the information on the AI resources occupied by the terminal device is greater than the first threshold, and/or the remaining AI resources of the terminal device The information is less than the second threshold.
  • the transceiver unit 820 is also configured to receive second AI configuration information from the radio access network device, where the second AI configuration information is determined based on the notification information and the first capability information,
  • the second AI configuration information corresponds to one or more sets of AI capability information in the set of AI capability information or the combined information of at least two sets of AI capability information.
  • the transceiver unit 820 is also configured to receive first indication information from the radio access network device, where the first indication information indicates the triggering condition for reporting the notification information, and the first indication information includes the first threshold and/or the second threshold.
  • the transceiver unit 820 is also configured to send second instruction information to the radio access network device, where the second instruction information instructs to deactivate the AI configuration information of the terminal device.
  • the communication device 900 shown in FIG. 9 includes a processor 910 and an interface circuit 920.
  • the processor 910 and the interface circuit 920 are coupled to each other.
  • the interface circuit 920 may be a transceiver or an input-output interface.
  • the communication device 900 may also include a memory 930 for storing instructions executed by the processor 910 or input data required for the processor 910 to run the instructions or data generated after the processor 910 executes the instructions.
  • the processor 910 is used to realize the function of the above processing unit 810
  • the interface circuit 920 is used to realize the function of the above transceiver unit 820.
  • the chip of the terminal device implements the functions of the terminal device in the above method embodiment.
  • the chip of the terminal device receives information from other modules (such as radio frequency modules or antennas) in the terminal device, and the information is sent by the wireless access network device to the terminal device; or, the chip of the terminal device sends information to other modules in the terminal device. (such as a radio frequency module or antenna) sends information, which is sent by the terminal device to the wireless access network device.
  • the module of the wireless access network device implements the functions of the wireless access network device in the above method embodiment.
  • the module of the wireless access network device receives information from other modules (such as radio frequency modules or antennas) in the wireless access network device, and the information is sent by the terminal device to the wireless access network device; or, the wireless access network device
  • the module sends information to other modules (such as radio frequency modules or antennas) in the wireless access network equipment, and the information is sent by the wireless access network equipment to the terminal equipment.
  • the module of the wireless access network equipment here can be the baseband chip of the wireless access network equipment, or it can be a DU or other module.
  • the DU here can be an open radio access network (open radio access network, O-RAN) architecture DU under.
  • the present application provides a communication system, including a wireless access network device and a terminal device, wherein the wireless access network device can implement the wireless communication system in the embodiments of FIG. 2, FIG. 4, FIG. 5, and FIG. 7.
  • the terminal device can realize the functions of the terminal device in the embodiments of FIG. 2, FIG. 4, FIG. 5, and FIG. 7.
  • the present application provides a base station including a CU and a DU, wherein the DU can implement the functions of the DU in the embodiments of FIG. 2, FIG. 4, FIG. 5, and FIG. 7.
  • the processor in the embodiment of the present application can be a central processing unit (Central Processing Unit, CPU), or other general-purpose processor, digital signal processor (Digital Signal Processor, DSP), or application specific integrated circuit. (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.
  • a general-purpose processor can be a microprocessor or any conventional processor.
  • the method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions.
  • Software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory memory, register, hard disk, mobile Hard disk, compact disc read-only memory (CD-ROM) or any other form of storage media well known in the art.
  • An exemplary storage medium is coupled to the processor such that the processor can read information from the storage medium and write information to the storage medium.
  • the storage medium can also be an integral part of the processor.
  • the processor and storage media may be located in an ASIC.
  • the ASIC may be located in the radio access network device or the terminal device.
  • the processor and the storage medium may also exist as discrete components in the radio access network device or the terminal device.
  • the computer program product includes one or more computer programs or instructions.
  • a computer program (Computer Program) refers to a set of instructions that instruct each step of an electronic computer or other device with message processing capabilities. It is usually written in a certain programming language and runs on a certain target architecture. When the computer program or instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are executed in whole or in part.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, a wireless access network device, a terminal device, or other programmable devices.
  • the computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.
  • the computer program or instructions may be transmitted from a website, computer, A server or data center transmits via wired or wireless means to another website site, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media.
  • the available media may be magnetic media, such as floppy disks, hard disks, and tapes; optical media, such as digital video optical disks; or semiconductor media, such as solid-state hard drives.
  • the computer-readable storage medium may be volatile or nonvolatile storage media, or may include both volatile and nonvolatile types of storage media.
  • the protocol described in this application may refer to a communication protocol or specification, such as the 3GPP communication protocol.
  • the terminal device and/or the radio access network device may perform some or all of the steps in the embodiment of the present application. These steps or operations are only examples. In the embodiment of the present application, the terminal device and/or the radio access network device may also perform Other operations or variations of various operations. In addition, various steps may be performed in a different order than those presented in the embodiments of the present application, and it may not be necessary to perform all operations in the embodiments of the present application.
  • “at least one” refers to one or more, and “plurality” refers to two or more.
  • “And/or” describes the association of associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the related objects before and after are an “or” relationship; in the formula of this application, the character “/” indicates that the related objects before and after are a kind of "division” Relationship.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请提供一种无线通信方法及通信装置。该方法中，终端设备向无线接入网设备上报该终端设备支持的一组或多组AI能力信息，无线接入网设备确定该一组或多组AI能力信息分别对应的AI资源需求信息，进而能够根据AI资源需求信息决策如何为终端设备进行AI配置，使得终端设备能够合理、有效地使用AI功能，进而能够提升终端设备与无线接入网设备之间的协作效率。

Description

一种无线通信方法及通信装置
相关申请的交叉引用
本申请要求在2022年08月29日提交中国专利局、申请号为202211039259.8、申请名称为“一种无线通信方法及通信装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及无线通信技术领域，尤其涉及一种无线通信方法及通信装置。
背景技术
人工智能(artificial intelligence，AI)是通过模拟人脑进行复杂计算的技术。随着数据存储和计算能力的提升，人工智能得到了越来越多的运用。第三代合作伙伴计划(3rd generation partnership project，3GPP)提出将人工智能运用到第五代(5th generation，5G)通信系统中，通过智能收集和数据分析，提升网络性能和用户体验。
然而，如何在5G及未来通信系统中合理、有效地使用AI功能，以提升终端设备与无线接入网设备之间的协作效率，有待解决。
发明内容
本申请提供一种无线通信方法及通信装置，用以提升终端设备与无线接入网设备之间的协作效率。
第一方面，本申请实施例提供一种无线通信方法，该方法可以由无线接入网设备或应用于无线接入网设备中的模块(如芯片)来执行。该方法包括：无线接入网设备接收终端设备的第一能力信息，该第一能力信息包括该终端设备支持的至少一组该AI能力信息；该无线接入网设备根据该第一能力信息，确定该至少一组AI能力信息分别对应的AI资源需求信息。
上述方案，终端设备向无线接入网设备上报该终端设备支持的一组或多组AI能力信息，无线接入网设备确定该一组或多组AI能力信息分别对应的AI资源需求信息，进而能够根据AI资源需求信息决策如何为终端设备进行AI配置，使得终端设备能够合理、有效地使用AI功能，进而能够提升终端设备与无线接入网设备之间的协作效率。
一种可能的实现方法中，该无线接入网设备根据该第一能力信息，确定该至少一组AI能力信息分别对应的AI资源需求信息，包括：该无线接入网设备根据该第一能力信息和预定义的对应关系，确定该至少一个AI能力信息分别对应的AI资源需求信息，该预定义的对应关系包括该至少一个AI能力信息与该AI资源需求信息之间的对应关系。
上述方案，预先定义AI能力信息与AI资源需求信息之间的对应关系，无线接入网设备根据该对应关系能够快速、准确确定终端设备发送的第一能力信息中的至少一组AI能力信息分别对应的AI资源需求信息，进而有助于实现为终端设备准确确定AI配置信息。
一种可能的实现方法中，该无线接入网设备接收该终端设备的第二能力信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；该无线接入网设备根据该第二能力信息和该至少一组AI能力信息分别对应的AI资源需求信息，确定第一AI配置信息，该第一AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息；该无线接入网设备向该终端设备发送该第一AI配置信息。
上述方案，由于第一AI配置信息是根据终端设备支持的至少一组AI能力信息生成的，因此终端设备支持该第一AI配置信息，有助于实现为终端设备执行正确的AI配置。
一种可能的实现方法中，该无线接入网设备接收来自该终端设备的通知信息，该通知信息包括该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项。
一种可能的实现方法中，该无线接入网设备根据该通知信息和该第一能力信息，确定第二AI配置信息，该第二AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息；该无线接入网设备向该终端设备发送该第二AI配置信息。
上述方案，能够实现为终端设备更新AI配置信息，以使得终端设备根据更新的AI配置信息更加合理、有效地使用AI功能，从而满足终端设备与无线接入网设备之间的通信需求和提升终端设备与无 线接入网设备之间的协作效率。
一种可能的实现方法中，该无线接入网设备向该终端设备发送第一指示信息，该第一指示信息指示上报该通知信息的触发条件。
一种可能的实现方法中，该无线接入网设备接收来自该终端设备的第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息；该无线接入网设备根据该第二指示信息，去激活该终端设备的AI配置信息。
上述方案，在终端设备不需要使用AI功能时，可以去激活终端设备的AI配置信息，有助于节约终端设备的能耗。
一种可能的实现方法中，该无线接入网设备接收终端设备的第一能力信息，包括：该无线接入网设备从其他无线接入网设备、该终端设备或核心网设备接收该第一能力信息。
一种可能的实现方法中，该无线接入网设备接收终端设备的第二能力信息，包括：该无线接入网设备从其他无线接入网设备、该终端设备或核心网设备接收该第二能力信息。
第二方面，本申请实施例提供一种无线通信方法，该方法可以由终端设备或应用于终端设备中的模块(如芯片)来执行。该方法包括：终端设备确定第一能力信息，该第一能力信息包括该终端设备支持的至少一组该AI能力信息；该终端设备向无线接入网设备发送该第一能力信息。
上述方案，终端设备向无线接入网设备上报该终端设备支持的一组或多组AI能力信息，无线接入网设备可以根据该终端设备支持的一组或多组AI能力信息，决策如何为终端设备进行AI配置，使得终端设备能够合理、有效地使用AI功能，进而能够提升终端设备与无线接入网设备之间的协作效率。
一种可能的实现方法中，该终端设备向该无线接入网设备发送第二能力信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；该终端设备接收来自该无线接入网设备的第一AI配置信息，该第一AI配置信息是根据该第二能力信息和该至少一组AI能力信息分别对应的AI资源需求信息确定的，该第一AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息。
上述方案，由于第一AI配置信息是根据终端设备支持的至少一组AI能力信息生成的，因此终端设备支持该第一AI配置信息，有助于实现为终端设备执行正确的AI配置。
一种可能的实现方法中，该终端设备确定满足触发条件，向该无线接入网设备发送通知信息，该通知信息包括该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项；其中，该触发条件包括：该终端设备占用的AI资源的信息大于第一门限，和/或，该终端设备剩余的AI资源的信息小于第二门限。
一种可能的实现方法中，该终端设备接收来自该无线接入网设备的第二AI配置信息，该第二AI配置信息是根据该通知信息和该第一能力信息确定的，该第二AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息。
上述方案，能够实现为终端设备更新AI配置信息，以使得终端设备根据更新的AI配置信息更加合理、有效地使用AI功能，从而满足终端设备与无线接入网设备之间的通信需求和提升终端设备与无线接入网设备之间的协作效率。
一种可能的实现方法中，该终端设备接收来自该无线接入网设备的第一指示信息，该第一指示信息指示上报该通知信息的该触发条件，该第一指示信息包括该第一门限和/或该第二门限。
一种可能的实现方法中，该终端设备向该无线接入网设备发送第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息。
上述方案，在终端设备不需要使用AI功能时，可以去激活终端设备的AI配置信息，有助于节约终端设备的能耗。
基于上述第一方面、第二方面的任意实现方法：
一种可能的实现方法中，每组AI能力信息包括该终端设备支持的AI功能、AI子功能、协作等级、AI模型或AI算法中的至少一个。
一种可能的实现方法中，每组AI能力信息包括至少两个AI能力信息，该至少两个AI能力信息之间存在对应关系。
上述方案，同一组内的多个AI能力信息之间存在对应关系，从而无线接入网设备在生成AI配置信息时，根据同一组内的AI能力信息进行组合配置，避免生成终端设备不支持的AI配置，有助于减少错误配置的发生。
一种可能的实现方法中，该第一能力信息还包括：该至少一组AI能力信息分别对应的AI资源需求信息，或者，该至少一组AI能力信息分别对应的AI资源需求信息的索引信息。
一种可能的实现方法中，该终端设备能够提供的AI资源的信息包括该终端设备的最大计算能力信息、最大存储能力信息、最大电量信息、处理时延信息、支持的AI模型信息或者支持的AI算法信息中的至少一个。
第三方面，本申请实施例提供一种无线通信方法，该方法可以由无线接入网设备或应用于无线接入网设备中的模块(如芯片)来执行。该方法包括：无线接入网设备接收终端设备的第一能力信息，该第一能力信息包括在第二能力信息指示的AI资源的范围内该终端设备支持的一组AI能力信息或者至少两组AI能力信息的组合信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；该无线接入网设备根据该第一能力信息，确定第一AI配置信息，该第一AI配置信息对应该一组AI能力信息或该至少两组AI能力信息的组合信息中的一组或多组AI能力信息；该无线接入网设备向该终端设备发送该第一AI配置信息。
上述方法，由于第一AI配置信息是根据终端设备支持的AI能力信息生成的，因此终端设备支持该第一AI配置信息，有助于实现为终端设备执行正确的AI配置，从而提升终端设备与无线接入网设备之间的协作效率。
一种可能的实现方法中，该无线接入网设备接收来自该终端设备的通知信息，该通知信息包括该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项。
一种可能的实现方法中，该无线接入网设备根据该通知信息和该第一能力信息，确定第二AI配置信息，该第二AI配置信息对应该一组AI能力信息或该至少两组AI能力信息的组合信息中的一组或多组AI能力信息；该无线接入网设备向该终端设备发送该第二AI配置信息。
上述方案，能够实现为终端设备更新AI配置信息，以使得终端设备根据更新的AI配置信息更加合理、有效地使用AI功能，从而满足终端设备与无线接入网设备之间的通信需求和提升终端设备与无线接入网设备之间的协作效率。
一种可能的实现方法中，该无线接入网设备向该终端设备发送第一指示信息，该第一指示信息指示上报该通知信息的触发条件。
一种可能的实现方法中，该无线接入网设备接收来自该终端设备的第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息；该无线接入网设备根据该第二指示信息，去激活该终端设备的AI配置信息。
一种可能的实现方法中，该无线接入网设备接收终端设备的第一能力信息，包括：该无线接入网设备从其他无线接入网设备、该终端设备或核心网设备接收该第一能力信息。
第四方面，本申请实施例提供一种无线通信方法，该方法可以由终端设备或应用于终端设备中的模块(如芯片)来执行。该方法包括：终端设备根据第二能力信息，确定第一能力信息，该第一能力信息包括在第二能力信息指示的AI资源的范围内该终端设备支持的至少AI能力信息或者至少两组AI能力信息的组合信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；该终端设备向无线接入网设备发送该第一能力信息。
上述方案，终端设备向无线接入网设备上报该终端设备支持的AI能力信息，无线接入网设备可以根据该终端设备支持的AI能力信息，决策如何为终端设备进行AI配置，使得终端设备能够合理、有效地使用AI功能，进而能够提升终端设备与无线接入网设备之间的协作效率。
一种可能的实现方法中，该终端设备能够提供的AI资源的信息包括该终端设备的最大计算能力信息、最大存储能力信息、最大电量信息、处理时延信息、支持的AI模型信息或者支持的AI算法信息中的至少一个。
一种可能的实现方法中，该终端设备确定满足触发条件，向该无线接入网设备发送通知信息，该通知信息包括该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项；其中，该触发条件包括：该终端设备占用的AI资源的信息大于第一门限，和/或，该终端设备剩余的AI资源的信息小于第二门限。
一种可能的实现方法中，该终端设备接收来自该无线接入网设备的第二AI配置信息，该第二AI配置信息是根据该通知信息和该第一能力信息确定的，该第二AI配置信息对应该一组AI能力信息或者至少两组AI能力信息的组合信息中的一组或多组AI能力信息。
上述方案，能够实现为终端设备更新AI配置信息，以使得终端设备根据更新的AI配置信息更加合理、有效地使用AI功能，从而满足终端设备与无线接入网设备之间的通信需求和提升终端设备与无线接入网设备之间的协作效率。
一种可能的实现方法中，该终端设备接收来自该无线接入网设备的第一指示信息，该第一指示信息指示上报该通知信息的该触发条件，该第一指示信息包括该第一门限和/或该第二门限。
一种可能的实现方法中，该终端设备向该无线接入网设备发送第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息。
基于上述第三方面、第四方面的任意实现方法：
一种可能的实现方法中，每组AI能力信息包括该终端设备支持的AI功能、AI子功能、协作等级、AI模型或AI算法中的至少一个。
一种可能的实现方法中，每组AI能力信息包括至少两个AI能力信息，该至少两个AI能力信息之间存在对应关系。
上述方案，同一组内的多个AI能力信息之间存在对应关系，从而无线接入网设备在生成AI配置信息时，根据同一组内的AI能力信息进行组合配置，避免生成终端设备不支持的AI配置，有助于减少错误配置的发生。
第五方面，本申请实施例提供一种通信装置，该装置可以是无线接入网设备，还可以是用于无线接入网设备的模块(如芯片)。该装置具有实现上述第一方面或第三方面的任意实现方法的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。
第六方面，本申请实施例提供一种通信装置，该装置可以是终端设备，还可以是用于终端设备的模块(如芯片)。该装置具有实现上述第二方面或第四方面的任意实现方法的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。
第七方面，本申请实施例提供一种通信装置，包括处理器和存储器；该存储器用于存储计算机指令，当该装置运行时，该处理器执行该存储器存储的计算机指令，以使该装置执行上述第一方面至第四方面中的任意实现方法。
第八方面，本申请实施例提供一种通信装置，包括用于执行上述第一方面至第四方面中的任意实现方法的各个步骤的单元或手段(means)。
第九方面，本申请实施例提供一种通信装置，包括处理器和接口电路，所述处理器用于通过接口电路与其它装置通信，并执行上述第一方面至第四方面中的任意实现方法。该处理器包括一个或多个。
第十方面，本申请实施例提供一种通信装置，包括与存储器耦合的处理器，该处理器用于调用所述存储器中存储的程序，以执行上述第一方面至第四方面中的任意实现方法。该存储器可以位于该装置之内，也可以位于该装置之外。且该处理器可以是一个或多个。
第十一方面，本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当其在通信装置上运行时，使得上述第一方面至第四方面中的任意实现方法被执行。
第十二方面，本申请实施例还提供一种计算机程序产品，该计算机程序产品包括计算机程序或指令，当计算机程序或指令被通信装置运行时，使得上述第一方面至第四方面中的任意实现方法被执行。
第十三方面，本申请实施例还提供一种芯片系统，包括：处理器，用于执行上述第一方面或第三方面的任意实现方法。
第十四方面，本申请实施例还提供一种芯片系统，包括：处理器，用于执行上述第二方面或第四方面的任意实现方法。
第十五方面，本申请实施例还提供一种通信系统，包括：用于执行上述第一方面任意实现方法的无线接入网设备和用于执行上述第二方面任意实现方法的终端设备。
第十六方面，本申请实施例还提供一种通信系统，包括：用于执行上述第三方面任意实现方法的无线接入网设备和用于执行上述第四方面任意实现方法的终端设备。
附图说明
图1为本申请实施例应用的通信系统的架构示意图；
图2为本申请实施例提供的一种无线通信方法的流程示意图；
图3为本申请实施例提供的一种无线通信方法的流程示意图；
图4为本申请实施例提供的一种无线通信方法的流程示意图；
图5为本申请实施例提供的一种无线通信方法的流程示意图；
图6为本申请实施例提供的一种无线通信方法的流程示意图；
图7为本申请实施例提供的一种无线通信方法的流程示意图；
图8为本申请的实施例提供的可能的通信装置的结构示意图；
图9为本申请的实施例提供的可能的通信装置的结构示意图。
具体实施方式
图1为本申请实施例应用的通信系统的架构示意图。该通信系统包括终端设备和无线接入网设备。该通信系统适用于5G通信网络，非陆地网络(non-terrestrial network，NTN)或者未来通信网络，例如第六代(6th generation，6G)通信网络。
终端设备是一种具有无线收发功能的设备，终端设备可以部署在陆地上，包括室内或室外、手持或车载；也可以部署在水面上(如轮船等)；还可以部署在空中(例如飞机、气球和卫星上等)。所述终端设备可以是手机(mobile phone)、平板电脑(pad)、带无线收发功能的电脑、虚拟现实(virtual reality，VR)终端设备、增强现实(augmented reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self driving)中的无线终端设备、远程医疗(telemedicine)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端设备、智慧家庭(smart home)中的无线终端，以及还可以是用户设备(user equipment，UE)等。
无线接入网(radio access network，RAN)设备，是能够将终端设备接入到无线网络的设备。无线接入网设备可以是：下一代节点(gNodeB，gNB)、传输接收点(transmission reception point，TRP)、演进型节点B(evolved Node B，eNB)、无线网络控制器(radio network controller，RNC)、节点B(Node B，NB)、基站控制器(base station controller，BSC)、基站收发台(base transceiver station,BTS)、家庭基站(例如，home evolved NodeB，或home Node B，HNB)、基带单元(base band unit，BBU)，或无线保真(wireless fidelity，Wifi)接入点(access point，AP)、接入回传一体化(integrated access and backhaul，IAB)等。
本申请实施例中的无线接入网设备也可以是集中单元(central unit，CU)或分布式单元(distributed unit，DU)，或者包括CU和DU。CU和DU可以理解为是对无线接入网设备从逻辑功能角度进行的划分。其中，CU和DU在物理上可以是分离的，也可以部署在一起，本申请实施例对此不做具体限定。一个CU可以连接一个DU，或者也可以多个DU共用一个CU。CU和DU的切分可以按照协议栈切分，其中一种可能的方式是将无线资源控制(radio resource control，RRC)、业务数据适配协议栈(service data adaptation protocol，SDAP)以及分组数据汇聚协议(packet data convergence protocol，PDCP)层部署在CU，其余的无线链路控制(radio link control，RLC)层、介质访问控制(media access control，MAC)层以及物理层部署在DU。本发明中并不完全限定上述协议栈切分方式，还可以有其它的切分方式。
本申请实施例中的无线接入网设备也可以是指集中式单元控制面(CU-CP)节点或者集中式单元用户面(CU-UP)节点，或者包括CU-CP和CU-UP。其中，CU-CP负责控制面功能，主要包含RRC和PDCP-C。PDCP-C主要负责控制面数据的加解密，完整性保护，数据传输等。CU-UP负责用户面功能，主要包含SDAP和PDCP-U。其中SDAP主要负责将核心网的数据进行处理并将流(flow)映射到承载。PDCP-U主要负责数据面的加解密，完整性保护，头压缩，序列号维护，数据传输等。
无线接入网设备和终端设备可以部署在陆地上，包括室内或室外、手持或车载；也可以部署在水面上；还可以部署在空中的飞机、气球和卫星上。本申请的实施例对无线接入网设备和终端设备的应用场景不做限定。
本申请的实施例可以适用于下行信号传输，也可以适用于上行信号传输。对于下行信号传输，发送设备是无线接入网设备，对应的接收设备是终端设备。对于上行信号传输，发送设备是终端设备，对应的接收设备是无线接入网设备。本申请的实施例对信号的传输方向不做限定。
无线接入网设备和终端设备之间可以通过授权频谱(licensed spectrum)进行通信，也可以通过免授权频谱(unlicensed spectrum)进行通信，也可以同时通过授权频谱和免授权频谱进行通信。无线接 入网设备和终端设备之间可以通过6千兆赫(gigahertz，GHz)以下的频谱进行通信，也可以通过6G以上的频谱进行通信，还可以同时使用6G以下的频谱和6G以上的频谱进行通信。本申请的实施例对无线接入网设备和终端设备之间所使用的频谱资源不做限定。
为便于理解本申请方案，下面针对本申请中涉及的一些名词或术语进行说明。该名词或术语也属于本发明的一部分。
一、AI功能
AI功能也称为AI应用场景。AI功能包括但不限于：信道状态信息参考信号(channel status information reference signal，CSI-RS)反馈增强(CSI-RS feedback enhancement)、波束管理增强(beam management enhancement)、定位增强(positioning accuracy enhancement)。下面分别说明。示例性的，一个AI功能可以包括多个AI子功能。
1)CSI-RS反馈增强
CSI-RS包括但不限于以下至少一项：信道质量指示(chanel quality indicator，CQI)、预编码矩阵指示(precoding matrix indicator，PMI)、CSI-RS资源指示(CSI-RS resource indicator，CRI)、层指示(layer indicator，LI)、秩指示(rank indicator，RI)。
CSI-RS反馈增强可以包括至少一个子功能，比如分别为：CSI压缩，CSI预测，CSI-RS配置信令减少。其中，CSI压缩又可以分为在空域、时域和频域至少一种域上的CSI压缩。
2)波束管理增强
波束管理增强可以包括至少一个子功能，比如分别为：波束扫描矩阵预测、最优波束预测。
3)定位增强
定位增强用于提升定位准确率。定位增强可以包括至少一个子功能，比如分别为：基于接入网设备的定位增强、基于定位管理功能网元的定位增强、基于终端设备的定位增强。
二、AI模型的协作等级
考虑到AI模型的部署，终端设备与无线接入网设备之间的交互，可能的协作等级(collaboration level)可以分为三种：
1)协作等级0(Level 0)
协作等级0也称为无协作(No collaboration)。在该协作等级0中，无线接入网设备的AI模型对终端设备完全不可见，AI模型的训练和推理都在无线接入网设备内部完成，不会在空口向终端设备发送模型的信息或模型实例的信息。
2)协作等级1(Level 1)
协作等级1也称为无模型交互的基于信令的协作(signaling-based collaboration without model transfer)。在该协作等级1中，一种可能的实现方式下，无线接入网设备向终端设备发送AI模型的实例，即字典，终端设备使用该字典协助无线接入网设备进行AI推理，对空口有影响。终端设备根据该字典进行信道压缩编码。可选的，终端设备内部也可以部署有AI模型，当终端设备部署有AI模型，则终端设备根据该AI模型以及从无线接入网设备收到的字典，进行信道压缩编码。终端设备和无线接入网设备可以联合训练模型，例如通过联邦学习方式训练模型。终端设备与无线接入网设备在空口上不会直接传递模型，但可以传递模型参数、权值等。
本申请实施例中，终端设备或无线接入网设备部署AI模型，可以理解为部署用于实现AI模型的功能的软件模块或硬件模块。
此外，考虑到模型的部署，协作等级1可以分为协作等级1A和协作等级1B，其中：
协作等级1A：也称为单侧节点部署模型的无模型交互的基于信令的协作(signaling-based collaboration for single-sided model without model transfer)，也即无线接入网设备部署有AI模型，终端设备没有部署AI模型。
协作等级1B：也称为双侧节点部署模型的无模型交互的基于信令的协作(signaling-based collaboration for two-sided model without model transfer)，也即无线接入网设备和终端设备均部署有AI模型。
3)协作等级2(Level 2)
协作等级2也称为有模型交互的基于信令的协作(signaling-based collaboration with model transfer)。在该协作等级2中，无线接入网设备与终端设备均部署有AI模型，都可以进行推理，且空口上可以交 互AI模型的信息。协作等级2与协作等级1的区别包括：协作等级2在空口上可以传递AI模型的信息。
为了能够合理、有效地为终端设备进行AI配置，本申请提出了一种无线通信方法。可以理解，本申请提供的方法可以由终端设备和/或无线接入网设备执行，也可以由用于终端设备和/或无线接入网设备的模块(例如芯片)执行，以下以终端设备以及无线接入网设备作为执行主体介绍本申请提供的无线通信方法。图2为本申请实施例提供的一种无线通信方法的流程示意图。该方法包括以下步骤：
步骤201，终端设备确定第一能力信息，第一能力信息包括终端设备支持的至少一组AI能力信息。
其中，每组AI能力信息包括至少一个AI能力信息，示例性地，每组AI能力信息包括终端设备支持的AI功能、AI子功能、协作等级、AI模型或AI算法中的至少一个。
当每组AI能力信息包括至少两个AI能力信息时，则该至少两个AI能力信息之间存在对应关系，也即该至少两个AI能力信息构成配对关系。
示例性地，第一能力信息包括6组AI能力信息，分别如下：
第1组AI能力信息：CSI压缩、协作等级1。
第2组AI能力信息：CSI预测、协作等级2。
第3组AI能力信息：CSI-RS配置信令减少、协作等级2。
第4组AI能力信息：波束扫描矩阵预测、协作等级2。
第5组AI能力信息：最优波束预测、协作等级1。
第6组AI能力信息：基于终端设备的定位增强、协作等级1。
其中，每组AI能力信息中的各项内容之间存在对应关系，以第1组AI能力信息为例，AI子功能为CSI压缩，该CSI压缩相应的协作等级为协作等级1。具体地，终端设备支持使用协作等级1来实现CSI压缩的AI子功能，CSI压缩与协作等级1之间具有绑定关系或协作关系。示例性地，如果终端设备内没有部署AI模型，无线接入网设备可以向终端设备发送AI模型的实例，然后终端设备基于该AI模型的实例进行CSI压缩，并向无线接入网设备发送压缩后的CSI，实现了终端设备与无线接入网设备之间基于协作等级1进行CSI的压缩。示例性地，根据第2组AI能力信息，可以确定CSI预测和协作等级2存在对应关系，进一步的，也可以确定CSI预测和小于协作等级2的其它协作等级存在对应关系，比如可以确定CSI预测和协作等级0或协作等级1存在对应关系。可以理解的，作为又一种可能的实现方式，第一能力信息可以用于指示AI功能信息或AI子功能信息以及其对应的最高协作等级信息。
步骤202，终端设备向无线接入网设备发送第一能力信息。相应地，无线接入网设备接收该第一能力信息。
步骤203，无线接入网设备根据第一能力信息，确定至少一组AI能力信息分别对应的AI资源需求信息。
其中，AI资源需求信息用于指示激活终端设备的一组AI能力信息时所需要的终端设备的AI资源信息。这里的AI资源信息包括但不限于以下一项或多项：需要的计算能力信息、需要的存储能力信息、需要的电量信息、需要的处理时延信息、需要的AI模型信息或者需要的AI算法信息。
一种实现方法中，无线接入网设备也可以从其他无线接入网设备或核心网设备接收该终端设备的第一能力信息。该其他无线接入网设备可以与该无线接入网设备相邻的基站、CU或DU等，本申请实施例不做限定。该核心网设备可以是接入与移动性管理功能(access and mobility management function，AMF)网元或会话管理功能(session management function，SMF)网元等，本申请实施例不做限定。可以理解的，在该实现方式中，步骤201和步骤202为可选步骤。
上述方案，终端设备向无线接入网设备上报该终端设备支持的一组或多组AI能力信息，无线接入网设备确定该一组或多组AI能力信息分别对应的AI资源需求信息，进而能够根据AI资源需求信息决策如何为终端设备进行AI配置，使得终端设备能够合理、有效地使用AI功能，进而能够提升终端设备与无线接入网设备之间的协作效率。
下面介绍上述步骤203的不同实现方法。
实现方法一，第一能力信息还包括至少一组AI能力信息分别对应的AI资源需求信息。
该实现方法中，第一能力信息包括至少一组AI能力信息以及该至少一组AI能力信息分别对应的AI资源需求信息。因此，无线接入网设备根据第一能力信息，可以确定至少一组AI能力信息分别对应 的AI资源需求信息。
实现方法二，第一能力信息还包括至少一组AI能力信息分别对应的AI资源需求信息的索引信息。
该实现方法中，第一能力信息包括至少一组AI能力信息以及该至少一组AI能力信息分别对应的AI资源需求信息的索引信息。因此无线接入网设备根据第一能力信息，可以确定至少一组AI能力信息分别对应的AI资源需求信息的索引信息，进而根据至少一组AI能力信息分别对应的AI资源需求信息的索引信息，确定至少一组AI能力信息分别对应的AI资源需求信息。
作为一个示例，第一能力信息中的至少一组AI能力信息分别包括AI子功能和协作等级，第一能力信息中的AI资源需求信息的索引信息包括需要的计算能力的索引信息、需要的存储能力的索引信息和需要的AI模型的索引信息。其中，表1为AI能力信息与AI资源需求信息的索引信息之间的对应关系的一个示例。
表1
其中，AI资源需求信息的索引信息和AI资源需求信息(包括计算能力信息、存储能力信息、AI模型信息等等)之间的对应关系，可以是协议预定义的或者终端设备和无线接入网设备交互的。上述对应关系可以以表格、函数、序列等形式存储在无线接入网设备和/或终端设备中。以下以表格为例进行说明。表2为计算能力的索引信息与计算能力信息之间的对应关系的一个示例。表3为存储能力的索引信息与存储能力信息之间的对应关系的一个示例。表4为AI模型的索引信息与AI模型信息之间的对应关系的一个示例。该表2至表4示例了AI资源需求信息的索引信息与AI资源需求信息之间的对应关系。在实际应用中，也可以将表2至表4合成一张表，来定义AI资源需求信息的索引信息与AI资源需求信息之间的对应关系，本申请对此不限定。
表2
其中，flops指的是每秒所执行的浮点运算次数(floating-point operations per second)。
表3

表4
比如，当第一能力信息包括CSI压缩、协作等级1、需要的计算能力的索引信息1、需要的存储能力的索引信息1和需要的AI模型的索引信息1，根据上述表2～4，无线接入网设备可以确定(CSI压缩，协作等级1)的组合对应的AI资源需求信息包括：需要的计算能力信息为a1～a2、需要的存储能力信息为0～10M，需要的AI模型信息为AI模型1。
该实现方法二中，基于上述表2至表4的示例，终端设备和无线接入网设备均存储该表2至表4。终端设备确定需要上报的至少一组AI能力信息以及该至少一组AI能力信息分别对应的AI资源需求信息之后，再根据上述表2至表4确定至少一组AI能力信息分别对应的AI资源需求信息的索引信息，进而在第一能力信息中包含至少一组AI能力信息以及该至少一组AI能力信息分别对应的AI资源需求信息的索引信息。无线接入网设备收到第一能力信息之后，根据表2至表4，确定至少一组AI能力信息分别对应的AI资源需求信息。
实现方法三，无线接入网设备根据第一能力信息和预定义的对应关系，确定至少一个AI能力信息分别对应的AI资源需求信息，该预定义的对应关系包括至少一个AI能力信息与AI资源需求信息之间的对应关系。
具体地，无线接入网设备收到第一能力信息之后，通过查询预定义的对应关系，可以确定第一能力信息中的至少一个AI能力信息分别对应的AI资源需求信息。该对应关系可以是AI能力信息与AI资源需求信息之间的对应关系。示例性地，第一能力信息包括AI能力信息，无线接入网设备可以根据AI能力信息与AI资源需求信息之间的对应关系，确定该AI能力信息对应的AI资源需求信息。或者，该对应关系包括AI能力信息与AI资源需求信息的索引信息之间的对应关系，以及AI资源需求信息的索引信息与AI资源需求信息之间存在对应关系。示例性地，第一能力信息包括AI能力信息，无线接入网设备可以根据上述对应关系，确定该AI能力信息对应的AI资源需求信息的索引信息，进一步地，无线接入网设备根据AI资源需求信息的索引信息与AI资源需求信息之间的对应关系，确定该AI能力对应的资源需求信息。
其中，上述对应关系可以以表格、函数、序列等形式存储于无线接入网设备和/或终端设备中。示例性地，AI能力信息包括AI子功能和协作等级，AI资源需求信息包括需要的计算能力信息、需要的存储能力信息以及需要的AI模型信息。无线接入网设备接收终端设备的AI能力信息，通过查询上述表1所示的AI能力信息与AI资源需求信息的索引信息之间的对应关系，确定AI能力信息对应的AI资源需求信息的索引信息，进一步地，查询表2～4所示的AI资源需求信息的索引信息与AI资源需求信息之间的对应关系，能够确定AI能力信息对应的AI资源需求信息。比如，当第一能力信息包括CSI压缩、协作等级1，根据上述表1，无线接入网设备可以确定相应的AI资源需求信息的索引信息分别为：需要的计算能力的索引信息为1，需要的存储能力的索引信息为1，需要的AI模型的索引信息为1，进一步地，根据上述表2～4，无线接入网设备可以确定该AI功能信息对应的AI资源需求信息：需要的计算能力为a1～a2、需要的存储能力为0～10M，需要的AI模型为AI模型1。
该实现方法三中，基于上述表1至表4的示例，无线接入网设备存储该表1至表4。终端设备发送的第一能力信息包括至少一组AI能力信息。无线接入网设备收到第一能力信息之后，根据表1至表4， 确定至少一组AI能力信息分别对应的AI资源需求信息。
通过上述实现方法一至实现方法三中的任一种方法，无线接入网设备可以准确确定一组AI能力信息对应的AI资源需求信息，有助于实现为终端设备配置合适的AI配置。其中，上述实现方法一中，终端设备在第一能力信息中携带至少一组AI能力信息以及至少一组AI能力信息分别对应的AI资源需求信息，从而无线接入网设备根据第一能力信息即可快速确定至少一组AI能力信息分别对应的AI资源需求信息，可以减少无线接入网设备的开销。上述实现方法二中，终端设备在第一能力信息中携带至少一组AI能力信息以及至少一组AI能力信息分别对应的AI资源需求信息的索引信息，由于AI资源需求信息的索引信息占用的开销要少于AI资源需求信息，因此可以减少终端设备与无线接入网设备之间的信令开销，提升通信效率。上述实现方法三中，终端设备在第一能力信息中携带至少一组AI能力信息，由于终端设备不需要确定至少一组AI能力信息分别对应的AI资源需求信息或对应的AI资源需求信息的索引信息，因此可以减少终端设备的开销，并且由于不需要在第一能力信息中携带至少一组AI能力信息分别对应的AI资源需求信息或对应的AI资源需求信息的索引信息，因此可以减少终端设备与无线接入网设备之间的信令开销，提升通信效率。
一种可能的实现方法中，上述图2的实施例中还包括以下步骤204至步骤206中的一个或多个步骤。
步骤204，终端设备向无线接入网设备发送第二能力信息。相应地，无线接入网设备接收该第二能力信息。
第二能力信息用于指示终端设备能够提供的AI资源的信息。比如第二能力信息可以包括终端设备的最大计算能力信息、最大存储能力信息、最大电量信息、处理时延信息、终端设备支持的AI模型信息或者支持的AI算法信息中的至少一个。
步骤205，无线接入网设备根据第二能力信息和至少一组AI能力信息分别对应的AI资源需求信息，确定终端设备的第一AI配置信息。
一种实现方法中，无线接入网设备也可以从其他无线接入网设备或核心网设备接收该终端设备的第二能力信息。该其他无线接入网设备可以与该无线接入网设备相邻的基站、CU或DU等，本申请实施例不做限定。该核心网设备可以是AMF网元或SMF网元等，本申请实施例不做限定。可以理解的，本实现方式中，步骤204可以不被执行。
无线接入网设备根据第二能力信息和至少一组AI能力信息分别对应的AI资源需求信息，从该至少一组AI能力信息中选择一组或多组AI能力信息。该一组或多组AI能力信息分别对应的AI资源需求信息均能够被第二能力信息所满足，或者理解为该一组或多组AI能力信息分别对应的AI资源均没有超出第二能力信息指示的AI资源。然后，无线接入网设备根据该一组或多组AI能力信息，确定第一AI配置信息，因此该第一AI配置信息对应该一组或多组AI能力信息。
下面结合具体示例说明。假设第一能力信息包括前述的6组AI能力信息，且假设第1、3～5组AI能力信息对应的AI资源需求能够被第二能力信息指示的AI资源所满足，而第2、6组AI能力信息对应的AI资源需求不能被第二能力信息指示的AI资源所满足，因此该第1、3～5组AI能力信息可以作为候选的AI能力信息。
然后无线接入网设备根据从第1、3～5组AI能力信息中选择的一组或多组AI能力信息，生成第一AI配置信息。比如，无线接入网设备选择第1、4组AI能力信息生成第一AI配置信息。本申请实施例对无线接入网设备从多组AI能力信息中选择一组或多组AI能力信息的具体实现方法不做限定，比如可以是随机选择一组AI能力信息，或者是基于历史选择，选择与上一次选择的AI能力信息相同或不同的AI能力信息，或者对多组AI能力信息全部选择等等。
一种实现方法中，第一AI配置信息由第1、4组AI能力信息组成。基于该方案，则第一AI配置信息包括：{CSI压缩、协作等级1}和{波束扫描矩阵预测、协作等级2}。其中，CSI压缩以及协作等级1构成一个配置，波束扫描矩阵预测以及协作等级2构成另一个配置。
又一种实现方法中，第一AI配置信息是根据第1、4组AI能力信息生成的，但与第1、4组AI能力信息不完全相同。例如，第一AI配置信息包括：{CSI压缩、协作等级1、模型1}和{波束扫描矩阵预测、协作等级1、模型1}。其中，CSI压缩、协作等级1以及模型1构成一个配置，波束扫描矩阵预测、协作等级1以及模型1构成另一个配置。其中，终端设备上报的第一能力信息中的第1组AI能力信息没有包含模型信息，表明该第1组AI能力信息支持任意模型，因此无线接入网设备根据该第1组AI能力信息生成第一AI配置信息时，选择了模型1与该第1组AI能力信息进行组合。其中，这里仅 以选择模型1作为示例，实际应用中，对于选择模型的方法不做限定，比如可以是随机选择，或者是选择开销最小的模型等等。类似的，无线接入网设备根据该第4组AI能力信息生成第一AI配置信息时，选择了模型1与该第4组AI能力信息进行组合。其中，终端设备上报的第一能力信息中第4组AI能力信息中的协作等级为2，可以理解为终端设备支持波束扫描矩阵预测和任一小于和/或等于协作等级2的协作等级的AI能力信息。
需要说明的是，无线接入网设备也支持该第一AI配置信息。具体的，无线接入网设备支持第一AI配置信息中的AI功能、AI子功能、协作等级、AI模型、或AI算法等。
步骤206，无线接入网设备向终端设备发送第一AI配置信息。相应地，终端设备接收该第一AI配置信息。
终端设备收到第一AI配置信息后，根据该第一AI配置信息执行相应的AI功能或AI子功能。
上述方法，由于第一AI配置信息是根据终端设备支持的至少一组AI能力信息生成的，因此终端设备支持该第一AI配置信息，有助于实现为终端设备执行正确的AI配置。并且，同一组内的多个AI能力信息之间存在对应关系，从而无线接入网设备在生成AI配置信息时，根据同一组内的AI能力信息进行组合配置，避免生成终端设备不支持的AI配置，有助于减少错误配置的发生。
其中，上述步骤204与上述步骤202可以在同一个步骤实现，也可以分为两个不同步骤实现，本申请对此不限定。
图3为本申请实施例提供的一种无线通信方法的流程示意图。该方法包括以下步骤：
步骤301，终端设备根据第二能力信息，确定第一能力信息，第一能力信息包括在第二能力信息指示的AI资源的范围内终端设备支持的一组AI能力信息或者至少两组AI能力信息的组合信息。在一个实施方式中，第二能力信息用于指示终端设备支持的AI资源的最大值。示例性的。第二能力信息包括索引值，该索引值可映射到该终端设备支持的AI资源的最大值；或者，第二能力信息包括该终端设备支持的AI资源的最大值的具体取值。
该第二能力信息与图2的实施例中的第二能力信息的含义相同，可以参考前述描述。
该第一能力信息与图2的实施例中的第一能力信息的含义不同。具体的，在图2的实施例，第一能力信息对应的AI资源或AI资源之和有可能会超出第二能力信息指示的终端设备能够提供的AI资源的范围；在图2的实施例中，无线接入网设备根据第二能力信息确定第一AI配置，且使得第一AI配置需要的AI资源或AI资源之和不超出第二能力信息指示的AI资源的范围。而在图3的实施例中，第一能力信息包括在第二能力信息指示的AI资源的范围内终端设备支持的一组AI能力信息或者至少两组AI能力信息的组合信息，因此第一能力信息对应的AI资源不会超出第二能力信息指示的终端设备能够提供的AI资源的范围。可以理解为，终端设备根据第二能力信息确定第一能力信息，且使得第一能力信息指示的AI能力信息或AI能力信息组合需要的AI资源或AI资源之和不超出第二能力信息指示的AI资源的范围。
示例性地，终端设备支持6组AI能力信息，分别如下：
第1组AI能力信息：CSI压缩、协作等级1。
第2组AI能力信息：CSI预测、协作等级2。
第3组AI能力信息：CSI-RS配置信令减少、协作等级2。
第4组AI能力信息：波束扫描矩阵预测、协作等级2。
第5组AI能力信息：最优波束预测、协作等级1。
第6组AI能力信息：基于终端设备的定位增强、协作等级1。
以终端设备支持的AI资源包括能够提供的存储能力，且能够提供的最大存储能力为100M为例，即第二能力信息指示的终端设备能够提供的最大存储能力为100M。
比如上述第1组AI能力信息对应的AI资源包括：需要的存储能力为30M，上述第2组AI能力信息对应的AI资源包括：需要的存储能力为40M，上述第3组AI能力信息对应的AI资源包括：需要的存储能力为50M，上述第4组AI能力信息对应的AI资源包括：需要的存储能力为100M，上述第5组AI能力信息对应的AI资源包括：需要的存储能力为70M，上述第6组AI能力信息对应的AI资源包括：需要的存储能力为50M。终端设备根据终端设备的存储能力为100M，以及上述各组AI能力信息需要的存储能力信息，确定支持的第一能力信息包括{第1组AI能力信息(30M)；第2组AI能力信息(40M)}、{第1组AI能力信息(30M)；第3组AI能力信息(50M)}、{第1组AI能力信息(30M)； 第5组AI能力信息(70M)}、{第1组AI能力信息(30M)；第6组AI能力信息(50M)}、{第2组AI能力信息(40M)；第3组AI能力信息(50M)}、{第2组AI能力信息(30M)；第6组AI能力信息(50M)}、{第3组AI能力信息(50M)；第6组AI能力信息(50M)}、{第4组AI能力信息(100M)}中的至少一个。可以看出，上述第一能力信息中的一组AI能力信息或多组AI能力信息的组合对应的AI资源均在第二能力信息指示的终端设备能够提供的AI资源的范围内，即一组AI能力信息或多组AI能力信息的组合需要的存储能力的总和均小于或等于100M。
可以理解的是，若第二能力信息指示的AI资源有多种，则针对每种AI资源，终端设备确定的第一能力信息中一组AI能力信息或多组AI能力信息的组合对应的该种AI资源信息的总和，小于或等于第二能力信息指示的终端设备能够提供的该种AI资源。
步骤302，终端设备向无线接入网设备发送第一能力信息。相应地，无线接入网设备接收该第一能力信息。
步骤303，无线接入网设备根据第一能力信息，确定第一AI配置信息。
一种实现方法，无线接入网设备从第一能力信息中选择一组AI能力信息或多组AI能力信息的组合，构成第一AI配置信息，该第一AI配置信息与选择的一组AI能力信息相同，或者与选择的多组AI能力信息的组合相同，或者与选择的多组AI能力信息的组合中的一组或多组AI能力信息相同。结合前述步骤301中的示例，无线接入网设备可以选择{第1组AI能力信息(30M)；第2组AI能力信息(40M)}中的一组或两组AI能力信息构成第一AI配置信息，或者选择{第1组AI能力信息(30M)；第3组AI能力信息(50M)}中的一组或两组AI能力信息构成第一AI配置信息，或者选择{第1组AI能力信息(30M)；第5组AI能力信息(70M)}中的一组或两组AI能力信息作为第一AI配置信息，或者选择{第1组AI能力信息(30M)；第6组AI能力信息(50M)}中的一组或两组AI能力信息构成第一AI配置信息，或者选择{第2组AI能力信息(40M)；第3组AI能力信息(50M)}中的一组或两组AI能力信息构成第一AI配置信息，或者选择{第2组AI能力信息(30M)；第6组AI能力信息(50M)}中的一组或两组AI能力信息构成第一AI配置信息，或者选择{第3组AI能力信息(50M)；第6组AI能力信息(50M)}中的一组或两组AI能力信息构成第一AI配置信息，或者选择{第4组AI能力信息(100M)}构成第一AI配置信息。
又一种实现方法，无线接入网设备从第一能力信息中选择一组AI能力信息或多组AI能力信息的组合，并基于选择的一组AI能力信息或多组AI能力信息的组合，生成第一AI配置信息，该第一AI配置信息与选择的AI能力信息不完全相同，具体的，可以由该选择的AI能力信息以及与该AI能力信息对应的其它信息构成第一AI配置信息。以前述步骤301中的示例为例，比如无线接入网设备选择的从第一能力信息中选择了{第1组AI能力信息(30M)；第2组AI能力信息(40M)}，无线接入网设备确定的第一AI配置信息包括{CSI压缩、协作等级1、AI模型1}和{CSI预测、协作等级2、AI模型2}，可以看出，第一AI配置信息中除了包含第1组AI能力信息和第2组AI能力信息，还包括第1组AI能力信息对应的AI模型1，以及包括第2组AI能力信息对应的AI模型2。其中，这里为第1组AI能力信息选择模型1，为第2组AI能力信息选择模型2仅是作为示例，实际应用中，对于选择模型的方法不做限定，比如可以是随机选择，或者是选择开销最小的模型等等。
需要说明的是，无线接入网设备也支持该第一AI配置信息。具体的，无线接入网设备支持第一AI配置信息中AI功能、AI子功能、协作等级、AI模型、AI算法等。
一种实现方法中，无线接入网设备除了可以从终端设备接收该终端设备的第一能力信息，也可以从其他无线接入网设备或核心网设备接收该终端设备的第一能力信息。这里的核心网设备可以是AMF网元或SMF网元等。可以理解的，本实现方式中，步骤301和步骤302可以不被执行。
步骤304，无线接入网设备向终端设备发送第一AI配置信息。相应地，终端设备接收该第一AI配置信息。
终端设备收到第一AI配置信息后，根据该第一AI配置信息执行相应的AI功能、AI子功能。
上述方法，由于第一AI配置信息是根据终端设备支持的AI能力信息生成的，因此终端设备支持该第一AI配置信息，有助于实现为终端设备执行正确的AI配置。并且，同一组内的多个AI能力信息之间存在对应关系，从而无线接入网设备在生成第一AI配置信息时，根据同一组内的AI能力信息进行组合配置，避免生成终端设备不支持的AI配置，有助于减少错误配置的发生。
图4为本申请实施例提供的又一种无线通信方法的流程示意图。该方法用于实现向终端设备发送更 新的AI配置信息。该方法可以与上述图2或图3的实施例相结合实施，也可以单独实施。该方法包括以下步骤：
步骤401，无线接入网设备向终端设备发送第一指示信息。
该第一指示信息指示上报通知信息的触发配置信息，该第一指示信息包括第一门限和/或第二门限。其中，第一门限和/或第二门限的值可以是协议预定义的。
该步骤401为可选步骤。若不执行步骤401，终端设备可以被预配置该第一门限和第二门限。
步骤402，终端设备确定满足第一指示信息对应的触发条件，向无线接入网设备发送通知信息。
该通知信息包括终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项。其中，终端设备占用的AI资源的信息包括但不限于以下一项或多项：占用的计算资源、占用的存储资源、已经使用的电量。终端设备剩余的AI资源的信息包括但不限于以下一项或多项：剩余的计算资源、剩余的存储资源、剩余的电量。期望的AI配置信息包括但不限于以下一项或多项：AI功能、AI子功能、协作等级、AI模型或AI算法中的一个或多个。
一种实现方法中，该触发条件包括：终端设备占用的AI资源的信息大于或等于第一门限，和/或，终端设备剩余的AI资源的信息小于或等于第二门限。比如，当终端设备占用的AI资源的信息包括占用的计算资源和占用的存储资源，则第一门限包括占用的计算资源的门限值和占用的存储资源的门限值。比如，若终端设备剩余的AI资源的信息包括剩余的计算资源和剩余的存储资源，则第二门限包括剩余的计算资源的门限值和剩余的存储资源的门限值。
步骤403，无线接入网设备根据通知信息和第一能力信息，确定第二AI配置信息。
该第二AI配置信息可以理解为是更新的AI配置信息。
一种实现方法中，无线接入网设备中存储历史的AI配置信息，该历史的AI配置信息可以是最近一次为该终端设备配置的AI配置信息。无线接入网设备需要更新AI配置信息时，可以基于该历史的AI配置信息、通知信息和第一能力信息，确定第二AI配置信息。
其中，若通知信息中包含期望的AI配置信息，无线接入网设备优先考虑根据该期望的AI配置信息为终端设备生成更新的AI配置信息，即第二AI配置信息。
一种实现方法中，当该图4的实施例与上述图2或图3的实施例相结合实施，则该第二AI配置信息可以对应上述第一能力信息中的一组或多组AI能力信息，也即该第二AI配置信息是根据第一能力信息中的一组或多个AI能力信息生成的。基于该方法，可以理解为该第二AI配置信息是对图2或图3的实施例中的第一AI配置信息的更新。
步骤404，无线接入网设备向终端设备发送第二AI配置信息。
上述方案，可以实现为终端设备更新AI配置信息，以使得终端设备根据更新的AI配置信息更加合理、有效地使用AI功能，从而满足终端设备与无线接入网设备之间的通信需求和提升终端设备与无线接入网设备之间的协作效率。
一种实现方法中，无线接入网设备在为终端设备配置AI配置信息之后，如果终端设备不需要使用已经配置的AI配置信息，无线接入网设备可以去激活终端设备上已经配置的AI配置信息。下面介绍一种触发去激活终端设备的AI配置信息的实现方法。比如，终端设备确定需要去激活AI配置信息时，向无线接入网设备发送第二指示信息，该第二指示信息指示去激活终端设备的AI配置信息，无线接入网设备可以根据第二指示信息去激活终端设备的AI配置信息。或者，第二指示信息可以用于指示终端设备期望去激活AI功能，无线接入网设备可以去激活终端设备上对应的AI功能。该去激活终端设备上的AI配置信息的方法可以独立实施，也可以与上述图2、图3或图4的实施例相结合实施例，本申请不做限定。
一种可能的实现方法中，当无线接入网设备包括CU和DU，CU负责与终端设备之间交互无线资源控制(radio resource connection，RRC)消息，DU负责对收到的来自终端设备的信息进行处理，以及还可以生成信息并通过CU将生成的信息发送给终端设备。
示例性地，当无线接入网设备包括CU和DU，图2的实施例可以按照图5的实施例进行实施。具体的，图2中的步骤202对应图5中的步骤202a和步骤202b，图2中的步骤204对应图5中的步骤204a和步骤204b，图2中的步骤206对应图5中的步骤206a和步骤206b，以及图2中的步骤203、205由图5中的DU执行。
示例性地，当无线接入网设备包括CU和DU，图3的实施例可以按照图6的实施例进行实施。具 体的，图3中的步骤302对应图6中的步骤302a和步骤302b，图3中的步骤304对应图6中的步骤304a和步骤304b，以及图3中的步骤303由图6中的DU执行。
示例性地，当无线接入网设备包括CU和DU，图4的实施例可以按照图7的实施例进行实施。具体的，图4中的步骤401对应图7中的步骤401a和步骤401b，图4中的步骤402对应图7中的步骤402a和步骤402b，图4中的步骤404对应图7中的步骤404a和步骤404b，以及图4中的步骤403由图7中的DU执行。
又一种可能的实现方式中，无线接入网设备(CU或DU)中可以进一步拆分为具有AI决策功能的第一网元，和具有AI实现功能的第二网元。其中，第一网元可以称为AI控制器，或者近实时无线接入网智能控制器。第二网元用于管理其和其它接入网设备或终端设备之间的信息的发送或接收，并转发相关信息给第一网元。第一网元可以基于上述信息进行决策，并发送确定的配置信息给第二网元，用于第二网元根据该配置信息执行后续操作。比如向其他接入网设备或终端设备发送上述配置信息。
示例性地，当无线接入网设备包括上述第一网元和第二网元时，上述实施例中无线接入网设备接收第一能力信息，或者接收第一能力信息和第二能力信息，以及确定至少一组AI能力信息分别对应的AI资源需求信息，或者确定第一AI配置信息的操作，可以包括：
第二网元接收第一能力信息，或者接收第一能力信息和第二能力信息；
第二网元向第一网元发送接收的第一能力信息，或者接收第一能力信息和第二能力信息的部分或全部信息；
第一网元根据接收的第一能力信息，或者接收第一能力信息和第二能力信息的部分或全部信息，确定至少一组AI能力信息分别对应的AI资源需求信息，或者确定第一AI配置信息；
第一网元向第二网元发送上述至少一组AI能力信息分别对应的AI资源需求信息，或者确定第一AI配置信息。
可以理解的，本申请实施例中，终端设备和/或无线接入网设备可以执行本申请实施例中的部分或全部步骤，这些步骤或操作仅是示例，本申请实施例还可以执行其它操作或者各种操作的变形。此外，各个步骤可以按照本申请实施例呈现的不同的顺序来执行，并且有可能并非要执行本申请实施例中的全部操作。
可以理解的是，为了实现上述实施例中功能，无线接入网设备和终端设备包括了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本申请中所公开的实施例描述的各示例的单元及方法步骤，本申请能够以硬件或硬件和计算机软件相结合的形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用场景和设计约束条件。
图8和图9为本申请的实施例提供的可能的通信装置的结构示意图。这些通信装置可以用于实现上述方法实施例中终端设备或无线接入网设备的功能，因此也能实现上述方法实施例所具备的有益效果。在本申请的实施例中，该通信装置可以是图1所示的终端设备，也可以是图1所示的无线接入网设备，还可以是应用于终端设备或无线接入网设备的模块(如芯片)。
图8所示的通信装置800包括处理单元810和收发单元820。通信装置800用于实现上述方法实施例中终端设备或无线接入网设备的功能。
当通信装置800用于实现上述图2、图4、图5、图7的实施例中无线接入网设备或DU的功能，收发单元820，用于接收终端设备的第一能力信息，该第一能力信息包括该终端设备支持的至少一组该AI能力信息；处理单元810，用于根据该第一能力信息，确定该至少一组AI能力信息分别对应的AI资源需求信息。
一种可能的实现方法中，处理单元810，具体用于根据该第一能力信息和预定义的对应关系，确定该至少一个AI能力信息分别对应的AI资源需求信息，该预定义的对应关系包括该至少一个AI能力信息与该AI资源需求信息之间的对应关系。
一种可能的实现方法中，收发单元820，还用于接收该终端设备的第二能力信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；处理单元810，还用于根据该第二能力信息和该至少一组AI能力信息分别对应的AI资源需求信息，确定第一AI配置信息，该第一AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息；该无线接入网设备向该终端设备发送该第一AI配置信息。
一种可能的实现方法中，收发单元820，还用于接收来自该终端设备的通知信息，该通知信息包括 该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项。
一种可能的实现方法中，处理单元810，还用于根据该通知信息和该第一能力信息，确定第二AI配置信息，该第二AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息；收发单元820，还用于向该终端设备发送该第二AI配置信息。
一种可能的实现方法中，收发单元820，还用于向该终端设备发送第一指示信息，该第一指示信息指示上报该通知信息的触发条件。
一种可能的实现方法中，收发单元820，还用于接收来自该终端设备的第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息；该无线接入网设备根据该第二指示信息，去激活该终端设备的AI配置信息。
一种可能的实现方法中，收发单元820，具体用于从其他无线接入网设备、该终端设备或核心网设备接收该第一能力信息。
一种可能的实现方法中，收发单元820，具体用于从其他无线接入网设备、该终端设备或核心网设备接收该第二能力信息。
当通信装置800用于实现上述图2、图4、图5、图7的实施例中终端设备的功能，处理单元810，用于确定第一能力信息，该第一能力信息包括该终端设备支持的至少一组该AI能力信息；收发单元820，用于向无线接入网设备发送该第一能力信息。
一种可能的实现方法中，收发单元820，还用于向该无线接入网设备发送第二能力信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；接收来自该无线接入网设备的第一AI配置信息，该第一AI配置信息是根据该第二能力信息和该至少一组AI能力信息分别对应的AI资源需求信息确定的，该第一AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息。
一种可能的实现方法中，收发单元820，还用于当处理单元810确定满足触发条件，则向该无线接入网设备发送通知信息，该通知信息包括该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项；其中，该触发条件包括：该终端设备占用的AI资源的信息大于第一门限，和/或，该终端设备剩余的AI资源的信息小于第二门限。
一种可能的实现方法中，收发单元820，还用于接收来自该无线接入网设备的第二AI配置信息，该第二AI配置信息是根据该通知信息和该第一能力信息确定的，该第二AI配置信息对应该至少一组AI能力信息中的一组或多组AI能力信息。
一种可能的实现方法中，收发单元820，还用于接收来自该无线接入网设备的第一指示信息，该第一指示信息指示上报该通知信息的该触发条件，该第一指示信息包括该第一门限和/或该第二门限。
一种可能的实现方法中，收发单元820，还用于向该无线接入网设备发送第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息。
当通信装置800用于实现上述图3、图4、图6、图7的实施例中无线接入网设备或DU的功能，收发单元820，用于接收终端设备的第一能力信息，该第一能力信息包括在第二能力信息指示的AI资源的范围内该终端设备支持的一组该AI能力信息或者至少两组AI能力信息的组合信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；处理单元810，用于根据该第一能力信息，确定第一AI配置信息，该第一AI配置信息对应该一组AI能力信息或该至少两组AI能力信息的组合信息中的一组或多组AI能力信息；收发单元820，还用于向该终端设备发送该第一AI配置信息。
一种可能的实现方法中，收发单元820，还用于接收来自该终端设备的通知信息，该通知信息包括该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项。
一种可能的实现方法中，处理单元810，还用于根据该通知信息和该第一能力信息，确定第二AI配置信息，该第二AI配置信息对应该一组AI能力信息或该至少两组AI能力信息的组合信息中的一组或多组AI能力信息；收发单元820，还用于向该终端设备发送该第二AI配置信息。
一种可能的实现方法中，收发单元820，还用于向该终端设备发送第一指示信息，该第一指示信息指示上报该通知信息的触发条件。
一种可能的实现方法中，收发单元820，还用于接收来自该终端设备的第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息；处理单元810，还用于根据该第二指示信息，去激活该终端设备的AI配置信息。
一种可能的实现方法中，收发单元820，具体用于从其他无线接入网设备、该终端设备或核心网设 备接收该第一能力信息。
当通信装置800用于实现上述图3、图4、图6、图7的实施例中终端设备的功能，处理单元810，用于根据第二能力信息，确定第一能力信息，该第一能力信息包括在第二能力信息指示的AI资源的范围内该终端设备支持的一组AI能力信息或者至少两组AI能力信息的组合信息，该第二能力信息用于指示该终端设备能够提供的AI资源的信息；收发单元820，用于向无线接入网设备发送该第一能力信息。
一种可能的实现方法中，收发单元820，还用于当处理单元810确定满足触发条件，则向该无线接入网设备发送通知信息，该通知信息包括该终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项；其中，该触发条件包括：该终端设备占用的AI资源的信息大于第一门限，和/或，该终端设备剩余的AI资源的信息小于第二门限。
一种可能的实现方法中，收发单元820，还用于接收来自该无线接入网设备的第二AI配置信息，该第二AI配置信息是根据该通知信息和该第一能力信息确定的，该第二AI配置信息对应该一组AI能力信息或者至少两组AI能力信息的组合信息中的一组或多组AI能力信息。
一种可能的实现方法中，收发单元820，还用于接收来自该无线接入网设备的第一指示信息，该第一指示信息指示上报该通知信息的该触发条件，该第一指示信息包括该第一门限和/或该第二门限。
一种可能的实现方法中，收发单元820，还用于向该无线接入网设备发送第二指示信息，该第二指示信息指示去激活该终端设备的AI配置信息。
有关上述处理单元810和收发单元820更详细的描述，可以直接参考上述方法实施例中相关描述直接得到，这里不加赘述。
图9所示的通信装置900包括处理器910和接口电路920。处理器910和接口电路920之间相互耦合。可以理解的是，接口电路920可以为收发器或输入输出接口。可选的，通信装置900还可以包括存储器930，用于存储处理器910执行的指令或存储处理器910运行指令所需要的输入数据或存储处理器910运行指令后产生的数据。
当通信装置900用于实现上述方法实施例时，处理器910用于实现上述处理单元810的功能，接口电路920用于实现上述收发单元820的功能。
当上述通信装置为应用于终端设备的芯片，该终端设备的芯片实现上述方法实施例中终端设备的功能。该终端设备的芯片从终端设备中的其它模块(如射频模块或天线)接收信息，该信息是无线接入网设备发送给终端设备的；或者，该终端设备的芯片向终端设备中的其它模块(如射频模块或天线)发送信息，该信息是终端设备发送给无线接入网设备的。
当上述通信装置为应用于无线接入网设备的模块，该无线接入网设备的模块实现上述方法实施例中无线接入网设备的功能。该无线接入网设备的模块从无线接入网设备中的其它模块(如射频模块或天线)接收信息，该信息是终端设备发送给无线接入网设备的；或者，该无线接入网设备的模块向无线接入网设备中的其它模块(如射频模块或天线)发送信息，该信息是无线接入网设备发送给终端设备的。这里的无线接入网设备的模块可以是无线接入网设备的基带芯片，也可以是DU或其他模块，这里的DU可以是开放式无线接入网(open radio access network，O-RAN)架构下的DU。
在一个实施方式中，本申请提供一种通信系统，包括无线接入网设备以及终端设备，其中，无线接入网设备可以实现上述图2、图4、图5、图7的实施例中无线接入网设备或DU的功能，终端设备可以实现上述图2、图4、图5、图7的实施例中终端设备的功能。
在一个实施方式中，本申请提供一种包括CU以及DU的基站，其中，DU可以实现上述图2、图4、图5、图7的实施例中DU的功能。
可以理解的是，本申请的实施例中的处理器可以是中央处理单元(Central Processing Unit，CPU)，还可以是其它通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其它可编程逻辑器件、晶体管逻辑器件，硬件部件或者其任意组合。通用处理器可以是微处理器，也可以是任何常规的处理器。
本申请的实施例中的方法步骤可以通过硬件的方式来实现，也可以由处理器执行软件指令的方式来实现。软件指令可以由相应的软件模块组成，软件模块可以被存放于随机存取存储器、闪存、只读存储器、可编程只读存储器、可擦除可编程只读存储器、电可擦除可编程只读存储器、寄存器、硬盘、移动 硬盘、致密光盘只读存储器(compact disc read-only memory，CD-ROM)或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于无线接入网设备或终端设备中。当然，处理器和存储介质也可以作为分立组件存在于无线接入网设备或终端设备中。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序或指令。计算机程序(Computer Program)是指一组指示电子计算机或其他具有消息处理能力设备每一步动作的指令，通常用某种程序设计语言编写，运行于某种目标体系结构上。在计算机上加载和执行所述计算机程序或指令时，全部或部分地执行本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、无线接入网设备、终端设备或者其它可编程装置。所述计算机程序或指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机程序或指令可以从一个网站站点、计算机、服务器或数据中心通过有线或无线方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是集成一个或多个可用介质的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，例如，软盘、硬盘、磁带；也可以是光介质，例如，数字视频光盘；还可以是半导体介质，例如，固态硬盘。该计算机可读存储介质可以是易失性或非易失性存储介质，或可包括易失性和非易失性两种类型的存储介质。
本申请中所述的协议可以是指通信协议或者说规范，例如3GPP通信协议。
在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，不同的实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
可以理解的，本申请实施例中，终端设备和/或无线接入网设备可以执行本申请实施例中的部分或全部步骤，这些步骤或操作仅是示例，本申请实施例中，还可以执行其它操作或者各种操作的变形。此外，各个步骤可以按照本申请实施例呈现的不同的顺序来执行，并且有可能并非要执行本申请实施例中的全部操作。
本申请中，“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。在本申请的文字描述中，字符“/”，一般表示前后关联对象是一种“或”的关系；在本申请的公式中，字符“/”，表示前后关联对象是一种“相除”的关系。
可以理解的是，在本申请的实施例中涉及的各种数字编号仅为描述方便进行的区分，并不用来限制本申请的实施例的范围。上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定。

Claims (25)

  1. 一种无线通信方法，其特征在于，所述方法应用于无线接入网设备，包括：
    接收终端设备的第一能力信息，所述第一能力信息包括所述终端设备支持的至少一组人工智能AI能力信息；
    根据所述第一能力信息，确定所述至少一组AI能力信息分别对应的AI资源需求信息。
  2. 如权利要求1所述的方法，其特征在于，每组AI能力信息包括所述终端设备支持的AI功能、AI子功能、协作等级、AI模型或AI算法中的至少一个。
  3. 如权利要求1或2所述的方法，其特征在于，每组AI能力信息包括至少两个AI能力信息，所述至少两个AI能力信息之间存在对应关系。
  4. 如权利要求1至3中任一项所述的方法，其特征在于，所述第一能力信息还包括：
    所述至少一组AI能力信息分别对应的AI资源需求信息，或者，
    所述至少一组AI能力信息分别对应的AI资源需求信息的索引信息。
  5. 如权利要求1至3中任一项所述的方法，其特征在于，所述根据所述第一能力信息，确定所述至少一组AI能力信息分别对应的AI资源需求信息，包括：
    根据所述第一能力信息和预定义的对应关系，确定所述至少一个AI能力信息分别对应的AI资源需求信息，所述预定义的对应关系包括所述至少一个AI能力信息与所述AI资源需求信息之间的对应关系。
  6. 如权利要求1至5中任一项所述的方法，其特征在于，所述方法还包括：
    接收所述终端设备的第二能力信息，所述第二能力信息用于指示所述终端设备能够提供的AI资源的信息；
    根据所述第二能力信息和所述至少一组AI能力信息分别对应的AI资源需求信息，确定第一AI配置信息，所述第一AI配置信息对应所述至少一组AI能力信息中的一组或多组AI能力信息；
    向所述终端设备发送所述第一AI配置信息。
  7. 如权利要求6所述的方法，其特征在于，所述终端设备能够提供的AI资源的信息包括所述终端设备的最大计算能力信息、最大存储能力信息、最大电量信息、处理时延信息、所述终端设备支持的AI模型信息或者支持的AI算法信息中的至少一个。
  8. 如权利要求1至7中任一项所述的方法，其特征在于，所述方法还包括：
    接收来自所述终端设备的通知信息，所述通知信息包括所述终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项。
  9. 如权利要求8所述的方法，其特征在于，所述方法还包括：
    根据所述通知信息和所述第一能力信息，确定第二AI配置信息，所述第二AI配置信息对应所述至少一组AI能力信息中的一组或多组AI能力信息；
    向所述终端设备发送所述第二AI配置信息。
  10. 如权利要求8或9所述的方法，其特征在于，所述方法还包括：
    向所述终端设备发送第一指示信息，所述第一指示信息指示上报所述通知信息的触发条件。
  11. 如权利要求1至7中任一项所述的方法，其特征在于，所述方法还包括：
    接收来自所述终端设备的第二指示信息，所述第二指示信息指示去激活所述终端设备的AI配置信息；
    根据所述第二指示信息，去激活所述终端设备的AI配置信息。
  12. 如权利要求1至11中任一项所述的方法，其特征在于，所述接收终端设备的第一能力信息，包括：
    从其他无线接入网设备、所述终端设备或核心网设备接收所述第一能力信息。
  13. 一种无线通信方法，其特征在于，所述方法应用于终端设备，包括：
    确定第一能力信息，所述第一能力信息包括所述终端设备支持的至少一组人工智能AI能力信息；
    向无线接入网设备发送所述第一能力信息。
  14. 如权利要求13所述的方法，其特征在于，每组AI能力信息包括所述终端设备支持的AI功能、AI子功能、协作等级、AI模型或AI算法中的至少一个。
  15. 如权利要求13或14所述的方法，其特征在于，每组AI能力信息包括至少两个AI能力信息，所述至少两个AI能力信息之间存在对应关系。
  16. 如权利要求13至15中任一项所述的方法，其特征在于，所述第一能力信息还包括：
    所述至少一组AI能力信息分别对应的AI资源需求信息，或者，
    所述至少一组AI能力信息分别对应的AI资源需求信息的索引信息。
  17. 如权利要求13至16中任一项所述的方法，其特征在于，所述方法还包括：
    向所述无线接入网设备发送第二能力信息，所述第二能力信息用于指示所述终端设备能够提供的AI资源的信息；
    接收来自所述无线接入网设备的第一AI配置信息，所述第一AI配置信息是根据所述第二能力信息和所述至少一组AI能力信息分别对应的AI资源需求信息确定的，所述第一AI配置信息对应所述至少一组AI能力信息中的一组或多组AI能力信息。
  18. 如权利要求17所述的方法，其特征在于，所述终端设备能够提供的AI资源的信息包括所述终端设备的最大计算能力信息、最大存储能力信息、最大电量信息、处理时延信息、支持的AI模型信息或者支持的AI算法信息中的至少一个。
  19. 如权利要求13至18中任一项所述的方法，其特征在于，所述方法还包括：
    确定满足触发条件，向所述无线接入网设备发送通知信息，所述通知信息包括所述终端设备占用的AI资源的信息、剩余的AI资源的信息、期望的AI配置信息中的至少一项；
    其中，所述触发条件包括：所述终端设备占用的AI资源的信息大于第一门限，和/或，所述终端设备剩余的AI资源的信息小于第二门限。
  20. 如权利要求19所述的方法，其特征在于，所述方法还包括：
    接收来自所述无线接入网设备的第二AI配置信息，所述第二AI配置信息是根据所述通知信息和所述第一能力信息确定的，所述第二AI配置信息对应所述至少一组AI能力信息中的一组或多组AI能力信息。
  21. 如权利要求19或20所述的方法，其特征在于，所述方法还包括：
    接收来自所述无线接入网设备的第一指示信息，所述第一指示信息指示上报所述通知信息的所述触发条件，所述第一指示信息包括所述第一门限和/或所述第二门限。
  22. 如权利要求13至18中任一项所述的方法，其特征在于，所述方法还包括：
    向所述无线接入网设备发送第二指示信息，所述第二指示信息指示去激活所述终端设备的AI配置信息。
  23. 一种通信装置，其特征在于，包括处理器和接口电路，所述接口电路用于接收来自所述通信装置之外的其它通信装置的信号并传输至所述处理器或将来自所述处理器的信号发送给所述通信装置之外的其它通信装置，所述处理器通过逻辑电路或执行代码指令用于实现如权利要求1至12中任一项所述的方法，或用于实现如权利要求13至22中任一项所述的方法。
  24. 一种计算机可读存储介质，其特征在于，所述存储介质中存储有计算机程序或指令，当所述计算机程序或指令被通信装置执行时，实现如权利要求1至12中任一项所述的方法，或实现如权利要求13至22中任一项所述的方法。
  25. 一种计算机程序产品，其特征在于，所述计算机程序产品包括计算机程序或指令，当计算机程序或指令被通信装置运行时，使得权利要求1至12中任一项所述方法，或权利要求13至22中任一项所述方法被执行。
PCT/CN2023/113109 2022-08-29 2023-08-15 一种无线通信方法及通信装置 WO2024046113A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211039259.8A CN117692892A (zh) 2022-08-29 2022-08-29 一种无线通信方法及通信装置
CN202211039259.8 2022-08-29

Publications (1)

Publication Number Publication Date
WO2024046113A1 true WO2024046113A1 (zh) 2024-03-07

Family

ID=90100392

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/113109 WO2024046113A1 (zh) 2022-08-29 2023-08-15 一种无线通信方法及通信装置

Country Status (2)

Country Link
CN (1) CN117692892A (zh)
WO (1) WO2024046113A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111819872A (zh) * 2020-06-03 2020-10-23 北京小米移动软件有限公司 信息传输方法、装置、通信设备及存储介质
WO2021128110A1 (zh) * 2019-12-25 2021-07-01 华为技术有限公司 通信方法及装置
EP3944029A1 (en) * 2020-07-21 2022-01-26 Siemens Aktiengesellschaft Method and system for determining a compression rate for an ai model of an industrial task
CN114208292A (zh) * 2020-06-29 2022-03-18 北京小米移动软件有限公司 接入控制方法及装置、存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021128110A1 (zh) * 2019-12-25 2021-07-01 华为技术有限公司 通信方法及装置
CN111819872A (zh) * 2020-06-03 2020-10-23 北京小米移动软件有限公司 信息传输方法、装置、通信设备及存储介质
CN114208292A (zh) * 2020-06-29 2022-03-18 北京小米移动软件有限公司 接入控制方法及装置、存储介质
EP3944029A1 (en) * 2020-07-21 2022-01-26 Siemens Aktiengesellschaft Method and system for determining a compression rate for an ai model of an industrial task

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LENOVO: "Further aspects on AI/ML for beam management", 3GPP DRAFT; R1-2204420, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG1, no. e-Meeting; 20220509 - 20220520, 29 April 2022 (2022-04-29), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052144023 *

Also Published As

Publication number Publication date
CN117692892A (zh) 2024-03-12

Similar Documents

Publication Publication Date Title
JP7033205B2 (ja) データ伝送方法、基地局および端末
US20210144722A1 (en) Method for transmitting uplink channel via multi-beams, terminal device and network-side device
CN110880958B (zh) 一种射频参数的上报方法及装置
US10856267B2 (en) Information indication method and related device
WO2018201402A1 (zh) 确定上行信号的传输参数的方法、终端和网络设备
JP6863485B2 (ja) データ指示方法、装置及び通信システム
CN113595696B (zh) 通信方法、装置及系统
KR20220050364A (ko) 셀-탈피 대규모 mimo 전송 방법 및 이를 위한 장치
WO2021047666A1 (zh) 一种探测参考信号传输的方法、相关设备以及存储介质
WO2020199815A1 (zh) 通信方法及装置
WO2018202168A1 (zh) 信息传输方法及装置
WO2024046113A1 (zh) 一种无线通信方法及通信装置
WO2023060449A1 (zh) 无线通信的方法、终端设备和网络设备
WO2021197473A1 (zh) 一种信号传输方法和设备
WO2021159841A1 (zh) 一种控制信息传输方法及装置
WO2022067784A1 (zh) 一种信号传输的指示方法和通信装置
WO2020007295A1 (zh) 上报及接收参考信号的方法和设备
WO2024149387A1 (zh) 通信方法及通信装置
TWI857573B (zh) 資訊傳輸方法、裝置、網路設備及終端
US20240298192A1 (en) Beam indication method and apparatus
WO2021004475A1 (zh) 一种通信方法及装置
WO2024061125A1 (zh) 一种通信方法及装置
WO2024093906A1 (zh) 一种上行发送功率确定的方法和装置
WO2024131889A1 (zh) 一种通信方法、装置、芯片及模组设备
US20240048216A1 (en) Communication method and communication apparatus

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23859147

Country of ref document: EP

Kind code of ref document: A1