WO2024061125A1 - 一种通信方法及装置 - Google Patents

一种通信方法及装置 Download PDF

Info

Publication number
WO2024061125A1
WO2024061125A1 PCT/CN2023/119099 CN2023119099W WO2024061125A1 WO 2024061125 A1 WO2024061125 A1 WO 2024061125A1 CN 2023119099 W CN2023119099 W CN 2023119099W WO 2024061125 A1 WO2024061125 A1 WO 2024061125A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
function
sub
terminal device
indicate
Prior art date
Application number
PCT/CN2023/119099
Other languages
English (en)
French (fr)
Inventor
程雯洁
耿婷婷
曾宇
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 WO2024061125A1 publication Critical patent/WO2024061125A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/043—Distributed expert systems; Blackboards
    • 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

Definitions

  • the present application relates to the field of communication technology, and in particular, to a communication method and device.
  • AI Artificial intelligence
  • 3GPP 3rd generation partnership project proposes to apply AI to the new radio (NR) system.
  • NR new radio
  • the base station can first query the UE's capabilities. After receiving the query request, the UE can send all AI capability information supported by the UE to the base station.
  • the information may include all AI functions supported by the UE and capability parameters that the UE can provide for each AI function. However, the base station may only need part of the UE's AI capabilities, but not all of the UE's AI capabilities.
  • the UE sends all AI capability information to the base station, which causes the base station to receive more redundant information and increases transmission overhead.
  • Embodiments of the present application provide a communication method and device for reducing the overhead of terminal equipment sending capability information.
  • a first communication method is provided, which method can be executed by a first communication device, or by other equipment including the function of the first communication device, or by a chip system (or chip) or other functional modules.
  • the chip The system or functional module can implement the functions of the first communication device, and the chip system or functional module is, for example, provided in the first communication device.
  • the first communication device is, for example, an access network device, or a CU, or a CU-CP, or a CU-CP2, etc.
  • the method includes: receiving first information, the first information including first sub-information used to indicate a first AI function supported by the terminal device; determining second information according to the first information, The second information is used to indicate requesting the AI function provided by the terminal device; sending the second information to the terminal device; receiving third information from the terminal device, where the third information includes the second The capability parameters corresponding to the AI functions indicated by the information.
  • the first communication device can screen (or filter) according to the AI function supported by the terminal device to determine the second information.
  • the second information can indicate that the network side actually needs the AI function provided by the terminal device, then The terminal equipment only needs to send the corresponding capability parameter to the first communication device according to the second information. It can be seen that the terminal device in the embodiment of the present application does not need to send all AI capability parameters to the network side. Due to the filtering process on the network side, the terminal device only needs to send the capability parameters actually required by the network side to the network side, which reduces Redundant information also saves transmission overhead.
  • the first sub-information is also used to indicate one or more of the following: the collaboration level corresponding to the first AI function; the capability corresponding to the first AI function; The AI algorithm corresponding to the first AI function; or, the AI model corresponding to the first AI function.
  • the first sub-information may indicate the first AI function supported by the terminal device and the collaboration level corresponding to the first AI function, so that the capability of the terminal device is indicated more clearly.
  • the second information is also used to indicate one or more of the following: the collaboration level corresponding to the AI function provided by the terminal device is requested; the AI function provided by the terminal device is requested to correspond to capabilities; request the AI algorithm corresponding to the AI function provided by the terminal device; or request the AI model corresponding to the AI function provided by the terminal device.
  • the third information also includes one or more of the following: capability parameters corresponding to the collaboration level indicated by the second information; capability parameters corresponding to the capabilities indicated by the second information ; The capability parameters corresponding to the AI algorithm indicated by the second information; or, the capability parameters corresponding to the AI model indicated by the second information.
  • receiving the first information includes: receiving the first information from the terminal device; or, receiving Receive the first information from a second communication device, which is an adjacent access network device of the first communication device or a core network device.
  • the first information can come from the terminal device, or from adjacent access network equipment or core network equipment, etc., and the specific source is not limited.
  • the first communication device is an access network device; or the first communication device is a CU; or the first communication device is a CU-CP; or The first communication device is CU-CP2; or the first communication device is LMF; or the first communication device is AMF.
  • the first communication device is the CU or the CU-CP or the CU-CP2.
  • Determining the second information according to the first information includes: sending the information to the DU. the first information, receiving the second information from the DU; or, receiving the first AI function requirement information from the DU, and determining the first AI function requirement information according to the first information and the first information.
  • the first AI function requirement information includes second sub-information
  • the second sub-information is used to indicate that the DU requests the second AI function provided by the terminal device; or, according to the second AI function
  • the demand information and the first information determine the second information
  • the second AI function demand information includes third sub-information
  • the third sub-information is used to instruct the first communication device to request the terminal
  • the third AI function provided by the device, or the third sub-information is used to instruct the first communication device to request the third AI function provided by the terminal device, and is also used to indicate one or more of the following: the The collaboration level corresponding to the third AI function, the capability corresponding to the third AI function, the AI algorithm corresponding to the third AI function, or the AI model corresponding to the third AI function.
  • DU requires the terminal device to support the AI function.
  • the DU can screen (or filter) according to the AI function supported by the terminal device to determine the second information.
  • the DU can also send the DU's requirements (such as the first AI function requirement information) to the first communication device, and the first communication device performs screening (or filtering) based on the DU's requirements and the AI functions supported by the terminal device, to determine the second information.
  • the first communication device requires the terminal device to support the AI function, and the first communication device can screen (or filter) according to the requirements of the first communication device and the AI function supported by the terminal device to determine the second information .
  • the second sub-information is also used to indicate one or more of the following: the collaboration level corresponding to the second AI function; the capability corresponding to the second AI function; The AI algorithm corresponding to the second AI function; or, the AI model corresponding to the second AI function.
  • determining the second information based on the first AI function requirement information and the first information includes one or more of the following: the first AI function and the third
  • the two AI functions are the same AI function.
  • the first sub-information is also used to indicate that the cooperation level corresponding to the first AI function is the first level.
  • the second sub-information indicates that the DU requests the second AI function.
  • the corresponding collaboration level is the second level.
  • the terminal device supports the first level including supporting the second level, it is determined that the second information includes the first sub-information; if the first AI function includes The second AI function determines that the second information includes the second sub-information; or, if the first AI function and the second AI function are the same AI function, and the first information does not indicate The collaboration level corresponding to the first AI function determines that the second information includes the second sub-information.
  • the first communication device can determine the second information in a variety of ways, which is relatively flexible.
  • the method further includes: sending the third information to the DU. If the DU requires the terminal device to support the AI function, the first communication device can send the third information to the DU, so that the DU can clarify the AI function provided by the terminal device.
  • the third information includes fourth sub-information, and the fourth sub-information is used to indicate the fourth AI function provided by the terminal device and the capabilities corresponding to the fourth AI function.
  • the value of the parameter, or the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, and is also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the The capability corresponding to the fourth AI function, the AI algorithm corresponding to the fourth AI function, the AI model corresponding to the fourth AI function, or the value of the capability parameter corresponding to the fourth AI function; or, the value of the capability parameter corresponding to the fourth AI function; or
  • the third information includes fourth sub-information and includes the maximum value of the capability parameter supported by the terminal device.
  • the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, or the fourth sub-information Used to indicate the fourth AI function provided by the terminal device, and also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the capability corresponding to the fourth AI function, the AI algorithms corresponding to the four AI functions, or AI models corresponding to the fourth AI function.
  • the third information may include multiple sub-information, where each sub-information may include an AI function provided by the terminal device and the value of the capability parameter corresponding to the AI function, so that the third information indicates the AI capability provided by the terminal device. More explicit.
  • the third information may include a plurality of sub-information, wherein each sub-information does not include the value of the capability parameter, but the third information additionally includes the maximum value of the capability parameter supported by the terminal device, thereby reducing the cost of the third information. overhead.
  • the capability parameters include one or more of the following: computing capability parameters of the terminal device, so The energy consumption parameters of the terminal device, the storage capacity parameters of the terminal device, the power parameters of the terminal device, the processing delay of the terminal device, the AI model supported by the terminal device, or the terminal device supports AI algorithm.
  • the capability parameters may also include other corresponding parameters, with no specific restrictions.
  • the first AI function includes at least one sub-function, or the first AI function is a sub-function of an AI function.
  • the AI function indicated by one sub-information may be a sub-function, or it may be an AI function including at least one sub-function.
  • a second communication method is provided, which method can be executed by a terminal device, or by other devices including terminal device functions, or by a chip system (or chip) or other functional module, the chip system or functional module
  • the function of the terminal device can be realized, and the chip system or functional module is, for example, provided in the terminal device.
  • the method includes: receiving second information from the first communication device, the second information being used to indicate requesting the AI function provided by the terminal device; sending third information to the first communication device, the third information Includes capability parameters corresponding to the AI function indicated by the second information.
  • the second information is also used to indicate one or more of the following: the collaboration level corresponding to the AI function provided by the terminal device is requested; the AI function provided by the terminal device is requested to correspond to capabilities; request the AI algorithm corresponding to the AI function provided by the terminal device; or request the AI model corresponding to the AI function provided by the terminal device.
  • the third information also includes one or more of the following: capability parameters corresponding to the collaboration level indicated by the second information; capability parameters corresponding to the capabilities indicated by the second information ; The capability parameters corresponding to the AI algorithm indicated by the second information; or, the capability parameters corresponding to the AI model indicated by the second information.
  • the method further includes: sending first information to the first communication device, the first information including first sub-information, the first sub-information being used to indicate a first AI function supported by the terminal device, wherein the second information is related to the first information.
  • the first sub-information is also used to indicate one or more of the following: the collaboration level corresponding to the first AI function; the capability corresponding to the first AI function; The AI algorithm corresponding to the first AI function; or, the AI model corresponding to the first AI function.
  • the first AI function includes at least one sub-function, or the first AI function is a sub-function of an AI function.
  • the third information includes fourth sub-information, and the fourth sub-information is used to indicate the fourth AI function provided by the terminal device and the capabilities corresponding to the fourth AI function.
  • the value of the parameter, or the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, and is also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the The capability corresponding to the fourth AI function, the AI algorithm corresponding to the fourth AI function, the AI model corresponding to the fourth AI function, or the value of the capability parameter corresponding to the fourth AI function; or, the value of the capability parameter corresponding to the fourth AI function; or
  • the third information includes fourth sub-information and includes the maximum value of the capability parameter supported by the terminal device.
  • the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, or the fourth sub-information Used to indicate the fourth AI function provided by the terminal device, and also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the capability corresponding to the fourth AI function, the AI algorithms corresponding to the four AI functions, or AI models corresponding to the fourth AI function.
  • the capability parameters include one or more of the following: computing capability parameters of the terminal device, energy consumption parameters of the terminal device, and storage capability parameters of the terminal device.
  • the power parameters of the terminal device the processing delay of the terminal device, the AI model supported by the terminal device, or the AI algorithm supported by the terminal device.
  • a third communication method is provided, which method can be executed by a terminal device, or by other devices including terminal device functions, or by a chip system (or chip) or other functional module, the chip system or functional module
  • the function of the terminal device can be realized, and the chip system or functional module is, for example, provided in the terminal device.
  • the method includes: receiving request information from the first communication device, the request information being used to indicate requesting the AI function provided by the terminal device; determining third information according to the request information and the capability information of the terminal device, so The third information includes capability parameters corresponding to the AI function indicated by the request information; and the third information is sent to the first communication device.
  • the terminal device can determine the AI capability information that is actually required to be provided by the terminal device, so that the terminal device can send the corresponding capability parameters to the network side without having to send capabilities that the network side does not need. parameters, thereby reducing redundant information and saving transmission overhead.
  • the filtering process of the terminal device capability information is performed on the UE side, so the UE side does not need to send the first information as described above to the network side in advance, which can further save transmission overhead.
  • the request information is also used to indicate a request for one or more of the following: a collaboration level corresponding to the AI function provided by the terminal device; a capability corresponding to the AI function provided by the terminal device. ; The AI algorithm corresponding to the AI function provided by the terminal device; or, the AI model corresponding to the AI function provided by the terminal device.
  • the third information further includes one or more of the following: capability parameters corresponding to the collaboration level indicated by the request information; capability parameters corresponding to the capabilities indicated by the request information; The capability parameters corresponding to the AI algorithm indicated by the request information; or the capability parameters corresponding to the AI model indicated by the request information.
  • the request information includes fifth sub-information, the fifth sub-information is used to indicate requesting the second AI function provided by the terminal device, or the fifth sub-information is Instructing to request the second AI function provided by the terminal device, and also instructing to request one or more of the following: the collaboration level corresponding to the second AI function, the capability corresponding to the second AI function, the The AI algorithm corresponding to the second AI function, or the AI model corresponding to the second AI function; and/or the capability information includes sixth sub-information, the sixth sub-information is used to indicate that the terminal device supports The first AI function, or the sixth sub-information is used to indicate the first AI function supported by the terminal device, and is also used to indicate one or more of the following: the collaboration level corresponding to the first AI function , the capability corresponding to the first AI function, the AI algorithm corresponding to the first AI function, or the AI model corresponding to the first AI function.
  • the request information may include one or more sub-information, each of which may indicate an AI function provided by the requesting terminal device, or indicate an AI function provided by the requesting terminal device and the AI The collaboration level corresponding to the function.
  • the capability information may include one or more sub-information, each of which may indicate an AI function supported by the terminal device, or indicate an AI function supported by the terminal device and the AI The collaboration level corresponding to the function.
  • determining the third information according to the request information and the capability information of the terminal device includes: the first AI function and the second AI function are the same AI function, and the The sixth sub-information indicates that the cooperation level corresponding to the first AI function is the first level, and the fifth sub-information indicates that the cooperation level corresponding to the second AI function is the second level. If the terminal device supports the The first level includes supporting the second level, determining that the third information includes the fifth sub-information; and/or, if the first AI function includes the second AI function, determining that the third information Includes the fifth sub-information. There are many ways for the terminal device to determine the third information, which are relatively flexible.
  • the third information includes fourth sub-information, and the fourth sub-information is used to indicate the fourth AI function provided by the terminal device and the capabilities corresponding to the fourth AI function.
  • the value of the parameter, or the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, and is also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the The capability corresponding to the fourth AI function, the AI algorithm corresponding to the fourth AI function, the AI model corresponding to the fourth AI function, or the value of the capability parameter corresponding to the fourth AI function; or, the value of the capability parameter corresponding to the fourth AI function; or
  • the third information includes fourth sub-information and includes the maximum value of the capability parameter supported by the terminal device.
  • the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, or the fourth sub-information Used to indicate the fourth AI function provided by the terminal device, and also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the capability corresponding to the fourth AI function, the AI algorithms corresponding to the four AI functions, or AI models corresponding to the fourth AI function.
  • the capability parameters include one or more of the following: computing capability parameters of the terminal device, energy consumption parameters of the terminal device, storage capability parameters of the terminal device, The power parameters of the terminal device, the processing delay of the terminal device, the AI model supported by the terminal device, or the AI algorithm supported by the terminal device.
  • a fourth aspect provides a fourth communication method.
  • the method can be executed by the first communication device, or by other equipment including the function of the first communication device, or by a chip system (or chip) or other functional module.
  • the chip The system or functional module can implement the functions of the first communication device, and the chip system or functional module is, for example, provided in the first communication device.
  • the first communication device is, for example, an access network device, or a CU, or a CU-CP, or a CU-CP2, etc.
  • the method includes: sending request information to a terminal device, the request information being used to indicate requesting an AI function provided by the terminal device; receiving third information from the terminal device, the third information including the request information indication The capability parameters corresponding to the AI functions.
  • the request information is also used to indicate a request for one or more of the following: a collaboration level corresponding to the AI function provided by the terminal device; a capability corresponding to the AI function provided by the terminal device. ; The AI algorithm corresponding to the AI function provided by the terminal device; or, the AI model corresponding to the AI function provided by the terminal device.
  • the third information further includes one or more of the following: capability parameters corresponding to the collaboration level indicated by the request information; capability parameters corresponding to the capabilities indicated by the request information; The capability parameters corresponding to the AI algorithm indicated by the above request information number; or, the capability parameters corresponding to the AI model indicated by the request information.
  • the first communication device is an access network device; or the first communication device is a CU; or the first communication device is a CU-CP; or The first communication device is an LMF; or, the first communication device is an AMF.
  • the first communication device is a CU or CU-CP
  • the method further includes: receiving the request information from the DU; or, determining the request information according to the second AI function requirement information.
  • Request information wherein the second AI function requirement information is used to indicate a request for an AI function provided by the terminal device, or the second AI function requirement information is used to indicate a request for an AI function provided by the terminal device, and It also indicates one or more of the following: the collaboration level corresponding to the AI function provided by the terminal device, the capability corresponding to the AI function provided by the terminal device, the AI algorithm corresponding to the AI function provided by the terminal device, or, the Describes the AI model corresponding to the AI functions provided by the terminal device.
  • the method further includes: sending the third information to the DU.
  • the third information includes fourth sub-information, and the fourth sub-information is used to indicate the fourth AI function provided by the terminal device and the capabilities corresponding to the fourth AI function.
  • the value of the parameter, or the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, and is also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the The value of the capability parameter corresponding to the fourth AI function, the capability corresponding to the fourth AI function, the AI algorithm corresponding to the fourth AI function, or the AI model corresponding to the fourth AI function; or, the third The third information includes fourth sub-information and includes the maximum value of the capability parameter supported by the terminal device.
  • the fourth sub-information is used to indicate the fourth AI function provided by the terminal device, or the fourth sub-information Used to indicate the fourth AI function provided by the terminal device, and also used to indicate one or more of the following: the collaboration level corresponding to the fourth AI function, the capability corresponding to the fourth AI function, the AI algorithms corresponding to the four AI functions, or AI models corresponding to the fourth AI function.
  • the capability parameters include one or more of the following: computing capability parameters of the terminal device, energy consumption parameters of the terminal device, and storage capability parameters of the terminal device.
  • the power parameters of the terminal device the processing delay of the terminal device, the AI model supported by the terminal device, or the AI algorithm supported by the terminal device.
  • a communication device may be the first communication device described in any one of the above first to fourth aspects.
  • the communication device has the function of the first communication device.
  • the communication device is, for example, a first communication device, or a larger device including the first communication device, or a functional module in the first communication device, such as a baseband device or a chip system.
  • the communication device includes a baseband device and a radio frequency device.
  • the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module). The transceiver unit can realize the sending function and the receiving function.
  • the transceiver unit When the transceiver unit realizes the sending function, it can be called a sending unit (sometimes also called a sending module). When the transceiver unit realizes the receiving function, it can be called a receiving unit (sometimes also called a sending module). receiving module).
  • the sending unit and the receiving unit can be the same functional module, which is called the sending and receiving unit, and the functional module can realize the sending function and the receiving function; or the sending unit and the receiving unit can be different functional modules, and the sending and receiving unit is responsible for these functions.
  • the transceiver unit (or the receiving unit) is configured to receive first information, where the first information includes first sub-information, and the first sub-information is used to indicate The first AI function supported by the terminal device; the processing unit is used to determine second information according to the first information, and the second information is used to indicate a request for the AI function provided by the terminal device; the transceiver unit ( Or, the sending unit) is used to send the second information to the terminal device; the sending and receiving unit (or the receiving unit) is also used to receive the third information from the terminal device, so The third information includes capability parameters corresponding to the AI function indicated by the second information.
  • the transceiver unit (or the sending unit) is used to send request information to a terminal device, where the request information is used to indicate requesting the AI function provided by the terminal device;
  • the transceiver unit (or the receiving unit) is configured to receive third information from the terminal device, where the third information includes capability parameters corresponding to the AI function indicated by the request information.
  • the communication device further includes a storage unit (sometimes also referred to as a storage module), the processing unit is configured to be coupled with the storage unit and execute the program in the storage unit or Instructions enable the communication device to perform the functions of the first communication device described in any one of the above first to fourth aspects.
  • a storage unit sometimes also referred to as a storage module
  • the processing unit is configured to be coupled with the storage unit and execute the program in the storage unit or Instructions enable the communication device to perform the functions of the first communication device described in any one of the above first to fourth aspects.
  • a sixth aspect provides a communication device.
  • the communication device may be the terminal device described in any one of the above first to fourth aspects.
  • the communication device has the function of the above-mentioned terminal device.
  • the communication device is, for example, a terminal device, or includes a terminal device Larger equipment, or functional modules in terminal equipment, such as baseband devices or chip systems.
  • the communication device includes a baseband device and a radio frequency device.
  • the communication device includes a processing unit (sometimes also called a processing module) and a transceiver unit (sometimes also called a transceiver module).
  • a processing unit sometimes also called a processing module
  • a transceiver unit sometimes also called a transceiver module
  • the transceiver unit (or the receiving unit) is configured to receive second information from the first communication device, where the second information is used to indicate requesting the terminal device to provide AI function; the transceiver unit (or the sending unit) is used to send third information to the first communication device, where the third information includes capability parameters corresponding to the AI function indicated by the second information. .
  • the transceiver unit (or the receiving unit) is configured to receive request information from the first communication device, where the request information is used to indicate requesting AI provided by the terminal device. Function; the processing unit is configured to determine third information based on the request information and the capability information of the terminal device, where the third information includes capability parameters corresponding to the AI function indicated by the request information; the transceiver unit (or the sending unit), configured to send the third information to the first communication device.
  • the communication device further includes a storage unit (sometimes also referred to as a storage module), the processing unit is configured to be coupled with the storage unit and execute the program in the storage unit or Instructions enable the communication device to perform the functions of the terminal device described in any one of the above first to fourth aspects.
  • a storage unit sometimes also referred to as a storage module
  • the processing unit is configured to be coupled with the storage unit and execute the program in the storage unit or Instructions enable the communication device to perform the functions of the terminal device described in any one of the above first to fourth aspects.
  • a seventh aspect provides a communication system, including a first communication device and a terminal device, wherein the first communication device is used to perform the method performed by the first communication device as described in the first or second aspect, and the terminal device For performing the method performed by the terminal device as described in the first or second aspect; or, the first communication device is used for performing the method performed by the first communication device as described in the third or fourth aspect, The terminal device is used to perform the method performed by the terminal device as described in the third or fourth aspect.
  • a computer-readable storage medium is provided.
  • the computer-readable storage medium is used to store a computer program or instructions that, when executed, cause the method executed by the first communication device or terminal device in the above aspects. be realized.
  • a ninth aspect provides a computer program product containing instructions that, when run on a computer, enables the methods described in the above aspects to be implemented.
  • a chip system including a processor and an interface.
  • the processor is configured to call and run instructions from the interface, so that the chip system implements the methods of the above aspects.
  • FIG1 is a schematic diagram of the structure of an access network device
  • Figure 2 shows the framework diagram of AI application in NR
  • Figure 3 is a schematic diagram of a network architecture applied in the embodiment of the present application.
  • Figure 4 is a flow chart of a communication method provided by an embodiment of the present application.
  • Figure 5 is a flow chart of another communication method provided by an embodiment of the present application.
  • Figure 6 is a schematic diagram of a device provided by an embodiment of the present application.
  • Figure 7 is a schematic diagram of yet another device provided by an embodiment of the present application.
  • the technical solution provided by the embodiments of this application can be applied to the fourth generation mobile communication technology (the 4th generation, 4G) system, such as the long term evolution (LTE) system, or can be applied to the fifth generation mobile communication technology (the 5th generation (5G) system, such as the NR system, or can also be applied to the next generation mobile communication system or other similar communication systems, such as the sixth generation mobile communication technology (the 6th generation, 6G) system, etc., the specific details are not Make restrictions.
  • D2D device-to-device
  • V2X vehicle to everything
  • both communicating parties may be UEs
  • one communicating party may be a UE and the other party may be a network device (such as an access network device), or both communicating parties may be network devices.
  • the communication parties are network equipment and UE as an example.
  • the number of nouns means “singular noun or plural noun", that is, “one or more”, unless otherwise specified.
  • At least one means one or more
  • plural means two or more.
  • “And/or” describes the relationship between 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 are in an "or” relationship.
  • A/B means: A or B.
  • At least one of the following or similar expressions thereof refers to any combination of these items, including any combination of a single item (items) or a plurality of items (items).
  • at least one of a, b, or c means: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c Can be single or multiple.
  • first and second mentioned in the embodiment of this application are used to distinguish multiple objects and are not used to limit the size, content, order, timing, priority or importance of multiple objects.
  • the first resource unit and the second resource unit can be the same resource unit, or they can be different resource units.
  • such names do not indicate the location, size, application scenarios, and priorities of the two resource units. level or importance.
  • the numbering of steps in the various embodiments introduced in this application is only to distinguish different steps and is not used to limit the order between steps. For example, S401 may occur before S402, or may occur after S402, or may occur simultaneously with S402.
  • the terminal device is a device with wireless transceiver function, which can be a fixed device, a mobile device, a handheld device (such as a mobile phone), a wearable device, a vehicle-mounted device, or a wireless device built into the above device. (For example, communication module, modem, or chip system, etc.).
  • the terminal device is used to connect people, objects, machines, etc., and can be widely used in various scenarios, including but not limited to the following scenarios: cellular communication, device-to-device communication (device-to-device, D2D), car-to-everything (vehicle to everything, V2X), machine-to-machine/machine-type communications (M2M/MTC), Internet of things (IoT), virtual reality (VR) , augmented reality (AR), industrial control, self-driving, remote medical, smart grid, smart furniture, smart office, smart wear, smart transportation , terminal equipment for smart cities, drones, robots and other scenarios.
  • the terminal equipment may sometimes be called user equipment (UE), terminal, access station, UE station, remote station, wireless communication equipment, or user device, etc.
  • UE user equipment
  • the network device in the embodiment of this application is a device in a wireless network, such as a radio access network (RAN) node that connects a terminal device to a wireless network, or a radio access network device.
  • RAN nodes are: gNB, transmission reception point (TRP), evolved Node B (eNB), radio network controller (radio network controller, RNC), Node B (Node B) B, NB), base station controller (BSC), base transceiver station (BTS), home base station (for example, home evolved NodeB, or home Node B, HNB), base band unit (base band unit , BBU), or wireless fidelity (Wifi) access point (AP), integrated access and backhaul (IAB), etc.
  • TRP transmission reception point
  • eNB evolved Node B
  • RNC radio network controller
  • BSC base station controller
  • BTS base transceiver station
  • home base station for example, home evolved NodeB, or home Node B
  • the RAN node can also refer to a centralized unit (central unit, CU) or a distributed unit (distributed unit, DU), or the RAN node can also be composed of CU and DU.
  • CU and DU can be understood as the division of RAN nodes from the perspective of logical functions.
  • CU and DU are connected through the F1 interface;
  • CU can represent gNB and connect to the core network through the NG interface.
  • 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, which can save costs and facilitate network expansion.
  • 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 radio link control
  • MAC media access control
  • PHY physical layer
  • the RAN node in the embodiment of the present application may also include a centralized unit control plane (CU-CP) node and/or a centralized unit user plane (CU-UP) node.
  • CU-CP is responsible for the control plane function, which mainly includes RRC and PDCP-control (control, C).
  • PDCP-C is mainly responsible for encryption and decryption of control plane data, integrity protection, data transmission, etc.
  • the CU control plane CU-CP also includes a further segmentation architecture, that is, the existing CU-CP is further segmented into CU-CP1 and CU-CP2.
  • CU-CP1 includes various radio resource management functions, and CU-CP2 only includes RRC functions and PDCP-C functions (ie, the basic functions of control plane signaling at the PDCP layer).
  • CU-UP is responsible for user plane functions, mainly including SDAP and PDCP-user (user, 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.
  • CU-CP and CU-UP are connected through the E1 interface.
  • CU-CP can represent the RAN node, connect to the core network through the NG interface, and connect to the DU through F1-C (control plane).
  • PDCP-C is also set in CU-UP.
  • the communication device for realizing the network device function may be a network device, or may be capable of supporting the network device.
  • the device for implementing the function such as a chip system, can be installed in a network device.
  • the device for implementing the function of the network device is a network device as an example to describe the technical solution provided in the embodiment of the present application.
  • 3GPP proposes that AI can be applied to the NR system. Through intelligent data collection and analysis, network performance and user experience can be improved.
  • 3GPP has preliminarily defined the framework for the application of AI in NR, as shown in Figure 2.
  • the data source can store data from gNB, gNB-CU, gNB-DU, UE or other management entities.
  • the data source can be used as a database for AI model training and data analysis and reasoning.
  • "data collection" in Figure 2 can represent the data source.
  • the model training host can analyze the training data provided by the data source to give the optimal AI model.
  • the "model training" box in Figure 2 can represent the model training host.
  • the model inference host uses the AI model to give a reasonable AI-based prediction of the network operation based on the data provided by the data source, or guide the network to make policy adjustments.
  • the "model inference" box in Figure 2 can represent the model inference host.
  • the relevant policy adjustments are uniformly planned by the actor entity and sent to multiple network entities for operation.
  • the specific performance information of the network will be input into the data source again for storage.
  • AI model also known as AI algorithm (or AI operator)
  • AI algorithm or AI operator
  • AI model is a general term for mathematical algorithms based on the principles of artificial intelligence, and is also the basis for using AI to solve specific problems.
  • the type of AI model is not limited.
  • an AI model can be a machine learning model, a deep learning model, or a reinforcement learning model.
  • Machine learning is a method of realizing artificial intelligence.
  • the goal of this method is to design and analyze some algorithms (ie, models) that allow computers to automatically "learn".
  • the designed algorithms can be called machine learning models.
  • Machine learning models are a type of algorithm that automatically analyze and obtain patterns from data and use the patterns to predict unknown data.
  • Deep learning is a new technical field arising from the machine learning research process. Specifically, deep learning is a method in machine learning based on deep representation learning of data. Deep learning explains data by establishing a neural network that simulates the human brain for analysis and learning. Since in machine learning methods, almost all features need to be determined by industry experts and then the features are encoded. However, deep learning algorithms try to learn features from the data themselves. Algorithms designed based on deep learning ideas are called deep learning models.
  • Reinforcement learning is a special field in machine learning. It is a process that continuously learns optimal strategies, makes sequence decisions, and obtains maximum returns through the interaction between an agent and the environment. In layman's terms, reinforcement learning is learning "what to do (that is, how to map the current situation into actions) to maximize the numerical revenue signal.” The agent is not told what actions to take, but must discover by itself which actions will yield the most lucrative returns. Reinforcement learning is different from supervised learning and unsupervised learning in the field of machine learning. Supervised learning is the process of learning from externally provided labeled training data (task-driven), while unsupervised learning is looking for unlabeled data. The process of implicit structure (data-driven). Reinforcement learning is the process of finding better solutions through "trials". The agent must exploit existing experience to obtain benefits, and at the same time conduct trials so that it can obtain better action selection space in the future (that is, learn from mistakes). Algorithms designed based on reinforcement learning are called reinforcement learning models.
  • AI model training refers to the process of using a designated initial model to calculate the training data, and using a certain method to adjust the parameters in the initial model based on the calculation results, so that the model gradually learns certain rules and has specific functions.
  • the AI model with stable functions after training can be used for inference.
  • the inference of the AI model is the process of using the trained AI model to calculate the input data and obtain the predicted inference results (which can also be called output data).
  • AI functions, or use cases based on AI 5.
  • 3GPP has designed some basic application scenarios for the application of AI on the RAN side, such as channel state information (CSI)-reference signal (RS) feedback enhancement (feedback enhancement) and beam management enhancement (beam management enhancement) or positioning accuracy enhancements, etc.
  • CSI channel state information
  • RS reference signal
  • beam management enhancement beam management enhancement
  • CSI is the channel attribute of the communication link and is the channel quality information sent by the UE to the access network device.
  • the UE sends downlink CSI to the access network device, so that the access network device can select a more appropriate modulation and coding scheme (MCS) for the UE to better adapt to the changing wireless channel.
  • MCS modulation and coding scheme
  • the CSI sent by the UE may include one or more 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) , SS/PBCH block resource indicator (SS/PBCH block resource indicator, SSBRI), layer indicator (LI), rank indicator (RI), or layer 1 reference signal received power (layer 1reference signal receiver power, L1-RSRP).
  • rank is the rank in the antenna matrix in the multi-input multi-output (MIMO) scheme, indicating one or more parallel effective data streams
  • RI is used to indicate the physical downlink shared channel (physical downlink shared channel, PDSCH) effective data layer number.
  • CSI-RS feedback enhancement can include sub-scenarios such as CSI compression, CSI prediction, and CSI-RS configuration signaling reduction.
  • CSI compression may include compression in at least one domain among spatial domain, time domain or frequency domain.
  • the access network device and the UE first interact with a dictionary.
  • the access network equipment trains a model in advance based on factors such as the capabilities of the UE and the requirements of the access network equipment.
  • the model includes, for example, an encoder model and a corresponding decoder model.
  • the access network device can send the encoder model to the UE, and can also send tools such as quantizer to the UE. Among them, the quantizer is used to quantize the compressed signal.
  • the UE can obtain the first matrix based on the measured downlink channel matrix and encoder network.
  • the UE may input the measured downlink channel matrix into the encoder network to obtain a first matrix output by the encoder network.
  • the UE may preprocess the measured downlink channel matrix, and then input the preprocessed downlink channel matrix into the encoder network to obtain the first matrix output by the encoder network.
  • the UE can use an existing dictionary to compress the first matrix, and can use a quantizer to quantize the compressed signal, and then send the quantization result to the access network device.
  • the access network equipment reversely recovers the original downlink channel matrix based on the dictionary, decoder network, and quantization results from the UE.
  • AI-based beam management enhancement can include sub-scenarios such as beam scanning matrix prediction and optimal beam prediction.
  • An implementation process of beam management enhancement is as follows:
  • a certain number of UEs perform omnidirectional beam scanning on the synchronization signal and physical broadcast channel (PBCH) block (SSB). These UEs can send scanning results to the access network equipment.
  • the scanning results are, for example, Includes received signal quality information on each beam.
  • the access network equipment can be trained based on the scanning results of these UEs to obtain a sparse scanning matrix, or a sparse model. This matrix is usually unique to the cell.
  • the sparse model may include information about better beams.
  • the access network device sends the sparse model to the UE (can consider sending it through a system information block (SIB) message, etc.).
  • SIB system information block
  • the UE can perform beam scanning in the P1 phase based on the sparse matrix, and the UE can The scan result is sent to the access network device, and the scan result is called a sparse scan result, for example.
  • the access network equipment sends reference signals through beams in a wide range. The UE selects the best beam based on measurements and sends the best beam information to the access network equipment.
  • the access network equipment obtains the optimal beam based on the sparse scanning results.
  • the access network device can perform P2 scanning on the UE based on the beam, and the UE can send the identifier of the best beam to the access network device.
  • P2 scanning means that the access network device sends a reference signal through a narrower beam within a narrower range, and the UE selects the best beam based on the measurement and sends the information of the best beam to the access network device.
  • the enhancement of positioning accuracy based on AI is mainly to improve positioning accuracy.
  • An implementation process for positioning accuracy enhancement is as follows:
  • the original data includes, for example, the coordinate information of the UE, and/or line of sight (LOS)/non-line of sight (NLOS) status and other information.
  • LOS line of sight
  • NLOS non-line of sight
  • LMF Location management function
  • access network equipment train models separately.
  • the model trained by LMF can be used to infer the final positioning information of the UE (such as the longitude and latitude of the UE) based on the original data.
  • the model trained by gNB Can be used to reason about LOS/NLOS judgment results based on original data.
  • level 0 level 0
  • level 1 level 1
  • level 2 level 2
  • Level 0 also known as collaboration level 0, is the no collaboration level.
  • the AI model on the access network device side is completely invisible to the UE.
  • the training and inference processes of the AI model are completed within the access network device and have no impact on the air interface.
  • Level 1 also known as collaboration level 1, is a signaling-based collaboration without model transfer level.
  • the access network device sends a dictionary to the UE, so that the UE can assist the access network device in AI inference, which has a certain impact on the air interface.
  • AI models can also be deployed inside the UE, and the UE can compress and encode the downlink channel matrix based on the AI model and dictionary deployed by the UE.
  • UE and access network equipment can jointly train the AI model, for example, through federated learning.
  • the AI model will not be directly transmitted between the UE and the access network equipment, but the relevant parameters of the AI model can be transmitted.
  • level 1 can also be further subdivided into level 1A and level 1B.
  • level 1A signaling-based collaboration for single-sided model without model transfer for single-sided node deployment model without model interaction.
  • the AI model can be deployed in the access network device or UE, that is, the AI model is deployed on one side.
  • level 1B signaling-based collaboration for two-sided model without model transfer for two-sided node deployment model without model interaction.
  • the access network equipment and UE can deploy AI models separately, that is, the AI models are deployed on both sides.
  • Level 2 also known as collaboration level 2 is a signaling-based collaboration with model transfer level with model interaction.
  • both the access network device and the UE can have AI functions.
  • the access network device and the UE can deploy AI models respectively, and the access network device and the UE can perform reasoning and other processes based on the deployed AI models.
  • the access network device and the UE can directly transmit the AI model.
  • cooperation levels may also be included.
  • future communication systems may also support some cooperation levels, which are not limited by the embodiments of this application.
  • Figure 3 shows a communication network architecture applicable to the embodiment of the present application.
  • the first communication device can communicate with the UE.
  • the UE can send the AI capability information of the UE to the first communication device.
  • the first communication device is, for example, an access network device; or the first communication device is a functional module included in the access network device, such as CU, or CU-CP, or CU-CP2; or the first communication device is a functional module including an access network device. Larger equipment for network access equipment.
  • the access network device is, for example, the aforementioned RAN node. For introduction to the RAN node and the UE, please refer to the above.
  • the first communication device is, for example, a core network device; or the first communication device is a functional module included in the core network device; or the first communication device is a larger device including the core network device.
  • the core network equipment is, for example, LMF or access and mobility management function (AMF).
  • An embodiment of the present application provides a communication method. Please refer to Figure 4, which is a flow chart of the method. This method can be applied to the network architecture shown in Figure 3.
  • the UE involved in this method is the UE in Figure 3
  • the first communication device involved in this method is the first communication device in Figure 3.
  • the UE sends the first information to the first communication device.
  • the first communication device receives the first information from the UE.
  • the second communication device sends the first information to the first communication device, and accordingly, the first communication device receives the first information from the second communication device.
  • the second communication device is, for example, an adjacent access network device of the first communication device, or a core network device, or the like.
  • the first information comes from the UE as an example.
  • the first information may also be called AI capability support information, or may also have other names.
  • the first information includes M sub-information, and M is a positive integer.
  • the first information may indicate one or more of the following: AI functions supported by the UE, collaboration levels corresponding to the AI functions supported by the UE, capabilities corresponding to the AI functions supported by the UE, and capabilities corresponding to the AI functions supported by the UE.
  • each sub-information in the M sub-information may indicate one or more of the above.
  • one sub-information in the M sub-information is the first sub-information
  • the first sub-information may indicate one or more of the following: The first AI function supported by the UE, the collaboration level corresponding to the first AI function supported by the UE, the capability corresponding to the first AI function supported by the UE, the AI algorithm corresponding to the first AI function supported by the UE, or, the UE supports The AI model corresponding to the first AI function.
  • capabilities corresponding to AI functions or AI sub-functions may include capabilities related to AI models and/or AI services, such as one or more of training, inference, or monitoring capabilities.
  • training refers to the training of the AI model corresponding to the AI function or AI sub-function of the network device
  • inference refers to the inference of the AI model corresponding to the AI function or sub-function of the network device
  • monitoring refers to the network device Supports monitoring of AI models corresponding to AI functions or sub-functions.
  • each sub-information in the M sub-information may indicate an AI function supported by the UE and the cooperation level corresponding to the AI function; or, each sub-information in some sub-information in the M sub-information may indicate an AI function supported by the UE. and the collaboration level corresponding to the AI function, and the remaining sub
  • Each sub-information in the information indicates an AI function supported by the UE, but does not indicate the cooperation level.
  • one sub-information among the M sub-information is the first sub-information, and the first sub-information may indicate the first AI function supported by the UE and indicate the cooperation level corresponding to the first AI function.
  • the collaboration level indicated by one sub-information among the M sub-information may be the collaboration level that the UE can support for the AI function indicated by the sub-information.
  • the capability indicated by one sub-information among the M sub-information may be the capability that the requested UE can support for the AI function indicated by the sub-information.
  • the AI algorithm indicated by one sub-information in the M sub-information may be an AI algorithm that the UE is requested to support for the AI function indicated by the sub-information.
  • the AI model indicated by one sub-information among the M sub-information may be an AI model that the UE is requested to support for the AI function indicated by the sub-information.
  • each sub-information in the M sub-information indicates an AI function
  • the AI functions indicated by different sub-information may be the same or different.
  • each sub-information in the M sub-information indicates an AI function
  • different sub-information indicates different AI functions
  • the AI function indicated by one sub-information in the M sub-information may include at least one sub-function, that is, the AI function may be regarded as the total AI function, and the AI function also includes at least one sub-function; and/or, M sub-information
  • the AI function indicated by another sub-information in can be a sub-function included in one AI function.
  • an AI function is the CSI-RS feedback enhancement function, which can be referred to as the CSI function and can be represented by "CSI”.
  • the CSI function may include at least one sub-function, for example, one of the sub-functions is CSI-1, another of the sub-functions is CSI-2, and yet another of the sub-functions is CSI-3.
  • the CSI-1 function is, for example, a CSI compression function
  • the CSI-2 function is, for example, a CSI prediction function
  • the CSI-3 function is, for example, a CSI-RS configuration signaling reduction function.
  • another AI function is a BM function.
  • the BM function is, for example, a beam management function.
  • the beam management function is, for example, the aforementioned beam management enhancement function, which can be represented by "BM”.
  • another AI function is a positioning function, such as a PA function.
  • the PA function is, for example, the aforementioned positioning accuracy enhancement function, which can be represented by "PA”.
  • the first information indicates the AI function supported by the UE
  • the first information may indicate the [AI function] supported by the UE and the [sub-function] supported by the UE.
  • one sub-information in the M sub-information may indicate [AI function 1]
  • Another sub-information among the M sub-information may indicate [Sub-Function 1].
  • sub-information 1 among M sub-information indicates [CSI-1]
  • sub-information 2 among M sub-information indicates [CSI-2]
  • sub-information 3 among M sub-information indicates [BM].
  • the first information may indicate the [AI function] supported by the UE without indicating the [sub-function] supported by the UE.
  • sub-information 1 in the M sub-information indicates [CSI]
  • sub-information 2 in the M sub-information indicates [CSI].
  • the first information may indicate the [sub-function] supported by the UE without indicating the [AI function] supported by the UE.
  • sub-information 1 in the M sub-information indicates [CSI-1]
  • sub-information 2 in the M sub-information indicates [CSI-1]. Instructions [CSI-2].
  • the first information indicates the supported AI functions and the collaboration level corresponding to the AI functions supported by the UE
  • the first information may indicate one or more of the following: [AI function] supported by the UE, [Sub-function supported by the UE] ], [AI function, collaboration level] supported by the UE, or [sub-function, collaboration level] supported by the UE.
  • M sub-information may include one or more of the following sub-information: sub-information indicating [AI function 1], sub-information indicating [sub-function 1], sub-information indicating [AI function 1, collaboration level], or, Sub-information indicating [Sub-Function 1, Cooperation Level].
  • sub-information 1 in M sub-information indicates [CSI-1, collaboration level 1]
  • sub-information 2 in M sub-information indicates [CSI-2, collaboration level 1]
  • sub-information 3 in M sub-information indicates [ BM, collaboration level 2].
  • sub-information 1 in M sub-information indicates [CSI-1]
  • sub-information 2 in M sub-information indicates [CSI-2]
  • sub-information 3 in M sub-information indicates [BM, cooperation level 2].
  • the first information indicates the supported AI functions, the cooperation level corresponding to the AI functions supported by the UE, the capabilities corresponding to the AI functions supported by the UE, the AI algorithms corresponding to the AI functions supported by the UE, or the AI functions supported by the UE.
  • a sub-information 1 in the first information may indicate (or include) the following one or more items: AI function [CSI-RS feedback enhancement function, Beam management, positioning], AI sub-functions [CSI-1, CSI-2], collaboration level [collaboration level 0/collaboration level 1A/collaboration level 1B/collaboration level 2], capabilities corresponding to AI sub-functions [training, inference, Monitoring], AI algorithms [identifier, IDs], or AI models [IDs].
  • AI function CSI-RS feedback enhancement function, Beam management, positioning]
  • AI sub-functions [CSI-1, CSI-2]
  • collaboration level collaboration level 0/collaboration level 1A/collaboration level 1B/collaboration level 2
  • capabilities corresponding to AI sub-functions [training, inference, Monitoring]
  • AI algorithms identifier, IDs]
  • IDs AI models
  • sub-information 1 indicates the AI function [CSI-RS feedback enhancement function, beam management, positioning]. It can be understood that the AI function indicated by sub-information 1 may include one of the CSI-RS feedback enhancement function, beam management, or positioning. item or multiple items.
  • the first communication device determines the second information according to the first information.
  • the second information may indicate one or more of the following: requesting (or expecting; or hoping) the AI function provided by the UE, requesting (or expecting; or hoping) the collaboration level corresponding to the AI function provided by the UE, Request (or, expect; or, hope) the capability corresponding to the AI function provided by the UE, request (or, expect; or, hope) Desire) the AI algorithm corresponding to the AI function provided by the UE, or request (or, expect; or, hope) the AI model corresponding to the AI function provided by the UE.
  • the second information may indicate that the network side actually needs the AI capability provided by the UE.
  • the first communication device may determine the second information based on the first information in a variety of ways, as described below with examples.
  • the network element that requires the UE to provide AI capabilities is, for example, DU
  • the first communication device is, for example, CU, or CU-CP, or CU-CP2
  • the first communication device determines the second information based on the first information.
  • the first communication device sends the first information to the DU
  • the DU can send the determined second information to the first communication device, so that the first communication device determines the second information.
  • the DU obtains the second information.
  • the DU may determine the second information based on the first AI function requirement information and the first information.
  • the first AI function requirement information may indicate that the DU requires AI capabilities provided by the UE.
  • network elements that require the UE to provide AI capabilities include, for example, access network elements and/or core network elements.
  • Access network elements such as access network equipment, or DU, etc.; core network elements.
  • the elements include, for example, LMF and/or AMF, or may also include other core network elements.
  • the network element that requires the UE to provide AI capabilities is taken as an example. However, the actual situation is not limited to this. That is, the network element that requires the UE to provide AI capabilities can also be replaced by DU with other networks. Yuan.
  • the first AI function requirement information includes, for example, N sub-information, where N is a positive integer.
  • the first AI function requirement information may indicate one or more of the following: DU requests (or expects; or hopes) the AI function provided by the UE, DU requests the collaboration level corresponding to the AI function provided by the UE, DU The capability corresponding to the AI function provided by the UE is requested, the DU requests the AI algorithm corresponding to the AI function provided by the UE, or the DU requests the AI model corresponding to the AI function provided by the UE.
  • the first AI function requirement information indicates that the DU requests an AI function provided by the UE.
  • Each sub-information in the N sub-information may indicate that the DU requests an AI function provided by the UE.
  • one sub-information in the N sub-information is the second sub-information
  • the second sub-information may indicate that the DU requests a second AI function provided by the UE.
  • items indicated by different sub-information may be the same, partially the same or completely different.
  • the contents of the same item indicated by different sub-information may be the same or different. For this, please refer to the introduction of M sub-information in S401.
  • the AI function indicated by one sub-information among the N sub-information may include at least one sub-function; and/or the AI function indicated by another sub-information among the N sub-information may be a sub-function included in one AI function. Function.
  • this part and further examples please refer to the introduction of the first information in S401.
  • DU determines (or filters; or screens) the second information based on the first AI function requirement information and the first information, and can be implemented in a variety of ways. Some examples are given below, but are not limited to the examples below. DU may determine the second information according to one or more of the following methods A to F.
  • Method A If N sub-information intersects with M sub-information, and the intersection includes one or more sub-information, then DU may determine that the second information includes the intersection.
  • the first AI function requirement information includes sub-information 1 and sub-information 2, sub-information 1 indicates [CSI-1, cooperation level 1], sub-information 2 indicates [BM, cooperation level 2]; the first information includes sub-information 3, Sub-information 4 and sub-information 5, sub-information 3 indicates [CSI-1, cooperation level 1], sub-information 4 indicates [CSI-3, cooperation level 1], and sub-information 5 indicates [BM, cooperation level 2].
  • sub-information 1 is the same as sub-information 3
  • sub-information 2 is the same as sub-information 5. Therefore, sub-information 1 and sub-information 2 are the intersection of the first AI function requirement information and the first information. Therefore, DU can determine that the second information includes sub-information.
  • Method B If the first AI function requirement information and the first information have sub-information that does not completely overlap, the second information can be determined based on the UE's support for the collaboration level.
  • the first information includes the aforementioned first sub-information
  • the first AI function requirement information includes the aforementioned second sub-information.
  • the first sub-information indicates the first AI function supported by the UE, and indicates that the cooperation level corresponding to the first AI function is the first level;
  • the second sub-information indicates the second AI function that the DU requests the UE to provide, and indicates that the second AI function corresponds to
  • the collaboration level is the second level. If the first AI function and the second AI function are the same AI function, but the first level and the second level are different, it indicates that the first sub-information and the second sub-information are sub-information that does not completely overlap.
  • the second information may include the first sub-information.
  • the first level is higher than the second level, and if it is specified that a UE that supports a high collaboration level can also support a low collaboration level, then the UE can support the second level as long as it can support the first level.
  • the second information may not include the second level.
  • the first sub-information also does not include the second sub-information. For example, if the first level is lower than the second level, if it is specified that a UE that supports a low collaboration level may not necessarily be able to support a high collaboration level, then a UE that supports the first level may not necessarily be able to support the second level.
  • the first level is higher than the second level, but if it is specified that the UE with a high cooperation level does not If the low cooperation level is supported (or may not be supported), then even if the UE supports the first level, it may not necessarily be able to support the second level.
  • the first AI function requirement information includes sub-information 1 and sub-information 2, sub-information 1 indicates [CSI-1, cooperation level 1], sub-information 2 indicates [BM, cooperation level 2] ⁇ ; the first information includes sub-information Information 3 to sub-information 5, sub-information 3 indicates [CSI-1, cooperation level 2], sub-information 4 indicates [CSI-3, cooperation level 1], and sub-information 5 indicates [BM, cooperation level 2].
  • the sub-information 2 and the sub-information 5 are the same, and the sub-information 1 and the sub-information 3 are not completely overlapping sub-information.
  • collaboration level 2 is higher than collaboration level 1.
  • the relevant standard stipulates that the AI function of the high collaboration level can support the AI function of the low collaboration level
  • the second information may include sub-information 1 and sub-information 5.
  • the relevant standard indicates that the AI function of the high collaboration level cannot support the AI function of the low collaboration level
  • the second information may include sub-information 5 but not sub-information 3.
  • Method C If a sub-information in the first information indicates the complete AI function (or in other words, the total AI function, that is, the AI function includes at least one sub-function), and a sub-information in the first AI function requirement information indicates the If the AI function is an AI sub-function, the second information may include the sub-information in the first AI function requirement information.
  • the first information includes the aforementioned first sub-information
  • the first AI function requirement information includes the aforementioned second sub-information.
  • the first sub-information indicates the first AI function supported by the UE, and optionally also indicates that the cooperation level corresponding to the first AI function is the first level;
  • the second sub-information indicates the second AI function that the DU requests the UE to provide, and optionally also indicates the third AI function.
  • the collaboration level corresponding to the second AI function is the second level. If the first AI function includes the second AI function, or in other words, the second AI function is a sub-function of the first AI function, then the second information may include the second sub-information.
  • the first AI function requirement information includes sub-information 1, which indicates [CSI-1, cooperation level 1]; the first information includes sub-information 2 to sub-information 4, and sub-information 2 indicates [CSI, cooperation level 1], sub-information 3 indicates [CSI-3, cooperation level 2], sub-information 4 indicates [BM, cooperation level 2].
  • sub-information 2 indicates the CSI function
  • sub-information 1 indicates a sub-function (CSI-1) of the CSI function
  • the second information may include sub-information 1.
  • Method D If a sub-information in the first AI function requirement information indicates a complete AI function (or in other words, a total AI function, that is, the AI function includes at least one sub-function), and a sub-information in the first information indicates the If the AI function is an AI sub-function, the second information may include the sub-information in the first information. At this time, although the UE cannot provide the complete AI functions required by the DU, it can provide part of the AI functions required by the DU.
  • the first information includes the aforementioned first sub-information
  • the first AI function requirement information includes the aforementioned second sub-information.
  • the first sub-information indicates the first AI function supported by the UE, and optionally also indicates that the cooperation level corresponding to the first AI function is the first level;
  • the second sub-information indicates the second AI function that the DU requests the UE to provide, and optionally also indicates the third AI function.
  • the collaboration level corresponding to the second AI function is the second level. If the second AI function includes the first AI function, or in other words, the first AI function is a sub-function of the second AI function, then the second information may include the first sub-information.
  • the first information includes sub-information 1, which indicates [CSI-1, collaboration level 1]; the first AI function requirement information includes sub-information 2 to sub-information 4, and sub-information 2 indicates [CSI, collaboration level 1] 1], sub-information 3 indicates [CSI-3, cooperation level 2], sub-information 4 indicates [BM, cooperation level 2].
  • sub-information 2 indicates the CSI function
  • sub-information 1 indicates a sub-function (CSI-1) of the CSI function
  • the second information may include sub-information 1.
  • the first AI functional requirement information includes sub-information 1 and sub-information 2.
  • Sub-information 1 indicates [CSI, collaboration level 0 and collaboration level 2, reasoning and training, [AI algorithm 1, AI model 1]]
  • sub-information Information 2 indicates [Beam Management, Collaboration Level 2, Training and Inference, [AI Algorithm 1, AI Model 1 and AI Model 2], [AI Algorithm 2, AI Model 2]].
  • the first information includes sub-information 3 and sub-information 4.
  • Sub-information 3 indicates [CSI-1, collaboration level 0, inference, [AI algorithm 1, AI model 1 and AI model 2]]]
  • sub-information 4 indicates [beam management, collaboration Level 0, inference, [AI algorithm 2, AI model 2]].
  • CSI-1 is a sub-function of CSI
  • the second information may include [CSI-1, collaboration level 0, inference, [AI algorithm 1, AI model 1]].
  • this example can also be used as an example of method B.
  • Methods A to F in the embodiments of the present application can be applied individually, or any two or more methods can be used in combination.
  • Method E If a certain sub-information in the first information does not indicate a collaboration level, it may be assumed that the UE can support all collaboration levels for the AI function indicated by the sub-information.
  • the first information includes the aforementioned first sub-information
  • the first AI function requirement information includes the aforementioned second sub-information.
  • the first sub-information indicates the first AI function supported by the UE, but does not indicate the cooperation level corresponding to the first AI function;
  • the second sub-information indicates the second AI function that the DU requests the UE to provide, and optionally also indicates the corresponding level of the second AI function.
  • the collaboration level is the second level. If the first AI function and the second AI function are the same AI function, then the second information may include second sub-information.
  • the first AI function requirement information includes sub-information 1 and sub-information 2, sub-information 1 indicates [CSI-1, cooperation level 1], sub-information 2 indicates [BM, cooperation level 2]; the first information includes sub-information 3 and sub-information 4, sub-information 3 indicates [CSI-1], sub-information 4 Instructions [BM, Collaboration Level 2].
  • sub-information 2 and sub-information 4 are the same.
  • sub-information 2 does not indicate the cooperation level corresponding to CSI-1, indicating that the UE can support all cooperation levels for CSI-1, so it also supports cooperation level 1. Therefore the second information may include sub-information 1 and sub-information 2.
  • Method F If the first AI function requirement information and the first information have no intersection, the second information is empty, or the second information cannot be obtained.
  • the first AI function requirement information includes sub-information 1, and sub-information 1 indicates [CSI-1, collaboration level 1]; the first information includes sub-information 2 and sub-information 3, and sub-information 2 indicates [CSI-2, collaboration level 1] , sub-information 3 indicates [BM, collaboration level 2]. It can be seen that the sub-information included in the first AI function requirement information has no intersection with the sub-information included in the first information, so the second information is empty, or the second information cannot be obtained.
  • method F can also be implemented in such a way that if none of methods A to E are satisfied, the second information will be empty, or the second information cannot be obtained.
  • the network element that requires the UE to provide AI capabilities is, for example, DU
  • the first communication device is, for example, CU, or CU-CP, or CU-CP2
  • the first communication device determines the second information based on the first information.
  • the DU sends the first AI function requirement information to the first communication device
  • the first communication device can determine the second information based on the first AI function requirement information and the first information.
  • the second information is obtained by the first communication device.
  • the first communication device determines the second information based on the first AI function requirement information and the first information refer to the above description of DU determining the second information. Introduction to the method.
  • the network element that requires the UE to provide AI capabilities is, for example, CU, CU-CP, or CU-CP2, and the first communication device is, for example, CU, CU-CP, or CU-CP2. It can be understood that the UE is required to provide AI capabilities.
  • the network element that provides AI capabilities is the first communication device. Then one way for the first communication device to determine the second information based on the first information is that the first communication device can determine the second information based on the second AI function requirement information and the first information. information.
  • the second AI function requirement information may indicate one or more of the following: the first communication device requires AI capabilities provided by the UE, the first communication device requires the cooperation level corresponding to the AI function provided by the UE, and the first communication device requires the AI capabilities provided by the UE.
  • the first communication device needs the AI algorithm corresponding to the AI function provided by the UE, or the first communication device needs the AI model corresponding to the AI function provided by the UE.
  • the second AI function requirement information includes, for example, K sub-information, where K is a positive integer.
  • K is a positive integer.
  • Each sub-information in the K sub-information may indicate one or more of the following: the first communication device requires AI capabilities provided by the UE, the first communication device requires The collaboration level corresponding to the AI function provided by the UE, the first communication device needs the capability corresponding to the AI function provided by the UE, the first communication device needs the AI algorithm corresponding to the AI function provided by the UE, or, the first communication device The AI model corresponding to the AI function provided by the UE is required.
  • the second AI function requirement information indicates that the first communication device requests an AI function provided by the UE.
  • each sub-information in the K sub-information may indicate that the first communication device requests an AI function provided by the UE, for example, K sub-information
  • K sub-information One of the sub-information is the third sub-information
  • the third sub-information may indicate that the first communication device requests the third AI function provided by the UE.
  • the items indicated by different sub-information may be the same, partially the same or completely different.
  • the contents of the same item indicated by different sub-information may be the same or different.
  • the AI function indicated by one sub-information among the K sub-information may include at least one sub-function; and/or the AI function indicated by another sub-information among the K sub-information may be a sub-function included in one AI function. Function.
  • this part and further examples please refer to the introduction of the first information in S401.
  • the first communication device determines the second information based on the second AI function requirement information and the first information
  • S403 and S404 may not be performed.
  • the first communication device sends the second information to the UE.
  • the UE receives the second information from the first communication device.
  • the UE sends the third information to the first communication device.
  • the first communication device receives the third information from the UE.
  • the third information may include (or indicate) one or more of the following: the value of the capability parameter corresponding to the AI function indicated by the second information (or in other words, the third information may include the capability parameter corresponding to the AI function provided by the UE), The value of the capability parameter corresponding to the collaboration level indicated by the second information (or the third information may include the capability parameter corresponding to the collaboration level of the AI function provided by the UE), and the capability parameter corresponding to the capability indicated by the second information.
  • the value of the power parameter (or the third information may include the capability parameter corresponding to the capability corresponding to the AI function provided by the UE), the value of the capability parameter corresponding to the AI algorithm indicated by the second information (or the third information may include the value of the capability parameter corresponding to the AI function provided by the UE)
  • the capability parameter corresponding to the AI algorithm corresponding to the AI function), or the value of the capability parameter corresponding to the AI model indicated by the second information (or the third information may include the capability corresponding to the AI model corresponding to the AI function provided by the UE) parameter).
  • the capability parameters may include one or more of the following: computing capability parameters, UE storage capability parameters, UE power parameters, UE processing delay, UE supported AI models, energy consumption parameters, or UE support AI algorithm.
  • the third information may include H sub-information, where H is a positive integer.
  • H sub-information in the H sub-information may indicate one or more of the following: the value of the capability parameter corresponding to the AI function indicated by the second information, the value of the capability parameter corresponding to the collaboration level indicated by the second information, The value of the capability parameter corresponding to the capability, the value of the capability parameter corresponding to the AI algorithm indicated by the second information, or the value of the capability parameter corresponding to the AI model indicated by the second information.
  • H sub-information items indicated by different sub-information may be the same, partially the same or completely different.
  • the contents of items indicated by different sub-information may be the same or different. For this, please refer to the relevant introduction to M sub-information in S401.
  • each sub-information in the H sub-information may indicate one or more items as described in the previous paragraph.
  • the third information may also indicate the AI function provided by the UE.
  • the H sub-information Each sub-information in some or all of the sub-information may indicate one or more of the following: an AI function provided by the UE, the collaboration level corresponding to the AI function, the capability corresponding to the AI function, and the AI algorithm corresponding to the AI function. , the AI model corresponding to the AI function, or the value of the capability parameter corresponding to the AI function.
  • one sub-information in the H sub-information is the fourth sub-information
  • the fourth sub-information may indicate one or more of the following: the fourth AI function provided by the UE, the cooperation level corresponding to the fourth AI function, the corresponding The ability, the AI algorithm corresponding to the fourth AI function, the AI model corresponding to the fourth AI function, or the value of the capability parameter corresponding to the fourth AI function.
  • the items indicated by different sub-information may be the same, for example, both indicate an AI function provided by the UE and the cooperation level corresponding to the AI function; or the items indicated by different sub-information may also be different, for example One sub-information in the H sub-information indicates an AI function provided by the UE and the cooperation level corresponding to the AI function, while another sub-information in the H sub-information indicates an AI function provided by the UE and the capabilities corresponding to the AI function. and the AI algorithm corresponding to the AI function, but does not indicate the collaboration level corresponding to the AI function.
  • each sub-information in the H sub-information may indicate the value of the capability parameter provided by the UE for the AI function indicated by the sub-information.
  • This method provides a clear indication of the capability parameter of each AI function.
  • the third information may also indicate the AI function provided by the UE.
  • each sub-information in the H sub-information may indicate an AI function provided by the UE and the value of the corresponding capability parameter.
  • one sub-information in the H sub-information is The fourth sub-information may indicate the fourth AI function provided by the UE and the value of the capability parameter corresponding to the fourth AI function.
  • the third information may also indicate the AI function provided by the UE and the collaboration level corresponding to the AI function provided by the UE.
  • each sub-information in the H sub-information may indicate an AI function provided by the UE and the collaboration level corresponding to the AI function.
  • the value of the capability parameter corresponding to the AI function or, each sub-information in some sub-information in the H sub-information can indicate an AI function provided by the UE, the cooperation level corresponding to the AI function, and the corresponding
  • the value of the capability parameter, and each sub-information in the remaining sub-information indicates an AI function provided by the UE and the value of the capability parameter corresponding to the AI function, but does not indicate the collaboration level.
  • one of the H sub-information is the fourth sub-information
  • the fourth sub-information may indicate the fourth AI function provided by the UE, the cooperation level corresponding to the fourth AI function, and the value of the capability parameter corresponding to the fourth AI function.
  • the collaboration level indicated by one sub-information in the H sub-information may be the collaboration level supported by the UE for the AI function indicated by the sub-information.
  • the second information includes sub-information 1 and sub-information 2, sub-information 1 indicates [CSI-1, cooperation level 1], and sub-information 2 indicates [BM, cooperation level 2] ⁇ .
  • the third information may include sub-information 3 and sub-information 4.
  • Sub-information 3 indicates [CSI-1, collaboration level 1, storage capacity requirement a1, computing power requirement b1, power requirement c1, processing delay information d1, AI model information e1 , others]
  • sub-information 4 indicates [BM, collaboration level 2, storage capacity requirement a2, computing power requirement b2, power requirement c2, processing delay information d2, AI model information e2, other].
  • each sub-information in the H sub-information does not indicate the value of the capability parameter provided by the UE for the AI function indicated by the sub-information, but the third information may also include in addition to the H sub-information.
  • the maximum value of the capability parameters supported by the UE does not need to include the value of the capability parameter multiple times, which can reduce the transmission overhead of the third information.
  • the third information can also indicate the AI function provided by the UE.
  • each sub-information in part or all of the H sub-information can indicate one or more of the following: an AI provided by the UE function, the collaboration level corresponding to the AI function, the capability corresponding to the AI function, the AI algorithm corresponding to the AI function, or the AI model corresponding to the AI function.
  • one sub-information in the H sub-information is the fourth sub-information
  • the fourth sub-information may indicate one or more of the following: the fourth AI function provided by the UE, the collaboration corresponding to the fourth AI function Level, the ability corresponding to the fourth AI function, the AI algorithm corresponding to the fourth AI function, or the AI model corresponding to the fourth AI function.
  • H sub-information items indicated by different sub-information may be the same or different.
  • the third information may indicate the AI function provided by the UE and the collaboration level corresponding to the AI function provided by the UE, then each sub-information in the H sub-information may indicate an AI function provided by the UE and the collaboration level corresponding to the AI function;
  • each sub-information in some sub-information in the H sub-information may indicate an AI function provided by the UE and the cooperation level corresponding to the AI function, while each sub-information in the remaining sub-information indicates an AI function provided by the UE, and Does not indicate collaboration level.
  • one of the H sub-information is the fourth sub-information, and the fourth sub-information may indicate the fourth AI function provided by the UE and the cooperation level corresponding to the fourth AI function.
  • the second information includes sub-information 1 and sub-information 2, sub-information 1 indicates [CSI-1, cooperation level 1], and sub-information 2 indicates [BM, cooperation level 2] ⁇ .
  • the third information may include sub-information 3, sub-information 4, and the maximum value of the capability parameters supported by the UE.
  • Sub-information 3 indicates [CSI-1, cooperation level 1]
  • sub-information 4 indicates [BM, cooperation level 2].
  • the maximum value of the capability parameters supported by the UE includes, for example, [maximum storage capacity, maximum computing capacity, maximum power information, processing delay information, AI model information, and others].
  • the first communication device may also send the third communication device to DU.
  • the DU can receive the third information from the first communication device, so that the DU obtains the AI capability information of the UE.
  • the network side can first determine the AI capability information (such as the second information) that the UE actually needs to provide, so that the UE can send the capability parameters corresponding to the AI function indicated by the second information to the network side, without having to send the capability parameters corresponding to the AI function not indicated by the second information to the network side, thereby reducing redundant information and saving transmission overhead.
  • AI capability information such as the second information
  • the UE can determine the AI capability information that the network side actually needs to provide from the UE. Please refer to Figure 5 for a flow chart of this method.
  • the first communication device sends request information to the UE.
  • the UE receives the request information from the first communication device.
  • the request information may indicate an AI function requested to be provided by the UE, or may indicate an AI function requested to be provided by the UE and a collaboration level corresponding to the AI function.
  • the network element that requires the UE to provide AI capabilities is, for example, CU, CU-CP, or CU-CP2, and the first communication device is, for example, CU, CU-CP, or CU-CP2. It can be understood that the UE is required to provide AI capabilities.
  • the network element that provides the AI capability is the first communication device, so the request information can be determined by the first communication device itself.
  • the first communication device can determine the request information based on the second AI function requirement information.
  • the second AI can be Some or all of the sub-information included in the functional requirement information is used as the request information.
  • the second AI function requirement information reference may be made to the embodiment shown in FIG. 4 .
  • the network element that requires the UE to provide AI capabilities is, for example, a DU
  • the first communication device is, for example, a CU, a CU-CP, or a CU-CP2
  • the DU can send the request information to the first communication device, so that the first communication device can obtain the request information.
  • the DU can determine the request information based on the first AI function requirement information, for example, part or all of the sub-information included in the first AI function requirement information can be used as the request information.
  • the first AI function requirement information can refer to the embodiment shown in Figure 4.
  • the request information includes, for example, E sub-information, where E is a positive integer.
  • the request information may indicate one or more of the following: requesting (or expecting; or hoping) the AI function provided by the UE, the collaboration level corresponding to the AI function provided by the requested UE, the AI function provided by the requested UE.
  • the corresponding capability is to request the AI algorithm corresponding to the AI function provided by the UE, or to request the AI model corresponding to the AI function provided by the UE.
  • each sub-information in the E sub-information may indicate one or more items as described above. For example, one of the sub-information in the E sub-information is the fifth sub-information.
  • the fifth sub-information may indicate one or more of the following: the second AI function provided by the UE is requested, and the cooperation level corresponding to the second AI function provided by the UE is requested. , request the capability corresponding to the second AI function provided by the UE, request the AI algorithm corresponding to the second AI function provided by the UE, or request the AI model corresponding to the second AI function provided by the UE.
  • the collaboration level indicated by one sub-information in the E sub-information may be the collaboration level provided by the requesting UE for the AI function indicated by the sub-information.
  • the capability indicated by one sub-information in the E sub-information may be the capability that the UE is requested to provide for the AI function indicated by the sub-information.
  • the AI algorithm indicated by one sub-information in the E sub-information may be the AI algorithm provided by the requesting UE for the AI function indicated by the sub-information.
  • the AI model indicated by one sub-information in the E sub-information may be the AI model provided by the requesting UE for the AI function indicated by the sub-information.
  • items indicated by different sub-information may be the same, partially the same or completely different.
  • the second AI function in the embodiment of the present application and the second AI function in the embodiment shown in FIG. 4 may be the same AI function, or they may be different AI functions.
  • items indicated by different sub-information may be the same, partially the same or completely different.
  • one of the sub-information indicates the second AI function requested to be provided by the UE, and the capabilities corresponding to the second AI function provided by the requested UE; and the other sub-information indicates the third AI function provided by the requested UE, and the requesting UE
  • E sub-information the contents of the same item indicated by different sub-information may be the same or different.
  • each sub-information in the E sub-information indicates the AI function requested from the UE, and the AI functions indicated by different sub-information may be the same or different.
  • each sub-information in the E sub-information indicates the AI function requested to be provided by the UE, and different sub-information indicates different AI functions, it is equivalent to the E sub-information indicating E AI functions provided by the requested UE.
  • the AI function indicated by it may include at least one sub-function; and/or, the AI function indicated by another sub-information in the E sub-information may be one A sub-function included in the AI function.
  • the AI function indicated by another sub-information in the E sub-information may be one A sub-function included in the AI function.
  • the UE determines the third information according to the request information and the capability information of the UE.
  • the capability information of the UE includes, for example, the AI capability information of the UE.
  • the third information may include (or indicate) the value of the capability parameter corresponding to the AI function indicated by the request information (or in other words, the third information includes the capability parameter corresponding to the AI function provided by the UE); or, the third information may include ( Or, indicate) the value of the capability parameter corresponding to the AI function and collaboration level indicated by the request information (or in other words, the third information includes the capability parameter corresponding to the AI function and collaboration level provided by the UE); or, the third information may Include (or indicate) the value of the capability parameter corresponding to one or more of the AI functions, collaboration levels, capabilities, AI algorithms or AI models indicated by the request information (or, the third information includes the AI functions provided by the UE , collaboration level, capability, AI algorithm or capability parameter corresponding to the AI model); or, the third information indicates that the UE does not support providing the requested AI function.
  • the capability information includes, for example, F sub-information, where F is a positive integer.
  • the capability information may indicate the AI function supported by the UE.
  • each sub-information in the F sub-information may indicate one or more of the following: the AI function supported by the UE, the collaboration level corresponding to the AI function supported by the UE, The capabilities corresponding to the AI functions supported by the UE, the AI algorithms corresponding to the AI functions supported by the UE, or the AI models corresponding to the AI functions supported by the UE.
  • a sub-information may indicate one or more of the following: an AI function 1 supported by the UE, a collaboration level corresponding to the AI function 1 supported by the UE, a capability corresponding to the AI function 1 supported by the UE, an AI function supported by the UE The AI algorithm corresponding to 1, or the AI model corresponding to the AI function 1 supported by the UE.
  • one of the sub-information in the F sub-information is the sixth sub-information.
  • the sixth sub-information may indicate the first AI function supported by the UE, the cooperation level corresponding to the first AI function supported by the UE, and the first AI function supported by the UE.
  • the corresponding capability is the AI algorithm corresponding to the first AI function supported by the UE, or the AI model corresponding to the first AI function supported by the UE.
  • the first AI function in the embodiment of the present application and the first AI function in the embodiment shown in FIG. 4 may be the same AI function, or they may be different AI functions.
  • items indicated by different sub-information may be the same, partially the same or completely different.
  • contents of items indicated by different sub-information may be the same or different.
  • the AI function indicated by one sub-information in F sub-information may include at least one sub-function, that is, the AI function may be regarded as the total AI function, and the AI function also includes at least one sub-function; and/or, F sub-information
  • the AI function indicated by another sub-information in can be a sub-function included in one AI function.
  • the UE determines (or filters; or filters) the third information based on the capability information and the request information, which may include one or more of the methods A to F introduced in S402 of the embodiment shown in Figure 4, so it can Refer to the previous introduction and will not go into details here.
  • the UE sends the third information to the first communication device.
  • the first communication device receives the third information from the UE.
  • the third information may include (or indicate) the value of the capability parameter corresponding to the AI function indicated by the request information, or the third information may include (or indicate) the capability corresponding to the AI function and collaboration level indicated by the request information.
  • the value of the parameter regarding the implementation of the third information, reference may be made to S404 of the embodiment shown in FIG. 4 .
  • the third information determined by the UE in S502 is empty, or the third information cannot be determined, the third information may also indicate that the UE does not support providing the requested AI function.
  • the network element that requires the UE to provide AI capabilities is DU
  • the first communication device is, for example, CU, CU-CP, or CU-CP2
  • the first communication device may also send the first communication device to DU.
  • the DU can receive the third information from the first communication device, so that the DU obtains the AI capability information of the UE.
  • the UE can determine the AI capability information that is actually required to be provided by the UE, so that the UE can send the corresponding capability parameters to the network side without having to send capability parameters that the network side does not need. Redundant information is reduced and transmission overhead is saved. Moreover, the filtering process of AI capability information is performed on the UE side, so the UE side does not need to send it to the network side in advance.
  • the first information introduced in the embodiment shown in Figure 4 can further save transmission overhead.
  • FIG 6 shows a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • the communication device 600 may be the first communication device or the circuit system of the first communication device described in any of the embodiments shown in Figure 4 or Figure 5, and is used to implement the steps corresponding to the above method embodiments. Method for first communication device.
  • the communication device 600 may be the circuit system of the UE in any one of the embodiments shown in Figure 4 or Figure 5, used to implement the method corresponding to the UE in the above method embodiment.
  • one circuit system is a chip system.
  • the communication device 600 includes at least one processor 601 .
  • the processor 601 can be used for internal processing of the device to implement certain control processing functions.
  • processor 601 includes instructions.
  • processor 601 can store data.
  • different processors may be independent devices, may be located in different physical locations, and may be located on different integrated circuits.
  • different processors may be integrated into one or more processors, for example, on one or more integrated circuits.
  • communication device 600 includes one or more memories 603 for storing instructions.
  • the memory 603 may also store data.
  • the processor and memory can be provided separately or integrated together.
  • the communication device 600 includes a communication line 602 and at least one communication interface 604. Since the memory 603, the communication line 602 and the communication interface 604 are all optional, they are all indicated by dotted lines in FIG. 6 .
  • the communication device 600 may also include a transceiver and/or an antenna.
  • the transceiver may be used to send information to or receive information from other devices.
  • the transceiver may be called a transceiver, a transceiver circuit, an input/output interface, etc., and is used to implement the transceiver function of the communication device 600 through an antenna.
  • the transceiver includes a transmitter and a receiver.
  • the transmitter can be used to generate a radio frequency signal from a baseband signal
  • the receiver can be used to convert the radio frequency signal into a baseband signal.
  • the processor 601 may include a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. circuit.
  • CPU central processing unit
  • ASIC application specific integrated circuit
  • Communication line 602 may include a path that carries information between the above-mentioned components.
  • Communication interface 604 uses any device such as a transceiver for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), Cable access network, etc.
  • RAN radio access network
  • WLAN wireless local area networks
  • Cable access network etc.
  • the memory 603 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.
  • the memory 603 may exist independently and be connected to the processor 601 through the communication line 602. Alternatively, the memory 603 may also be integrated with the processor 601.
  • the memory 603 is used to store computer execution instructions for executing the solution of the present application, and is controlled by the processor 601 for execution.
  • the processor 601 is configured to execute computer execution instructions stored in the memory 603, thereby implementing the steps performed by the first communication device described in any one of the embodiments shown in Figure 4 or Figure 5, or to implement Figure 4 Or the steps performed by the terminal device described in any one of the embodiments shown in FIG. 5 .
  • the computer-executed instructions in the embodiments of the present application may also be called application codes, which are not specifically limited in the embodiments of the present application.
  • the processor 601 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 6 .
  • the communication device 600 may include multiple processors, such as the processor 601 and the processor 605 in FIG6 .
  • processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor.
  • the processor here may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).
  • the chip When the device shown in FIG. 6 is a chip, such as the chip of the first communication device or the chip of the UE, the chip includes a processor 601 (which may also include a processor 605), a communication line 602 and a communication interface 604. Optionally, this may include memory 603. Specifically, the communication interface 604 may be an input interface, a pin or a circuit, etc. Memory 603 may be a register, cache, etc. Processor 601 and processing The processor 605 may be a general CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the program execution of the communication method of any of the above embodiments.
  • Embodiments of the present application can divide the device into functional modules according to the above method examples.
  • each functional module can be divided into corresponding functional modules, or two or more functions can be integrated into one processing module.
  • the above integrated modules can be implemented in the form of hardware or software function modules.
  • the division of modules in the embodiment of the present application is schematic and is only a logical function division. In actual implementation, there may be other division methods.
  • Figure 7 shows a schematic diagram of a device.
  • the device 700 may be the first communication device or UE involved in the above method embodiments, or the first communication device 700.
  • the device 700 includes a sending unit 701, a processing unit 702 and a receiving unit 703.
  • the device 700 can be used to implement the steps performed by the first communication device or UE in the communication method of the embodiment of the present application.
  • the relevant features can refer to any one of the embodiments shown in Figures 4 or 5 above, and will not be repeated here.
  • the functions/implementation processes of the sending unit 701, the receiving unit 703 and the processing unit 702 in Figure 7 can be implemented by the processor 601 in Figure 6 calling computer execution instructions stored in the memory 603.
  • the function/implementation process of the processing unit 702 in Figure 7 can be realized by the processor 601 in Figure 6 calling the computer execution instructions stored in the memory 603.
  • the functions/implementation of the sending unit 701 and the receiving unit 703 in Figure 7 The process can be implemented through the communication interface 604 in Figure 6.
  • the functions/implementation processes of the sending unit 701 and the receiving unit 703 can also be implemented through pins or circuits.
  • the present application also provides a computer-readable storage medium, which stores a computer program or instructions.
  • the computer program or instructions When the computer program or instructions are run, the method executed by the first communication device or UE in the foregoing method embodiments is implemented. Methods.
  • the functions described in the above embodiments can be implemented in the form of software functional units and sold or used as independent products.
  • the technical solution of the present application essentially or contributes to the technical solution or the part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium and includes a number of instructions.
  • Storage media include: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk and other media that can store program code.
  • the computer program product includes: computer program code.
  • the computer program code When the computer program code is run on a computer, it causes the computer to execute the command executed by the first communication device or UE in any of the foregoing method embodiments. method of execution.
  • Embodiments of the present application also provide a processing device, including a processor and an interface; the processor is configured to execute the method executed by the first communication device or UE involved in any of the above method embodiments.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another, e.g., the computer instructions may be transferred from a website, computer, server, or data center Transmission to another website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means.
  • 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, data center, etc. that contains one or more available media integrated.
  • the available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media (eg, solid state disk (SSD)), etc.
  • the various illustrative logic units and circuits described in the embodiments of the present application can be programmed by general-purpose processors, digital signal processors (digital signal processors, DSPs), application specific integrated circuits (ASICs), and field programmable A field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to implement or operate the functions described.
  • the general-purpose processor may be a microprocessor.
  • the general-purpose processor may also be any conventional processor, controller, microcontroller or state machine.
  • a processor may also be implemented as a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration. accomplish.
  • the steps of the method or algorithm described in the embodiments of this application can be directly embedded in hardware, a software unit executed by a processor, or a combination of the two.
  • Software units can be stored in RAM, flash memory, ROM, erasable programmable read-only memory (erasable programmable read-only memory (EPROM), EEPROM, register, hard disk, removable disk, CD-ROM or any other form of storage media in this field.
  • the storage medium can be connected to the processor, so that the processor can read information from the storage medium and can store and write information to the storage medium.
  • the storage medium can also be integrated into the processor.
  • the processor and the storage medium can be installed in the ASIC, and the ASIC can be installed in the terminal device.
  • the processor and the storage medium may also be provided in different components in the terminal device.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device.
  • Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.
  • the first communication device or UE 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, other operations or operations may also be performed. A variation of the operation. 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.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本申请涉及一种通信方法及装置。第一通信装置接收第一信息，第一信息包括第一子信息，第一子信息用于指示终端设备支持的第一人工智能(artificial intelligence，AI)功能。第一通信装置根据第一信息确定第二信息，第二信息用于指示请求终端设备提供的AI功能。第一通信装置向终端设备发送第二信息，并接收来自终端设备的第三信息，第三信息包括第二信息指示的AI功能对应的能力参数。终端设备只需将网络侧实际需要的能力参数发送给网络侧，减少了冗余信息，节省了传输开销。

Description

一种通信方法及装置
相关申请的交叉引用
本申请要求在2022年09月24日提交中国国家知识产权局、申请号为202211168801.X、申请名称为“一种通信方法及装置”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；本申请要求在2023年08月30日提交中国国家知识产权局、申请号为202311103713.6、申请名称为“一种通信方法及装置”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
本申请涉及通信技术领域，尤其涉及一种通信方法及装置。
背景技术
人工智能(artificial intelligence，AI)技术是一种在20世纪50年代就已经提出，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，AI得到了越来越多的运用。目前第三代合作伙伴计划(3rd generation partnership project，3GPP)提出可将AI运用到新空口(new radio，NR)系统中，通过智能收集和分析数据，可以提升网络性能和用户体验。
如果基站需要用户设备(user equipment，UE)配合实现相应的AI功能，则基站可以首先查询UE的能力，UE接收该查询请求后可以向基站发送该UE支持的全部AI能力信息，该全部AI能力信息可包括UE支持的全部AI功能以及UE能够为每种AI功能提供的能力参数。但基站可能只需要UE的一部分AI能力，并不需要UE的全部AI能力。UE将全部AI能力信息都发送给基站，导致基站会接收较多的冗余信息，也增大了传输开销。
发明内容
本申请实施例提供一种通信方法及装置，用于降低终端设备发送能力信息的开销。
第一方面，提供第一种通信方法，该方法可由第一通信装置执行，或由包括第一通信装置功能的其他设备执行，或由芯片系统(或，芯片)或其他功能模块执行，该芯片系统或功能模块能够实现第一通信装置的功能，该芯片系统或功能模块例如设置在第一通信装置中。第一通信装置例如为接入网设备，或为CU，或为CU-CP，或为CU-CP2等。该方法包括：接收第一信息，所述第一信息包括第一子信息，所述第一子信息用于指示终端设备支持的第一AI功能；根据所述第一信息确定第二信息，所述第二信息用于指示请求所述终端设备提供的AI功能；向所述终端设备发送所述第二信息；接收来自所述终端设备的第三信息，所述第三信息包括所述第二信息指示的AI功能对应的能力参数。
本申请实施例中，第一通信装置可以根据终端设备支持的AI功能进行筛选(或者说，过滤)，以确定第二信息，第二信息可指示网络侧实际需要终端设备提供的AI功能，则终端设备根据第二信息向第一通信装置发送相应的能力参数即可。可见，本申请实施例中的终端设备不必向网络侧发送全部的AI能力参数，由于网络侧的筛选过程，使得终端设备只需将网络侧实际需要的能力参数发送给网络侧即可，减少了冗余信息，也节省了传输开销。
在一种可选的实施方式中，所述第一子信息还用于指示如下一项或多项：所述第一AI功能对应的协作等级；所述第一AI功能对应的能力；所述第一AI功能对应的AI算法；或，所述第一AI功能对应的AI模型。第一子信息可指示终端设备支持的第一AI功能以及指示第一AI功能对应的协作等级，使得对终端设备的能力的指示更为明确。
在一种可选的实施方式中，所述第二信息还用于指示如下一项或多项：请求所述终端设备提供的AI功能对应的协作等级；请求所述终端设备提供的AI功能对应的能力；请求所述终端设备提供的AI功能对应的AI算法；或，请求所述终端设备提供的AI功能对应的AI模型。
在一种可选的实施方式中，所述第三信息还包括如下一项或多项：所述第二信息指示的协作等级对应的能力参数；所述第二信息指示的能力对应的能力参数；所述第二信息指示的AI算法对应的能力参数；或，所述第二信息指示的AI模型对应的能力参数。
在一种可选的实施方式中，接收第一信息，包括：接收来自所述终端设备的所述第一信息；或，接 收来自第二通信装置的所述第一信息，所述第二通信装置为所述第一通信装置的相邻接入网设备，或为核心网设备。第一信息可以来自终端设备，也可以来自相邻接入网设备或核心网设备等，具体来源不做限制。
在一种可选的实施方式中，所述第一通信装置为接入网设备；或，所述第一通信装置为CU；或，所述第一通信装置为CU-CP；或，所述第一通信装置为CU-CP2；或，所述第一通信装置为LMF；或，所述第一通信装置为AMF。
在一种可选的实施方式中，所述第一通信装置为所述CU或所述CU-CP或所述CU-CP2，根据所述第一信息确定第二信息，包括：向DU发送所述第一信息，接收来自所述DU的所述第二信息；或，接收来自DU的第一AI功能需求信息，并根据所述第一AI功能需求信息以及所述第一信息确定所述第二信息，其中，所述第一AI功能需求信息包括第二子信息，所述第二子信息用于指示所述DU请求所述终端设备提供的第二AI功能；或，根据第二AI功能需求信息以及所述第一信息确定所述第二信息，其中，所述第二AI功能需求信息包括第三子信息，所述第三子信息用于指示所述第一通信装置请求所述终端设备提供的第三AI功能，或者，所述第三子信息用于指示所述第一通信装置请求所述终端设备提供的第三AI功能，以及还用于指示如下一项或多项：所述第三AI功能对应的协作等级，所述第三AI功能对应的能力，所述第三AI功能对应的AI算法，或，所述第三AI功能对应的AI模型。例如是DU需要终端设备支持AI功能，如果第一通信装置为CU或CU-CP或CU-CP2，则可由DU根据终端设备支持的AI功能进行筛选(或者说，过滤)，以确定第二信息；或者DU也可将DU的需求(例如第一AI功能需求信息)发送给第一通信装置，由第一通信装置根据DU的需求以及终端设备支持的AI功能进行筛选(或者说，过滤)，以确定第二信息。或者，也可能是第一通信装置需要终端设备支持AI功能，则第一通信装置可以根据第一通信装置的需求以及终端设备支持的AI功能进行筛选(或者说，过滤)，以确定第二信息。
在一种可选的实施方式中，所述第二子信息还用于指示如下一项或多项：所述第二AI功能对应的协作等级；所述第二AI功能对应的能力；所述第二AI功能对应的AI算法；或，所述第二AI功能对应的AI模型。
在一种可选的实施方式中，根据所述第一AI功能需求信息以及所述第一信息确定所述第二信息，包括如下一项或多项：所述第一AI功能与所述第二AI功能为同一AI功能，所述第一子信息还用于指示所述第一AI功能对应的协作等级为第一等级，所述第二子信息指示所述DU请求所述第二AI功能对应的协作等级为第二等级，如果所述终端设备支持所述第一等级包括支持所述第二等级，确定所述第二信息包括所述第一子信息；如果所述第一AI功能包括所述第二AI功能，确定所述第二信息包括所述第二子信息；或，如果所述第一AI功能与所述第二AI功能为同一AI功能，且所述第一信息未指示所述第一AI功能对应的协作等级，确定所述第二信息包括所述第二子信息。第一通信装置可以采用多种方式确定第二信息，较为灵活。
在一种可选的实施方式中，所述方法还包括：向所述DU发送所述第三信息。如果是DU需要终端设备支持AI功能，则第一通信装置可将第三信息发送给DU，使得DU明确终端设备所提供的AI功能。
在一种可选的实施方式中，所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、所述第四AI功能对应的AI模型、或所述第四AI功能对应的能力参数的值；或，所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。第三信息可包括多个子信息，其中每个子信息都可以包括终端设备提供的一种AI功能以及该AI功能所对应的能力参数的值，使得第三信息对于终端设备所提供的AI能力的指示更为明确。或者，第三信息可以包括多个子信息，其中每个子信息并不包括能力参数的值，而是第三信息还额外包括终端设备支持的能力参数的最大值，由此能够减小第三信息的开销。
在一种可选的实施方式中，所述能力参数包括如下一项或多项：所述终端设备的计算能力参数，所 述终端设备的能耗参数，所述终端设备的存储能力参数，所述终端设备的电量参数，所述终端设备的处理时延，所述终端设备支持的AI模型，或，所述终端设备支持的AI算法。除此之外，能力参数还可以包括其他相应的参数，具体不做限制。
在一种可选的实施方式中，所述第一AI功能包括至少一个子功能，或，所述第一AI功能为一个AI功能的子功能。一个子信息所指示的AI功能可以是一个子功能，或者也可以是包括至少一个子功能的AI功能。
第二方面，提供第二种通信方法，该方法可由终端设备执行，或由包括终端设备功能的其他设备执行，或由芯片系统(或，芯片)或其他功能模块执行，该芯片系统或功能模块能够实现终端设备的功能，该芯片系统或功能模块例如设置在终端设备中。该方法包括：接收来自第一通信装置的第二信息，所述第二信息用于指示请求所述终端设备提供的AI功能；向所述第一通信装置发送第三信息，所述第三信息包括所述第二信息指示的AI功能对应的能力参数。
在一种可选的实施方式中，所述第二信息还用于指示如下一项或多项：请求所述终端设备提供的AI功能对应的协作等级；请求所述终端设备提供的AI功能对应的能力；请求所述终端设备提供的AI功能对应的AI算法；或，请求所述终端设备提供的AI功能对应的AI模型。
在一种可选的实施方式中，所述第三信息还包括如下一项或多项：所述第二信息指示的协作等级对应的能力参数；所述第二信息指示的能力对应的能力参数；所述第二信息指示的AI算法对应的能力参数；或，所述第二信息指示的AI模型对应的能力参数。
在一种可选的实施方式中，所述方法还包括：向所述第一通信装置发送第一信息，所述第一信息包括第一子信息，所述第一子信息用于指示终端设备支持的第一AI功能，其中，所述第二信息与所述第一信息相关。
在一种可选的实施方式中，所述第一子信息还用于指示如下一项或多项：所述第一AI功能对应的协作等级；所述第一AI功能对应的能力；所述第一AI功能对应的AI算法；或，所述第一AI功能对应的AI模型。
在一种可选的实施方式中，所述第一AI功能包括至少一个子功能，或，所述第一AI功能为一个AI功能的子功能。
在一种可选的实施方式中，所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、所述第四AI功能对应的AI模型、或所述第四AI功能对应的能力参数的值；或，所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。
在一种可选的实施方式中，所述能力参数包括如下一项或多项：所述终端设备的计算能力参数，所述终端设备的能耗参数，所述终端设备的存储能力参数，所述终端设备的电量参数，所述终端设备的处理时延，所述终端设备支持的AI模型，或，所述终端设备支持的AI算法。
关于第二方面或各种可选的实施方式所带来的技术效果，可参考第一方面或相应实施方式的技术效果的介绍。
第三方面，提供第三种通信方法，该方法可由终端设备执行，或由包括终端设备功能的其他设备执行，或由芯片系统(或，芯片)或其他功能模块执行，该芯片系统或功能模块能够实现终端设备的功能，该芯片系统或功能模块例如设置在终端设备中。该方法包括：接收来自第一通信装置的请求信息，所述请求信息用于指示请求所述终端设备提供的AI功能；根据所述请求信息以及所述终端设备的能力信息确定第三信息，所述第三信息包括所述请求信息指示的AI功能对应的能力参数；向所述第一通信装置发送所述第三信息。通过本申请实施例的技术方案，可以由终端设备确定实际需要终端设备提供的AI能力信息，从而终端设备可以向网络侧发送对应的能力参数，而不必向网络侧发送网络侧所不需要的能力参数，从而减少了冗余信息，也节省了传输开销。而且对于终端设备能力信息的过滤过程在UE侧执行，则UE侧不必事先向网络侧发送如前文所介绍的第一信息，能够进一步节省传输开销。
在一种可选的实施方式中，所述请求信息还用于指示请求如下一项或多项：所述终端设备提供的AI功能对应的协作等级；所述终端设备提供的AI功能对应的能力；所述终端设备提供的AI功能对应的AI算法；或，所述终端设备提供的AI功能对应的AI模型。
在一种可选的实施方式中，所述第三信息还包括如下一项或多项：所述请求信息指示的协作等级对应的能力参数；所述请求信息指示的能力对应的能力参数；所述请求信息指示的AI算法对应的能力参数；或，所述请求信息指示的AI模型对应的能力参数。
在一种可选的实施方式中，所述请求信息包括第五子信息，所述第五子信息用于指示请求所述终端设备提供的第二AI功能，或者，所述第五子信息用于指示请求所述终端设备提供的第二AI功能，以及还用于指示请求如下一项或多项：所述第二AI功能对应的协作等级，所述第二AI功能对应的能力，所述第二AI功能对应的AI算法，或，所述第二AI功能对应的AI模型；和/或，所述能力信息包括第六子信息，所述第六子信息用于指示所述终端设备支持的第一AI功能，或者，所述第六子信息用于指示所述终端设备支持的第一AI功能，以及还用于指示如下一项或多项：所述第一AI功能对应的协作等级，所述第一AI功能对应的能力，所述第一AI功能对应的AI算法，或，所述第一AI功能对应的AI模型。请求信息的一种实现方式为，请求信息可包括一个或多个子信息，其中的每个子信息可指示请求终端设备提供的一种AI功能，或指示请求终端设备提供的一种AI功能以及该AI功能对应的协作等级。另外，能力信息的一种实现方式为，能力信息可包括一个或多个子信息，其中的每个子信息可指示终端设备支持的一种AI功能，或指示终端设备支持的一种AI功能以及该AI功能对应的协作等级。
在一种可选的实施方式中，根据所述请求信息以及所述终端设备的能力信息确定第三信息，包括：所述第一AI功能与所述第二AI功能为同一AI功能，所述第六子信息指示所述第一AI功能对应的协作等级为第一等级，所述第五子信息指示所述第二AI功能对应的协作等级为第二等级，如果所述终端设备支持所述第一等级包括支持所述第二等级，确定所述第三信息包括所述第五子信息；和/或，如果所述第一AI功能包括所述第二AI功能，确定所述第三信息包括所述第五子信息。终端设备确定第三信息的方式有多种，较为灵活。
在一种可选的实施方式中，所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、所述第四AI功能对应的AI模型、或所述第四AI功能对应的能力参数的值；或，所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。
在一种可选的实施方式中，所述能力参数包括如下一项或多项：所述终端设备的计算能力参数，所述终端设备的能耗参数，所述终端设备的存储能力参数，所述终端设备的电量参数，所述终端设备的处理时延，所述终端设备支持的AI模型，或，所述终端设备支持的AI算法。
关于第三方面的部分可选的实施方式所带来的技术效果，可参考对于第一方面的相应实施方式的技术效果的介绍。
第四方面，提供第四种通信方法，该方法可由第一通信装置执行，或由包括第一通信装置功能的其他设备执行，或由芯片系统(或，芯片)或其他功能模块执行，该芯片系统或功能模块能够实现第一通信装置的功能，该芯片系统或功能模块例如设置在第一通信装置中。第一通信装置例如为接入网设备，或为CU，或为CU-CP，或为CU-CP2等。该方法包括：向终端设备发送请求信息，所述请求信息用于指示请求所述终端设备提供的AI功能；接收来自所述终端设备的第三信息，所述第三信息包括所述请求信息指示的AI功能对应的能力参数。
在一种可选的实施方式中，所述请求信息还用于指示请求如下一项或多项：所述终端设备提供的AI功能对应的协作等级；所述终端设备提供的AI功能对应的能力；所述终端设备提供的AI功能对应的AI算法；或，所述终端设备提供的AI功能对应的AI模型。
在一种可选的实施方式中，所述第三信息还包括如下一项或多项：所述请求信息指示的协作等级对应的能力参数；所述请求信息指示的能力对应的能力参数；所述请求信息指示的AI算法对应的能力参 数；或，所述请求信息指示的AI模型对应的能力参数。
在一种可选的实施方式中，所述第一通信装置为接入网设备；或，所述第一通信装置为CU；或，所述第一通信装置为CU-CP；或，所述第一通信装置为LMF；或，所述第一通信装置为AMF。
在一种可选的实施方式中，所述第一通信装置为CU或CU-CP，所述方法还包括：接收来自DU的所述请求信息；或，根据第二AI功能需求信息确定所述请求信息，其中，所述第二AI功能需求信息用于指示请求所述终端设备提供的AI功能，或者，所述第二AI功能需求信息用于指示请求所述终端设备提供的AI功能，以及还指示如下一项或多项：所述终端设备提供的AI功能对应的协作等级，所述终端设备提供的AI功能对应的能力，所述终端设备提供的AI功能对应的AI算法，或，所述终端设备提供的AI功能对应的AI模型。
在一种可选的实施方式中，如果所述请求信息来自所述DU，所述方法还包括：向所述DU发送所述第三信息。
在一种可选的实施方式中，所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力参数的值、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型；或，所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。
在一种可选的实施方式中，所述能力参数包括如下一项或多项：所述终端设备的计算能力参数，所述终端设备的能耗参数，所述终端设备的存储能力参数，所述终端设备的电量参数，所述终端设备的处理时延，所述终端设备支持的AI模型，或，所述终端设备支持的AI算法。
关于第四方面或各种可选的实施方式所带来的技术效果，可参考第三方面或相应实施方式的技术效果的介绍。
第五方面，提供一种通信装置。所述通信装置可以为上述第一方面至第四方面中的任一方面所述的第一通信装置。所述通信装置具备上述第一通信装置的功能。所述通信装置例如为第一通信装置，或为包括第一通信装置的较大设备，或为第一通信装置中的功能模块，例如基带装置或芯片系统等。一种可选的实现方式中，所述通信装置包括基带装置和射频装置。另一种可选的实现方式中，所述通信装置包括处理单元(有时也称为处理模块)和收发单元(有时也称为收发模块)。收发单元能够实现发送功能和接收功能，在收发单元实现发送功能时，可称为发送单元(有时也称为发送模块)，在收发单元实现接收功能时，可称为接收单元(有时也称为接收模块)。发送单元和接收单元可以是同一个功能模块，该功能模块称为收发单元，该功能模块能实现发送功能和接收功能；或者，发送单元和接收单元可以是不同的功能模块，收发单元是对这些功能模块的统称。
在一种可选的实施方式中，所述收发单元(或，所述接收单元)，用于接收第一信息，所述第一信息包括第一子信息，所述第一子信息用于指示终端设备支持的第一AI功能；所述处理单元，用于根据所述第一信息确定第二信息，所述第二信息用于指示请求所述终端设备提供的AI功能；所述收发单元(或，所述发送单元)，用于向所述终端设备发送所述第二信息；所述收发单元(或，所述接收单元)，还用于接收来自所述终端设备的第三信息，所述第三信息包括所述第二信息指示的AI功能对应的能力参数。
在一种可选的实施方式中，所述收发单元(或，所述发送单元)，用于向终端设备发送请求信息，所述请求信息用于指示请求所述终端设备提供的AI功能；所述收发单元(或，所述接收单元)，用于接收来自所述终端设备的第三信息，所述第三信息包括所述请求信息指示的AI功能对应的能力参数。
在一种可选的实施方式中，所述通信装置还包括存储单元(有时也称为存储模块)，所述处理单元用于与所述存储单元耦合，并执行所述存储单元中的程序或指令，使能所述通信装置执行上述第一方面至第四方面中的任一方面所述的第一通信装置的功能。
第六方面，提供一种通信装置。所述通信装置可以为上述第一方面至第四方面中的任一方面所述的终端设备。所述通信装置具备上述终端设备的功能。所述通信装置例如为终端设备，或为包括终端设备 的较大设备，或为终端设备中的功能模块，例如基带装置或芯片系统等。一种可选的实现方式中，所述通信装置包括基带装置和射频装置。另一种可选的实现方式中，所述通信装置包括处理单元(有时也称为处理模块)和收发单元(有时也称为收发模块)。关于收发单元的实现方式可参考第七方面的介绍。
在一种可选的实施方式中，所述收发单元(或，所述接收单元)，用于接收来自第一通信装置的第二信息，所述第二信息用于指示请求所述终端设备提供的AI功能；所述收发单元(或，所述发送单元)，用于向所述第一通信装置发送第三信息，所述第三信息包括所述第二信息指示的AI功能对应的能力参数。
在一种可选的实施方式中，所述收发单元(或，所述接收单元)，用于接收来自第一通信装置的请求信息，所述请求信息用于指示请求所述终端设备提供的AI功能；所述处理单元，用于根据所述请求信息以及所述终端设备的能力信息确定第三信息，所述第三信息包括所述请求信息指示的AI功能对应的能力参数；所述收发单元(或，所述发送单元)，用于向所述第一通信装置发送所述第三信息。
在一种可选的实施方式中，所述通信装置还包括存储单元(有时也称为存储模块)，所述处理单元用于与所述存储单元耦合，并执行所述存储单元中的程序或指令，使能所述通信装置执行上述第一方面至第四方面中的任一方面所述的终端设备的功能。
第七方面，提供一种通信系统，包括第一通信装置以及终端设备，其中，第一通信装置用于执行如第一方面或第二方面所述的由第一通信装置执行的方法，终端设备用于执行如第一方面或第二方面所述的由终端设备执行的方法；或者，第一通信装置用于执行如第三方面或第四方面所述的由第一通信装置执行的方法，终端设备用于执行如第三方面或第四方面所述的由终端设备执行的方法。
第八方面，提供一种计算机可读存储介质，所述计算机可读存储介质用于存储计算机程序或指令，当其被运行时，使得上述各方面中第一通信装置或终端设备所执行的方法被实现。
第九方面，提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得上述各方面所述的方法被实现。
第十方面，提供一种芯片系统，包括处理器和接口，所述处理器用于从所述接口调用并运行指令，以使所述芯片系统实现上述各方面的方法。
附图说明
图1为接入网设备的一种结构示意图；
图2为AI在NR中应用的框架图；
图3为本申请实施例应用的一种网络架构的示意图；
图4为本申请实施例提供的一种通信方法的流程图；
图5为本申请实施例提供的另一种通信方法的流程图；
图6为本申请实施例提供的一种装置的示意图；
图7为本申请实施例提供的又一种装置的示意图。
具体实施方式
本申请实施例提供的技术方案可以应用于第四代移动通信技术(the 4th generation，4G)系统中，例如长期演进(long term evolution，LTE)系统，或可以应用于第五代移动通信技术(the 5th generation，5G)系统中，例如NR系统，或者还可以应用于下一代移动通信系统或其他类似的通信系统，例如第六代移动通信技术(the 6th generation，6G)系统等，具体的不做限制。另外本申请实施例提供的技术方案还可以应用于设备到设备(device-to-device，D2D)场景，例如NR-D2D场景等，或者可以应用于车联网(vehicle to everything，V2X)场景，例如NR-V2X场景，或智能驾驶、辅助驾驶、或智能网联车等领域。如果应用于D2D场景，则通信双方可以均为UE；如果应用于非D2D场景，则通信的一方可以是UE，另一方是网络设备(例如接入网设备)，或者通信双方可能均为网络设备。在下文的介绍过程中，以通信双方分别是网络设备和UE为例。
本申请实施例中，对于名词的数目，除非特别说明，表示“单数名词或复数名词”，即"一个或多个”。“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。字符“/”一般表示前后关联对象是一种“或”的关系。例如，A/B，表示： A或B。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a,b,或c中的至少一项(个)，表示：a,b,c,a和b,a和c,b和c,或a和b和c，其中a,b,c可以是单个，也可以是多个。
本申请实施例提及“第一”、“第二”等序数词是用于对多个对象进行区分，不用于限定多个对象的大小、内容、顺序、时序、优先级或者重要程度等。例如，第一资源单元和第二资源单元，可以是同一个资源单元，也可以是不同的资源单元，且，这种名称也并不是表示这两个资源单元的位置、大小、应用场景、优先级或者重要程度等的不同。另外，本申请所介绍的各个实施例中对于步骤的编号，只是为了区分不同的步骤，并不用于限定步骤之间的先后顺序。例如，S401可以发生在S402之前，或者可能发生在S402之后，或者也可能与S402同时发生。
以下，对本申请实施例中的部分用语或概念进行解释说明，以便于本领域技术人员理解。
1、本申请实施例中，终端设备是一种具有无线收发功能的设备，可以是固定设备，移动设备、手持设备(例如手机)、穿戴设备、车载设备，或内置于上述设备中的无线装置(例如，通信模块，调制解调器，或芯片系统等)。所述终端设备用于连接人，物，机器等，可广泛用于各种场景，例如包括但不限于以下场景：蜂窝通信、设备到设备通信(device-to-device，D2D)、车到一切(vehicle to everything，V2X)、机器到机器/机器类通信(machine-to-machine/machine-type communications，M2M/MTC)、物联网(internet of things，IoT)、虚拟现实(virtual reality，VR)、增强现实(augmented reality，AR)、工业控制(industrial control)、无人驾驶(self driving)、远程医疗(remote medical)、智能电网(smart grid)、智能家具、智能办公、智能穿戴、智能交通，智慧城市(smart city)、无人机、机器人等场景的终端设备。所述终端设备有时可称为用户设备(user equipment，UE)、终端、接入站、UE站、远方站、无线通信设备、或用户装置等等。为描述方便，后文将终端设备以UE为例进行说明。
2、本申请实施例中的网络设备，是无线网络中的设备，例如包括将终端设备接入到无线网络的无线接入网(radio access network，RAN)节点，或无线接入网设备。目前，一些RAN节点的举例为：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。在一种网络结构中，RAN节点也可以是指集中单元(central unit，CU)或者分布式单元(distributed unit，DU)，或者，RAN节点也可以是CU和DU组成的。CU和DU可以理解为是对RAN节点从逻辑功能角度的划分。CU和DU之间通过F1接口连接；CU可代表gNB，通过NG接口与核心网连接。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，可以节省成本，以及易于网络扩展。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(PHY)等部署在DU。本申请实施例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RAN节点也可以包括集中式单元控制面(CU-CP)节点和/或集中式单元用户面(CU-UP)节点，可参考图1。其中CU-CP负责控制面功能，主要包含RRC和PDCP-控制(control，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的控制面CU-CP还包括一种进一步切分的架构，即把现有的CU-CP进一步切分为CU-CP1和CU-CP2。其中CU-CP1包括各种无线资源管理功能，CU-CP2仅包括RRC功能和PDCP-C功能(即，控制面信令在PDCP层的基本功能)。CU-UP负责用户面功能，主要包含SDAP和PDCP-用户(user，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(bearer)。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。其中CU-CP和CU-UP通过E1接口连接。CU-CP可代表RAN节点，通过NG接口与核心网连接，通过F1-C(控制面)与DU连接。另外还有一种可能的实现是PDCP-C也设置在CU-UP。
本申请实施例中，用于实现网络设备功能的通信装置可以是网络设备，也可以是能够支持网络设备 实现该功能的装置，例如芯片系统，该装置可以被安装在网络设备中。在本申请实施例提供的技术方案中，以用于实现网络设备的功能的装置是网络设备为例，描述本申请实施例提供的技术方案。
3、目前3GPP提出可将AI运用到NR系统中，通过智能收集和分析数据，可以提升网络性能和用户体验。3GPP初步定义了AI在NR中应用的框架，可参考图2。其中，数据源(data source)可存储来自gNB、gNB-CU、gNB-DU、UE或其他管理实体的数据，数据源可作为AI模型训练和数据分析推理的数据库，例如图2中的“数据收集”可以表示数据源。模型训练主机(model training host)通过对数据源提供的训练数据(training data)进行分析，可给出最优的AI模型，例如图2中的“模型训练”方框可表示模型训练主机。模型推理主机(model inference host)使用该AI模型，基于数据源提供的数据，可对网络的运行给出基于AI的合理预测，或是指导网络做出策略调整，例如图2中的“模型推理”方框可表示模型推理主机。相关的策略调整，由行动(actor)实体统一规划，并发送给多个网络实体运行。同时，在网络应用了调整的策略后，网络的具体表现信息会被再次输入到数据源进行存储。
4、AI模型。
AI模型也即AI算法(或者AI算子)，是基于人工智能的原理构建的数学算法的统称，也是利用AI解决特定问题的基础。本申请实施例中对AI模型的类型并不限定。例如，AI模型可以是机器学习模型，也可以是深度学习模型，还可以是强化学习模型。
机器学习是实现人工智能的一种方法，该方法的目标是设计和分析一些让计算机可以自动“学习”的算法(即，模型)，所设计的算法可称为机器学习模型。机器学习模型是一类从数据中自动分析获得规律，并利用规律对未知数据进行预测的算法。机器学习模型有多种，例如根据模型训练时是否需要依赖训练数据对应的标签，可将机器学习模型分为有监督学习模型和无监督学习模型。
深度学习是机器学习研究过程中产生的一个新的技术领域。具体地，深度学习是机器学习中一种基于对数据进行深层次表征学习的方法，深度学习通过建立模拟人脑进行分析学习的神经网络来解释数据。由于在机器学习方法中，几乎所有的特征都需要通过行业专家确定，然后对特征进行编码。然而深度学习算法试图自己从数据中学习特征，根据深度学习思想设计的算法称为深度学习模型。
强化学习是机器学习中的一个特殊领域，是通过智能体(agent)和环境(environment)的相互作用，不断学习最优策略，做出序列决策，并获得最大回报的过程。通俗言之，强化学习是学习“做什么(即如何把当前的情景映射成动作)才能使得数值化的收益信号最大化”。智能体不会被告知应该采取什么动作，而是必须自己通过尝试去发现哪些动作会产生最丰厚的收益。强化学习与机器学习领域中的有监督学习和无监督学习不同，有监督学习是从外部提供的带标签的训练数据中进行学习的过程(任务驱动型)，无监督学习是寻找未标注的数据中隐含结构的过程(数据驱动型)。强化学习是通过“试探”寻找更优解的过程。智能体必须开发已有的经验来获取收益，同时也要进行试探，使得未来可以获得更好的动作选择空间(即从错误中学习)。根据强化学习设计的算法称为强化学习模型。
任何一个AI模型在用于解决特定的技术问题之前，都需要经过训练。AI模型的训练是指利用指定初始模型对训练数据进行计算，根据计算的结果采用一定的方法对初始模型中的参数进行调整，使得该模型逐渐学习到一定的规律，具备特定的功能的过程。经过训练后具有稳定功能的AI模型即可用于推理。AI模型的推理是利用训练完成的AI模型对输入数据进行计算，获得预测的推理结果(也可以称为输出数据)的过程。
5、AI功能，或者说，基于AI的用例(use case)。
当前3GPP针对AI在RAN侧的应用设计了一些基本的应用场景，例如包括信道状态信息(channel state information，CSI)-参考信号(reference signal，RS)反馈增强(feedback enhancement)、波束管理增强(beam management enhancement)或定位精度增强(positioning accuracy enhancements)等，下面简单介绍一下这几种场景。其中，如果UE支持某种AI场景，也可以认为是UE具有该AI功能。
(1)CSI-RS反馈增强。
CSI是通信链路的信道属性，是UE发送给接入网设备的信道质量信息。UE通过将下行CSI发送给接入网设备，从而接入网设备可以据此为UE选择更加合适的调制和编码方案(modulation and coding scheme，MCS)，以更好地适应变换的无线信道。UE发送的CSI可包括如下一项或多项：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)，SS/PCH块资源指示(SS/PBCH block resource indicator，SSBRI)，层指示(layer indicator，LI)，秩指示(rank lndicator，RI)，或，层1的参考信号接受功率(layer 1reference  signal receiver power，L1-RSRP)。其中，秩(rank)为多输入多输出(multi input multi output，MIMO)方案中天线矩阵中的秩，表示一个或多个并行的有效的数据流，RI用来指示物理下行共享信道(physical downlink shared channel，PDSCH)的有效的数据层数。
CSI-RS反馈增强又可以包括CSI压缩、CSI预测、CSI-RS配置信令减少等子场景。其中，CSI压缩又可以包括在空域、时域或频域中的至少一种域上的压缩。
以CSI-RS压缩为例，一种实现流程如下：
A1、接入网设备与UE先交互一个字典。
另外，接入网设备根据UE的能力以及接入网设备的要求等因素，提前训练好模型，该模型例如包括编码器(encoder)模型和对应的解码器(decoder)模型等。接入网设备可以向UE发送编码器模型，还可以向UE发送量化器(quantizer)等工具。其中，量化器用于对压缩后的信号进行量化处理。
A2、UE根据测量的下行信道矩阵以及编码器网络，可以得到第一矩阵。
例如，UE可将测量的下行信道矩阵输入该编码器网络，得到该编码器网络输出的第一矩阵。或者，UE可以对测量的下行信道矩阵进行预处理，再将预处理后的下行信道矩阵输入该编码器网络，得到该编码器网络输出的第一矩阵。进一步，UE可以利用已有的字典，将该第一矩阵进行压缩，以及可以利用量化器对压缩后的信号进行量化处理，再将量化结果发送给接入网设备。
A3、接入网设备根据字典、解码器网络以及来自UE的量化结果，逆向恢复得到原始的下行信道矩阵。
(2)波束管理增强。
基于AI的波束管理增强可以包括波束扫描矩阵预测、最优波束预测等子场景。波束管理增强的一种实现流程如下：
B1、初始模型的生成。通过一定数量的UE对同步信号和物理广播信道(physical broadcast channel，PBCH)块(synchronization signal and PBCH block，SSB)进行全向波束扫描，这些UE可以向接入网设备发送扫描结果，扫描结果例如包括每个波束上的接收信号质量信息。接入网设备可以根据这些UE的扫描结果进行训练，得到稀疏扫描的矩阵，或者称为稀疏模型，这种矩阵通常是小区所独有的。该稀疏模型可以包括较优的波束的信息。
B2、接入网设备将该稀疏模型发送给UE(可以考虑通过系统信息块(system information block，SIB)消息等方式发送)，UE可根据该稀疏矩阵执行P1阶段的波束扫描，且UE可将扫描结果发送给接入网设备，该扫描结果例如称为稀疏扫描结果。其中在P1阶段内，接入网设备在较宽的范围内通过波束发送参考信号，UE根据测量选择最佳波束，并将最佳波束的信息发送给接入网设备。
B3、接入网设备基于该稀疏扫描结果得到最优的波束。
例如，接入网设备可以基于波束对UE进行P2扫描，UE可以向接入网设备发送最佳波束的标识。P2扫描是指接入网设备在较窄的范围内通过较窄的波束发送参考信号，UE根据测量选择最佳波束，并将最佳波束的信息发送给接入网设备。
(3)定位精度增强。
基于AI的定位精度增强，主要是为了提升定位准确率。定位精度增强的一种实现流程如下：
C1、通过运营商控制的参考(reference)UE来收集原始数据。原始数据例如包括UE的坐标信息，和/或视线(line of sight，LOS)/非视线(non-line of sight，NLOS)状态等信息。
C2、位置管理功能(location management function，LMF)和接入网设备分别训练模型，LMF训练的模型可用于根据原始数据推理UE的最终定位信息(例如UE所在的经纬度等信息)，gNB训练的模型可用于根据原始数据推理LOS/NLOS判断结果。
6、AI功能的协作等级(collaboration level)。
考虑到AI功能的应用(例如AI模型的部署)，以及考虑到UE和网络侧之间的交互等因素，目前可包括三种协作等级，分别为等级0(level 0)、等级1(level 1)和等级2(level 2)，下面分别介绍。
level 0，也可称为协作等级0，为无协作(no collaboration)等级。
在level 0下，接入网设备侧的AI模型对UE是完全不可见的，AI模型的训练和推理等过程都在接入网设备内部完成，对空口也无影响。
level 1，也可称为协作等级1，无模型交互的基于信令的协作(signaling-based collaboration without model transfer)等级。
在level 1下，接入网设备通过向UE发送字典的方式，使得UE能够协助接入网设备进行AI推理，对空口有一定的影响。UE内部也可以部署AI模型，UE可以根据UE部署的AI模型和字典来对下行信道矩阵进行压缩编码。UE和接入网设备可以联合训练AI模型，例如通过联邦学习的方式来训练。在空口上，UE与接入网设备之间不会直接传输AI模型，但可以传输AI模型的相关参数。此外，考虑到AI模型的部署，level 1也可以进一步细分为level 1A和level 1B。
level 1A，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)。在level 1A下，AI模型可以部署在接入网设备或UE中，即，AI模型为单侧部署。
level 1B，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)。在level 1A下，接入网设备和UE可以分别部署AI模型，即，AI模型为双侧部署。
level 2，也可称为协作等级2，有模型交互的基于信令的协作(signaling-based collaboration with model transfer)等级。
在level 2下，接入网设备和UE都可以具有AI功能，例如接入网设备和UE可以分别部署AI模型，接入网设备和UE可以各自根据部署的AI模型进行推理等过程。在空口上，接入网设备与UE能够直接传输AI模型。
除了如上三种协作等级外还可以包括其他协作等级，例如未来的通信系统还可能支持一些协作等级，本申请实施例不限制。
示例性地，图3给出了本申请实施例适用的一种通信网络架构。第一通信装置与UE能够通信，例如该UE可以向第一通信装置发送该UE的AI能力信息。第一通信装置例如为接入网设备；或者，第一通信装置为接入网设备包括的功能模块，例如CU，或CU-CP，或CU-CP2等；或者，第一通信装置为包括接入网设备的较大设备。该接入网设备例如为前述的RAN节点，关于该RAN节点以及UE的介绍可参考前文。或者，第一通信装置例如为核心网设备；或者第一通信装置为核心网设备包括的功能模块；或者，第一通信装置为包括核心网设备的较大设备。该核心网设备例如为LMF或接入与移动管理功能(access and mobility management function，AMF)等。
为了更好地介绍本申请实施例，下面结合附图介绍本申请实施例所提供的方法。本申请的各个实施例对应的附图中，凡是用虚线表示的步骤均为可选的步骤。
本申请实施例提供一种通信方法，请参见图4，为该方法的流程图。该方法可应用于图3所示的网络架构，例如该方法所涉及的UE即为图3中的UE，该方法所涉及的第一通信装置即为图3中的第一通信装置。
S401、UE向第一通信装置发送第一信息，相应的，第一通信装置接收来自UE的第一信息。或者，第二通信装置向第一通信装置发送第一信息，相应的，第一通信装置接收来自第二通信装置的第一信息。第二通信装置例如为第一通信装置的相邻接入网设备，或为核心网设备等。图4中，以第一信息来自UE为例。
第一信息也可称为AI能力支持信息，或者也可以有其他名称。例如，第一信息包括M个子信息，M为正整数。可选的，第一信息可指示如下一项或多项：UE支持的AI功能，UE支持的AI功能所对应的协作等级，UE支持的AI功能所对应的能力，UE支持的AI功能所对应的AI算法，或，UE支持的AI功能所对应的AI模型。例如，M个子信息中的每个子信息可以指示如上所述的一项或多项，例如M个子信息中的一个子信息为第一子信息，第一子信息可指示如下一项或多项：UE支持的第一AI功能，UE支持的第一AI功能所对应的协作等级，UE支持的第一AI功能所对应的能力，UE支持的第一AI功能所对应的AI算法，或，UE支持的第一AI功能所对应的AI模型。本申请的各个实施例中，AI功能或AI子功能对应的能力，可以包括与AI模型和/或AI业务相关的能力，例如包括训练、推理、或监控等能力中的一项或多项。其中，“训练”是指网络设备支持AI功能或AI子功能对应的AI模型的训练；“推理”是指网络设备支持AI功能或子功能对应的AI模型的推理；“监控”是指网络设备支持AI功能或子功能对应的AI模型的监控。
M个子信息中，不同的子信息所指示的项可能相同、部分相同或完全不同。例如，M个子信息中的每个子信息可以指示UE支持的一个AI功能以及该AI功能对应的协作等级；或者，M个子信息中有部分子信息中的每个子信息可指示UE支持的一个AI功能以及该AI功能对应的协作等级，而剩余子 信息中的每个子信息指示UE支持的一个AI功能，而不指示协作等级。例如，M个子信息中的一个子信息为第一子信息，第一子信息可指示UE支持的第一AI功能，以及指示第一AI功能对应的协作等级。其中，M个子信息中的一个子信息所指示的协作等级，可以是UE对于该子信息指示的AI功能所能够支持的协作等级。M个子信息中的一个子信息所指示的能力，可以是请求UE对于该子信息指示的AI功能所能够支持的能力。M个子信息中的一个子信息所指示的AI算法，可以是请求UE对于该子信息指示的AI功能所能够支持的AI算法。M个子信息中的一个子信息所指示的AI模型，可以是请求UE对于该子信息指示的AI功能所能够支持的AI模型。
M个子信息中，不同的子信息所指示的相同项的内容可能相同或不同。例如M个子信息中的每个子信息均指示AI功能，不同的子信息指示的AI功能可以相同，或者也可以不同。其中，如果M个子信息中的每个子信息均指示AI功能，且不同的子信息指示的AI功能不同，则相当于M个子信息可指示UE支持的M个AI功能。
M个子信息中的一个子信息所指示的AI功能，可以包括至少一个子功能，即，该AI功能可以视为总AI功能，该AI功能还包括至少一个子功能；和/或，M个子信息中的另一个子信息所指示的AI功能，可以是一个AI功能所包括的一个子功能。例如一种AI功能为CSI-RS反馈增强功能，可以简称为CSI功能，可用“CSI”表示。CSI功能可以包括至少一个子功能，例如其中一个子功能为CSI-1，其中另一个子功能为CSI-2，其中又一个子功能为CSI-3。其中，CSI-1功能例如为CSI压缩功能，CSI-2功能例如为CSI预测功能，CSI-3功能例如为CSI-RS配置信令减少功能。又例如，另一种AI功能为BM功能，BM功能例如为波束管理功能，该波束管理功能例如为前述的波束管理增强功能，可用“BM”表示。再例如，又一种AI功能为定位功能，例如PA功能，该PA功能例如为前述的定位精度增强功能，可用“PA”表示。
例如第一信息指示UE支持的AI功能，则第一信息可以指示UE支持的[AI功能]和UE支持的[子功能]，例如M个子信息中的一个子信息可以指示[AI功能1]，M个子信息中的另一个子信息可以指示[子功能1]。例如，M个子信息中的子信息1指示[CSI-1]，M个子信息中的子信息2指示[CSI-2]，M个子信息中的子信息3指示[BM]。或者，第一信息可以指示UE支持的[AI功能]而不指示UE支持的[子功能]，例如，M个子信息中的子信息1指示[CSI]，M个子信息中的子信息2指示[BM]。或者，第一信息可以指示UE支持的[子功能]而不指示UE支持的[AI功能]，例如，M个子信息中的子信息1指示[CSI-1]，M个子信息中的子信息2指示[CSI-2]。
又例如，第一信息指示支持的AI功能以及UE支持的AI功能所对应的协作等级，则第一信息可以指示如下一项或多项：UE支持的[AI功能]，UE支持的[子功能]，UE支持的[AI功能，协作等级]，或，UE支持的[子功能，协作等级]。例如，M个子信息可包括如下一种或多种子信息：指示[AI功能1]的子信息，指示[子功能1]的子信息，指示[AI功能1，协作等级]的子信息，或，指示[子功能1，协作等级]的子信息。例如，M个子信息中的子信息1指示[CSI-1，协作等级1]，M个子信息中的子信息2指示[CSI-2，协作等级1]，M个子信息中的子信息3指示[BM，协作等级2]。又例如，M个子信息中的子信息1指示[CSI-1]，M个子信息中的子信息2指示[CSI-2]，M个子信息中的子信息3指示[BM，协作等级2]。
又例如，第一信息指示支持的AI功能、UE支持的AI功能所对应的协作等级、UE支持的AI功能所对应的能力、UE支持的AI功能所对应的AI算法、或UE支持的AI功能所对应的AI模型中的一项或多项，举例来说，第一信息中的一个子信息1可以指示(或，包括)如下一项或多项：AI功能[CSI-RS反馈增强功能，波束管理，定位]，AI子功能[CSI-1，CSI-2]，协作等级[协作等级0/协作等级1A/协作等级1B/协作等级2]，AI子功能对应的能力[训练，推理，监控]，AI算法[标识(identifier，ID)s]，或，AI模型[IDs]。
其中，上述的每个中括号(即，[])内的各个元素之间的关系可以是“和/或”的关系，或者理解为是包括其中一项或多项的关系。例如，子信息1指示AI功能[CSI-RS反馈增强功能，波束管理，定位]，可理解为，子信息1指示的AI功能可包括CSI-RS反馈增强功能、波束管理、或定位中的一项或多项。
S402、第一通信装置根据第一信息确定第二信息。第二信息可指示如下一项或多项：请求(或，期望；或，希望)该UE提供的AI功能，请求(或，期望；或，希望)该UE提供的AI功能对应的协作等级，请求(或，期望；或，希望)该UE提供的AI功能所对应的能力，请求(或，期望；或，希 望)该UE提供的AI功能所对应的AI算法，或，请求(或，期望；或，希望)该UE提供的AI功能所对应的AI模型。
可理解为，第二信息可指示网络侧实际需要该UE提供的AI能力。
第一通信装置根据第一信息确定第二信息，可能有多种方式，如下举例介绍。
1、第一通信装置确定第二信息的第一种方式。
可选的，需要该UE提供AI能力的网元例如为DU，而第一通信装置例如为CU，或CU-CP，或CU-CP2，那么第一通信装置根据第一信息确定第二信息的一种方式为，第一通信装置向DU发送第一信息，DU可将确定的第二信息发送给第一通信装置，从而第一通信装置就确定了第二信息。在这种情况下，是由DU得到第二信息，例如DU可以根据第一AI功能需求信息以及第一信息来确定第二信息，第一AI功能需求信息可指示DU需要UE提供的AI能力。本申请的各个实施例中，需要该UE提供AI能力的网元例如包括接入网网元和/或核心网网元，接入网网元例如接入网设备，或者DU等；核心网网元例如包括LMF和/或AMF，或者还可能包括其他核心网网元。在本申请各个实施例的示例中，以需要该UE提供AI能力的网元为DU为例，但实际不限于此，即，需要该UE提供AI能力的网元也可以由DU替换为其他网元。
第一AI功能需求信息例如包括N个子信息，N为正整数。可选的，第一AI功能需求信息可指示如下一项或多项：DU请求(或，期望；或，希望)UE提供的AI功能，DU请求UE提供的AI功能所对应的协作等级，DU请求UE提供的AI功能所对应的能力，DU请求UE提供的AI功能所对应的AI算法，或，DU请求UE提供的AI功能所对应的AI模型。例如第一AI功能需求信息指示DU请求UE提供的AI功能，N个子信息中的每个子信息可以指示DU请求UE提供的一个AI功能，例如N个子信息中的一个子信息为第二子信息，第二子信息可指示DU请求UE提供的第二AI功能。N个子信息中，不同的子信息所指示的项可能相同、部分相同或完全不同。另外E个子信息中，不同的子信息所指示的相同项的内容可能相同或不同。对此可参考S401中对于M个子信息的介绍。
N个子信息中的一个子信息所指示的AI功能，可以包括至少一个子功能；和/或，N个子信息中的另一个子信息所指示的AI功能，可以是一个AI功能所包括的一个子功能。关于这部分内容的介绍以及进一步的举例等内容，可参考S401中对于第一信息的介绍。
DU根据第一AI功能需求信息以及第一信息确定(或者说，过滤；或者，筛选)第二信息，可以有多种实现方式。下文给出一些举例，但并不限于下文的举例。DU可以根据如下的方式A～方式F中的一种或多种方式来确定第二信息。
方式A、如果N个子信息与M个子信息有交集，该交集包括一个或多个子信息，那么DU可以确定第二信息包括该交集。
例如，第一AI功能需求信息包括子信息1和子信息2，子信息1指示[CSI-1，协作等级1]，子信息2指示[BM，协作等级2]；第一信息包括子信息3、子信息4和子信息5，子信息3指示[CSI-1，协作等级1]，子信息4指示[CSI-3，协作等级1]，子信息5指示[BM，协作等级2]。其中，子信息1与子信息3相同，子信息2与子信息5相同，因此子信息1和子信息2为第一AI功能需求信息和第一信息的交集，因此DU可以确定第二信息包括子信息1和子信息2。
方式B、如果第一AI功能需求信息与第一信息有不完全重合的子信息，可根据UE对协作等级的支持情况确定第二信息。
例如，第一信息包括前述的第一子信息，第一AI功能需求信息包括前述的第二子信息。第一子信息指示UE支持的第一AI功能，以及指示第一AI功能对应的协作等级为第一等级；第二子信息指示DU请求UE提供的第二AI功能，以及指示第二AI功能对应的协作等级为第二等级。如果第一AI功能与第二AI功能为同一AI功能，而第一等级与第二等级不同，则表明第一子信息与第二子信息为不完全重合的子信息。那么，如果UE支持第一等级包括支持第二等级，或者理解为，UE只要能够支持第一等级就能够支持第二等级，那么第二信息可以包括第一子信息。例如第一等级高于第二等级，如果规定支持高协作等级的UE也能够支持低协作等级，则UE只要能够支持第一等级就能够支持第二等级。
或者，如果UE支持第一等级不包括支持第二等级，或者理解为，UE具有支持第一等级的能力时，并不表明UE也具有支持第二等级的能力，那么第二信息可以不包括第一子信息也不包括第二子信息。例如第一等级低于第二等级，如果规定支持低协作等级的UE不一定能支持高协作等级，则UE支持第一等级时并不一定能支持第二等级。又例如，第一等级高于第二等级，但如果规定高协作等级的UE不 支持(或不一定支持)低协作等级，则UE支持第一等级时也并不一定能支持第二等级。
举例来说，第一AI功能需求信息包括子信息1和子信息2，子信息1指示[CSI-1，协作等级1]，子信息2指示[BM，协作等级2]}；第一信息包括子信息3～子信息5，子信息3指示[CSI-1，协作等级2]，子信息4指示[CSI-3，协作等级1]，子信息5指示[BM，协作等级2]。其中子信息2与子信息5相同，子信息1与子信息3为不完全重合的子信息。例如协作等级2高于协作等级1，如果相关标准中规定高协作等级的AI功能可以支持低协作等级的AI功能，则第二信息可包括子信息1和子信息5。或者，如果相关标准中指出高协作等级的AI功能不可以支持低协作等级的AI功能，则第二信息可包括子信息5而不包括子信息3。
方式C、若第一信息中的一个子信息指示完整AI功能(或者说，总AI功能，即，该AI功能包括至少一个子功能)，而第一AI功能需求信息中的一个子信息指示该AI功能的一个AI子功能，则第二信息可包括第一AI功能需求信息中的该子信息。
例如第一信息包括前述的第一子信息，第一AI功能需求信息包括前述的第二子信息。第一子信息指示UE支持的第一AI功能，可选还指示第一AI功能对应的协作等级为第一等级；第二子信息指示DU请求UE提供的第二AI功能，可选还指示第二AI功能对应的协作等级为第二等级。如果第一AI功能包括第二AI功能，或者说，第二AI功能是第一AI功能的一个子功能，那么第二信息可包括第二子信息。
举例来说，第一AI功能需求信息包括子信息1，子信息1指示[CSI-1，协作等级1]；第一信息包括子信息2～子信息4，子信息2指示[CSI，协作等级1]，子信息3指示[CSI-3，协作等级2]，子信息4指示[BM，协作等级2]。其中，子信息2指示的是CSI功能，而子信息1指示的是CSI功能的一个子功能(CSI-1)，则第二信息可以包括子信息1。
方式D、若第一AI功能需求信息中的一个子信息指示完整AI功能(或者说，总AI功能，即，该AI功能包括至少一个子功能)，而第一信息中的一个子信息指示该AI功能的一个AI子功能，则第二信息可包括第一信息中的该子信息。此时，虽然UE不能提供DU所需的完整AI功能，但能够提供DU所需的一部分AI功能。
例如第一信息包括前述的第一子信息，第一AI功能需求信息包括前述的第二子信息。第一子信息指示UE支持的第一AI功能，可选还指示第一AI功能对应的协作等级为第一等级；第二子信息指示DU请求UE提供的第二AI功能，可选还指示第二AI功能对应的协作等级为第二等级。如果第二AI功能包括第一AI功能，或者说，第一AI功能是第二AI功能的一个子功能，那么第二信息可包括第一子信息。
举例来说，第一信息包括子信息1，子信息1指示[CSI-1，协作等级1]；第一AI功能需求信息包括子信息2～子信息4，子信息2指示[CSI，协作等级1]，子信息3指示[CSI-3，协作等级2]，子信息4指示[BM，协作等级2]。其中，子信息2指示的是CSI功能，而子信息1指示的是CSI功能的一个子功能(CSI-1)，则第二信息可以包括子信息1。
再举例来说，第一AI功能需求信息包括子信息1和子信息2，子信息1指示[CSI，协作等级0和协作等级2，推理和训练，[AI算法1，AI模型1]]，子信息2指示[波束管理，协作等级2，训练和推理，[AI算法1，AI模型1和AI模型2]，[AI算法2，AI模型2]]。第一信息包括子信息3和子信息4，子信息3指示[CSI-1，协作等级0，推理，[AI算法1，AI模型1和AI模型2]]，子信息4指示[波束管理，协作等级0，推理，[AI算法2，AI模型2]]。其中，CSI-1是CSI的一个子功能，则第二信息可以包括[CSI-1，协作等级0，推理，[AI算法1，AI模型1]]。其中，本示例也可以作为方式B的示例。本申请实施例中的方式A至方式F可以分别单独应用，或者其中的任意两种或多种方式也可以结合应用。
方式E、如果第一信息中的某个子信息未指示协作等级，则可默认UE对于该子信息所指示的AI功能是能够支持全部协作等级。
例如第一信息包括前述的第一子信息，第一AI功能需求信息包括前述的第二子信息。第一子信息指示UE支持的第一AI功能，但并未指示第一AI功能对应的协作等级；第二子信息指示DU请求UE提供的第二AI功能，可选还指示第二AI功能对应的协作等级为第二等级。如果第一AI功能与第二AI功能为同一AI功能，那么第二信息可以包括第二子信息。
举例来说，第一AI功能需求信息包括子信息1和子信息2，子信息1指示[CSI-1，协作等级1]，子信息2指示[BM，协作等级2]；第一信息包括子信息3和子信息4，子信息3指示[CSI-1]，子信息4 指示[BM，协作等级2]。其中，子信息2和子信息4相同，另外，子信息2并未指示CSI-1对应的协作等级，表明UE对于CSI-1能够支持全部协作等级，则对于协作等级1也就是支持的。因此第二信息可以包括子信息1和子信息2。
方式F、如果第一AI功能需求信息和第一信息没有交集，则第二信息为空，或者，无法得到第二信息。
例如第一AI功能需求信息包括子信息1，子信息1指示[CSI-1，协作等级1]；第一信息包括子信息2和子信息3，子信息2指示[CSI-2，协作等级1]，子信息3指示[BM，协作等级2]，可见，第一AI功能需求信息包括的子信息与第一信息包括的子信息无交集，因此第二信息为空，或者无法得到第二信息。
或者，方式F也可以实现为，如果方式A～方式E均不满足，则第二信息为空，或者，无法得到第二信息。
2、第一通信装置确定第二信息的第二种方式。
可选的，需要该UE提供AI能力的网元例如为DU，而第一通信装置例如为CU，或CU-CP，或CU-CP2，那么第一通信装置根据第一信息确定第二信息的一种方式为，DU向第一通信装置发送第一AI功能需求信息，第一通信装置可根据该第一AI功能需求信息以及第一信息确定第二信息。在这种情况下，是由第一通信装置得到第二信息，关于第一通信装置根据第一AI功能需求信息以及第一信息确定第二信息的方式，可参考上文中DU确定第二信息的方式的介绍。
3、第一通信装置确定第二信息的第三种方式。
可选的，需要该UE提供AI能力的网元例如为CU、CU-CP或CU-CP2，而第一通信装置例如为CU、CU-CP、或CU-CP2，可理解为，需要该UE提供AI能力的网元为第一通信装置，那么第一通信装置根据第一信息确定第二信息的一种方式为，第一通信装置可根据第二AI功能需求信息以及第一信息确定第二信息。第二AI功能需求信息可指示如下一项或多项：第一通信装置需要UE提供的AI能力，第一通信装置需要该UE提供的AI功能对应的协作等级，第一通信装置需要该UE提供的AI功能所对应的能力，第一通信装置需要该UE提供的AI功能所对应的AI算法，或，第一通信装置需要该UE提供的AI功能所对应的AI模型。
第二AI功能需求信息例如包括K个子信息，K为正整数，K个子信息中的每个子信息可指示如下一项或多项：第一通信装置需要UE提供的AI能力，第一通信装置需要该UE提供的AI功能对应的协作等级，第一通信装置需要该UE提供的AI功能所对应的能力，第一通信装置需要该UE提供的AI功能所对应的AI算法，或，第一通信装置需要该UE提供的AI功能所对应的AI模型。可选的，第二AI功能需求信息指示第一通信装置请求UE提供的AI功能，那么，K个子信息中的每个子信息可以指示第一通信装置请求UE提供的一个AI功能，例如K个子信息中的一个子信息为第三子信息，第三子信息可指示第一通信装置请求UE提供的第三AI功能。
K个子信息中，不同的子信息所指示的项可能相同、部分相同或完全不同。另外K个子信息中，不同的子信息所指示的相同项的内容可能相同或不同。对此可参考S401中对于M个子信息的介绍。
K个子信息中的一个子信息所指示的AI功能，可以包括至少一个子功能；和/或，K个子信息中的另一个子信息所指示的AI功能，可以是一个AI功能所包括的一个子功能。关于这部分内容的介绍以及进一步的举例等内容，可参考S401中对于第一信息的介绍。
关于第一通信装置根据第二AI功能需求信息以及第一信息确定第二信息的方式，可参考上文中DU确定第二信息的方式的介绍。
如上介绍了第一通信装置根据第一信息确定第二信息的几种方式，除了如上方式外，第一通信装置根据其他方式确定第二信息的方案也在本申请实施例的保护范围内。
其中，如果第一通信装置或DU确定的第二信息为空，或者第一通信装置或DU并未确定第二信息，则可以不必执行S403和S404。
S403、第一通信装置向UE发送第二信息。相应的，UE接收来自第一通信装置的第二信息。
S404、UE向第一通信装置发送第三信息。相应的，第一通信装置接收来自UE的第三信息。第三信息可包括(或，指示)如下一项或多项：第二信息指示的AI功能对应的能力参数的值(或者说，第三信息可包括UE提供的AI功能对应的能力参数)，第二信息指示的协作等级对应的能力参数的值(或者，第三信息可包括UE提供的AI功能的协作等级所对应的能力参数)，第二信息指示的能力对应的能 力参数的值(或者，第三信息可包括UE提供的AI功能对应的能力所对应的能力参数)，第二信息指示的AI算法对应的能力参数的值(或者，第三信息可包括UE提供的AI功能对应的AI算法所对应的能力参数)，或，第二信息指示的AI模型对应的能力参数的值(或者，第三信息可包括UE提供的AI功能对应的AI模型所对应的能力参数)。
可选的，能力参数可以包括如下一项或多项：计算能力参数，UE的存储能力参数，UE的电量参数，UE的处理时延，UE支持的AI模型，能耗参数，或，UE支持的AI算法。
例如，第三信息可包括H个子信息，H为正整数。H个子信息中的每个子信息可指示如下一项或多项：第二信息指示的AI功能对应的能力参数的值，第二信息指示的协作等级对应的能力参数的值，第二信息指示的能力对应的能力参数的值，第二信息指示的AI算法对应的能力参数的值，或，第二信息指示的AI模型对应的能力参数的值。H个子信息中，不同的子信息所指示的项可能相同、部分相同或完全不同。H个子信息中，不同的子信息所指示的项的内容可能相同或不同。对此可参考S401中对于M个子信息的相关介绍。
作为一种可选的实施方式，H个子信息中的每个子信息都可以指示如上一段所述的一项或多项，另外，第三信息还可指示UE提供的AI功能，那么，H个子信息中的部分或全部子信息中的每个子信息可以指示如下一项或多项：UE提供的一个AI功能，该AI功能对应的协作等级，该AI功能对应的能力，该AI功能对应的AI算法，该AI功能对应的AI模型，或，该AI功能对应的能力参数的值。例如H个子信息中的一个子信息为第四子信息，第四子信息可指示如下一项或多项：UE提供的第四AI功能，第四AI功能对应的协作等级，第四AI功能对应的能力，第四AI功能对应的AI算法，第四AI功能对应的AI模型，或，第四AI功能对应的能力参数的值。其中，H个子信息中，不同的子信息指示的项可以相同，例如均指示UE提供的一个AI功能，以及该AI功能对应的协作等级；或者，不同的子信息指示的项也可以不同，例如H个子信息中的一个子信息指示UE提供的一个AI功能，以及该AI功能对应的协作等级，而H个子信息中的另一个子信息指示UE提供的一个AI功能，该AI功能对应的能力，以及该AI功能对应的AI算法，但并不指示该AI功能对应的协作等级。
举例来说，H个子信息中的每个子信息都可以指示UE对于该子信息指示的AI功能提供的能力参数的值，这种方式对于每个AI功能的能力参数的指示较为清晰。另外，第三信息还可指示UE提供的AI功能，那么，H个子信息中的每个子信息可以指示UE提供的一个AI功能以及对应的能力参数的值，例如H个子信息中的一个子信息为第四子信息，第四子信息可指示UE提供的第四AI功能以及第四AI功能对应的能力参数的值。
或者，第三信息还可指示UE提供的AI功能以及UE提供的AI功能所对应的协作等级，那么H个子信息中的每个子信息可以指示UE提供的一个AI功能、该AI功能对应的协作等级、以及该AI功能对应的能力参数的值；或者，H个子信息中有部分子信息中的每个子信息可指示UE提供的一个AI功能、该AI功能对应的协作等级、以及该AI功能对应的能力参数的值，而剩余子信息中的每个子信息指示UE提供的一个AI功能以及该AI功能对应的能力参数的值，而不指示协作等级。例如H个子信息中的一个子信息为第四子信息，第四子信息可指示UE提供的第四AI功能、第四AI功能对应的协作等级、以及第四AI功能对应的能力参数的值。其中，H个子信息中的一个子信息所指示的协作等级，可以是UE对于该子信息指示的AI功能所支持的协作等级。
例如，第二信息包括子信息1和子信息2，子信息1指示[CSI-1，协作等级1]，子信息2指示[BM，协作等级2]}。那么第三信息可以包括子信息3和子信息4，子信息3指示[CSI-1，协作等级1，存储能力需求a1，计算能力需求b1，电量需求c1，处理时延信息d1，AI模型信息e1，其他]，子信息4指示[BM，协作等级2，存储能力需求a2，计算能力需求b2，电量需求c2，处理时延信息d2，AI模型信息e2，其他]。
作为另一种可选的实施方式，H个子信息中的每个子信息不指示UE对于该子信息指示的AI功能提供的能力参数的值，而是第三信息除了包括H个子信息外还可以包括该UE支持的能力参数的最大值。在这种方式下，第三信息不必多次包括能力参数的值，能够减小第三信息的传输开销。另外在这种方式下，第三信息还可指示UE提供的AI功能，那么，H个子信息中的部分或全部子信息中的每个子信息可以指示如下一项或多项：UE提供的一个AI功能，该AI功能对应的协作等级，该AI功能对应的能力，该AI功能对应的AI算法，或，该AI功能对应的AI模型。例如H个子信息中的一个子信息为第四子信息，第四子信息可指示如下一项或多项：UE提供的第四AI功能，第四AI功能对应的协作 等级，第四AI功能对应的能力，第四AI功能对应的AI算法，或，第四AI功能对应的AI模型。
H个子信息中，不同的子信息指示的项可以相同或不同。例如，第三信息可指示UE提供的AI功能以及UE提供的AI功能所对应的协作等级，那么H个子信息中的每个子信息可以指示UE提供的一个AI功能以及该AI功能对应的协作等级；或者，H个子信息中有部分子信息中的每个子信息可指示UE提供的一个AI功能以及该AI功能对应的协作等级，而剩余子信息中的每个子信息指示UE提供的一个AI功能，而不指示协作等级。例如H个子信息中的一个子信息为第四子信息，第四子信息可指示UE提供的第四AI功能以及第四AI功能对应的协作等级。
例如，第二信息包括子信息1和子信息2，子信息1指示[CSI-1，协作等级1]，子信息2指示[BM，协作等级2]}。那么第三信息可以包括子信息3、子信息4、以及UE支持的能力参数的最大值，子信息3指示[CSI-1，协作等级1]，子信息4指示[BM，协作等级2]，UE支持的能力参数的最大值例如包括[最大存储能力，最大计算能力，最大电量信息，处理时延信息，AI模型信息，其他]。
可选的，如果需要该UE提供AI能力的网元为DU，而第一通信装置例如为CU、CU-CP、或CU-CP2，那么在S404之后，第一通信装置还可以向DU发送第三信息，DU可以接收来自第一通信装置的第三信息，从而DU就获得了UE的AI能力信息。
通过本申请实施例的技术方案，可以由网络侧先确定实际需要UE提供的AI能力信息(例如第二信息)，从而UE可以向网络侧发送第二信息所指示的AI功能对应的能力参数，而不必向网络侧发送第二信息未指示的AI功能对应的能力参数，从而减少了冗余信息，也节省了传输开销。
接下来介绍本申请实施例提供的另一种通信方法，在该方法中，可由UE确定网络侧实际需要UE提供的AI能力信息。请参考图5，为该方法的流程图。
S501、第一通信装置向UE发送请求信息。相应的，UE接收来自第一通信装置的请求信息。该请求信息可指示请求该UE提供的AI功能，或指示请求该UE提供的AI功能以及该AI功能对应的协作等级。
可选的，需要该UE提供AI能力的网元例如为CU、CU-CP或CU-CP2，而第一通信装置例如为CU、CU-CP、或CU-CP2，可理解为，需要该UE提供AI能力的网元为第一通信装置，那么该请求信息可以是第一通信装置自行确定的，例如第一通信装置可根据第二AI功能需求信息确定该请求信息，例如可将第二AI功能需求信息包括的部分或全部子信息作为该请求信息。第二AI功能需求信息可参考图4所示的实施例。
或者，需要该UE提供AI能力的网元例如为DU，而第一通信装置例如为CU、CU-CP、或CU-CP2，那么DU可以向第一通信装置发送该请求信息，从而第一通信装置可以获得该请求信息。例如DU可以根据第一AI功能需求信息确定该请求信息，例如可将第一AI功能需求信息包括的部分或全部子信息作为该请求信息。第一AI功能需求信息可参考图4所示的实施例。
请求信息例如包括E个子信息，E为正整数。可选的，请求信息可指示如下一项或多项：请求(或，期望；或，希望)UE提供的AI功能，请求UE提供的AI功能所对应的协作等级，请求UE提供的AI功能所对应的能力，请求UE提供的AI功能所对应的AI算法，或，请求UE提供的AI功能所对应的AI模型。那么，E个子信息中的每个子信息可以指示如上所述的一项或多项。例如E个子信息中的一个子信息为第五子信息，第五子信息可指示如下一项或多项：请求UE提供的第二AI功能，请求UE提供的第二AI功能所对应的协作等级，请求UE提供的第二AI功能所对应的能力，请求UE提供的第二AI功能所对应的AI算法，或，请求UE提供的第二AI功能所对应的AI模型。其中，E个子信息中的一个子信息所指示的协作等级，可以是请求UE对于该子信息指示的AI功能所提供的协作等级。E个子信息中的一个子信息所指示的能力，可以是请求UE对于该子信息指示的AI功能所提供的能力。E个子信息中的一个子信息所指示的AI算法，可以是请求UE对于该子信息指示的AI功能所提供的AI算法。E个子信息中的一个子信息所指示的AI模型，可以是请求UE对于该子信息指示的AI功能所提供的AI模型。
E个子信息中，不同的子信息所指示的项可能相同、部分相同或完全不同。本申请实施例中的第二AI功能与图4所示的实施例中的第二AI功能可以是同一AI功能，或者是不同的AI功能。E个子信息中，不同的子信息所指示的项可能相同、部分相同或完全不同。例如其中的一个子信息指示请求UE提供的第二AI功能，以及指示请求UE提供的第二AI功能所对应的能力；而其中的另一个子信息指示请求UE提供的第三AI功能，请求UE提供的第三AI功能所对应的协作等级，以及指示请求UE提供的 第三AI功能所对应的能力。
E个子信息中，不同的子信息所指示的相同项的内容可能相同或不同。例如E个子信息中的每个子信息均指示请求UE提供的AI功能，不同的子信息指示的AI功能可以相同，或者也可以不同。其中，如果E个子信息中的每个子信息均指示请求UE提供的AI功能，且不同的子信息指示的AI功能不同，则相当于E个子信息可指示请求UE提供的E个AI功能。
E个子信息中的一个子信息如果指示AI功能，则其所指示的AI功能，可以包括至少一个子功能；和/或，E个子信息中的另一个子信息所指示的AI功能，可以是一个AI功能所包括的一个子功能。关于这部分内容的介绍以及进一步的举例等内容，可参考图4所示的实施例的S401中对于第一信息的介绍。
S502、UE根据请求信息以及该UE的能力信息确定第三信息。该UE的能力信息例如包括该UE的AI能力信息。第三信息可包括(或，指示)该请求信息指示的AI功能对应的能力参数的值(或者说，第三信息包括UE提供的AI功能对应的能力参数)；或者，第三信息可包括(或，指示)该请求信息指示的AI功能和协作等级所对应的能力参数的值(或者说，第三信息包括UE提供的AI功能和协作等级所对应的能力参数)；或者，第三信息可包括(或，指示)该请求信息指示的AI功能、协作等级、能力、AI算法或AI模型中的一项或多项所对应的能力参数的值(或者，第三信息包括UE提供的AI功能、协作等级、能力、AI算法或AI模型所对应的能力参数)；或者，第三信息指示UE不支持提供请求的AI功能。
该能力信息例如包括F个子信息，F为正整数。可选的，能力信息可指示UE支持的AI功能，那么，F个子信息中的每个子信息可以指示如下一项或多项：UE支持的AI功能，UE支持的AI功能所对应的协作等级，UE支持的AI功能所对应的能力，UE支持的AI功能所对应的AI算法，或，UE支持的AI功能所对应的AI模型。例如，一个子信息可指示如下一项或多项：UE支持的一个AI功能1，UE支持的AI功能1所对应的协作等级，UE支持的AI功能1所对应的能力，UE支持的AI功能1所对应的AI算法，或，UE支持的AI功能1所对应的AI模型。例如F个子信息中的一个子信息为第六子信息，第六子信息可指示UE支持的第一AI功能，UE支持的第一AI功能所对应的协作等级，UE支持的第一AI功能所对应的能力，UE支持的第一AI功能所对应的AI算法，或，UE支持的第一AI功能所对应的AI模型。本申请实施例中的第一AI功能与图4所示的实施例中的第一AI功能可以是同一AI功能，或者是不同的AI功能。
F个子信息中，不同的子信息所指示的项可能相同、部分相同或完全不同。F个子信息中，不同的子信息所指示的项的内容可能相同或不同。对此可参考图4所示的实施例的S401中对于M个子信息的相关介绍。
F个子信息中的一个子信息所指示的AI功能，可以包括至少一个子功能，即，该AI功能可以视为总AI功能，该AI功能还包括至少一个子功能；和/或，F个子信息中的另一个子信息所指示的AI功能，可以是一个AI功能所包括的一个子功能。关于这部分内容可参考图4所示的实施例的S401中对于第一信息的介绍。
UE根据能力信息以及请求信息确定(或者说，过滤；或者，筛选)第三信息，可以包括图4所示的实施例的S402介绍的方式A～方式F中的一种或多种，因此可参考前文的介绍，此处不再赘述。
S503、UE向第一通信装置发送第三信息。相应的，第一通信装置接收来自UE的第三信息。
第三信息可包括(或，指示)该请求信息指示的AI功能对应的能力参数的值，或者，第三信息可包括(或，指示)该请求信息指示的AI功能和协作等级所对应的能力参数的值，关于第三信息的实现方式可参考图4所示的实施例的S404。
或者，如果UE在S502中确定的第三信息为空，或者无法确定第三信息，那么第三信息也可以指示UE不支持提供请求的AI功能。
可选的，如果需要该UE提供AI能力的网元为DU，而第一通信装置例如为CU、CU-CP、或CU-CP2，那么在S503之后，第一通信装置还可以向DU发送第三信息，DU可以接收来自第一通信装置的第三信息，从而DU就获得了UE的AI能力信息。
通过本申请实施例的技术方案，可以由UE确定实际需要UE提供的AI能力信息，从而UE可以向网络侧发送对应的能力参数，而不必向网络侧发送网络侧所不需要的能力参数，从而减少了冗余信息，也节省了传输开销。而且对于AI能力信息的过滤过程在UE侧执行，则UE侧不必事先向网络侧发送 如图4所示的实施例所介绍的第一信息，能够进一步节省传输开销。
图6给出了本申请实施例提供的一种通信装置的结构示意图。所述通信装置600可以是图4或图5所示的实施例中的任一个实施例所述的第一通信装置或该第一通信装置的电路系统，用于实现上述方法实施例中对应于第一通信装置的方法。或者，所述通信装置600可以是图4或图5所示的实施例中的任一个实施例的UE的电路系统，用于实现上述方法实施例中对应于UE的方法。具体的功能可以参见上述方法实施例中的说明。其中，例如一种电路系统为芯片系统。
该通信装置600包括至少一个处理器601。处理器601可以用于装置的内部处理，实现一定的控制处理功能。可选地，处理器601包括指令。可选地，处理器601可以存储数据。可选地，不同的处理器可以是独立的器件，可以位于不同物理位置，可以位于不同的集成电路上。可选地，不同的处理器可以集成在一个或多个处理器中，例如，集成在一个或多个集成电路上。
可选地，通信装置600包括一个或多个存储器603，用以存储指令。可选地，所述存储器603中还可以存储有数据。所述处理器和存储器可以单独设置，也可以集成在一起。
可选地，通信装置600包括通信线路602，以及至少一个通信接口604。其中，因为存储器603、通信线路602以及通信接口604均为可选项，因此在图6中均以虚线表示。
可选地，通信装置600还可以包括收发器和/或天线。其中，收发器可以用于向其他装置发送信息或从其他装置接收信息。所述收发器可以称为收发机、收发电路、输入输出接口等，用于通过天线实现通信装置600的收发功能。可选地，收发器包括发射机(transmitter)和接收机(receiver)。示例性地，发射机可以用于将基带信号生成射频(radio frequency)信号，接收机可以用于将射频信号转换为基带信号。
处理器601可以包括一个通用中央处理器(central processing unit，CPU)，微处理器，特定应用集成电路(application specific integrated circuit，ASIC)，或一个或多个用于控制本申请方案程序执行的集成电路。
通信线路602可包括一通路，在上述组件之间传送信息。
通信接口604，使用任何收发器一类的装置，用于与其他设备或通信网络通信，如以太网，无线接入网(radio access network，RAN)，无线局域网(wireless local area networks，WLAN)，有线接入网等。
存储器603可以是只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)或者可存储信息和指令的其他类型的动态存储设备，也可以是电可擦可编程只读存储器(electrically erasable programmable read-only memory，EEPROM)、只读光盘(compact disc read-only memory，CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。存储器603可以是独立存在，通过通信线路602与处理器601相连接。或者，存储器603也可以和处理器601集成在一起。
其中，存储器603用于存储执行本申请方案的计算机执行指令，并由处理器601来控制执行。处理器601用于执行存储器603中存储的计算机执行指令，从而实现图4或图5所示的实施例中的任一个实施例所述的第一通信装置所执行的步骤，或，实现图4或图5所示的实施例中的任一个实施例所述的终端设备所执行的步骤。
可选的，本申请实施例中的计算机执行指令也可以称之为应用程序代码，本申请实施例对此不作具体限定。
在具体实现中，作为一种实施例，处理器601可以包括一个或多个CPU，例如图6中的CPU0和CPU1。
在具体实现中，作为一种实施例，通信装置600可以包括多个处理器，例如图6中的处理器601和处理器605。这些处理器中的每一个可以是一个单核(single-CPU)处理器，也可以是一个多核(multi-CPU)处理器。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(例如计算机程序指令)的处理核。
当图6所示的装置为芯片时，例如是第一通信装置的芯片，或UE的芯片，则该芯片包括处理器601(还可以包括处理器605)、通信线路602和通信接口604，可选的，该可包括存储器603。具体地，通信接口604可以是输入接口、管脚或电路等。存储器603可以是寄存器、缓存等。处理器601和处理 器605可以是一个通用的CPU，微处理器，ASIC，或一个或多个用于控制上述任一实施例的通信方法的程序执行的集成电路。
本申请实施例可以根据上述方法示例对装置进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。比如，在采用对应各个功能划分各个功能模块的情况下，图7示出了一种装置示意图，该装置700可以是上述各个方法实施例中所涉及的第一通信装置或UE，或者为第一通信装置中的芯片或UE中的芯片。该装置700包括发送单元701、处理单元702和接收单元703。
应理解，该装置700可以用于实现本申请实施例的通信方法中由第一通信装置或UE执行的步骤，相关特征可以参照上文图4或图5所示实施例中的任一个实施例，此处不再赘述。
可选的，图7中的发送单元701、接收单元703以及处理单元702的功能/实现过程可以通过图6中的处理器601调用存储器603中存储的计算机执行指令来实现。或者，图7中的处理单元702的功能/实现过程可以通过图6中的处理器601调用存储器603中存储的计算机执行指令来实现，图7中的发送单元701和接收单元703的功能/实现过程可以通过图6中的通信接口604来实现。
可选的，当该装置700是芯片或电路时，则发送单元701和接收单元703的功能/实现过程还可以通过管脚或电路等来实现。
本申请还提供一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序或指令，当该计算机程序或指令被运行时，实现前述方法实施例中由第一通信装置或UE所执行的方法。这样，上述实施例中所述功能可以软件功能单元的形式实现并作为独立的产品销售或使用。基于这样的理解，本申请的技术方案本质上或者说对做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。存储介质包括：U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
本申请还提供一种计算机程序产品，该计算机程序产品包括：计算机程序代码，当该计算机程序代码在计算机上运行时，使得该计算机执行前述任一方法实施例中由第一通信装置或UE所执行的方法。
本申请实施例还提供了一种处理装置，包括处理器和接口；所述处理器用于执行上述任一方法实施例所涉及的第一通信装置或UE所执行的方法。
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指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照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、或者其他可编程装置。所述计算机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(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)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包含一个或多个可用介质集成的服务器、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)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。
本申请实施例中所描述的各种说明性的逻辑单元和电路可以通过通用处理器，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)，或其它可编程逻辑装置，离散门或晶体管逻辑，离散硬件部件，或上述任何组合的设计来实现或操作所描述的功能。通用处理器可以为微处理器，可选地，该通用处理器也可以为任何传统的处理器、控制器、微控制器或状态机。处理器也可以通过计算装置的组合来实现，例如数字信号处理器和微处理器，多个微处理器，一个或多个微处理器联合一个数字信号处理器核，或任何其它类似的配置来实现。
本申请实施例中所描述的方法或算法的步骤可以直接嵌入硬件、处理器执行的软件单元、或者这两者的结合。软件单元可以存储于RAM、闪存、ROM、可擦除可编程只读存储器(erasable programmable  read-only memory，EPROM)、EEPROM、寄存器、硬盘、可移动磁盘、CD-ROM或本领域中其它任意形式的存储媒介中。示例性地，存储媒介可以与处理器连接，以使得处理器可以从存储媒介中读取信息，并可以向存储媒介存写信息。可选地，存储媒介还可以集成到处理器中。处理器和存储媒介可以设置于ASIC中，ASIC可以设置于终端设备中。可选地，处理器和存储媒介也可以设置于终端设备中的不同的部件中。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
本申请的各个实施例中的内容可以相互参考，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，第一通信装置或UE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。

Claims (40)

  1. 一种通信方法，其特征在于，应用于第一通信装置，所述方法包括：
    接收第一信息，所述第一信息包括第一子信息，所述第一子信息用于指示终端设备支持的第一人工智能AI功能；
    根据所述第一信息确定第二信息，所述第二信息用于指示请求所述终端设备提供的AI功能；
    向所述终端设备发送所述第二信息；
    接收来自所述终端设备的第三信息，所述第三信息包括所述第二信息指示的AI功能对应的能力参数。
  2. 根据权利要求1所述的方法，其特征在于，所述第一子信息还用于指示如下一项或多项：
    所述第一AI功能对应的协作等级；
    所述第一AI功能对应的能力；
    所述第一AI功能对应的AI算法；或，
    所述第一AI功能对应的AI模型。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第二信息还用于指示如下一项或多项：
    请求所述终端设备提供的AI功能对应的协作等级；
    请求所述终端设备提供的AI功能对应的能力；
    请求所述终端设备提供的AI功能对应的AI算法；或，
    请求所述终端设备提供的AI功能对应的AI模型。
  4. 根据权利要求1～3任一项所述的方法，其特征在于，所述第三信息还包括如下一项或多项：
    所述第二信息指示的协作等级对应的能力参数；
    所述第二信息指示的能力对应的能力参数；
    所述第二信息指示的AI算法对应的能力参数；或，
    所述第二信息指示的AI模型对应的能力参数。
  5. 根据权利要求1～4任一项所述的方法，其特征在于，接收第一信息，包括：
    接收来自所述终端设备的所述第一信息；或，
    接收来自第二通信装置的所述第一信息，所述第二通信装置为所述第一通信装置的相邻接入网设备，或为核心网设备。
  6. 根据权利要求1～5任一项所述的方法，其特征在于，
    所述第一通信装置为接入网设备；或，
    所述第一通信装置为集中单元CU；或，
    所述第一通信装置为集中式单元控制面CU-CP；或，
    所述第一通信装置为位置管理功能LMF；或，
    所述第一通信装置为接入与移动管理功能AMF。
  7. 根据权利要求6所述的方法，其特征在于，所述第一通信装置为所述CU或所述CU-CP，根据所述第一信息确定第二信息，包括：
    向分布式单元DU发送所述第一信息，接收来自所述DU的所述第二信息；或，
    接收来自DU的第一AI功能需求信息，并根据所述第一AI功能需求信息以及所述第一信息确定所述第二信息，其中，所述第一AI功能需求信息包括第二子信息，所述第二子信息用于指示所述DU请求所述终端设备提供的第二AI功能；或，
    根据第二AI功能需求信息以及所述第一信息确定所述第二信息，其中，所述第二AI功能需求信息包括第三子信息，所述第三子信息用于指示所述第一通信装置请求所述终端设备提供的第三AI功能，或者，所述第三子信息用于指示所述第一通信装置请求所述终端设备提供的第三AI功能，以及还用于指示如下一项或多项：所述第三AI功能对应的协作等级，所述第三AI功能对应的能力，所述第三AI功能对应的AI算法，或，所述第三AI功能对应的AI模型。
  8. 根据权利要求7所述的方法，其特征在于，所述第二子信息还用于指示如下一项或多项：
    所述第二AI功能对应的协作等级；
    所述第二AI功能对应的能力；
    所述第二AI功能对应的AI算法；或，
    所述第二AI功能对应的AI模型。
  9. 根据权利要求7或8所述的方法，其特征在于，根据所述第一AI功能需求信息以及所述第一信息确定所述第二信息，包括如下一项或多项：
    所述第一AI功能与所述第二AI功能为同一AI功能，所述第一子信息还用于指示所述第一AI功能对应的协作等级为第一等级，所述第二子信息指示所述DU请求所述第二AI功能对应的协作等级为第二等级，如果所述终端设备支持所述第一等级包括支持所述第二等级，确定所述第二信息包括所述第一子信息；
    如果所述第一AI功能包括所述第二AI功能，确定所述第二信息包括所述第二子信息；或，
    如果所述第一AI功能与所述第二AI功能为同一AI功能，且所述第一信息未指示所述第一AI功能对应的协作等级，确定所述第二信息包括所述第二子信息。
  10. 根据权利要求7～9任一项所述的方法，其特征在于，所述方法还包括：
    向所述DU发送所述第三信息。
  11. 根据权利要求1～10任一项所述的方法，其特征在于，
    所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述终端设备提供的第四AI功能、所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、所述第四AI功能对应的AI模型、或所述第四AI功能对应的能力参数的值；或，
    所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。
  12. 根据权利要求1～11任一项所述的方法，其特征在于，所述能力参数包括如下一项或多项：
    所述终端设备的计算能力参数；
    所述终端设备的能耗参数；
    所述终端设备的存储能力参数；
    所述终端设备的电量参数；
    所述终端设备的处理时延；
    所述终端设备支持的AI模型；或，
    所述终端设备支持的AI算法。
  13. 根据权利要求1～12任一项所述的方法，其特征在于，所述第一AI功能包括至少一个子功能，或，所述第一AI功能为一个AI功能的子功能。
  14. 一种通信方法，其特征在于，应用于终端设备，所述方法包括：
    接收来自第一通信装置的第二信息，所述第二信息用于指示请求所述终端设备提供的AI功能；
    向所述第一通信装置发送第三信息，所述第三信息包括所述第二信息指示的AI功能对应的能力参数。
  15. 根据权利要求14所述的方法，其特征在于，所述第二信息还用于指示如下一项或多项：
    请求所述终端设备提供的AI功能对应的协作等级；
    请求所述终端设备提供的AI功能对应的能力；
    请求所述终端设备提供的AI功能对应的AI算法；或，
    请求所述终端设备提供的AI功能对应的AI模型。
  16. 根据权利要求14或15所述的方法，其特征在于，所述第三信息还包括如下一项或多项：
    所述第二信息指示的协作等级对应的能力参数；
    所述第二信息指示的能力对应的能力参数；
    所述第二信息指示的AI算法对应的能力参数；或，
    所述第二信息指示的AI模型对应的能力参数。
  17. 根据权利要求14～16任一项所述的方法，其特征在于，所述方法还包括：
    向所述第一通信装置发送第一信息，所述第一信息包括第一子信息，所述第一子信息用于指示终端设备支持的第一AI功能，其中，所述第二信息与所述第一信息相关。
  18. 根据权利要求17所述的方法，其特征在于，所述第一子信息还用于指示如下一项或多项：
    所述第一AI功能对应的协作等级；
    所述第一AI功能对应的能力；
    所述第一AI功能对应的AI算法；或，
    所述第一AI功能对应的AI模型。
  19. 根据权利要求17或18所述的方法，其特征在于，所述第一AI功能包括至少一个子功能，或，所述第一AI功能为一个AI功能的子功能。
  20. 根据权利要求14～19任一项所述的方法，其特征在于，
    所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、所述第四AI功能对应的AI模型、或所述第四AI功能对应的能力参数的值；或，
    所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。
  21. 根据权利要求14～20任一项所述的方法，其特征在于，所述能力参数包括如下一项或多项：
    所述终端设备的计算能力参数；
    所述终端设备的能耗参数；
    所述终端设备的存储能力参数；
    所述终端设备的电量参数；
    所述终端设备的处理时延；
    所述终端设备支持的AI模型；或，
    所述终端设备支持的AI算法。
  22. 一种通信方法，其特征在于，应用于终端设备，所述方法包括：
    接收来自第一通信装置的请求信息，所述请求信息用于指示请求所述终端设备提供的人工智能AI功能；
    根据所述请求信息以及所述终端设备的能力信息确定第三信息，所述第三信息包括所述请求信息指示的AI功能对应的能力参数；
    向所述第一通信装置发送所述第三信息。
  23. 根据权利要求22所述的方法，其特征在于，所述请求信息还用于指示请求如下一项或多项：
    所述终端设备提供的AI功能对应的协作等级；
    所述终端设备提供的AI功能对应的能力；
    所述终端设备提供的AI功能对应的AI算法；或，
    所述终端设备提供的AI功能对应的AI模型。
  24. 根据权利要求22或23所述的方法，其特征在于，所述第三信息还包括如下一项或多项：
    所述请求信息指示的协作等级对应的能力参数；
    所述请求信息指示的能力对应的能力参数；
    所述请求信息指示的AI算法对应的能力参数；或，
    所述请求信息指示的AI模型对应的能力参数。
  25. 根据权利要求22～24任一项所述的方法，其特征在于，
    所述请求信息包括第五子信息，所述第五子信息用于指示请求所述终端设备提供的第二AI功能，或者，所述第五子信息用于指示请求所述终端设备提供的第二AI功能，以及还用于指示请求如下一项或多项：所述第二AI功能对应的协作等级，所述第二AI功能对应的能力，所述第二AI功能对应的AI算法，或，所述第二AI功能对应的AI模型；
    所述能力信息包括第六子信息，所述第六子信息用于指示所述终端设备支持的第一AI功能，或者，所述第六子信息用于指示所述终端设备支持的第一AI功能，以及还用于指示如下一项或多项：所述第一AI功能对应的协作等级，所述第一AI功能对应的能力，所述第一AI功能对应的AI算法，或，所述第一AI功能对应的AI模型。
  26. 根据权利要求25所述的方法，其特征在于，根据所述请求信息以及所述终端设备的能力信息确定第三信息，包括：
    所述第一AI功能与所述第二AI功能为同一AI功能，所述第六子信息指示所述第一AI功能对应的协作等级为第一等级，所述第五子信息指示所述第二AI功能对应的协作等级为第二等级，如果所述终端设备支持所述第一等级包括支持所述第二等级，确定所述第三信息包括所述第五子信息；和/或，
    如果所述第一AI功能包括所述第二AI功能，确定所述第三信息包括所述第五子信息。
  27. 根据权利要求25或26所述的方法，其特征在于，
    所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、所述第四AI功能对应的AI模型、或所述第四AI功能对应的能力参数的值；或，
    所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。
  28. 根据权利要求22～27任一项所述的方法，其特征在于，所述能力参数包括如下一项或多项：
    所述终端设备的计算能力参数；
    所述终端设备的能耗参数；
    所述终端设备的存储能力参数；
    所述终端设备的电量参数；
    所述终端设备的处理时延；
    所述终端设备支持的AI模型；或，
    所述终端设备支持的AI算法。
  29. 一种通信方法，其特征在于，应用于第一通信装置，所述方法包括：
    向终端设备发送请求信息，所述请求信息用于指示请求所述终端设备提供的人工智能AI功能；
    接收来自所述终端设备的第三信息，所述第三信息包括所述请求信息指示的AI功能对应的能力参数。
  30. 根据权利要求29所述的方法，其特征在于，所述请求信息还用于指示请求如下一项或多项：
    所述终端设备提供的AI功能对应的协作等级；
    所述终端设备提供的AI功能对应的能力；
    所述终端设备提供的AI功能对应的AI算法；或，
    所述终端设备提供的AI功能对应的AI模型。
  31. 根据权利要求29或30所述的方法，其特征在于，所述第三信息还包括如下一项或多项：
    所述请求信息指示的协作等级对应的能力参数；
    所述请求信息指示的能力对应的能力参数；
    所述请求信息指示的AI算法对应的能力参数；或，
    所述请求信息指示的AI模型对应的能力参数。
  32. 根据权利要求29～31任一项所述的方法，其特征在于，
    所述第一通信装置为接入网设备；或，
    所述第一通信装置为集中单元CU；或，
    所述第一通信装置为集中式单元控制面CU-CP；或，
    所述第一通信装置为位置管理功能LMF；或，
    所述第一通信装置为接入与移动管理功能AMF。
  33. 根据权利要求32所述的方法，其特征在于，所述第一通信装置为CU或CU-CP，
    所述方法还包括：接收来自分布式单元DU的所述请求信息；或，
    根据第二AI功能需求信息确定所述请求信息，其中，所述第二AI功能需求信息用于指示请求所述终端设备提供的AI功能，或者，所述第二AI功能需求信息用于指示请求所述终端设备提供的AI功能，以及还指示如下一项或多项：所述终端设备提供的AI功能对应的协作等级，所述终端设备提供的AI功能对应的能力，所述终端设备提供的AI功能对应的AI算法，或，所述终端设备提供的AI功能对应的AI模型。
  34. 根据权利要求33所述的方法，其特征在于，如果所述请求信息来自所述DU，所述方法还包括：
    向所述DU发送所述第三信息。
  35. 根据权利要求29～34任一项所述的方法，其特征在于，
    所述第三信息包括第四子信息，所述第四子信息用于指示所述终端设备提供的第四AI功能以及所述第四AI功能对应的能力参数的值，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力参数的值、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型；或，
    所述第三信息包括第四子信息，以及包括所述终端设备支持的能力参数的最大值，所述第四子信息用于指示所述终端设备提供的第四AI功能，或，所述第四子信息用于指示所述终端设备提供的第四AI功能，以及还用于指示如下一项或多项：所述第四AI功能对应的协作等级、所述第四AI功能对应的能力、所述第四AI功能对应的AI算法、或所述第四AI功能对应的AI模型。
  36. 根据权利要求29～35任一项所述的方法，其特征在于，所述能力参数包括如下一项或多项：
    所述终端设备的计算能力参数；
    所述终端设备的能耗参数；
    所述终端设备的存储能力参数；
    所述终端设备的电量参数；
    所述终端设备的处理时延；
    所述终端设备支持的AI模型；或，
    所述终端设备支持的AI算法。
  37. 一种通信装置，其特征在于，包括处理器和存储器，所述存储器和所述处理器耦合，所述处理器用于执行如权利要求1～13任一项所述的方法，或用于执行如权利要求14～21任一项所述的方法，或用于执行如权利要求22～28任一项所述的方法，或用于执行如权利要求29～36任一项所述的方法。
  38. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质用于存储计算机程序，当所述计算机程序在计算机上运行时，使得所述计算机执行如权利要求1～13任一项所述的方法，或使得所述计算机执行如权利要求14～21任一项所述的方法，或使得所述计算机执行如权利要求22～28任一项所述的方法，或使得所述计算机执行如权利要求29～36任一项所述的方法。
  39. 一种芯片系统，其特征在于，所述芯片系统包括：
    处理器和接口，所述处理器用于从所述接口调用并运行指令，当所述处理器执行所述指令时，实现如权利要求1～13任一项所述的方法，或实现如权利要求14～21任一项所述的方法，或实现如权利要求22～28任一项所述的方法，或实现如权利要求29～36任一项所述的方法。
  40. 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，当所述计算机程序在计算机上运行时，使得所述计算机执行如权利要求1～13任一项所述的方法，或使得所述计算机执行如权利要求14～21任一项所述的方法，或使得所述计算机执行如权利要求22～28任一项所述的方法，或使得所述计算机执行如权利要求29～36任一项所述的方法。
PCT/CN2023/119099 2022-09-24 2023-09-15 一种通信方法及装置 WO2024061125A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202211168801.X 2022-09-24
CN202211168801 2022-09-24
CN202311103713.6A CN117768875A (zh) 2022-09-24 2023-08-30 一种通信方法及装置
CN202311103713.6 2023-08-30

Publications (1)

Publication Number Publication Date
WO2024061125A1 true WO2024061125A1 (zh) 2024-03-28

Family

ID=90313172

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/119099 WO2024061125A1 (zh) 2022-09-24 2023-09-15 一种通信方法及装置

Country Status (2)

Country Link
CN (1) CN117768875A (zh)
WO (1) WO2024061125A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020076144A1 (ko) * 2018-10-12 2020-04-16 엘지전자 주식회사 무선 통신 시스템에서 복수개의 무선 접속 방식을 지원하는 단말의 능력을 네트워크에 설정하는 방법 및 이를 위한 장치
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
CN113747462A (zh) * 2020-05-30 2021-12-03 华为技术有限公司 一种信息处理方法及相关设备
CN114143799A (zh) * 2020-09-03 2022-03-04 华为技术有限公司 通信方法及装置
CN114845293A (zh) * 2021-02-02 2022-08-02 荣耀终端有限公司 一种ue能力上报的方法以及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020076144A1 (ko) * 2018-10-12 2020-04-16 엘지전자 주식회사 무선 통신 시스템에서 복수개의 무선 접속 방식을 지원하는 단말의 능력을 네트워크에 설정하는 방법 및 이를 위한 장치
CN113747462A (zh) * 2020-05-30 2021-12-03 华为技术有限公司 一种信息处理方法及相关设备
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
CN114143799A (zh) * 2020-09-03 2022-03-04 华为技术有限公司 通信方法及装置
CN114845293A (zh) * 2021-02-02 2022-08-02 荣耀终端有限公司 一种ue能力上报的方法以及装置

Also Published As

Publication number Publication date
CN117768875A (zh) 2024-03-26

Similar Documents

Publication Publication Date Title
US20220116799A1 (en) Method and device for o-ran-based performance optimization and configuration
US20230209390A1 (en) Intelligent Radio Access Network
CN110880958B (zh) 一种射频参数的上报方法及装置
CN114303347A (zh) 通信网络中与机器学习相关的方法、装置和机器可读介质
US20230245000A1 (en) Model evaluation method and apparatus
US20230262478A1 (en) Model configuration method and apparatus
WO2022151084A1 (zh) 信息量化方法、装置、通信设备及存储介质
WO2024012331A1 (zh) 一种确定人工智能ai模型的方法及装置
WO2024061125A1 (zh) 一种通信方法及装置
WO2019242540A1 (zh) 非授权频段上波束管理的方法、终端设备和网络设备
WO2022206513A1 (zh) 模型处理的方法、通信装置和系统
TWI760964B (zh) 控制資訊傳輸方法、基地台、終端及電腦可讀存儲介質
WO2022165721A1 (zh) Ran域的模型共享方法及装置
WO2022088003A1 (zh) 一种信息传输的方法、轻量化处理的方法以及相关通信装置
WO2024032202A1 (zh) 一种协作传输接收点指示方法及装置
WO2024046113A1 (zh) 一种无线通信方法及通信装置
WO2024011581A1 (zh) 一种通信方法及装置
WO2024008004A1 (zh) 一种通信方法及装置
US20240020513A1 (en) Data processing method and apparatus
WO2024060139A1 (zh) 通信方法、装置、存储介质及程序产品
WO2024093503A1 (zh) 一种处理模型的方法和装置
WO2023065314A1 (en) Wireless communication method and apparatus of supporting artificial intelligence
TWI834162B (zh) 信號傳輸方法、裝置、終端及基地台
WO2022100514A1 (zh) 决策方法和决策装置
EP4369253A1 (en) Dataset sharing transmission instructions for separated two-sided ai/ml based model training

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: 23867414

Country of ref document: EP

Kind code of ref document: A1