Communication method and apparatus

Abstract

A communication method and apparatus, which relate to the technical field of communications and are used for reducing the waste of transmission resources. A terminal device side sends to an access network device side a transmission requirement thereof for an AI model, and the access network device side then determines, for the terminal device and on the basis of the requirement, a transmission mode to be used for transmitting a first AI model to the terminal device. Moreover, after the access network device side sends a transmission requirement thereof to the terminal device side, the terminal device side reports to the access network device side capability parameters thereof for receiving an AI model, such that the access network device side can determine, for the terminal device and on the basis of the capability of the current terminal device and the requirement of the access network device side thereof, a better AI-model transmission mode that can match the capability of the terminal device. A transmission mode determined on the basis of the solution provided in the present application can satisfy requirements of a terminal device (or an access network device) in different mobile scenarios, thereby reducing the waste of transmission resources.

Description

Communication method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on October 31, 2023, with application number 202311436084.9 and application name "A Communication Method and Device", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0004] Artificial intelligence (AI) technology, first proposed in the 1950s, simulates the human brain to perform complex calculations. With advances in data storage and computing power, AI is increasingly being used. Currently, the Third Generation Partnership Project (3GPP) has proposed applying AI to New Radio (NR) systems. By intelligently collecting and analyzing data, it can improve network performance and user experience.

[0005] Currently, terminal devices are required to have AI capabilities, which requires obtaining AI models from the network. However, the model requirements of terminal devices vary in different mobile scenarios, and the way the network transmits AI models to terminal devices is not well adapted to different mobile scenarios, resulting in a waste of transmission resources.

[0006] Summary of the Invention

[0007] Embodiments of the present application provide a communication method and apparatus for reducing waste of transmission resources.

[0008] In a first aspect, an embodiment of the present application provides a communication method, which can be performed by a second communication device, or by other devices including the functions of the second communication device, or by a chip system (or, chip) or other functional module, which can realize the functions of the second communication device, and the chip system or functional module is, for example, provided in the second communication device. The second communication device can be an access network device or a module in the access network device (such as a chip or circuit), or a CU, or a CU-CP, or a CU-CP2, etc. The communication method includes: the second communication device receives first information. The first information can come from the first communication device. The first information indicates the transmission requirements of the first communication device for the first artificial intelligence AI model to be applied; the first information is used to determine the transmission method of the first AI model; and second information is sent to the first communication device, and the second information is used to indicate the transmission method of the first AI model. Exemplarily, the first communication device can be a terminal device or a chip or functional module in the terminal device.

[0009] In an embodiment of the present application, after receiving a transmission request from a terminal device, the access network device determines, based on the request, which transmission method to use for transmitting the first AI model to the terminal device. The method employed in the present application can match the transmission requirements of the terminal device, and the determined transmission method can adapt to the requirements of the terminal device in different mobile scenarios, thereby reducing the waste of transmission resources.

[0010] In one possible design, the transmission method of the first AI model includes one or more of the following: an access network device transmission method, wherein the access network device transmission method indicates that the first AI model is transmitted from the access network device to the first communication device; a third-party server OTT transmission method, wherein the OTT transmission method indicates that the first AI model is transmitted from the OTT to the first communication device; or, a core network device transmission method, wherein the core network device transmission method indicates that the first AI model is transmitted from the core network device to the first communication device.

[0011] In one possible design, the first information indicates one or more of the following: the expected time; the identifier of the first AI model; the metadata of the first AI model; the first AI function supported by the first AI model; the expected minimum transmission delay; the second AI function to be executed after completing the first AI function; or the moving path of the first communication device.

[0012] In one possible design, the method also includes: receiving third information from a first communication device, the third information including first sub-information, the first sub-information indicating the capability parameters of the first communication device to receive the first AI model, and the third information is used to determine the transmission method of the first AI model.

[0013] In the above method, the terminal device side reports its own receiving AI model capability parameters to the access network device side, so that the access network device side can determine a better AI model transmission method for the terminal device that can match the capabilities of the terminal device based on the current capabilities of the terminal device and the needs of the terminal device.

[0014] In one possible design, the first sub-information includes one or more of the following: storage capacity parameters of the first communication device; computing capacity parameters of the first communication device; communication capacity parameters of the first communication device; transmission rate allowed by the first communication device; arrival time of the first AI model expected by the first communication device; and model transmission mode supported by the first communication device.

[0015] In the above method, the storage capacity, computing capacity and communication capacity of the terminal device side change in real time. The access network device side configures the model transmission mode for the terminal device based on these capacity parameters of the terminal device side, which can improve the accuracy of the model transmission mode determination and improve the transmission efficiency.

[0016] In one possible design, the third information also includes second sub-information, where the second sub-information indicates capability parameters of a second AI model supported by the third-party application service OTT and provided to the first communication device, where the second AI model includes the first AI model.

[0017] In one possible design, the second sub-information includes one or more of the following: an identifier of the second AI model; an identifier of the OTT; metadata of the second AI model; a transmission rate supported by the OTT for transmitting the second AI model; a transmission delay supported by the OTT for transmitting the second AI model; an arrival time supported by the OTT for transmitting the second AI model; or a model transmission method supported by the OTT.

[0018] In one possible design, the access network device may request the OTT from the OTT side for capability parameters of the second AI model supported by the OTT.

[0019] In one possible design, receiving third information from a first communication device includes periodically receiving third information from the first communication device.

[0020] In the above method, the terminal device periodically reports its own capability parameters, or periodically reports its own capability parameters and the capability parameters of a second AI model supported by OTT. After receiving the transmission request from the terminal device, the access network device no longer needs to obtain these capability parameters from the terminal device, which can improve transmission efficiency.

[0021] In one possible design, the method further includes: sending first indication information to the first communication device, where the first indication information is used to indicate conditions that need to be met when the first communication device reports the third information.

[0022] In the above design, the access network device side instructs the terminal device side to report the capability parameters when the conditions are met, to prevent invalid reporting caused by the reported parameters on the terminal device side not changing, thereby reducing resource waste.

[0023] In one possible design, the first indication information includes one or more of the following:

[0024] an identifier of a triggering event, where the triggering event indicates that the first communication device is triggered to report the third information;

[0025] triggering reporting of a transmission rate variation range satisfied by the third information; or

[0026] The receiving delay variation range satisfied by triggering reporting of the third information.

[0027] In one possible design, the method also includes: sending second indication information to the first communication device, where the second indication information is used to instruct the first communication device to select to report part or all of the parameters in the third information based on current capabilities.

[0028] In the above design, the access network device side instructs the terminal device side to choose which parameters to report based on the current capabilities. For example, if some capabilities are not restricted, they do not need to be reported, which can reduce the waste of resources caused by reporting invalid capability parameters.

[0029] In one possible design, the method further includes: sending third indication information to the first communication device, where the third indication information is used to indicate parameters requested to be reported by the first communication device.

[0030] In the above design, the access network device side instructs the terminal device side which parameters to report based on its own needs, which can reduce the waste of resources caused by reporting invalid capability parameters.

[0031] In one possible design, the method also includes: receiving fourth information from a core network device, wherein the fourth information is used to indicate that the core network device supports providing capability parameters of a third AI model for the first communication device, and the third AI model includes the first AI model.

[0032] In one possible design, the fourth information includes one or more of the following: an identifier of the third AI model; metadata of the third AI model; a transmission rate supported by the core network device for transmitting the third AI model; a transmission delay supported by the core network device for transmitting the third AI model; an arrival time supported by the core network device for transmitting the third AI model; or a model transmission method supported by the core network device.

[0033] In one possible design, the method also includes: transmitting model transmission information corresponding to the first AI model to the first communication device; the model transmission information includes model information of the first AI model; or, the model transmission information includes the model information, and the model transmission information also includes the adopted transmission method and / or the estimated completion time; the adopted transmission method includes adopting user plane signaling or control plane signaling.

[0034] In one possible design, the model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; and fourth indication information, where the fourth indication information is used to indicate a structure of the first AI model.

[0035] In a second aspect, an embodiment of the present application provides a communication method, which can be performed by a first communication device. The first communication device can be a terminal device or a chip system (or, chip) or other functional module in the terminal device. The method includes: sending first information to a second communication device, the first information being used to indicate the transmission requirements of the first communication device for the first artificial intelligence AI model to be applied; the first information being used to determine the transmission method of the first AI model; and receiving second information from the second communication device, the second information being used to indicate the transmission method of the first AI model.

[0036] In one possible design, the transmission mode of the first AI model includes one or more of the following: an access network device transmission mode, wherein the access network device transmission mode indicates that the first AI model is transmitted from the access network device to the first communication device; an OTT transmission mode, wherein the OTT transmission mode indicates that the first AI model is transmitted from the OTT to the first communication device; or, a core network device transmission mode, wherein the core network device transmission mode indicates that the first AI model is transmitted from the core network device to the first communication device.

[0037] In one possible design, the first information indicates one or more of the following: the expected time; the identifier of the first AI model; the metadata of the first AI model; the first AI function supported by the first AI model; the expected minimum transmission delay; the second AI function to be executed after completing the first AI function; or the moving path of the first communication device.

[0038] In one possible design, the method also includes: sending third information to the second communication device, the third information including first sub-information, the first sub-information indicating the ability parameters of the first communication device to receive the first AI model, and the third information is used to determine the transmission method of the first AI model.

[0039] In one possible design, the first sub-information includes one or more of the following: storage capacity parameters of the first communication device; computing capacity parameters of the first communication device; communication capacity parameters of the first communication device; transmission rate allowed by the first communication device; arrival time of the first AI model expected by the first communication device; and model transmission mode supported by the first communication device.

[0040] In one possible design, the third information also includes second sub-information, where the second sub-information indicates capability parameters of a second AI model supported by the third-party application service OTT and provided to the first communication device, where the second AI model includes the first AI model.

[0041] In one possible design, the second sub-information includes one or more of the following: an identifier of the second AI model; an identifier of the OTT; metadata of the second AI model; a transmission rate supported by the OTT for transmitting the second AI model; a transmission delay supported by the OTT for transmitting the second AI model; an arrival time supported by the OTT for transmitting the second AI model; or a model transmission method supported by the OTT.

[0042] In one possible design, the method further includes: receiving sixth information from the OTT, the sixth information indicating capability parameters of the second AI model supported by the OTT for the first communication device. Exemplarily, the sixth information includes one or more of the following: an identifier of the second AI model; an identifier of the OTT; metadata of the second AI model; a transmission rate supported by the OTT for transmitting the second AI model; a transmission latency supported by the OTT for transmitting the second AI model; an arrival time supported by the OTT for transmitting the second AI model; or a model transmission method supported by the OTT.

[0043] In one possible design, sending the third information to the second communication device includes: periodically sending the third information to the second communication device.

[0044] In one possible design, the method further includes: receiving first indication information from the second communication device, the first indication information being used to indicate conditions that need to be met when the first communication device reports the third information.

[0045] In one possible design, the first indication information includes one or more of the following: an identifier of a triggering event, where the triggering event indicates that the first communication device is triggered to report the third information; a transmission rate variation range satisfied by triggering the reporting of the third information; or a reception delay variation range satisfied by triggering the reporting of the third information.

[0046] In one possible design, the method also includes: receiving second indication information from a second communication device, wherein the second indication information is used to instruct the first communication device to select to report part or all of the parameters in the third information based on current capabilities.

[0047] In one possible design, the method further includes: receiving third indication information from the second communication device, where the third indication information is used to indicate parameters requested to be reported by the first communication device.

[0048] In one possible design, the method also includes: receiving model transmission information corresponding to the first AI model from the second communication device; the model transmission information includes model information of the first AI model; or, the model transmission information includes the model information, and the model transmission information also includes the adopted transmission method and / or the estimated completion time; the adopted transmission method includes adopting user plane signaling or adopting control plane signaling.

[0049] In one possible design, the model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; or fourth indication information, where the fourth indication information is used to indicate a structure of the first AI model.

[0050] In a third aspect, an embodiment of the present application provides a communication method, which can be executed by a second communication device, or by other devices including the functions of the second communication device, or by a chip system (or, chip) or other functional module, which can realize the functions of the second communication device, and the chip system or functional module is, for example, set in the second communication device. The second communication device can be an access network device or a module in the access network device (such as a chip or circuit), or a CU, or a CU-CP, or a CU-CP2, etc. The communication method includes: sending fifth information to a first communication device, the fifth information is used to indicate the transmission requirements of a first artificial intelligence AI model, and the first AI model is an AI model requested to be configured by the first communication device; receiving third information from the first communication device, the third information includes first sub-information, the first sub-information indicates the ability parameters of the first communication device to receive the first AI model, and the third information is used to determine the transmission method of the first AI model; sending second information to the first communication device, the second information is used to indicate the transmission method of the first AI model.

[0051] In this embodiment of the present application, after the access network device sends a transmission request to the terminal device, the terminal device reports its own AI model receiving capability parameters to the access network device. This allows the access network device to determine a more optimal AI model transmission method for the terminal device based on the current terminal device capabilities and its own requirements. The determined transmission method can adapt to the needs of the terminal device in different mobile scenarios, reducing the waste of transmission resources.

[0052] In one possible design, the transmission mode of the first AI function includes one or more of the following: an access network device transmission mode, wherein the access network device transmission mode indicates that the first AI model is transmitted from the access network device to the first communication device; an OTT transmission mode, wherein the OTT transmission mode indicates that the first AI model is transmitted from the OTT to the first communication device; or, a core network device transmission mode, wherein the core network device transmission mode indicates that the first AI model is transmitted from the core network device to the first communication device.

[0053] In one possible design, the fifth information indicates one or more of the following: the first AI model; the first AI function supported by the first AI model; the capability requested to be reported by the first communication device, or the reason for transmission.

[0054] In one possible design, the first sub-information includes one or more of the following: a storage capacity parameter of the first communication device; a computing capacity parameter of the first communication device; a communication capacity parameter of the first communication device; a transmission rate allowed by the first communication device; an arrival time of the first AI model expected by the first communication device; or a model transmission method supported by the first communication device.

[0055] In one possible design, the third information also includes second sub-information, where the second sub-information indicates capability parameters of a second AI model supported by the third-party application service OTT and provided to the first communication device, and the structure of the second AI model includes the first AI model.

[0056] In one possible design, the second sub-information includes one or more of the following: an identifier of the second AI model; an identifier of the OTT; metadata of the second AI model; a transmission rate supported by the OTT for transmitting the second AI model; a transmission delay supported by the OTT for transmitting the second AI model; an arrival time supported by the OTT for transmitting the second AI model; or a model transmission method supported by the OTT.

[0057] In one possible design, the method also includes: receiving fourth information from a core network device, wherein the fourth information is used to indicate that the core network device supports capability parameters of a third AI model provided for the first communication device, and the third AI model includes the first AI model.

[0058] In one possible design, the fourth information includes one or more of the following: an identifier of the third AI model; metadata of the third AI model; a transmission rate supported by the core network device for transmitting the third AI model; a transmission delay supported by the core network device for transmitting the third AI model; an arrival time supported by the core network device for transmitting the third AI model; or a model transmission method supported by the core network device.

[0059] In one possible design, the method further includes: sending a request message to a core network device, wherein the request message is used to request the core network device to support capability parameters of the third AI model provided for the first communication device.

[0060] In one possible design, the method also includes: transmitting model transmission information corresponding to the first AI model to the first communication device; the model transmission information includes model information of the first AI model; or, the model transmission information includes the model information, and the model transmission information also includes a transmission method and / or an estimated completion time; the transmission method includes using user plane signaling or using control plane signaling.

[0061] In one possible design, the model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; or fourth indication information, where the fourth indication information is used to indicate a structure of the first AI model.

[0062] In a fourth aspect, an embodiment of the present application provides a communication method, which can be performed by a first communication device. The first communication device can be a terminal device or a chip system (or, chip) or other functional module in the terminal device. The method includes: receiving fifth information from a second communication device, the fifth information is used to indicate the transmission requirements of a first artificial intelligence AI model, and the first AI model is an AI model requested to be configured by the first communication device; sending third information to the second communication device, the third information includes first sub-information, the first sub-information indicates the ability parameters of the first communication device to receive the first AI model, and the third information is used to determine the transmission method of the first AI model; receiving second information from the second communication device, the second information is used to indicate the transmission method of the first AI model.

[0063] In one possible design, a transmission manner of the first AI function includes one or more of the following:

[0064] An access network device transmission mode, wherein the access network device transmission mode indicates that the first AI model is transmitted from the access network device to the first communication device; an OTT transmission mode, wherein the OTT transmission mode indicates that the first AI model is transmitted from the OTT to the first communication device; or a core network device transmission mode, wherein the core network device transmission mode indicates that the first AI model is transmitted from the core network device to the first communication device.

[0065] In one possible design, the fifth information indicates one or more of the following: the first AI model; the first AI function supported by the first AI model; the capability requested to be reported by the first communication device, or the reason for transmission.

[0066] In one possible design, the first sub-information includes one or more of the following: a storage capacity parameter of the first communication device; a computing capacity parameter of the first communication device; a communication capacity parameter of the first communication device; a transmission rate allowed by the first communication device; an arrival time of the first AI model expected by the first communication device; or a model transmission method supported by the first communication device.

[0067] In one possible design, the third information also includes second sub-information, where the second sub-information indicates capability parameters of a second AI model supported by the third-party application service OTT and provided to the first communication device, and the structure of the second AI model includes the first AI model.

[0068] In one possible design, the second sub-information includes one or more of the following: an identifier of the second AI model; an identifier of the OTT; metadata of the second AI model; a transmission rate supported by the OTT for transmitting the second AI model; a transmission delay supported by the OTT for transmitting the second AI model; an arrival time supported by the OTT for transmitting the second AI model; or a model transmission method supported by the OTT.

[0069] In one possible design, the method also includes: receiving model transmission information corresponding to the first AI model from the second communication device; the model transmission information includes model information of the first AI model; or, the model transmission information includes the model information, and the model transmission information also includes a transmission method and / or an estimated completion time; the transmission method includes using user plane signaling or using control plane signaling.

[0070] In one possible design, the model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; or fourth indication information, where the fourth indication information is used to indicate a structure of the first AI model.

[0071] In a fifth aspect, a communication device is provided. The communication device may be the second communication device described in any one of the first to fourth aspects. The communication device has the functions of the second communication device. The communication device may be, for example, the second communication device, or a larger device including the second communication device, or a functional module within the second communication device, such as a baseband device or a chip system. In one optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also referred to as a processing module) and a transceiver unit (sometimes also referred to as a transceiver module). The transceiver unit is capable of performing both transmitting and receiving functions. When the transceiver unit performs the transmitting function, it may be referred to as a transmitting unit (sometimes also referred to as a transmitting module); when the transceiver unit performs the receiving function, it may be referred to as a receiving unit (sometimes also referred to as a receiving module). The transmitting unit and the receiving unit may be the same functional module, referred to as a transceiver unit, which is capable of both transmitting and receiving functions; alternatively, the transmitting unit and the receiving unit may be different functional modules, with the transceiver unit being a collective term for these functional modules.

[0072] In an optional embodiment, the transceiver unit (or, the receiving unit) is used to receive first information, where the first information indicates the transmission requirements of the first communication device for the first artificial intelligence AI model to be applied; the first information is used to determine the transmission method of the first AI model; the transceiver unit (or, the sending unit) sends second information to the first communication device, where the second information is used to indicate the transmission method of the first AI model.

[0073] In an optional embodiment, the transceiver unit (or the sending unit) is used to send fifth information to the first communication device, the fifth information is used to indicate the transmission requirements of the first artificial intelligence AI model, and the first AI model is the AI ​​model requested to be configured by the first communication device; the transceiver unit (or the receiving unit) is used to receive third information from the first communication device, the third information includes first sub-information, the first sub-information indicates the ability parameters of the first communication device to receive the first AI model, and the third information is used to determine the transmission method of the first AI model. The transceiver unit (or the sending unit) is used to send second information to the first communication device, and the second information is used to indicate the transmission method of the first AI model.

[0074] In an optional embodiment, the communication device also includes a storage unit (sometimes also referred to as a storage module), and the processing unit is used to couple with the storage unit and execute the program or instructions in the storage unit, enabling the communication device to perform the functions of the second communication device described in any one of the first to fourth aspects above.

[0075] In a sixth aspect, a communication device is provided. The communication device may be the first communication device described in any one of the first to fourth aspects above. The communication device has the functions of the first communication device above. The communication device is, for example, a terminal device, or a larger device including a terminal device, or a functional module in a terminal device, such as a baseband device or a chip system. In an optional implementation, the communication device includes a baseband device and a radio frequency device. In another optional implementation, the communication device includes a processing unit (sometimes also referred to as a processing module) and a transceiver unit (sometimes also referred to as a transceiver module). For the implementation of the transceiver unit, please refer to the introduction of the seventh aspect.

[0076] In an optional embodiment, the transceiver unit (or, the sending unit) is used to send first information to a second communication device, where the first information is used to indicate the transmission requirements of the first communication device for the first artificial intelligence AI model to be applied; the first information is used to determine the transmission method of the first AI model; the transceiver unit (or, the receiving unit) is used to receive second information from the second communication device, where the second information is used to indicate the transmission method of the first AI model.

[0077] In an optional embodiment, the transceiver unit (or the receiving unit) is configured to receive fifth information from a second communication device, the fifth information being used to indicate a transmission requirement of a first artificial intelligence (AI) model, the first AI model being an AI model for which the first communication device is requested to be configured; the transceiver unit (or the sending unit) is configured to send third information to the second communication device, the third information including first sub-information, the first sub-information indicating the capability parameters of the first communication device for receiving the first AI model, and the third information being used to determine a transmission method for the first AI model. The transceiver unit (or the receiving unit) is configured to receive second information from the second communication device, the second information being used to indicate a transmission method for the first AI model.

[0078] In an optional embodiment, the communication device also includes a storage unit (sometimes also referred to as a storage module), and the processing unit is used to couple with the storage unit and execute the program or instructions in the storage unit, enabling the communication device to perform the functions of the terminal device described in any one of the first to fourth aspects above.

[0079] In the seventh aspect, a communication system is provided, comprising a first communication device and a second communication device, wherein the first communication device is used to execute the method executed by the first communication device as described in the second aspect or the fourth aspect, and the second communication device is used to execute the method executed by the second communication device as described in the first aspect or the third aspect.

[0080] In an eighth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store a computer program or instruction, which, when executed, enables the method executed by the first communication device or terminal equipment in the above aspects to be implemented.

[0081] In a ninth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the methods described in the above aspects to be implemented.

[0082] In a tenth aspect, a chip system is provided, comprising a processor and an interface, wherein the processor is configured to call and execute instructions from the interface so that the chip system implements the methods of the above aspects.

[0083] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] FIG1 is a schematic structural diagram of an access network device;

[0085] Figure 2 shows the framework of AI application in NR;

[0086] FIG3 is a schematic diagram of a network architecture used in an embodiment of the present application;

[0087] FIG4 is a flow chart of a communication method provided in an embodiment of the present application;

[0088] FIG5 is a flow chart of another communication method provided in an embodiment of the present application;

[0089] FIG6 is a flow chart of another communication method provided in an embodiment of the present application;

[0090] FIG7 is a flow chart of another communication method provided in an embodiment of the present application;

[0091] FIG8 is a flow chart of another communication method provided in an embodiment of the present application;

[0092] FIG9 is a schematic structural diagram of a device 900 provided in an embodiment of the present application;

[0093] FIG10 is a schematic structural diagram of a device 1000 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0094] The technical solutions provided in the embodiments of the present application can be applied to the fourth generation mobile communication technology (the 4th generation, 4G) system, such as the long term evolution (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., without specific limitation. In addition, the technical solutions provided in the embodiments of the present application can also be applied to device-to-device (D2D) scenarios, such as the NR-D2D scenario, etc., or can be applied to vehicle-to-everything (V2X) scenarios, such as the NR-V2X scenario, or intelligent driving, assisted driving, or intelligent connected vehicles and other fields. If applied to the D2D scenario, both parties in communication can be UEs; if applied to non-D2D scenarios, one party in communication can be a UE and the other party can be a network device (such as an access network device), or both parties in communication can be network devices. In the following introduction, the example in which the two parties in communication are a network device and a UE is taken as an example.

[0095] In the embodiments of the present application, the number of nouns, unless otherwise specified, means "singular noun or plural noun", that is, "one or more". "At least one" means one or more, and "plural" means two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. For example, A / B means: A or B. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, 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.

[0096] The ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish between multiple objects, and are not used to limit the size, content, order, timing, priority or importance of multiple objects. For example, the first resource unit and the second resource unit can be the same resource unit or different resource units, and this name does not indicate the difference in position, size, application scenario, priority or importance of the two resource units. In addition, the numbering of the steps in the various embodiments introduced in this application is only to distinguish different steps, and is not used to limit the order between the steps. For example, S401 may occur before S402, or may occur after S402, or may occur at the same time as S402.

[0097] Below, some terms or concepts in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0098] 1. In the embodiments of the present application, a terminal device is a device with wireless transceiver functions, which can be a fixed device, a mobile device, a handheld device (such as a mobile phone), a wearable device, an in-vehicle device, or a wireless device built into the above devices (such as a communication module, a modem, or a chip system, etc.). The terminal device is used to connect people, objects, machines, etc., and can be widely used in various scenarios, such as but not limited to the following scenarios: cellular communication, device-to-device communication (D2D), vehicle to everything (V2X), machine-to-machine / machine-type communication (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 wearable, smart transportation, smart city, drones, robots, and other scenarios. The terminal device may sometimes be referred to as user equipment (UE), terminal, access station, UE station, remote station, wireless communication device, or user device, etc. For ease of description, the terminal device will be described below using UE as an example.

[0099] 2. The network device in the embodiment of the present application is a device in a wireless network, such as a radio access network (RAN) node or a radio access network device that connects a terminal device to a wireless network. Currently, some examples of RAN nodes are: gNB, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved NodeB, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wifi) access point (AP), integrated access and backhaul (IAB), etc. In a network structure, a RAN node may also refer to a centralized unit (CU) or a distributed unit (DU), or a RAN node may also be composed of a CU and a DU. CU and DU can be understood as the division of RAN nodes from a logical functional perspective. The CU and DU are connected via the F1 interface; the CU can represent the gNB and is connected to the core network via the NG interface. Among them, the CU and DU can be physically separated or deployed together, and this embodiment of the present application does not specifically limit this. One CU can be connected to one DU, or multiple DUs can share one CU, which can save costs and facilitate network expansion. The division of CU and DU can be based on the protocol stack. One possible way is to deploy the radio resource control (RRC), service data adaptation protocol stack (SDAP) and packet data convergence protocol (PDCP) layer in the CU, and the remaining radio link control (RLC) layer, media access control (MAC) layer and physical layer (PHY) in the DU. The embodiment of the present application does not completely limit the above-mentioned protocol stack division method, and there may be other division methods.

[0100] 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, as shown in Figure 1. The CU-CP is responsible for control plane functions, mainly including RRC and PDCP-control (control, C). PDCP-C is mainly responsible for encryption and decryption, integrity protection, data transmission, etc. of the control plane data. The CU control plane CU-CP also includes a further divided architecture, that is, the existing CU-CP is further divided 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 (that is, 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 encryption and decryption, integrity protection, header compression, sequence number maintenance, data transmission, etc. of the data plane. The CU-CP and CU-UP are connected via an E1 interface. The CU-CP represents a RAN node, connected to the core network via the NG interface and to the DU via the F1-C (control plane). Another possible implementation is to also place the PDCP-C in the CU-UP.

[0101] In the embodiments of the present application, the communication device for implementing the network device function may be a network device, or may be a device capable of supporting the network device to implement the function, such as a chip system, which may be installed in the network device. In the technical solutions provided in the embodiments of the present application, the technical solutions provided in the embodiments of the present application are described by taking the network device as an example of the device for implementing the network device function being a network device.

[0102] The network equipment and terminal equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on the water; and can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the network equipment and terminal equipment.

[0103] Network devices and terminal devices, as well as terminal devices and terminal devices, can communicate through licensed spectrum (licensed spectrum), can communicate through unlicensed spectrum (unlicensed spectrum), or can communicate through both licensed spectrum and unlicensed spectrum at the same time. Network devices and terminal devices, as well as terminal devices and terminal devices, can communicate through spectrum below 6 gigahertz (GHz), can communicate through spectrum above 6G, or can communicate through spectrum below 6G and spectrum above 6G at the same time. The embodiments of the present application do not limit the spectrum resources used between network devices and terminal devices.

[0104] 3. 3GPP has proposed applying AI to NR systems. Through intelligent data collection and analysis, network performance and user experience can be improved. 3GPP has initially defined a framework for AI applications in NR, as shown in Figure 2. The data source can store data from the gNB, gNB-CU, gNB-DU, UE, or other management entities. The data source serves as a database for AI model training and data analysis and inference. For example, "Data Collection" in Figure 2 represents the data source. The model training host analyzes the training data provided by the data source to generate an optimal AI model. For example, the "Model Training" box in Figure 2 represents the model training host. The model inference host uses this AI model to generate AI-based predictions about network operation based on the data provided by the data source, or to guide network policy adjustments. For example, the "Model Inference" box in Figure 2 represents the model inference host. These policy adjustments are centrally planned by the actor entity and sent to multiple network entities for execution. At the same time, after the network applies the adjusted strategy, the specific performance information of the network will be input into the data source again for storage.

[0105] 4. AI model.

[0106] An AI model, also known as an AI algorithm (or AI operator), is a general term for mathematical algorithms built on the principles of artificial intelligence, and is also the basis for using AI to solve specific problems. The types of AI models are not limited in the embodiments of this application. For example, an AI model can be a machine learning model, a deep learning model, or a reinforcement learning model. The AI ​​model can also be replaced by a model level (ML) model.

[0107] Machine learning is an approach to artificial intelligence. Its goal is to design and analyze algorithms (i.e., models) that enable computers to automatically "learn." These algorithms are called machine learning models. Machine learning models automatically analyze data to identify patterns and use these patterns to make predictions about unknown data. There are many types of machine learning models. For example, depending on whether the model training relies on labels corresponding to the training data, machine learning models can be divided into supervised learning models and unsupervised learning models.

[0108] Deep learning is a new technical field that has emerged from the research of machine learning. Specifically, deep learning is a method within machine learning that relies on learning deep representations of data. Deep learning interprets data by building neural networks that mimic the analytical learning of the human brain. While nearly all features in machine learning require the identification and encoding of subject matter experts, deep learning algorithms attempt to independently learn features from data. Algorithms designed based on deep learning principles are called deep learning models.

[0109] Reinforcement learning is a specialized field within machine learning. It involves the process of continuously learning optimal strategies, making sequential decisions, and maximizing rewards through the interaction between an agent and its environment. Simply put, reinforcement learning involves learning what to do (i.e., how to map the current situation into actions) to maximize a numerical reward signal. The agent is not told what actions to take; instead, it must independently discover, through experimentation, which actions yield the most lucrative rewards. Reinforcement learning differs from supervised and unsupervised learning in machine learning. Supervised learning involves learning from externally provided labeled training data (task-driven), while unsupervised learning seeks to uncover hidden structures in unlabeled data (data-driven). Reinforcement learning involves the process of finding optimal solutions through trial and error. The agent must exploit past experience to gain rewards while also conducting trials to expand its future action options (i.e., learn from its mistakes). Algorithms designed based on reinforcement learning are called reinforcement learning models.

[0110] Before any AI model can be used to solve a specific technical problem, it must be trained. AI model training involves using a specified initial model to calculate training data and then adjusting the parameters of the initial model based on the calculation results, so that the model gradually learns certain patterns and acquires specific functions. After training, a stable AI model can be used for inference. AI model inference is the process of using a trained AI model to calculate input data and obtain predicted inference results (also known as output data).

[0111] 5. AI capabilities, or AI-based use cases.

[0112] Currently, 3GPP has designed some basic application scenarios for AI applications on the RAN side, such as channel state information (CSI)-reference signal (RS) feedback enhancement (referred to as CSI feedback enhancement), beam management enhancement, or positioning accuracy enhancements. The following briefly introduces these scenarios. Among them, if the UE supports a certain AI scenario, it can also be considered that the UE has the AI ​​function.

[0113] (1) CSI-RS feedback enhancement.

[0114] CSI is a channel attribute of the communication link and is the channel quality information sent by the UE to the access network device. The UE sends the 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. The CSI sent by the UE may include one or more of the following: channel quality indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CSI-RS resource indicator, CRI), SS / PCH block resource indicator (SSBRI), layer indicator (LI), rank indicator (RI), or layer 1 reference signal receiver power (L1-RSRP). The rank is the rank of the antenna matrix in the multiple-input multiple-output (MIMO) scheme, representing one or more parallel valid data streams, and the RI is used to indicate the number of valid data layers of the physical downlink shared channel (PDSCH).

[0115] CSI-RS feedback enhancement may include sub-scenarios such as CSI compression, CSI prediction, and CSI-RS configuration signaling reduction. CSI compression may include compression in at least one of the spatial, time, or frequency domains.

[0116] Taking CSI-RS compression as an example, one implementation process is as follows:

[0117] A1. The access network device and the UE first exchange a dictionary.

[0118] In addition, the access network device pre-trains a model based on factors such as the UE's capabilities and the access network device's requirements. This model, for example, includes 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 a quantizer to the UE. The quantizer is used to quantize the compressed signal.

[0119] A2. The UE may obtain a first matrix according to the measured downlink channel matrix and the encoder network.

[0120] For example, the UE may input a measured downlink channel matrix into the encoder network to obtain a first matrix output by the encoder network. Alternatively, the UE may preprocess the measured downlink channel matrix and then input the preprocessed downlink channel matrix into the encoder network to obtain a first matrix output by the encoder network. Furthermore, the UE may compress the first matrix using an existing dictionary, quantize the compressed signal using a quantizer, and then transmit the quantization result to the access network device.

[0121] A3. The access network device reversely recovers the original downlink channel matrix based on the dictionary, the decoder network, and the quantization result from the UE.

[0122] (2) Enhanced beam management.

[0123] AI-based beam management enhancements can include sub-scenarios such as beam scanning matrix prediction and optimal beam prediction. One implementation process of beam management enhancements is as follows:

[0124] B1. Initial model generation. 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 device, including, for example, received signal quality information on each beam. The access network device can perform training based on the scanning results of these UEs to obtain a sparse scanning matrix, or a sparse model, which is typically unique to a cell. The sparse model can include information about the preferred beam.

[0125] B2. The access network device sends the sparse model to the UE (possibly via a system information block (SIB) message, for example). The UE performs beam scanning in phase P1 based on the sparse matrix and sends the scanning results, for example, to the access network device. During phase P1, the access network device transmits reference signals via beams over a wide range. The UE selects the optimal beam based on measurements and sends information about the optimal beam to the access network device.

[0126] B3. The access network device obtains the optimal beam based on the sparse scanning result.

[0127] For example, the access network device can perform a beam-based P2 scan on the UE, and the UE can send the identifier of the optimal beam to the access network device. P2 scanning means that the access network device sends a reference signal using a narrow beam within a narrow range. The UE selects the optimal beam based on the measurement and sends the optimal beam information to the access network device.

[0128] (3) Enhanced positioning accuracy.

[0129] AI-based positioning accuracy enhancement is mainly used to improve positioning accuracy. One implementation process of positioning accuracy enhancement is as follows:

[0130] C1. Collecting raw data through a reference UE controlled by an operator. The raw data may include, for example, UE coordinate information and / or line of sight (LOS) / non-line of sight (NLOS) status information.

[0131] C2, the location management function (LMF), and the access network equipment train models separately. The model trained by the LMF can be used to infer the final positioning information of the UE (such as the latitude and longitude of the UE) based on the raw data. The model trained by the gNB can be used to infer the LOS / NLOS judgment result based on the raw data.

[0132] 6. The collaboration level of AI functions.

[0133] Taking into account the application of AI functions (such as the deployment of AI models) and factors such as the interaction between the UE and the network side, three levels of collaboration are currently available: level 0, level 1, and level 2, which are introduced below.

[0134] Level 0, also known as collaboration level 0, is a no collaboration level.

[0135] At level 0, 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 all completed within the access network device and have no impact on the air interface.

[0136] Level 1, also known as collaboration level 1, is a signaling-based collaboration without model transfer.

[0137] At level 1, the access network device sends a dictionary to the UE, enabling the UE to assist the access network device in AI reasoning, which has a certain impact on the air interface. The AI ​​model can also be deployed within the UE, and the UE can compress and encode the downlink channel matrix based on the AI ​​model and dictionary deployed by the UE. The UE and access network device can jointly train the AI ​​model, for example, through federated learning. Over the air interface, the AI ​​model is not directly transmitted between the UE and the access network device, but related parameters of the AI ​​model can be transmitted. In addition, considering the deployment of the AI ​​model, level 1 can be further subdivided into level 1A and level 1B.

[0138] Level 1A: Signaling-based collaboration for a single-sided model without model transfer. Under level 1A, the AI ​​model can be deployed in the access network device or the UE, that is, the AI ​​model is deployed on a single side.

[0139] Level 1B, signaling-based collaboration for a two-sided model without model transfer. Under level 1B, the access network device and the UE can deploy AI models separately, that is, the AI ​​model is deployed on both sides.

[0140] Level 2, also known as collaboration level 2, is a signaling-based collaboration with model transfer level.

[0141] At level 2, both access network devices and UEs can have AI capabilities. For example, AI models can be deployed on each device and each can perform inference based on the deployed AI models. Over the air interface, the access network device and UE can directly transmit AI models.

[0142] In addition to the above three collaboration levels, other collaboration levels may also be included. For example, future communication systems may also support some collaboration levels, which is not limited in the embodiments of the present application.

[0143] 7. Distribution of AI models.

[0144] In some potential application scenarios, the UE requires AI capabilities and must download AI models from the network to implement these capabilities. Currently, UE AI capabilities can be divided into two categories: The first category involves the UE independently completing specific services based on an AI model, such as AI-based encoding of the CSI channel. The second category involves the UE assisting access network equipment in inference or training an AI model, but the UE currently lacks an AI model or requires an update.

[0145] The transmission methods of the AI ​​model designed in the embodiments of the present application may include: (1) access network device transmission method, in which the AI ​​model is transmitted from the access network device to the UE. (2) core network device transmission method, in which the AI ​​model is transmitted from the core network device to the UE. (3) third-party server transmission method, such as OTT (over-the-top) transmission method or OAM transmission method. Among them, OTT refers to providing various application services to users through the Internet. This type of application is different from the communication services currently provided by operators. It only uses the operator's network, and the service is provided by a third party outside the operator.

[0146] For example, the node that sends the AI ​​model to the UE may be an access network device, a core network device other than LMF, LMF, or a third-party server.

[0147] Exemplarily, Figure 3 shows a communication network architecture applicable to an embodiment of the present application. The first communication device is capable of communicating with a network device. The first communication device may be a UE, or a chip or chip system in the UE, or a functional module in the UE, such as a processing module. The second communication device is capable of communicating with the UE, for example, the UE may send AI capability information of the UE to the second communication device. The second communication device is, for example, an access network device; or, the second communication device is a chip or chip system in the access network device, or the second communication device is a functional module included in the access network device, such as a CU, or a CU-CP, or a CU-CP2, etc.; or, the second communication device is a larger device including an access network device. The access network device is, for example, the aforementioned RAN node, and reference can be made to the previous text for an introduction to the RAN node and the UE.

[0148] In order to better describe the embodiments of the present application, the following describes the methods provided by the embodiments of the present application in conjunction with the accompanying drawings. In the accompanying drawings corresponding to the various embodiments of the present application, all steps indicated by dotted lines are optional steps.

[0149] An embodiment of the present application provides a communication method, as shown in FIG4 , which is a flow chart of the communication method. The method can be applied to the network architecture shown in FIG3 . For example, the first communication device in the method is the first communication device in FIG3 , and the second communication device involved in the method is the second communication device in FIG3 . The first communication device may be a UE, or a chip or chip system in the UE, or a functional module in the UE. In the subsequent description, the first communication device is taken as an example of a UE. The second communication device is, for example, an access network device; or the second communication device is a chip or chip system in the access network device, or the second communication device is a functional module included in the access network device, such as a CU, or a CU-CP, or a CU-CP2, etc.; or the second communication device is a larger device including an access network device. In the subsequent description, the second communication device is taken as an access network device as an example.

[0150] S401: A UE sends first information to an access network device. Correspondingly, the access network device receives the first information from the UE.

[0151] The first information is used to indicate the UE's transmission requirements for the first AI model to be applied. The first information may also be referred to as model transmission requirement information, or may be referred to by other names. Optionally, the first information may indicate one or more of the following: an expected time, an identifier of the first AI model, metadata of the first AI model, a first AI function supported by the first AI model, an expected minimum transmission delay, a second AI function to be executed after completing the first AI function, or the UE's mobility path. The expected minimum transmission delay may also be a transmission delay requirement. AI functions (such as the first AI function and the second AI function) may be understood as AI use cases. The first AI function may be referred to as the first AI use case, and the second AI function may be referred to as the second AI use case. In some embodiments, the first AI function supported by the first AI model may also be understood as the first AI use case to be executed. The expected time may be any of a time period, a time point, or a time index. The first AI use case may be CSI feedback enhancement, beamforming enhancement, or positioning enhancement, or other AI use cases. The second AI use case may be CSI feedback enhancement, beamforming enhancement, or positioning enhancement, or other AI use cases.

[0152] Exemplarily, the metadata of the model may indicate one or more of the following: the input parameters used by the model, the output parameters of the model, the version number corresponding to the model, the formats supported by the model, the model's requirements for UE capabilities, the device vendor identifiers to which the model can be applied, the scenarios in which the model can be used, the AI ​​use cases supported by the model, the complexity of the model's calculations, the processing power requirements, the range of the model's size, the model's performance (such as accuracy, etc.), or the functions possessed by the model.

[0153] After receiving the first information, the access network device can determine the transmission method of the first AI model based on the first information.

[0154] S402: The access network device sends second information to the UE. In response, the UE receives the second information from the access network device. The second information is used to indicate the transmission mode of the first AI model.

[0155] The transmission mode of the first AI model may include one or more of the following: an access network device transmission mode, a third-party server transmission mode, or a core network device transmission mode. The access network device transmission mode indicates that the first AI model is transmitted from the access network device to the UE. The third-party server transmission mode indicates that the first AI model is transmitted from the third-party server to the UE. The core network device transmission mode indicates that the first AI model is transmitted from the core network device to the UE. The third-party server may be a third-party device such as an OAM or OTT device.

[0156] Exemplarily, the access network transmission mode may include one or more of the following:

[0157] In mode 1a, the access network device transmits / sends the first AI model to the UE via control plane signaling. For example, the control plane signaling may be RRC signaling.

[0158] In mode 1b, the access network device transmits / sends the first AI model to the UE through user plane (UP) data.

[0159] Exemplarily, the core network device transmission mode may include one or more of the following:

[0160] In method 2a, core network devices other than LMF transmit / send the first AI model to the UE through non-access stratum (NAS) signaling.

[0161] In mode 2b, a core network device other than the LMF transmits / delivers the first AI model to the UE via user plane data. For example, the core network device other than the LMF may be an AMF or SMF device.

[0162] Mode 3a: LMF transmits / sends the first AI model to the UE through LTE positioning protocol (LPP) signaling.

[0163] Mode 3b: LMF transmits / sends the first AI model to the UE through user plane data.

[0164] In some embodiments, different AI use cases and model deployments have different model requirements. Consequently, they place varying demands on model functionality, size, and transmission latency. As an example, see Table 1, which illustrates the relationship between different methods and AI use cases. For ease of description, Method 4 in Table 1 represents a third-party server transmission method.

[0165] Table 1

[0166] In a possible implementation, the information used to determine the transmission method of the first AI model may include, in addition to the first information, one or more of the following: the UE's ability parameters for receiving the first AI model, the OTT's ability parameters for transmitting the AI ​​model, or the core network device's ability parameters for transmitting the AI ​​model.

[0167] Exemplarily, the capability parameters of the UE for receiving the first AI model may include one or more of the following: a storage capability parameter of the UE, a computing capability parameter of the UE, a communication capability parameter of the UE, a transmission rate allowed by the UE, an arrival time of the first AI model expected by the UE, and a model transmission mode supported by the UE.

[0168] Exemplarily, the capability parameters of the OTT transmission AI model may include one or more of the following: an identifier of the second AI model, an identifier of the OTT, metadata of the second AI model, a transmission rate supported by OTT for transmitting the second AI model, a transmission delay supported by OTT for transmitting the second AI model, an arrival time supported by OTT for transmitting the second AI model, or a model transmission mode supported by OTT. The second AI model may be an AI model provided by OTT to the UE. The second AI model may include the first AI model. For example, the first AI model is a sub-model in the second AI model, or the second AI model is the first AI model. In some embodiments, the second AI model may include multiple AI models (also referred to as multiple AI sub-models), and the embodiments of the present application do not limit the number of AI models of the second AI model.

[0169] Exemplarily, the capability parameter of the core network device for transmitting an AI model may include one or more of the following: an identifier of a third AI model, metadata of the third AI model, a transmission rate supported by the core network device for transmitting the third AI model, a transmission delay supported by the core network device for transmitting the third AI model, an arrival time supported by the core network device for transmitting the third AI model, or a model transmission mode supported by the core network device. The third AI model may be an AI model supported by the core network device for providing to the UE. The third AI model may include the first AI model. For example, the first AI model is a sub-model of the third AI model, or the third AI model is the first AI model. In some embodiments, the third AI model may include multiple AI models (also referred to as multiple AI sub-models). The embodiments of the present application do not limit the number of AI models of the third AI model.

[0170] There may be multiple ways for the access network device to obtain information used to determine the transmission mode of the first AI model, as illustrated below.

[0171] (1) The information used by the access network device to determine the transmission mode of the first AI model includes the UE's capability parameter for receiving the first AI model. The UE sends the UE's capability parameter for receiving the first AI model to the access network device. For example, the UE sends third information to the access network device, and the third information includes first sub-information. The first sub-information indicates the UE's capability parameter for receiving the first AI model. For example, the first sub-information may include one or more capability parameters of the UE for receiving the first AI model.

[0172] Mode A1: The first possible mode in which the access network device obtains the capability parameters of the UE to receive the first AI model.

[0173] The UE may periodically send the model transmission capability parameters of the AI ​​model supported by itself to the access network device. For example, the UE periodically sends the third information to the access network device. Optionally, the access network device may indicate to the UE the period for sending its own capability parameters. Thus, the UE may periodically send the model transmission capability parameters of the AI ​​model supported by itself to the access network device according to the period indicated by the access network device.

[0174] Mode A2: A second possible mode in which the access network device obtains the capability parameters of the UE for receiving the first AI model.

[0175] The access network device may provide the UE with first indication information, where the first indication information is used to indicate conditions that must be met when the UE reports the third information. Thus, based on the first indication information, when the conditions are met, the UE may send the third information to the access network device, i.e., send the UE's capability parameter for receiving the first AI model to the access network device.

[0176] Exemplarily, the first indication information may include one or more of the following: an identifier of the triggering event, a transmission rate variation range satisfied by triggering the UE to report the third information, a transmission rate range satisfied by triggering the UE to report the third information, a reception delay variation range satisfied by triggering the reporting of the third information, or a reception delay range satisfied by triggering the reporting of the third information.

[0177] The trigger event identifier can be the ID of the triggered event, used to identify the trigger event. The trigger event indicates that the UE is triggered to report the third information. The transmission rate change range that triggers the UE to report the third information can be a transmission rate change threshold or a transmission rate change interval. The transmission rate change threshold can instruct the UE to send the third information to the access network device when the transmission rate change value for a period of time is greater than the rate change threshold. The transmission rate change interval can instruct the UE to send the third information to the access network device when the transmission rate change value of the UE falls within the transmission rate change interval. The transmission rate range that triggers the UE to report the third information can be a transmission rate threshold or a transmission rate interval. The transmission rate threshold can instruct the UE to send the third information to the access network device when the transmission rate of the UE is greater than the transmission rate threshold. The transmission rate interval can instruct the UE to send the third information to the access network device when the transmission rate of the UE falls within the transmission rate interval. The reception delay change range that triggers the reporting of the third information can be a reception delay change threshold or a reception delay change interval. The reception delay variation threshold indicates that when the change value of the UE's reception delay over a period of time is greater than the reception delay variation threshold, the third information is sent to the access network device. The reception delay variation interval indicates that when the change value of the UE's reception delay is within the reception delay variation interval, the third information is sent to the access network device. The reception delay range that triggers reporting of the third information may adopt the reception delay threshold or the reception delay interval. When the reception delay threshold indicates that the UE's reception delay is greater than the reception delay threshold, the third information is sent to the access network device. When the reception delay of the UE is within the reception delay interval, the third information is sent to the access network device.

[0178] In a possible implementation, the access network device may also instruct the UE which capability parameters to report specifically. In one example, the access network device sends a second indication message to the UE. The second indication message is used to instruct the UE to choose to report some or all of the parameters in the third information based on the current capability. For example, the UE's current computing capability is sufficient, and it is not necessary to report its own computing capability parameters. For another example, the UE supports all model transmission modes and it is not necessary to report the supported model transmission modes. For another example, if the UE's storage capacity is limited, it is possible to report its own storage capacity parameters. The UE can choose which capability parameters to report based on its own capabilities. The access network device may send the first indication message and the second indication message to the UE together, or may send them separately.

[0179] In another example, the access network device sends third indication information to the UE, where the third indication information indicates the parameters that the UE is requested to report. In this example, the access network device can instruct the UE on which parameters to report based on demand, indicating the specific parameters to the UE. The access network device can send the first indication information and the third indication information to the UE together or separately.

[0180] Mode A3: The third possible mode in which the access network device obtains the capability parameters of the UE for receiving the first AI model.

[0181] The UE sends the first information to the access network device, and may also send the UE's ability parameter for receiving the first AI model to the access network device, that is, send the third information to the access network device. The UE may send the first information and the third information to the access network device together, or send them separately.

[0182] (2) The information used by the access network device to determine the transmission method of the first AI model includes the capability parameters of the OTT transmission AI model.

[0183] Method B1 is the first possible way for access network equipment to obtain the capability parameters of the OTT transmission AI model.

[0184] The access network device sends indication information 1 to OTT, where indication information 1 instructs OTT to report the capability parameters of the transmission AI model. Thus, upon receiving indication information 1, OTT sends the capability parameters of the OTT transmission AI model to the access network device. In some embodiments, indication information 1 may also include one or more of the following: an identifier of the first AI model, metadata of the first AI model, or a reason for the request, etc. For example, the reason for the request may be an AI use case to be executed and / or a transmission capability limitation of the access network device, etc. Exemplarily, the access network device may send indication information 1 to OTT after receiving the first information sent by the UE.

[0185] Method B2 is the second possible way for access network equipment to obtain the capability parameters of the OTT transmission AI model.

[0186] The UE can obtain the OTT transmission AI model capability parameters from the OTT and then send them to the access network device. Referring to FIG5 , a flow chart of the communication method provided in an embodiment of the present application is shown.

[0187] S501: The UE obtains capability parameters of an OTT transmission AI model from the OTT. In some possible implementations, the UE may determine the first information based on the capability parameters of the OTT transmission AI model and the AI ​​use case that the UE needs to execute.

[0188] S502-S503, refer to S401-S402, and will not be repeated here.

[0189] Method B3 is the third possible way for access network equipment to obtain the capability parameters of the OTT transmission AI model.

[0190] The UE can obtain the capability parameters of the OTT transmission AI model from the OTT and then send them to the access network device.

[0191] In one example, the UE may periodically obtain the capability parameters of the OTT transmission AI model and then periodically send the UE's capability parameters for receiving the AI ​​model to the access network device. For example, the UE periodically sends third information to the access network device, where the third information includes not only the first sub-information described above but also the second sub-information indicating the capability parameters of the OTT transmission AI model.

[0192] In another example, the access network device may indicate a condition for the UE to report the third information. For example, the access network device may send first indication information to the UE, where the first indication information is used to indicate a condition that the UE must meet to report the third information. Thus, the UE may send the third information to the access network device based on the first indication information when the condition is met.

[0193] 6, which is a flow chart of a communication method according to an embodiment of the present application, illustrates a process of exchanging capability parameters between an access network device and a UE.

[0194] S601: The access network device sends fourth information to the UE. The fourth information may include first indication information, or the fourth information may include first indication information and second indication information, or the fourth information may include first indication information and third indication information. The first indication information, the second indication information, and the third indication information are described above and are not repeated here.

[0195] S602: The UE obtains the capability parameters of the OTT transmission AI model from the OTT.

[0196] S603, the UE sends third information to the access network device. The third information includes the first sub-information and / or the second sub-information. For example, when the fourth information includes the second indication information, the second indication information indicates which parameters in the capability parameters the UE selects to report based on the current capability. The specific capability parameters may include which parameters may be specified by the protocol or may be pre-configured by the access network device. In some scenarios, the UE may not report its own capability parameters and may only report the capability parameters of the OTT transmission AI model. In other scenarios, the UE may also report its own capability parameters without reporting the capability parameters of the OTT transmission model. In some scenarios, the UE may also report both its own capability parameters and the capability parameters of the OTT transmission AI model. For another example, the fourth information includes the third indication information, and the third indication information indicates the parameters requested to be reported by the UE, such as a parameter identifier. The parameters requested to be reported by the UE may include only the UE's capability parameters, or only the capability parameters of the OTT transmission AI model, or both the UE's capability parameters and the capability parameters of the OTT transmission AI model.

[0197] (2) The information used by the access network device to determine the transmission method of the first AI model includes the capability parameters of the core network device to transmit the AI ​​model.

[0198] Method C1 is the first possible method for access network equipment to obtain the capability parameters of core network equipment to transmit AI models.

[0199] The access network device can instruct the core network device to periodically send the capability parameters of the core network transmission AI model. For example, the access network device can indicate the reporting period to the core network device, so that the core network device periodically sends the capability parameters of the core network transmission AI model to the access network device according to the reporting period.

[0200] Method C2 is the second possible method for the access network device to obtain the core network device's AI model transmission capability parameters. The access network device may also send reporting conditions to the core network device. For example, the reporting condition may be a change in the core network device's transmission capability. Another example is that the change range of a capability parameter of the core network device exceeds a threshold, or the current value of a capability parameter reaches a set threshold. Based on the reporting conditions, the core network device sends the core network device's AI model transmission capability parameters to the access network device.

[0201] Mode C3 is the third possible way for the access network device to obtain the capability parameters of the core network device for transmitting the AI ​​model. The access network device may also request the core network device to transmit the capability parameters of the AI ​​model after receiving the first information sent by the UE. For example, after receiving the first information sent by the UE, the access network device sends a request message to the core network device, and the request message is used to request the core network device to report the capability parameters of the AI ​​model. Thus, after receiving the request message, the core network device sends the capability parameters of the AI ​​model to the access network device. The request information may include one or more of the identifier of the AI ​​model, the metadata of the AI ​​model, or the reason for the request.

[0202] In some possible implementations, the method of transmitting the AI ​​model based on the user plane (UP) plane can establish a PDU session through the core network device and then transmit it based on the UP plane. Therefore, the access network device can obtain the model transmission capability information of the core network device (for example, AMF) and confirm that some models can be transmitted by the user plane, which can include some models sent directly by the access network device based on the user plane data (which can be understood as the DRB directly established by the gNB to transmit the AI ​​model), and some models that need to be sent by the core network device to execute user plane data (which can be understood as the relevant DRB in the PDU session established by the core network device to transmit the model).

[0203] In a possible implementation, the access network device may also send the capability parameters of the access network device to transmit the AI ​​model to the UE. Exemplarily, the access network device may send the capability parameters of the access network device to transmit the AI ​​model to the UE in a broadcast / unicast manner. The capability parameters of the access network device to transmit the AI ​​model can be used by the UE to determine its own transmission requirements for the first AI model to be applied. In some application scenarios, the UE can determine the UE's transmission requirements for the first AI model to be applied based on the capability parameters of the access network device to transmit the AI ​​model. In other application scenarios, the UE can determine the UE's transmission requirements for the first AI model to be applied based on the capability parameters of the access network device to transmit the AI ​​model and the capability parameters of the OTT transmission AI model (and the AI ​​use case to be executed). For example, the capability parameters of the access network device to transmit the AI ​​model may include one or more of the following: an identifier of the AI ​​model supported by the access network device, metadata of the AI ​​model supported by the access network device, whether the access network device supports dual connectivity (DC) transmission, or information such as the model transmission capability of the neighboring access network device.

[0204] In some embodiments, after the access network device obtains the information used to determine the transmission mode of the AI ​​model for the UE, it can also send this information to the neighboring access network device. For example, when the UE switches from the access network device to the neighboring access network device, the access network device can carry this information in the switching request message. For another example, the access network device can periodically send information used to determine the transmission mode of the AI ​​model for the UE to the neighboring access network device. For another example, the access network device can send information used to determine the transmission mode of the AI ​​model for the UE to the neighboring access network device when the sending conditions are met. For example, the sending condition may be that the information used to determine the transmission mode of the AI ​​model for the UE changes. The neighboring access network device receives the information used to determine the transmission mode of the AI ​​model for the UE, and can also determine the transmission mode of the AI ​​model for the UE according to demand.

[0205] The communication method provided in the embodiment of the present application is described below in conjunction with the application scenario. Referring to Figure 7, a flow chart of a communication method provided in an embodiment of the present application is shown. In Figure 7, the information used to determine the transmission method of the AI ​​model for the UE includes the UE's transmission requirements for the first AI model to be applied, the UE's ability parameters for receiving the AI ​​model, the OTT transmission AI model's ability parameters, and the core network device's ability parameters for transmitting the AI ​​model is taken as an example. It should be noted that the way in which the access network device in Figure 7 obtains the UE's ability parameters for receiving the AI ​​model, the OTT transmission AI model's ability parameters, and the core network device's ability parameters for transmitting the AI ​​model is only an example, and any of the above-described methods can be adopted, and this application does not limit it.

[0206] S701: The UE obtains capability parameters of an OTT transmission AI model from the OTT. The UE may determine first information based on the capability parameters of the OTT transmission AI model and its own AI use case to be executed.

[0207] S702, see S401, no further details will be given here.

[0208] S703, optionally, the UE sends capability information of the UE receiving the first AI model and capability information of the OTT transmission AI model to the access network device.

[0209] S704, optionally, the access network device obtains capability information of the core network device for transmitting the AI ​​model from the core network device.

[0210] S705: The access network device determines a transmission mode for the first AI model.

[0211] In one example, the transmission mode of the first AI model includes the transmission mode of the access network device. S706 is then executed, and the access network device sends model transmission information corresponding to the first AI model to the UE. For example, the model transmission information may be included in the second information. The model transmission information may include model information of the first AI model; or, the model transmission information includes model information, and the model transmission information also includes the transmission mode and / or estimated completion time adopted by the access network device. The transmission mode adopted by the access network device includes adopting a user plane signaling mode or a control plane signaling mode. Exemplarily, the model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; or fourth indication information, wherein the fourth indication information is used to indicate the structure of the first AI model. Further, the access network device completes the transmission of part or all of the structure of the first AI model.

[0212] Optionally, the access network device may no longer send model transmission information corresponding to the first AI model to the UE, and directly complete the transmission of part or all of the structure of the first AI model to the UE.

[0213] In another example, the transmission mode of the first AI model includes an OTT transmission mode. Then, S707 is executed, and the access network device sends model transmission information of the OTT transmission of the first AI model to the UE. For example, the model transmission information of the OTT transmission of the first AI model can be included in the second information.

[0214] S708: The UE forwards model transmission information for transmitting the first AI model by the OTT to the OTT. The model transmission information for transmitting the first AI model by the OTT includes model information of the first AI model; alternatively, the model transmission information includes model information, and the model transmission information also includes an estimated completion time. Furthermore, the OTT completes the transmission of part or all of the structure of the first AI model.

[0215] In another example, the transmission mode of the first AI model includes a core network device transmission mode. S709 is then executed, and the access network device sends model transmission information of the core network device transmitting the first AI model to the core network device. Further, the core network device can complete the transmission of part or all of the structure of the first AI model based on the model transmission information of the first AI model. The model transmission information of the core network device transmitting the first AI model includes the model information of the first AI model; or, the model transmission information of the core network device transmitting the first AI model includes the model information, and the model transmission information also includes the transmission mode and / or the estimated completion time adopted by the core network device. The transmission mode adopted by the core network device can be NAS signaling, LPP signaling, or UP data. Further, the core network device completes the transmission of part or all of the structure of the first AI model.

[0216] Illustratively, the estimated completion time mentioned above may be one or more of a time point, a time period, or a time mark.

[0217] Exemplarily, the above-mentioned model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; or fourth indication information, where the fourth indication information is used to indicate the structure of the first AI model.

[0218] The fourth indication information may adopt one or more of the following indication methods: model segmentation indication, bit indication, structure indication, or parameter indication. In some scenarios, the UE and the access network device need to cooperate to complete a certain function. The first AI model may be a sub-model of an AI model configured on the UE and the access network device. Alternatively, multiple models are trained on the access network device, the core network device, or the OTT, and the first AI model is only one of the multiple models trained by the access network device, the core network device, or the OTT.

[0219] It should be noted that the transmission mode of the first AI model determined by the access network device may include only one or multiple transmission modes. In the case of multiple transmission modes, the transmission of the first AI model may be completed by multiple devices.

[0220] Model segmentation indication, which indicates the segment to which the part transmitted by the device belongs in the first AI model. For example, the first AI model is divided into two segments, and the part transmitted by the device is the first 50% of the first AI model. Bit indication, which indicates the position of the part transmitted by the device in the first AI model through bits. Structure indication, which indicates that the first AI model is to be packaged and sent directly. Parameter indication, which can indicate the specific structure of the model included in the first AI model (for example, the number of layers included in the first AI model, the number of neurons in each layer, or the identifier of the sub-model included in the first AI model) and the network parameters used in each layer (which can be network parameters that are not 0 or network parameters that need to be updated, and can be transmitted in a compressed manner).

[0221] S710, at least one of the core network device, the access network device, or the OTT device transmits the first AI model to the UE according to the received model transmission information.

[0222] Through the solution provided by the embodiments of the present application, the UE can determine the transmission requirements of the AI ​​model, so that the access network device determines which transmission mode to use for the UE and indicates the adopted transmission mode to the UE. The transmission mode determined for the UE is adapted to the UE's transmission requirements, avoiding the problem of mismatch between the transmission requirements and the transmission mode.

[0223] The above description is from the perspective of the UE sending the model transmission requirement to the access network device. Next, another communication method provided by an embodiment of the present application is introduced. In this method, the access network device determines the transmission requirement of the first AI model and sends it to the UE. The access network device determines the transmission method of the first AI model for the UE and indicates the adopted transmission method to the UE. See Figure 8, which is a flow chart of this method. For example, the first communication device in this method is the first communication device in Figure 3, and the second communication device involved in this method is the second communication device in Figure 3. The first communication device can be a UE, or a chip or chip system in the UE, or a functional module in the UE. In the subsequent description, the first communication device is taken as an example of a UE. The second communication device is, for example, an access network device; or the second communication device is a chip or chip system in the access network device, or the second communication device is a functional module included in the access network device, such as a CU, or a CU-CP, or a CU-CP2, etc.; or the second communication device is a larger device including an access network device. In the subsequent description, the second communication device is taken as an access network device as an example.

[0224] S801: The access network device sends fifth information to the UE. Correspondingly, the UE receives the fifth information from the access network device.

[0225] The fifth information is used to indicate the transmission requirement of the first AI model, where the first AI model is the AI ​​model requested to be configured by the UE.

[0226] S802: The UE sends third information to the access network device. Correspondingly, the access network device receives the third information from the UE.

[0227] The third information is the first sub-information, the first sub-information indicates the capability parameter of the UE to receive the first AI model, and the third information is used to determine the transmission mode of the first AI model. The relevant description of the third information is as described above and will not be repeated here.

[0228] In some embodiments, the access network device may also use the above-mentioned method A1 or A2 to obtain the UE's ability to receive the AI ​​model. In this case, the UE may not perform S802. For example, in this case, the UE may send a reception confirmation or a transmission request confirmation indication to the access network device to confirm that the transmission request has been received, or to indicate confirmation of the transmission request.

[0229] In one possible implementation, the information used to determine the transmission method of the first AI model may further include one or more of the following: capability parameters for transmitting the AI ​​model over the over-the-top (OTT) network or capability parameters for transmitting the AI ​​model via a core network device. The relevant content regarding the capability parameters for transmitting the AI ​​model over the OTT network or the capability parameters for transmitting the AI ​​model via a core network device is as described above and will not be further elaborated here.

[0230] In one example, when the information used to determine the transmission method of the first AI model includes the capability parameters of the OTT transmission AI model, after the UE receives the fifth information, S804 can be executed before S802 to obtain the capability parameters of the OTT transmission AI model from OTT. The third information also includes second sub-information, and the second sub-information is used to indicate that OTT supports the capability parameters of the AI ​​model provided to the UE. That is, the UE sends its own capability parameters and the capability parameters of the OTT transmission AI model to the access network device. In some embodiments, the access network device can also adopt the above-mentioned method B1 to obtain the capability parameters of the OTT transmission AI model. Exemplarily, after the access network device sends the fifth information to the UE, it can send indication information 1 to OTT. Indication information 1 instructs OTT to report the capability parameters of the transmission AI model. Therefore, when OTT receives indication information 1, it sends the capability parameters of the OTT transmission AI model to the access network device.

[0231] In another example, when the information used to determine the transmission of the first AI model includes the core network device's capability parameters for transmitting the AI ​​model, the access network device may further execute S805 to send a request message to the core network device, wherein the request message is used to request the core network device to report the capability parameters for transmitting the AI ​​model. After receiving the request message, the core network device executes S806 to send fourth information to the access network device. The fourth information is used to indicate that the core network device supports the capability parameters of a third AI model provided to the UE, wherein the third AI model includes the first AI model. Optionally, the request message may include one or more of the following: an identifier of the AI ​​model, metadata of the AI ​​model, or a reason for the request. In some embodiments, the access network device may also employ the above-described methods C1 and C2 to obtain the core network device's capability parameters for transmitting the AI ​​model. S805 occurs after S801 and before S803. The order of S805 and S802 is not specifically limited in this application.

[0232] S803: The access network device sends second information to the UE, where the second information is used to indicate the transmission mode of the first AI model. The description of the second information is as described above and is not repeated here. For example, the access network device may determine the transmission mode of the first AI model and then send the second information to the UE.

[0233] S807-S811, refer to S706-S710, which will not be repeated here.

[0234] Figure 9 shows a schematic diagram of the structure of a communication device provided in an embodiment of the present application. The communication device 900 may be the first communication device (or UE) or the circuit system of the first communication device described in any one of the embodiments shown in Figures 4 to 8, and is used to implement the method corresponding to the first communication device (UE) in the above method embodiment. Alternatively, the communication device 900 may be the second communication device or the circuit system of the second communication device (or access network device) in any one of the embodiments shown in Figures 4 to 8, and is used to implement the method corresponding to the access network device in the above method embodiment. For specific functions, please refer to the description in the above method embodiment. Among them, for example, a circuit system is a chip system.

[0235] The communication device 900 includes at least one processor 901. Processor 901 can be used for internal processing of the device to implement certain control processing functions. Optionally, processor 901 includes instructions. Optionally, processor 901 can store data. Optionally, different processors can be independent devices, located in different physical locations, or on different integrated circuits. Optionally, different processors can be integrated into one or more processors, for example, on one or more integrated circuits.

[0236] Optionally, the communication device 900 includes one or more memories 903 for storing instructions. Optionally, data may also be stored in the memories 903. The processor and memory may be provided separately or integrated together.

[0237] Optionally, the communication device 900 includes a communication line 902 and at least one communication interface 904. Since the memory 903, the communication line 902 and the communication interface 904 are all optional, they are indicated by dotted lines in FIG9 .

[0238] Optionally, the communication device 900 may further 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 referred to as a transceiver, a transceiver circuit, an input / output interface, etc., and is used to implement the transceiver function of the communication device 900 through the antenna. Optionally, the transceiver includes a transmitter and a receiver. For example, the transmitter may be used to generate a radio frequency signal from a baseband signal, and the receiver may be used to convert the radio frequency signal into a baseband signal.

[0239] The processor 901 may include a general-purpose 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.

[0240] Communication link 902 may include a pathway for transmitting information between the aforementioned components.

[0241] The communication interface 904 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0242] The memory 903 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, 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 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 903 may exist independently and be connected to the processor 901 via the communication line 902. Alternatively, the memory 903 may be integrated with the processor 901.

[0243] Among them, the memory 903 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 901. The processor 901 is used to execute the computer-executable instructions stored in the memory 903, thereby implementing the steps performed by the first communication device (or UE) described in any of the embodiments shown in Figures 4 to 8, or implementing the steps performed by the second communication device (or access network device) described in any of the embodiments shown in Figures 4 to 8.

[0244] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.

[0245] In a specific implementation, as an embodiment, the processor 901 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 9 .

[0246] In a specific implementation, as an embodiment, the communication device 900 may include multiple processors, such as processor 901 and processor 905 in FIG9 . Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0247] When the device shown in FIG9 is a chip, such as a chip of a first communication device or a chip of a UE, the chip includes a processor 901 (and may also include a processor 905), a communication circuit 902, and a communication interface 904. Optionally, the chip may include a memory 903. Specifically, the communication interface 904 may be an input interface, a pin, or a circuit. The memory 903 may be a register, a cache, or the like. The processor 901 and the processor 905 may be a general-purpose CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of a program of the communication method of any of the above embodiments.

[0248] In the embodiment of the present application, the functional modules of the device can be divided according to the above method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation. For example, in the case of dividing each functional module according to each function, Figure 10 shows a schematic diagram of a device, and the device 1000 can be the first communication device (or UE) or the second communication device (or access network device) involved in the above-mentioned various method embodiments, or a chip in the first communication device (or UE) or the chip in the second communication device (or access network device). The device 1000 includes a sending unit 1001, a processing unit 1002 and a receiving unit 1003.

[0249] It should be understood that the device 1000 can be used to implement the steps performed by the access network 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 to 8 above, and will not be repeated here.

[0250] Optionally, the functions / implementation processes of the sending unit 1001, the receiving unit 1003, and the processing unit 1002 in FIG10 may be implemented by the processor 901 in FIG9 calling computer-executable instructions stored in the memory 903. Alternatively, the functions / implementation processes of the processing unit 1002 in FIG10 may be implemented by the processor 901 in FIG9 calling computer-executable instructions stored in the memory 903, and the functions / implementation processes of the sending unit 1001 and the receiving unit 1003 in FIG10 may be implemented by the communication interface 904 in FIG9.

[0251] Optionally, when the device 1000 is a chip or a circuit, the functions / implementation processes of the sending unit 1001 and the receiving unit 1003 can also be implemented through pins or circuits.

[0252] The present application also provides a computer-readable storage medium, which stores a computer program or instruction. When the computer program or instruction is executed, the method performed by the first communication device or the second communication device in the aforementioned method embodiment is implemented. In this way, the functions described in the above embodiments can be implemented in the form of software functional units and sold or used as independent products. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes 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 several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0253] The present application also provides a computer program product, which includes: computer program code, which, when executed on a computer, enables the computer to execute the method executed by the first communication device or UE in any of the aforementioned method embodiments.

[0254] An embodiment of the present application further provides a processing device, including a processor and an interface; the processor is used to execute the method executed by the first communication device or UE involved in any of the above method embodiments.

[0255] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0256] The various illustrative logic units and circuits described in the embodiments of the present application can be implemented or operated by a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.

[0257] The steps of the methods or algorithms described in the embodiments of the present application can be directly embedded in hardware, software units executed by a processor, or a combination of the two. The software unit can be stored in RAM, flash memory, ROM, erasable programmable read-only memory (EPROM), EEPROM, registers, hard disks, removable disks, CD-ROMs, or other storage media in any form known in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Alternatively, the storage medium can also be integrated into the processor. The processor and storage medium can be provided in an ASIC, which can be provided in a terminal device. Alternatively, the processor and storage medium can also be provided in different components in the terminal device.

[0258] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0259] The contents of the various embodiments of this application can refer to each other. If there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0260] It is understood that in the embodiments of the present application, the first communication device or the second communication device may perform some or all of the steps in the embodiments of the present application. These steps or operations are merely examples. In the embodiments of the present application, other operations or variations of various operations may also be performed. In addition, the various steps may be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be performed.

[0261] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. A communication method, characterized in that: include: Receiving first information from a first communication device, the first information being used to indicate a transmission requirement of the first communication device for a first artificial intelligence (AI) model to be applied; the first information being used to determine a transmission method of the first AI model; Sending second information to the first communication device, where the second information is used to indicate a transmission method of the first AI model.

2. The method according to claim 1, characterized in that The transmission method of the first AI model includes one or more of the following: An access network device transmission mode, where the access network device transmission mode indicates that the first AI model is transmitted from the access network device to the first communication device; OTT transmission mode, where the OTT transmission mode indicates that the first AI model is transmitted to the first communication device by OTT; or A core network device transmission mode, wherein the core network device transmission mode indicates that the first AI model is transmitted from the core network device to the first communication device.

3. The method according to claim 1 or 2, characterized in that The first information indicates one or more of the following: Desired time; an identifier of the first AI model; metadata of the first AI model; a first AI function supported by the first AI model; Expected minimum transmission delay; a second AI function to be executed after completing the first AI function; or, The moving path of the first communication device.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Receive third information from a first communication device, the third information including first sub-information, the first sub-information indicating an ability parameter of the first communication device to receive the first AI model, and the third information is used to determine a transmission method of the first AI model.

5. The method according to claim 4, characterized in that The first sub-information includes one or more of the following: a storage capacity parameter of the first communication device; a computing capability parameter of the first communication device; a communication capability parameter of the first communication device; a transmission rate allowed by the first communication device; the arrival time of the first AI model expected by the first communication device; or, A model transmission mode supported by the first communication device.

6. The method according to claim 4, characterized in that The third information also includes second sub-information, where the second sub-information indicates that the third-party application service OTT supports capability parameters of a second AI model provided to the first communication device, where the second AI model includes the first AI model.

7. The method according to claim 6, characterized in that The second sub-information includes one or more of the following: an identifier of the second AI model; The identifier of the OTT; metadata of the second AI model; The OTT supports a transmission rate for transmitting the second AI model; The OTT supports a transmission delay of the second AI model; The OTT supports the arrival time of transmitting the second AI model; or, The model transmission method supported by the OTT.

8. The method according to any one of claims 4 to 7, characterized in that: The method further comprises: Receive fourth information from a core network device, where the fourth information is used to indicate that the core network device supports providing capability parameters of a third AI model for the first communication device, where the third AI model includes the first AI model.

9. The method according to claim 8, characterized in that The fourth information includes one or more of the following: an identifier of the third AI model; Metadata of the third AI model; The core network device supports a transmission rate for transmitting the third AI model; The core network device supports a transmission delay for transmitting the third AI model; The core network device supports the arrival time of transmitting the third AI model; or, The model transmission mode supported by the core network device.

10. The method according to any one of claims 2 to 9, characterized in that: The method further comprises: Transmitting model transmission information corresponding to the first AI model to the first communication device; The model transmission information includes model information of the first AI model; or, The model transmission information includes the model information, and the model transmission information also includes the adopted transmission method and / or the estimated completion time; The adopted transmission mode includes adopting a user plane signaling mode or a control plane signaling mode.

11. The method according to claim 10, characterized in that The model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; or Fourth indication information, where the fourth indication information is used to indicate the structure of the first AI model.

12. A communication method, characterized in that: include: Sending first information to the second communication device, where the first information is used to indicate the transmission requirement of the first communication device for the first artificial intelligence AI model to be applied; The first information is used to determine a transmission method of the first AI model; Receive second information from the second communication device, where the second information is used to indicate a transmission method of the first AI model.

13. The method according to claim 12, characterized in that The transmission method of the first AI model includes one or more of the following: An access network device transmission mode, where the access network device transmission mode indicates that the first AI model is transmitted from the access network device to the first communication device; OTT transmission mode, where the OTT transmission mode indicates that the first AI model is transmitted to the first communication device by OTT; or A core network device transmission mode, wherein the core network device transmission mode indicates that the first AI model is transmitted from the core network device to the first communication device.

14. The method according to claim 12 or 13, characterized in that The first information indicates one or more of the following: Desired time; an identifier of the first AI model; metadata of the first AI model; a first AI function supported by the first AI model; Expected minimum transmission delay; a second AI function to be executed after completing the first AI function; or, The moving path of the first communication device.

15. The method according to any one of claims 12 to 14, characterized in that: The method further comprises: Send third information to the second communication device, the third information including first sub-information, the first sub-information indicating the ability parameter of the first communication device to receive the first AI model, and the third information is used to determine the transmission method of the first AI model.

16. The method according to claim 15, characterized in that The first sub-information includes one or more of the following: a storage capacity parameter of the first communication device; a computing capability parameter of the first communication device; a communication capability parameter of the first communication device; a transmission rate allowed by the first communication device; an arrival time of the first AI model expected by the first communication device; A model transmission mode supported by the first communication device.

17. The method according to claim 15, characterized in that The third information also includes second sub-information, where the second sub-information indicates that the third-party application service OTT supports capability parameters of a second AI model provided to the first communication device, where the second AI model includes the first AI model.

18. The method according to claim 17, characterized in that: The second sub-information includes one or more of the following: an identifier of the second AI model; The identifier of the OTT; metadata of the second AI model; The OTT supports a transmission rate for transmitting the second AI model; The OTT supports a transmission delay of the second AI model; The OTT supports the arrival time of transmitting the second AI model; or, The model transmission method supported by the OTT.

19. The method according to any one of claims 13 to 18, characterized in that: The method further comprises: receiving model transmission information corresponding to the first AI model from the second communication device; The model transmission information includes model information of the first AI model; or, The model transmission information includes the model information, and the model transmission information also includes a transmission method and / or an estimated completion time adopted by the first communication device; The transmission method adopted by the first communication device includes a user plane signaling method or a control plane signaling method.

20. The method of claim 19, wherein: The model information includes one or more of the following: an identifier of the first AI model; metadata of the first AI model; or Fourth indication information, where the fourth indication information is used to indicate the structure of the first AI model.

21. A communication device, characterized in that: The method comprises one or more modules or units for implementing the method steps described in any one of claims 1 to 20.

22. A communication device, characterized in that: The method comprises a processor and a memory, wherein the memory is coupled to the processor, and the processor is used to execute the method according to any one of claims 1 to 11, or to execute the method according to any one of claims 12 to 20.

23. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program. When the computer program runs on a computer, the computer executes the method according to any one of claims 1 to 11, or executes the method according to any one of claims 12 to 20.

24. A chip system, characterized in that: The chip system comprises: A processor and an interface, wherein the processor is used to call and run instructions from the interface, and when the processor executes the instructions, the method according to any one of claims 1 to 11 is implemented; or the method according to any one of claims 12 to 20 is implemented.

25. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is run on a computer, the computer is enabled to execute the method according to any one of claims 1 to 11, or execute the method according to any one of claims 12 to 20.

Images