Communication methods and communication devices

Abstract

The present application relates to communication methods and communication devices. A method comprises: a first communication device sends first information, the first information being used for indicating information related to a processing capability of the first communication device. In the embodiments of the present application, by synchronizing information related to a processing capability of a communication device, computing resources of the communication device can be reasonably utilized.

Description

Communication methods and communication equipment Technical Field

[0001] This application relates to the field of communications, and more specifically, to a communication method and a communication device. Background Technology

[0002] The application of artificial intelligence (AI)-based solutions in wireless communication systems is increasing. For example, AI can be used to address issues such as Channel-State Information (CSI) feedback, channel estimation, localization, and beam management. In practical applications, it's necessary to consider the resource dependence of these solutions and potential problems. For instance, the limited computing resources and / or capabilities of base stations and user equipment (UE) must be taken into account. Summary of the Invention

[0003] This application provides a communication method and a communication device.

[0004] This application provides a communication method, including:

[0005] The first communication device sends first information, which is used to indicate information related to the processing capability of the first communication device.

[0006] This application provides a communication method, including:

[0007] The second communication device receives first information, which is used to indicate information related to the processing capabilities of the first communication device.

[0008] This application provides a first communication device, including:

[0009] A transceiver unit is used to send first information, which is used to indicate information related to the processing capabilities of the first communication device.

[0010] This application provides a second communication device, including:

[0011] The transceiver unit is used to receive first information, which is used to indicate information related to the processing capabilities of the first communication device.

[0012] This application provides a communication device, including a transceiver, a processor, and a memory. The memory stores a computer program, the transceiver communicates with other devices, and the processor calls and runs the computer program stored in the memory to enable the communication device to perform the aforementioned communication method.

[0013] This application provides a chip for implementing the above-described communication method.

[0014] Specifically, the chip includes a processor for retrieving and running a computer program from memory, causing a device equipped with the chip to perform the aforementioned communication method.

[0015] This application provides a computer-readable storage medium for storing a computer program, which, when run by a device, causes the device to perform the aforementioned communication method.

[0016] This application provides a computer program product, including computer program instructions that cause a computer to execute the above-described communication method.

[0017] This application provides a computer program that, when run on a computer, causes the computer to perform the aforementioned communication method.

[0018] In this embodiment of the application, by synchronizing information related to the processing capabilities of the communication device, the computing resources of the communication device can be utilized in a reasonable manner. Attached Figure Description

[0019] Figure 1 is a schematic diagram of an application scenario according to an embodiment of this application.

[0020] Figure 2 is a schematic flowchart of a communication method according to an embodiment of this application.

[0021] Figure 3 is a schematic flowchart of a communication method according to another embodiment of this application.

[0022] Figure 4 is a schematic flowchart of a communication method according to another embodiment of this application.

[0023] Figure 5 is a schematic flowchart of a communication method according to an embodiment of this application.

[0024] Figure 6 is a schematic flowchart of a communication method according to another embodiment of this application.

[0025] Figure 7 is a schematic flowchart of a communication method according to another embodiment of this application.

[0026] Figure 8 is a schematic diagram of the first AI processing capability reported by the UE.

[0027] Figure 9 is a schematic diagram of the second AI processing capability reported by the UE.

[0028] Figure 10 is a flowchart of the UE instructing the network to perform AI functions.

[0029] Figure 11 is a schematic diagram of the second processing capability of the UE reporting function or model.

[0030] Figure 12 is a schematic block diagram of a first communication device according to an embodiment of the present application.

[0031] Figure 13 is a schematic block diagram of a second communication device according to an embodiment of the present application.

[0032] Figure 14 is a schematic block diagram of a communication device according to an embodiment of this application.

[0033] Figure 15 is a schematic block diagram of a chip according to an embodiment of this application.

[0034] Figure 16 is a schematic block diagram of a communication system according to an embodiment of this application. Detailed Implementation

[0035] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0036] The technical solutions of this application embodiment can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, Advanced Long Term Evolution (LTE-A) systems, New Radio (NR) systems, evolution systems of NR systems, LTE-based access to unlicensed spectrum (LTE-U) systems, NR-based access to unlicensed spectrum (NR-U) systems, Non-Terrestrial Networks (NTN) systems, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), 5th-Generation (5G) systems, or other communication systems.

[0037] Traditional communication systems typically support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication but also, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to these communication systems.

[0038] In one implementation, the communication system in this application embodiment can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) network deployment scenario.

[0039] In one embodiment, the communication system in this application can be applied to unlicensed spectrum, wherein the unlicensed spectrum can also be considered as shared spectrum; or, the communication system in this application can also be applied to licensed spectrum, wherein the licensed spectrum can also be considered as non-shared spectrum.

[0040] This application describes various embodiments in conjunction with network devices and terminal devices. The terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device, etc.

[0041] Terminal devices can be stations (STAION, ST) in WLANs, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistant (PDA) devices, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, in-vehicle devices, wearable devices, terminal devices in next-generation communication systems such as NR networks, or terminal devices in future evolved Public Land Mobile Network (PLMN) networks, etc.

[0042] In the embodiments of this application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships); and it can also be deployed in the air (such as airplanes, balloons and satellites).

[0043] In the embodiments of this application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical care, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0044] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0045] In the embodiments of this application, the network device can be a device for communicating with mobile devices, such as an access point (AP) in a WLAN, an evolved Node B (eNB or eNodeB) in LTE, a relay station or access point, or a vehicle-mounted device, a wearable device, a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or an NTN network, etc.

[0046] By way of example and not limitation, in this embodiment, the network device may have mobility characteristics; for example, the network device may be a mobile device. Optionally, the network device may be a satellite or a balloon station. For example, the satellite may be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a highly elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station located on land, water, or other similar locations.

[0047] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0048] Figure 1 illustrates an exemplary communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one embodiment, the communication system 100 may include multiple network devices 110, and the coverage area of ​​each network device 110 may include other numbers of terminal devices 120; this embodiment does not limit the scope of the present application.

[0049] In one embodiment, the communication system 100 may also include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which are not limited in this application.

[0050] Network equipment can be further divided into access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks used to communicate with the access network equipment. Access network equipment can be evolved Node Bs (eNBs or e-NodeBs) in Long-Term Evolution (LTE), Next-Generation Radio (NR) (mobile communication system), or Authorized Auxiliary Access Long-Term Evolution (LAA-LTE) systems, such as macro base stations, micro base stations (also called "small base stations"), pico base stations, access points (APs), transmission points (TPs), or new generation Node Bs (gNodeBs).

[0051] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Taking the communication system shown in Figure 1 as an example, the communication device may include network devices and terminal devices with communication functions. The network devices and terminal devices can be specific devices in this application embodiment, which will not be described in detail here. The communication device may also include other devices in the communication system, such as network controllers, mobility management entities, and other network entities. This application embodiment does not limit this.

[0052] It should be understood that the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0053] It should be understood that the term "instruction" mentioned in the embodiments of this application can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0054] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0055] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0056] In some examples, artificial intelligence can solve one or more of the following problems: Channel-State Information (CSI) feedback, achieving AI-based CSI information compression and feedback through the introduction of AI encoders and decoders; Channel estimation, achieving high-performance estimation of a given channel through AI channel estimators; Localization, obtaining high-precision localization results based on positioning channel information using AI-based localization algorithms; and Beam management, obtaining preferred or more refined beam information, or predicting beam information for future times, based on known beam information using AI-based beam management algorithms.

[0057] For AI-based wireless communication solutions, the main implementers of the solution, such as base stations or user units (UEs), require sufficient computing resources to quickly complete complex calculations. In other words, the corresponding wireless communication problem can only be solved under the aforementioned resource conditions. However, considering the limited computing resources and / or computing capabilities of base stations or UEs, it is necessary to avoid situations where the parallel execution of functions and / or models exceeds the corresponding computing resources and / or computing capabilities of the base station or UE.

[0058] Figure 2 is a schematic flowchart of a communication method 200 according to an embodiment of this application. This method can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes at least a portion of the following:

[0059] S210, the first communication device sends first information, which is used to indicate information related to the processing capability of the first communication device.

[0060] In the embodiments of this application, the first communication device has the capability to process some functions and / or models. For example, the first communication device has the capability to process AI functions and / or AI models. In some scenarios, the first communication device can receive AI functions and / or AI models from a second communication device. For example, the UE receives AI functions and / or AI models issued by a base station. The processing capability of the first communication device may affect whether the received AI functions and / or AI models can be run normally. The first communication device, such as the UE, can report first information to the second communication device, such as the base station, to inform the second communication device of the processing capability-related information of the first communication device. In this way, the second communication device can rationally utilize the computing resources and / or computing power of the first communication device to run the corresponding functions and / or models based on the processing capability-related information of the first communication device. For example, the base station can determine which AI capabilities and / or AI models to issue to the UE based on the UE's AI-related processing capabilities, thereby rationally utilizing the UE's computing resources and / or computing power to run the AI ​​capabilities and / or AI models.

[0061] In the embodiments of this application, AI may be replaced by expressions such as Machine Learning (ML), AI / ML, AI and / or ML, etc. These expressions have basically similar meanings and can be flexibly changed according to the needs of specific applications.

[0062] This application embodiment can make reasonable use of the computing resources of the communication device by synchronizing information related to the processing capabilities of the communication device. For example, when the UE reports its AI-related processing capabilities to the network, these capabilities can be reasonably used to run the UE's computing resources and / or computing power to run AI models and / or AI functions.

[0063] Figure 3 is a schematic flowchart of a communication method 300 according to another embodiment of this application. The method may include one or more features of the above-described communication method. In one embodiment, the method further includes:

[0064] S310, The first communication device receives second information, which is used to trigger the first communication device to send the first information.

[0065] In this embodiment, the first communication device can proactively report first information, or it can trigger the reporting of first information based on second information sent by the second communication device. For example, the second communication device can request the first communication device to report all AI / ML-related processing capabilities it supports through the second information. As another example, if the second communication device is about to send a certain AI / ML model to the first communication device, the second communication device can carry information such as the identifier of this AI / ML model through the second information. The first communication device can then report processing capabilities related to this AI / ML model based on the identifier and other information.

[0066] In one implementation, the second information includes one or more of the following: a first communication device capability request message; a Radio Resource Control (RRC) message. For example, the second information sent by the base station to the UE may be a UE capability request (e.g., a UECapabilityEnqiry) message or an RRC message, triggering the UE to report processing capabilities related to AI / ML.

[0067] In one implementation, the processing capability information of the first communication device includes: the first processing capability of the first communication device. In this embodiment, the first communication device can send its overall first processing capability to the second communication device. For example, the UE reports its AI processing capability to the network. Here, the UE's AI processing capability can be the overall AI processing capability of the UE.

[0068] In the embodiments of this application, the granularity of the first processing capability can be defined by a protocol, configured by the network to the first communication device, or indicated by the first communication device to the second communication device. For example, the granularity of an APU can be X FLOPs for one APU, or X computations for one APU, etc.

[0069] In one implementation, the first processing capability of the first communication device is for one or more of the following:

[0070] First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

[0071] For example, the UE reports its AI processing capabilities for use case A to the base station. Another example is the UE reporting its AI processing capabilities for use case group 1 (including use case A, use case B, and use case C). Yet another example is the UE reporting AI processing capabilities shared by use cases A and B, or AI processing capability 1 for use case A and AI processing capability 2 for use case B. Yet another example is the UE reporting its AI processing capabilities for carrier CA1 to the base station. Yet another example is the UE reporting its AI processing capabilities for carrier CA1, carrier CA2, and carrier CA3. Yet another example is the UE reporting its AI processing capabilities for serving cell Cell1 to the base station. Yet another example is the UE reporting its AI processing capabilities for serving cell Cell1, serving cell Cell2, and serving cell Cell3.

[0072] In one implementation, the first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support. For example, the AI ​​processing capability that the UE can support.

[0073] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0074] The number of Accelerated Intelligence Processing Units (APUs) that the first communication device can support;

[0075] The number of floating-point operations (FLOPs) that the first communication device can support;

[0076] The number of trillions of operations (TOPs) that this first communication device can support.

[0077] For example, if the UE reports that it supports X1 APUs, then the AI ​​processing capability it can support is X1 APUs. Similarly, if the UE reports that it supports X2 FLOPs, then the AI ​​processing capability it can support is X2 FLOPs. And if the UE reports that it supports X3 TOPs, then the AI ​​processing capability it can support is X3 TOPs.

[0078] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0079] The number of APUs that the first communication device can support within the first time unit;

[0080] The number of FLOPs that the first communication device can support within the first time unit;

[0081] The number of TOPs that the first communication device can support within the first time unit.

[0082] In one implementation, the first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0083] In this embodiment, the AI ​​processing capability supported by the first communication device can have a certain time validity, that is, it can be valid within a certain time range. For example, the UE can report one or more of the number of APUs, the number of FLOPs, and the number of TOPs that the UE can support in the first time unit. If the UE reports that the number of APUs it can support in n1 frames is X1, the AI ​​processing capability that the UE can support is X1 APUs, and it is valid within the n1 frames. If the UE reports that the number of FLOPs it can support in n2 seconds is X2, the AI ​​processing capability that the UE can support is X2 FLOPs, and it is valid within the n2 seconds. As another example, if the UE reports that the number of TOPs it can support in n3 time slots is X3, the AI ​​processing capability that the UE can support is X3 TOPs, and it is valid within the n3 time slots.

[0084] In one embodiment, the processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

[0085] In this embodiment, the first communication device can send a first function and / or a second processing capability corresponding to a first model of the first communication device to the second communication device. For example, the UE reports the AI ​​processing capability corresponding to its AI function and / or AI model to the network. The AI ​​processing capabilities corresponding to different AI functions and / or AI models may be different or partially the same. For example, AI function F1 corresponds to AI processing capability 1, AI function F2 corresponds to AI processing capability 2, AI model M1 corresponds to AI processing capability 3, and AI model M3 corresponds to AI processing capability 4.

[0086] In the embodiments of this application, the granularity of the second processing capability can be defined by a protocol, configured by the network to the first communication device, or indicated by the first communication device to the second communication device. For example, the granularity of an APU can be one APU corresponding to Y TOPs, one APU corresponding to Y computations, etc.

[0087] In one implementation, the first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

[0088] In this embodiment, the configurable AI functions and / or AI models of the first communication device may include AI functions and / or AI models that allow other communication devices to configure for the first communication device. The AI ​​functions and / or AI models supported by the first communication device may include the range of AI functions and / or AI models that the first communication device is capable of supporting. For example, UE1 may support AI function F1, AI function F2, and AI model M1. UE2 may support AI function F3, AI function F4, and AI model M2. The AI ​​functions and / or AI models already supported by the first communication device may include the AI ​​functions and / or AI models currently supported by the first communication device. For example, UE1 already supports AI function F1. UE2 already supports AI function F3 and AI model M2.

[0089] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0090] The number of APUs corresponding to the AI ​​function and / or the AI ​​model;

[0091] The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model;

[0092] The number of TOPs corresponding to the AI ​​function and / or the AI ​​model;

[0093] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0094] The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0095] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, first resource, or first reference signal.

[0096] In this embodiment of the application, the first communication device may report to the second communication device one or more of the number of APUs, FLOPs, and TOPs corresponding to the AI ​​functions and / or AI models that the first communication device can configure, supports, or has already supported.

[0097] For example, the UE reports that the number of APUs corresponding to the configurable AI function F1 is X1, and the AI ​​processing capacity corresponding to AI function F1 is X1 APUs. As another example, the UE reports that the number of FLOPs corresponding to the AI ​​model M1 it can support is X2, and the AI ​​processing capacity corresponding to AI model M1 is X2 FLOPs. Furthermore, the UE reports that the number of TOPs corresponding to the AI ​​model M2 it already supports is X3, and the AI ​​processing capacity corresponding to AI model M2 is X3 TOPs.

[0098] In this embodiment of the application, the first communication device may report to the second communication device one or more of the number of APUs, FLOPs, and TOPs required for the first configuration, first resource, or first reference signal to process the AI ​​functions and / or AI models that the first communication device can configure, supports, or has already supported, and which are configurable, supportable, or supported.

[0099] For example, the UE reports that the number of APUs required for the first configuration of its configurable AI function F2 is X4, and the AI ​​processing capacity required for the first configuration of AI function F2 is X4 APUs. As another example, the UE reports that the number of FLOPs required for the first resource processed by its supported AI model M3 is X5, and the AI ​​processing capacity required for the first resource processed by AI model M3 is X5 FLOPs. As yet another example, the UE reports that the number of TOPs required for the first resource processed by its supported AI model M4 is X6, and the AI ​​processing capacity required for the first reference signal processed by AI model M4 is X6 TOPs.

[0100] In some examples, the first configuration can be a CSI configuration, the first resource can be a CSI resource, and the first reference signal can be a CSI reference signal.

[0101] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0102] The number of APUs required for each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0103] The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0104] The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0105] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0106] The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0107] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit.

[0108] In one implementation, the second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0109] In the embodiments of this application, the configurable, supportable, or supported AI processing capabilities of the first communication device can have a certain time validity, that is, they can be effective within a certain time range.

[0110] For example, if the UE reports that the number of APUs corresponding to the configurable AI function F1 within n1 frames is X1, then the AI ​​processing capability corresponding to AI function F1 is X1 APUs configurable within n1 frames. As another example, if the UE reports that the number of FLOPs corresponding to the AI ​​model M1 it can support within n2 seconds is X2, then the AI ​​processing capability corresponding to AI model M1 is X2 FLOPs supported within n2 seconds. Similarly, if the UE reports that the number of TOPs corresponding to the AI ​​model M2 it already supports within n3 time slots is X3, then the AI ​​processing capability corresponding to AI model M2 is X3 TOPs already supported within n3 time slots.

[0111] For example, if the UE reports that its configurable AI function F2 processes the first configuration, the number of APUs required within n4 symbols is X4, and the AI ​​processing capability required for F2 to process the first configuration is X4 APUs within n4 symbols. As another example, if the UE reports that its supported AI model M3 processes the first resource, the number of FLOPs required within n5 subframes is X5, and the AI ​​processing capability required for M3 to process the first resource is X5 FLOPs within n5 subframes. Similarly, if the UE reports that its supported AI model M4 processes the first resource, the number of TOPs required within n6 milliseconds is X6, and the AI ​​processing capability required for M4 to process the first reference signal is X6 TOPs within n6 milliseconds.

[0112] In one implementation, the AI ​​function and / or AI model includes one or more of the following:

[0113] AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based localization, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation, AI / ML-based demodulation, AI / ML-based channel coding, AI / ML-based channel decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based Radio Link Failure (RLF) prediction, AI / ML-based resource management.

[0114] For example, a UE reporting its first CSI feedback function to the network requires Y1 APUs. Another example is a UE reporting AI / ML-based CSI feedback function to the network, which requires Y2 FLOPs. Yet another example is a UE reporting AI / ML-based CSI feedback coding model estimation function to the network, which requires Y3 TOPs. A third example is a UE reporting AI / ML-based beam prediction function to the network, which requires Y4 APUs. A fourth example is a UE reporting AI / ML-based beam management failure prediction function to the network, which requires Y5 FLOPs. A fifth example is a UE reporting AI / ML-based positioning function to the network, which requires Y6 TOPs. A sixth example is a UE reporting AI / ML-based channel estimation to the network, which requires Y7 TOPs. A seventh example is a UE reporting AI / ML-based modulation and demodulation to the network, which requires Y8 APUs. Finally, a UE reporting AI / ML-based channel coding and / or decoding to the network requires Y9 FLOPs.

[0115] In one implementation, the second processing capability is transmitted in one or more of the following processes:

[0116] When the first communication device reports its capability;

[0117] When the first communication device reports the first supported function and / or first model;

[0118] When the first communication device reports the available first function and / or first model;

[0119] When the first communication device reports the activation of the first function and / or the first model.

[0120] In this embodiment, the first communication device may send first information including a first processing capability and / or a second processing capability to the second communication device when reporting its capabilities to the second communication device. The first communication device may also send first information including a first processing capability and / or a second processing capability to the second communication device when supporting a first function and / or a first model. Furthermore, the first communication device may send first information including a first processing capability and / or a second processing capability to the second communication device when activating a first function and / or a first model.

[0121] In the embodiments of this application, the first processing capability may include the first AI / ML processing capability of the first communication device, and the second processing capability may include the second AI / ML processing capability corresponding to the function and / or model of the first communication device.

[0122] In one implementation, the second processing capability is sent in one or more of the following messages:

[0123] Capability information of the first communication device;

[0124] The available functionalities of the first communication device are reported.

[0125] In the embodiments of this application, the information in one or more steps of the interaction between the first communication device and the second communication device may carry second processing capability information. For example, the network may send a UE capability request message to the UE. The UE may send UE capability information to the network, which may carry the second processing capability corresponding to the UE's AI function and / or AI model. The network may send an RRC reconfiguration message to the UE. The UE may send an available function report to the network, which may carry the second processing capability corresponding to the UE's AI function and / or AI model.

[0126] In one embodiment, the processing capability information of the first communication device includes: the number of use cases that the first communication device can support; and the processing capability requirements corresponding to each use case that the first communication device can support. In this application embodiment, the use cases that the first communication device can support may include, but are not limited to, one or more of the following: CSI scheme, beam management, beam prediction, positioning, channel estimation, superimposed pilot reception, modulation and demodulation, channel coding and decoding, precoding, waveform nonlinearity compensation, mobility management, RLF prediction, and resource management. For example, the UE can support K use cases. The UE can first report its supported AI / ML processing capability 1 corresponding to Case 1 and AI / ML processing capability 2 corresponding to Case 2. Case 1 and Case 2 can be different CSI schemes, or Case 1 can be a CSI scheme and Case 2 can be channel estimation or other schemes.

[0127] In one implementation, the processing capacity requirement for each use case includes: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

[0128] In one implementation, the third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0129] In the embodiments of this application, the processing capability requirements corresponding to each use case can be time-sensitive or long-term. For example, the AI / ML processing capability corresponding to use case 1 is no more than X1 APUs. Similarly, the AI / ML processing capability corresponding to use case 2 is no more than X2 FLOPs. Furthermore, the AI / ML processing capability corresponding to use case 3 is no more than X3 TOPs. The AI / ML processing capability corresponding to use case 4 is no more than X4 APUs within n1 frames. Furthermore, the AI / ML processing capability corresponding to use case 5 is no more than X5 FLOPs within n2 time slots. And, the AI / ML processing capability corresponding to use case 6 is no more than X6 TOPs within n3 milliseconds.

[0130] Figure 4 is a schematic flowchart of a communication method 400 according to another embodiment of this application. The method may include one or more features of the above-described communication method. In one embodiment, the method further includes:

[0131] S410, the first communication device receives third information, which is used to indicate the processing capability requirements of the second communication device for the first communication device.

[0132] In this embodiment, the first communication device can receive third information from the second communication device. If the third information includes information about the second communication device's processing capabilities required by the first communication device, the first communication device can determine whether it can meet the required information based on its own computing resources and / or computing capabilities. If it can meet the requirements, the first communication device can reply to the second communication device with first information including confirmation information.

[0133] In one implementation, the processing capability requirement information for the first communication device includes one or more of the following:

[0134] The requirement for the AI ​​processing capabilities of this first communication device;

[0135] The required level of AI processing capability for the first communication device;

[0136] The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device;

[0137] The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

[0138] For example, the UE receives a network requirement for AI processing capabilities including X1 APUs. Another example is the UE receiving a network requirement for AI processing capabilities at Level 1, corresponding to X1 APUs and X2 FLOPs. Yet another example is the UE receiving a network requirement for AI processing capabilities corresponding to the AI ​​functions and / or AI models it can support, including X3 APUs and X4 TOPs. Finally, the UE receives a network requirement for AI processing capabilities corresponding to the AI ​​functions and / or AI models it can configure, including no more than X5 APUs, X6 FLOPs, and X7 TOPs.

[0139] In one embodiment, the processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability demand of the second communication device for the first communication device.

[0140] In this embodiment, if the first communication device can determine, based on its own computing resources and / or computing power, that it can meet the processing power requirements of the second communication device for the first communication device, the first communication device can reply to the second communication device with first information including requirement confirmation information. Otherwise, the first communication device can reply to the second communication device with first information including requirement rejection information, or it can report the aforementioned first processing power and / or second processing power to the second communication device.

[0141] Figure 5 is a schematic flowchart of a communication method 500 according to an embodiment of this application. This method can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes at least a portion of the following:

[0142] S510, the second communication device receives first information, which is used to indicate information related to the processing capability of the first communication device.

[0143] Figure 6 is a schematic flowchart of a communication method 600 according to another embodiment of this application. The method may include one or more features of the above-described communication method. In one embodiment, the method further includes:

[0144] S610, the second communication device sends a second message, which triggers the first communication device to send the first message.

[0145] In one implementation, the second information includes one or more of the following: a first communication device capability request message; an RRC message.

[0146] In one embodiment, the processing capability information of the first communication device includes: the first processing capability of the first communication device.

[0147] In one implementation, the first processing capability of the first communication device is for one or more of the following:

[0148] First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

[0149] In one embodiment, the first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support.

[0150] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0151] The number of APUs that this first communication device can support;

[0152] The number of FLOPs that the first communication device can support;

[0153] The number of TOPs that the first communication device can support.

[0154] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0155] The number of APUs that the first communication device can support within the first time unit;

[0156] The number of FLOPs that the first communication device can support within the first time unit;

[0157] The number of TOPs that the first communication device can support within the first time unit.

[0158] In one implementation, the first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0159] In one embodiment, the processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

[0160] In one implementation, the first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

[0161] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0162] The number of APUs corresponding to the AI ​​function and / or the AI ​​model;

[0163] The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model;

[0164] The number of TOPs corresponding to the AI ​​function and / or the AI ​​model;

[0165] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0166] The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0167] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, first resource, or first reference signal.

[0168] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0169] The number of APUs required for each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0170] The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0171] The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0172] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0173] The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0174] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit.

[0175] In one implementation, the second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0176] In one implementation, the AI ​​function and / or AI model includes one or more of the following:

[0177] AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based localization, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation, AI / ML-based demodulation, AI / ML-based channel coding, AI / ML-based channel decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based RLF prediction, AI / ML-based resource management.

[0178] In one implementation, the second processing capability is transmitted in one or more of the following processes:

[0179] When the first communication device reports its capability;

[0180] When the first communication device reports the first supported function and / or first model;

[0181] When the first communication device reports the available first function and / or first model;

[0182] When the first communication device reports the activation of the first function and / or the first model.

[0183] In one implementation, the second processing capability is sent in one or more of the following messages:

[0184] Capability information of the first communication device;

[0185] The available functionalities of the first communication device are reported.

[0186] In one embodiment, the processing capability information of the first communication device includes:

[0187] The number of use cases that the first communication device can support; the processing capacity requirements corresponding to each use case that the first communication device can support.

[0188] In one implementation, the processing capacity requirement for each use case includes: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

[0189] In one implementation, the third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0190] Figure 7 is a schematic flowchart of a communication method 700 according to another embodiment of this application. The method may include one or more features of the above-described communication method. In one embodiment, the method further includes:

[0191] S710, the second communication device sends third information, which is used to indicate the second communication device's demand information for the processing capabilities of the first communication device.

[0192] In one implementation, the processing capability requirement information for the first communication device includes one or more of the following:

[0193] The requirement for the AI ​​processing capabilities of this first communication device;

[0194] The required level of AI processing capability for the first communication device;

[0195] The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device;

[0196] The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

[0197] In one embodiment, the processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability demand of the second communication device for the first communication device.

[0198] Specific examples of the second communication device executing communication methods 500, 600, and 700 in this embodiment can be found in the relevant descriptions of the second communication device in methods 200, 300, and 400 above. For the sake of brevity, they will not be repeated here.

[0199] The communication method in this application embodiment may include a scheme for confirming or indicating AI / ML processing capabilities. The UE may report one or more of the following information: (1) the UE's AI processing capabilities; (2) the AI ​​processing capabilities / requirements corresponding to the AI ​​function (AI model). AI can be expressed as ML, AI / ML, AL, and / or ML, etc.

[0200] In some examples, the UE reports the first AI processing capability that the UE can support, such as X APUs (or X FLOPs that can be supported, or X TOPs that can be supported).

[0201] In some examples, the UE reports the second AI processing capability corresponding to the configurable / supportable / supported AI function (AI model), for example, a specific AI function (AI model) requires Y APUs (or YFLOPs, or YTOPs).

[0202] Optionally, the UE reports the number K of use cases that can be supported (e.g., parallel support) (e.g., K AI functions or K models). The AI ​​processing capability corresponding to each use case reported by the UE should not exceed X APUs (or XFLOPs, or XTOPs). The UE reports the AI ​​processing capability corresponding to the configurable, supportable, or already supported AI functions (AI models), for example, Y APUs (or YFLOPs, or YTOPs).

[0203] The aforementioned "UE reporting" method can be accomplished / replaced by protocol agreement, or it can be accomplished / replaced by the network indicating the UE's needs and the UE confirming the corresponding needs.

[0204] The AI ​​functions (AI models) that the UE can configure / support / have already supported can come from network instructions and transmissions.

[0205] The granularity of the aforementioned first processing capability can be defined by the protocol, configured by the network for the UE, or instructed by the UE to the network, such as the granularity of the APU.

[0206] In some application scenarios, within AI / ML solutions, different use cases may have demands for AI computing power. The AI ​​use cases that a UE can activate and use simultaneously may be limited by the UE's AI processing capabilities. Consider introducing a general-purpose AI processing unit (APU) to provide clearer definitions and protocol design for its usage.

[0207] In this embodiment of the application, as shown in Figure 8, the content reported by the UE in S810 may include one or more of the following: (1) the UE's AI processing capability, and / or (2) the AI ​​processing capability / requirements corresponding to the AI ​​function (AI model). The specific reported content will be explained and illustrated below.

[0208] 1. The UE reports its AI processing capabilities to the network:

[0209] The UE reports its AI processing capabilities to the network. Specifically, this may include one or more of the following: The UE reports its first AI processing capability that it can support, such as one or more of X APUs, X FLOPs, and X TOPs. Furthermore, the UE may also report the effective time of one or more of X APUs, X FLOPs, and X TOPs.

[0210] The granularity of the aforementioned first processing capability can be defined by the protocol, configured by the network for the UE, or instructed by the UE to the network, such as the granularity of the APU.

[0211] Considering that the actual AI processing capabilities on the UE side are not disclosed, the actual computing power or available resources on the UE side corresponding to the first AI processing capability can be implemented by the UE and are not disclosed. The UE can only indicate a logical first processing capability, such as the number of AI processing units (APUs). The UE indicates the number of AI processing units corresponding to the different use cases, functions, and models (e.g., AI functions, models) it supports to the network.

[0212] Optionally, the UE may instruct the network, or the network may configure the UE. The granularity of the aforementioned first processing capability may include the granularity of the APU. For example, one AI processing unit corresponds to X FLOPs. For example, one AI processing unit corresponds to X computations.

[0213] Optionally, the aforementioned first processing capability may be specific to a particular use case, specific to a group of use cases, or shared by all use cases.

[0214] Optionally, the aforementioned first processing capability may be targeted at a specific carrier, multiple carriers, a serving cell, or multiple serving cells.

[0215] As shown in Figure 9, optionally, the network can instruct the UE to report its AI processing capabilities to the network (S910). For example, the network instructs the UE to report a first processing capability. For example, the base station sends a UE capability request message (e.g., UE Capability Entrance) or sends a Radio Resource Control (RRC) message, triggering the UE to report the first processing capability (S920).

[0216] II. The UE reports the AI ​​processing capabilities corresponding to the AI ​​function (AI model) to the network:

[0217] The UE reports the secondary AI processing capability corresponding to the AI ​​function (AI model). Specifically, this may include, for example, Y APUs (or YFLOPs, or YTOPs) corresponding to a specific AI function (AI model).

[0218] The AI ​​function (AI model) reported by the UE can be a configurable, supported, or already supported AI function (AI model) of the UE. Additionally, the configurable, supported, or already supported AI function (AI model) of the UE can come from network instructions or transmissions.

[0219] For example: The UE reports the first AI function or the first AI model corresponding to Y APUs (or requires Y FLOPs, or Y TOPs). The first AI function or the first AI model can be one or more of the following functions or models: AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based positioning, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation and demodulation, AI / ML-based channel coding and decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based radio link failure (RLF) prediction, AI / ML-based resource management, etc.

[0220] The number of APUs (or FLOPs, or TOPs) required for different initial AI functions or models can vary. Examples are shown below:

[0221] For example, the UE needs Y1 APUs (or Y1 FLOPs, or Y1 TOPs) to report the first CSI scheme (model) or the first CSI compression scheme (model).

[0222] For example, the UE needs Y2 APUs (or Y2 FLOPs, or Y2 TOPs) to report the first beam management or prediction scheme (model).

[0223] For example, the UE needs Y3 APUs (or Y3 FLOPs, or Y3 TOPs) to report the first channel estimation scheme (model).

[0224] For example, the UE needs Y4 APUs (or Y4 FLOPs, or Y4 TOPs) to report the first superimposed pilot processing scheme (model).

[0225] For example, the UE needs Y5 APUs (or Y5 FLOPs, or Y5 TOPs) to report the first modulation or demodulation scheme (model).

[0226] For example, the UE needs Y6 APUs (or Y6 FLOPs, or Y6 TOPs) to report the first encoding or decoding scheme (model).

[0227] For example, a UE needs 7 APUs (or 7 FLOPs, or 7 TOPs) to report the first mobility management scheme (model).

[0228] For example, the UE needs Y8 APUs (or Y8 FLOPs, or Y8 TOPs) to report the second CSI scheme (model) or the second CSI compression scheme (model).

[0229] For example, a UE needs Y9 APUs (or Y9 FLOPs, or Y9 TOPs) to report a second beam management or beam prediction scheme (model).

[0230] Further examples will not be elaborated here.

[0231] Optionally, the second AI processing capability corresponding to the AI ​​function (AI model) reported by the UE may also include: the Y APUs (or YFLOPs or YTOPs) required for the UE to process specific configurations, resources, and reference signals in the AI ​​function (AI model) reported by the UE.

[0232] For example, if a UE reports that it uses AI functions (AI models) to process the first reference signal (e.g., CSI configuration, CSI resources, CSI reference signal), it requires Y10 APUs (or Y10 FLOPs, or Y10 TOPs).

[0233] For example, if a UE reports that it is using AI functions (AI models) to process the first transmission scheme (e.g., overlaying pilot configuration, resources, and symbols), it requires Y11 APUs (or Y11 FLOPs, or Y11 TOPs).

[0234] Further examples will not be elaborated here.

[0235] III. Examples of the methods and processes for UE to report the second AI processing capability corresponding to the AI ​​function (AI model) are as follows:

[0236] The UE can indicate the second AI processing capability corresponding to the AI ​​function (AI model) to the network in one or more of the following processes.

[0237] (1) UE capability reporting.

[0238] (2) When the UE reports supported functionalities, it indicates the second AI processing capability corresponding to that functionality (or model).

[0239] (3) When the UE reports applicable functionalities, it indicates the second AI processing capability corresponding to that functionality (or model).

[0240] (4) When the UE reports activated functionalities, it indicates the second AI processing capability corresponding to that functionality (or model).

[0241] For example, in the second or fourth step of the process shown in Figure 10, the network is instructed to have the second AI processing capability corresponding to the AI ​​function (AI model).

[0242] Step S1010: The network sends a UE Capability Request message to the UE.

[0243] Step S1020: The UE sends a UE Capability Information message to the network, which includes the functions supported by the UE.

[0244] Step S1030: The network sends an RRC Reconfiguration message to the UE.

[0245] Step S1040: UE reports applicable functionality reporting.

[0246] Step S1050: The network sends an RRC Reconfiguration message to the UE.

[0247] Step S1060: The UE and the network perform one or more operations such as activation, deactivation, inference, and monitoring.

[0248] IV. As shown in Figure 11, optionally, the base station may instruct the UE to report a second processing capability corresponding to a specific function or model (S1110). For example, the base station may send a UE capability request message (e.g., UE Capability Entrance) or an RRC message to trigger the UE to report the second processing capability corresponding to the specific function or model (S1120). In the message sent by the base station, a specific function or model may be indicated, such as a specific ID (e.g., function ID, model ID, data ID, condition D, etc.), requiring the UE to report the second processing capability of the function or model corresponding to the ID.

[0249] The network instructs the UE to report its AI processing capabilities (first processing capabilities) and the network instructs the UE to report the second processing capabilities corresponding to a specific function or model. The same signaling can be used. For example, one message can simultaneously trigger the UE to report the first processing capabilities and the second processing capabilities corresponding to a specific function or model.

[0250] V. Optionally, the UE may report the number of use cases K that it can support (e.g., parallel support) (e.g., K AI functions or K models), and / or the UE may report that the AI ​​processing capability requirement for each use case does not exceed X APUs (or X FLOPs, or X TOPs). This is another method for the UE to indirectly indicate its AI processing capability by using the number of supportable use cases and the maximum processing capability that each use case cannot exceed to help the network side understand the UE's AI processing capability.

[0251] VI. Optionally, the "UE reporting" operation and function mentioned in the above description can be replaced by a protocol agreement.

[0252] For example, the agreement stipulates (1) the AI ​​processing capability of the UE, or stipulates the AI ​​processing capability level of the UE, and / or (2) the AI ​​processing capability / requirements corresponding to the AI ​​function (AI model).

[0253] For example, the protocol specifies the AI ​​processing capability of the UE, which may include one or more of the following: the protocol specifies the UE's primary AI processing capability, such as X APUs (AI processing units), X FLOPs, or X TOPs.

[0254] For example, the agreement specifies the AI ​​processing capabilities corresponding to the AI ​​function (AI model).

[0255] For example, the agreement specifies the second AI processing capability corresponding to the AI ​​function (AI model). Specifically, it may include, for example, the number of Y APUs corresponding to a specific AI function (AI model) (or YFLOPs or YTOPs).

[0256] 7. The "UE reporting" operation and function mentioned above can be completed by the network instructing the UE. Optionally, the UE can notify the network to confirm the corresponding requirement.

[0257] For example: the network indicates (1) the requirement for the AI ​​processing capability of the UE, or the requirement for the AI ​​processing capability level of the UE, and / or (2) the AI ​​processing capability / requirement corresponding to the AI ​​function (AI model).

[0258] For example, the network indicates a requirement for the UE's AI processing capabilities. Specifically, this may include one or more of the following: the network indicates a requirement for the UE's initial AI processing capabilities, such as X APUs (AI processing units), XFLOPs, or XTOPs. Optionally, the UE notifies the network to confirm the corresponding requirement.

[0259] For example, the network indicates the AI ​​processing capability corresponding to the AI ​​function (AI model). Optionally, the UE notifies the network to confirm the corresponding AI processing capability indicated by the network.

[0260] For example, the network indicates the second AI processing capability corresponding to the AI ​​function (AI model). Specifically, it may include, for example, the number of Y APUs (or YFLOPs or YTOPs) corresponding to a specific AI function (AI model).

[0261] 8. During the above process, when the network provides indication information to the UUE, one or more of the following methods may be used:

[0262] (1) Broadcast message, (2) RRC message, (3) Media Access Control Control Element (MAC CE), (4) Downlink Control Information (DCI) message, (5) Physical Downlink Control Channel (PDCCH), (6) Physical Downlink Shared Channel (PDSCH), (7) Downlink Reference Signal Transmission, (8) AI / ML Dedicated Downlink Channel, (9) Network-side Capability Indicator, (10) Specific Dataset Transmission Channel, (11) Specific Dataset Transmission Container.

[0263] In the above process, when the UE sends indication information to the network, one or more of the following methods can be used:

[0264] (1) RRC message, (2) UCI ​​message, (3) Physical Uplink Control Channel (PUCCH), (4) Physical Uplink Shared Channel (PUSCH), (5) Uplink Reference Signal Transmission, (6) AI / ML Dedicated Uplink Channel, (7) UE-side Capability Indicator, (8) Specific Dataset Transmission Channel, (9) Specific Dataset Transmission Container.

[0265] This application provides a scheme for confirming and indicating AI / ML processing power (APU). Since different use cases in AI / ML schemes may have demands for AI computing power, the AI ​​use cases that can be activated and used simultaneously are limited by the AI ​​processing power. This scheme considers introducing a general AI processing power unit, requiring clear explanation and protocol design regarding the definition and usage of the APU. Furthermore, considering the issue of the public availability of the actual AI processing power on the UE side, and considering that the AI ​​functions / models used on the UE side may also originate from the network, and that the configuration and activation of functions / models are affected by factors such as network control, this application provides a method that allows the network to determine the UE APU status corresponding to a specific AI function or model while protecting the UE-side computing power information.

[0266] Figure 12 is a schematic block diagram of a first communication device 1200 according to an embodiment of the present application. The first communication device 1200 may include:

[0267] The transceiver unit 1210 is used to send first information, which is used to indicate information related to the processing capability of the first communication device.

[0268] In one embodiment, the transceiver unit 1210 is further configured to receive second information, which is used to trigger the first communication device to send the first information.

[0269] In one implementation, the second information includes one or more of the following: a first communication device capability request message; an RRC message.

[0270] In one embodiment, the processing capability information of the first communication device includes: the first processing capability of the first communication device.

[0271] In one implementation, the first processing capability of the first communication device is for one or more of the following:

[0272] First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

[0273] In one embodiment, the first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support.

[0274] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0275] The number of APUs that this first communication device can support;

[0276] The number of FLOPs that the first communication device can support;

[0277] The number of TOPs that the first communication device can support.

[0278] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0279] The number of APUs that the first communication device can support within the first time unit;

[0280] The number of FLOPs that the first communication device can support within the first time unit;

[0281] The number of TOPs that the first communication device can support within the first time unit.

[0282] In one implementation, the first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0283] In one embodiment, the processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

[0284] In one implementation, the first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

[0285] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0286] The number of APUs corresponding to the AI ​​function and / or the AI ​​model;

[0287] The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model;

[0288] The number of TOPs corresponding to the AI ​​function and / or the AI ​​model;

[0289] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0290] The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0291] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, first resource, or first reference signal.

[0292] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0293] The number of APUs required for each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0294] The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0295] The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0296] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0297] The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0298] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit.

[0299] In one implementation, the second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0300] In one implementation, the AI ​​function and / or AI model includes one or more of the following:

[0301] AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based localization, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation, AI / ML-based demodulation, AI / ML-based channel coding, AI / ML-based channel decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based RLF prediction, AI / ML-based resource management.

[0302] In one implementation, the second processing capability is transmitted in one or more of the following processes:

[0303] When the first communication device reports its capability;

[0304] When the first communication device reports the first supported function and / or first model;

[0305] When the first communication device reports the available first function and / or first model;

[0306] When the first communication device reports the activation of the first function and / or the first model.

[0307] In one implementation, the second processing capability is sent in one or more of the following messages:

[0308] Capability information of the first communication device;

[0309] The available functionalities of the first communication device are reported.

[0310] In one embodiment, the processing capability information of the first communication device includes:

[0311] The number of use cases that the first communication device can support; the processing capacity requirements corresponding to each use case that the first communication device can support.

[0312] In one implementation, the processing capacity requirement for each use case includes: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

[0313] In one implementation, the third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0314] In one embodiment, the transceiver unit 1210 is further configured to receive third information, which is used to indicate the processing capability requirements of the second communication device for the first communication device.

[0315] In one implementation, the processing capability requirement information for the first communication device includes one or more of the following:

[0316] The requirement for the AI ​​processing capabilities of this first communication device;

[0317] The required level of AI processing capability for the first communication device;

[0318] The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device;

[0319] The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

[0320] In one embodiment, the processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability demand of the second communication device for the first communication device.

[0321] The first communication device 1200 of this application embodiment can realize the corresponding functions of the first communication device in the foregoing method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the first communication device 1200 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the first communication device 400 of the application embodiment can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0322] Figure 13 is a schematic block diagram of a second communication device 1300 according to an embodiment of the present application. The second communication device 1300 may include:

[0323] The transceiver unit 1310 is used to receive first information, which is used to indicate information related to the processing capability of the first communication device.

[0324] In one embodiment, the transceiver unit 1310 is further configured to send second information, which triggers the first communication device to send the first information.

[0325] In one implementation, the second information includes one or more of the following: a first communication device capability request message; an RRC message.

[0326] In one embodiment, the processing capability information of the second communication device includes: the first processing capability of the first communication device.

[0327] In one implementation, the first processing capability of the first communication device is for one or more of the following:

[0328] First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

[0329] In one embodiment, the first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support.

[0330] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0331] The number of APUs that this first communication device can support;

[0332] The number of FLOPs that the first communication device can support;

[0333] The number of TOPs that the first communication device can support.

[0334] In one implementation, the AI ​​processing capabilities supported by the first communication device include one or more of the following:

[0335] The number of APUs that the first communication device can support within the first time unit;

[0336] The number of FLOPs that the first communication device can support within the first time unit;

[0337] The number of TOPs that the first communication device can support within the first time unit.

[0338] In one implementation, the first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0339] In one embodiment, the processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

[0340] In one implementation, the first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

[0341] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0342] The number of APUs corresponding to the AI ​​function and / or the AI ​​model;

[0343] The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model;

[0344] The number of TOPs corresponding to the AI ​​function and / or the AI ​​model;

[0345] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0346] The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal;

[0347] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, first resource, or first reference signal.

[0348] In one implementation, the second processing capability corresponding to the AI ​​function and / or the AI ​​model includes one or more of the following:

[0349] The number of APUs required for each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0350] The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0351] The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model;

[0352] The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0353] The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit;

[0354] The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit.

[0355] In one implementation, the second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0356] In one implementation, the AI ​​function and / or AI model includes one or more of the following:

[0357] AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based localization, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation, AI / ML-based demodulation, AI / ML-based channel coding, AI / ML-based channel decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based RLF prediction, AI / ML-based resource management.

[0358] In one implementation, the second processing capability is transmitted in one or more of the following processes:

[0359] When the first communication device reports its capability;

[0360] When the first communication device reports the first supported function and / or first model;

[0361] When the first communication device reports the available first function and / or first model;

[0362] When the first communication device reports the activation of the first function and / or the first model.

[0363] In one implementation, the second processing capability is sent in one or more of the following messages:

[0364] Capability information of the first communication device;

[0365] The available functionalities of the first communication device are reported.

[0366] In one embodiment, the processing capability information of the first communication device includes:

[0367] The number of use cases that the first communication device can support; the processing capacity requirements corresponding to each use case that the first communication device can support.

[0368] In one implementation, the processing capacity requirement for each use case includes: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

[0369] In one implementation, the third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

[0370] In one embodiment, the transceiver unit 1310 is further configured to transmit third information, which is used to indicate the processing capability requirements of the second communication device for the first communication device.

[0371] In one implementation, the processing capability requirement information for the first communication device includes one or more of the following:

[0372] The requirement for the AI ​​processing capabilities of this first communication device;

[0373] The required level of AI processing capability for the first communication device;

[0374] The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device;

[0375] The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

[0376] In one embodiment, the processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability demand of the second communication device for the first communication device.

[0377] The second communication device 1300 of this application embodiment can realize the corresponding functions of the second communication device in the foregoing method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the second communication device 1300 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the second communication device 1300 of the application embodiment can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0378] Figure 14 is a schematic structural diagram of a communication device 1400 according to an embodiment of this application. The communication device 1400 includes a processor 1410, which can call and run computer programs from memory to enable the communication device 1400 to implement the methods in the embodiments of this application.

[0379] In one embodiment, the communication device 1400 may further include a memory 1420. The processor 1410 can retrieve and run computer programs from the memory 1420 to enable the communication device 1400 to implement the methods described in the embodiments of this application.

[0380] The memory 1420 can be a separate device independent of the processor 1410, or it can be integrated into the processor 1410.

[0381] In one embodiment, the communication device 1400 may further include a transceiver 1430, and the processor 1410 may control the transceiver 1430 to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices.

[0382] The transceiver 1430 may include a transmitter and a receiver. The transceiver 1430 may further include an antenna, and the number of antennas may be one or more.

[0383] In one embodiment, the communication device 1400 may be the first communication device in the embodiments of this application, and the communication device 1400 may implement the corresponding processes implemented by the first communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0384] In one embodiment, the communication device 1400 may be a second communication device in the embodiments of this application, and the communication device 1400 may implement the corresponding processes implemented by the second communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0385] Figure 15 is a schematic structural diagram of a chip 1500 according to an embodiment of this application. The chip 1500 includes a processor 1510, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0386] In one embodiment, chip 1500 may further include memory 1520. Processor 1510 can retrieve and run computer programs from memory 1520 to implement the methods executed by the first or second communication device in this embodiment.

[0387] The memory 1520 can be a separate device independent of the processor 1510, or it can be integrated into the processor 1510.

[0388] In one embodiment, the chip 1500 may further include an input interface 1530. The processor 1510 can control the input interface 1530 to communicate with other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0389] In one embodiment, the chip 1500 may further include an output interface 1540. The processor 1510 can control the output interface 1540 to communicate with other devices or chips; specifically, it can output information or data to other devices or chips.

[0390] In one implementation, the chip can be applied to the first communication device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the first communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0391] In one implementation, the chip can be applied to the second communication device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the second communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0392] The chips used in the first communication device and the second communication device can be the same chip or different chips.

[0393] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0394] The processors mentioned above can be general-purpose processors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processors mentioned above can be microprocessors or any conventional processor.

[0395] The aforementioned memory can be volatile memory or non-volatile memory, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM).

[0396] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0397] Figure 16 is a schematic block diagram of a communication system 1600 according to an embodiment of the present application. The communication system 1600 includes a first communication device 1610 and a second communication device 1620.

[0398] A first communication device 1610 is used to send first information, which is used to indicate information related to the processing capability of the first communication device.

[0399] The second communication device 1620 is used to receive the first information.

[0400] The first communication device 1610 can be used to implement the corresponding functions implemented by the first communication device in the above method, and the second communication device 1620 can be used to implement the corresponding functions implemented by the second communication device in the above method. For the sake of brevity, further details are omitted here.

[0401] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0402] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0403] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0404] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, comprising: The first communication device sends first information, which is used to indicate information related to the processing capabilities of the first communication device.

2. The method according to claim 1, wherein, The method further includes: The first communication device receives the second information, which triggers the first communication device to send the first information.

3. The method according to claim 2, wherein, The second information includes one or more of the following: a first communication device capability request message; a radio resource control (RRC) message.

4. The method according to any one of claims 1 to 3, wherein, The information related to the processing capability of the first communication device includes: the first processing capability of the first communication device.

5. The method according to claim 4, wherein, The first processing capability of the first communication device is for one or more of the following: First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

6. The method according to claim 4 or 5, wherein, The first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support.

7. The method according to claim 6, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of artificial intelligence processing units (APUs) that the first communication device can support; The number of floating-point operations (FLOPs) that the first communication device can support; The number of trillions of operations (TOPs) that the first communication device can support.

8. The method according to claim 6, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of APUs that the first communication device can support within the first time unit; The number of FLOPs that the first communication device can support within the first time unit; The number of TOPs that the first communication device can support within the first time unit.

9. The method according to claim 8, wherein, The first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

10. The method according to any one of claims 1 to 3, wherein, The processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

11. The method according to claim 10, wherein, The first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

12. The method according to claim 11, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

13. The method according to claim 11, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit; The number of TOPs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

14. The method according to claim 13, wherein, The second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

15. The method according to any one of claims 11 to 14, wherein, The AI ​​functions and / or AI models include one or more of the following: Channel State Information (CSI) Feedback Based on Artificial Intelligence (AI) / Machine Learning (ML): Coding Model for CSI Feedback Based on AI / ML; CSI Prediction Based on AI / ML; Beam Management Based on AI / ML; Beam Prediction Based on AI / ML; Beam Management Failure Prediction Based on AI / ML; Localization Based on AI / ML; Channel Estimation Based on AI / ML; Superimposed Pilot Reception Based on AI / ML; Modulation Based on AI / ML; Demodulation Based on AI / ML; Channel Coding Based on AI / ML; Channel Decoding Based on AI / ML; Precoding Based on AI / ML; Waveform Nonlinear Compensation Based on AI / ML; Mobility Management Based on AI / ML; Radio Link Failure (RLF) Prediction Based on AI / ML; Resource Management Based on AI / ML.

16. The method according to any one of claims 10 to 15, wherein, The second processing capability is sent in one or more of the following processes: When the first communication device reports its capability; When the first communication device reports the supported first function and / or first model; When the first communication device reports the available first function and / or first model; When the first communication device reports the activation of the first function and / or the first model.

17. The method according to any one of claims 10 to 16, wherein, The second processing capability is sent in one or more of the following messages: Capability information of the first communication device; The first communication device reports its available functions.

18. The method according to any one of claims 1 to 17, wherein, The processing capability information of the first communication device includes: The number of use cases that the first communication device can support; the processing capability requirements corresponding to each use case that the first communication device can support.

19. The method according to claim 18, wherein, The processing capacity requirements for each use case include: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

20. The method according to claim 19, wherein, The third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

21. The method according to claim 1, wherein, The method further includes: The first communication device receives third information, which is used to indicate the processing capability requirements of the second communication device for the first communication device.

22. The method according to claim 21, wherein, The processing capability requirements of the first communication device include one or more of the following: The requirement for AI processing capabilities of the first communication device; The required level of AI processing capability for the first communication device; The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device; The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

23. The method according to claim 21 or 22, wherein, The processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability requirements of the second communication device for the first communication device.

24. A communication method, comprising: The second communication device receives the first information, which is used to indicate information related to the processing capabilities of the first communication device.

25. The method according to claim 24, wherein, The method further includes: The second communication device sends a second message, which triggers the first communication device to send the first message.

26. The method of claim 25, wherein, The second information includes one or more of the following: a first communication device capability request message; an RRC message.

27. The method according to any one of claims 24 to 26, wherein, The information related to the processing capability of the first communication device includes: the first processing capability of the first communication device.

28. The method according to claim 27, wherein, The first processing capability of the first communication device is for one or more of the following: First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

29. The method according to claim 27 or 28, wherein, The first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support.

30. The method according to claim 29, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of APUs that the first communication device can support; The number of FLOPs that the first communication device can support; The number of TOPs that the first communication device can support.

31. The method according to claim 29, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of APUs that the first communication device can support within the first time unit; The number of FLOPs that the first communication device can support within the first time unit; The number of TOPs that the first communication device can support within the first time unit.

32. The method according to claim 31, wherein, The first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

33. The method according to any one of claims 24 to 26, wherein, The processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

34. The method according to claim 33, wherein, The first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

35. The method according to claim 34, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

36. The method according to claim 34, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit; The number of TOPs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

37. The method of claim 36, wherein, The second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

38. The method according to any one of claims 34 to 37, wherein, The AI ​​functions and / or AI models include one or more of the following: AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based localization, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation, AI / ML-based demodulation, AI / ML-based channel coding, AI / ML-based channel decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based RLF prediction, AI / ML-based resource management.

39. The method according to any one of claims 33 to 38, wherein, The second processing capability is sent in one or more of the following processes: When the first communication device reports its capability; When the first communication device reports the supported first function and / or first model; When the first communication device reports the available first function and / or first model; When the first communication device reports the activation of the first function and / or the first model.

40. The method according to any one of claims 33 to 39, wherein, The second processing capability is sent in one or more of the following messages: Capability information of the first communication device; The first communication device reports its available functions.

41. The method according to any one of claims 24 to 40, wherein, The processing capability information of the first communication device includes: The number of use cases that the first communication device can support; the processing capability requirements corresponding to each use case that the first communication device can support.

42. The method according to claim 41, wherein, The processing capacity requirements for each use case include: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

43. The method according to claim 42, wherein, The third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

44. The method of claim 24, wherein, The method further includes: The second communication device sends a third message, which is used to indicate the second communication device's requirement for the processing capabilities of the first communication device.

45. The method according to claim 44, wherein, The processing capability requirements of the first communication device include one or more of the following: The requirement for AI processing capabilities of the first communication device; The required level of AI processing capability for the first communication device; The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device; The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

46. ​​The method according to claim 44 or 45, wherein, The processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability requirements of the second communication device for the first communication device.

47. A first communication device, comprising: The transceiver unit is used to send first information, which is used to indicate information related to the processing capabilities of the first communication device.

48. The first communication device according to claim 47, wherein, The transceiver unit is also used to receive second information, which triggers the first communication device to send the first information.

49. The first communication device according to claim 48, wherein, The second information includes one or more of the following: a first communication device capability request message; an RRC message.

50. The first communication device according to any one of claims 47 to 49, wherein, The information related to the processing capability of the first communication device includes: the first processing capability of the first communication device.

51. The first communication device according to claim 50, wherein, The first processing capability of the first communication device is for one or more of the following: First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

52. The first communication device according to claim 50 or 51, wherein, The first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support.

53. The first communication device according to claim 52, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of APUs that the first communication device can support; The number of FLOPs that the first communication device can support; The number of TOPs that the first communication device can support.

54. The first communication device according to claim 52, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of APUs that the first communication device can support within the first time unit; The number of FLOPs that the first communication device can support within the first time unit; The number of TOPs that the first communication device can support within the first time unit.

55. The first communication device according to claim 54, wherein, The first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

56. The first communication device according to any one of claims 47 to 49, wherein, The processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

57. The first communication device according to claim 56, wherein, The first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

58. The first communication device according to claim 57, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

59. The first communication device according to claim 57, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit; The number of TOPs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

60. The first communication device according to claim 59, wherein, The second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

61. The first communication device according to any one of claims 57 to 60, wherein, The AI ​​functions and / or AI models include one or more of the following: AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based localization, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation, AI / ML-based demodulation, AI / ML-based channel coding, AI / ML-based channel decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based RLF prediction, AI / ML-based resource management.

62. The first communication device according to any one of claims 56 to 61, wherein, The second processing capability is sent in one or more of the following processes: When the first communication device reports its capability; When the first communication device reports the supported first function and / or first model; When the first communication device reports the available first function and / or first model; When the first communication device reports the activation of the first function and / or the first model.

63. The first communication device according to any one of claims 56 to 62, wherein, The second processing capability is sent in one or more of the following messages: Capability information of the first communication device; The first communication device reports its available functions.

64. The first communication device according to any one of claims 47 to 63, wherein, The processing capability information of the first communication device includes: The number of use cases that the first communication device can support; the processing capability requirements corresponding to each use case that the first communication device can support.

65. The first communication device according to claim 64, wherein, The processing capacity requirements for each use case include: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

66. The first communication device according to claim 65, wherein, The third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

67. The first communication device according to claim 47, wherein, The transceiver unit is also used to receive third information, which is used to indicate the processing capability requirements of the second communication device for the first communication device.

68. The first communication device according to claim 67, wherein, The processing capability requirements of the first communication device include one or more of the following: The requirement for AI processing capabilities of the first communication device; The required level of AI processing capability for the first communication device; The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device; The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

69. The first communication device according to claim 67 or 68, wherein, The processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability requirements of the second communication device for the first communication device.

70. A second communication device, comprising: The transceiver unit is used to receive first information, which is used to indicate information related to the processing capabilities of the first communication device.

71. The second communication device according to claim 70, wherein, The transceiver unit is also used to send second information, which triggers the first communication device to send the first information.

72. The second communication device according to claim 71, wherein, The second information includes one or more of the following: a first communication device capability request message; an RRC message.

73. The second communication device according to any one of claims 70 to 72, wherein, The information related to the processing capability of the second communication device includes: the first processing capability of the first communication device.

74. The second communication device according to claim 73, wherein, The first processing capability of the first communication device is for one or more of the following: First use case; First use case group; Multiple use cases; One carrier; Multiple carriers; One serving cell; Multiple serving cells.

75. The second communication device according to claim 73 or 74, wherein, The first processing capability of the first communication device includes the AI ​​processing capability that the first communication device can support.

76. The second communication device according to claim 75, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of APUs that the first communication device can support; The number of FLOPs that the first communication device can support; The number of TOPs that the first communication device can support.

77. The second communication device according to claim 75, wherein, The AI ​​processing capabilities supported by the first communication device include one or more of the following: The number of APUs that the first communication device can support within the first time unit; The number of FLOPs that the first communication device can support within the first time unit; The number of TOPs that the first communication device can support within the first time unit.

78. The second communication device according to claim 77, wherein, The first time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

79. The second communication device according to any one of claims 70 to 72, wherein, The processing capability information of the first communication device includes: the first function of the first communication device and / or the second processing capability corresponding to the first model.

80. The second communication device according to claim 79, wherein, The first function and / or first model of the first communication device includes configurable, supportable, or supported AI functions and / or AI models of the first communication device.

81. The second communication device according to claim 80, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of TOPs required for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

82. The second communication device according to claim 80, wherein, The AI ​​function and / or the second processing capability corresponding to the AI ​​model includes one or more of the following: The number of APUs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of FLOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of TOPs required within each second time unit corresponding to the AI ​​function and / or the AI ​​model; The number of APUs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal; The number of FLOPs required by the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal within each second time unit; The number of TOPs required in each second time unit for the AI ​​function and / or the AI ​​model to process the first configuration, the first resource, or the first reference signal.

83. The second communication device according to claim 82, wherein, The second time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

84. The second communication device according to any one of claims 80 to 83, wherein, The AI ​​functions and / or AI models include one or more of the following: AI / ML-based CSI feedback, AI / ML-based CSI feedback coding model, AI / ML-based CSI prediction, AI / ML-based beam management, AI / ML-based beam prediction, AI / ML-based beam management failure prediction, AI / ML-based localization, AI / ML-based channel estimation, AI / ML-based superimposed pilot reception, AI / ML-based modulation, AI / ML-based demodulation, AI / ML-based channel coding, AI / ML-based channel decoding, AI / ML-based precoding, AI / ML-based waveform nonlinearity compensation, AI / ML-based mobility management, AI / ML-based RLF prediction, AI / ML-based resource management.

85. The second communication device according to any one of claims 79 to 84, wherein, The second processing capability is sent in one or more of the following processes: When the first communication device reports its capability; When the first communication device reports the supported first function and / or first model; When the first communication device reports the available first function and / or first model; When the first communication device reports the activation of the first function and / or the first model.

86. The second communication device according to any one of claims 79 to 85, wherein, The second processing capability is sent in one or more of the following messages: Capability information of the first communication device; The first communication device reports its available functions.

87. The second communication device according to any one of claims 70 to 86, wherein, The processing capability information of the first communication device includes: The number of use cases that the first communication device can support; the processing capability requirements corresponding to each use case that the first communication device can support.

88. The second communication device according to claim 87, wherein, The processing capacity requirements for each use case include: no more than the number of APUs, no more than the number of FLOPs, or no more than the number of X TOPs, no more than the number of APUs in the third time unit, no more than the number of FLOPs in the third time unit, and no more than the number of TOPs in the third time unit.

89. The second communication device according to claim 88, wherein, The third time unit is any of the following: millisecond, second, symbol, time slot, subframe, frame.

90. The second communication device according to claim 70, wherein, The transceiver unit is also used to send third information, which is used to indicate the processing capability requirements of the second communication device for the first communication device.

91. The second communication device according to claim 90, wherein, The processing capability requirements of the first communication device include one or more of the following: The requirement for AI processing capabilities of the first communication device; The required level of AI processing capability for the first communication device; The AI ​​function and / or AI processing capability corresponding to the AI ​​model of the first communication device; The AI ​​processing requirements corresponding to the AI ​​functions and / or AI models of the first communication device.

92. The second communication device according to claim 90 or 91, wherein, The processing capability-related information of the first communication device includes: demand confirmation information, which is used to confirm the processing capability requirements of the second communication device for the first communication device.

93. A communication device, comprising: A transceiver, a processor, and a memory, wherein the memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to invoke and run the computer program stored in the memory to cause the communication device to perform the method as described in any one of claims 1 to 46.

94. A chip, comprising: A processor for retrieving and running a computer program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1 to 46.

95. A computer-readable storage medium for storing a computer program that, when run by a device, causes the device to perform the method as claimed in any one of claims 1 to 46.

96. A computer program product comprising computer program instructions that cause a computer to perform the method as claimed in any one of claims 1 to 46.

97. A computer program that causes a computer to perform the method as claimed in any one of claims 1 to 46.

98. A communication system, comprising: A first communication device is configured to perform the method as described in any one of claims 1 to 23; A second communication device is used to perform the method as described in any one of claims 24 to 46.

Images