Communication method and apparatus

Abstract

A communication method and apparatus. A terminal can indicate, to a network, available inference parameter groups or one or more available sets of inference parameters in an inference parameter group, so that the network learns the availability of each set of inference parameters, thereby avoiding using unavailable inference parameters to configure an unreasonable inference scheme. The method comprises: a terminal receives first information, wherein the first information comprises at least one inference parameter group, a first inference parameter group comprises Y sets of inference parameters, Y is a positive integer greater than 1, and the first inference parameter group is any inference parameter group of the at least one inference parameter group; and the terminal sends second information, wherein the second information indicates that all the Y sets of inference parameters are available, or the second information indicates M available sets of inference parameters among the Y sets of inference parameters, and M is a positive integer smaller than Y.

Description

Communication methods and devices

[0001] This application claims priority to Chinese Patent Application No. 202510372077.X, filed on March 25, 2025, entitled "Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to communication methods and apparatus. Background Technology

[0003] Current mobile networks, supporting increasingly diverse services, require support for ultra-high speeds, ultra-low latency, ultra-high reliability, and massive connectivity. These new demands present unprecedented challenges to mobile network planning, operation, and efficient management. Network planning based on human experience or simple algorithms is time-consuming, costly, and suffers from poor adaptability in self-optimization and scheduling algorithms, making it unsuitable for addressing these new challenges. Therefore, the application of artificial intelligence (AI) in mobile networks has emerged. Introducing AI and machine learning (ML) into mobile networks can significantly improve the efficiency of network planning, configuration, and resource scheduling, achieving network intelligence.

[0004] Currently, for AL / ML models on the terminal side, the network can send one or more sets of inference parameters to the terminal to determine whether the terminal's model and / or functions are available with the set of inference parameters. The terminal can report the availability of each set of inference parameters to indicate whether the terminal's model and / or functions support the set of inference parameters.

[0005] However, a set of inference parameters may include multiple sets of inference parameters. In this case, how to report the availability of inference parameters is a problem that needs to be solved. Summary of the Invention

[0006] This application provides a communication method and apparatus that can report at least one set of inference parameters that are available from a set of inference parameters, thereby improving the accuracy of inference parameter availability reporting.

[0007] In a first aspect, a communication method is provided. This method can be executed by a terminal, by a module applied to the terminal (e.g., a processor, chip, or chip system), or by a logical node, logical module, or software capable of implementing all or part of the terminal's functions. The method includes: receiving first information, the first information including at least one inference parameter group, the first inference parameter group including Y sets of inference parameters, where Y is a positive integer greater than 1, and the first inference parameter group being any one of the at least one inference parameter group; and sending second information, the second information indicating that all Y sets of inference parameters are available, or, the second information indicating that M sets of inference parameters are available from the Y sets of inference parameters, where M is a positive integer less than Y.

[0008] In the above design approach, when an inference parameter group includes multiple sets of inference parameters, the terminal can indicate to the network that all sets of inference parameters in a set are available, or indicate that one or more sets of inference parameters in a set are available. That is, availability can be reported at the granularity of each set of inference parameters. Compared with reporting availability at the granularity of a set, this improves the accuracy of the terminal's reporting of inference parameter availability. It allows the network to know the availability of each set of inference parameters, thereby avoiding problems such as using unavailable inference parameters to configure unreasonable inference schemes, which could lead to the model failing to activate. This can also improve the accuracy of model application.

[0009] In conjunction with the first aspect mentioned above, in one possible design, when the second information indicates that all Y sets of inference parameters are available, the second information includes the identifier of the first inference parameter group and first indication information, whereby the first indication information indicates availability. This indicates that the first inference parameter group is available, meaning that all Y sets of inference parameters in the first inference parameter group are available. Compared to reporting the identifier of each set of inference parameters in the first inference parameter group, this saves signaling overhead.

[0010] In conjunction with the first aspect mentioned above, in one possible design approach, when the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, the second information includes the identification information of each set of inference parameters in the M sets of inference parameters and the first indication information. The first indication information indicates availability. In this way, the available inference parameters can be indicated by the identification information of the inference parameters and the first indication information, so as to accurately indicate the available inference parameters in a set of inference parameters, avoiding the general indication that the set of inference parameters is available, which would lead the network side to believe that every set of inference parameters in the set of inference parameters is available, and thus configure an unreasonable inference scheme using in fact unavailable inference parameters.

[0011] In conjunction with the first aspect described above, in one possible design approach, the identification information of the m-th set of inference parameters in the M sets of inference parameters is the arrangement position of the m-th set of inference parameters in at least one inference parameter group, where m = 1, ..., M. Thus, the terminal can indicate the availability of the m-th set of inference parameters by the arrangement position of the m-th set of inference parameters in at least one inference parameter group, and further, by combining this with the first indication information.

[0012] In conjunction with the first aspect mentioned above, in one possible design approach, the identification information of the m-th inference parameter among the M sets of inference parameters is a global identifier for the m-th inference parameter, where m = 1, ..., M. Thus, the terminal can indicate the availability of the m-th inference parameter by using its global identifier, and further, by combining this with the first indication information.

[0013] Optionally, Y sets of inference parameters are carried in Y information cells, and the global identifier of the m-th set of inference parameters is the identifier of the information cell carrying the m-th set of inference parameters, where m = 1, ..., M.

[0014] In conjunction with the first aspect described above, in one possible design, the second information also includes the identifier of the first inference parameter group. Thus, when the terminal reports the identifier of the first inference parameter group, it can directly indicate the inference parameter group corresponding to the available M sets of inference parameters.

[0015] In conjunction with the first aspect above, in one possible design approach, the identification information of the m-th inference parameter in the M sets of inference parameters includes the identifier of the first inference parameter group and the index of the m-th inference parameter. The index of the m-th inference parameter is determined based on at least one of the following: the identifier of the first inference parameter group, the global identifier of the m-th inference parameter, or the arrangement position of the m-th inference parameter in at least one inference parameter group, where m = 1, ..., M.

[0016] In the above design, within the first inference parameter group, the index of the m-th set of inference parameters can indicate the m-th set of inference parameters. Therefore, based on the index of the m-th set of inference parameters and combined with the identifier of the first inference parameter group, the m-th set of inference parameters in at least one inference parameter group can be indicated. Furthermore, combined with the first indication information, it can be indicated that the m-th set of inference parameters is available.

[0017] In conjunction with the first aspect above, in one possible design, where the second information indicates the availability of M sets of inference parameters out of Y sets of inference parameters, the second information includes an identifier of the first inference parameter group and a bit map. The bit map includes Y bits, each of the Y bits corresponding to one set of inference parameters out of the Y sets of inference parameters. The M sets of inference parameters are the inference parameters corresponding to the bits in the Y bits that are set to a first value.

[0018] Among them, after sorting the Y sets of inference parameters according to the global identifier or index of the Y sets of inference parameters, the y-th bit in the Y sets of inference parameters corresponds to the y-th set of inference parameters in the Y sets of inference parameters, y = 1, ..., Y.

[0019] In the above design, the M sets of inference parameters available in an inference parameter group can be indicated by the bitmap, which reduces resource overhead.

[0020] In conjunction with the first aspect described above, in one possible design approach, where the second information indicates that M sets of inference parameters are available out of Y sets, the method further includes: sending a third information indicating that N sets of inference parameters are unavailable out of the Y sets, where N is a positive integer less than Y. The terminal can also directly indicate the unavailable inference parameters to the RAN node, allowing the network side to more directly determine the unavailable inference parameters and avoid configuring an unreasonable inference scheme using unavailable inference parameters.

[0021] In conjunction with the first aspect mentioned above, in one possible design approach, the first information also includes an identifier for the first inference parameter group, so that the terminal can determine the multiple sets of inference parameters corresponding to the first inference parameter group based on the identifier of the first inference parameter group.

[0022] In conjunction with the first aspect above, in one possible design approach, the first information may also include one or more of the following: a global identifier for each set of inference parameters in the Y sets of inference parameters, or an index for the Y sets of inference parameters, so that the terminal may indicate a set of available or unavailable inference parameters based on the above information.

[0023] Optionally, the first information may also include the total number of sets of inference parameters in the first inference parameter group, so that the terminal can directly determine the total number of sets of inference parameters in the first inference parameter group based on this information, saving the terminal time overhead in determining the total number of sets.

[0024] Secondly, a communication method is provided. This method can be executed by a RAN node, by a module applied to the RAN node (e.g., a processor, chip, or chip system), or by a logical node, logical module, or software capable of implementing all or part of the RAN node's functions. The method includes: sending first information, the first information including at least one first inference parameter group, the first inference parameter group including Y sets of inference parameters, where Y is a positive integer greater than 1, and the first inference parameter group being any one of the at least one inference parameter group; receiving second information, the second information indicating that all Y sets of inference parameters are available, or, the second information indicating that M sets of inference parameters are available from the Y sets of inference parameters, where M is a positive integer less than Y. The technical effects of the second aspect are analogous to those of the first aspect and will not be elaborated further here.

[0025] In conjunction with the second aspect above, in one possible design approach, when the second information indicates that all Y sets of inference parameters are available, the second information includes the identifier of the first inference parameter group and the first indication information, which indicates availability.

[0026] In conjunction with the second aspect above, in one possible design approach, where the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, the second information includes identification information for each set of inference parameters in the M sets of inference parameters, and a first indication information indicating availability.

[0027] In conjunction with the second aspect above, in one possible design approach, the identification information of the m-th set of inference parameters in the M sets of inference parameters is the arrangement position of the m-th set of inference parameters in the first inference parameter group, where m = 1, ..., M.

[0028] In conjunction with the second aspect above, in one possible design approach, the identification information of the m-th set of inference parameters in the M sets of inference parameters is the global identifier of the m-th set of inference parameters, where m = 1, ..., M.

[0029] In conjunction with the second aspect above, in one possible design approach, Y sets of inference parameters are carried in Y information cells, and the global identifier of the m-th set of inference parameters is the identifier of the information cell carrying the m-th set of inference parameters, where m = 1, ..., M.

[0030] In conjunction with the second aspect mentioned above, in one possible design approach, the second information also includes the identifier of the first inference parameter group.

[0031] In conjunction with the second aspect above, in one possible design approach, the identification information of the m-th set of inference parameters in the M sets of inference parameters includes the identifier of the first inference parameter group and the index of the m-th set of parameters. The index of the m-th set of parameters is determined based on at least one of the following: the identifier of the first inference parameter group, the global identifier of the m-th set of inference parameters, or the arrangement position of the m-th set of inference parameters in at least one inference parameter group, where m = 1, ..., M.

[0032] In conjunction with the second aspect above, in one possible design, where the second information indicates the availability of M sets of inference parameters out of Y sets of inference parameters, the second information includes an identifier of the first inference parameter group and a bit map. The bit map includes Y bits, each of the Y bits corresponding to one set of inference parameters out of the Y sets of inference parameters. The M sets of inference parameters are the inference parameters corresponding to the bits in the Y bits that are set to a first value.

[0033] In conjunction with the second aspect above, in one possible design, where the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, the method further includes: receiving third information indicating that N sets of inference parameters are unavailable out of Y sets of inference parameters, where N is a positive integer less than Y.

[0034] In conjunction with the second aspect mentioned above, in one possible design approach, the first information also includes the identifier of the first inference parameter group.

[0035] In conjunction with the second aspect above, in one possible design approach, the first information may also include one or more of the following: a global identifier for each set of inference parameters in the Y sets of inference parameters, or an index for the Y sets of inference parameters.

[0036] In conjunction with the second aspect above, in one possible design, the method is applied to an access network device, which includes a first centralized unit (CU) and a first distributed unit (DU). The method further includes: the first CU determining first information; or, the first DU determining the first information and the first DU sending the first information to the first CU.

[0037] Thirdly, a communication device is provided for implementing various methods. The communication device includes modules, units, or means corresponding to the implementation of the methods, which can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions.

[0038] In some possible designs, the communication device may include a processing module and a transceiver module. The processing module can be used to implement the processing functions in any of the above aspects and any possible implementations thereof. The transceiver module may include a receiving module and a transmitting module, respectively used to implement the receiving function and the transmitting function in any of the above aspects and any possible implementations thereof.

[0039] In some possible designs, the transceiver module can consist of transceiver circuits, transceivers, transceivers, or communication interfaces.

[0040] Fourthly, a communication device is provided, comprising: a processor and a memory; the memory being used to store computer instructions that, when executed by the processor, cause the communication device to perform the method described in either aspect.

[0041] Fifthly, a communication device is provided, comprising: a processor and a communication interface; the communication interface being used to communicate with a module outside the communication device; the processor being used to execute a computer program or instructions to cause the communication device to perform the method described in any one of these aspects.

[0042] A sixth aspect provides a communication device comprising: at least one processor; said processor being configured to execute a computer program or instructions stored in a memory to cause the communication device to perform the method described in any of the aspects. The memory may be coupled to the processor, or may be independent of the processor.

[0043] In a seventh aspect, a communication device (e.g., the communication device may be a chip or a chip system) is provided, the communication device including a processor for implementing the functions involved in any one of the first to second aspects.

[0044] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0045] In some possible designs, when the device is a chip system, it can be composed of chips or contain chips and other discrete components.

[0046] It is understood that the communication device provided in the third to seventh aspects may be the terminal in the first aspect, or a module or unit (e.g., a chip, chip system, or circuit) in the terminal that performs the methods / operations / steps / actions described in the first aspect, or a module or unit that can be used in conjunction with the terminal, or a logical node, logical module, or software that can realize all or part of the terminal's functions; or, the communication device may be the RAN node in the second aspect, or a module or unit (e.g., a chip, chip system, or circuit) in the RAN node that performs the methods / operations / steps / actions described in the second aspect, or a module or unit that can be used in conjunction with the RAN node, or a logical node, logical module, or software that can realize all or part of the RAN node's functions.

[0047] It is understandable that when the communication device provided by any of the third to seventh aspects is a chip, the sending action / function of the communication device can be understood as outputting information, and the receiving action / function of the communication device can be understood as inputting information.

[0048] Eighthly, a computer-readable storage medium is provided that stores a computer program or instructions that, when executed on a communication device, enable the communication device to perform the method described in any one of the first to second aspects.

[0049] A ninth aspect provides a computer program product containing instructions that, when run on a communication device, enables the communication device to perform the method described in any one of the first to second aspects.

[0050] A tenth aspect provides a communication system comprising a terminal and a RAN node. The terminal is configured to perform the methods described in the first aspect and any possible design thereof, and the RAN node is configured to perform the methods described in the second aspect and any possible design thereof.

[0051] The technical effects of any of the design methods in aspects three through ten can be found in the technical effects of different design methods in aspects one through two, and will not be repeated here. Attached Figure Description

[0052] Figure 1 is a schematic diagram of a wide beam and a narrow beam;

[0053] Figure 2 is a schematic diagram of a spatial beam prediction scenario;

[0054] Figure 3 is a schematic diagram of a time-domain beam prediction scenario;

[0055] Figure 4 is a schematic diagram of CSI feedback enhancement based on artificial intelligence;

[0056] Figure 5 is a schematic diagram of the configuration process of a terminal-side AI model;

[0057] Figure 6 is a schematic diagram of the configuration process for another terminal-side AI model;

[0058] Figure 7 is a schematic diagram of the architecture of a communication system provided in this application;

[0059] Figure 8 is a schematic diagram of an open RAN architecture (CU-DU separation architecture);

[0060] Figure 9 is a schematic diagram of another RIC architecture in an open RAN;

[0061] Figure 10 is a flowchart illustrating a communication method provided in this application;

[0062] Figures 11-12 are schematic diagrams showing the mapping of the inference parameters provided in this application in the signaling;

[0063] Figure 13 is a flowchart illustrating a communication method provided in this application;

[0064] Figure 14 is a flowchart illustrating a communication method provided in this application;

[0065] Figures 15-17 are schematic diagrams of the communication device provided in this application. Detailed Implementation

[0066] In the description of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0067] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0068] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0069] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0070] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process 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.

[0071] It is understood that in this application, "...when" and "if" both refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require a judgment action to be performed during implementation, nor do they imply any other limitations.

[0072] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0073] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0074] To facilitate understanding of the technical solutions of the embodiments of this application, a brief introduction to the relevant technologies of this application is given below.

[0075] I. Artificial intelligence (AI).

[0076] With the development of communication technology, current mobile networks support an increasing variety of services. These networks need to support diverse requirements such as ultra-high speed, ultra-low latency, ultra-high reliability, and massive connectivity, making network planning, configuration, and resource scheduling increasingly complex. Furthermore, the increasing use of communication spectrum by networks places higher demands on energy efficiency. These new requirements, scenarios, and characteristics present unprecedented challenges to network planning, operation, and efficient management. Relying on manual experience or simple algorithms for network planning, self-optimization of network configuration, resource scheduling, and energy conservation suffers from drawbacks such as high time consumption, high cost, and poor adaptability of self-optimization and scheduling algorithms, making it unsuitable for addressing these new challenges.

[0077] Introducing AI models (such as artificial intelligence and / or machine learning (AI / ML) models) into mobile networks can significantly improve the efficiency of network planning, configuration, resource scheduling, and energy conservation, thus achieving network intelligence. Artificial intelligence can simulate arbitrary nonlinear models, effectively adapting to real-world environments and approaching performance limits. Artificial intelligence and machine learning acquire massive amounts of data, using machine learning algorithms to train models and / or make decision inferences, outputting AI models and / or decision results (such as predictions of future business data volume over a certain period). To achieve network intelligence, it is necessary to research key technologies such as intelligent wireless network frameworks, the functions of AI modules / platforms, and protocol processes.

[0078] II. Channel State Information (CSI).

[0079] In the field of wireless communication, channel state information (CSI) refers to the known channel properties of a communication link. CSI describes how a signal propagates from the transmitter to the receiver and represents the combined effects of scattering, fading, and power attenuation with distance. This method is called channel estimation. CSI enables transmission to adapt to current channel conditions, which is crucial for achieving reliable communication at high data rates in multi-antenna systems. In practical implementation and application, access network equipment sends CSI reference signals to terminals for measurement. The terminals calculate the measured values ​​and report them to the access network equipment for CSI acquisition or beam management, or they may not report them but only use them to select the receiving beam.

[0080] III. Beam Management and Beam Selection.

[0081] With the advancement of wireless communication technology, communication systems face increasingly diverse service demands, placing higher requirements on system capacity and communication latency. To address these challenges, 5G (5th-generation mobile communication technology) introduces high-frequency bands (e.g., bands above 6 GHz). These high-frequency bands offer advantages in bandwidth and frequency compared to mid- and low-frequency bands (bands below 6 GHz), thus providing higher transmission rates and system capacity. However, the weaker penetration and stronger path fading of high-frequency signals limit their propagation distance and coverage. To address this issue, based on massive MIMO (Massively Multi-Analog Devices) technology, high-frequency communication systems can employ numerous antennas for beamforming, thereby achieving substantial beam gain to compensate for the limited propagation distance and coverage caused by the characteristics of high-frequency propagation.

[0082] Beam management is crucial for achieving beam gain. To achieve beam management, related technologies employ a layered scanning approach to reduce beam scanning overhead. This involves scanning a wide beam first, and then scanning a small portion of a narrow beam within the wide beam, thereby reducing overhead.

[0083] As can be understood, as shown in Figure 1, the wide-beam signal emitted by the RAN node (access network equipment) has a large coverage area, resembling a wide fan or ellipse. Its wide signal coverage allows the RAN node's signal to propagate over a large area, making it suitable for cell broadcast signal transmission. The narrow-beam signal emitted by the RAN node, on the other hand, has a more concentrated direction, with multiple beams radiating outwards in a narrow shape. Its signal energy is concentrated in a specific direction, allowing for more precise targeting of the target terminal.

[0084] Beam selection is typically accomplished through reference signals and corresponding beam measurements. Specifically, the reference signals mainly include the synchronization signal block (SSB) and the channel state information-reference signal (CSI-RS). The SSB is the cell broadcast signal, which includes the primary synchronization signal (PSS), the secondary synchronization signal (SSS), the physical broadcast channel (PBCH), and the demodulation reference signal (DMRS).

[0085] SSB (Special Signal Broadcast) is transmitted periodically according to cell configuration. Its functions include beam management, initial access, and time-frequency synchronization. Simply put, the SSB signal can be considered a wide-beam signal. Correspondingly, the CSI-RS signal is a user-level signal. The network side configures one or more CSI-RS resources for users based on actual conditions. Similarly, the CSI-RS signal can be used for beam management and channel quality measurement; it can be simply understood as a narrow-beam signal.

[0086] Traditional beam management systems perform a two-step beam scan during the service beam selection phase: The first phase scans the SSB (wide beam), during which the terminal measures and reports the reference signal received power (RSRP) of the SSB to the network. The second phase, based on the RSRP reported by the terminal, the network selects the SSB with the highest RSRP and configures CSI-RS resource scanning to scan the narrow beams covered by this SSB to determine the optimal beam. During the narrow beam scanning process configured by the network, the network sends transmit configuration indication (TCI) status information containing quasi-co-location (QCL) information to instruct the terminal to receive using a fixed wide beam. The terminal feeds back the measurement results to the network, which then determines the optimal beam for subsequent data transmission based on the measurement results. Each TCI status may include a reference signal resource identifier. The reference signal resource identifier can be at least one of the following: non-zero power (NZP) channel state information reference signal (CSI-RS) resource identifier (NZP-CSI-RS-ResourceId) or SSB index (SSB-Index).

[0087] IV. Application Scenarios of Artificial Intelligence

[0088] Application scenarios of artificial intelligence in the field of wireless communication can include: Application scenario 1, beam management based on artificial intelligence; Application scenario 2, mobility management enhancement based on artificial intelligence; Application scenario 3, positioning based on artificial intelligence; Application scenario 4, CSI feedback enhancement based on artificial intelligence.

[0089] The following sections will explain application scenarios 1 through 4.

[0090] Application Scenario 1: Beam Management Based on Artificial Intelligence

[0091] With the development of artificial intelligence (AI) technology, it has played a significant role in beam management, especially in reducing beam scanning overhead. Typically, the AI ​​model takes the received power of a wide beam or a sparsely scanned narrow beam measured by the terminal as input. The model infers and outputs a Top-k list of candidate best narrow beams (the RSRP value or ID of the output beam set). The network side then performs a scan based on the Top-k list to ultimately determine the optimal beam. AI models can usually be deployed on either the terminal or the network side. This application primarily focuses on the application of terminal-side models in serving beam selection scenarios. Beam management also includes beam recovery procedures, which will not be elaborated upon here.

[0092] Beam management can be applied to downlink transmit beam prediction based on terminal-side and network-side models. AI-based beam management is mainly applied in two aspects: firstly, spatial downlink transmit beam prediction of group A beams based on group B beam measurement results (BM-Case 1), hereinafter referred to as spatial beam prediction; and secondly, temporal downlink transmit beam prediction of group A beams based on historical measurement results of group B beams (BM-Case 2), hereinafter referred to as temporal beam prediction.

[0093] In addition, when performing beam prediction, on the one hand, the necessary signaling or mechanisms are specified to facilitate low-complexity mobility operations specifically for beam management use cases; on the other hand, enabling methods are determined to ensure consistency between training and inference on the terminal side under additional conditions on the network side.

[0094] In spatial beam prediction, as shown in Figure 2, the set of scanned beams (e.g., beams of a specific pattern scanned at a certain moment) (hereinafter referred to as set B) is determined from the codebook. After inputting the measurements of set B (usually RSRP values) into the AI ​​model, the measurements of the complete set of beams (hereinafter referred to as set A) can be obtained after inference and prediction by the AI ​​model. Then, based on the measurements of set A, the beam numbers corresponding to the top-K measurements are determined (the beam numbers corresponding to the top-K measurements can be called the indices of the top-K beams).

[0095] Under time-domain beam prediction, as shown in Figure 3(a), the terminal determines the input information of the AI ​​model within a sliding time window T1 (e.g., the measurement of set B between time (t-N+1) and time (t)). The terminal sends the input information to the network side (RAN node). The network side inputs the input information into the AI ​​model. After the AI ​​model infers and predicts, it obtains the preset result of the future time window T2 (including the measurement of set A in each time slot in the time window T2 determined by the regression model, the measurement of set A for each time slot, and the index of the top-K beams determined by the classification model). Finally, the network side reports the index of the top-K beams corresponding to each time slot to the terminal device.

[0096] Alternatively, as shown in Figure 3(b), the terminal determines the input information of the AI ​​model within a sliding time window T1 (e.g., the measurement of set B between time (t-N+1) and time (t), inputs the input information into the AI ​​model, and after the AI ​​model infers and predicts, obtains the preset result of the time window T2 for the future time (including the measurement of set A in each time slot in the time window T2 determined by the regression model, the measurement of set A for each time slot, and the index of the top-K beams determined by the classification model). Finally, the terminal reports the index of the top-K beams corresponding to each time slot to the network side.

[0097] Application Scenario 2: AI-based Enhanced Mobility Management

[0098] During mobility management, access network equipment configures terminals to report measurements and makes handover decisions based on the reported results. After introducing AI models, access network equipment can make predictions based on the limited measurement results reported by terminals (e.g., configuring a small number of measurement beams, or reducing the number of beams and cell measurements by the terminal) and select the optimal cell for handover decisions.

[0099] Application Scenario 3: AI-based positioning:

[0100] Currently, AI-based positioning scenarios mainly include five specific application scenarios in two types: Type 1, direct positioning based on AI models, and Type 2, assisted positioning based on AI models.

[0101] Type 1: Direct localization based on AI models:

[0102] Use Case 1: Models applied to the terminal side, directly based on AI models for localization. For example, the terminal performs signal measurements, and based on the measurement results, the AI ​​model directly predicts the localization result.

[0103] Use Case 2: Terminal-Assisted Location Management Function (LMF) positioning. For example, LMF uses AI models to perform positioning based on terminal-assisted information. Specifically, LMF is responsible for receiving and processing positioning requests or positioning-related data requests, selecting a positioning method based on the request, and measuring the positioning results.

[0104] Use Case 3: LMF positioning assisted by access network equipment. For example, LMF positioning is performed using an AI model based on auxiliary information from the access network equipment side.

[0105] Type 2, AI model-based assisted localization:

[0106] Use Case 4: AI Model-Assisted Localization on the Terminal Side. For example, the terminal side makes predictions based on its measurement results and sends the predictions to the LMF to assist it in localization.

[0107] Use Case 5: AI Model-Assisted LMF Localization on the Access Network Device Side. For example, the access network device makes a prediction based on the measurement results and sends the prediction results to the LMF to assist the LMF in localization.

[0108] Application Scenario 4: AI-based CSI Feedback Enhancement

[0109] Currently, communication systems use codebooks as the basic tool for CSI feedback, and multiple codebook schemes are defined for different feedback levels, such as Type I codebooks and Type II codebooks. However, the above codebooks are all designed for uniformly arranged antenna arrays and are not optimized for special antennas (such as three-dimensional (3D) antennas), resulting in performance limitations.

[0110] Artificial intelligence-based CSI feedback enhancement can overcome the aforementioned bottlenecks and achieve better feedback performance through optimization for specific channel environments. The basic principle of AI-based CSI feedback enhancement is to treat the high-dimensional channel information feedback task as an end-to-end CSI image compression and reconstruction task. As shown in Figure 4, firstly, the complete channel information is input to the encoder. The encoder (usually the terminal side) uses an encoder to extract features from the complete channel information and compress it into a bitstream that meets the feedback requirements. This bitstream is then fed back to the decoder (usually the access network equipment side) via a feedback link. The decoder uses a decoder to decompress the bitstream and reconstruct its features, ultimately outputting the complete channel information. The encoder and decoder are jointly optimized during end-to-end training to obtain the best CSI reconstruction performance. In actual deployment, the encoder and decoder can be paired according to the training process; that is, the compressed CSI output by a certain encoder needs to be reconstructed using the corresponding decoder.

[0111] Furthermore, AI-based channel state information (CSI) prediction can also be based on existing CSIs to obtain unknown time-frequency resource CSIs without incurring new air interface resource overhead. While CSIs at different times / spaces are not entirely identical, they exhibit a certain degree of correlation, making CSI prediction possible. Traditional CSI prediction schemes are limited by prediction accuracy when handling complex data, hindering their practical application. AI-based CSI prediction is expected to significantly improve prediction accuracy, thus potentially enabling the acquisition of unknown CSIs with low overhead in real-world systems.

[0112] Based on data correlation categories, AI-based CSI prediction can be divided into four types: 1) The first type considers temporal correlation, i.e., predicting the CSI of the next moment or the next time period based on the CSI of the previous period. This is mainly applied in time-varying channels or high-speed mobile scenarios. 2) The second type considers frequency correlation, such as predicting and reconstructing downlink CSI based on the uplink CSI of frequency division duplexing (FDD). 3) The third type considers spatial correlation prediction problems. 4) The fourth type considers channel correlation prediction problems between adjacent users.

[0113] Currently, a two-stage reporting process is being discussed to configure the terminal-side model. As shown in Figure 5, steps 1-6 illustrate the specific implementation process of configuring the AI / ML functions or models on the terminal side of the network. Steps 1-2 complete the first stage of reporting, and steps 3-4 complete the second stage of reporting.

[0114] Step 1: The network sends a capability query message (UECapabilityEnqiry) to the terminal.

[0115] Step 2: After receiving the query, the terminal reports the terminal capability information (UECapabilityInformation) to the network. The terminal capability information includes the AI ​​capabilities that the terminal can support. For example, the terminal indicates which AI / ML functions or models it supports in which scenarios, such as indicating that it supports AI / ML functions or models in beam management scenarios, or indicating that it supports AI / ML functions or models in positioning scenarios; or, the terminal indicates that it supports AI / ML functions without indicating the specific scenario.

[0116] Step 3: Based on the AI / ML functions or models supported by the terminal, the network sends a radio resource control (RRC) connection reconfiguration message to the terminal according to the network's needs. The RRC connection reconfiguration message includes reported configuration information, which is used to instruct the terminal to report available AI / ML functions or models.

[0117] In step 3, the network can provide the terminal with two configurations: one is one or more Channel State Information Report Configurations (CSI-ReportConfig) for inference configuration, and the relevant identifiers can be used as working assumption configurations within the CSI framework. This is mainly used by the terminal to feed back channel state information to the network, helping the network optimize signal transmission.

[0118] Another type is a set or more sets of inference parameters used solely for applicability reporting (rather than inference). These inference parameters help the terminal determine whether the AI / ML functions or models on the terminal side are suitable for the specific inference scenario indicated by the inference parameters. For example, inference parameters include the number of beams configured in SETA and SETB in beam management scenarios (e.g., SETA=16, SETB=8); the number of time slots to be predicted and measured in beam management time-domain prediction scenarios; inference parameters required in other possible scenarios; and additional network-side configuration conditions (associated ID), etc. These inference parameters can be added as new fields to existing information elements (IEs) in the communication protocol. Existing information elements can be CSI-ReportConfig IEs or otherConfig IEs; alternatively, a redefined information element can be used, such as an information element with a structure similar to CSI-ReportConfig, where the redefined information element may only include inference parameters. Information elements with a structure similar to CSI-ReportConfig and CSI-ReportConfig information elements both belong to CSI-MeasConfig. This application does not impose any restrictions on the information elements or methods used to carry inference parameters.

[0119] Step 4: Based on the network configuration, the terminal sends an Applicability Report, which indicates the available AI / ML functions or models.

[0120] In step 4, the terminal can report the applicability of one or more CSI-ReportConfigs and one or more sets of inference parameters to the network, so that the network can understand whether the AI / ML function or model can be used normally on the terminal side.

[0121] For example, in related technologies, a specific implementation of a terminal reporting the applicability of one or more sets of inference parameters to the network may include: the terminal can report the availability of one or more sets of inference parameters sent by the network in step 3 to indicate whether the AI / ML function or model on the terminal side supports the inference parameters sent by the network. If the availability of one or more sets of inference parameters is available, it means that the AI / ML function or model on the terminal side supports the inference parameters sent by the network.

[0122] Step 5: The network performs RRC reconfiguration for inference based on the terminal's suitability report.

[0123] Step 6: Activation / Deactivation / Inference / Monitoring.

[0124] For example, the network can activate or deactivate certain functions, perform inference-related processing, and monitor the status of the terminal and the communication process to ensure that the entire communication process is stable and efficient.

[0125] As can be seen from steps 3 and 4 above, the network can currently send one or more sets of inference parameters to the terminal. Correspondingly, the terminal can receive one or more sets of inference parameters from the network side and determine whether the terminal's model and / or function can use the one or more sets of inference parameters, that is, whether the inference parameters can be used in the terminal's model and / or function, or whether the inference parameters match the terminal's model and / or function. The terminal can report the availability of each set of inference parameters to indicate whether the terminal's model and / or function supports the set of inference parameters.

[0126] However, there is currently no clear definition for the division of inference parameter groups. Therefore, a set of inference parameters may include multiple sets of inference parameters. If there are unavailable inference parameters among these sets, and the terminal reports the availability of the inference parameters in that set at the group level, the results will be inaccurate. For example, some inference parameters in a set of inference parameters may be unavailable, but the entire set may be reported as available. In this case, the network side may configure an unreasonable inference scheme based on the unavailable inference parameters within the set, resulting in the terminal device's model and / or functions failing to activate. For instance, as shown in Figure 6, the RRC connection reconfiguration message sent by the network in step 3 includes inference parameter group 1. Inference parameter group 1 includes two sets of inference parameters, where the first set is available and the second set is unavailable. In this case, when the terminal reports, it reports the entire inference parameter group 1 as available at the group level. The network side may configure an unreasonable inference scheme based on the unavailable second set of inference parameters within inference parameter group 1, resulting in the terminal device's model and / or functions failing to activate.

[0127] As can be seen from the above, a set of inference parameters may include multiple sets of inference parameters. How the terminal can report the availability of inference parameters to avoid the problem that the terminal device's model and / or functions cannot be activated due to unreasonable configuration of the inference scheme in subsequent steps is a problem that needs to be solved.

[0128] In view of this, this application provides a communication method in which a terminal receives first information from a RAN node, wherein the first information includes at least one inference parameter group. If the first inference parameter group includes Y sets of inference parameters, where Y is a positive integer greater than 1, and the first inference parameter group is any one of the at least one inference parameter group. The terminal can send second information to the RAN node to indicate that all Y sets of inference parameters in the first inference parameter group are available, or to indicate that M sets of inference parameters in the first inference parameter group are available, where M is a positive integer less than Y. This allows availability to be reported at the granularity of each set of inference parameters. Compared to reporting availability at the group level, this improves the accuracy of inference parameter availability reporting by the terminal, enabling the network to know the availability of each set of inference parameters. This avoids problems such as using unavailable inference parameters to configure unreasonable inference schemes, leading to model inactivation failures, and thus improves the accuracy of model application.

[0129] The technical solutions of this application embodiment can be used in various communication systems, including third-generation partnership project (3GPP) communication systems, such as fourth-generation (4G) systems like long-term evolution (LTE), 5G systems like new radio (NR), hybrid LTE and 5G networks, non-terrestrial networks (NTN), or other future communication systems. The communication system can also be a non-3GPP communication system; there is no limitation on this.

[0130] The communication systems described above are merely illustrative examples, and are not limited to those described herein. The communication systems provided in this application do not impose any limitations on the solutions described herein. This will be explained uniformly here and will not be repeated below.

[0131] Figure 7 illustrates a possible, non-limiting system diagram. As shown in Figure 7, the communication system includes a radio access network (RAN) 700 and a core network (CN) 800. RAN 700 includes at least one RAN node (710a and 710b in Figure 7, collectively referred to as 710) and at least one terminal (720a-720j in Figure 7, collectively referred to as 720). RAN 700 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment (not shown in Figure 7). Terminal 720 is wirelessly connected to RAN node 710. RAN node 710 is wirelessly or wired connected to core network 800. The core network equipment in core network 800 and RAN node 710 in RAN 700 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0132] RAN 700 can be a 3GPP-related cellular system, such as 4G or 5G mobile communication systems, or future-oriented evolution systems (such as future communication networks). RAN 700 can also be an open access network (open RAN, O-RAN, or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 700 can also be a communication system that integrates two or more of the above systems.

[0133] RAN node 710, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and assists terminals in achieving wireless access. Multiple RAN nodes 710 in the communication system can be of the same type or different types. In some scenarios, the roles of RAN node 710 and terminal 720 are relative. For example, network element 720i in Figure 7 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 720j accessing RAN 700 through network element 720i, network element 720i is a base station; however, for base station 710a, network element 720i is a terminal. RAN node 710 and terminal 720 are sometimes both referred to as communication devices. For example, network elements 710a and 710b in Figure 7 can be understood as communication devices with base station functions, and network elements 720a-720j can be understood as communication devices with terminal functions.

[0134] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a future communication network, a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node can be a macro base station (as shown in Figure 7, 710a), a micro base station or indoor station (as shown in Figure 7, 710b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the RAN node functions.

[0135] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0136] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0137] Figure 8 is a schematic diagram illustrating an open RAN architecture (CU-DU separation architecture), which may include other components besides those shown in Figure 8.

[0138] In a communication system, network elements are connected via interfaces (e.g., NG, Xn) or air interfaces (Uu). These network element nodes, such as core network equipment, RAN nodes, and one or more devices in the terminal, may also contain one or more AI modules (for clarity, only one is shown in Figure 8). A RAN node can be a single RAN node or can include multiple RAN nodes, for example, CU and DU, where CU and DU are connected via an F1 interface. CU and / or DU may also contain one or more AI modules. Optionally, a CU can be further divided into CU-CP and CU-UP, where CU-CP is connected to DU via an F1-C interface, and CU-UP is connected to DU via an F1-U interface. CU-CP and / or CU-UP contain one or more AI models. AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, AI modules can implement different functions. An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0139] Figure 9 is a schematic diagram of another RAN intelligent controller (RIC) architecture in an open RAN.

[0140] The RIC architecture communication system includes RICs, which are categorized into near-real-time (NRT) RICs and non-real-time (Non-RT) RICs. Near-real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or radio units (RUs)) and / or terminals. This information can be used as training data or inference data. Optionally, NRT RICs can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, a NRT RIC delivers an inference result to a DU, which then forwards it to an RU.

[0141] Non-real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers the inference result to a DU, which then forwards it to an RU. Near-real-time and non-real-time RICs can also be configured as separate network elements. Optionally, near-real-time and non-real-time RICs can also be part of other devices; for example, a near-real-time RIC can be located in a RAN node (e.g., in a CU or DU), while a non-real-time RIC can be located in operations, administration, and maintenance (OAM) systems, cloud servers, core network devices, or other network devices.

[0142] A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be handheld terminals, in-vehicle terminals, mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, etc. The embodiments of this application do not limit the device form of the terminal.

[0143] The core network 800 can be an evolved packet core (EPC), a 5G core network (5GC), or a possible future core network form. The embodiments of this application do not limit the core network.

[0144] In addition, this application can be applied to the following application scenarios 1-4 (Application Scenario 1: AI-based beam management; Application Scenario 2: AI-based mobility management enhancement; Application Scenario 3: AI-based positioning; Application Scenario 4: AI-based CSI feedback enhancement). In different application scenarios, terminals, RAN nodes, or core network elements can possess AI / ML capabilities and be configured with AI / ML models or functions for inference, providing radio-related data analysis and policy feedback to RAN nodes. The AI / ML models or functions can be trained internally by the terminal, RAN node, or core network element, or they can be transmitted to the terminal, RAN node, or core network element from other nodes. This application does not restrict the way the terminal, RAN node, or core network element is configured with AI / ML models or functions.

[0145] It should be noted that the communication system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0146] The following description, using the communication system shown in Figure 7 as an example and taking the interaction between the terminal and the RAN node as an example, illustrates the data transmission method based on quality of service provided in this application. It should be noted that in the following embodiments of this application, the message names, parameter names, or information names between the terminal and the RAN node are merely examples; other names may exist in other embodiments, and the method provided in this application does not specifically limit these.

[0147] It is understood that in the embodiments of this application, the terminal or RAN node may execute some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the various steps may be executed in different orders as presented in the embodiments of this application, and it is not necessarily necessary to execute all the operations in the embodiments of this application.

[0148] It is understood that this application uses RAN nodes and terminals as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction. For example, the method executed by the RAN node in this application can also be executed by a module applied to the RAN node (e.g., a chip, chip system, or processor), or by a logical node, logical module, or software that can implement all or part of the RAN node's functions; similarly, the method executed by the terminal in this application can also be executed by a module applied to the terminal (e.g., a chip, chip system, or processor), or by a logical node, logical module, or software that can implement all or part of the terminal's functions.

[0149] Furthermore, in this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "RAN node sending information" can be understood as the RAN node sending information to another device (such as a terminal), or it can be understood as logical module 1 (such as a processing module) in the RAN node sending information to logical module 2 (such as a transceiver module) in the RAN node.

[0150] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as one logical module within a device receiving information from another logical module. For example, "terminal receiving information" can be understood as the terminal receiving information from another device (such as a RAN node), or it can be understood as logical module 1 (such as a processing module) in the terminal receiving information from logical module 2 (such as a transceiver module) in the terminal.

[0151] In this application, phrases such as "sending information to... (e.g., a terminal)" or related illustrations in the accompanying drawings can be understood as indicating that the destination of the information is the terminal. This can include sending information directly or indirectly to the terminal. Similarly, phrases such as "receiving information from... (e.g., a RAN node)," "receiving information from... (e.g., a RAN node)," or "receiving information sent by (e.g., a RAN node)," or related illustrations in the accompanying drawings, can be understood as indicating that the source of the information is the RAN node. This can include receiving information directly or indirectly from the RAN node. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0152] Referring to Figure 10, which is a flowchart of a communication method provided in an embodiment of this application, the method may include the following steps:

[0153] S1001, the RAN node sends the first information to the terminal. Correspondingly, the terminal receives the first information from the RAN node.

[0154] The first information includes at least one set of inference parameters, and each set of inference parameters may include at least one set of inference parameters. For example, the first set of inference parameters includes Y sets of inference parameters, where Y is a positive integer greater than 1, and the first set of inference parameters is any one of the at least one set of inference parameters.

[0155] Optionally, a set of inference parameters can be carried in a single information element. This information element can be an existing information element in the communication protocol or a redefined information element, such as the CSI-ReportConfigPartial information element under CSI-MeasConfig or the subsetParameter information element under otherConfig. This application does not impose any restrictions on this. For other information elements and methods of carrying inference parameters, please refer to the embodiment shown in step 3 of Figure 5 above, which will not be repeated here.

[0156] For example, taking the first information as including inference parameter group 1 and inference parameter group 2, where inference parameter group 1 includes 3 sets of inference parameters (set 1 to set 3), and inference parameter group 2 includes 2 sets of inference parameters (set 4 to set 5), as shown in Figure 11(a), the 5 sets of inference parameters can be carried in the CSI-ReportConfigPartial information element under CSI-MeasConfig. Specifically, the first set of inference parameters is in CSI-ReportConfigPartial0, the second set is in CSI-ReportConfigPartial1, the third set is in CSI-ReportConfigPartial2, the fourth set is in CSI-ReportConfigPartial3, and the fifth set is in CSI-ReportConfigPartial4. Alternatively, as shown in Figure 11(b), the five sets of inference parameters can also be carried in the subsetParameter information element under otherConfig, where the first set of inference parameters is in subsetParameter0, the second set of inference parameters is in subsetParameter1, the third set of inference parameters is in subsetParameter2, the fourth set of inference parameters is in subsetParameter3, and the fifth set of inference parameters is in subsetParameter4.

[0157] In one possible implementation, where the RAN node (also known as an access network device) includes a first centralized unit (CU) and a first distributed unit (DU), prior to S1001, the communication method provided in this application further includes: the first CU determining first information. Then, the RAN node sends the first information to the terminal, including: the first CU encapsulating the first information into an RRC message, the first CU sending the encapsulated RRC message to the first DU, and the first DU sending the first information to the terminal.

[0158] Alternatively, prior to S1001, the communication method provided in this application further includes: a first DU determining first information, and the first DU (via the F1 interface) sending the first information to a first CU. Then, the RAN node sends the first information to the terminal, including: the first CU encapsulating the first information into an RRC message, the first CU sending the encapsulated RRC message to the first DU, and the first DU sending the first information to the terminal.

[0159] S1002, The terminal sends the second information to the RAN node. Correspondingly, the RAN node receives the second information from the terminal.

[0160] Specifically, for the first set of inference parameters, the second information indicates that all Y sets of inference parameters are available, or the second information indicates that M sets of inference parameters are available from the Y sets of inference parameters, where M is a positive integer less than Y. If the second information indicates that M sets of inference parameters are available from the Y sets of inference parameters, the second information may implicitly indicate that the remaining YM sets of inference parameters (excluding the M sets of inference parameters) are unavailable.

[0161] In one possible implementation, after receiving the first information, the terminal determines whether its model / function (e.g., an AI model) supports the y-th set of inference parameters in the first inference parameter set. For example, taking the application of the y-th set of inference parameters in a beam management scenario, the y-th set of inference parameters may include parameters such as SETA, SETB, additional network conditions, and reported content. The terminal determines whether its model / function can infer the measurement quantity (e.g., RSRP value) of each beam in SETA from the measurement quantity (e.g., RSRP value) of each beam in SETB, whether its AI model is trained based on additional network conditions, and whether the format of the reported content (e.g., the indices of the top-K beams determined based on SETA) conforms to a preset specification. If it is determined that the terminal's AI model can infer SETA from SETB, is trained based on additional network conditions, and the format of the reported content conforms to the preset specification, then the terminal can confirm that its model / function supports the y-th set of inference parameters. Furthermore, after determining whether the terminal-side model / function supports each set of inference parameters in at least one inference parameter group, the terminal indicates the available inference parameter group, or one or more sets of inference parameters, to the RAN node via the second information. In other words, the availability of a certain set of inference parameters can be understood as the terminal supporting that set of inference parameters. Terminal support for a set of inference parameters can be understood as the inference parameters being usable in a specific AI model of the terminal, or matching a specific AI model of the terminal.

[0162] In one possible implementation, when the RAN node (also known as the access network device) includes a first CU and a first DU, the terminal sends second information to the RAN node, including: the terminal sending second information to the first DU, and the first DU sending second information to the first CU.

[0163] In the above technical solution, the terminal receives first information from the RAN node, wherein the first information includes at least one inference parameter group. If the first inference parameter group includes Y sets of inference parameters, Y is a positive integer greater than 1, and the first inference parameter group is any one of the at least one inference parameter group. The terminal can send second information to the RAN node to indicate that all Y sets of inference parameters in the first inference parameter group are available, or to indicate that M sets of inference parameters in the first inference parameter group are available, where M is a positive integer less than Y. This means that availability can be reported at the granularity of each set of inference parameters. Compared to reporting availability at the group level, this improves the accuracy of inference parameter availability reporting by the terminal, allowing the network to know the availability of each set of inference parameters. This avoids problems such as using unavailable inference parameters to configure unreasonable inference schemes, leading to model activation failures, and thus improves the accuracy of model application.

[0164] Optionally, if the second information indicates that M sets of inference parameters are available in the Y sets of inference parameters, the communication method of this application may further include S1003.

[0165] S1003, the terminal sends third information to the RAN node. Correspondingly, the RAN node receives the third information from the terminal.

[0166] The third piece of information indicates that N sets of inference parameters are unavailable out of the Y sets of inference parameters, where N is a positive integer less than Y.

[0167] Optionally, the third information includes the identification information of each set of inference parameters in the N sets of inference parameters and the second indication information, whereby the second indication information indicates that the parameter is unavailable. The identification information of the inference parameters is specifically described in S1002 for the identification information of the m-th set of inference parameters, and will not be repeated here.

[0168] Optionally, the second indication information can be a 1-bit information, such as 1 or 0, where 1 indicates unavailable and 0 indicates available; or 0 indicates unavailable and 1 indicates available. The second indication information can also be "false", where "false" indicates unavailable. The second indication can also be "unavailable". This application does not limit the form of the second indication information.

[0169] In one possible implementation, when the RAN node (also known as the access network device) includes a first CU and a first DU, the terminal sends third information to the RAN node, including: the terminal sending third information to the first DU, and the first DU sending third information to the first CU.

[0170] In the above technical solution, the terminal can indicate to the network side, through a display instruction, that N sets of inference parameters out of Y sets of inference parameters are unavailable.

[0171] The following is an explanation of the first piece of information.

[0172] In some embodiments, the first information further includes an identifier for a first inference parameter group. That is, the first information includes an identifier for each inference parameter group in at least one inference parameter group.

[0173] Optionally, each set of inference parameters corresponds to an identifier (set ID) for an inference parameter group. An identifier for one inference parameter group can correspond to multiple sets of inference parameters, and multiple sets of inference parameters under the same identifier are defined as one inference parameter group. For example, as shown in Figure 12(a), the first information includes inference parameter group 1 and inference parameter group 2. Inference parameter group 1 includes 3 sets of inference parameters (set 1 to set 3), and inference parameter group 2 includes 2 sets of inference parameters (set 4 to set 5). Furthermore, set 1 to set 3 of inference parameters correspond to the identifier of inference parameter group 1, and set 4 to set 5 of inference parameters correspond to the identifier of inference parameter group 2.

[0174] Furthermore, in some other embodiments, the first information also includes one or more of the following: a global identifier for each set of inference parameters in the Y sets of inference parameters, or an index for the Y sets of inference parameters.

[0175] For example, the first information includes at least one inference parameter group, an identifier for at least one inference parameter group, and a global identifier for each set of inference parameters within each inference parameter group. For instance, as shown in Figure 12(b), the first information includes inference parameter group 1 and inference parameter group 2. Inference parameter group 1 includes 3 sets of inference parameters (set 1 to set 3), and inference parameter group 2 includes 2 sets of inference parameters (set 4 to set 5). Set 1 corresponds to global identifier 1, set 2 corresponds to global identifier 2, set 3 corresponds to global identifier 3, set 4 corresponds to global identifier 4, and set 5 corresponds to global identifier 5. Furthermore, sets 1 to 3 correspond to the identifier of inference parameter group 1, and sets 4 to 5 correspond to the identifier of inference parameter group 2.

[0176] Alternatively, the first information may include at least one inference parameter group, an identifier for at least one inference parameter group, and an index for each set of inference parameters within each inference parameter group. For example, as shown in Figure 12(c), the first information includes inference parameter group 1 and inference parameter group 2. Inference parameter group 1 includes 3 sets of inference parameters (set 1 to set 3), and inference parameter group 2 includes 2 sets of inference parameters (set 4 to set 5). Set 1 corresponds to index 1, set 2 corresponds to index 2, set 3 corresponds to index 3, set 4 corresponds to index 1, and set 5 corresponds to index 2. Furthermore, sets 1 to 3 correspond to the identifier of inference parameter group 1, and sets 4 to 5 correspond to the identifier of inference parameter group 2.

[0177] Alternatively, the first information may include at least one inference parameter group, an identifier for at least one inference parameter group, a global identifier for each set of inference parameters within each inference parameter group, and an index for each set of inference parameters within each inference parameter group. For example, as shown in Figure 12(d), the first information includes inference parameter group 1 and inference parameter group 2. Inference parameter group 1 includes 3 sets of inference parameters (set 1 to set 3), and inference parameter group 2 includes 2 sets of inference parameters (set 4 to set 5). Set 1 of inference parameters corresponds to global identifier 1, and global identifier 1 corresponds to index 1; set 2 of inference parameters corresponds to global identifier 2, and global identifier 2 corresponds to index 2; set 3 of inference parameters corresponds to global identifier 3, and global identifier 3 corresponds to index 3; set 4 of inference parameters corresponds to global identifier 4, and global identifier 4 corresponds to index 1; set 5 of inference parameters corresponds to global identifier 5, and global identifier 5 corresponds to index 2. Furthermore, sets 1 to 3 of inference parameters correspond to the identifier of inference parameter group 1, and sets 4 to 5 of inference parameters correspond to the identifier of inference parameter group 2.

[0178] One possible implementation is that different sets of inference parameters have different global identifiers. The global identifier of the y-th inference parameter in the Y sets of inference parameters can be the identifier of the cell carrying that set of inference parameters, where y = 1, ..., Y. For example, if the y-th inference parameter is carried in the first cell, and since a cell typically carries one set of inference parameters, the identifier of the first cell can be used as the global identifier of the y-th inference parameter. Alternatively, the global identifier of the y-th inference parameter in the Y sets of inference parameters can also be a unique identifier for the y-th inference parameter. For example, a unique identifier for the y-th inference parameter can be pre-set, and this unique identifier differs from the unique identifiers of other inference parameters in at least one inference parameter group. In this case, the unique identifier of the y-th inference parameter can be used as the global identifier for the y-th inference parameter.

[0179] As one possible implementation, different sets of inference parameters within the same group may have different indices, while different sets of inference parameters within different groups may have the same index. For example, as shown in Figure 12(c) or (d), the indices of the three sets of inference parameters in inference parameter group 1 are different; the indices of the two sets of inference parameters in inference parameter group 2 are different; the index of the first set of inference parameters in inference parameter group 1 and the index of the fourth set of inference parameters in inference parameter group 2 are the same, both being index 1. The index of the y-th set of inference parameters in Y sets of inference parameters can be determined based on the identifier of the first inference parameter group, the global identifier of the y-th set of inference parameters, or the arrangement position of the y-th set of inference parameters in at least one inference parameter group, where y = 1, ..., Y.

[0180] In one example, when the index of the y-th inference parameter in Y sets of inference parameters is determined based on the identifier of the first inference parameter group and the global identifier of the y-th inference parameter, the RAN node can map the global identifier of the Y sets of inference parameters corresponding to the identifier of the first inference parameter group to the index of the Y sets of inference parameters based on the identifier of the first inference parameter group. For example, taking the first information as including inference parameter group 1 and inference parameter group 2 (the first inference parameter group is either one of them), where inference parameter group 1 includes 3 sets of inference parameters (sets 1 to 3), and inference parameter group 2 includes 2 sets of inference parameters (sets 4 to 5). The RAN node can determine that the first to third sets of inference parameters belong to inference parameter group 1 based on the identifier of inference parameter group 1. Then, it maps the global identifier of the first set of inference parameters to index 1, the global identifier of the second set of inference parameters to index 2, and the global identifier of the third set of inference parameters to index 3. Similarly, the RAN node can determine that the fourth to fifth sets of inference parameters belong to inference parameter group 2 based on the identifier of inference parameter group 2. Then, it maps the global identifier of the fourth set of inference parameters to index 1 and the global identifier of the fifth set of inference parameters to index 2.

[0181] Alternatively, the global identifier of the first set of inference parameters can be mapped to index 0, the global identifier of the second set of inference parameters can be mapped to index 1, and the global identifier of the third set of inference parameters can be mapped to index 2. Similarly, the RAN node can determine that the fourth to fifth sets of inference parameters belong to inference parameter group 2 based on the identifier of inference parameter group 2, and then map the global identifier of the fourth set of inference parameters to index 0 and the global identifier of the fifth set of inference parameters to index 1.

[0182] In another example, when the index of the y-th inference parameter in Y sets of inference parameters is determined based on the identifier of the first inference parameter group and the position of the y-th inference parameter in at least one inference parameter group, the RAN node can map the Y sets of inference parameters corresponding to the identifier of the first inference parameter group to the index of the Y sets of inference parameters according to their position in at least one inference parameter group. For example, assuming the first information includes inference parameter group 1 and inference parameter group 2 (the first inference parameter group being either one), and inference parameter group 1 includes 3 sets of inference parameters (sets 1 to 3), and inference parameter group 2 includes 2 sets of inference parameters (sets 4 to 5), the RAN node can determine that sets 1 to 3 belong to inference parameter group 1 based on the identifier of inference parameter group 1. Furthermore, the RAN node can determine that the position of the first set of inference parameters in inference parameter group 1 within at least one inference parameter group (i.e., 5 sets of inference parameters) is the first position. Therefore, the RAN node can determine the index of the first set of inference parameters as index 1. Similarly, the RAN node can determine that the fourth to fifth sets of inference parameters belong to the inference parameter group 2 based on the identifier of the inference parameter group 2. Furthermore, the RAN node can determine that the fourth set of inference parameters in the inference parameter group 2 is the fourth position in at least one inference parameter group (i.e., 5 sets of inference parameters). Then, the RAN node can determine the index of the fourth set of inference parameters as index 1.

[0183] Furthermore, in some other embodiments, the first information also includes the total number of sets of inference parameters in each of at least one inference parameter group. For example, the first information includes at least one inference parameter group, an identifier of at least one inference parameter group, a global identifier for each set of inference parameters in each inference parameter group, and the total number of sets of inference parameters in each inference parameter group; or, the first information includes at least one inference parameter group, an identifier of at least one inference parameter group, an index for each set of inference parameters in each inference parameter group, and the total number of sets of inference parameters in each inference parameter group; or, the first information includes at least one inference parameter group, an identifier of at least one inference parameter group, a global identifier for each set of inference parameters in each inference parameter group, an index for each set of inference parameters in each inference parameter group, and the total number of sets of inference parameters in each inference parameter group.

[0184] The following is an explanation of the second piece of information.

[0185] In some embodiments, when the second information indicates that all Y sets of inference parameters are available, the second information includes the identifier of the first inference parameter group and first indication information, the first indication information indicating availability. For example, referring to Figure 12(a), as shown in Figure 13, if both sets of inference parameters in inference parameter group 2 are available, then the second information may include the identifier of inference parameter group 2 and the first indication information.

[0186] Optionally, the first indication information can be a 1-bit information, such as 1 or 0, where 1 indicates availability and 0 indicates unavailability; or 0 indicates availability and 1 indicates unavailability. The first indication information can also be "true", where "true" indicates availability; the first indication can also be "available". This application does not limit the form of the first indication information.

[0187] In other embodiments, when the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, the second information includes identification information for each set of inference parameters in the M sets of inference parameters and first indication information, the first indication information indicating availability. For example, as shown in FIG13, if the first set of inference parameters in inference parameter group 1 is unavailable, but the second and third sets of inference parameters are available, then the second information may include identification information for the second and third sets of inference parameters and the first indication information.

[0188] The following examples, from Example 1 to Example 3, illustrate the identification information of the m-th set of inference parameters in the M sets of inference parameters, where m = 1, ..., M.

[0189] Example 1: The identification information of the m-th set of inference parameters in M ​​sets of inference parameters is the arrangement position of the m-th set of inference parameters in at least one inference parameter group.

[0190] For example, referring to Figure 12(a), consider the case where the first set of inference parameters corresponding to inference parameter group 1 is unavailable, while the second and third sets of inference parameters are available. In this case, the m-th set of inference parameters is the second and third sets of inference parameters in inference parameter group 1. As shown in Figure 12(a), the RAN node has sent at least one inference parameter group, and at least one inference parameter group (i.e., two inference parameter groups) includes a total of 5 sets of inference parameters. Therefore, the identifier of the second set of inference parameters can be its position in the 5 sets of inference parameters, i.e., 2; the identifier of the third set of inference parameters can be its position in the 5 sets of inference parameters, i.e., 3. For example, consider the case where the fourth set of inference parameters corresponding to inference parameter group 2 is unavailable, while the fifth set of inference parameters is available. In this case, the m-th set of inference parameters is the fifth set of inference parameters corresponding to inference parameter group 2. Therefore, the identifier of the fifth set of inference parameters can be its position in the 5 sets of inference parameters, i.e., 5.

[0191] Example 2: The identification information of the m-th set of inference parameters in M ​​sets of inference parameters is the global identifier of the m-th set of inference parameters.

[0192] For example, referring to Figure 12(b), consider the case where the first set of inference parameters corresponding to inference parameter group 1 is unavailable, while the second and third sets of inference parameters are available. In this case, the m-th set of inference parameters consists of the second and third sets of inference parameters in inference parameter group 1. The identifier of the second set of inference parameters can be its global identifier; the identifier of the third set of inference parameters can also be its global identifier. Similarly, consider the case where the fourth set of inference parameters corresponding to inference parameter group 2 is unavailable, while the fifth set of inference parameters is available. In this case, the m-th set of inference parameters is the fifth set of inference parameters corresponding to inference parameter group 2, and therefore, the identifier of the fifth set of inference parameters can be its global identifier.

[0193] Optionally, Y sets of inference parameters are carried in Y information cells, and the global identifier of the m-th set of inference parameters is the identifier of the information cell carrying the m-th set of inference parameters. For example, if the m-th set of inference parameters is carried in the CSI-ReportConfig information cell, then the global identifier of the m-th set of inference parameters can be the identifier of the CSI-ReportConfig information cell.

[0194] For Examples 1 and 2 above, optionally, the second information may also include the identifier of the first inference parameter group, so that the network side can directly determine the inference parameter group corresponding to the available M sets of inference parameters based on the second information, saving time overhead.

[0195] Example 3: The identification information of the m-th set of inference parameters in M ​​sets of inference parameters includes the identifier of the first inference parameter group and the index of the m-th set of inference parameters.

[0196] The index of the m-th set of inference parameters is determined based on at least one of the following: the identifier of the first inference parameter group, the global identifier of the m-th set of inference parameters, or the arrangement position of the m-th set of inference parameters in at least one inference parameter group. The specific process for determining the index is described in S1001 above regarding the index of the y-th set of inference parameters, and will not be repeated here.

[0197] For example, referring to Figure 12(c) or (d), consider the case where the first set of inference parameters corresponding to inference parameter group 1 is unavailable, while the second and third sets of inference parameters are available. In this case, the m-th set of inference parameters consists of the second and third sets of inference parameters in inference parameter group 1. The identification information of the second set of inference parameters can be the identifier of inference parameter group 1 and the index of the second set of inference parameters; the identification information of the third set of inference parameters can also be the identifier of inference parameter group 1 and the index of the third set of inference parameters. Consider the case where the fourth set of inference parameters corresponding to inference parameter group 2 is unavailable, while the fifth set of inference parameters is available. In this case, the m-th set of inference parameters is the fifth set of inference parameters corresponding to inference parameter group 2, and the identification information of the fifth set of inference parameters can be the identifier of inference parameter group 2 and the index of the fifth set of inference parameters.

[0198] In some other embodiments, when the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, the second information includes an identifier of the first inference parameter group and a bitmap. The bitmap includes Y bits, each of which corresponds to one set of inference parameters out of the Y sets. The M sets of inference parameters are the inference parameters corresponding to the bits in the Y bits that are set to a first value. For example, the first value can be 1 (1 represents availability) or it can be 0 (0 represents availability). This application does not limit the setting of the first value.

[0199] In this context, the Y sets of inference parameters are sorted according to their global identifiers or indices. The y-th bit in the Y sets of inference parameters corresponds to the y-th set of inference parameters, where y = 1, ..., Y. For example, inference parameter group 1 includes 3 sets of inference parameters. After sorting according to their global identifiers or indices, the first set of inference parameters is unavailable, while the second and third sets are available. In this case, the second information includes the identifier of inference parameter group 1 and a bitmap of "011". The first bit "0" in the bitmap represents that the first set of inference parameters is unavailable, the second bit "1" represents that the second set of inference parameters is available, and the third bit "1" represents that the third set of inference parameters is available. Inference parameter group 2 includes two sets of inference parameters (i.e., the fourth set of inference parameters and the fifth set of inference parameters). After sorting according to the global identifier or index of the two sets of inference parameters, the fourth set of inference parameters is unavailable, and the fifth set of inference parameters is available. Therefore, the second information includes the identifier of inference parameter group 2 and a bit map of "01". The first bit "0" in the bit map represents that the fourth set of inference parameters is unavailable, and the second bit "1" in the bit map represents that the fifth set of inference parameters is available.

[0200] The following section explains how the terminal determines the bitmap corresponding to the inference parameter group.

[0201] In one possible implementation, for at least one inference parameter group in the first information, the terminal can determine the total number of sets of inference parameters contained in the first inference parameter group based on the identifier of the inference parameter group and the global identifier of each set of inference parameters (for example, the terminal determines the number of global identifiers of the inference parameters corresponding to the identifier of the first inference parameter group as the total number of sets of inference parameters contained in the first inference parameter group); or, if the first information includes the total number of sets of inference parameters in the first inference parameter group, the terminal can directly determine the total number of sets of inference parameters contained in the first inference parameter group based on the information.

[0202] Furthermore, the terminal can map the global identifiers of the Y sets of inference parameters corresponding to the first inference parameter group into a bitmap according to the size order of the total number Y sets of inference parameters contained in the first inference parameter group; or, the terminal can map the indexes of the Y sets of inference parameters corresponding to the first inference parameter group into a bitmap according to the size order of the total number Y sets of inference parameters contained in the first inference parameter group.

[0203] In one example, inference parameter group 1 contains a total of 3 sets of inference parameters. The terminal can map the availability of the 3 sets of inference parameters to a bitmap in sequence according to the size order of the global identifiers of the 3 sets of inference parameters corresponding to inference parameter group 1. For example, if the global identifiers of the 3 sets of inference parameters corresponding to inference parameter group 1 are paraId1 (corresponding to the 1st set of inference parameters), paraId2 (corresponding to the 2nd set of inference parameters), and paraId3 (corresponding to the 3rd set of inference parameters), and the 1st set of inference parameters is unavailable, while the 2nd and 3rd sets of inference parameters are available, the terminal maps the availability of the 3 sets of inference parameters to a "011" bitmap in ascending order of the size of the global identifiers. Here, the first "0" in the bitmap represents the 1st set of inference parameters being unavailable, the second "1" represents the 2nd set of inference parameters being available, and the third "1" represents the 3rd set of inference parameters being available. (Of course, the availability of the 3 sets of inference parameters can also be mapped to a "100" bitmap (1 represents unavailable, 0 represents available).

[0204] In another example, inference parameter group 1 contains a total of 3 sets of inference parameters. The terminal can map the availability of the 3 sets of inference parameters to a bitmap in order of their indices. For example, if the indices of the 3 sets of inference parameters in inference parameter group 1 are index 1 (corresponding to the first set of inference parameters), index 2 (corresponding to the second set of inference parameters), and index 3 (corresponding to the third set of inference parameters), and the first set of inference parameters is unavailable, while the second and third sets are available, the terminal maps the availability of the 3 sets of inference parameters to a "011" bitmap in ascending order of their indices. Here, the first "0" in the bitmap represents the first set of inference parameters being unavailable, the second "1" represents the second set of inference parameters being available, and the third "1" represents the third set of inference parameters being available. (Of course, the availability of the 3 sets of inference parameters can also be mapped to a "100" bitmap (1 represents unavailable, 0 represents available).

[0205] The above explains how the terminal determines the bitmap corresponding to the inference parameter group.

[0206] As one possible implementation, after receiving the second information, the RAN node can parse the second information to determine the available inference parameter set or the M sets of inference parameters available in the Y sets of inference parameters of the first set of inference parameters.

[0207] For example, if the second information contains the identifier and first indication information of the first inference parameter group, the RAN node can determine whether the first inference parameter group is available based on the identifier and first indication information of the first inference parameter group.

[0208] For example, if the second information contains the arrangement position of the available m-th set of inference parameters in at least one inference parameter group and the first indication information, since the RAN node knows the transmission order of each set of inference parameters in at least one inference parameter group, the RAN node determines the m-th set of inference parameters based on the arrangement position of the m-th set of inference parameters in at least one inference parameter group, and then determines whether the m-th set of inference parameters is available by combining the first indication information.

[0209] For example, if the second information contains a global identifier for the available m-th set of inference parameters and a first indication information, and the global identifier is unique in at least one group of inference parameters, then the RAN node determines the m-th set of inference parameters based on the global identifier of the m-th set of inference parameters, and then determines whether the m-th set of inference parameters is available by combining the first indication information.

[0210] For example, if the second information contains the index of the available m-th set of parameters, the identifier of the corresponding first inference parameter group, and the first indication information, and the index is unique in the first inference parameter group, then the RAN node can determine the m-th set of inference parameters based on the identifier of the first inference parameter group and the index of the m-th set of inference parameters, and then determine whether the m-th set of inference parameters is available by combining the first indication information.

[0211] For example, if the second information includes the identifier and bitmap of the first inference parameter group, the RAN node can know from the identifier of the first inference parameter group that the bitmap indicates one or more sets of inference parameters available in the first inference parameter group. The RAN node can parse the bitmap in the second information according to the terminal mapping order to know one or more sets of inference parameters available in the first inference parameter group.

[0212] Referring to Figure 14, which is a flowchart of another communication method provided in an embodiment of this application, the method may include the following steps:

[0213] S1401, the RAN node sends the first information to the terminal. Correspondingly, the terminal receives the first information from the RAN node.

[0214] The first information includes at least one inference parameter group, the first inference parameter group includes Y sets of inference parameters, where Y is a positive integer greater than 1, and the first inference parameter group is any one of the at least one inference parameter groups.

[0215] Optionally, the description of the first information is based on the embodiment shown in S1001 above, and will not be repeated here.

[0216] S1402, The terminal sends the fourth information to the RAN node. Correspondingly, the RAN node receives the fourth information from the terminal.

[0217] Specifically, for the first inference parameter group, the fourth information indicates that all Y sets of inference parameters are unavailable, or the fourth information indicates that N sets of inference parameters out of the Y sets are unavailable, where N is a positive integer less than Y. In the case where the fourth information indicates that N sets of inference parameters out of the Y sets are unavailable, the fourth information can implicitly indicate that the remaining YN sets of inference parameters (excluding the N sets) are available inference parameters.

[0218] As one possible implementation, when the fourth information indicates that all Y sets of inference parameters are unavailable, the fourth information includes the identifier of the first inference parameter group and the second indication information, whereby the second indication information indicates that the parameters are unavailable. For example, referring to Figure 12(a), if all three sets of inference parameters in inference parameter group 1 are unavailable, then the second information may include the identifier of inference parameter group 1 and the second indication information.

[0219] As another possible implementation, when the fourth information indicates that N sets of inference parameters out of Y sets of inference parameters are unavailable, the fourth information includes the identification information of each set of inference parameters in the N sets of inference parameters and the second indication information, the second indication information indicating availability. Specifically, the identification information of the inference parameters is described in S1002 for the identification information of the m-th set of inference parameters, and will not be repeated here.

[0220] In one possible implementation, when the RAN node (also known as the access network device) includes a first CU and a first DU, the terminal sends fourth information to the RAN node, including: the terminal sending fourth information to the first DU, and the first DU sending fourth information to the first CU.

[0221] In the above technical solution, the terminal receives first information from the RAN node, wherein the first information includes at least one inference parameter group. If the first inference parameter group includes Y sets of inference parameters, Y is a positive integer greater than 1, and the first inference parameter group is any one of the at least one inference parameter group. The terminal can send fourth information to the RAN node to indicate that all Y sets of inference parameters in the first inference parameter group are unavailable, or to indicate that N sets of inference parameters in the first inference parameter group are unavailable, where N is a positive integer less than Y. This allows availability to be reported at the granularity of each set of inference parameters. Compared to reporting availability at the group level, this improves the accuracy of inference parameter availability reporting by the terminal, enabling the network to know the availability of each set of inference parameters. This avoids problems such as using unavailable inference parameters to configure unreasonable inference schemes, leading to model activation failures, and thus improves the accuracy of model application.

[0222] Optionally, if the second information indicates that N sets of inference parameters are unavailable in the Y sets of inference parameters, the communication method of this application may further include S1403.

[0223] S1403, The terminal sends the fifth message to the RAN node. Correspondingly, the RAN node receives the fifth message from the terminal.

[0224] The fifth piece of information indicates the available M sets of inference parameters out of the Y sets of inference parameters, where M is a positive integer less than Y.

[0225] Optionally, for the explanation of the fifth information, please refer to the explanation in S1002 when the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, and it will not be repeated here.

[0226] In one possible implementation, when the RAN node (also known as the access network device) includes a first CU and a first DU, the terminal sends the fifth information to the RAN node, including: the terminal sending the fifth information to the first DU, and the first DU sending the fifth information to the first CU.

[0227] In the above technical solution, the terminal can indicate to the network side the available M sets of inference parameters out of the Y sets of inference parameters through a display instruction.

[0228] The method provided in this application has been described above. In addition, this application also provides a communication device for implementing the functions described in the above method embodiments.

[0229] It is understood that, in order to achieve the aforementioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0230] This application embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0231] Figure 15 shows a schematic diagram of a communication device 150. The communication device 150 includes a processing module 1501 and a transceiver module 1502. This communication device 150 can be used to implement the functions of the aforementioned terminal or RAN node.

[0232] In some embodiments, the communication device 150 may further include a storage module (not shown in FIG15) for storing program instructions and data.

[0233] In some embodiments, the transceiver module 1502, also referred to as a transceiver unit, is used to implement sending and / or receiving functions. The transceiver module 1502 may consist of a transceiver circuit, a transceiver, a transceiver unit, or a communication interface.

[0234] In some embodiments, the transceiver module 1502 may include a receiving module and a sending module, respectively configured to perform the receiving and sending steps performed by the terminal or RAN node in the above method embodiments, and / or other processes to support the technology described herein; the processing module 1501 may be configured to perform the processing steps performed by the terminal or RAN node in the above method embodiments, and / or other processes to support the technology described herein.

[0235] When the communication device 150 is used to implement the functions of a terminal, in one possible implementation: the transceiver module 1502 is used to receive first information, the first information including at least one inference parameter group, the first inference parameter group including Y sets of inference parameters, where Y is a positive integer greater than 1, and the first inference parameter group is any one of the at least one inference parameter group; the transceiver module 1502 is also used to send second information, the second information indicating that all Y sets of inference parameters are available, or, the second information indicating that M sets of inference parameters are available from the Y sets of inference parameters, where M is a positive integer less than Y.

[0236] Optionally, in one possible implementation, if the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, the transceiver module 1502 is further configured to send a third information indicating that N sets of inference parameters are not available out of Y sets of inference parameters, where N is a positive integer less than Y.

[0237] Optionally, in one possible implementation, the processing module 1501 is used to parse the first information and also to determine the second information.

[0238] When the communication device 150 is used to implement the functions of a RAN node, in one possible implementation: the transceiver module 1502 is used to send first information, the first information including at least one first inference parameter group, the first inference parameter group including Y sets of inference parameters, where Y is a positive integer greater than 1, and the first inference parameter group is any one of the at least one inference parameter group; the transceiver module 1502 is also used to receive second information, the second information indicating that all Y sets of inference parameters are available, or, the second information indicating that M sets of inference parameters are available from the Y sets of inference parameters, where M is a positive integer less than Y.

[0239] Optionally, in one possible implementation, if the second information indicates that M sets of inference parameters are available out of Y sets of inference parameters, the transceiver module 1502 is further configured to receive a third information indicating that N sets of inference parameters are not available out of Y sets of inference parameters, where N is a positive integer less than Y.

[0240] Optionally, in one possible implementation, the processing module 1501 is used to determine the first information and also to parse the second information.

[0241] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0242] In this application, the communication device 150 can be presented in an integrated manner by dividing it into various functional modules. Here, "module" can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0243] In some embodiments, when the communication device 150 in FIG15 is a chip or chip system, the function / implementation process of the transceiver module 1502 can be implemented through the input / output interface (or communication interface) of the chip or chip system, and the function / implementation process of the processing module 1501 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0244] Since the communication device 150 provided in this embodiment can execute the above method, the technical effects it can achieve can be referred to the above method embodiment, and will not be repeated here.

[0245] As a possible product form, the terminal or RAN node described in the embodiments of this application can be implemented using one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0246] As another possible product form, the terminal or RAN node described in this application embodiment can be implemented using a general bus architecture. For clarity, refer to Figure 16, which is a schematic diagram of the communication device 1600 provided in this application embodiment. The communication device 1600 includes a processor 1601 and a transceiver 1602. The communication device 1600 can be a terminal, or a chip or chip system therein; alternatively, the communication device 1600 can be a RAN node, or a chip or module therein. Figure 16 only shows the main components of the communication device 1600. In addition to the processor 1601 and transceiver 1602, the communication device may further include a memory 1603 and input / output devices (not shown in the figure).

[0247] Optionally, the processor 1601 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process the data of the software programs, thereby implementing the methods provided in the above-described method embodiments. The memory 1603 is mainly used to store software programs and data. The transceiver 1602 may include a radio frequency (RF) circuit and an antenna. The RF circuit is mainly used for converting baseband signals to RF signals and processing RF signals. The antenna is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves. Input / output devices, such as touch screens, displays, and keyboards, are mainly used to receive user input data and output data to the user.

[0248] Optionally, the processor 1601, transceiver 1602, and memory 1603 can be connected via a communication bus.

[0249] When the communication device is powered on, the processor 1601 can read the software program in the memory 1603, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 1601 performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit processes the baseband signal and transmits the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor 1601. The processor 1601 converts the baseband signal into data and processes the data.

[0250] In another implementation, the radio frequency circuitry and antenna can be set up independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antenna can be arranged remotely, independent of the communication device.

[0251] In some embodiments, those skilled in the art will recognize that the above-described communication device 150 can take the form of the communication device 1600 shown in FIG16 in terms of hardware implementation.

[0252] As an example, the function / implementation of the processing module 1501 in Figure 15 can be achieved by the processor 1601 in the communication device 1600 shown in Figure 16 calling computer execution instructions stored in the memory 1603. The function / implementation of the transceiver module 1502 in Figure 15 can be achieved by the transceiver 1602 in the communication device 1600 shown in Figure 16.

[0253] As another possible product form, the terminal or RAN node in this application may adopt the composition structure shown in FIG17, or include the components shown in FIG17. FIG17 is a schematic diagram of the composition of a communication device 1700 provided in this application. The communication device 1700 may be a terminal or a chip or system-on-a-chip in the terminal; or, it may be a RAN node or a module or chip or system-on-a-chip in the RAN node.

[0254] As shown in Figure 17, the communication device 1700 includes at least one processor 1701 and at least one communication interface (Figure 17 is merely an example illustrating the inclusion of a communication interface 1704 and a processor 1701). Optionally, the communication device 1700 may also include a communication bus 1702 and a memory 1703.

[0255] Processor 1701 can be a general-purpose central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a PLD, or any combination thereof. Processor 1701 can also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation. As one possible implementation, processor 1701 may include one or more CPUs, such as CPU0 and CPU1 in Figure 17.

[0256] Communication bus 1702 is used to connect different components in communication device 1700, enabling communication between them. Communication bus 1702 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in Figure 17, but this does not indicate that there is only one bus or one type of bus.

[0257] Communication interface 1704 is used for communicating with other devices or communication networks. Exemplarily, communication interface 1704 can be a module, circuit, transceiver, or any device capable of communication. Optionally, communication interface 1704 can also be an input / output interface located within processor 1701, used to implement signal input and signal output for the processor.

[0258] The memory 1703 may be a device with storage function, used to store instructions and / or data. The instructions may be computer programs.

[0259] For example, the memory 1703 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and / or instructions; it may also be a random access memory (RAM) or other type of dynamic storage device capable of storing information and / or instructions; it may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0260] It should be noted that the memory 1703 can exist independently of the processor 1701, or it can be integrated with the processor 1701. The memory 1703 can be located inside or outside the communication device 1700, without limitation. The processor 1701 can be used to execute the instructions stored in the memory 1703 to implement the methods provided in the following embodiments of this application.

[0261] As an optional implementation, the communication device 1700 may also include an output device 1705 and an input device 1706. The output device 1705 communicates with the processor 1701 and can display information in various ways. For example, the output device 1705 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 1706 communicates with the processor 1701 and can receive user input in various ways. For example, the input device 1706 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0262] In some embodiments, those skilled in the art will recognize that the communication device 150 shown in FIG15 can take the form of the communication device 1700 shown in FIG17 in terms of hardware implementation.

[0263] As an example, the function / implementation of the processing module 1501 in Figure 15 can be achieved by the processor 1701 in the communication device 1700 shown in Figure 17 calling computer execution instructions stored in the memory 1703. The function / implementation of the transceiver module 1502 in Figure 15 can be achieved by the communication interface 1704 in the communication device 1700 shown in Figure 17.

[0264] It should be noted that the structure shown in Figure 17 does not constitute a specific limitation on the terminal or RAN node. For example, in other embodiments of this application, the terminal or RAN node may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0265] In some embodiments, this application also provides a communication device, which includes a processor for implementing the methods in any of the above method embodiments.

[0266] As one possible implementation, the communication device also includes a memory. This memory stores necessary computer programs and data. The computer program may include instructions, which a processor can invoke to instruct the communication device to execute the methods described in any of the above method embodiments. Alternatively, the memory may not be present in the communication device.

[0267] As another possible implementation, the communication device also includes an interface circuit, which is a code / data read / write interface circuit, used to receive computer execution instructions (which are stored in memory and may be read directly from memory or may be transmitted through other devices) and transmit them to the processor.

[0268] As another possible implementation, the communication device also includes a communication interface for communicating with modules outside the communication device.

[0269] It is understood that the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or may include chips and other discrete devices. This application does not specifically limit this.

[0270] This application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a computer, implements the functions of any of the above-described method embodiments.

[0271] This application also provides a computer program product that, when executed by a computer, implements the functions of any of the above method embodiments.

[0272] 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.

[0273] It is understood that the systems, apparatuses, and methods described in this application can also be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0274] The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. The components shown as units may or may not be physical units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0275] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0276] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the 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 containing one or more servers, data centers, etc., that can be integrated with the medium. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive (SSD)). In this embodiment, the computer may include the aforementioned apparatus.

[0277] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0278] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the scope of this application. Accordingly, this specification and drawings are merely illustrative descriptions of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of the claims and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A communication method, characterized in that, The method includes: Receive first information, the first information includes at least one inference parameter group, the first inference parameter group includes Y sets of inference parameters, Y is a positive integer greater than 1, and the first inference parameter group is any one of the at least one inference parameter groups; Send a second message indicating that all Y sets of inference parameters are available, or the second message indicating that M sets of inference parameters are available out of the Y sets of inference parameters, where M is a positive integer less than Y.

2. The method according to claim 1, characterized in that, If the second information indicates that all Y sets of inference parameters are available, the second information includes the identifier of the first inference parameter group and first indication information, wherein the first indication information indicates availability.

3. The method according to claim 1, characterized in that, When the second information indicates that M sets of inference parameters are available out of the Y sets of inference parameters, the second information includes the identification information of each set of inference parameters in the M sets of inference parameters and the first indication information, the first indication information indicating availability.

4. The method according to claim 3, characterized in that, The identification information of the m-th set of inference parameters in the M sets of inference parameters is the arrangement position of the m-th set of inference parameters in the at least one set of inference parameters, where m = 1, ..., M.

5. The method according to claim 3, characterized in that, The identification information of the m-th set of inference parameters in the M sets of inference parameters is the global identifier of the m-th set of inference parameters, where m = 1, ..., M.

6. The method according to claim 5, characterized in that, The Y sets of inference parameters are carried in Y information cells, and the global identifier of the m-th set of inference parameters is the identifier of the information cell carrying the m-th set of inference parameters, where m = 1, ..., M.

7. The method according to any one of claims 3-6, characterized in that, The second information also includes the identifier of the first inference parameter group.

8. The method according to claim 3, characterized in that, The identification information of the m-th inference parameter in the M sets of inference parameters includes the identifier of the first inference parameter group and the index of the m-th inference parameter. The index of the m-th inference parameter is determined according to at least one of the following: the identifier of the first inference parameter group, the global identifier of the m-th inference parameter, or the arrangement position of the m-th inference parameter in the at least one inference parameter group, where m = 1, ..., M.

9. The method according to claim 1, characterized in that, When the second information indicates that M sets of inference parameters are available out of the Y sets of inference parameters, the second information includes the identifier of the first inference parameter group and a bit map. The bit map includes Y bits, each of the Y bits corresponds to one set of inference parameters in the Y sets of inference parameters, and the M sets of inference parameters are the inference parameters corresponding to the bits in the Y bits that are set to a first value.

10. The method according to claim 9, characterized in that, After the Y sets of inference parameters are sorted according to the global identifier or index of the Y sets of inference parameters, the y-th bit of the Y bits corresponds to the y-th set of inference parameters in the Y sets of inference parameters, y = 1, ..., Y.

11. The method according to any one of claims 1 or 3-10, characterized in that, If the second information indicates that M sets of inference parameters are available out of the Y sets of inference parameters, the method further includes: Send a third message indicating that N sets of inference parameters are unavailable out of the Y sets of inference parameters, where N is a positive integer less than Y.

12. The method according to any one of claims 1-11, characterized in that, The first information also includes the identifier of the first inference parameter group.

13. The method according to claim 12, characterized in that, The first information also includes one or more of the following: the global identifier of each set of inference parameters in the Y sets of inference parameters, or the index of the Y sets of inference parameters.

14. A communication method, characterized in that, The method includes: Send a first message, the first message including at least one first inference parameter group, the first inference parameter group including Y sets of inference parameters, Y being a positive integer greater than 1, and the first inference parameter group being any one of the at least one inference parameter groups; Receive a second message indicating that all Y sets of inference parameters are available, or the second message indicating that M sets of inference parameters are available from the Y sets of inference parameters, where M is a positive integer less than Y.

15. The method according to claim 14, characterized in that, If the second information indicates that all Y sets of inference parameters are available, the second information includes the identifier of the first inference parameter group and first indication information, wherein the first indication information indicates availability.

16. The method according to claim 14, characterized in that, When the second information indicates that M sets of inference parameters are available out of the Y sets of inference parameters, the second information includes the identification information of each set of inference parameters in the M sets of inference parameters, and the first indication information, which indicates availability.

17. The method according to claim 16, characterized in that, The identification information of the m-th set of inference parameters in the M sets of inference parameters is the arrangement position of the m-th set of inference parameters in the first inference parameter group, where m = 1, ..., M.

18. The method according to claim 16, characterized in that, The identification information of the m-th set of inference parameters in the M sets of inference parameters is the global identifier of the m-th set of inference parameters, where m = 1, ..., M.

19. The method according to claim 18, characterized in that, The Y sets of inference parameters are carried in Y information cells, and the global identifier of the m-th set of inference parameters is the identifier of the information cell carrying the m-th set of inference parameters, where m = 1, ..., M.

20. The method according to any one of claims 16-19, characterized in that, The second information also includes the identifier of the first inference parameter group.

21. The method according to claim 16, characterized in that, The identification information of the m-th inference parameter in the M sets of inference parameters includes the identifier of the first inference parameter group and the index of the m-th inference parameter. The index of the m-th inference parameter is determined according to at least one of the following: the identifier of the first inference parameter group, the global identifier of the m-th inference parameter, or the arrangement position of the m-th inference parameter in the at least one inference parameter group, where m = 1, ..., M.

22. The method according to claim 14, characterized in that, When the second information indicates that M sets of inference parameters are available out of the Y sets of inference parameters, the second information includes the identifier of the first inference parameter group and a bit map. The bit map includes Y bits, each of the Y bits corresponds to one set of inference parameters in the Y sets of inference parameters, and the M sets of inference parameters are the inference parameters corresponding to the bits in the Y bits that are set to a first value.

23. The method according to any one of claims 14 or 16-22, characterized in that, If the second information indicates that M sets of inference parameters are available out of the Y sets of inference parameters, the method further includes: Receive a third message indicating that N sets of inference parameters are unavailable among the Y sets of inference parameters, where N is a positive integer less than Y.

24. The method according to any one of claims 14-23, characterized in that, The first information also includes the identifier of the first inference parameter group.

25. The method according to claim 24, characterized in that, The first information also includes one or more of the following: the global identifier of each set of inference parameters in the Y sets of inference parameters, or the index of the Y sets of inference parameters.

26. The method according to any one of claims 14-25, characterized in that, The method is applied to access network devices. The access network device includes a first centralized unit (CU) and a first distributed unit (DU), and the method further includes: The first CU determines the first information; or, The first DU determines the first information, and the first DU sends the first information to the first CU.

27. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 1-13, or includes a module for performing the method as described in any one of claims 14-26.

28. A communication device, characterized in that, The communication device includes a processor; the processor is configured to run a computer program or instructions to cause the communication device to perform the method as claimed in any one of claims 1-13, or to cause the communication device to perform the method as claimed in any one of claims 14-26.

29. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions or programs that, when executed on a computer, cause the method described in any one of claims 1-13 to be performed, or cause the method described in any one of claims 14-26 to be performed.

30. A computer program product, characterized in that, The computer program product includes computer instructions; when some or all of the computer instructions are run on a computer, they cause the method of any one of claims 1-13 to be performed, or cause the method of any one of claims 14-26 to be performed.

Images