Communication method and apparatus

Abstract

The present application relates to the technical field of communications. Provided are a communication method and apparatus, which are used for selecting an appropriate model on the basis of data sets, thereby improving the reliability of data processing such as training, inference, or supervision. The method comprises: receiving first indication information used for indicating a first data set and used for indicating an association relationship between the first data set and at least one second data set; and determining a first model on the basis of the first indication information.

Description

A communication method and apparatus

[0001] This application claims priority to Chinese Patent Application No. 202410699109.2, filed with the State Intellectual Property Office of China on May 30, 2024, entitled "A Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0003] As wireless communication networks become more complex, service demands become more diverse, and service experiences become more personalized, artificial intelligence (AI) or machine learning (ML) models and algorithms will be more widely used in wireless communication scenarios. For example, AI or ML algorithms can be applied to scenarios such as channel prediction, network resource scheduling, or location calculation to improve data processing efficiency.

[0004] In reasoning based on a model, the training data and the inference data need to maintain a certain consistency for the model-based inference to have high reliability. For example, an AI device can train on dataset 1 collected from urban micro-cells to obtain model 1; and train on dataset 2 collected from rural macro-cells to obtain model 2. If inference is performed on dataset 3 collected from urban micro-cells, model 1 corresponding to training data with high consistency with dataset 3 (such as dataset 1) can be selected for inference, thus ensuring high reliability of the inference.

[0005] However, when performing data processing tasks through models in current communication networks, it may involve interaction or collaborative processing between multiple communication devices. For example, if the first device is used for training data and the second device is used for inference or supervision, the second device may not be able to select a matching model based on the dataset used to perform the data processing task, thus failing to guarantee the reliability of inference or supervision. Summary of the Invention

[0006] This application provides a communication method and apparatus for selecting a suitable model based on a dataset, thereby improving the reliability of data processing such as training, inference, or supervision.

[0007] To achieve the above objectives, this application adopts the following technical solution:

[0008] In a first aspect, a communication method is provided, which can be executed by a first device, the first device being a communication device or functional module (such as a chip or circuit), for example, the first device being a terminal. The method includes: receiving first indication information for indicating a first dataset and for indicating an association relationship between the first dataset and at least one second dataset; and determining a first model based on the first indication information.

[0009] In the above embodiments, the communication devices can indicate the association between different datasets, so that the receiving end can determine the matching target model for the dataset to perform the data processing task based on the association between the datasets. For example, the dataset to perform the data processing task can be training data, inference data, or supervision data, thereby ensuring the reliability of the data processing task and improving the data processing efficiency.

[0010] In one implementation, the first indication information is used to indicate that the data features corresponding to the first dataset and the second dataset are the same. That is, the first indication information can indicate that two or more datasets have the same data features, and the same data features mean that the datasets have high consistency. Data processing based on a model trained on a dataset with high consistency has high reliability.

[0011] In one implementation, determining a first model based on the first indication information includes: determining the first model based on the second dataset; wherein the first model is obtained by training data on the second dataset, or the first model is obtained by training data on a subset of the second dataset or a dataset associated with the second dataset.

[0012] In the above embodiments, the first device can select a model corresponding to a second dataset (such as one used for data training or related to the first dataset) that is related to the first dataset as the target model for data processing of the first dataset, based on the first instruction information, thereby improving the reliability of data processing.

[0013] In one implementation, the first indication information includes the name or index number of at least one data feature. Different names or index numbers corresponding to different data features can be predefined or preconfigured, allowing the first indication information to carry the name or index number corresponding to that data feature to indicate information about related datasets, thus saving signaling overhead.

[0014] In one implementation, the first indication information includes the name and / or index number of at least one second dataset. This can be achieved by predefining or preconfiguring the names or index numbers corresponding to different datasets, allowing the first indication information to carry the name or index number of a specific dataset to indicate information about related datasets, thus saving signaling overhead.

[0015] In one implementation, the data characteristics include at least one of the following: the source of the data in the dataset, data distribution characteristics, data temporal characteristics, data channel quality, data frequency domain characteristics, data spatial characteristics, data format, model characteristics, or functional characteristics. That is, communication devices can use first indication information to indicate the correlation between relevant parameters such as the source of the data, data distribution characteristics, data temporal characteristics, data channel quality, data frequency domain characteristics, data spatial characteristics, data format, model characteristics, or functional characteristics of the data in two or more datasets. This allows for the determination of a matching model based on the correlation, thereby improving the reliability of data processing.

[0016] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship. That is, the association relationship between different datasets can be represented as a QCL relationship, thereby determining the dataset association model based on the QCL relationship and improving the reliability of data processing.

[0017] In one implementation, the association relationship is a consistency relationship. Furthermore, the association relationship between different datasets can also be represented as a consistency relationship, a similarity relationship, or other similarity relationships, thus improving the flexibility of the indication method.

[0018] In one embodiment, the method further includes: obtaining configuration information, the configuration information including at least one of the following: a correspondence between I1 data features and I data feature index numbers; a correspondence between I data features and J feature parameters, wherein a data feature includes at least one feature parameter; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates an association relationship between at least one data feature between at least two different datasets; I1, I, J, M1, and M are positive integers, I is greater than or equal to I1, J is greater than or equal to I, and M1 is greater than or equal to M.

[0019] In the above embodiments, by predefining or preconfiguring the dataset index number corresponding to different datasets, the data feature index number corresponding to different data features, or the index number corresponding to different associations, the first indication information can be carried with the index number to indicate the datasets, data features, or associations that have an association relationship, thereby saving the signaling overhead of the indication information.

[0020] In one embodiment, before receiving the first indication information, the method further includes: receiving second indication information for indicating the activation of N related information among M1 related information, wherein M1 is greater than N, and M1 and N are positive integers; the first indication information is used to indicate at least one of the N related relationships.

[0021] In the above embodiments, a few of the multiple associations can be activated first by the second instruction information, and then further indicated by the first instruction information, thereby reducing the instruction overhead of the first instruction information.

[0022] In one embodiment, the method further includes: sending a third instruction message to a second device to request information about other datasets related to the first dataset, or information about models related to the first dataset, or related information about the first dataset.

[0023] In the above embodiments, if the first device does not obtain a matching first model, it can send a third instruction message to the second device to request information on other datasets or models that are related to the dataset to be processed, thereby improving the reliability and flexibility of data processing.

[0024] In one implementation, the third indication information includes the name or index number of at least one data feature, or an index number including at least one association relationship. That is, the request sent by the first device to the second device may carry information about the requested data feature related to the dataset to be processed, or information about the association relationship with the dataset to be processed, thereby obtaining more accurate feedback information. This improves the reliability and flexibility of data processing.

[0025] In one implementation, the third indication information is carried in the negative acknowledgment (NACK) signaling. That is, the overhead of indication signaling can be saved by extending the function of the negative acknowledgment (NACK) signaling to include the indication function of the third indication information.

[0026] In one embodiment, the method further includes: receiving a third dataset from the second device; training a second model based on the third dataset; and using the second model to perform inference or supervision on the first dataset based on the second model.

[0027] In the above embodiments, if the first device obtains a third dataset that is related to the first dataset (such as having the same data characteristics), it can train the third dataset to obtain a second model, which is used to perform inference or supervision on the first dataset based on the second model, thereby improving the reliability and flexibility of data processing.

[0028] In one implementation, the first dataset and the second dataset are any two of training data, supervised data, or inference data.

[0029] In one implementation, the first dataset and / or the second dataset are any one of training data, supervised data, or inference data. That is, during the training, supervision, or inference processes of model processing, the consistency of the training data, supervised data, or inference data datasets can be indicated by the first indication information, thereby improving the reliability of the data processing process.

[0030] In one embodiment, the first indication information is further used to indicate that the first model and at least one second model have the same model features; wherein, the model features include at least one of the following: model structure, model format, model parameters, or the scenario in which the model is applicable.

[0031] In the above embodiments, the first indication information can also be used to indicate the relationship between models, such as the same model features. Therefore, the reliability of performing data processing tasks based on models with the same model features is high.

[0032] In one embodiment, the first indication information is further used to indicate that the first dataset and at least one second dataset have the same functional characteristics, and / or to indicate that the first model and the second model have the same functional characteristics; wherein, the functional characteristics include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction function, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning function, beam management function, other functions or sub-functions, or the scenarios or model parameters to which the functions are applicable, etc.

[0033] In the above embodiments, the first indication information can also be used to indicate the correlation between corresponding functional features. For example, if the functional features are the same, the reliability of performing data processing tasks based on models with the same functional features is high, or the reliability of performing data processing tasks based on datasets with the same functional features is high.

[0034] In one implementation, the first indication information is sent via unicast, multicast, or broadcast. That is, the communication method provided in this application can be applied to scenarios where a network device interacts with one or more terminals, thereby improving the reliability of data processing tasks.

[0035] In one implementation, the first indication information is used to indicate a first dataset and to indicate data features of the first dataset; determining a first model based on the first indication information includes: determining the first model based on the data features; wherein the first model is obtained by training data on a dataset having the data features. That is, the first indication information may not include the name or identifier of a second dataset, and the first device can determine a matching target model for the dataset performing the data processing task based on the data features indicated by the first indication information. This target model can be obtained by training data on a dataset having the data features. For example, a first model can be trained based on a second dataset, wherein the second dataset also has the same data features as the first dataset. This ensures the reliability of the data processing task and improves data processing efficiency.

[0036] Secondly, a communication method is provided, which can be executed by a second device or by a module (such as a chip or circuit) of the second device, for example, the second device can be a network device. The method includes: sending first indication information to a first device to indicate a first dataset, and to indicate an association relationship between the first dataset and at least one second dataset.

[0037] In one implementation, the first indication information is used to indicate that the data characteristics corresponding to the first dataset and the second dataset are the same.

[0038] In one implementation, the first model is trained on the second dataset, or the first model is trained on a subset of the second dataset or a dataset associated with the second dataset.

[0039] In one implementation, the first indication information includes the name or index number of at least one data feature.

[0040] In one implementation, the first indication information includes the name and / or index number of at least one second dataset.

[0041] In one implementation, the data characteristics include at least one of the following: the source of the data in the dataset, the data distribution characteristics, the temporal characteristics of the data, the channel quality of the data, the frequency domain characteristics of the data, the spatial characteristics of the data, the data format, the model characteristics, or the functional characteristics.

[0042] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0043] In one implementation, the association relationship is a consistency relationship.

[0044] In one embodiment, the method further includes: obtaining configuration information, the configuration information including at least one of the following: a correspondence between I1 data features and I data feature index numbers; a correspondence between I data features and J feature parameters, wherein a data feature includes at least one feature parameter; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates an association relationship between at least one data feature between at least two different datasets; I1, I, J, M1, and M are positive integers, I is greater than or equal to I1, J is greater than or equal to I, and M1 is greater than or equal to M.

[0045] In one embodiment, the method further includes: sending a second indication message to a first device to indicate the activation of N associations among M1 associations, wherein M1 is greater than N, and M1 and N are positive integers; the first indication message is used to indicate at least one of the N associations.

[0046] In one embodiment, the method further includes: receiving third instruction information from a first device for requesting information about other datasets related to the first dataset, or information about models related to the first dataset, or related information related to the first dataset.

[0047] In one implementation, the third indication information includes the name or index number of at least one data feature, or includes the index number of at least one association relationship.

[0048] In one implementation, the third indication information is carried in the negative response (NACK) signaling.

[0049] In one embodiment, the method further includes: sending a third dataset to a first device for data training based on the third dataset to obtain a second model; the second model is used for inference or supervision of the first dataset based on the second model.

[0050] In one implementation, the first dataset and the second dataset are any two of training data, supervised data, or inference data.

[0051] In one embodiment, the first indication information is further used to indicate that the model features corresponding to the first model and the second model are the same; wherein, the model features include at least one of the following: model structure, model format, model parameters, or the scenario in which the model is applicable.

[0052] In one implementation, the first indication information is further used to indicate that the first dataset and the second dataset have the same functional characteristics, and / or to indicate that the first model and the second model have the same functional characteristics; wherein, the functional characteristics include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction function, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning function, beam management function, other functions or sub-functions, or the scenarios or model parameters to which the functions are applicable, etc.

[0053] In one implementation, the first instruction information is unicast, multicast, or broadcast.

[0054] In one implementation, the first indication information is used to indicate a first dataset, and to indicate data characteristics of the first dataset.

[0055] Thirdly, a communication method is provided. This method can be executed by a first device or by a module (such as a chip or circuit) of the first device; for example, the first device can be a terminal. The method includes: receiving first indication information indicating an association relationship between a first model and at least one second model.

[0056] In the above embodiments, the communication devices can indicate the association relationships between different models, enabling the receiving end to determine the matching target model for the task to be performed based on these relationships. For example, the task to be performed could be model aggregation, model pairing, or model transmission, thereby ensuring the reliability of the task. In one embodiment, the target model is a second model.

[0057] In one implementation, a second model is sent according to the first instruction information.

[0058] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0059] In one implementation, the association relationship is a consistency relationship. Furthermore, the association relationship between different models can also be expressed as a consistency relationship, a similarity relationship, or other similarity relationships, thus improving the flexibility of the indication method.

[0060] In one implementation, the association is based on the similarity of model characteristics. These model characteristics include at least one of the following: model structure, model format, model parameters, or the scenarios in which the model is applicable.

[0061] In one implementation, the first model or the second model can be at least one of the following: AI / ML model, AL / ML sub-model, AI / ML model parameters, AL / ML sub-model parameters, AI / ML model structure, AL / ML sub-model structure, AI / ML model related data, and AL / ML sub-model related data.

[0062] In one implementation, the first instruction information is unicast, multicast, or broadcast.

[0063] Fourthly, a communication method is provided. This method can be executed by a second device or by a module (such as a chip or circuit) of the second device; for example, the second device can be a network device. The method includes: sending first indication information to indicate an association relationship between the first model and at least one second model.

[0064] In one implementation, a second model is received.

[0065] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0066] In one implementation, the association relationship is a consistency relationship.

[0067] In one implementation, the first model or the second model can be at least one of the following: AI / ML model, AL / ML sub-model, AI / ML model parameters, AL / ML sub-model parameters, AI / ML model structure, AL / ML sub-model structure, AI / ML model related data, and AL / ML sub-model related data.

[0068] In one implementation, the first instruction information is unicast, multicast, or broadcast.

[0069] Fifthly, a communication method is provided. This method can be executed by a first device or by a module (such as a chip or circuit) of the first device; for example, the first device can be a terminal. The method includes: receiving first indication information for indicating an association between a first function and at least one second function.

[0070] In the above embodiments, the communication devices can indicate the association between different functions, so that the receiving end can determine the matching target function for the task to be executed based on the association between the functions. For example, the function to be executed can be AI / ML function, etc., thereby ensuring the reliability of the task.

[0071] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0072] In one implementation, the association relationship is a consistency relationship. Furthermore, the association relationship between different functions can also be expressed as a consistency relationship, a similarity relationship, or other similar forms, improving the flexibility of the indication method.

[0073] In one implementation, the association is based on the same functional characteristics. These functional characteristics include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning, beam management, other functions or sub-functions, or the applicable scenarios or model parameters for those functions.

[0074] In one implementation, the first function or the second function may be at least one of the following: AI / ML function, AL / ML sub-function, AI / ML function parameters, AL / ML sub-function parameters, AI / ML function structure, AL / ML sub-function structure, AI / ML function-related data, and AL / ML sub-function-related data.

[0075] In one implementation, the first instruction information is unicast, multicast, or broadcast.

[0076] Sixthly, a communication method is provided. This method can be executed by a second device or by a module (such as a chip or circuit) of the second device; for example, the second device can be a network device. The method includes: sending first indication information to indicate an association between a first function and at least one second function.

[0077] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0078] In one implementation, the association relationship is a consistency relationship.

[0079] In one implementation, the association is based on the same functional characteristics. These functional characteristics include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning, beam management, other functions or sub-functions, or the applicable scenarios or model parameters for those functions.

[0080] In one implementation, the first function or the second function may be at least one of the following: AI / ML function, AL / ML sub-function, AI / ML function parameters, AL / ML sub-function parameters, AI / ML function structure, AL / ML sub-function structure, AI / ML function-related data, and AL / ML sub-function-related data.

[0081] In one implementation, the first instruction information is unicast, multicast, or broadcast.

[0082] In a seventh aspect, a communication device is provided for implementing the above-described method. The communication device may be the first or second device as described in any of the above aspects, or a node or device including the first or second device, or a module within the first or second device, such as a chip, chip system, or circuit, or a logic node, logic module, or software capable of performing some or all of the functions.

[0083] The communication device includes modules, units, or means that implement the methods described above. These modules, units, or means 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 described above.

[0084] In conjunction with the seventh aspect above, in one possible implementation, 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 of their possible implementations. The processing module may be, for example, a processor. The transceiver module, also referred to as a transceiver unit, is used to implement the sending and / or receiving functions in any of the above aspects and any of their possible implementations. The transceiver module may consist of a transceiver circuit, a transceiver, a transceiver unit, or a communication interface.

[0085] In conjunction with the seventh aspect above, in one possible implementation, the transceiver module includes a sending module and a receiving module, which are used to implement the sending and receiving functions in any of the above aspects and any possible implementations.

[0086] Eighthly, a communication device is provided, comprising: a processor; the processor being coupled to a memory and, after reading instructions from the memory, executing the method as described in any of the preceding aspects according to the instructions. The communication device may be the first or second device as described in any of the preceding aspects, or a node or device comprising the first or second device, or a module of the first or second device, such as a chip, chip system, or circuit, or a logic node, logic module, or software capable of implementing some or all of the functions.

[0087] In conjunction with the eighth aspect above, in one possible implementation, the communication device further includes a memory for storing necessary program instructions and data.

[0088] In conjunction with the eighth aspect above, in one possible implementation, the communication device is a chip or a chip system. Optionally, when the communication device is a chip system, it can be composed of chips or may include chips and other discrete components.

[0089] A ninth aspect provides a communication device, comprising: a processor and an interface circuit; the interface circuit being configured to receive a computer program or instructions and transmit them to the processor; the processor being configured to execute the computer program or instructions to cause the communication device to perform the method described in any of the preceding aspects. The communication device may be the first or second device as described in any of the preceding aspects, or a node or device comprising the first or second device, or a module of the first or second device, such as a chip, chip system, or circuit, or a logic node, logic module, or software capable of implementing some or all of the functions.

[0090] In conjunction with the ninth aspect above, in one possible implementation, the communication device is a chip or a chip system. Optionally, when the communication device is a chip system, it can be composed of chips or may include chips and other discrete components.

[0091] In a tenth aspect, a computer-readable storage medium is provided, which stores instructions that, when executed on a computer, cause the computer to perform the methods described in any of the preceding aspects.

[0092] In an eleventh aspect, a computer program product containing instructions is provided, which, when run on a computer, enables the computer to perform the methods described in any of the preceding aspects.

[0093] The technical effects of any of the possible implementations in the second to eleventh aspects can be found in the technical effects of the different possible implementations in the first aspect above, and will not be repeated here.

[0094] Understandably, provided that the solutions do not contradict each other, the solutions in the above aspects can be combined. Attached Figure Description

[0095] Figure 1 is a schematic diagram of the architecture of a communication system provided in an embodiment of this application;

[0096] Figure 2 is a schematic diagram of the architecture of a communication device provided in an embodiment of this application;

[0097] Figure 3 is a flowchart illustrating a communication method provided in an embodiment of this application;

[0098] Figure 4 is a schematic diagram of the relationship between datasets provided in an embodiment of this application;

[0099] Figure 5 is a schematic diagram of the architecture of another communication device provided in an embodiment of this application. Detailed Implementation

[0100] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "a plurality of" means two or more.

[0101] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0102] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0103] First, a brief introduction will be given to the implementation environment and application scenarios of the embodiments of this application.

[0104] This application can be applied to scenarios involving communication between network devices, between network devices and terminals, and between terminals. For example, network devices may include base stations, which provide wireless access services to terminals. Base stations can communicate with each other via backhaul links, which can be wired (e.g., fiber optic, copper cable) or wireless (e.g., microwave). Terminals can communicate with their corresponding base stations via wireless links. Terminals can also communicate with each other via sidelinks.

[0105] In this embodiment, a network device is a means deployed in a radio access network to provide wireless communication functions for terminal devices. Network devices can include various forms of macro network devices, micro network devices (also known as small cells), relay stations, access points, etc. In systems employing different radio access technologies, the name of the network device may differ, such as a base transceiver station (BTS) in a Global System for Mobile Communication (GSM) or Code Division Multiple Access (CDMA) network, an NB (NodeB) in Wideband Code Division Multiple Access (WCDMA), or an eNB or eNodeB (evolutionary NodeB) in Long Term Evolution (LTE). A network device can also be a radio controller in a cloud radio access network (CRAN) scenario. A network device can also be a network device in a future fifth-generation mobile communication network or a network device in a future evolved public land mobile network (PLMN). A network device can also be a wearable device or an in-vehicle device. Network devices can also be transmission reception points (TRPs) or transmission points (TPs). Network devices can also be core network elements, dedicated nodes, or network management components, such as those used for operation, administration, maintenance (OAM).

[0106] Figure 1 is a schematic diagram illustrating a possible, non-limiting system. The communication method provided in this application embodiment can be applied to the network architecture shown in Figure 1. As shown in Figure 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1, collectively referred to as 120). RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is wirelessly or wired connected to core network 200. The core network device in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0107] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems (such as 6G mobile communication systems). RAN 100 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0108] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, network element 120i in Figure 1 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station; but for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0109] In one possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a TRP, a next-generation NodeB (gNB), a next-generation base station in a 6th-generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. The RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, the 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.

[0110] 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).

[0111] 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.

[0112] 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 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.

[0113] In addition, the terminal can also be a virtual reality (VR) terminal, an augmented reality (AR) terminal, or a mixed reality (MR) terminal. VR terminals, AR terminals, and MR terminals can all be called extended reality terminals. XR terminals can be, for example, head-mounted devices (such as helmets, head-mounted displays (HMDs), or glasses), all-in-one devices, as well as televisions, monitors, cars, in-vehicle devices, tablets, or smart screens. XR terminals can access the network wirelessly or via wired means, such as through WiFi or 5G systems. XR terminals can present XR data to users, allowing users to experience diverse XR services by wearing or using XR terminals.

[0114] The functions of the other network elements included in Figure 1 can be found in the relevant descriptions in conventional technologies, and will not be repeated here.

[0115] The communication system 10 shown in Figure 1 is for illustrative purposes only and is not intended to limit the technical solutions of this application. Those skilled in the art should understand that in specific implementations, the communication system 10 may also include other devices, and the number of RAN nodes and terminals may be determined according to specific needs without limitation.

[0116] Optionally, each network element or device (such as a RAN node or terminal) in Figure 1 of this application may also be referred to as a communication device, which may be a general-purpose device or a special-purpose device. This application does not make any specific limitation on this.

[0117] Optionally, the functions of each network element or device (e.g., RAN node or terminal) in Figure 1 of this application can be implemented by one device, multiple devices working together, or one or more functional modules within a single device. This application does not impose specific limitations on these functions. It is understood that the aforementioned functions can be network elements in hardware devices, software functions running on dedicated hardware, a combination of hardware and software, or virtualization functions instantiated on a platform (e.g., a cloud platform).

[0118] It is understood that the devices or network elements in Figure 1 above can communicate directly or through forwarding by other devices. This application embodiment does not specifically limit this.

[0119] It is understood that Figure 1 above is merely a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided in this application. Those skilled in the art should understand that in specific implementation processes, the communication system may include fewer devices or network elements than shown in Figure 1, or the communication system may also include other devices or other network elements, and the number of devices or network elements in the communication system can be determined according to specific needs.

[0120] It should be noted that the communication system shown in Figure 1 is for illustrative purposes only and is not intended to limit the technical solutions of this application. Those skilled in the art should understand that in specific implementations, the communication system may also include other devices or network elements, and the number of each network element may be determined according to specific needs.

[0121] Optionally, each network element in Figure 1 of this application embodiment can be a functional module within a device. It is understood that the above functions can be network elements in hardware devices, such as communication chips in mobile phones, or software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., cloud platform).

[0122] For example, each network element in Figure 1 can be implemented using the communication device 20 in Figure 2. Figure 2 shows a schematic diagram of the hardware structure of a communication device applicable to embodiments of this application. The communication device 20 includes at least one processor 201, a communication line 202, a memory 203, and at least one communication interface 204.

[0123] The processor 201 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0124] Communication line 202 may include a path for transmitting information between the aforementioned components, such as a bus.

[0125] Communication interface 204 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet interface, RAN interface, wireless local area network (WLAN) interface, etc.

[0126] The memory 203 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), 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, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may exist independently and be connected to the processor via communication line 202. The memory may also be integrated with the processor. The memory provided in this application embodiment is generally non-volatile. The memory 203 is used to store computer execution instructions involved in the scheme of this application and is controlled by the processor 201 for execution. The processor 201 is used to execute computer execution instructions stored in the memory 203, thereby implementing the method provided in the embodiments of this application.

[0127] Optionally, the computer execution instructions in the embodiments of this application may also be referred to as application code, and the embodiments of this application do not specifically limit this.

[0128] In a specific implementation, as one example, processor 201 may include one or more CPUs, such as CPU0 and CPU1 in FIG2.

[0129] In a specific implementation, as one embodiment, the communication device 20 may include multiple processors, such as processor 201 and processor 207 in FIG. 2. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0130] In a specific implementation, as one embodiment, the communication device 20 may further include an output device 205 and an input device 206. The output device 205 communicates with the processor 201 and can display information in various ways. For example, the output device 205 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 206 communicates with the processor 201 and can receive user input in various ways. For example, the input device 206 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0131] The communication device 20 described above can be a general-purpose device or a dedicated device. In specific implementations, the communication device 20 can be a portable computer, a web server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, an embedded device, or a device with a similar structure to that shown in Figure 2. This application does not limit the type of communication device 20.

[0132] The communication method provided in the embodiments of this application will be described in detail below.

[0133] It should be noted that the message names between network elements or the names of parameters in the messages in the following embodiments of this application are just examples. Other names may be used in the specific implementation. This application does not limit them in this respect.

[0134] Furthermore, in this application, "sending information to...(terminal)" can be understood as the destination of the information being the terminal. This can include sending information to the terminal directly or indirectly. "Receiving information from...(terminal)" can be understood as the source of the information being the terminal, and can include receiving information from the terminal directly or indirectly. 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.

[0135] Unless otherwise specified in this application, "at least one" means "one or more".

[0136] It is understood that some or all of the steps in the embodiments of this application are merely examples, and other steps or variations thereof may also be performed in the embodiments of this application. Furthermore, the steps may be performed in different orders as presented in the embodiments of this application, and it is not necessary to perform all the steps in the embodiments of this application.

[0137] This application provides a communication method in which the sending end indicates the association between at least two datasets to the receiving end, so that the receiving end can determine the matching target model based on the dataset for performing the data processing task. The dataset can be training data, inference data, or supervised data, thereby ensuring the reliability of the data processing task and improving the data processing efficiency.

[0138] For example, the following embodiments of this application describe the application of this application to a first device and a second device. The first device or the second device can be a network device or a terminal, such as any network element shown in FIG1, or a device, module or chip in any network element.

[0139] As shown in Figure 3, the method may include the following steps.

[0140] 301: The second device sends a first instruction message to the first device, indicating the first dataset and the association between the first dataset and at least one second dataset.

[0141] For example, the model can be an AI or ML model. An AL / ML model can be understood as a data-driven algorithm that uses AI / ML technology to generate a set of outputs from a set of inputs. An AL / ML model can also be understood as learning patterns and rules from a training dataset, and then using these patterns or rules to perform operations such as prediction, supervision, or inference. In practical applications, AI or ML models can be applied to AL4NET scenarios such as channel prediction, intelligent signal generation, network state tracking, network resource scheduling, or location calculation to improve communication processing efficiency. AI or ML models can also be applied to NET4AI scenarios to improve the processing efficiency of AI / ML and other services.

[0142] For example, different models can be obtained by training on different training datasets. There may be certain relationships between two or more datasets. Therefore, when a communication device selects a model to perform a data processing task on a specific dataset, it can choose the model corresponding to the dataset with the relationship to perform the data processing task, such as data training, inference, or supervision, which can improve the reliability of the data processing task.

[0143] As shown in Figure 4, the terminal trains data using dataset 1 to obtain model 1; and trains data using dataset 2 to obtain model 2. If the network device collects dataset 3 and sends it to the terminal, requesting the terminal to perform inference calculations based on dataset 3, the terminal needs to select the model with higher reliability for inference calculations from either model 1 or model 2 for use on dataset 3. For example, based on the consistency or correlation between datasets, the terminal can select one or more datasets with high consistency or correlation with dataset 3 for inference, thus ensuring higher reliability of the inference calculations.

[0144] For example, as shown in Figure 4, if dataset 1 is a dataset collected from urban micro-communities, the data characteristics of this dataset may include: a high ratio of base stations to terminals, a high density of base stations, a high density of terminals, a dense building layout, and the building material being reinforced concrete, etc.

[0145] Dataset 2 is a dataset collected from rural macrocells. The data characteristics of this dataset may include: a low ratio of base stations to terminals, a low density of base stations, a low density of terminals, a relatively scattered building layout, and the building material being brick-concrete structure, etc.

[0146] If the dataset 3 used by the terminal to perform data processing tasks (such as data inference) is also a dataset collected from urban micro-communities, even if the urban micro-communities for which dataset 3 and dataset 1 were collected are different, the data characteristics of dataset 3 and dataset 1 are highly consistent, while the data characteristics of dataset 3 and dataset 2 are less consistent. Therefore, the reliability of the terminal selecting model 1 to perform inference calculations on dataset 3 is high; that is, the terminal can determine that the model matched by dataset 3 is model 1.

[0147] In the embodiments of this application, indication information can be used to indicate the association relationship between two or more different datasets to other communication devices.

[0148] Correspondingly, the first device receives the first instruction information, obtains the first dataset, and the association between the first dataset and the second dataset.

[0149] In one implementation, the first indication information can be carried in a unicast, multicast, or broadcast message. That is, the embodiments of this application can be applied to scenarios where a network device interacts with multiple terminals, or scenarios where a network device interacts with a single terminal, etc.

[0150] 302: The first device determines the first model based on the first instruction information.

[0151] Specifically, the first device can determine the target model based on the relationship between the first dataset and the second dataset. For example, if the target model is determined to be the first model, it can be used to process the first dataset.

[0152] In one implementation, step 302, where the first device determines the first model based on the first instruction information, may specifically include:

[0153] The first device determines a first model based on a second dataset; wherein the first model is obtained by training data on the second dataset, or the first model is obtained by training data on a subset of the second dataset or a dataset associated with the second dataset.

[0154] In one implementation, the first indication information can be used to indicate that the data features corresponding to the first dataset and the second dataset are the same. That is, if the data features corresponding to the first dataset and the second dataset are the same, the first device can select the model corresponding to (or associated with) the second dataset as the target model based on the first indication information to process the data of the first dataset, thereby improving the reliability of data processing.

[0155] For example, the first indication information may indicate that data feature 1 is the same as that of the first dataset and the second dataset. Alternatively, the first indication information may indicate that both data feature 1 and data feature 2 are the same as those of the first dataset and the second dataset. Additionally, optionally, the first indication information may also indicate that data feature 3 is the same as that of the first dataset and the third dataset.

[0156] For example, data characteristics include at least one of the following: the source of the data in the dataset, the data distribution characteristics, the temporal characteristics of the data, the channel quality of the data, the frequency domain characteristics of the data, the spatial characteristics of the data, the data format, the model characteristics, or the functional characteristics, etc.

[0157] For example, the correspondence between data features and data feature index numbers can be predefined or configured, as shown in Table 1 below.

[0158] Table 1. Correspondence between data features and index numbers (data feature IDs)

[0159] For example, a dataset may also be a dataset containing model features or functional features.

[0160] It should be noted that in the field of communication technology, models and functions may also be represented by datasets. The datasets involved in this application may be datasets containing models or datasets containing functions. Therefore, the relationships between datasets (such as consistency relationships) may also be relationships between datasets and models, or relationships between datasets and functions, etc.

[0161] A brief introduction to data characteristics is as follows. For example, multiple data characteristics can be configured with corresponding characteristic names and / or identifiers (IDs) through protocol predefinition or high-level configuration to save on the overhead of indication signaling. A data characteristic may include at least one characteristic parameter. A data characteristic may include one or more of the following characteristic parameters:

[0162] (1) The source of the data in the dataset, used to indicate that the data in dataset 2 and dataset 1 are applicable to the same or similar scenarios.

[0163] Data scenarios can include: indoor factory, indoor office, rural macro-cell (RMA), urban macro-cell (UMA), urban micro-cell (UMI), or rural micro-cell (RMI), etc.

[0164] For example, the correspondence between data features and data feature index numbers can be predefined or configured, as shown in Table 2 below.

[0165] Table 2. Correspondence between data features and index numbers (data feature IDs)

[0166] In addition, the source of the data in the dataset can also include one or more of the following information: the density of building layout in the scene, the density of base stations and terminals, the ratio of the number of base stations and terminals, or information related to building materials, etc. For example, as shown in Table 3 below.

[0167] Table 3. Correspondence between data features and index numbers (data feature IDs)

[0168] Optionally, the scene sources of the data in the dataset may also include: the ratio of line-of-sight (LOS) data to non-line-of-sight (NLOS) data, or the ratio of indoor data to outdoor data, etc.

[0169] Optionally, the source of data in the dataset may also include one or more of the following: cell (group) number, TRP (group) number, or location-related information (which may be a predefined location, such as Xm*Ym, or a radius of Xm).

[0170] Optionally, the sources of data in the dataset may also include: network ID, core network ID, etc.

[0171] Optionally, the scenario source of the data in the dataset can also include duplex type, such as full-duplex, half-duplex, or subband full duplex (SBFD) mode.

[0172] (2) Data distribution characteristics, used to indicate that the data distribution characteristics of dataset 2 and dataset 1 are the same or similar.

[0173] For example, data distribution characteristics may include the central tendency of the data, such as the mean, median, or mode.

[0174] Optionally, the data dispersion may also be included: such as one or more of the following: variance, standard deviation, coefficient of variation, heterogeneity ratio, or quartiles.

[0175] Optionally, the data distribution shape may also be included: one or more of the following: Gaussian distribution, Rice distribution, or Rayleigh distribution.

[0176] Optionally, information such as the diversity of data may also be included.

[0177] (3) Time characteristics of the data, used to indicate that the time characteristics of the data in dataset 2 and dataset 1 are the same or similar.

[0178] For example, data time characteristics may include one or more of the following: the length of the data observation window, the start position of the data observation window, or the end position of the data observation window.

[0179] Optionally, it may also include one or more of periodic, semi-periodic, or aperiodic time windows, or event windows.

[0180] Optionally, information such as the freshness of the data can also be included.

[0181] (4) Data channel quality, indicating that the data channel quality of dataset 2 and dataset 1 is the same or similar.

[0182] For example, the channel quality or strength parameters of the data may include one or more of the following: reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), received signal strength indication (RSSI), signal to interference plus noise ratio (SINR), channel quality indicator (CQI), or precoding matrix indicator (PMI).

[0183] (5) Frequency domain characteristics of the data, used to indicate that the frequency domain characteristics of the data in dataset 2 and dataset 1 are the same or similar.

[0184] For example, the frequency domain characteristics of the data may include some or all of the information such as the location of the data subband, the width of the data subband, or the carrier frequency of the data (e.g., 2 GHz or 3.5 GHz).

[0185] (6) Spatial characteristics of the data, used to indicate that the spatial characteristics of the data in dataset 2 and dataset 1 are the same or similar.

[0186] For example, in a beam management scenario, the spatial characteristics of the data may include some or all of the beam shape or beam number, etc.

[0187] (7) Data format, used to indicate that the data formats of dataset 2 and dataset 1 are the same or similar.

[0188] For example, the data format may include the input or output format (type).

[0189] Optionally, the data format may also include: the type of the precoding matrix, the type of the channel matrix such as sparse or dense or radio frequency map (RF map).

[0190] Optionally, the data format may also include types such as the dimensions of the data input or output.

[0191] Optionally, the data format may also include: different dimensions may be one or more of different antenna ports, different bandwidths / subbands, etc.

[0192] Optionally, the data format may also include: data quantization methods, such as one or more of the modes of vector quantization, scalar quantization, or codebook-based quantization.

[0193] (8) Model features, used to indicate that the model features of dataset 2 and dataset 1 are the same or similar.

[0194] For example, model features may include model structure or architecture and / or model substructures: such as two-sided models, one-sided models; such as simultaneous models, sequential models; or, protocol-predefined model structures or frameworks such as convolutional layers, pooling layers and / or input layers; or, model structures such as CNN, recurrent neural network (RNN), etc.

[0195] Optionally, model features may also include some or all of the following: quantization metrics, transmission / reception format (transmission of the entire model / partial model / sub-model), model complexity, and model hardware requirements.

[0196] Optionally, model features may also include model parameters, such as some or all of the parameters like gradients and weights.

[0197] Optionally, model features may also include a reference model structure;

[0198] Optionally, model features may also include reference model parameters;

[0199] Optionally, model features may also include the scenarios in which the model is applicable.

[0200] (9) Functional characteristics, used to indicate that the functional characteristics of dataset 2 and dataset 1 are the same or similar.

[0201] For example, functional features may include lifecycle management (LCM) related functions, such as data collection, model training, model management, model inference, model storage, model supervision, etc.

[0202] Optional features may also include channel prediction models, CSI prediction, CSI compression, modulation and coding scheme (MCS) prediction, positioning functions such as AI positioning, beam management, and so on.

[0203] Optionally, functional features may also include other functionalities or sub-functionalities.

[0204] Optionally, functional features may also include the scenarios or model parameters to which the function is applicable.

[0205] In one implementation, the first indication information may include the name or index number of at least one data feature, used to indicate the same data feature or similar data feature between two or more datasets (i.e., the data feature has a high degree of consistency, such as the consistency is higher than a preset condition).

[0206] For example, the first indication information may include an index number ID-1 corresponding to the data feature shown in Table 2 above, which indicates that the source of the data in the dataset is the city macrocell (UMA).

[0207] For example, the first indication information may include an index number ID-1 corresponding to the data feature shown in Table 1 above, which is used to indicate the source of the data in the dataset.

[0208] In one implementation, the first indication information may include the identifier or index number of at least one dataset to indicate a dataset with an association relationship, for example, at least one dataset (such as a second dataset) has an association relationship with a first dataset that performs the data processing task.

[0209] For example, the first indication information may include the ID of the dataset, such as Dataset ID-2 or Dataset ID-3.

[0210] Optionally, the first indication information may include the name and / or index number of the first dataset for which the data processing task is performed.

[0211] For example, the first indication information includes the index number ID-1 corresponding to the data feature shown in Table 2 above, and the index number Dataset ID-2 of the dataset, which is used to indicate the association relationship between the first dataset Dataset ID-2 that performs the data processing task: the same data feature specifically includes having the same data source, and the same data source is: the source of the data is the city macrocell UMA.

[0212] In one implementation, the association between datasets can be a quasi-co-location (QCL) type relationship, a consistency relationship, a share relationship, a proximity relationship, or a similar relationship, etc. This application does not specifically limit the specific form and name of the association relationship.

[0213] In antenna technology, if the wireless channel properties of one antenna port can be deduced from the wireless channel properties of the other, or if the large-scale channel characteristic parameters of two antenna ports are the same (or similar), then these two antenna ports can be considered quasi-co-located, and the relationship between them can be indicated by QCL (Quasi-Co-located Channel Parameters). In other words, the QCL relationship can be used to indicate that the wireless channel properties of two antenna ports are the same or similar. For example, large-scale channel characteristic parameters may include one or more of the following: Doppler shift, Doppler spread, average delay, delay spread, or spatial receiver parameters.

[0214] In this application, QCL relationships can be used to indicate the association between two or more datasets, and to indicate that the reliability of data processing of one dataset by using the model corresponding to one dataset is high.

[0215] The following section will introduce the method of indicating the first instruction information with specific examples.

[0216] In one implementation, QCL relationships between datasets can be predefined through a protocol, such as predefined QCL relationships X1, X2, X3, X4, etc., or predefined QCL relationships 1, 2, 3, 4, or 5, etc., wherein the QCL relationship may include one or more data features.

[0217] It should be noted that among the predefined multiple QCL relations, X1, X2, or X3, etc., used to distinguish different QCL relations, can also be represented by other numbers or letters, such as A, B, C, D, E, or F. For example, predefined QCL relation E {data feature 1}: QCL relation E represents shared data feature 1, QCL relation F {data feature 2}: QCL relation F represents shared data feature 2. This application does not limit the naming of QCL relations.

[0218] For example, predefined QCL relationships can represent the following associations.

[0219] QCL relation A{base station to terminal ratio 1, base station and terminal density 1, building layout 1};

[0220] QCL relation B{ratio of base stations to terminals 2, density of base stations and terminals 2, building layout 2};

[0221] QCL relation C{Urban Micro-Community UMI};

[0222] QCL relationships such as D{Urban Macrocell UMA}, etc.

[0223] Alternatively, in another implementation, the protocol predefines or configures the correspondence between the ID of the data feature and the data feature, as well as predefines or configures the QCL relationship associated with the data feature.

[0224] For example, the protocol predefines the following relationships. The correspondence between data feature 1 and data feature 2, etc., and which specific data feature they correspond to can be found in Tables 1, 2, or 3 of the aforementioned examples.

[0225] QCL relation E{data feature 1};

[0226] QCL relation F{data feature 2}.

[0227] It should be noted that the association between datasets in the above embodiments of this application is exemplified by QCL relationships. Association relationships can also be represented in other forms, such as consistency relationships.

[0228] For example, the protocol predefines: consistency relation X{data feature 1};

[0229] Consistency relation Z{data feature 2}.

[0230] Alternatively, in one implementation, the correspondence between data features and data feature IDs can be predefined or configured through the protocol. The first indication information carries the data feature ID to indicate the association between datasets, without carrying indications such as QCL relationship or consistency relationship. The receiving end can confirm that the content indicated by the first indication information includes: the association between datasets is that the data features are the same.

[0231] For example, the association between datasets can be configured through higher-level signaling, such as by carrying first indication information in a radio resource control (RRC) message.

[0232] The following will use specific examples to illustrate the specific instructions for the first instruction message.

[0233] For example, the first indication information indicates that: for dataset 1, dataset 2|QCL relation E{data features (optional, may include one or more feature parameters)} is configured to indicate the data features associated with dataset 1 and dataset 2, that is, the data features specified in dataset 1 and dataset 2 are the same.

[0234] Alternatively, the protocol predefines or configures the meaning of the QCL relation E{data characteristics}, configuring dataset 1 with dataset 2|QCL relation E{data characteristics} to indicate that dataset 1 and dataset 2 have the same data characteristics.

[0235] In another example, the protocol predefines or configures the association between data feature ID and data feature, as shown in Tables 1-3 above. The first indication information indicates that: for dataset 1, the relationship between dataset 2 and QCL is E{data feature ID}, indicating that the same data feature between dataset 1 and dataset 2 is the data feature corresponding to the data feature ID.

[0236] Alternatively, the protocol can predefine or configure the association between data feature IDs and data features, as well as the correspondence between QCL relationships and index numbers. For example, it can predefine the index number corresponding to the QCL relationship E{data feature ID}, and indicate through the first indication information: configure dataset 1, dataset 2|QCL relationship E, indicating that the same data feature between dataset 1 and dataset 2 is the data feature corresponding to this data feature ID. As shown in Table 4 below.

[0237] Table 4. Correspondence between QCL relationships and index numbers

[0238] In another example, the first indication information indicates that dataset 1 and dataset 2 are configured, indicating that dataset 1 and dataset 2 have the same data characteristics. Here, dataset 1 can be a dataset containing configuration information for one or more of the following: physical downlink shared channel (PDSCH), reference signal (RS), or minimization drive test (MDT); alternatively, dataset 1 can be map data that may contain multi-path related channel parameters; or dataset 1 can be map data that may contain configuration information for multiple RSs, such as downlink positioning reference signal (DL PRS).

[0239] In summary, in order to save the overhead of instruction signaling (such as the first instruction information), configuration information can be sent through protocol predefinition or higher-level signaling, so that both communicating parties, such as the first device and the second device, can obtain the configuration information and thus determine the specific instruction content of the first instruction information based on the configuration information.

[0240] In one embodiment, the communication method further includes: a first device and / or a second device acquiring configuration information, the configuration information including at least one of the following: a correspondence between I1 data features and I data feature index numbers; a correspondence between I data features and J feature parameters, wherein a data feature includes at least one feature parameter; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates an association relationship of at least one data feature between at least two different datasets. I1, I, J, M1, and M are positive integers, where I is greater than or equal to I1, J is greater than or equal to I, and M1 is greater than or equal to M. The configuration information can be predefined by the protocol or configured via higher-layer signaling.

[0241] In other words, an index number of a data feature can correspond to one or more data features, a data feature can correspond to one or more feature parameters, and an index number of an association can correspond to one or more associations, thereby reducing the overhead of instruction signaling.

[0242] One possible example: Configuration information can be predefined through the protocol or obtained through higher-level signaling to configure multiple relationships. For instance, the configuration information can be carried in Radio Resource Control (RRC) messages. For example, the configuration information may include the aforementioned QCL relationship definition and the index number corresponding to the QCL relationship, with each index number corresponding to shared information for one or more models.

[0243] Then, the first indication information can be indicated via physical layer signaling, that is, specifying one or more QCL relationships. For example, the first indication information can be carried in downlink control information (DCI), sidelink control information (SCI), or uplink control information (UCI). Alternatively, the first indication information can also be indicated via higher layer signaling, such as by carrying it in the medium access control control element (MAC CE).

[0244] The following section will use specific examples to illustrate the implementation of configuration information and the first instruction information.

[0245] For example, higher-level signaling configuration includes multiple associations and a correspondence between associations and index numbers. Each index number can correspond to one or more associations, where each association can indicate that one or more data characteristics are the same. See Tables 5 to 10 below.

[0246] Table 5. Correspondence between different association relationships and index numbers

[0247] For example, as shown in Table 5, the physical layer signaling or MAC CE carries first indication information, which indicates dataset 1 and indicates dataset 10. According to the correspondence shown in Table 5, it can be seen that the data feature 1 and data feature 3 of dataset 1 and dataset 2 are the same, and the data feature 2 of dataset 1 and dataset 3 are the same.

[0248] Among them, the association relationship can be represented as a QCL relationship, as shown in Table 5; or, the association relationship can be represented as a consistency relationship, as shown in Table 6 below.

[0249] Table 6. Correspondence between different association relationships and index numbers

[0250] For example, relationships can also be represented by specific data features, as shown in Table 7 below.

[0251] Table 7. Correspondence between different association relationships and index numbers

[0252] For example, as shown in Table 7, the physical layer signaling or MAC CE carries first indication information, which indicates dataset 3 and is indicated as dataset 3 indicating 00. According to the correspondence shown in Table 7, it can be seen that the data feature 1 of the indicated dataset 3 and dataset 1 is the same.

[0253] In addition, the specific definitions of association relationships can be predefined through the protocol, and configuration information can be used to configure the correspondence between different association relationship IDs, dataset IDs, and index numbers. The association relationship can be represented as a QCL relationship, as shown in Table 8; or as a consistency relationship, as shown in Table 9; or other possible relationships, as shown in Table 10. This application does not limit the naming or numbering of association relationships.

[0254] Table 8. Correspondence between different associations and index numbers

[0255] Table 9. Correspondence between different associations and index numbers

[0256] Table 10. Correspondence between different association relationships and index numbers

[0257] In another possible embodiment, the second device sends first indication information to the first device to indicate a first dataset and its data characteristics. This first indication information may include the name or ID of the first dataset, but not the name or ID of the second dataset. In other words, the first indication information indicates the data characteristics of the first dataset.

[0258] In this implementation, step 302 described above, where the first device determines the first model based on the first instruction information, specifically includes: the first device can determine the first model based on the data features indicated by the first instruction information; wherein, the first model is obtained by training data on a dataset with data features. For example, if the first instruction information indicates that the data features of the first dataset include {data feature 1}, then a model trained on the dataset with {data feature 1} can be determined as the first model, and data processing can be performed on the first dataset based on the first model.

[0259] For example, the specific definitions of associations (such as Z1, Z2, etc.) can be predefined through the protocol. Configuration information is used to configure the correspondence between different associations and index numbers, as shown in Table 11 below. The first indication information indicates one of the index numbers, which can be used to indicate that a specific dataset has the data features included in the relationship corresponding to that index number. For example, if relationship Z2 indicates that it includes data feature 1 and data feature 2, then the first indication information 01, and the indication of the first dataset, can be used to indicate that the first dataset includes data feature 1 and data feature 2.

[0260] Table 11. Correspondence between different association relationships and index numbers

[0261] In another possible implementation, the communication devices may predefine configuration information or obtain it from a higher layer, configuring M1 associations. Optionally, one index number may correspond to one or more associations; therefore, the M1 associations may correspond to M index numbers. Before the first device receives the first indication information, the system may further include: the second device can activate N associations among the configured M1 associations by sending second indication information to the first device. For example, the second indication information may be carried in a MAC CE.

[0262] Then, the second device can send a first indication message to the first device, that is, it can use log2(N) bits to indicate one of the N associations. Where M1≥M>N, and M1, M and N are all positive integers.

[0263] It should be noted that the dataset (or simply dataset) in the embodiments of this application can be training data, supervised data, or inference data, and the two or more datasets indicated by the first indication information or configuration information can be any two of the training data, supervised data, or inference data.

[0264] In one implementation, if in step 302 above, the first device does not match the corresponding model according to the first instruction information, such as if the first device determines that it does not maintain or save a model that is highly consistent with the first dataset or has the same data characteristics locally according to the first instruction information, then the first device may request to update the model or request to update the information of the associated dataset.

[0265] For example, the first instruction information indicates that the first dataset and the second dataset share the same data characteristic: Rural Macrocell (RMA). If the first device does not locally store a model of the Rural Macrocell scene, then the first device can request to update the model or update the information of the dataset associated with the first dataset.

[0266] Optionally, the method may also include the following steps.

[0267] The first device sends a third instruction to the second device to request information about other datasets related to the first dataset, or information about models related to the first dataset, or related information about the first dataset.

[0268] For example, the first device may request other datasets that are related to the first dataset. If the second device sends a third dataset to the first device, the first device may receive the third dataset from the second device. Then, the first device may train data based on the third dataset to obtain a second model. Thus, the first device may perform data processing tasks on the first dataset based on the second model, such as inference or supervised processing.

[0269] Optionally, the third indication information may include the name or index number of one or more data features corresponding to the first dataset, or the index number of one or more associations associated with the first dataset.

[0270] In other words, the third indication information can be used to indicate that the first device has not maintained the model corresponding to the data feature, and to request the relevant information of the model or dataset associated with the data feature.

[0271] For example, if the data feature of the first dataset is Rural Macrocell (RMA), and the first device does not have a model of the rural macrocell scene stored locally, it can send a third instruction message to the second device, carrying the name or index number of the data feature, to request information about the dataset associated with the data feature of rural macrocell (RMA).

[0272] Alternatively, in another example, the first device may request information about a model that is related to the first dataset, such as second information, and the first device may perform data processing tasks on the first dataset based on the second model.

[0273] Alternatively, in another example, the first device may request to obtain association information related to the first dataset. For example, if the first device receives an instruction indicating that the third dataset is related to the first dataset (e.g., data feature 2 is the same), and the first device has a model trained based on the third dataset, such as the second model, then the first device may determine the second model and perform data processing tasks on the first dataset based on the second model.

[0274] In one implementation, the third indication information may specifically be a negative acknowledge (NACK) signaling message. The NACK signaling message is used to indicate that the first device does not maintain a model matching the dataset and requests information about the relevant model or dataset.

[0275] For example, the first indication information can be carried in a UCI, such as by sending a UCI in a PUCCH, or by multiplexing a UCI in a PUSCH and carrying a NACK signaling message in the UCI to indicate the third indication information.

[0276] Optionally, NACK signaling can also be used to indicate message reception failure or message decoding failure. For this purpose, different frequency domain resources can be used to send NACK signaling to distinguish whether the NACK signaling indicates third indication information or indicates message reception failure or decoding failure. For example, sending NACK signaling through the first frequency domain resource indicates third indication information; sending NACK signaling through the second frequency domain resource indicates message reception failure or decoding failure.

[0277] Furthermore, in one embodiment, the communication devices can also interact to indicate one or more associations between multiple models (or sub-models), which is used to indicate that one or more model features are the same between two or more models (or sub-models).

[0278] For example, the first indication information in the foregoing embodiments can also be used to indicate that the model features corresponding to the first model and the second model are the same; wherein, the model features include at least one of the following: model structure, model format, model parameters, or the scenario in which the model is applicable. Alternatively, implemented independently of the foregoing embodiments, the second device can send fourth indication information to the first device to indicate that the model features corresponding to the first model and the second model are the same.

[0279] It should be understood that, similar to the data features included in the datasets in the foregoing embodiments, models have corresponding model features. Based on the association relationships between datasets indicated in the foregoing examples, the association relationships of model features between models can be configured. For example, the fourth indication information is used to indicate that for model 1, the model 2|QCL relationship E{model feature 1} is configured, indicating that model 1 and model 2 have the same model feature 1.

[0280] For example, model features may include one or more of the following:

[0281] (1) Model structure and / or model substructure: such as two-sided model, one-sided model; such as synchronous model, sequence model; or, protocol-predefined model structure or framework such as convolutional layer, pooling layer and / or input layer; or, model structure such as CNN, recurrent neural network (RNN);

[0282] (2) Model format: such as some or all of the following: quantification indicators, sending / receiving format (sending the whole model / partial model / sub-model), model complexity, model hardware requirements, etc.

[0283] (3) Model parameters: such as some or all of the parameters such as gradient and weight;

[0284] (4) Reference model structure;

[0285] (5) Reference model parameters;

[0286] (6) Scenarios in which the model is applicable, etc.

[0287] It should be understood that the way to indicate the relationship between models regarding model features can refer to the way to indicate the relationship between datasets mentioned above. For example, predefine the correspondence between model features and index numbers, or predefine or configure the QCL relationship or other relationship between models with the same model features. For example, replacing the data feature ID with the model feature ID and the data feature with the model feature mentioned above can be used to indicate that the model features between models or sub-models are the same.

[0288] It should be noted that, in addition to indicating the relationship between models, it can also indicate the relationship between a model and a sub-model, or the relationship between sub-models, etc. This application does not limit this.

[0289] In another embodiment, the communication devices may also indicate the relationship between functions or sub-functions corresponding to the dataset or the relationship between functions or sub-functions corresponding to the model through indication information, that is, to indicate that the functions (or sub-functions) are the same.

[0290] For example, the first indication information in the foregoing embodiments can also be used to indicate that the first dataset and the second dataset have the same functional features, and / or to indicate that the first model and the second model have the same functional features; wherein, the functional features include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction function, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning function, beam management function, other functions or sub-functions, and the scenarios or model parameters to which the functions are applicable, etc.

[0291] Alternatively, implemented independently of the foregoing embodiments, the second device may send a fifth instruction message to the first device to indicate that the functional features corresponding to the first dataset and the second dataset are the same, and / or to indicate that the functional features corresponding to the first model and the second model are the same.

[0292] It should be understood that, similar to the data features included in the datasets in the foregoing embodiments, models may correspond to specific functional features, or datasets may correspond to specific functional features. Therefore, based on the association relationships between datasets indicated in the foregoing examples, the association relationships of functional features between datasets / models can be configured. For example, the fifth indication information is used to indicate that for model 1, the model 2|QCL relationship E{functional feature 1} is configured, indicating that functional feature 1 is the same for model 1 and model 2.

[0293] For example, functional characteristics may include one or more of the following:

[0294] (1) Functions related to model lifecycle management (LCM): such as data collection, model training, model management, model inference, model storage, model supervision, etc.

[0295] (2) Communication functions: channel prediction model, CSI prediction, CSI compression, modulation and coding scheme (MCS) prediction, positioning functions such as AI positioning, beam management and other functions, some or all of them.

[0296] (3) Other functions or sub-functions.

[0297] (4) The scenarios or model parameters to which the function is applicable.

[0298] It should be understood that the indication method for the relationship between functional features can refer to the indication method for the relationship between the aforementioned datasets, such as the predefined correspondence between functional features and index numbers, or the predefined QCL relationship or other relationship between the same model features. For example, replacing the data feature ID with the functional feature ID and the data feature with the aforementioned functional features in the previous example can be used to indicate that the functional features between multiple models are the same, or to indicate that the functional features between multiple datasets are the same.

[0299] It should be noted that, in addition to indicating the relationship between functions of a model (or dataset), it can also indicate the relationship between functions and sub-functions, or the relationship between sub-functions, etc. This application does not limit this.

[0300] The various embodiments mentioned above in this application can be combined without contradiction, and no limitation is imposed.

[0301] The above primarily describes the solution provided in this application from the perspective of interaction between various network devices. Accordingly, this application also provides a communication device, which can be the first device in the above method embodiments, or a component such as a chip that can be used in the first device; or it can be the second device in the above embodiments, or a component such as a chip that can be used in the second device. For example, the first device or the second device can be a terminal or a network device.

[0302] 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 unit and algorithm operations 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.

[0303] It should be understood that the above description of the interaction between various network elements only uses terminals or network devices as examples. In reality, the processing performed by the terminals is not limited to being performed by a single network element, and the processing performed by the network devices is not limited to being performed by a single network element.

[0304] This application can divide the communication device into functional modules based on the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated modules can be implemented in hardware or as software functional modules. It is understood that the module division in this application is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0305] For example, when the functional modules are divided in an integrated manner, Figure 5 shows a schematic diagram of the structure of a communication device 500. The communication device 500 includes an interface module 501 and a processing module 502.

[0306] In some embodiments, the communication device 500 may further include a storage module (not shown in FIG5) for storing program instructions and data.

[0307] For example, the communication device 500 can be used to implement the function of the first device in the above embodiments. The communication device 500 is, for example, the first device described in the various embodiments of FIG3 above.

[0308] The interface module 501 can be used to receive first indication information, which indicates a first dataset and the association between the first dataset and at least one second dataset.

[0309] The processing module 502 can be used to determine the first model based on the first indication information.

[0310] In one implementation, the first indication information is used to indicate that the data characteristics corresponding to the first dataset and the second dataset are the same.

[0311] In one implementation, the processing module 502 may be used to determine the first model based on the second dataset; wherein the first model is obtained by training data based on the second dataset, or the first model is obtained by training data based on a subset of the second dataset or a dataset associated with the second dataset.

[0312] In one implementation, the first indication information includes the name or index number of at least one data feature.

[0313] In one implementation, the first indication information includes the name and / or index number of at least one second dataset.

[0314] In one implementation, the data characteristics include at least one of the following: the source of the data in the dataset, the data distribution characteristics, the temporal characteristics of the data, the channel quality of the data, the frequency domain characteristics of the data, the spatial characteristics of the data, the data format, the model characteristics, or the functional characteristics.

[0315] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0316] In one embodiment, the interface module 501 can also be used to obtain configuration information, which includes at least one of the following: a correspondence between I1 data features and I data feature index numbers; a correspondence between I data features and J feature parameters, wherein a data feature includes at least one feature parameter; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates the association relationship of at least one data feature between at least two different datasets; I1, I, J, M1 and M are positive integers, I is greater than or equal to I1, J is greater than or equal to I, and M1 is greater than or equal to M.

[0317] In one embodiment, the interface module 501 can also be used to receive second indication information, which is used to indicate the activation of N association information among M1 association information, wherein M1 is greater than N, and M1 and N are positive integers; the first indication information is used to indicate at least one of the N association relationships.

[0318] In one embodiment, the interface module 501 can also be used to send third instruction information to the second device to request information about other datasets that are related to the first dataset, or information about models that are related to the first dataset, or related information related to the first dataset.

[0319] In one implementation, the third indication information includes the name or index number of at least one data feature, or includes the index number of at least one association relationship.

[0320] In one implementation, the third indication information is carried in the negative response (NACK) signaling.

[0321] In one embodiment, the interface module 501 can also be used to receive a third dataset from the second device; the processing module 502 can also be used to train data based on the third dataset to obtain a second model; the second model is used to perform inference or supervision on the first dataset based on the second model.

[0322] In one implementation, the first dataset and the second dataset are any two of training data, supervised data, or inference data.

[0323] In one embodiment, the first indication information is further used to indicate that the model features corresponding to the first model and the second model are the same; wherein, the model features include at least one of the following: model structure, model format, model parameters, or the scenario in which the model is applicable.

[0324] In one embodiment, the first indication information is further used to indicate that the first dataset and the second dataset have the same functional characteristics, and / or to indicate that the first model and the second model have the same functional characteristics; wherein, the functional characteristics include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction function, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning function, beam management function, other functions or sub-functions, or the scenarios or model parameters to which the functions are applicable.

[0325] Additionally, the communication device 500 can be used to implement the functions of the second device in the above embodiments. The communication device 500 is, for example, the second device described in the various embodiments of FIG3, and can be, for example, a RAN node, such as a base station.

[0326] The interface module 501 can be used to send first indication information to the first device to indicate the first dataset and to indicate the association between the first dataset and at least one second dataset.

[0327] In one implementation, the first indication information is used to indicate that the data characteristics corresponding to the first dataset and the second dataset are the same.

[0328] In one implementation, the first model is trained on the second dataset, or the first model is trained on a subset of the second dataset or a dataset associated with the second dataset.

[0329] In one implementation, the first indication information includes the name or index number of at least one data feature.

[0330] In one implementation, the first indication information includes the name and / or index number of at least one second dataset.

[0331] In one implementation, the data characteristics include at least one of the following: the source of the data in the dataset, the data distribution characteristics, the temporal characteristics of the data, the channel quality of the data, the frequency domain characteristics of the data, the spatial characteristics of the data, the data format, the model characteristics, or the functional characteristics.

[0332] In one implementation, the association relationship is a quasi-co-addressable (QCL) relationship.

[0333] In one implementation, the association relationship is a consistency relationship.

[0334] In one embodiment, the interface module 501 can also be used to obtain configuration information, which includes at least one of the following: a correspondence between I1 data features and I data feature index numbers; a correspondence between I data features and J feature parameters, wherein a data feature includes at least one feature parameter; or, a correspondence between M1 association information and M index numbers, wherein the association information indicates the association relationship of at least one data feature between at least two different datasets; I1, I, J, M1 and M are positive integers, I is greater than or equal to I1, J is greater than or equal to I, and M1 is greater than or equal to M.

[0335] In one embodiment, the interface module 501 can also be used to send a second indication information to the first device to indicate the activation of N association information among M1 association information, wherein M1 is greater than N, and M1 and N are positive integers; the first indication information is used to indicate at least one of the N association relationships.

[0336] In one embodiment, the interface module 501 can also be used to receive third instruction information from the first device, for requesting information about other datasets related to the first dataset, or information about models related to the first dataset, or related information related to the first dataset.

[0337] In one implementation, the third indication information includes the name or index number of at least one data feature, or includes the index number of at least one association relationship.

[0338] In one implementation, the third indication information is carried in the negative response (NACK) signaling.

[0339] In one embodiment, the interface module 501 can also be used to send a third dataset to the first device for data training based on the third dataset to obtain a second model; the second model is used to perform inference or supervision on the first dataset based on the second model.

[0340] In one implementation, the first dataset and the second dataset are any two of training data, supervised data, or inference data.

[0341] In one embodiment, the first indication information is further used to indicate that the model features corresponding to the first model and the second model are the same; wherein, the model features include at least one of the following: model structure, model format, model parameters, or the scenario in which the model is applicable.

[0342] In one implementation, the first indication information is further used to indicate that the first dataset and the second dataset have the same functional characteristics, and / or to indicate that the first model and the second model have the same functional characteristics; wherein, the functional characteristics include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction function, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning function, beam management function, other functions or sub-functions, or the scenarios or model parameters to which the functions are applicable, etc.

[0343] In summary, when the communication device 500 is used to implement the functions performed by the first device or the second device in the above embodiments, other functions that the communication device 500 can implement can be referred to the relevant descriptions of any of the embodiments shown above, and will not be elaborated further.

[0344] In one embodiment, the communication device 500 may take the form shown in FIG2. For example, the processor 201 in FIG2 can cause the communication device 20 to execute the method described in the above method embodiment by calling computer execution instructions stored in the memory 203.

[0345] For example, the function / implementation process of the processing module 502 in Figure 5 can be implemented by the processor 201 in Figure 2.

[0346] For example, the function / implementation process of the interface module 501 in Figure 5 can be implemented through the communication interface 204 in Figure 2.

[0347] It is understood that one or more of the above modules or units can be implemented by software, hardware, or a combination of both. When any of the above modules or units are implemented by software, the software exists as computer program instructions and is stored in memory. The processor can be used to execute the program instructions and implement the above method flow. The processor can be built into a system-on-chip (SoC) or ASIC, or it can be a separate semiconductor chip. In addition to the core that executes the software instructions for computation or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), or logic circuits that implement dedicated logic operations.

[0348] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a CPU, microprocessor, digital signal processing (DSP) chip, microcontroller unit (MCU), artificial intelligence processor, ASIC, SoC, FPGA, PLD, application-specific digital circuit, hardware accelerator, or non-integrated discrete device, which can run the necessary software or perform the above method flow independently of software.

[0349] Optionally, this application also provides a chip system, including: at least one processor and an interface, wherein the at least one processor is coupled to a memory via the interface, and when the at least one processor executes a computer program or instructions in the memory, the method in any of the above method embodiments is executed. In one possible implementation, the chip system further includes a memory. Optionally, the chip system may be composed of chips or may include chips and other discrete devices; this application does not specifically limit this.

[0350] Optionally, this application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. This program can be stored in the aforementioned computer-readable storage medium. When executed, the program can include the processes described in the above method embodiments. The computer-readable storage medium can be an internal storage unit of the communication device in any of the foregoing embodiments, such as the hard disk or memory of the communication device. The aforementioned computer-readable storage medium can also be an external storage device of the communication device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the communication device. Further, the aforementioned computer-readable storage medium can include both internal storage units and external storage devices of the communication device. The aforementioned computer-readable storage medium is used to store the aforementioned computer program and other programs and data required by the communication device. The aforementioned computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0351] Optionally, this application also provides a computer program product. All or part of the processes in the above method embodiments can be executed by a computer program instructing related hardware. This program can be stored in the above computer program product, and when executed, it can include the processes described in the above method embodiments.

[0352] Optionally, this application also provides computer instructions. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware (such as a computer, processor, network device, or terminal device). The program can be stored in the aforementioned computer-readable storage medium or the aforementioned computer program product.

[0353] Optionally, this application also provides a communication system, including: the first device and the second device in the above embodiments. For example, the first device may be a terminal or a network device, and the second device may be a terminal or a network device.

[0354] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0355] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or 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 device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0356] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0357] Furthermore, 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0358] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, Applied to a first device, the method includes: Receive first indication information, which indicates a first dataset and indicates the association between the first dataset and at least one second dataset; The first model is determined based on the first instruction information.

2. The method according to claim 1, characterized in that, The first indication information is used to indicate that the data characteristics corresponding to the first dataset and the second dataset are the same.

3. The method according to claim 1 or 2, characterized in that, Determining the first model based on the first indication information includes: The first model is determined based on the second dataset; The first model is obtained by training data on the second dataset, or the first model is obtained by training data on a subset of the second dataset or a dataset associated with the second dataset.

4. The method according to any one of claims 1-3, characterized in that, The first indication information includes the name or index number of at least one data feature.

5. The method according to any one of claims 1-4, characterized in that, The first indication information includes the name and / or index number of at least one second dataset.

6. The method according to claim 2 or 4, characterized in that, The data features include at least one of the following: The data includes the source of the data, the distribution characteristics of the data, the temporal characteristics of the data, the channel quality of the data, the frequency domain characteristics of the data, the spatial characteristics of the data, the data format, and the model or functional characteristics.

7. The method according to any one of claims 1-6, characterized in that, The association relationship is a quasi-co-addressable (QCL) relationship.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: Obtain configuration information, which includes at least one of the following: The correspondence between I1 data features and I data feature index numbers; The correspondence between I data features and J feature parameters, wherein each data feature includes at least one feature parameter; or, The correspondence between M1 related information and M index numbers, wherein the related information indicates the association relationship of at least one data feature between at least two different datasets; I1, I, J, M1 and M are positive integers, I is greater than or equal to I1, J is greater than or equal to I, and M1 is greater than or equal to M.

9. The method according to claim 8, characterized in that, Before receiving the first indication information, the method further includes: Receive second indication information, used to indicate the activation of N associated information out of M1 associated information, where M1 is greater than N, and M1 and N are positive integers; The first indication information is used to indicate at least one of the N associations.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: Send a third instruction message to the second device to request information about other datasets related to the first dataset, or information about models related to the first dataset, or related information about the first dataset.

11. The method according to claim 10, characterized in that, The third indication information includes the name or index number of at least one data feature, or includes the index number of at least one association relationship.

12. The method according to claim 10 or 11, characterized in that, The third indication information is carried in the negative response (NACK) signaling.

13. The method according to any one of claims 10-12, characterized in that, The method further includes: Receive a third dataset from the second device; The second model is trained using the third dataset to obtain the second model; the second model is used to perform inference or supervision on the first dataset based on the second model.

14. The method according to any one of claims 1-13, characterized in that, The first dataset and the second dataset are any two of the following: training data, supervised data, or inference data.

15. The method according to any one of claims 1-14, characterized in that, The first indication information is also used to indicate that the first model has the same model features as at least one second model; wherein, the model features include at least one of the following: model structure, model format, model parameters, or the scenario in which the model is applicable.

16. The method according to any one of claims 1-15, characterized in that, The first indication information is also used to indicate that the first dataset and the second dataset have the same functional features, and / or to indicate that the first model and at least one second model have the same functional features; The functional features include at least one of the following: data collection, model training, model management, model inference, model storage, model supervision, channel prediction function, channel state information (CSI) prediction, CSI compression, modulation and coding strategy prediction, positioning function, beam management function, other functions or sub-functions, or the scenarios or model parameters to which the functions are applicable.

17. A communication method, characterized in that, Applied to a second device, the method includes: Send a first instruction message to the first device to indicate a first dataset and to indicate the association between the first dataset and at least one second dataset.

18. The method according to claim 17, characterized in that, The first indication information is used to indicate that the data characteristics corresponding to the first dataset and the second dataset are the same.

19. The method according to claim 17 or 18, characterized in that, Determining the first model based on the first indication information includes: The first model is determined based on the second dataset; The first model is obtained by training data on the second dataset, or the first model is obtained by training data on a subset of the second dataset or a dataset associated with the second dataset.

20. The method according to any one of claims 17-19, characterized in that, The first indication information includes the name or index number of at least one data feature.

21. The method according to any one of claims 17-20, characterized in that, The first indication information includes the name and / or index number of at least one second dataset.

22. The method according to claim 18 or 20, characterized in that, The data characteristics include at least one of the following: the source of the data in the dataset, the data distribution characteristics, the time characteristics of the data, the channel quality of the data, the frequency domain characteristics of the data, the spatial characteristics of the data, the data format, the model characteristics, or the functional characteristics.

23. The method according to any one of claims 17-22, characterized in that, The association relationship is a quasi-co-addressable (QCL) relationship.

24. The method according to any one of claims 17-23, characterized in that, Before sending the first instruction information to the first device, the method further includes: Send a second instruction message to the first device to instruct the activation of N associated information out of M1 associated information, where M1 is greater than N, and M1 and N are positive integers; The first indication information is used to indicate at least one of the N relationships.

25. The method according to any one of claims 17-24, characterized in that, The method further includes: The system receives a third instruction from the first device, which requests information about other datasets related to the first dataset, or information about models related to the first dataset, or related information about the first dataset.

26. A communication device, characterized in that, The communication device is used to implement the method as described in any one of claims 1-25.

27. A communication device, characterized in that, include: A processor coupled to a memory for storing a program or instructions which, when executed by the processor, cause the method as described in any one of claims 1-25 to be performed.

28. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed on a computer, the computer causes the computer to perform the method as described in any one of claims 1-25.

29. A computer program product, the computer program product comprising computer program code, characterized in that, When the computer program code is run on a computer, it causes the computer to perform the method as described in any one of claims 1-25.

30. A chip, characterized in that, Includes a processor configured to perform the method as described in any one of claims 1-25.

Images