Resource configuration method and apparatus, terminal device, and network device

Abstract

Embodiments of the present application provide a resource configuration method and apparatus, a terminal device, and a network device. The method comprises: a terminal device receives first information, the first information being used to configure a first resource set, a measurement result corresponding to each resource in the first resource set being used by an AI / ML model to determine a target resource in a second resource set, and a spatial filter associated with the target resource being used for downlink transmission between the terminal device and a network device.

Description

Resource configuration method and device, terminal device, and network device TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of mobile communication technology, and in particular to a resource configuration method and device, a terminal device, and a network device. BACKGROUND

[0002] Currently, using artificial intelligence (AI) or machine learning (ML) technology for beam management has become a hot topic in the field of communication.

[0003] In an AI / ML-based beam management scheme, a terminal device can measure a plurality of beams (characterized by using a reference signal resource index) in a first beam set (denoted as Set B), use the measurement results corresponding to the plurality of beams as inputs of an AI / ML model, and infer an optimal beam in a second beam set (denoted as Set A).

[0004] However, how to configure Set A and / or Set B for the AI / ML-based beam management scheme is not clear at present.

[0005] SUMMARY

[0006] Embodiments of the present application provide a resource configuration method and device, a terminal device, and a network device.

[0007] In a first aspect, a resource configuration method provided by embodiments of the present application includes:

[0008] A terminal device receives first information, the first information being used to configure a first resource set, measurement results corresponding to each resource in the first resource set being used by an AI / ML model to determine a target resource in a second resource set, and a spatial filter associated with the target resource being used for downlink transmission between the terminal device and a network device.

[0009] In a second aspect, a resource configuration method provided by embodiments of the present application includes:

[0010] A network device sends first information, the first information being used to configure a first resource set, measurement results corresponding to each resource in the first resource set being used by an AI / ML model to determine a target resource in a second resource set, and a spatial filter associated with the target resource being used for downlink transmission between a terminal device and the network device.

[0011] In a third aspect, a resource configuration device provided by embodiments of the present application is applied to a terminal device, and includes:

[0012] The receiving unit is configured to receive first information, the first information being used for configuring a first resource set, a measurement result corresponding to each resource in the first resource set being used for an AI / ML model to determine a target resource in a second resource set, and a spatial filter associated with the target resource being used for downlink transmission between the terminal device and the network device.

[0013] In a fourth aspect, a resource configuration apparatus is provided. The apparatus is applied to a network device and includes:

[0014] The sending unit is configured to send first information, the first information being used for configuring a first resource set, a measurement result corresponding to each resource in the first resource set being used for an AI / ML model to determine a target resource in a second resource set, and a spatial filter associated with the target resource being used for downlink transmission between the terminal device and the network device.

[0015] In a fifth aspect, a terminal device is provided. The terminal device includes a processor and a memory. The memory is configured to store a computer program, and the processor is configured to invoke and run the computer program stored in the memory to execute the resource configuration method.

[0016] In a sixth aspect, a network device is provided. The network device includes a processor and a memory. The memory is configured to store a computer program, and the processor is configured to invoke and run the computer program stored in the memory to execute the resource configuration method.

[0017] A chip is provided. The chip is configured to implement the resource configuration method.

[0018] Specifically, the chip includes a processor configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the resource configuration method.

[0019] A computer readable storage medium is provided. The computer readable storage medium is configured to store a computer program. The computer program causes a computer to execute the resource configuration method.

[0020] A computer program product is provided. The computer program product includes computer program instructions. The computer program instructions cause a computer to execute the resource configuration method.

[0021] A computer program is provided. When the computer program runs on a computer, the computer program causes the computer to execute the resource configuration method.

[0022] The embodiment of the present application provides a resource configuration method, wherein the network device can configure a first resource set for the terminal device, so that the AI / ML model can determine an optimal beam from a second resource set based on a measurement result of a resource in the first resource set. In this way, the configuration mode of the first resource set can be determined, and the normal communication can be ensured. BRIEF DESCRIPTION OF DRAWINGS

[0023] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0024] Fig. 1 shows a network architecture schematic diagram;

[0025] Fig. 2 shows a schematic diagram of a neural network model;

[0026] Fig. 3 shows a schematic diagram of another neural network model;

[0027] Fig. 4 shows a schematic diagram of a measurement window and a prediction window in time domain beam prediction;

[0028] Fig. 5 shows a flowchart of a resource configuration method provided by the embodiment of the present application;

[0029] Fig. 6 shows a flowchart of another resource configuration method provided by the embodiment of the present application;

[0030] Fig. 7 is a structural schematic diagram of a resource configuration device provided by the embodiment of the present application;

[0031] Fig. 8 is a structural schematic diagram of a resource configuration device provided by the embodiment of the present application;

[0032] Fig. 9 is a schematic structural diagram of a communication device provided by the embodiment of the present application;

[0033] Fig. 10 is a schematic structural diagram of a chip according to the embodiment of the present application;

[0034] Fig. 11 is a schematic block diagram of a communication system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0036] Fig. 1 is a schematic diagram of a communication architecture.

[0037] As shown in FIG. 1, the communication system 100 can include a terminal device 110 and a network device 120. The network device 120 can communicate with the terminal device 110 over an air interface. The terminal device 110 and the network device 120 support multi-service transmission.

[0038] It should be understood that the embodiments of the present application are only exemplarily described with respect to the communication system 100, but the embodiments of the present application are not limited thereto. That is, the technical solutions of the embodiments of the present application can be applied to various communication systems, such as a Long Term Evolution (LTE) system, an LTE Time Division Duplex (TDD), a Universal Mobile Telecommunication System (UMTS), an Internet of Things (IoT) system, a Narrow Band Internet of Things (NB-IoT) system, an enhanced Machine-Type Communications (eMTC) system, a 5G communication system (also referred to as a New Radio (NR) communication system), or a future communication system, etc.

[0039] In the communication system 100 shown in FIG. 1, the network device 120 can be an access network device that communicates with the terminal device 110. The access network device can provide communication coverage for a specific geographic area and can communicate with the terminal device 110 located in the coverage area.

[0040] The network device 120 can be an Evolutional Node B (eNB or eNodeB) in an LTE system, or a Next Generation Radio Access Network (NG RAN) device, or a base station (gNB) in an NR system, or a radio controller in a Cloud Radio Access Network (CRAN), or a relay station, an access point, a vehicle-mounted device, a wearable device, a hub, a switch, a bridge, a router, or a network device in a future evolved Public Land Mobile Network (PLMN), etc.

[0041] The terminal device 110 can be any terminal device, including but not limited to a terminal device that is connected to the network device 120 or other terminal devices using a wired or wireless connection.

[0042] For example, the terminal device 110 can refer to an access terminal, a user equipment (UE), a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user apparatus. The access terminal can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, an IoT device, a satellite handheld terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a 5G network or a terminal device in a future evolution network, etc.

[0043] The terminal device 110 can be used for Device to Device (D2D) communication.

[0044] It should be understood that the communication system 100 can include a plurality of network devices and each network device can include other numbers of terminal devices within its coverage, and the embodiments of the present application are not limited thereto.

[0045] It should be noted that FIG. 1 only schematically shows the system to which the present application is applicable, and of course, the method shown in the embodiments of the present application can also be applicable to other systems.

[0046] It should be noted that the term "and / or" in this document is merely an association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B together, and the existence of B alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects. It should also be understood that the "indication" mentioned in the embodiments of the present application can be direct indication or indirect indication, and can also mean having an association relationship. For example, A indicates B, which can mean that B can be obtained through A; or it can mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; or it can mean that A and B have an association relationship. It should also be understood that the "corresponding" mentioned in the embodiments of the present application can mean that there is a direct correspondence or an indirect correspondence between the two, or it can mean that there is an association relationship between the two, or it can mean the relationship of indication and being indicated, configuration and being configured, etc. It should also be understood that the "predefined" or "predefined rule" mentioned in the embodiments of the present application can be realized by pre-saving the corresponding code, table or other means that can be used to indicate related information in the device (for example, including terminal equipment and network equipment), and the specific implementation manner of the present application is not limited. For example, the predefinition can mean the definition in the protocol. It should also be understood that the "protocol" in the embodiments of the present application can mean a standard protocol in the communication field, for example, it can include the LTE protocol, the NR protocol and the related protocol applied to the future communication system, and the present application is not limited thereto.

[0047] In order to facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described as follows, and the following related technologies can be combined with the technical solutions of the embodiments of the present application in any way, which all belong to the protection scope of the embodiments of the present application.

[0048] In the discussion of 3GPP R18 stage, AI / ML based beam management as the main use case of AI project is widely concerned by companies. In the current 3GPP R19 stage, although there are many details that have not reached a consensus on how to implement AI / ML based beam management, two typical use cases are defined in 3GPP RAN1, which are downlink beam prediction based on spatial domain (BM-Case1) and time domain (BM-Case2).

[0049] The beam prediction based on spatial domain (BM-Case1) is introduced as follows.

[0050] The beam prediction based on spatial domain (BM-Case1) is to measure the beams in Set B to predict the beams in Set A in the spatial domain.

[0051] In some scenarios, Set B can be a subset of Set A, in which case Set B can be understood as a partial subset of beams (pairs) and Set A can be understood as a full set of beams (pairs). In other scenarios, Set B and Set A can also be two different sets of beams (pairs). Exemplarily, Set B can be a set of SSB resources with fewer beams (each SSB resource corresponding to a larger spatial coverage range), and Set A can be a set of CSI-RS resources with more beams (each CSI-RS resource corresponding to a smaller spatial coverage range).

[0052] FIG. 2 shows a schematic diagram of a neural network model, which is an optimal beam (pair) prediction model. This model can be considered to solve a multi-classification problem. This model can be used to fit the measured results of Set B (such as the L1-RSRP of the reference signals / beams (pairs) in Set B) to the relationship between the optimal L beams (pairs) in Set A. Among them, the measured results of Set B can be used as the input of the model, and the output can be the optimal L beam (pair) indexes selected from the full set (Set A), that is, the L beams (pairs) with the highest L1-RSRP in Set A. In the example of FIG. 5, the number of beams (pairs) in Set B is T, the number of beams (pairs) in Set A is M, L = 1, and beam (pair) #2 is the beam (pair) with the highest L1-RSRP, that is, the optimal beam (pair). The label used by this model is the L beam (pair) indexes with the optimal (i.e., the highest L1-RSRP) measured in the full set.

[0053] FIG. 3 shows a schematic diagram of another neural network model, which is an optimal beam quality prediction model, which can be understood as a linear regression problem. The input and output relationship of this model is: the relationship from the L1-RSRP of the partial subset to the L1-RSRP of the optimal L beams (pairs). The input part of this model is the same as the input of the model shown in FIG. 5, and the difference is that the output of this model is the L (L≥1) optimal L1-RSRP and the L beam (pair) indexes corresponding to the L optimal L1-RSRP. In the example of FIG. 6, the number of beams (pairs) in Set B is T. The label used by this model is the L optimal L1-RSRP measured in the full set and the L beam (pair) indexes corresponding thereto.

[0054] The following describes beam prediction based on the time domain (BM-Case2).

[0055] Beam prediction based on the time domain (BM-Case2) is the prediction of the optimal beam (selected from Set A) at one or more future time points by measuring the beams in Set B at one or more historical time points.

[0056] Considering the use case of pure time-domain beam prediction, Set B can be the same set as Set A. Of course, mixed time-domain and spatial-domain beam prediction can also be considered, Set B can be a subset of Set A or Set B is another set different from Set A.

[0057] FIG. 4 shows a schematic diagram of a measurement window and a prediction window in time-domain beam prediction. In the measurement window, the terminal device can measure the downlink reference signal (DL RS) at intervals of 100 ms, and accordingly, the terminal device can predict the optimal beam at future time points (prediction window) at intervals of 100 ms.

[0058] In some embodiments, a Long Short-Term Memory (LSTM) model can be used for time-domain beam prediction.

[0059] In the related art, the measurement and reporting of beam management can be based on a Channel State Information (CSI) configuration framework.

[0060] Among them, the CSI configuration framework includes the following Radio Resource Control (RRC) signaling: CSI measurement configuration (CSI-MeasConfig), CSI reporting configuration (CSI-ReportConfig), CSI resource configuration (CSI-ResourceConfig), CSI-RS resource set, SSB resource set, CSI-RS resource, SSB resource (one resource corresponds to one transmit beam).

[0061] Reference is made to the CSI-MeasConfig Information Element (IE) shown in Table 1-1. Among others, each CSI-MeasConfig IE indicates / associates one or more NZP CSI-RS resources (NZP-CSI-RS-Resource) and resource sets (NZP-CSI-RS-ResourceSet), and / or one or more CSI-IM resources (CSI-IM-Resource) and resource sets (CSI-IM-ResourceSet), and / or one or more SSB resource sets (CSI-SSB-ResourceSet), one or more CSI reporting configurations (CSI-ReportConfig), one or more CSI resource configurations (CSI-ResourceConfig), one or two lists of trigger states (i.e., CSI-AperiodicTriggerStateList and CSI-SemiPersistentOnPUSCH-TriggerStateList).

[0062] Table 1-1 CSI-MeasConfig IE

[0063] Reference Table 1-2 shows the CSI-ReportConfig IE. Each CSI-ReportConfig contains / associates one or more resource configurations (CSI-ResourceConfig) indicating the resource configuration for channel measurement and / or interference measurement. In addition, each CSI-ReportConfig also includes codebook configuration, including Type I, Type II or enhanced Type II codebook and codebook restriction subset. CSI-ReportConfig also includes the time domain behavior of CSI reporting, such as periodic (Periodic), semi-persistent on PUCCH (semiPersistentOnPUCCH), semi-persistent on PUSCH (semiPersistentOnPUSCH), aperiodic (Aperiodic). CSI-ReportConfig also includes the relevant indication quantity of CSI reported by the terminal device, including channel quality indicator (CQI), precoding matrix indicator (PMI), CSI-RS resource indicator (CRI), SSB resource indicator (SSBRI), layer indicator (LI), rank indicator (RI), layer 1 reference signal receiving power (L1-RSRP), or layer 1 signal to interference plus noise ratio (L1-SINR) and other related configuration parameters.

[0064] Table 1-2 CSI-ReportConfig IE

[0065] Reference Table 1-3 for CSI-ResourceConfig IE. Each CSI-ResourceConfig contains / associates with one or more CSI Resource Sets (CSI Resource Set). These CSI Resource Sets can be NZP CSI-RS Resource Sets (each NZP CSI-RS Resource Set is configured by NZP-CSI-RS-ResourceSet IE) and / or SSB (Resource) Sets (each SSB Resource Set is configured by CSI-SSB-ResourceSet IE); or CSI-IM Resource Sets (each CSI-IM Resource Set is configured by CSI-IM-ResourceSet IE).

[0066] Table 1-3 CSI-ResourceConfig IE

[0067] Reference Table 1-4 for NZP-CSI-RS-ResourceSet IE. NZP-CSI-RS-ResourceSet IE is used to configure NZP CSI-RS Resource Set and resource set specific parameters. Each NZP CSI-RS Resource Set contains / associates with one or more NZP CSI-RS resources (by referencing NZP-CSI-RS-ResourceId).

[0068] Table 1-4 NZP-CSI-RS-ResourceSet IE

[0069] Reference Table 1-5 for CSI-SSB-ResourceSet IE. CSI-SSB-ResourceSet IE is used to configure SSB Resource Set. Each SSB Resource Set contains one or more SSBs, which is a reference to the SSBs configured in ServingCellConfigCommon IE.

[0070] Table 1-5 CSI-SSB-ResourceSet IE

[0071] Reference is made to the NZP-CSI-RS-Resource IE shown in Tables 1-6. Among them, the NZP-CSI-RS-Resource IE is used to configure the NZP CSI-RS, mainly stipulates the structure of the NZP CSI-RS, the PRB occupied in the frequency domain, and the transmission period and time slot offset (if the NZP CSI-RS is configured by the CSI-ResourceConfig IE to be periodic or semi-persistent).

[0072] Table 1-6 NZP-CSI-RS-Resource IE

[0073] In the related art, the terminal device can perform reference signal measurement and reporting based on the above RRC parameters, thereby realizing beam management. The AI / ML-based beam prediction needs to introduce Set A and Set B. How to configure Set A and / or Set B is not clear at present.

[0074] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, which all belong to the protection scope of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0075] FIG. 5 is a flowchart of a resource configuration method provided by an embodiment of the present application. As shown in FIG. 5, the method includes the following contents.

[0076] S510, the network device sends first information, and correspondingly, the terminal device receives the first information.

[0077] Among them, the first information is used to configure a first resource set, and the measurement results corresponding to each resource in the first resource set are used for the AI / ML model to determine a target resource in a second resource set, and the spatial filter associated with the target resource is used for downlink transmission between the terminal device and the network device.

[0078] For ease of description, the first resource set is denoted as Set B, and the second resource set is denoted as Set A in the following.

[0079] It should be noted that the "resource set" in the embodiments of the present application can be understood as a set of reference signal resources, or a set of spatial filters, and can also be understood as a set of transmission beams. Therefore, the "resource set" can also be referred to as a "reference signal resource set", a "spatial filter set", or a "beam set".

[0080] Set B and / or Set A can include multiple reference signal resources. For example, Set B and / or Set A can include multiple CSI-RS resources, or multiple SSB resources.

[0081] It should be noted that the measurement of Set B / Set A described in the embodiments of the present application, or the measurement of Set B / Set A, can refer to measuring the reference signal sent by the network device on the resources of Set B / Set A.

[0082] It should be noted that different reference signal resources can be associated with different spatial filters, or in other words, different reference signal resources can be associated with different beams.

[0083] It should also be noted that Set B can be a subset or a full set of Set A, or Set B and Set A are two different resource sets, which are not limited in the embodiments of the present application.

[0084] In the embodiments of the present application, the network device can send first information to configure Set B for the terminal device. In this way, the network device can send a reference signal (such as a CSI-RS or an SSB) to the terminal device on the resources in Set B. Correspondingly, the terminal device can perform measurement on the resources of Set B configured by the first information, thereby obtaining the measurement results corresponding to each resource in Set B.

[0085] It should be noted that the network device can configure one Set B, or multiple Set B.

[0086] The measurement results corresponding to each resource in Set B can be used by the AI / ML model to determine the target resource from the multiple resources in Set A. Wherein, Set B can be understood as a measurement set, and Set A can be understood as a prediction set.

[0087] That is, the measurement results corresponding to each resource in Set B can be used as input parameters of the AI / ML model, and the inference of the AI / ML model can obtain one or more optimal resources (i.e., target resources) in Set A, thereby realizing beam prediction.

[0088] Exemplarily, the first information can be CSI reporting configuration information CSI-ReportConfig. The network device can configure one CSI-ReportConfig in the CSI-MeasConfig to correspond to Set B. The network device can configure the CSI-ReportConfig by using csi-ReportConfigToAddModList and csi-ReportConfigToReleaseList in the CSI-MeasConfig IE. Further, the network device can use resourcesForChannelMeasurement in the CSI-ReportConfig IE to be associated to one CSI-ResourceConfig. In the CSI-ResourceConfig, one NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) is configured to correspond to one Set B. Wherein, the NZP-CSI-RS-ResourceSetId indicates one NZP CSI-RS resource in the NZP-CSI-RS-ResourceSet, or the CSI-SSB-ResourceSetId indicates one SSB resource in the CSI-SSB-ResourceSet, which corresponds to one transmit spatial filter, i.e., transmit beam, in Set B.

[0089] In the method provided in the embodiments of the present application, the network device can configure Set B for the terminal device, so that the AI / ML model can determine the optimal beam from Set A based on the measurement result of Set B. In this way, the configuration manner of Set B can be determined, and the normal communication can be ensured.

[0090] It should be noted that the AI / ML model can be obtained by any existing model training method. Here, it is assumed that the model used to determine the target resource is a trained model.

[0091] In the embodiments of the present application, the AI / ML model can be deployed on the terminal device side or the network device side.

[0092] In one scenario (hereinafter referred to as scenario 1), the AI / ML model can be deployed on the terminal device side, and the terminal device can complete the beam prediction work.

[0093] In another scenario (hereinafter referred to as scenario 2), the AI / ML model can be deployed at the network device side. In this scenario, the terminal device can report the measurement results corresponding to each resource in Set B to the network device, and the network device can complete the work of beam prediction.

[0094] It should be noted that Set B and / or Set A have different configuration purposes, or in other words, Set B and / or Set A have different uses. For example, Set B and / or Set A can be used for inference of the AI / ML model, training of the AI / ML model, and monitoring of the AI / ML model.

[0095] It should be understood that the operations of the terminal device and the network device are different for different configuration purposes of Set B and / or Set A.

[0096] In some embodiments, for scenario 1, if the configuration purpose of Set B and / or Set A is model inference, the terminal device needs to measure Set B, and use the measurement results corresponding to each resource in Set B as an input of the AI / ML model, to infer the resources / resource indexes corresponding to the optimal K beams and / or the link quality (such as L1-RSRP) corresponding to the K beams from Set A by using the AI / ML model. The terminal device reports the inference result to the network device, and the network device performs beam indication for the terminal device according to the inference result.

[0097] For scenario 1, if the configuration purpose of Set B and / or Set A is model training, the terminal device needs to measure Set B, and use the measurement result as an input of the AI / ML model. In addition, the terminal device also needs to measure Set A, and use the full set or a subset (the optimal K) of Set A as the label of the model. One input of the model and the corresponding label can constitute a data sample. The data sample needs to be provided to an AI / ML model training entity (such as a terminal device, a server, or a network device) to complete the training of the model.

[0098] For scenario 1, if the configuration purpose of Set B and / or Set A is model monitoring, the terminal device needs to measure Set B, take the measurement result of Set B as the input of the AI / ML model, and use the AI / ML model to infer the resource / resource index corresponding to the optimal K beams and / or the link quality (for example, L1-RSRP) corresponding to the K beams from Set A. In addition, the terminal device also needs to measure Set A to find the real optimal K beams and link quality. The result inferred by the AI / ML model is compared to determine the adaptation degree of the model, thereby completing the performance monitoring of the model.

[0099] In some embodiments, for scenario 2, if the configuration purpose of Set B and / or Set A is model inference, the terminal device needs to measure Set B and report the measurement result corresponding to each resource in Set B to the network device. In this way, the network device takes the measurement result corresponding to each resource in Set B as the input of the AI / ML model, infers the resource / resource index corresponding to the optimal K beams and / or the link quality (for example, L1-RSRP) corresponding to the K beams from Set A. Further, the network device performs beam indication for the terminal device according to the inference result.

[0100] For scenario 2, if the configuration purpose of Set B and / or Set A is model training, the terminal device needs to measure Set B and take the measurement result as one input of the AI / ML model. In addition, the terminal device also needs to measure Set A, and take the full set or subset (optimal K) of Set A as the label of the model. One input of the model and the corresponding label can constitute a data sample. The model training entity on the terminal device side or the network device side needs a large number of data samples to complete the training of the model.

[0101] For scenario 2, if the configuration purpose of Set B and / or Set A is model monitoring, the terminal device needs to measure Set B and report the measurement result of Set B to the network device. The network device takes the measurement result of Set B as the input of the AI / ML model, and uses the AI / ML model to infer the optimal K beam corresponding resource / resource index and / or link quality (e.g. L1-RSRP) from Set A. In addition, the terminal device also needs to measure Set A to find the real optimal K beam and link quality and report it to the network device. In this way, the network device can compare the optimal K beam and link quality reported by the terminal device with the result inferred by the AI / ML model to judge the adaptation degree of the model, thereby completing the performance monitoring of the model.

[0102] It should be noted that the operation of the model can be described using inference, inference or prediction (Prediction), that is, inference, inference and prediction can represent the same meaning and can be replaced by each other.

[0103] In some embodiments, the network device can also indicate the configuration purpose of Set B.

[0104] In some embodiments, the network device can indicate the configuration purpose of Set B in the first information. Wherein, the configuration purpose includes one or more of model training, model inference, and model monitoring.

[0105] Exemplarily, the network device can add a new RRC parameter purpuse in the CSI-ReportConfig of configuring Set B, which can include at least three options, namely {training, inference and monitoring}.

[0106] It should be understood that the network device and the terminal device can complete the operation adapted to the configuration purpose according to the configured Set B and the configuration purpose corresponding to Set B. Wherein, the terminal device and the network device to implement the operation adapted to the configuration purpose can refer to the description in the foregoing, and for the sake of brevity, it will not be described here.

[0107] It can be understood that, for scenario 1, since the AI / ML model is deployed at the terminal device side, the network device needs to configure Set A for the terminal device in addition to configuring Set B for the terminal device. For scenario 2, the AI / ML model is deployed at the network device side, in the model inference stage, the network device only needs to configure Set B for the terminal device, and correspondingly, the terminal device completes measurement on Set B and reports the measurement result to the NW; and in the model monitoring and model training stage, the network device also needs to configure Set A for the terminal device, so that the terminal device measures Set A.

[0108] In the embodiments of the present application, there are multiple configuration modes of Set A. In one mode, the network device can configure Set A and Set B simultaneously in the first information. In another mode, the network device can not configure a specific Set A, but configure a candidate parameter range corresponding to Set A. In yet another mode, the network device can configure Set A for the terminal device by using another information different from the first information. The three modes will be introduced respectively as follows.

[0109] Mode #1: The network device can configure Set A and Set B simultaneously in the first information.

[0110] Exemplarily, the network device can configure Set A and Set B simultaneously in CSI-ReportConfig.

[0111] It should be noted that Set A and Set B configured by the first information are associated with each other. That is, Set A and Set B configured by the first information can be used for processing of the same AI / ML model.

[0112] In a possible implementation mode, the first information indicates first resource configuration information and second resource configuration information; wherein the first resource configuration information is used to configure Set B, and the second resource configuration information is used to configure Set A.

[0113] It can be understood that the first information can configure Set A and Set B by using different resource configuration information respectively.

[0114] Exemplarily, the first resource configuration information and / or the second resource configuration information can be CSI-ResourceConfig.

[0115] Exemplarily, the first information is CSI-ReportConfig, and in the CSI-ReportConfig, two different CSI-ResourceConfigId corresponding to Set A and Set B can be configured.

[0116] Exemplarily, referring to a CSI-ReportConfig IE shown in Table 2-1, an original RRC parameter resourcesForChannelMeasurement in the CSI-ReportConfig can be used to indicate a CSI-ResourceConfigId corresponding to Set B. Correspondingly, in the CSI-ResourceConfig corresponding to the CSI-ResourceConfigId, an NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or a CSI-SSB-ResourceSetId (SSB resource set) is configured to correspond to a Set B. In addition, a new RRC parameter resourcesForChannelMeasurement2 is added in the CSI-ReportConfig shown in Table 2-1 to indicate another CSI-ResourceConfigID corresponding to Set A. Correspondingly, in the CSI-ResourceConfig corresponding to the CSI-ResourceConfigID, an NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or a CSI-SSB-ResourceSetId (SSB resource set) is configured to correspond to a Set A.

[0117] In addition, Set A and Set B can also be configured in the opposite order. Exemplarily, in the CSI-ReportConfig IE shown in Table 2-1, an original RRC parameter resourcesForChannelMeasurement in the CSI-ReportConfig is used to indicate a CSI-ResourceConfigID corresponding to Set A. In addition, a new RRC parameter resourcesForChannelMeasurement2 is added in the CSI-ReportConfig to indicate another CSI-ResourceConfigID corresponding to Set B.

[0118] It should be noted that the reporting content reportQuantity of Set B in the CSI-ReportConfig can be selected as none.

[0119] Table 2-1 CSI-ReportConfig IE

[0120] It should be noted that the first resource configuration information can configure multiple candidate Set Bs, and the Set B is any one of the multiple candidate Set Bs; and / or the second resource configuration information configures multiple candidate Set As, and the Set A is any one of the multiple candidate Set As.

[0121] It can be understood that in the first resource configuration information, multiple NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) can be configured to correspond to multiple Set Bs for AI / ML model input.

[0122] Similarly, in the second resource configuration information, multiple NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) can be configured to correspond to multiple Set As.

[0123] In some embodiments, the network device can send second information, and correspondingly, the terminal device can receive the second information sent by the network device. The second information is used to indicate a Set B from multiple candidate Set Bs, and / or is used to indicate a Set A from the multiple candidate Set As.

[0124] That is, the network device can indicate a suitable Set B from the multiple candidate Set Bs and / or a suitable Set A from the multiple candidate Set As through signaling.

[0125] Exemplarily, the second information can be carried by RRC signaling.

[0126] Exemplarily, the second information can be carried by MAC CE signaling. The network device can activate or deactivate a suitable Set B and / or Set A using MAC CE signaling.

[0127] Exemplarily, the second information can also be carried by DCI signaling. The network device can dynamically indicate a suitable Set B and / or Set A for the terminal device using DCI signaling.

[0128] It should be noted that indicating a suitable Set B from the multiple candidate Set Bs and indicating a suitable Set A from the multiple candidate Set As can be indicated using the same signaling or different signaling. Exemplarily, the network device indicates a suitable Set B from the multiple candidate Set Bs through RRC signaling, and activates or deactivates a suitable Set A through MAC CE signaling. The embodiments of the present application do not limit this.

[0129] In some embodiments, the network device can also indicate the configuration purpose of Set A.

[0130] In some embodiments, the configuration purpose of Set A and Set B can be the same.

[0131] For example, if the configuration purpose of Set A and Set B is the same, only one purpuse can be included in the CSI-ResourceConfig IE to configure the configuration purpose of Set A and Set B.

[0132] In some embodiments, the configuration purpose of Set A and Set B can be different.

[0133] In some embodiments, the network device can indicate the configuration purpose of Set A in the first information. The configuration purpose includes one or more of model training, model inference, and model monitoring.

[0134] For example, referring to the CSI-ReportConfig IE shown in Table 2-1, the network device can add a RRC parameter purpuse2, which can include at least three options, i.e., {training, inference, and monitoring}.

[0135] It should be understood that the network device and the terminal device can complete operations adapted to the configuration purpose of Set B and Set A according to the configured Set B and Set A and the configuration purpose corresponding to Set B and Set A. The terminal device and the network device can implement operations adapted to the configuration purpose, which can be referred to the description above. For brevity, the description is not repeated here.

[0136] In another possible implementation, the first information indicates third resource configuration information; the third resource configuration information is used to configure Set A and Set B.

[0137] It can be understood that the first information can configure Set A and Set B at the same time through one resource configuration information.

[0138] In some embodiments, the third resource configuration information can be CSI-ResourceConfig.

[0139] For example, the first information can be CSI-ReportConfig, in which a CSI-ResourceConfigId is configured to correspond to the configuration of Set A and Set B.

[0140] Exemplarily, referring to a CSI-ResourceConfig IE shown in Table 2-2, one nzp-CSI-RS-SSB is configured in one CSI-ResourceConfig, the nzp-CSI-RS-SSB can contain one NZP-CSI-RS-ResourceSetId (CSI-RS resource set) and / or one CSI-SSB-ResourceSetId (SSB resource set) to correspond to one Set B; another nzp-CSI-RS-SSB2 is configured, and similarly, the nzp-CSI-RS-SSB2 contains one NZP-CSI-RS-ResourceSetId and / or one CSI-SSB-ResourceSetId to correspond to one Set A.

[0141] It should be noted that in the CSI-ResourceConfig IE shown in Table 2-2, the nzp-CSI-RS-SSB can correspond to one Set A; and the other nzp-CSI-RS-SSB2 can correspond to Set B.

[0142] Table 2-2 CSI-ResourceConfig IE

[0143] In some embodiments, considering more than one Set B and Set A, multiple NZP-CSI-RS-ResourceSetId (CSI-RS resource set) and / or CSI-SSB-ResourceSetId (SSB resource set) can be configured in one CSI-ResourceConfig to correspond to multiple Set B; and multiple NZP-CSI-RS-ResourceSetId and / or CSI-SSB-ResourceSetId are configured to correspond to multiple Set A.

[0144] Similarly, one NZP CSI-RS resource in the NZP-CSI-RS-ResourceSet or one SSB resource in the CSI-SSB-ResourceSet corresponds to one spatial filter, i.e., beam, in the Set B or Set A.

[0145] In some embodiments, the network device can also indicate the configuration purpose of the Set A.

[0146] It should be noted that the Set B and the Set A configured in the third resource configuration information described above can be applicable to different purposes, i.e., model training, model inference and model monitoring. For the configuration purposes of the Set B and the Set A, configuration can be configured at different CSI framework granularities.

[0147] Exemplarily, the network device can indicate the configuration purposes of the Set B and the Set A corresponding to the CSI-ResourceConfigId in the first information (i.e., CSI-ReportConfig). If the configuration purposes of the Set B and the Set A are the same, the CSI-ReportConfig can only include one Purpuse, which corresponds to the configuration purposes of the Set B and the Set A. If the configuration purposes of the Set B and the Set A are different, the CSI-ReportConfig can correspond to the configuration purposes of the Set B and the Set A through RRC parameters Purpuse and Purpuse2 respectively.

[0148] Exemplarily, the network device can also indicate the configuration purposes of the Set B and the Set A in the third resource configuration information (i.e., CSI-ResourceConfig) indicated by the first information. If the configuration purposes of the Set B and the Set A are the same, the CSI-ResourceConfig can only include one Purpuse, which corresponds to the configuration purposes of the Set B and the Set A. If the configuration purposes of the Set B and the Set A are different, referring to the CSI-ResourceConfig IE shown in Table 2-2, the CSI-ResourceConfig can correspond to the configuration purposes of the Set B and the Set A through RRC parameters Purpuse and Purpuse2 respectively.

[0149] In yet another possible implementation, the first information indicates fourth resource configuration information; wherein the fourth resource configuration information is used to configure the Set A; and the fourth resource configuration information includes third information, the third information is used to indicate that part of the resources in the Set A are used as the Set B.

[0150] It can be understood that the Set B can be a subset or a full set of the Set A. In this case, the network device can first configure the Set A, and then can configure the Set B through subset selection. It should be noted that the subset selection mentioned here includes selecting all the Set A as the Set B, i.e., the case that the Set B and the Set A are the same.

[0151] Exemplarily, the fourth resource information can be CSI-ResourceConfig.

[0152] Exemplarily, the first information is CSI-ReportConfig, in which one CSI-ResourceConfigId corresponds to Set A. In other words, Set A can be configured as one resourcesForChannelMeasurement in one CSI-ReportConfig, corresponding to one CSI-ResourceConfigId.

[0153] In the CSI-ResourceConfig corresponding to the CSI-ResourceConfigId, one NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) is configured to correspond to one Set A. When considering multiple Set A configurations, multiple Set A can be configured as multiple NZP-CSI-RS-ResourceSetId and / or multiple CSI-SSB-ResourceSetId in one CSI-ResourceConfig.

[0154] In some embodiments, the third information indicates part of the resources in Set A through a resource index value.

[0155] In some embodiments, the third information can be configured in the NZP-CSI-RS-ResourceSet or CSI-SSB-ResourceSet corresponding to Set A.

[0156] It can be understood that the third information can directly use the index value of part of the resources in Set A to indicate part of the resources in Set A to indicate Set B.

[0157] Exemplarily, referring to the NZP-CSI-RS-ResourceSet IE shown in Table 2-3, one Set A is corresponded through the RRC parameter nzp-CSI-RS-Resources. Set B is corresponded through the newly added RRC parameter nzp-CSI-RS-Resources2. The nzp-CSI-RS-Resources2 can use part of the NZP-CSI-RS-ResourceId in Set A to indicate Set B.

[0158] Table 2-3 NZP-CSI-RS-ResourceSet IE

[0159] Exemplarily, refer to a CSI-SSB-ResourceSet IE shown in Table 2-4. Set A is corresponded by RRC parameter csi-SSB-ResourceList. Set B is corresponded by newly added RRC parameter csi-SSB-ResourceList2. Wherein, csi-SSB-ResourceList2 can use part of SSB-Index in Set A to indicate Set B.

[0160] Table 2-4 CSI-SSB-ResourceSet IE

[0161] In some other embodiments, the third information indicates part of resources in Set A by a bitmap. Wherein, the number of bits of the third information is the total number of resources in Set A. Each bit in the third information corresponds to a resource in Set A. When the value of a certain bit in the third information is a first value, it means that the resource in Set A corresponding to the bit is selected as a resource of Set B; when the value of a certain bit in the third information is a second value, it means that the resource in Set A corresponding to the bit is not selected as a resource of Set B.

[0162] Exemplarily, refer to a NZP-CSI-RS-ResourceSet IE shown in Table 2-5. Set A is corresponded by RRC parameter nzp-CSI-RS-Resources. Set B is corresponded by newly added RRC parameter nzp-CSI-RS-Resources2. If Set A is configured with 64 resources in a resource set, then nzp-CSI-RS-Resources2 can be configured as a 64-bit bitmap, {001001…100}, wherein “1” means that the corresponding resource in Set A is selected as a resource of Set B; “0” means that the corresponding resource in Set A is not selected as a resource of Set B.

[0163] Table 2-5 NZP-CSI-RS-ResourceSet IE

[0164] Exemplarily, referring to a CSI-SSB-ResourceSet IE shown in Table 2-6, a Set A is corresponding to by a RRC parameter csi-SSB-ResourceList. A Set B is corresponding to by a newly added RRC parameter csi-SSB-ResourceList2. Wherein, if 64 resources are configured in a resource set in the Set A, the nzp-CSI-RS-Resources2 can be configured as a long 64-bit bitmap {001001…100}, wherein “1” indicates that the corresponding resource in the Set A is selected as a resource of the Set B; “0” indicates that the corresponding resource in the Set A is not selected as a resource of the Set B.

[0165] Table 2-6 CSI-SSB-ResourceSet IE

[0166] In some embodiments, the network device can also indicate the configuration purpose of the Set A.

[0167] It should be noted that the above Set B and Set A can be applied to different purposes, i.e., model training, model inference and model monitoring. The configuration purpose of the Set B and Set A can be configured at different CSI framework granularity.

[0168] Exemplarily, the network device can indicate the configuration purpose of the Set B and Set A corresponding to the above CSI-ResourceConfigId in the first information (i.e., CSI-ReportConfig). If the configuration purpose of the Set B and Set A is the same, the CSI-ReportConfig can only include one Purpuse, which corresponds to the configuration purpose of the Set B and Set A. If the configuration purpose of the Set B and Set A is different, the CSI-ReportConfig can correspond to the configuration purpose of the Set B and the configuration purpose of the Set A through RRC parameters Purpuse and Purpuse2 respectively.

[0169] Exemplarily, the network device can also indicate the configuration purposes of Set B and Set A in the fourth resource configuration information (i.e., CSI-ResourceConfig) indicated by the first information. If the configuration purposes of Set B and Set A are the same, the CSI-ResourceConfig can only include one Purpuse, which corresponds to the configuration purposes of Set B and Set A. If the configuration purposes of Set B and Set A are different, the CSI-ResourceConfig can correspond to the configuration purposes of Set B and Set A respectively through RRC parameters Purpuse and Purpuse2.

[0170] Exemplarily, since Set B can be a subset or a full set of Set A. In this case, the configuration purposes of Set B and Set A can be indicated in the NZP-CSI-RS-ResourceSet IE or CSI-SSB-ResourceSet IE of Set A. If the configuration purposes of Set B and Set A are the same, the NZP-CSI-RS-ResourceSet IE or CSI-SSB-ResourceSet IE can only include one Purpuse, which corresponds to the configuration purposes of Set B and Set A. If the configuration purposes of Set B and Set A are different, referring to Tables 2-3 to 2-6, the NZP-CSI-RS-ResourceSet IE or CSI-SSB-ResourceSet IE can correspond to the configuration purposes of Set B and Set A respectively through RRC parameters Purpuse and Purpuse2.

[0171] Method #2: The first information is also used to configure a candidate parameter range, and each parameter in the candidate parameter range is used to characterize each resource in Set A.

[0172] As described above, for scenario 1, when the configuration purpose of Set A is inference, the terminal device does not need to actually measure the resources in Set A, and accordingly, the network device also does not need to actually transmit reference signals on the resources in Set A. The configuration of Set A under the inference purpose is only to let the AI / ML model on the terminal device side know the prediction range of the optimal beam, i.e., to select the optimal K beams from which beams.

[0173] Based on this, the network device can not configure the reference signal resources of the real Set A, but configure a candidate parameter range (which can also be called a virtual Set A range) as the selection range of the predicted beam. In this way, the signaling overhead of resource configuration can be reduced.

[0174] It should be noted that each parameter in the candidate parameter range can represent (or refer to) each resource in Set A.

[0175] For example, if the candidate range of the optimal beam is 64 beams, the network device can configure the candidate parameter range as [0, 63]. Correspondingly, the terminal device can predict the optimal beam from the virtual beam index range of 0 to 63.

[0176] For example, the parameter in the candidate parameter range can be a CSI-RS resource indicator (CRI) or an SSB resource indicator (SSBRI) in Set A, and the present application does not limit this.

[0177] It should be noted that the configuration of Set A described above can be configured at different CSI framework granularities.

[0178] For example, referring to a CSI-ReportConfig IE shown in Table 2-7, the original RRC parameter resourcesForChannelMeasurement in the CSI-ReportConfig can be used to indicate a CSI-ResourceConfigId corresponding to Set B. In addition, a new RRC parameter SetA-Range is added to indicate the candidate parameter range of Set A.

[0179] Table 2-7 CSI-ReportConfig IE

[0180] For example, referring to a CSI-ResourceConfig IE shown in Table 2-8, one Set B can be corresponded by nzp-CSI-RS-SSB. In addition, a new RRC parameter SetA-Range is added in the CSI-ResourceConfig IE to indicate the candidate parameter range of Set A.

[0181] Table 2-8 CSI-ResourceConfig IE

[0182] For example, referring to a NZP-CSI-RS-ResourceSet IE shown in Table 2-9, one Set B can be corresponded by the RRC parameter nzp-CSI-RS-Resources, and the candidate parameter range of Set A can be indicated by a new RRC parameter SetA-Range.

[0183] Table 2-9 NZP-CSI-RS-ResourceSet IE

[0184] Exemplarily, referring to a CSI-SSB-ResourceSet IE shown in Table 2-10, Set B can be indicated by the RRC parameter csi-SSB-ResourceList, and Set A can be indicated by the newly added RRC parameter SetA-Range.

[0185] Table 2-10 CSI-SSB-ResourceSet IE

[0186] It should be noted that the above Set B and Set A can be applied to different purposes, i.e., model training, model inference and model monitoring. The configuration purposes of the Set B and Set A can also be configured at different CSI framework granularities.

[0187] Exemplarily, the network device can indicate the configuration purposes of Set B and Set A corresponding to the CSI-ResourceConfigId in the CSI-ReportConfig. If the configuration purposes of Set B and Set A are the same, the CSI-ReportConfig can only include one Purpuse, which corresponds to the configuration purposes of Set B and Set A. If the configuration purposes of Set B and Set A are different, the CSI-ReportConfig can correspond to the configuration purposes of Set B and Set A by the RRC parameters Purpuse and Purpuse2 respectively.

[0188] Exemplarily, the network device can also indicate the configuration purposes of Set B and Set A in the CSI-ResourceConfig. If the configuration purposes of Set B and Set A are the same, the CSI-ResourceConfig can only include one Purpuse, which corresponds to the configuration purposes of Set B and Set A. If the configuration purposes of Set B and Set A are different, the CSI-ResourceConfig can correspond to the configuration purposes of Set B and Set A by the RRC parameters Purpuse and Purpuse2 respectively.

[0189] Exemplarily, the network device can indicate the configuration purposes of Set B and Set A in the NZP-CSI-RS-ResourceSet IE or the CSI-SSB-ResourceSet IE of Set B. If the configuration purposes of Set B and Set A are the same, the NZP-CSI-RS-ResourceSet IE or the CSI-SSB-ResourceSet IE can only include one purpose, which corresponds to the configuration purposes of Set B and Set A. If the configuration purposes of Set B and Set A are different, referring to Tables 2-3 to 2-6, the NZP-CSI-RS-ResourceSet IE or the CSI-SSB-ResourceSet IE can correspond to the configuration purposes of Set B and Set A through the RRC parameters Purpose and Purpose2 respectively.

[0190] Method #3: The network device can configure Set A for the terminal device by using another information different from the first information.

[0191] Referring to FIG. 6, the resource configuration method provided by the embodiments of the present application can further include the following steps:

[0192] S520, the network device sends fourth information, and correspondingly, the terminal device receives the fourth information; wherein the fourth information is used to configure Set A (i.e. the second resource set).

[0193] It can be understood that the network device can configure Set A for the terminal device by using the fourth information different from the first information used to configure Set B.

[0194] It should be noted that the fourth information is of the same type as the first information. Exemplarily, the first information and the fourth information can be CSI-ReportConfig.

[0195] Exemplarily, the network device can configure one CSI-ReportConfig in the CSI-MeasConfig to correspond to the resources of Set B, and configure another CSI-ReportConfig to correspond to the resources of Set A. It should be noted that the above multiple CSI-ReportConfig can be configured by using the original csi-ReportConfigToAddModList and csi-ReportConfigToReleaseList.

[0196] It should be noted that the network device can send the first information and the fourth information at the same time, or the network device can send the first information first and then send the fourth information. In addition, the network device can also send the fourth information first and then send the first information. The present embodiment does not limit this.

[0197] It should be understood that, since Set A and Set B are configured by different information, it is necessary to associate Set A and Set B configured by different information.

[0198] In some embodiments, the first information can include first resource association information, and the first resource association information is used to indicate that Set A configured by the fourth information is associated with Set B; and / or the fourth information includes second resource association information, and the second resource association information is used to indicate that Set B configured by the first information is associated with Set A.

[0199] It should be noted that the first resource association information can be an index value of the fourth information, or an index value of Set A configured by the fourth information. The second resource association information can be an index value of the first information, or an index value of Set B configured by the first information.

[0200] Exemplarily, refer to a CSI-ReportConfig IE shown in Table 2-11. The CSI-ReportConfig is used to configure Set B, specifically, the network device uses the original RRC parameter resourcesForChannelMeasurement in the CSI-ReportConfig to indicate a CSI-ResourceConfigId corresponding to Set B. Further, a new RRC parameter associatedReportConfigId is used in the CSI-ReportConfig to indicate a CSI-ReportConfigId corresponding to Set A. The original RRC parameter resourcesForChannelMeasurement can also be used in the CSI-ReportConfig of Set A to indicate a CSI-ResourceConfigId corresponding to Set A.

[0201] In addition, the CSI-ReportConfig IE shown in Table 2-11 can also be used to configure Set A. The new RRC parameter associatedReportConfigId is used in the CSI-ReportConfig IE to indicate a CSI-ReportConfigId corresponding to Set B.

[0202] Table 2-11 CSI-ReportConfig IE

[0203] It should be noted that when multiple groups of Set B and Set A need to be configured, configuration at different granularities can be considered. In some embodiments, one CSI-ReportConfig contains multiple CSI-ResourceConfigId; each associated CSI-ResourceConfig contains one NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId, thereby realizing the configuration of multiple Set B or Set A.

[0204] In some other embodiments, one CSI-ReportConfig contains one CSI-ResourceConfigId; the CSI-ResourceConfig contains multiple NZP-CSI-RS-ResourceSetId and / or multiple CSI-SSB-ResourceSetId; each NZP-CSI-RS-ResourceSet or CSI-SSB-ResourceSet corresponds to the configuration of one Set B or Set A.

[0205] It should be noted that the Set A configured in the fourth information can be applicable to different purposes, i.e., model training, model inference and model monitoring.

[0206] Based on this, the network device can indicate the configuration purpose of Set A in the fourth information, and the configuration purpose of Set A includes one or more of model training, model inference and model monitoring.

[0207] Exemplarily, referring to the CSI-ReportConfig IE shown in Table 2-11, the network device can add an RRC parameter purpuse to the CSI-ReportConfig IE, which can include at least three options, i.e., {training, inference and monitoring}.

[0208] In summary, the network device can configure Set A and Set B for the terminal device, so that the AI / ML model can determine the optimal beam from Set A based on the measurement result of Set B. In this way, the configuration manner of Set B can be determined, and the normal communication can be ensured.

[0209] It should be noted that the terminal device can support multiple AI / ML models. Different AI / ML models are applicable to different communication environments, and therefore the AI / ML models need to maintain consistency in different stages of model training, model inference, and model monitoring.

[0210] In view of the consistency of the AI / ML model in different stages, the network device can indicate the associated ID for the configured Set B and / or Set A.

[0211] It should be noted that in the model training stage, the network device can configure the terminal device with Set B and / or Set A with a purpose of training and the corresponding associated ID. Correspondingly, the terminal device can measure the Set B and / or Set A matched with the associated ID to complete data collection of the model. The terminal device provides the collected data set to the AI / ML model training entity (such as the terminal device, the server, or the network device) for model training to obtain the trained AI / ML model.

[0212] In the model inference stage, the network device can configure the terminal device with Set B and / or Set A with a purpose of inference and the corresponding associated ID. Correspondingly, the terminal device can be associated with the above trained AI / ML model according to the associated ID. Further, the terminal device can perform beam prediction based on the AI / ML model and the Set B and / or Set A.

[0213] In the model monitoring stage, the network device can configure the terminal device with Set B and / or Set A with a purpose of inference and the corresponding associated ID. When the performance of the AI / ML model is determined to have a problem based on the Set B and / or Set A, the terminal device can report the associated ID to indicate the AI / ML model having the problem.

[0214] It should be understood that the associated ID can be associated with Set B and / or Set A with different purposes. Among them, the Set B and / or Set A with the same associated ID can be applicable to the same AI / ML model.

[0215] In some embodiments, the data collection of model training is performed through high-layer signaling, such as MDT (Minimization of Drive Test) signaling of RRC layer, and then the associated ID needs to be configured in the high-layer signaling related to MDT.

[0216] In some embodiments, the data collection for model training is performed through a physical layer, and the network device needs to configure corresponding physical layer resources for the terminal device. The resources for training should include the associated ID.

[0217] In some embodiments, the associated ID can be included in the first information. Through the associated ID, Set B and / or Set A of different purposes can be associated.

[0218] For example, referring to the CSI-ReportConfig IE shown in Table 2-1, Table 2-7, and Table 2-11, the associated ID is added to the RRC parameter to indicate the associated identification information of Set B and / or Set A.

[0219] In addition, the associated ID can also be configured at other CSI framework granularity. For example, referring to the CSI-ResourceConfig IE shown in Table 2-2 and Table 2-8, the associated ID is added to the RRC parameter to indicate the associated identification information of Set B and / or Set A. Referring to the NZP-CSI-RS-ResourceSet IE shown in Table 2-3, Table 2-5, and Table 2-9, the associated ID is added to the RRC parameter to indicate the associated identification information of Set B and / or Set A. Referring to the CSI-SSB-ResourceSet IE shown in Table 2-4, Table 2-6, and Table 2-10, the associated ID is added to the RRC parameter to indicate the associated identification information of Set B and / or Set A.

[0220] In some embodiments, the associated identification information can be a model ID, a model function, or other parameters, which are not limited in the embodiments of the present application.

[0221] It should be noted that the configuration range of the associated ID needs to consider the related capabilities of the terminal device, such as whether the terminal device supports the AI / ML model capability and how many AI / ML models the terminal device can support. In the embodiments of the present application, the terminal device can report the capability information to the network device in advance to indicate the related capabilities of the terminal device. Correspondingly, the associated ID configured by the network device through the first information should be less than the maximum number MaxAssociatedID of the AI / ML model supported by the terminal device.

[0222] In some embodiments, if the first information carries the associated identification information, the method provided by the embodiments of the present application further includes the following steps:

[0223] The terminal device takes the other configuration purpose Set A configured in the fifth information as the current Set A; the associated identification information carried by the fifth information is the same as the associated identification information carried by the first information.

[0224] It can be understood that the network device can not configure any Set A information for the terminal device. The terminal device can determine the configuration of Set A according to the configured associated ID.

[0225] Specifically, the terminal device can consider that the AI / ML model uses consistent Set B and Set A when inferring as when training the model. Therefore, the terminal device can use the associated ID carried in the first information to find the configuration information carrying the associated ID consistent with the associated ID carried in the first information from other configuration information. Take the Set A configured by the configuration information as the Set A associated with the Set B configured by the first information. In this way, the configuration signaling can be reduced and the transmission efficiency can be improved.

[0226] It should be noted that Set B still needs to be configured to the terminal device, because the terminal device needs to measure Set B as the input when inferring the model.

[0227] The resource configuration method provided by the embodiments of the present application will be described below in combination with specific application scenarios. In the following, UE will be used to describe the terminal device, and NW will be used to describe the network device.

[0228] The following embodiments one to five are applicable to the scenario where AI / ML is deployed on the UE side.

[0229] Embodiment one

[0230] For the configuration of Set B, referring to one CSI-ReportConfig IE shown in Table 2-1, the NW can configure one CSI-ResourceConfigId under one CSI-ReportConfig to correspond to the measurement resource of Set B. For example, in the RRC IE, the original resourcesForChannelMeasurement can be reused.

[0231] Within this CSI-ResourceConfig, one NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) is configured to correspond to one measurement resource set for model input, i.e., Set B. Within this Set B, one NZP CSI-RS resource in NZP-CSI-RS-ResourceSet or one SSB resource in CSI-SSB-ResourceSet corresponds to one transmit spatial filter, i.e., one transmit beam.

[0232] In some other embodiments, within the CSI-ResourceConfig, multiple NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) are configured to correspond to multiple measurement resource sets for model input, i.e., multiple Set B. NW can use other signaling to select one applicable Set B. In some embodiments, NW can use additional RRC parameters to select one suitable Set B. In some other embodiments, NW can use MAC CE signaling to activate / deactivate one suitable Set B.

[0233] The configuration method of Set B is applicable to different purposes, i.e., model training, model inference and model performance monitoring. Referring to the CSI-ReportConfig IE shown in Table 2-1, a parameter purpuse can be added in the CSI-ReportConfig IE. The purpuse contains at least three options, i.e., {training, inference and monitoring}.

[0234] It should be noted that the reporting content of Set B, reportQuantity, can be selected as none.

[0235] For the configuration of Set A, referring to Table 2-1, another CSI-ResourceConfigId is configured to correspond to Set A resources under the same CSI-ReportConfig. For example, in the RRC IE, a resourcesForChannelMeasurement2 can be added.

[0236] Set A has different meanings in different configuration purposes. For example, when the configuration purpose of Set A is training, Set A represents the measurement and / or selection range of the optimal beam as the label; when the configuration purpose of Set A is inference, Set A represents the range of the optimal beam selected by the model; when the configuration purpose of Set A is performance monitoring, Set A represents the range of the optimal beam selected by the model for monitoring, that is, the UE selects the optimal beam from the Set A, and compares it with the model prediction result to determine the adaptation degree of the model work. Therefore, a new purpose 2 is added to the RRC parameter.

[0237] In the CSI-ResourceConfig, one NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) is configured to correspond to one set of model outputs, that is, Set A. Among them, one NZP CSI-RS resource in the NZP-CSI-RS-ResourceSet or one SSB resource in the CSI-SSB-ResourceSet corresponds to one transmit spatial filter in Set A, that is, a transmit beam.

[0238] Similarly, in some embodiments, multiple NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) are configured in the CSI-ResourceConfig to correspond to multiple Set A. The NW can use other signaling to select a suitable Set A. In some embodiments, the NW can use additional RRC parameters to select a suitable Set A. In some other embodiments, the NW can use MAC CE signaling to activate / deactivate a suitable Set A.

[0239] It should be noted that here Set A does not need to be measured by the UE in the purpose of inference, so here Set A is not called “measurement resource”, but only a resource set.

[0240] When Set A is configured for the purpose of inference, the UE only takes the resource configuration of Set A as a reference, and the model on the UE side selects the resource index and / or the corresponding link quality such as L1-RSRP corresponding to the optimal K downlink transmit beams, and reports it to the NW. At the same time, the NW also does not need to send Set A to the UE configured with the purpose of inference.

[0241] When Set A is configured for model training, UE needs to measure Set A in real and select the best K downlink transmit beams corresponding to the resource index and / or corresponding link quality, such as L1-RSRP, as the label of model training.

[0242] When Set A is configured for model monitoring, UE needs to measure Set A in real and select the best K downlink transmit beams corresponding to the resource index and / or corresponding link quality, such as L1-RSRP. Compare the real measurement results with the prediction results of the model, so as to judge the working degree of the model, thus playing the function of model monitoring.

[0243] It should be noted that in the configuration method of Set B and / or Set A in Embodiment One, the two CSI-ResourceConfigId for channel measurement under the same CSI-ReportConfig can be naturally associated together, that is, the association of resourcesForChannelMeasurement and resourcesForChannelMeasurement2 represents the association of Set B and Set A.

[0244] In some other embodiments, the reverse order can also be used, that is, the first CSI-ResourceConfigId represents the resource configuration of Set A; the second CSI-ResourceConfigId represents the configuration of Set B associated with Set A.

[0245] It should also be noted that in order to align Set B and Set A in the model training and inference stages, the associatedID or its variant form, such as model ID, can be configured in the RRC parameter in the configuration of the inference stage of the model. UE can understand that the configuration of Set B and Set A configured in the CSI-ReportConfig where the associatedID is located is adapted to an AI / ML model for beam prediction. The model is associated with the same associatedID in the training.

[0246] In some embodiments, the data collection of model training is performed through high-layer signaling, such as MDT (Minimization of Drive Test) signaling of RRC layer, and then the Associated ID or its variant form, such as model ID, needs to be configured in the high-layer signaling related to MDT.

[0247] In some embodiments, the data collection for model training is conducted through physical layer, then the NW needs to configure corresponding physical layer resources for the UE, the resources for training should contain Associated ID or its variant form, such as model ID, etc.

[0248] In addition, for the configuration range of associated ID, the NW needs to consider the relevant capabilities of the UE, i.e. how many associated identifiers the UE can support at most. The associated ID configured by the NW should be less than MaxAssociatedID.

[0249] Embodiment two

[0250] In this embodiment, one CSI-ResourceConfigId can be configured under one CSI-ReportConfig to correspond to the resource configuration of Set B and Set A.

[0251] Exemplarily, refer to one CSI-ResourceConfig IE shown in Table 2-2. In this CSI-ResourceConfig, one nzp-CSI-RS-SSB is configured, which can contain one NZP-CSI-RS-ResourceSetId (CSI-RS resource set) and / or one CSI-SSB-ResourceSetId (SSB resource set) to correspond to one Set B; in addition, another nzp-CSI-RS-SSB2 is configured, which can also contain one NZP-CSI-RS-ResourceSetId and / or one CSI-SSB-ResourceSetId to correspond to one Set A.

[0252] In some embodiments, considering more than one group of Set B and Set A resources, multiple NZP-CSI-RS-ResourceSetId (CSI-RS resource set) and / or CSI-SSB-ResourceSetId (SSB resource set) can be configured in one CSI-ResourceConfig to correspond to multiple Set B; in addition, multiple NZP-CSI-RS-ResourceSetId and / or CSI-SSB-ResourceSetId can be configured to correspond to multiple Set A.

[0253] Similarly, one NZP CSI-RS resource in NZP-CSI-RS-ResourceSet or one SSB resource in CSI-SSB-ResourceSet corresponds to one transmit spatial filter, i.e. transmit beam, in Set B or Set A.

[0254] In the embodiments of the present application, the configuration methods of Set B and Set A are applicable to different purposes, i.e., model training, model inference and model monitoring. However, it should be noted that when the configuration purpose of Set A is model inference, the UE does not need to actually measure the resources corresponding to the Set A.

[0255] In the embodiments of the present application, referring to Table 2-2, the configuration purposes purpose and purpose2 of resources can be added in the RRC layer.

[0256] Under the configuration method of Set B and / or Set A in Embodiment Two, one NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId (corresponding to Set B) and another NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId (corresponding to Set B) configured in CSI-ResourceConfig can be naturally associated.

[0257] In some embodiments, the first NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId represents the resource configuration of Set B; the second NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId represents the configuration of Set A. According to the order of configuration, Set B can be naturally associated with Set A. Of course, in other embodiments, the order of Set B and Set A can be reversed.

[0258] It should be noted that in order to align Set B and / or Set A in the model training and inference stages, in the configuration of the inference stage of the model, the associatedID or its variants, such as model ID, can be configured in the CSI-ReportConfig, and the position is the same level as the configuration of Set B or Set A.

[0259] The UE can understand that the configuration of Set B or Set A configured in the associatedID in the CSI-ReportConfig is adapted to an AI / ML model for beam prediction. The model is associated with the same associatedID when training.

[0260] For other contents related to associatedID, please refer to the description of Embodiment One, which will not be repeated here for brevity.

[0261] Embodiment Three

[0262] In the embodiments of the present application, one CSI-ReportConfig can be configured in one CSI-MeasConfig to correspond to the resources of Set B, and another associated CSI-ReportConfig is configured to correspond to the resources of Set A.

[0263] For example, referring to a CSI-ReportConfig IE shown in 2-11, the newly added RRC parameter associatedReportConfigId is used in the CSI-ReportConfig of Set B to indicate a CSI-ReportConfig to correspond to the associated Set A.

[0264] It should be noted that the plurality of CSI-ReportConfig can be configured by using the original csi-ReportConfigToAddModList and csi-ReportConfigToReleaseList.

[0265] In some other embodiments, the association relationship of Set B and Set A can be reversed, that is, another associatedReportConfigId is associated in the configured CSI-ReportConfig of Set A as Set B.

[0266] Similarly, the purpose of the resource reporting configuration in the CSI-ReportConfig can be configured, that is, whether it is used for model training, model inference or model monitoring.

[0267] It should be noted that one CSI-ReportConfig contains one CSI-ResourceConfigId; the associated CSI-ResourceConfig can contain one NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId; and the associated NZP-CSI-RS-ResourceSet or CSI-SSB-ResourceSet can correspond to one Set B or Set A.

[0268] When considering the need to configure multiple sets of Set B and Set A, it can be considered to configure at different granularities. In some embodiments, one CSI-ReportConfig contains multiple CSI-ResourceConfigId; each associated CSI-ResourceConfig contains one NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId, thereby realizing the configuration of multiple Set B or Set A.

[0269] In some other embodiments, one CSI-ReportConfig contains one CSI-ResourceConfigId; the CSI-ResourceConfig contains multiple NZP-CSI-RS-ResourceSetId and / or multiple CSI-SSB-ResourceSetId; each NZP-CSI-RS-ResourceSet or CSI-SSB-ResourceSet corresponds to the configuration of one Set B or Set A.

[0270] In the embodiments of the present application, the association relationship of Set B and Set A can be obtained directly from the associatedReportConfigId configured in the CSI-ReportConfig, that is, the UE considers that Set B and Set A come from two CSI-ReportConfig associated together.

[0271] It should be noted that, in order to align the Set B and / or Set A in the model training and inference stage, the associatedID or its variant form, such as model ID, can be configured in the CSI-ReportConfig in the configuration of the inference stage of the model, and the position is in the same level as the configuration of Set B or Set A.

[0272] The UE can understand that the configuration of Set B or Set A configured in the CSI-ReportConfig where the associatedID is located is adapted to an AI / ML model for beam prediction. The model is associated with the same associatedID in the training.

[0273] Other contents about associatedID, please refer to the description of embodiment one, for brevity, will not be repeated here.

[0274] Embodiment four

[0275] It should be noted that embodiment four is only applicable to the case where Set B is a subset or the whole set of Set A.

[0276] It can be understood that if Set B is a subset or a full set of Set A, from the perspective of signaling design, Set A is configured first and then an associated Set B is configured. The associated Set B can be configured by subset selection. The subset selection herein includes selecting all of Set A as Set B, i.e., the case that Set B is the same as Set A.

[0277] In some embodiments, Set A can be configured as one NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId in one CSI-ResourceConfig. When considering multiple Set A configurations, multiple Set A can be configured as multiple NZP-CSI-RS-ResourceSetId and / or multiple CSI-SSB-ResourceSetId in one CSI-ResourceConfig.

[0278] In some other embodiments, Set A can be configured as one resourcesForChannelMeasurement in one CSI-ReportConfig, corresponding to one CSI-ResourceConfigId. The CSI-ResourceConfig can contain one or more NZP-CSI-RS-ResourceSetId or CSI-SSB-ResourceSetId.

[0279] Correspondingly, the configuration of the associated Set B is subset selection based on Set A.

[0280] In some embodiments, refer to one NZP-CSI-RS-ResourceSet IE shown in Table 2-5 and one CSI-SSB-ResourceSet IE shown in Table 2-6. The Set B selection information can be a bitmap. Exemplarily, if Set A is configured with 64 resources in one resource set, Set B can be configured as a 64-bit bitmap, {001001…100}, wherein “1” indicates that the corresponding resource in Set A is selected as a resource of Set B; “0” indicates that the corresponding resource in Set A is not selected as a resource of Set B.

[0281] In some other embodiments, refer to one NZP-CSI-RS-ResourceSet IE shown in Table 2-3, and one CSI-SSB-ResourceSet IE shown in Table 2-4. The Set B selection information can also be a string of resource indices, such as NZP-CSI-RS-ResourceId or SSB-Index directly. The string of resource indices is used to form a resource set, i.e. Set B.

[0282] In this embodiment, because Set B is a subset or the whole set of Set A, the association between Set B and Set A can be reflected by the way of subset selection.

[0283] It should be noted that, in order to align the Set B and / or Set A in the model training and inference stage, the associatedID or its variants, such as model ID, can be configured in the CSI-ReportConfig in the configuration of the inference stage of the model, and the location is in the same level as the configuration of Set B or Set A.

[0284] The UE can understand that the configuration of Set B or Set A configured in the CSI-ReportConfig where the associatedID is located is adapted to an AI / ML model for beam prediction. The model is associated with the same associatedID in the training.

[0285] Other contents about associatedID, please refer to the description of embodiment one, for brevity, will not be repeated here.

[0286] Embodiment five

[0287] As mentioned before, when the purpose of the configuration of Set A is inference, the UE does not need to measure the reference signal resources in Set A in reality. The NW also does not need to transmit the downlink reference signal resources in Set A in reality. The configuration of Set A for inference purpose is only to let the model on the UE side clear the prediction range of the optimal beam, i.e. to select the optimal K beams from which downlink beams.

[0288] In some embodiments, when the model at the UE side has completed training, the selection of the optimal beam can be understood as a multi-classification problem. Exemplarily, if the candidate range of the optimal beam is 64 downlink transmission beams, the NW does not need to configure a CSI resource set or a SSB resource set, but configure a virtual Set A range as the selection range of the predicted beam. The UE predicts the optimal beam from the range of 0 to 63 virtual beam indexes. Of course, in some embodiments, the beam index can be predicted based on CRI (CSI-RS resource indication) or SSBRI (SSB resource indication). The NW only needs to configure an abstract prediction range.

[0289] For the configuration of the Set A, it can be configured at different CSI framework granularity. Refer to the RRC IEs shown in Tables 2-7 to 2-10.

[0290] In addition, in other embodiments, even no Set A information can be configured. The UE determines the configuration of Set B and Set A according to the configured associatedID, and the UE considers that the model uses the same Set B and Set A in inference as in model training. It should be noted that Set B still needs to be configured to the UE, because the UE needs to measure Set B as the input in model inference.

[0291] Embodiments six to nine below are applicable to the scenario where AI / ML is deployed at the network device side.

[0292] Embodiment six

[0293] For model inference, the UE only needs to be configured with Set B, and the UE completes the measurement of Set B and reports the measurement result to the NW. The NW takes the Set B measurement result reported by the UE as the input of the model, and infers the optimal K transmission beams and the corresponding link quality from Set A. In the inference stage, Set A belongs to the implementation or algorithm of the NW, and does not need to be specified.

[0294] In addition, since the configuration of Set A is not required, the association between Set B and Set A, and the consistency problem of training and inference do not need to be considered here. The existing CSI framework in the NR protocol can support the configuration of a measurement resource set Set B.

[0295] Specifically, under one CSI-ReportConfig, one CSI-ResourceConfigId is configured to correspond to the measurement resource of Set B. Within the CSI-ResourceConfig, one NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) is configured to correspond to one Set B. Among them, one NZP CSI-RS resource in the NZP-CSI-RS-ResourceSet or one SSB resource contained in the CSI-SSB-ResourceSet corresponds to one transmit spatial filter, i.e., one transmit beam, in the Set B.

[0296] In some other embodiments, within the CSI-ResourceConfig, multiple NZP-CSI-RS-ResourceSetId (CSI-RS resource set) or CSI-SSB-ResourceSetId (SSB resource set) are configured to correspond to multiple Set B.

[0297] For the monitoring and training of the model, the UE needs to be configured with Set B and Set A. Therefore, reference can be made to the content described in Embodiment One.

[0298] Embodiment Seven

[0299] For model inference, the existing CSI framework in the NR protocol can support the configuration of one measurement resource set Set B.

[0300] For model training and monitoring, reference can be made to the content described in Embodiment Two.

[0301] Embodiment Eight

[0302] For model inference, the existing CSI framework in the NR protocol can support the configuration of one measurement resource set Set B.

[0303] For model training and monitoring, reference can be made to the content described in Embodiment Three.

[0304] Embodiment Nine

[0305] For model inference, the existing CSI framework in the NR protocol can support the configuration of one measurement resource set Set B.

[0306] For model training and monitoring, reference can be made to the content described in Embodiment Four.

[0307] In summary, the resource configuration method provided in the embodiments of the present application can be used in the existing CSI framework of NR, and various configuration methods of Set B and Set A are designed for different configuration purposes (model training, inference and performance monitoring), which solves the association between Set B and Set A and considers the consistency of the model in the training and inference stages.

[0308] The preferred embodiments of the present application are described in detail above with reference to the drawings, but the present application is not limited to the specific details of the above-described embodiments. Within the technical concept of the present application, various simple modifications can be made to the technical solutions of the present application, and these simple modifications all belong to the protection scope of the present application. For example, in the above-described specific embodiments, various specific technical features described in the embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, various possible combination manners are not described again in the present application. For another example, various different embodiments of the present application can also be combined in any manner, as long as it does not deviate from the idea of the present application, and it should also be considered as disclosed in the present application. For another example, under the premise of no conflict, each embodiment described in the present application and / or technical features in each embodiment can be combined with any prior art, and the technical solutions obtained after combination should also fall within the protection scope of the present application.

[0309] It should also be understood that in various method embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. In addition, in the embodiments of the present application, the terms "downlink", "uplink" and "sidelink" are used to represent the transmission direction of signals or data, wherein "downlink" is used to represent the transmission direction of signals or data as the first direction from the station to the user equipment of the cell, "uplink" is used to represent the transmission direction of signals or data as the second direction from the user equipment of the cell to the station, and "sidelink" is used to represent the transmission direction of signals or data as the third direction from the user equipment 1 to the user equipment 2. For example, "downlink signal" represents that the transmission direction of the signal is the first direction. In addition, in the embodiments of the present application, the term "and / or" is only used to describe the association relationship of the associated objects, which means that there can be three relationships. Specifically, A and / or B can represent three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are in an "or" relationship.

[0310] Fig. 7 is a structural composition schematic diagram of a communication device provided by the embodiments of the present application, which is applied to a terminal device, as shown in Fig. 7, the communication device comprises:

[0311] The receiving unit 710 is configured to receive first information, the first information being used for configuring a first resource set, each resource in the first resource set corresponding to a measurement result used for an artificial intelligence or machine learning, AI / ML, model to determine a target resource in a second resource set, a spatial filter associated with the target resource being used for downlink transmission between the terminal device and a network device.

[0312] In some embodiments, the first information comprises a configuration purpose of the first resource set; the configuration purpose comprises one or more of the following:

[0313] model training;

[0314] model inference;

[0315] model monitoring.

[0316] In some embodiments, the first information is further used for configuring the second resource set, the first resource set configured by the first information being associated with the second resource set configured by the first information.

[0317] In some embodiments, the first information indicates first resource configuration information and second resource configuration information;

[0318] the first resource configuration information being used for configuring the first resource set, and the second resource configuration information being used for configuring the second resource set.

[0319] In some embodiments, the first resource configuration information configures a plurality of candidate first resource sets, the first resource set being any one of the plurality of candidate first resource sets;

[0320] and / or,

[0321] the second resource configuration information configures a plurality of candidate second resource sets, the second resource set being any one of the plurality of candidate second resource sets.

[0322] In some embodiments, the receiving unit 710 is further configured to receive second information, the second information being used for indicating the first resource set from the plurality of candidate first resource sets, and / or being used for indicating the second resource set from the plurality of candidate second resource sets.

[0323] In some embodiments, the second information comprises one or more of the following:

[0324] RRC signaling;

[0325] MAC CE signaling,

[0326] DCI signaling.

[0327] In some embodiments, the first information indicates third resource configuration information; the third resource configuration information is used for configuring the first resource set and the second resource set.

[0328] In some embodiments, the first information indicates fourth resource configuration information; the fourth resource configuration information is used for configuring the second resource set.

[0329] The fourth resource configuration information includes third information, the third information is used for indicating part of resources in the second resource set as the first resource set.

[0330] In some embodiments, the third information indicates part of resources in the second resource set by a resource index value, or the third information indicates part of resources in the second resource set by a bit map.

[0331] In some embodiments, one or more of the first resource configuration information, the second resource configuration information, the third resource configuration information, and the fourth resource configuration information is channel state information, CSI, resource configuration information, CSI-ResourceConfig.

[0332] In some embodiments, the first information is also used for configuring a candidate parameter range, each parameter in the candidate parameter range is used for characterizing each resource in the second resource set.

[0333] In some embodiments, the first information further includes a configuration purpose of the second resource set, the configuration purpose includes one or more of the following:

[0334] Model training;

[0335] Model inference;

[0336] Model monitoring.

[0337] In some embodiments, the receiving unit 710 is further configured to receive fourth information, the fourth information is used for configuring the second resource set.

[0338] In some embodiments, the first information includes first resource association information, the first resource association information is used for indicating that the second resource set configured by the fourth information is associated with the first resource set.

[0339] and / or,

[0340] The fourth information includes second resource association information, the second resource association information is used for indicating that the first resource set configured by the first information is associated with the second resource set.

[0341] In some embodiments, the fourth information further includes the configuration purpose of the second resource set, the configuration purpose including one or more of the following:

[0342] Model training;

[0343] Model reasoning;

[0344] Model monitoring.

[0345] In some embodiments, the first information further includes association identification information, which is used to associate a first resource set with different configuration purposes, and / or to associate a second resource set with different configuration purposes.

[0346] In some embodiments, the first information carries associated identification information; the resource configuration device further includes a processing unit configured to use a second resource set with other configuration purposes configured in the fifth information as the second resource set; the associated identification information carried by the fifth information is the same as the associated identification information carried by the first information.

[0347] Figure 8 is a schematic diagram of the structure of a communication device provided in an embodiment of this application, applied to a network device. As shown in Figure 8, the communication device includes:

[0348] The sending unit 810 is configured to send first information, which is used to configure a first resource set. The measurement results corresponding to each resource in the first resource set are used by the AI / ML model to determine the target resource in the second resource set. The spatial filter associated with the target resource is used for downlink transmission between the terminal device and the network device.

[0349] In some embodiments, the first information includes the configuration purpose of the first resource set; the configuration purpose includes one or more of the following:

[0350] Model training;

[0351] Model reasoning;

[0352] Model monitoring.

[0353] In some embodiments, the first information is further used to configure the second resource set, wherein the first resource set configured by the first information is associated with the second resource set configured by the first information.

[0354] In some embodiments, the first information indicates first resource configuration information and second resource configuration information;

[0355] The first resource configuration information is used to configure the first resource set, and the second resource configuration information is used to configure the second resource set.

[0356] In some embodiments, the first resource configuration information configures a plurality of candidate first resource sets, wherein the first resource set is any one of the plurality of candidate first resource sets;

[0357] And / or,

[0358] The second resource configuration information configures multiple candidate second resource sets, where the second resource set is any one of the multiple candidate second resource sets.

[0359] In some embodiments, the sending unit 810 is further configured to send second information, the second information being used to indicate the first resource set from the plurality of candidate first resource sets, and / or to indicate the second resource set from the plurality of candidate second resource sets.

[0360] In some embodiments, the second information is one or more of the following:

[0361] RRC signaling;

[0362] MAC CE signaling,

[0363] DCI signaling.

[0364] In some embodiments, the first information indicates third resource configuration information; the third resource configuration information is used to configure the first resource set and the second resource set.

[0365] In some embodiments, the first information indicates fourth resource configuration information; the fourth resource configuration information is used to configure the second resource set.

[0366] The fourth resource configuration information includes third information, which is used to indicate that a portion of the resources in the second resource set should be used as the first resource set.

[0367] In some embodiments, the third information indicates a portion of the resources in the second resource set via a resource index value, or the third information indicates a portion of the resources in the second resource set via a bitmap.

[0368] In some embodiments, one or more of the first resource configuration information, the second resource configuration information, the third resource configuration information, and the fourth resource configuration information are channel state information (CSI) and resource configuration information (CSI-ResourceConfig).

[0369] In some embodiments, the first information is further used to configure a range of candidate parameters, wherein each parameter in the range of candidate parameters is used to characterize a resource in the second resource set.

[0370] In some embodiments, the first information further includes the configuration purpose of the second resource set, the configuration purpose including one or more of the following:

[0371] Model training;

[0372] Model reasoning;

[0373] Model monitoring.

[0374] In some embodiments, the sending unit 810 is further configured to send fourth information, the fourth information being used to configure the second resource set.

[0375] In some embodiments, the first information includes first resource association information, which is used to indicate that the second resource set configured by the fourth information is associated with the first resource set.

[0376] And / or,

[0377] The fourth information includes second resource association information, which is used to indicate that the first resource set configured by the first information is associated with the second resource set.

[0378] In some embodiments, the fourth information further includes the configuration purpose of the second resource set, the configuration purpose including one or more of the following:

[0379] Model training;

[0380] Model reasoning;

[0381] Model monitoring.

[0382] In some embodiments, the first information further includes association identification information, which is used to associate a first resource set with different configuration purposes, and / or to associate a second resource set with different configuration purposes.

[0383] Those skilled in the art should understand that the description of the communication device in the embodiments of this application can be understood with reference to the description of the communication method in the embodiments of this application.

[0384] Figure 9 is a schematic structural diagram of a communication device 900 provided in an embodiment of this application. This communication device can be a terminal device or a network device. The communication device 900 shown in Figure 9 includes a processor 910, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0385] Optionally, as shown in FIG9, the communication device 900 may further include a memory 920. The processor 910 may retrieve and run computer programs from the memory 920 to implement the methods described in the embodiments of this application.

[0386] The memory 920 can be a separate device independent of the processor 910, or it can be integrated into the processor 910.

[0387] Optionally, as shown in FIG9, the communication device 900 may further include a transceiver 930, and the processor 910 may control the transceiver 930 to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices.

[0388] The transceiver 930 may include a transmitter and a receiver. The transceiver 930 may further include antennas, and the number of antennas may be one or more.

[0389] Optionally, the communication device 900 may specifically be a network device in the embodiments of this application, and the communication device 900 may implement the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0390] Optionally, the communication device 900 may specifically be a mobile terminal / terminal device in the embodiments of this application, and the communication device 900 may implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0391] Figure 10 is a schematic structural diagram of a chip according to an embodiment of this application. The chip 1000 shown in Figure 10 includes a processor 1010, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0392] Optionally, as shown in FIG10, chip 1000 may further include memory 1020. Processor 1010 can call and run computer programs from memory 1020 to implement the methods in the embodiments of this application.

[0393] The memory 1020 can be a separate device independent of the processor 1010, or it can be integrated into the processor 1010.

[0394] Optionally, the chip 1000 may also include an input interface 1030. The processor 1010 can control the input interface 1030 to communicate with other devices or chips, specifically, to acquire information or data sent by other devices or chips.

[0395] Optionally, the chip 1000 may also include an output interface 1040. The processor 1010 can control the output interface 1040 to communicate with other devices or chips, specifically, to output information or data to other devices or chips.

[0396] Optionally, the chip can be applied to the network device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0397] Optionally, the chip can be applied to the mobile terminal / terminal device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0398] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0399] This application also provides a computer storage medium storing one or more programs, which can be executed by one or more processors to implement the methods in this application.

[0400] Figure 11 is a schematic block diagram of a communication system 1100 provided in an embodiment of this application. As shown in Figure 11, the communication system 1100 includes a terminal device 1110 and a network device 1120.

[0401] The terminal device 1110 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the network device 1120 can be used to implement the corresponding functions implemented by the network device in the above method. For the sake of brevity, these will not be elaborated here.

[0402] It should be understood that the processor in the embodiments of this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0403] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0404] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0405] This application also provides a computer-readable storage medium for storing computer programs.

[0406] Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of this application, and the computer program causes the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0407] Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device in the embodiments of this application, and the computer program causes the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0408] This application also provides a computer program product, including computer program instructions.

[0409] Optionally, the computer program product can be applied to the network device in the embodiments of this application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, they will not be described in detail here.

[0410] Optionally, the computer program product can be applied to the mobile terminal / terminal device in the embodiments of this application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, they will not be described in detail here.

[0411] This application also provides a computer program.

[0412] Optionally, the computer program can be applied to the network device in the embodiments of this application. When the computer program is run on the computer, it causes the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0413] Optionally, the computer program can be applied to the mobile terminal / terminal device in the embodiments of this application. When the computer program is run on a computer, it causes the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0414] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software 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.

[0415] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0416] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0417] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0418] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0419] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0420] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of resource configuration, the method comprising: receiving, by a terminal device, first information, the first information being used for configuring a first set of resources, a measurement result corresponding to each resource in the first set of resources being used for an artificial intelligence or machine learning, AI / ML, model to determine a target resource in a second set of resources, a spatial filter associated with the target resource being used for downlink transmission between the terminal device and a network device.

2. The method of claim 1, wherein, the first information comprising a configuration purpose of the first set of resources, the configuration purpose comprising one or more of: model training; model inference; model monitoring.

3. The method of claim 1 or 2, wherein, the first information being further used for configuring the second set of resources, the first set of resources configured by the first information being associated with the second set of resources configured by the first information.

4. The method of claim 3, wherein, the first information indicating first resource configuration information and second resource configuration information; the first resource configuration information being used for configuring the first set of resources, the second resource configuration information being used for configuring the second set of resources.

5. The method of claim 4, wherein, further comprising: the first resource configuration information configuring a plurality of candidate first sets of resources, the first set of resources being any one of the plurality of candidate first sets of resources; and / or, the second resource configuration information configuring a plurality of candidate second sets of resources, the second set of resources being any one of the plurality of candidate second sets of resources. 6.The method of claim 5, wherein: the terminal device receives second information, the second information being used for indicating the first set of resources from the plurality of candidate first sets of resources and / or being used for indicating the second set of resources from the plurality of candidate second sets of resources.

7. The method of claim 6, wherein, the second information being one or more of: RRC signaling; MAC CE signaling, DCI signaling.

8. The method of claim 3, wherein, the first information indicating third resource configuration information, the third resource configuration information being used for configuring the first set of resources and the second set of resources.

9. The method of claim 3, wherein, the first information indicating fourth resource configuration information, the fourth resource configuration information being used for configuring the second set of resources; the fourth resource configuration information comprising third information, the third information being used for indicating part of the second set of resources as the first set of resources.

10. The method of claim 9, wherein, the third information indicating the part of the second set of resources by a resource index value or the third information indicating the part of the second set of resources by a bitmap.

11. The method according to any one of claims 4 to 10, wherein, one or more of the first resource configuration information, the second resource configuration information, the third resource configuration information, and the fourth resource configuration information being channel state information, CSI, resource configuration information, CSI-ResourceConfig.

12. The method of claim 1 or 2, wherein, the first information being further used for configuring a candidate parameter range, each parameter in the candidate parameter range being used for characterizing each resource in the second set of resources.

13. The method according to any one of claims 3 to 12, wherein, the first information further comprising a configuration purpose of the second set of resources, the configuration purpose comprising one or more of: model training; model inference; model monitoring.

14. The method of claim 1 or 2, wherein, further comprising: the terminal device receiving fourth information, the fourth information being used for configuring the second set of resources.

15. The method of claim 14, wherein, further comprising: The first information includes first resource association information, the first resource association information being used to indicate that the second resource set configured by the fourth information is associated with the first resource set; and / or, The fourth information includes second resource association information, the second resource association information being used to indicate that the first resource set configured by the first information is associated with the second resource set.

16. The method of claim 14 or 15, wherein, The fourth information further includes a configuration purpose of the second resource set, the configuration purpose including one or more of the following: model training; model inference; model monitoring.

17. The method of any one of claims 1 to 16, wherein, The first information further includes association identification information, the association identification information being used to associate the first resource set of different configuration purposes, and / or, being used to associate the second resource set of different configuration purposes.

18. The method of claim 1 or 2, wherein, The first information carries the association identification information, and the method further includes: The terminal device takes the second resource set of other configuration purposes configured in the fifth information as the second resource set; the association identification information carried by the fifth information is the same as the association identification information carried by the first information.

19. A resource configuration method, the method comprising: a network device sending first information, the first information being used to configure a first resource set, a measurement result corresponding to each resource in the first resource set being used for an AI / ML model to determine a target resource in a second resource set, a spatial filter associated with the target resource being used for downlink transmission between the terminal device and the network device.

20. The method of claim 19, wherein, The first information includes a configuration purpose of the first resource set; the configuration purpose includes one or more of the following: model training; model inference; model monitoring.

21. The method of claim 19 or 20, wherein, The first information is further used to configure the second resource set, the first resource set configured by the first information being associated with the second resource set configured by the first information.

22. The method of claim 21, wherein, The first information indicates first resource configuration information and second resource configuration information; The first resource configuration information is used to configure the first resource set, and the second resource configuration information is used to configure the second resource set.

23. The method of claim 22, wherein, Further comprising: The first resource configuration information configures a plurality of candidate first resource sets, the first resource set being any one of the plurality of candidate first resource sets; and / or, The second resource configuration information configures a plurality of candidate second resource sets, the second resource set being any one of the plurality of candidate second resource sets.

24. The method of claim 24, wherein, Further comprising: The network device sends second information, the second information being used to indicate the first resource set from the plurality of candidate first resource sets, and / or, being used to indicate the second resource set from the plurality of candidate second resource sets.

25. The method of claim 24, wherein, The second information is one or more of the following: RRC signaling; MAC CE signaling, DCI signaling.

26. The method of claim 21, wherein, The first information indicates third resource configuration information; the third resource configuration information is used to configure the first resource set and the second resource set.

27. The method of claim 21, wherein, The first information indicates fourth resource configuration information; the fourth resource configuration information is used to configure the second resource set; The fourth resource configuration information includes third information, the third information being used to indicate part of the resources in the second resource set as the first resource set.

28. The method of claim 27, wherein, The third information indicates part of the second resource set by a resource index value, or the third information indicates part of the second resource set by a bit map.

29. The method of any one of claims 22 to 28, wherein, One or more of the first resource configuration information, the second resource configuration information, the third resource configuration information, and the fourth resource configuration information is channel state information (CSI) resource configuration information (CSI-ResourceConfig).

30. The method of claim 19 or 20, wherein, The first information is further used to configure a candidate parameter range, and each parameter in the candidate parameter range is used to characterize each resource in the second resource set.

31. The method of any one of claims 21 to 30, wherein, The first information further includes a configuration purpose of the second resource set, and the configuration purpose includes one or more of the following: model training; model inference; model monitoring.

32. The method of claim 19 or 20, wherein, Further comprising: The network device sends fourth information, and the fourth information is used to configure the second resource set.

33. The method of claim 32, wherein, Further comprising: The first information includes first resource association information, and the first resource association information is used to indicate that the second resource set configured by the fourth information is associated with the first resource set; and / or, The fourth information includes second resource association information, and the second resource association information is used to indicate that the first resource set configured by the first information is associated with the second resource set.

34. The method of claim 32 or 33, wherein, The fourth information further includes a configuration purpose of the second resource set, and the configuration purpose includes one or more of the following: model training; model inference; model monitoring.

35. The method of any one of claims 19 to 34, wherein, The first information further includes association identification information, and the association identification information is used to associate the first resource sets of different configuration purposes and / or is used to associate the second resource sets of different configuration purposes.

36. A resource configuration apparatus applied to a terminal device, the apparatus comprising: a receiving unit configured to receive first information, the first information being used to configure a first resource set, and a measurement result corresponding to each resource in the first resource set being used for an artificial intelligence or machine learning (AI / ML) model to determine a target resource in a second resource set, and a spatial filter associated with the target resource being used for downlink transmission between the terminal device and a network device.

37. A resource configuration apparatus applied to a network device, the apparatus comprising: a sending unit configured to send first information, the first information being used to configure a first resource set, and a measurement result corresponding to each resource in the first resource set being used for an AI / ML model to determine a target resource in a second resource set, and a spatial filter associated with the target resource being used for downlink transmission between the terminal device and the network device.

38. A terminal device comprising: a memory, a processor, and a transceiver, the transceiver being used to implement communication with the network device; the memory stores a computer program capable of running on the processor, the processor, in combination with the transceiver, implements the method according to any one of claims 1 to 18 when executing the program.

39. A network device comprising: a memory, a processor, and a transceiver, the transceiver being used to implement communication with the terminal device; the memory stores a computer program capable of running on the processor, the processor, in combination with the transceiver, implements the method according to any one of claims 19 to 35 when executing the program.

40. A computer storage medium having stored thereon one or more programs, the one or more programs being executable by one or more processors to implement the method of any of claims 1-18, or 19-35.

41. A chip comprising: A processor configured to invoke and run a computer program from a memory, such that a device in which the chip is installed performs the method of any of claims 1-18, or 19-35.

42. A computer program product comprising a computer storage medium having stored thereon a computer program comprising instructions executable by at least one processor to implement the method of any of claims 1-18, or 19-35 when the instructions are executed by the at least one processor.

43. A computer program causing a computer to perform the method of any of claims 1-18, or 19-35.

Images