Method performed by a user equipment and user equipment

Abstract

The application provides a method executed by a user equipment and the user equipment. The method comprises the following steps: receiving first configuration information and second configuration information sent by a base station, wherein the first configuration information is channel state indication information (CSI) reporting configuration information, and the second configuration information is configuration information for reporting artificial intelligence / machine learning (AI / ML) model monitoring information; performing CSI reporting according to at least the first configuration information; and performing monitoring of the AI / ML model according to at least the second configuration information.

Description

Technical Field

[0001] This invention relates to the field of wireless communication technology, and more particularly to a method performed by a user equipment and a corresponding user equipment. Background Technology

[0002] In Rel-15NR, user equipment (UE) can perform various downlink channel measurements and channel state information (CSI) reports based on network configuration information. The measurement configuration and corresponding reporting methods are configured through a reporting configuration, represented in the 3GPP protocol by the RRC parameter CSI-ReportConfig. Specifically, the reporting configuration includes the following three aspects:

[0003] 1) The number of measurements reported, i.e. how many measurement items need to be reported to the network.

[0004] A measurement report needs to explicitly configure which measurement items the user equipment (UE) needs to report. For example, a measurement report may include three items: Channel Quality Indicator (CQI), Channel Rank Indicator (RI), and Precoder Matrix Indicator (PMI), collectively referred to as channel state information. A measurement report may also include only one item, such as reporting the received signal strength, called Reference Signal Received Power (RSRP). RSRP is also a critical measurement, typically used in higher-level Radio Resource Management (RRM). In NR, RSRP reporting is introduced at the physical layer for Beam Management (BM), known as L1-RSRP.

[0005] 2) The object of measurement, i.e., the physical resources of downlink measurement.

[0006] In the configuration information of the RRC parameter CSI-ReportConfig, the reporting configuration is associated with one or more resource sets. Specifically, a measurement resource configuration is associated with one or more Non-Zero Power CSI Reference Signal (NZP-CSI RS) resource sets. The user equipment uses these NZP-CSI RS resource sets to measure the characteristics of the downlink channel. An NZP-CSI RS resource set may include a set of configured CSI-RS or a set of Synchronization Signal Blocks (SSBs). For example, L1-RSRP measurement reporting for beam management is performed on a set of SSBs or a set of NZP-CSI RSs.

[0007] 3) The reporting method, i.e., which uplink physical channel is used to carry CSI reporting.

[0008] In Rel-15NR, CSI reporting for user equipment can be divided into three types: periodic CSI report, semi-persistent CSI report, and aperiodic CSI report.

[0009] For periodic CSI reporting, the network needs to be configured with a specific reporting period. Periodic CSI reporting is carried out through the Physical Uplink Control Channel (PUCCH). Therefore, for periodic CSI reporting, the resource configuration information needs to be configured with the periodic PUCCH resources used for reporting.

[0010] For semi-persistent CSI reporting, the network activates or deactivates the corresponding CSI reporting via MAC CE. Semi-persistent CSI reporting can be carried through the allocated PUCCH or the allocated Physical Uplink Shared Channel (PUSCH). PUSCH is often used to carry semi-persistent CSI reports with larger amounts of information.

[0011] Aperiodic CSI reporting is triggered via downlink control information (DCI). Specifically, it is indicated by the CSI request field in the uplink scheduling authorization. This field contains a maximum of 6 bits, each combination corresponding to a configured aperiodic CSI report, meaning a maximum of 63 different aperiodic CSI reports can be triggered (all bits set to 0 indicate no aperiodic CSI report is triggered). Aperiodic CSI reports are carried via PUSCH.

[0012] At the 3GPP RAN#94e plenary meeting in December 2021, research on the application of Artificial Intelligence / Machine Learning (AI / ML) in the NR air interface was approved (see Non-Patent Literature 1). The use cases for this research project mainly include the following:

[0013] 1) Enhanced beam management, such as beam prediction in the time domain, reduction of overhead and latency in the spatial domain, and improved beam selection accuracy; the UE reports the Layer 1 Reference Signal Received Power (RSRP) to the base station, and the base station performs beam management based on the reported information;

[0014] 2) Positioning accuracy enhancement in different scenarios, such as scenarios with dense non-line of sight (NLOS).

[0015] The present disclosure provides a method for user equipment (UE) to perform AI / ML model monitoring in the context of enhanced NR beam management.

[0016] Existing technical documents

[0017] Non-patent literature

[0018] Non-patent literature 1: RP-234039, New WID on AI / ML for NR Air Interface, section 4.1 Summary of the Invention

[0019] To address at least some of the aforementioned problems, the present invention provides a method and a user equipment (UE) that are executed by the UE, which can ensure that the predicted L1-RSRP and the measured L1-RSRP used for model monitoring correspond to the same time instance, thereby effectively improving the accuracy of model monitoring and thus improving the accuracy of AI / ML model prediction.

[0020] According to the present invention, a method executed by a user equipment is proposed, comprising the following steps: receiving first configuration information and second configuration information sent by a base station, wherein the first configuration information is channel state indication information (CSI) reporting configuration information and the second configuration information is configuration information for reporting artificial intelligence / machine learning (AI / ML) model monitoring information; performing CSI reporting at least according to the first configuration information; and performing AI / ML model monitoring at least according to the second configuration information.

[0021] Preferably, the first configuration information includes at least one of the following configuration information: AI / ML related configuration information; reference signal configuration information for beam management reporting based on the configuration of a first reference signal for channel measurement, wherein the first reference signal for channel measurement is a Channel State Information Reference Signal (CSI-RS) resource set or a Synchronization Signal Block (SSB) resource set; the number N of future time instances; and a first identifier ID.

[0022] Preferably, the second configuration information includes at least one of the following configuration information: a second identifier ID, which indicates that the model monitoring information report is associated with the CSI report, or the second identifier ID is equal to the first identifier ID; and a second resource set for channel measurement reference signals, which is a CSI-RS resource set or an SSB resource set.

[0023] Preferably, the CSI report includes the CSI-RS resource identifier (CRI) / synchronization signal block resource identifier (SSBRI) and / or layer 1 reference signal received power (L1-RSRP) corresponding to the N future time instances.

[0024] Preferably, in the step of monitoring the AI / ML model, at least one of the following operations is performed: deriving, generating, or updating a report of the AI / ML model monitoring information based on measurements of at least one Channel State Information Reference Signal (CSI-RS) or Synchronization Signal Block (SSB); for the i-th time instance, performing AI / ML model monitoring based on at least one CSI-RS or SSB measurement and a comparison result of the Layer 1 Reference Signal Received Power (L1-RSRP) corresponding to the i-th time instance in the CSI report, where i is a natural number and 1 ≤ i ≤ N; and for the i-th time instance, deriving, generating, or updating a report of the AI / ML model monitoring information based on at least one CSI-RS or SSB measurement and a comparison result of the L1-RSRP corresponding to the i-th time instance in the CSI report.

[0025] Preferably, the CSI-RS or SSB is the CSI-RS or SSB resource in the second set of resources for channel measurement reference signals that is the closest in the time domain to the i-th time instance.

[0026] Preferably, the CSI-RS or SSB is the most recent CSI-RS or SSB resource in the second set of resources for channel measurement reference signals, no later than the i-th time instance.

[0027] In addition, according to the present invention, a user equipment is provided, comprising: a processor; and a memory storing instructions, wherein the instructions, when executed by the processor, perform the method described above.

[0028] Invention Effects

[0029] When applying artificial intelligence / machine learning (AI / ML) technologies in the NR air interface, for model inference on the user equipment side, when beam management reports are used for downlink transmission beam prediction in the time domain, this invention provides a method for UE to perform model monitoring. Specifically, for any time instance in the beam management report, the UE measures the L1-RSRP of the CSI-RS closest to that time instance in the time domain, and compares it with the predicted L1-RSRP corresponding to that time instance in the beam management report, thereby monitoring the prediction accuracy of the model. This proposed method ensures that the predicted L1-RSRP used by the UE for model monitoring corresponds to the same time instance as the measured L1-RSRP, effectively improving the accuracy of model monitoring and thus enhancing the accuracy of AI / ML model prediction. Attached Figure Description

[0030] The above and other features of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, wherein:

[0031] Figure 1 This is a schematic diagram illustrating the basic process of a method performed by a user device in Embodiment 1 of the invention.

[0032] Figure 2 This is a block diagram illustrating a user equipment according to an embodiment of the present invention. Detailed Implementation

[0033] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should be noted that the present invention should not be limited to the specific embodiments described below. Furthermore, for the sake of simplicity, detailed descriptions of well-known technologies not directly related to the present invention have been omitted to prevent confusion in understanding the present invention.

[0034] The following description uses 5G mobile communication systems and their subsequent evolutions as example application environments to specifically describe several embodiments according to the present invention. However, it should be noted that the present invention is not limited to the following embodiments, but is applicable to many other wireless communication systems, such as communication systems after 5G and 4G mobile communication systems before 5G.

[0035] The following describes some of the terms involved in this invention. Unless otherwise specified, the terms used in this invention are as defined herein. The terms given in this invention may be named differently in LTE, LTE-Advanced, LTE-Advanced Pro, NR and later communication systems, but a unified terminology is used in this invention. When applied to a specific system, it can be replaced with the terminology used in the corresponding system.

[0036] 3GPP: 3rd Generation Partnership Project

[0037] LTE: Long Term Evolution

[0038] NR: New Radio, New Wireless, New Air Interface

[0039] PDCCH: Physical Downlink Control Channel

[0040] DCI: Downlink Control Information

[0041] PDSCH: Physical Downlink Shared Channel

[0042] UE: User Equipment

[0043] eNB: evolved NodeB

[0044] gNB: NR base station

[0045] TTI: Transmission Time Interval

[0046] OFDM: Orthogonal Frequency Division Multiplexing

[0047] CP-OFDM: Cyclic Prefix Orthogonal Frequency Division Multiplexing

[0048] C-RNTI: Cell Radio Network Temporary Identifier

[0049] CSI: Channel State Information

[0050] HARQ: Hybrid Automatic Repeat Request.

[0051] CSI-RS: Channel State Information Reference Signal

[0052] CRS: Cell Reference Signal

[0053] PUCCH: Physical Uplink Control Channel

[0054] PUSCH: Physical Uplink Shared Channel

[0055] UL-SCH: Uplink Shared Channel

[0056] CG: Configured Grant, Configuration Scheduling License

[0057] MCS: Modulation and Coding Scheme

[0058] RB: Resource Block

[0059] RE: Resource Element

[0060] CRB: Common Resource Block

[0061] CP: Cyclic Prefix

[0062] PRB: Physical Resource Block

[0063] FDM: Frequency Division Multiplexing

[0064] RRC: Radio Resource Control

[0065] RSRP: Reference Signal Receiving Power

[0066] SRS: Sounding Reference Signal

[0067] DMRS: Demodulation Reference Signal

[0068] CRC: Cyclic Redundancy Check

[0069] SFI: Slot Format Indication

[0070] TDD: Time Division Duplexing

[0071] FDD: Frequency Division Duplexing

[0072] SIB: System Information Block

[0073] SIB1: System Information Block Type 1

[0074] PCI: Physical Cell ID

[0075] PSS: Primary Synchronization Signal

[0076] SSS: Secondary Synchronization Signal

[0077] BWP: Bandwidth Part

[0078] SFN: System Frame Number

[0079] IE: Information Element

[0080] SSB: Synchronization Signal Block

[0081] EN-DC: EUTRA-NR Dual Connection, LTE-NR Dual Connectivity

[0082] MCG: Master Cell Group

[0083] SCG: Secondary Cell Group

[0084] PCell: Primary Cell

[0085] SCell: Secondary Cell

[0086] SPS: Semi-Persistant Scheduling

[0087] TA: Timing Advance, uplink timing advance

[0088] PT-RS: Phase-Tracking Reference Signals

[0089] TB: Transport Block

[0090] CB: Code Block

[0091] QPSK: Quadrature Phase Shift Keying

[0092] 16 / 64 / 256QAM: 16 / 64 / 256 Quadrature Amplitude Modulation.

[0093] TDRA (field): Time Domain Resource Assignment.

[0094] FDRA (field): Frequency Domain Resource Assignment.

[0095] ARFCN: Absolute Radio Frequency Channel Number

[0096] SC-FDMA: Single Carrier-Frequency Division Multiple Access

[0097] MAC: Medium Access Control.

[0098] PDU: Protocol Data Unit

[0099] TBS: Transport Block Size

[0100] CQI: Channel Quality Indicator

[0101] RI: Rank Indicator

[0102] PMI: Precoder Matrix Indicator

[0103] RRM: Radio Resource Management

[0104] BM: Beam Management

[0105] NZP-CSI RS: Non-Zero Power CSI Reference Signal.

[0106] MAC CE: Medium Access Control Element.

[0107] CRI: CSI-RS Resource Indicator

[0108] SSBRI: SSB Resource Indicator

[0109] MSB: Most Significant Bit

[0110] LSB: Least Significant Bit

[0111] CPU: CSI Processing Unit, Channel State Information Processing Unit

[0112] The following is a description of prior art associated with the present invention. Unless otherwise specified, the same terms in the specific embodiments have the same meaning as in the prior art.

[0113] In this specification, "network" refers to a base station.

[0114] The parameter set (numerology) and time slots in NR

[0115] The parameter set numberology includes two aspects: subcarrier spacing and cyclic prefix (CP) length. NR supports five subcarrier spacings: 15kHz, 30kHz, 60kHz, 120kHz, and 240kHz (corresponding to μ = 0, 1, 2, 3, and 4). Table 4.2-1 shows the supported transmission parameter set, as detailed below.

[0116] Table 4.2-1 NR Supported Subcarrier Spacing

[0117] μ <![CDATA[Δf=2 μ ·15[kHz]]]> CP (Cyclic Prefix) 0 15 normal 1 30 normal 2 60 Normal, expansion 3 120 normal 4 240 normal

[0118] Extended CP is supported only when μ = 2, i.e., a 60kHz subcarrier spacing; other subcarrier spacings only support normal CP. For normal CP, each slot contains 14 OFDM symbols; for extended CP, each slot contains 12 OFDM symbols. For μ = 0 (15kHz subcarrier spacing), one slot = 1ms; for μ = 1 (30kHz subcarrier spacing), one slot = 0.5ms; for μ = 2 (60kHz subcarrier spacing), one slot = 0.25ms, and so on.

[0119] NR and LTE use the same definition for subframes, which is 1ms. For a subcarrier spacing configuration of μ, the slot numbering within a subframe (1ms) can be represented as... The range is 0 to The slot numbering within a system frame (10ms in duration) can be represented as: The range is 0 to in, The definitions for different subcarrier spacings μ are shown in the table below.

[0120] Table 4.3.2-1: Number of symbols per time slot, number of time slots per system frame, and number of time slots per subframe during normal CP.

[0121]

[0122] Table 4.3.2-2: Number of symbols per time slot, number of time slots per system frame, and number of time slots per subframe during extended CP (60kHz)

[0123]

[0124] On NR carriers, the system frame (or simply frame) number SFN ranges from 0 to 1023.

[0125] Resource blocks (RBs) and resource units (REs)

[0126] Resource blocks (RBs) are defined in the frequency domain as For consecutive subcarriers, for example, with a subcarrier spacing of 15 kHz, RB is 180 kHz in the frequency domain. For a subcarrier spacing of 15 kHz × 2 μ Resource element (RE) represents one subcarrier in the frequency domain and one OFDM symbol in the time domain.

[0127] Common Resource Block (CRB)

[0128] The Common Resource Block (CRB) is defined for a parameter set. For all parameter sets, the center frequency of subcarrier 0 of CRB number 0 points to the same location in the frequency domain, which is called "point A".

[0129] NR resource grid

[0130] For a given transmission direction on a carrier (denoted by x, where x = DL indicates downlink and x = UL indicates uplink), a resource grid is defined for each parameter set, which contains in the frequency domain... Subcarriers (i.e.) There are 1 resource block RB, and each resource block contains 1 resource block RB. (each subcarrier) contains, in the time domain OFDM symbols ( This represents the number of OFDM symbols within a subframe (the specific value is related to μ), where... The number of subcarriers in a resource block (RB) that satisfies The lowest-numbered common resource block (CRB) of a resource raster. The number of frequency domain resource blocks is configured by the higher-level parameter offsetToCarrier. The `carrierBandwidth` parameter is configured by the higher-level parameter. For a given set of parameters and the higher-level parameter `offsetToCarrier`, the gNB configures a cell-specific common `offsetToCarrier` in the `ServingCellConfigCommon` IE via dedicated signaling. Specifically, `ServingCellConfigCommon` includes the higher-level parameter `downlinkConfigCommon`, which contains the configuration information for `offsetToCarrier`.

[0131] Bandwidth Frame (BWP)

[0132] In NR, one or more bandwidth segments can be defined for each parameter set numberology. Each BWP contains one or more consecutive CRBs. Assuming a BWP is numbered i, its starting point... (or, use) (to represent) and length (or, use) (to represent) must simultaneously satisfy the following relations:

[0133]

[0134] That is, the CRB contained in the BWP must be located within the resource raster of the corresponding parameter set. The CRB number represents the distance from the lowest-numbered CRB of the BWP to point A, in units of RB.

[0135] The resource blocks within a BWP are called physical resource blocks (PRBs), and their numbering is... Physical resource block 0 corresponds to the lowest numbered CRB of the corresponding BWP, i.e., CRB For a given serving cell, the gNB configures a BWP using the following higher-level parameters:

[0136] 1) Subcarrier spacing;

[0137] 2) CP length;

[0138] 3) The high-level parameter locationAndBandwidth indicates the BWP relative to the starting CRB of the resource raster. offset value (RB) start ) and the number L of consecutive CRBs in the frequency domain of the BWP RB ,satisfy Among them O carrier This represents `offsetToCarrier`; where the parameter `locationAndBandwidth` indicates a `RIV` (Resource Indication Value). The `RIV` is related to `L`. RB and RB start The calculation relationship is as follows: If So otherwise, in, and,

[0139] 4) The serial number of the BWP;

[0140] 5) Configuration of BWP common and BWP proprietary parameters, such as the configuration of PDCCH and PDSCH for downlink BWP.

[0141] Channel State Information (CSI) Reporting in NR

[0142] In NR, user equipment can perform different downlink channel measurements and channel state information reports (CSI reports) based on network configuration information. The measurement configuration and the corresponding reporting method are accomplished through the reporting configuration, which is represented by the RRC parameter CSI-ReportConfig in the 3GPP protocol.

[0143] CSI Report Items

[0144] A measurement report needs to explicitly configure which measurement items the user equipment (UE) needs to report. For example, a measurement report may include three items: Channel Quality Indicator (CQI), Channel Rank Indicator (RI), and Precoder Matrix Indicator (PMI), collectively referred to as channel state information. A measurement report can also include only one item, such as reporting the received signal strength, called Reference Signal Received Power (RSRP). RSRP is also a critical measurement, generally used in higher-level Radio Resource Management (RRM). NR introduces RSRP reporting at the physical layer for Beam Management (BM), called L1-RSRP. For L1-RSRP reporting, UE can report the largest L1-RSRP measurement value; the remaining L1-RSRP values ​​are reported differentially, meaning the remaining reported L1-RSRP values ​​are the differences between the measured values ​​and the largest L1-RSRP measurement value.

[0145] CSI reported physical measurement resources

[0146] In the configuration information of the RRC parameter CSI-ReportConfig, the reporting configuration is associated with one or more resource sets. Specifically, a measurement resource configuration is associated with one or more Non-Zero Power CSI Reference Signal (NZP-CSI RS) resource sets. The user equipment uses this NZP-CSI RS resource set to measure the characteristics of the downlink channel. The NZP-CSI RS resource set may include a set of configured CSI-RS or a set of Synchronization Signal Blocks (SSBs). For example, L1-RSRP measurement reporting for beam management is performed on a set of SSBs or a set of NZP-CSI RS. For a configured set of NZP-CSI RS resources, a CSI-RS Resource Identifier (CRI) is used to represent a specific CSI-RS resource within that set. For example, if the group contains four CSI-RS resources, then the CRI is two bits: '00' represents the first CSI-RS resource, '01' represents the second CSI-RS resource, '10' represents the third CSI-RS resource, and '11' represents the fourth CSI-RS resource. Similarly, for a configured group of SSB resources, an SSB Resource Identifier (SSBRI) is used to represent a specific SSB resource within that group.

[0147] CSI reporting method

[0148] In NR, CSI reporting by user equipment can be divided into three types: periodic CSI report, semi-persistent CSI report, and aperiodic CSI report.

[0149] For periodic CSI reporting, the network needs to be configured with a specific reporting period. Periodic CSI reporting is carried out through the Physical Uplink Control Channel (PUCCH). Therefore, for periodic CSI reporting, the resource configuration information needs to be configured with the periodic PUCCH resources used for reporting.

[0150] For semi-persistent CSI reporting, the network activates or deactivates the corresponding CSI reporting via MAC CE. Semi-persistent CSI reporting can be carried through allocated PUCCHs or allocated Physical Uplink Shared Channels (PUSCHs). PUCCH resources are semi-statically and periodically configured. PUSCHs are often used to carry semi-persistent CSI reports with relatively large amounts of information.

[0151] Aperiodic CSI reporting is triggered via downlink control information (DCI). Specifically, it is indicated by the CSI request indication field in the uplink scheduling authorization. This indication field contains a maximum of 6 bits, each combination corresponding to a configured aperiodic CSI report, meaning a maximum of 63 different aperiodic CSI reports can be triggered (all bits set to 0 indicate no aperiodic CSI report is triggered). Aperiodic CSI reports are carried via PUSCH.

[0152] Artificial Intelligence / Machine Learning (AI / ML)

[0153] In this invention, an AI / ML model is used to represent the application of AI / ML technology in the NR air interface. In the case of CSI enhancement, the AI / ML model includes a CSI generation model (or encoder or auto-encoder) and a CSI reconstruction model (or decoder or auto-decoder). In the case of beam management enhancement, when the UE applies the AI / ML model, it can be used to generate reported beam measurement information. For example, when the model input is a Layer 1-RSRP (L1-RSRP) measured by a CSI-RS, the model output can be the L1-RSRP corresponding to an unmeasured CSI-RS (corresponding to a downlink beam). In this invention, the model output is referred to as the predicted L1-RSRP. When the network applies the AI / ML model, two reference signal sets can be configured for the UE. These two sets can be different; one is used for beam measurement, and the other represents the beams to be reported.

[0154] AI / ML technology can be divided into the following 5 aspects:

[0155] 1) AI / ML model training

[0156] The training of AI / ML models involves generating an inference relation (e.g., a function) based on a combination of input and output parameters, which is then used for subsequent inference. Taking a CSI generation model as an example, this model can be trained by a network or by a user device (UE). The input parameters of this model are the raw channel data (e.g., the original channel matrix), and the output parameter is the CSI reported to the network. Conversely, a CSI reconstruction model can also be trained by a network or by a UE. The input parameters of the CSI reconstruction model are the reported CSI, and the output parameter is the raw channel data.

[0157] 2) AI / ML model transfer

[0158] If the CSI generation model is trained by a network, the trained CSI generation model can be sent by the network to the UE for model inference. The sending of the model is called AI / ML model transfer.

[0159] 3) AI / ML model inference

[0160] Taking the CSI generation model as an example, the process by which the UE uses a CSI generation model to generate CSI reports is the inference process of the AI / ML model. Similarly, the process by which the network uses a CSI reconstruction model to generate raw channel data is also the inference process of the AI / ML model.

[0161] 4) AI / ML model monitoring

[0162] The network or UE needs to monitor the AI / ML model used to determine whether the model is suitable for the current channel conditions.

[0163] 5) AI / ML model update

[0164] When the network or UE deems the model no longer applicable, the AI / ML model will be updated.

[0165] Time instance in beam management report

[0166] A beam management report may include CSI-RS Resource Identifier (CRI), SSB Resource Identifier, and L1-RSRP. Unlike traditional beam management reports, when artificial intelligence / machine learning (AI / ML) technologies are applied in the NR air interface, for UE-side model inference, the beam management report may include one or more (denoted by N) CRIs / SSBRIs corresponding to future times, and / or L1-RSRPs. These future times are also called time instances. The number of time instances N can be configured through the RRC parameter. Specifically, one time instance corresponds to one or more CRIs / SSBRIs, and the corresponding predicted L1-RSRP.

[0167] Beam management report for time-domain uplink and downlink transmission beam prediction

[0168] The configuration information of the CSI report (beam management report) can include the number N of the aforementioned future time instances. For the aforementioned CSI report, the UE can perform receive measurements on the CSI-RS (or SSB) over a continuous period of time to generate the CSI report. This continuous period of time can be called the observation window, monitoring window, or measurement window.

[0169] CSI Reference Resource

[0170] In Rel-15NR, the CSI reference resource for a serving cell is defined as follows:

[0171] 1) For frequency domain resources, CSI reference resources represent the derived set of CSI-related downlink PRBs;

[0172] 2) For time-domain resources, assuming CSI reporting is performed in uplink time slot n', then the time-domain resource of the CSI reference resource is a downlink time slot, denoted as nn. CSI_ref ,in, μ DL and μ UL These represent the configuration of the downlink and uplink subcarrier spacing, respectively.

[0173] In Rel-15NR for n CSI_ref The definition is (taking non-periodic CSI reporting as an example):

[0174] ■ For aperiodic CSI reporting, if the CSI request field in the DCI indicates that the CSI reporting and CSI request are in the same time slot, then n CSI_ref The value of n ensures that the CSI reference resource and the corresponding CSI request are in the same valid downlink slot. Otherwise, n CSI_ref The value of is not less than the minimum delay requirement (in time slots), and satisfies nn CSI_ref This corresponds to a valid downlink time slot.

[0175] It is worth noting that in NR and NR AI / ML, the user equipment can determine the CSI reference resource corresponding to each CSI report configured by the base station and the report used for monitoring information of the AI / ML model. The methods for determining the CSI reference resource include, but are not limited to, the methods described above, and this invention does not impose any restrictions on them.

[0176] The following provides a detailed description of specific examples and embodiments related to this invention. Furthermore, as described above, the examples and embodiments described in this disclosure are illustrative and intended to facilitate understanding of the invention, and are not intended to limit the scope of the invention.

[0177] [Example 1]

[0178] Figure 1 This is a schematic diagram illustrating the basic process of a method executed by a user equipment according to Embodiment 1 of the present invention.

[0179] Below, in conjunction with Figure 1 The basic process diagram shown illustrates in detail the method executed by a user equipment according to Embodiment 1 of the present invention.

[0180] like Figure 1 As shown, in Embodiment 1 of the present invention, the steps performed by the user equipment include:

[0181] In step S101, the user equipment receives the first configuration information and the second configuration information sent by the base station.

[0182] The first configuration information is the reporting configuration information for Channel State Indication (CSI). The second configuration information is the configuration information for AI / ML model monitoring information reporting.

[0183] Optionally, the first configuration information includes, but is not limited to, the following configuration information:

[0184] ■ AI / ML related configuration information (or, the configuration information reported by the CSI applies an AI / ML model).

[0185] And / or,

[0186] ■In addition to configuring the first reference signal for channel measurement, it also includes reference signal configuration information for beam management reporting.

[0187] ●Optionally, the first reference signal for channel measurement is a CSI-RS resource set or an SSB resource set.

[0188] And / or,

[0189] ■ The number of future time instances, N.

[0190] And / or,

[0191] ■ First Identifier ID.

[0192] Optionally, the second configuration information includes, but is not limited to, the following configuration information:

[0193] ■ Second Identifier ID; Optionally, the second identifier ID indicates that the model monitoring information report is associated with the CSI report, or the second identifier ID is equal to the first identifier ID.

[0194] And / or,

[0195] ■The second set of resources used for channel measurement reference signals.

[0196] ●The second reference signal used for channel measurement is a CSI-RS resource set, or an SSB resource set.

[0197] In step S102, optionally, the user equipment performs CSI reporting at least according to the first configuration information.

[0198] The CSI report includes the CRI / SSBRI and / or L1-RSRP corresponding to the N future time instances.

[0199] In step S103, the user equipment performs monitoring of the AI / ML model at least according to the second configuration information.

[0200] Optionally, the user equipment derives, generates, or updates a report of the AI / ML model monitoring information based on measurements from at least one CSI-RS (or SSB).

[0201] or,

[0202] Optionally, for the i-th (1≤i≤N) time instance, the user equipment performs AI / ML model monitoring based on at least one CSI-RS (or SSB) measurement and the comparison result of the L1-RSRP corresponding to the i-th time instance in the CSI report.

[0203] or,

[0204] Optionally, for the i-th time instance, the user equipment derives, generates, or updates a report of the AI / ML model monitoring information based on at least one CSI-RS (or SSB) measurement and the comparison result of the Ll-RSRP corresponding to the i-th time instance in the CSI report.

[0205] in,

[0206] ■ The aforementioned CSI-RS (or SSB) is the CSI-RS (or SSB) resource in the second set of resources for channel measurement reference signals (no later than the CSI reference resource corresponding to the AI / ML model monitoring information report) that is the closest in the time domain to the i-th time instance.

[0207] or,

[0208] ■ The CSI-RS (or SSB) mentioned above is the most recent CSI-RS (or SSB) resource in the second set of resources for channel measurement reference signals that is no later than the i-th time instance (and no later than the CSI reference resource corresponding to the AI / ML model monitoring information report).

[0209] Figure 2 This is a block diagram illustrating the user equipment (UE) involved in this invention. For example... Figure 2 As shown, the user equipment UE20 includes a processor 201 and a memory 202. The processor 201 may include, for example, a microprocessor, a microcontroller, an embedded processor, etc. The memory 202 may include, for example, volatile memory (such as random access memory, RAM), a hard disk drive (HDD), non-volatile memory (such as flash memory), or other memory. Program instructions are stored on the memory 202. When executed by the processor 201, these instructions can perform the methods described in detail herein, executed by the user equipment.

[0210] The method and related apparatus of the present invention have been described above in conjunction with preferred embodiments. Those skilled in the art will understand that the methods shown above are merely exemplary, and the various embodiments described above can be combined with each other without contradiction. The method of the present invention is not limited to the steps and sequence shown above. The network nodes and user equipment shown above may include more modules, such as modules that can be developed or will be developed in the future for use with base stations, MMEs, or UEs, etc. The various identifiers shown above are merely exemplary and not limiting, and the present invention is not limited to the specific information elements exemplified by these identifiers. Those skilled in the art can make many variations and modifications based on the teachings of the illustrated embodiments.

[0211] It should be understood that the above embodiments of the present invention can be implemented by software, hardware, or a combination of both. For example, the various components inside the base station and user equipment in the above embodiments can be implemented by a variety of devices, including but not limited to: analog circuit devices, digital circuit devices, digital signal processing (DSP) circuits, programmable processors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), programmable logic devices (CPLDs), and so on.

[0212] In this application, "base station" can refer to a mobile communication data and control switching center with high transmission power and wide coverage, including functions such as resource allocation and scheduling, and data reception and transmission. "User equipment" can refer to user mobile terminals, such as mobile phones, laptops, and other terminal devices that can wirelessly communicate with base stations or micro base stations.

[0213] Furthermore, the embodiments of the present invention disclosed herein can be implemented on a computer program product. More specifically, the computer program product is one that has a computer-readable medium on which computer program logic is encoded, which, when executed on a computing device, provides related operations to implement the above-described technical solutions of the present invention. When executed on at least one processor of a computing system, the computer program logic causes the processor to perform the operations (methods) described in the embodiments of the present invention. This configuration of the present invention is typically provided as software, code, and / or other data structures disposed or encoded on a computer-readable medium such as an optical medium (e.g., CD-ROM), floppy disk, or hard disk, or other media such as firmware or microcode on one or more ROM, RAM, or PROM chips, or downloadable software images, shared databases, etc., in one or more modules. The software or firmware or such configuration can be installed on a computing device to cause one or more processors in the computing device to execute the technical solutions described in the embodiments of the present invention.

[0214] Furthermore, each functional module or feature of the base station equipment and terminal equipment used in each of the above embodiments can be implemented or executed by circuitry, which is typically one or more integrated circuits. Circuitry designed to perform the various functions described in this specification may include general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs) or general-purpose integrated circuits, field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic, or discrete hardware components, or any combination of the above devices. The general-purpose processor may be a microprocessor, or the processor may be an existing processor, controller, microcontroller, or state machine. The aforementioned general-purpose processor or each circuit may be configured by digital circuitry or by logic circuitry. Furthermore, when advancements in semiconductor technology lead to advanced technologies that can replace current integrated circuits, the present invention may also utilize integrated circuits obtained using such advanced technologies.

[0215] Although the present invention has been illustrated above with reference to preferred embodiments, those skilled in the art will understand that various modifications, substitutions, and alterations can be made to the invention without departing from its spirit and scope. Therefore, the invention should not be limited by the above embodiments, but rather by the appended claims and their equivalents.

Claims

1. A method executed by a user equipment, comprising the following steps: The system receives first configuration information and second configuration information sent by the base station. The first configuration information is the reporting configuration information for Channel State Indication Information (CSI), and the second configuration information is the configuration information for reporting monitoring information of Artificial Intelligence / Machine Learning (AI / ML) models. At least CSI reporting should be performed based on the first configuration information; as well as At least the monitoring of the AI / ML model shall be performed based on the second configuration information.

2. The method according to claim 1, wherein, The first configuration information includes at least one of the following configuration information: AI / ML related configuration information; Based on the configuration of the first reference signal for channel measurement, the reference signal configuration information for beam management reporting is provided. The first reference signal for channel measurement is a Channel State Information Reference Signal (CSI-RS) resource set or a Synchronization Signal Block (SSB) resource set. The number N of future time instances; and First identifier ID.

3. The method according to claim 2, wherein, The second configuration information includes at least one of the following configuration information: The second identifier ID indicates that the model monitoring information report is associated with the CSI report, or the second identifier ID is equal to the first identifier ID; as well as The second set of resources for channel measurement reference signals is either a CSI-RS resource set or an SSB resource set.

4. The method according to claim 2, wherein, The CSI report includes the CSI-RS resource identifier (CRI) / synchronization signal block resource identifier (SSBRI) and / or layer 1 reference signal received power (L1-RSRP) corresponding to the N future time instances.

5. The method according to claim 3 or 4, wherein, In the process of monitoring AI / ML models, at least one of the following operations is performed: A report is derived, generated, or updated based on measurements of at least one Channel State Information Reference Signal (CSI-RS) or Synchronization Signal Block (SSB). For the i-th time instance, monitoring of the AI / ML model is performed based on at least one CSI-RS or SSB measurement and the comparison result of the Layer 1 Reference Signal Received Power (L1-RSRP) corresponding to the i-th time instance in the CSI report, where i is a natural number and 1 ≤ i ≤ N; as well as For the i-th time instance, a report on the AI / ML model monitoring information is derived, generated, or updated based on at least one CSI-RS or SSB measurement and the comparison result of the L1-RSRP corresponding to the i-th time instance in the CSI report.

6. The method according to claim 5, wherein, The CSI-RS or SSB is the CSI-RS or SSB resource in the second set of resources for channel measurement reference signals that is the closest in the time domain to the i-th time instance.

7. The method according to claim 5, wherein, The CSI-RS or SSB is the most recent CSI-RS or SSB resource in the second set of resources for channel measurement reference signals that is no later than the i-th time instance.

8. A user equipment, comprising: processor; as well as Memory, which stores instructions The instructions, when executed by the processor, perform the method according to any one of claims 1-7.

Images