Method executed by user equipment and user equipment

Abstract

Provided are a method executed by a user equipment and the user equipment, the method comprising: receiving a media access control layer control unit (MAC CE) sent by a network, the MAC CE carrying semi-persistent CSI reporting indication information related to the reporting of channel state information (CSI); sending a physical uplink control channel (PUCCH) to the network on the first time slot; and transmitting a CSI report to a network on a PUCCH resource starting from a second time slot delayed by a given delay time with respect to the first time slot. In any one of the following cases, the given delay time is determined based on a delay parameter related to the use of an AI / ML model by the user equipment: the artificial intelligence / machine learning AI / ML model is used when the user equipment generates the CSI report; aiming at the generation of the CSI report by the user equipment, at least one effective AI / ML model exists; the semi-persistent CSI reporting configuration information comprises the configuration information of the AI / ML model.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communications, and in particular to a method executed by a user equipment and corresponding user equipment. Background Art

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

[0003] 1) The number of measurement reports, that is, how many measurement items need to be reported to the network.

[0004] A measurement report needs to clearly configure which measurement items the user equipment needs to report. For example, a measurement report can include three items: Channel Quality Indicator (CQI), Channel Rank Indicator (RI), and Channel Precoding 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 key measurement, generally used in high-level Radio Resource Management (RRM). NR introduces RSRP reporting at the physical layer for beam management (BM), called L1-RSRP.

[0005] 2) Measurement object, i.e. the physical resource for 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 channel state information reference signal (NonZero Power CSI Reference Signal, NZP-CSI RS) resource sets, and the user equipment uses the 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 RSs or a set of synchronization signal blocks (Synchronization Signal Block, SSB). For example, the L1-RSRP measurement report for beam management is performed for a set of SSBs or a set of NZP-CSI RSs.

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

[0008] In Rel-15NR, the CSI reporting of the user equipment can be divided into three types: periodic CSI reporting (PeriodicCSI report), semi-persistent CSI reporting (Semi-persistent CSI report) and aperiodic CSI reporting (AperiodicCSI report).

[0009] For periodic CSI reporting, the network needs to configure a certain reporting period. Periodic CSI reporting is carried by the Physical Uplink Control Channel (PUCCH). Therefore, for periodic CSI reporting, resource configuration information needs to configure the periodic PUCCH resources used for reporting.

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

[0011] Aperiodic CSI reporting is triggered by downlink control information (DCI). Specifically, it is indicated by the CSI request indication field in the uplink scheduling grant. The indication field contains up to 6 bits, and each combination corresponds to a configured aperiodic CSI report, which means that up to 63 different aperiodic CSI reports can be triggered (all bits set to 0 indicate that the aperiodic CSI report is not triggered). Aperiodic CSI reporting is carried by PUSCH.

[0012] At the 3GPP RAN#94e plenary meeting in December 2021, research on artificial intelligence / machine learning (AI / ML) within the standardized NR air interface was approved (see Non-Patent Document 1). The case studies for this research topic mainly include the following three aspects:

[0013] 1) Enhancements to CSI reporting, such as reducing CSI reporting overhead, improving CSI reporting accuracy, and improving CSI reporting prediction;

[0014] 2) Enhanced beam management, such as beam prediction in the time domain, reduced overhead and latency in the spatial domain, and improved beam selection accuracy;

[0015] 3) Enhanced positioning accuracy in different scenarios

[0016] enhancement), such as scenarios with dense Non-Line of Sight (NLOS).

[0017] The solution of this patent is a method for user equipment UE to report channel state information CSI when applying AI / ML in NR air interface.

[0018] Prior art literature

[0019] Non-patent literature

[0020] Non-Patent Literature 1: RP-213599, New SI: Study on AI / ML for NR air interface, section 4.1 Summary of the Invention

[0021] In order to solve at least part of the above problems, the present invention provides a method performed by a user equipment and the user equipment.

[0022] According to a first aspect of the present invention, a method performed by a user equipment is provided, comprising: receiving a media access control layer control element MAC CE sent by a network, the MAC CE carrying semi-persistent CSI reporting indication information related to reporting of channel state information CSI; sending a physical uplink control channel PUCCH to the network on a first time slot; and sending a CSI report to the network on a PUCCH resource starting from a second time slot delayed by a given delay time relative to the first time slot. In any of the following cases, the given delay time is determined based on a delay parameter related to the user equipment's use of an AI / ML model: the user equipment uses the artificial intelligence / machine learning AI / ML model when generating the CSI report; there is at least one valid AI / ML model for the user equipment's generation of the CSI report; and the configuration information of the AI / ML model is included in the semi-persistent CSI reporting configuration information.

[0023] Optionally, the given delay time may be greater than 3 ms.

[0024] Optionally, the delay parameter can be determined in any of the following ways: the delay parameter is determined based on the inference time of the user equipment using the AI / ML model for inference; the delay parameter is the maximum value among the inference times of multiple user equipment using the AI / ML model for inference; the delay parameter is the minimum value among the inference times of multiple user equipment using the AI / ML model for inference; the delay parameter is a value configured by the network through an RRC parameter; the delay parameter is a predefined given value. The multiple user equipments here may include user equipment that executes the method of the present invention.

[0025] Optionally, when the delay parameter is set to X, the given delay time is determined by The value represented by Indicates the number of time slots contained in a subframe.

[0026] Optionally, when the delay parameter is set to X, the given delay time is determined by The value represented by Indicates the number of time slots contained in a subframe.

[0027] Optionally, the AI / ML model configuration information includes at least one of the following: an identifier of a CSI reconstruction model; an identifier of a CSI generation model; an identifier of a paired CSI generation model and reconstruction model; an identifier of a data set for a training model; and an identifier of a training process for a training model.

[0028] According to another aspect of the present invention, there is further provided a user equipment, comprising: a processor; and

[0029] A memory stores instructions; wherein the instructions, when executed by the processor, execute the method as described above.

[0030] Beneficial effects of the present invention

[0031] When applying artificial intelligence / machine learning (AI / ML) technologies to the NR air interface, the present invention's solution additionally considers the inference latency of the AI / ML model when determining the earliest starting timeslot for semi-persistent CSI reporting. This solution ensures that after the network activates semi-persistent CSI reporting, the user equipment has sufficient time to perform the corresponding CSI channel measurements and generate the corresponding CSI reports. This effectively improves the accuracy of CSI reporting and the reliability of downlink transmission in the NR air interface. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] 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, in which:

[0033] Figure 1 It is a schematic diagram showing the basic process of the method executed by the user equipment in the first embodiment of the invention.

[0034] Figure 2 is a block diagram illustrating a user equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the present invention is not limited to the specific embodiments described below. In addition, for the sake of simplicity, detailed descriptions of known technologies that are not directly related to the present invention are omitted to prevent confusion in understanding the present invention.

[0036] The following describes multiple embodiments of the present invention using a 5G mobile communication system and its subsequent evolutionary versions as example application environments. 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.

[0037] The following describes some of the terms involved in the present invention. Unless otherwise specified, the terms used in the present invention are defined herein. The terms given in the present invention may be named differently in LTE, LTE-Advanced, LTE-Advanced Pro, NR, and later communication systems. However, the present invention adopts unified terminology. When applied to a specific system, the terms can be replaced with the terms used in the corresponding system.

[0038] 3GPP: 3rd Generation Partnership Project

[0039] LTE: Long Term Evolution

[0040] NR: New Radio, New Wireless, New Air Interface

[0041] PDCCH: Physical Downlink Control Channel, physical downlink control channel

[0042] DCI: Downlink Control Information, downlink control information

[0043] PDSCH: Physical Downlink Shared Channel, physical downlink shared channel

[0044] UE: User Equipment

[0045] eNB: evolved NodeB

[0046] gNB: NR base station

[0047] TTI: Transmission Time Interval, transmission time interval

[0048] OFDM: Orthogonal Frequency Division Multiplexing

[0049] CP-OFDM: Cyclic Prefix Orthogonal Frequency Division Multiplexing, orthogonal frequency division multiplexing with cyclic prefix

[0050] C-RNTI: Cell Radio Network Temporary Identifier, cell radio network temporary identifier

[0051] CSI: Channel State Information

[0052] HARQ: Hybrid Automatic Repeat Request

[0053] CSI-RS: Channel State Information Reference Signal

[0054] CRS: Cell Reference Signal, cell-specific reference signal

[0055] PUCCH: Physical Uplink Control Channel, physical uplink control channel

[0056] PUSCH: Physical Uplink Shared Channel, physical uplink shared channel

[0057] UL-SCH: Uplink Shared Channel, uplink shared channel

[0058] CG: Configured Grant, configured scheduling permission

[0059] MCS: Modulation and Coding Scheme, modulation and coding scheme

[0060] RB: Resource Block

[0061] RE:Resource Element

[0062] CRB: Common Resource Block

[0063] CP: Cyclic Prefix

[0064] PRB: Physical Resource Block, physical resource block

[0065] FDM: Frequency Division Multiplexing

[0066] RRC: Radio Resource Control

[0067] RSRP: Reference Signal Receiving Power, reference signal receiving power

[0068] SRS: Sounding Reference Signal, detection reference signal

[0069] DMRS: Demodulation Reference Signal

[0070] CRC: Cyclic Redundancy Check

[0071] SFI: Slot Format Indication, slot format indication

[0072] TDD: Time Division Duplexing

[0073] FDD: Frequency Division Duplexing

[0074] SIB: System Information Block

[0075] SIBl: System Information Block Type 1, System Information Block Type 1

[0076] PCI: Physical Cell ID, physical cell identifier

[0077] PSS: Primary Synchronization Signal

[0078] SSS: Secondary Synchronization Signal

[0079] BWP: BandWidth Part, bandwidth fragment / part

[0080] SFN: System Frame Number, system (wireless) frame number

[0081] IE: Information Element

[0082] SSB: Synchronization Signal Block, synchronization signal block

[0083] EN-DC: EUTRA-NR Dual Connection, LTE-NR dual connectivity

[0084] MCG: Master Cell Group

[0085] SCG: Secondary Cell Group

[0086] PCell: Primary Cell

[0087] SCell: Secondary Cell

[0088] SPS: Semi-Persistant Scheduling

[0089] TA: Timing Advance, uplink timing advance

[0090] PT-RS: Phase-Tracking Reference Signals, phase tracking reference signal

[0091] TB: Transport Block

[0092] CB: Code Block, coding block / code block

[0093] QPSK: Quadrature Phase Shift Keying, quadrature phase shift keying

[0094] 16 / 64 / 256QAM: 16 / 64 / 256Quadrature Amplitude Modulation, quadrature amplitude modulation

[0095] TDRA(field): Time Domain Resource Assignment, time domain resource allocation indication (field)

[0096] FDRA(field): Frequency Domain Resource Assignment, frequency domain resource allocation indication (field)

[0097] ARFCN: Absolute Radio Frequency Channel Number, absolute radio frequency channel number

[0098] SC-FDMA: Single Carrier-Frequency Division Multiple Access

[0099] MAC: Medium Access Control

[0100] PDU: Protocol Data Unit

[0101] TBS: Transport Block Size, transport block size

[0102] CQI: Channel Quality Indicator, channel quality indicator

[0103] RI: Rank Indicator, channel rank indication

[0104] PMI: Precoder Matrix Indicator, channel precoding matrix indicator

[0105] RRM: Radio Resource Management

[0106] BM: Beam Management

[0107] NZP-CSI RS: Non Zero Power CSI Reference Signal, non-zero power channel state information reference signal

[0108] MAC CE: Medium Access Control Control Element, media access control layer control unit

[0109] The following is a description of the prior art associated with the present invention. Unless otherwise specified, the same terms in the specific embodiments and the prior art have the same meanings.

[0110] In the specification of this article, the network refers to a base station.

[0111] In the description of this document, the use of artificial intelligence / machine learning (AI / ML) models may also be referred to as the use of enhanced CSI (or reporting).

[0112] Parameter set (numerology) in NR and time slot in NR

[0113] The parameter set numerology includes two aspects: subcarrier spacing and cyclic prefix (CP) length. NR supports five subcarrier spacings: 15k, 30k, 60k, 120k, and 240kHz (corresponding to μ = 0, 1, 2, 3, and 4). Table 4.2-1 shows the supported transmission parameter sets, as shown below.

[0114] Table 4.2-1 Subcarrier spacing supported by NR

[0115] μ <![CDATA[Δf=2 μ ·15[kHz]]]> CP (Cyclic Prefix) 0 15 normal 1 30 normal 2 60 Normal, Extended 3 120 normal 4 240 normal

[0116] Extended CP is supported only when μ = 2, that is, with a 60kHz subcarrier spacing. For other subcarrier spacings, only normal CP is supported. For normal CP, each slot contains 14 OFDM symbols; for extended CP, each slot contains 12 OFDM symbols. For μ = 0, that is, with a 15kHz subcarrier spacing, 1 slot = 1ms; for μ = 1, that is, with a 30kHz subcarrier spacing, 1 slot = 0.5ms; for μ = 2, that is, with a 60kHz subcarrier spacing, 1 slot = 0.25ms, and so on.

[0117] NR and LTE have the same definition of subframe, which is 1ms. For the subcarrier spacing configuration μ, the slot number within 1 subframe (1ms) can be expressed as Range is 0 to The slot number within a system frame (frame, duration 10ms) can be expressed as Range is 0 to in, and The definitions of different subcarrier spacing μ are shown in the following table.

[0118] Table 4.3.2-1: Number of symbols in each slot, number of slots in each system frame, and number of slots in each subframe under normal CP

[0119]

[0120] Table 4.3.2-2: Number of symbols per slot, number of slots per system frame, and number of slots per subframe when using extended CP (60kHz)

[0121]

[0122] On an NR carrier, the system frame (or, simply referred to as frame) number SFN ranges from 0 to 1023.

[0123] Resource blocks RB and resource elements RE

[0124] Resource blocks RB are defined in the frequency domain as For example, for a subcarrier spacing of 15kHz, the RB is 180kHz in the frequency domain. μ , the resource element RE represents 1 subcarrier in the frequency domain and 1 OFDM symbol in the time domain.

[0125] NR Common Resource Block (CRB)

[0126] Common resource blocks (CRBs) are defined for numerologies. For all numerologies, the center frequency of subcarrier 0 in CRB number 0 remains at the same location in the frequency domain, called point A.

[0127] NR resource grid

[0128] In a given transmission direction of a carrier (denoted by x, where x=DL means downlink and x=UL means uplink), a resource grid is defined for each numerology, which contains subcarriers (i.e. Resource blocks RB, each resource block contains subcarriers), which contain OFDM symbols ( represents the number of OFDM symbols in a subframe, and its specific value is related to μ), where Refers to the number of subcarriers in a resource block RB, satisfying The lowest-numbered common resource block (CRB) in the resource grid Configured by the high-level parameter offsetToCarrier, the number of frequency domain resource blocks Configured by the higher-layer parameter carrierBandwidth. For a given numerology and the higher-layer parameter offsetToCarrier, the gNB configures the cell-specific common offsetToCarrier in the ServingCellConfigCommon IE via dedicated signaling. Specifically, ServingCellConfigCommon includes the higher-layer parameter downlinkConfigCommon, which contains the offsetToCarrier configuration information.

[0129] Bandwidth Piece (BWP)

[0130] In NR, for each parameter set numerology, one or more bandwidth segments can be defined. Each BWP contains one or more consecutive CRBs. Assuming that a BWP is numbered i, its starting point is (Or, use to indicate) and length (Or, use To express) must satisfy the following relations at the same time:

[0131]

[0132]

[0133] That is, the CRB contained in the BWP must be located in the resource grid of the corresponding numerology. Use the CRB number to indicate the distance from the lowest-numbered CRB in the BWP to point A, in RBs.

[0134] The resource blocks within a BWP are called physical resource blocks (PRBs), which are numbered Among them, physical resource block 0 corresponds to the lowest numbered CRB of the BWP, namely CRB For a serving cell, the gNB configures a BWP using the following higher-layer parameters:

[0135] 1) Subcarrier spacing;

[0136] 2)CP length;

[0137] 3) The high-level parameter locationAndBandwidth indicates that the BWP is relative to the resource grid starting CRB The offset value offset(RB start ) and the number of consecutive CRBs in the BWP frequency domain L RB ,satisfy Among them O carrier Indicates offsetToCarrier; wherein the parameter locationAndBandwidth indicates a RIV (Resource Indication Value). RB and RB start The calculation relationship is: If So otherwise, in, and,

[0138] 4) The BWP number;

[0139] 5) BWP public and BWP-specific parameter configuration, such as the configuration of PDCCH and PDSCH of downlink BWP.

[0140] Channel State Information Reporting (CSI Report) in NR

[0141] In NR, user equipment can perform different downlink channel measurements and Channel State Indicator (CSI) reports based on network configuration information. The measurement configuration and corresponding reporting method are completed through the reporting configuration, which is represented by the RRC parameter CSI-ReportConfig in the 3GPP protocol.

[0142] CSI Reporting Items

[0143] A measurement report needs to clearly configure which measurement items the user equipment needs to report. For example, a measurement report can include three items: Channel Quality Indicator (CQI), Channel Rank Indicator (RI), and Channel Precoding 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 key measurement, generally used in high-level Radio Resource Management (RRM). NR introduces RSRP reporting at the physical layer for beam management (BM), called L1-RSRP.

[0144] Physical measurement resources reported by CSI

[0145] 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 channel state information reference signal (NonZero Power CSI Reference Signal, NZP-CSI RS) resource sets, and the user equipment uses the 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 RSs or a set of synchronization signal blocks (Synchronization Signal Block, SSB). For example, the L1-RSRP measurement report for beam management is performed for a set of SSBs or a set of NZP-CSI RSs.

[0146] CSI reporting method

[0147] In NR, the CSI reporting of user equipment can be divided into three types: periodic CSI report (Periodic CSI report), semi-persistent CSI report (Semi-persistent CSI report) and aperiodic CSI report (Aperiodic CSI report).

[0148] For periodic CSI reporting, the network needs to configure a certain reporting period. Periodic CSI reporting is carried by the Physical Uplink Control Channel (PUCCH). Therefore, for periodic CSI reporting, resource configuration information needs to configure the periodic PUCCH resources used for reporting.

[0149] For semi-persistent CSI reporting, the network activates or deactivates the corresponding CSI reporting through MAC CE. Semi-persistent CSI reporting can be carried by the allocated PUCCH or the allocated Physical Uplink Shared Channel (PUSCH). PUCCH resources are semi-statically and periodically configured. PUSCH is often used to carry semi-persistent CSI reporting with a relatively large amount of reported information.

[0150] Aperiodic CSI reporting is triggered by downlink control information (DCI). Specifically, it is indicated by the CSI request indication field in the uplink scheduling grant. The indication field contains up to 6 bits, and each combination corresponds to a configured aperiodic CSI report, which means that up to 63 different aperiodic CSI reports can be triggered (all bits set to 0 indicate that the aperiodic CSI report is not triggered). Aperiodic CSI reporting is carried by PUSCH.

[0151] Artificial Intelligence / Machine Learning (AI / ML)

[0152] In this specification, the AI / ML model is used to indicate 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 (also known as an encoder or auto-encoder) and a CSI reconstruction model (also known as a decoder or auto-decoder).

[0153] AI / ML technologies can be divided into the following five areas:

[0154] 1) AI / ML model training

[0155] The training of the AI / ML model means obtaining an inference relationship (for example, a function) based on the combination of input parameters and output parameters for subsequent reasoning. Taking the CSI generation model as an example, the model can be trained by the network or obtained by training by the UE. The input parameter of the model is the original data of the channel (for example, the original matrix of the channel), and the output parameter is the CSI reported to the network. Conversely, for the CSI reconstruction model, it can also be trained by the network or by training by the UE. The input parameter of the CSI reconstruction model is the reported CSI, and the output parameter is the original data of the channel.

[0156] 2) AI / ML model transfer

[0157] If the CSI generation model is trained by the network, the trained CSI generation model can be sent by the network to the UE for model inference. This model transmission is called AI / ML model transfer.

[0158] 3) AI / ML model inference

[0159] Taking the CSI generation model as an example, the process by which the UE generates CSI reports using a CSI generation model is the inference process of the AI / ML model. Similarly, the process by which the network generates raw channel data using a CSI reconstruction model is also the inference process of the AI / ML model.

[0160] 4) AI / ML model monitoring

[0161] The network or UE needs to monitor the AI / ML model used to determine whether the model is applicable to the current channel status.

[0162] 5) AI / ML model update

[0163] When the network or UE deems the model no longer applicable, the AI / ML model will be updated.

[0164] Hereinafter, specific examples and embodiments of the present invention will be described in detail. As described above, the examples and embodiments described in this disclosure are provided for illustrative purposes to facilitate understanding of the present invention and are not intended to limit the present invention.

[0165] [Example 1]

[0166] Figure 1 It is a schematic diagram showing the basic process of the method executed by the user equipment according to the first embodiment of the present invention.

[0167] Next, combine Figure 1 The basic process diagram shown is used to describe in detail the method executed by the user equipment according to the first embodiment of the present invention.

[0168] like Figure 1 As shown, in the first embodiment of the present invention, the steps performed by the user equipment include:

[0169] In step S101, the user equipment receives a media access control element (MAC CE) sent by the network.

[0170] The MAC CE is carried by the physical downlink shared channel PDSCH.

[0171] Furthermore, the MAC CE carries an activation command for semi-persistent CSI reporting.

[0172] In step S102, the user equipment sends a physical uplink control channel PUCCH.

[0173] The PUCCH carries HARQ feedback information (HARQ-ACK) for the PDSCH transmission.

[0174] And, the PUCCH is sent in time slot n.

[0175] In step S103, the user equipment reports channel state information CSI to the network.

[0176] As a method, if the user equipment (generating the CSI report) uses an artificial intelligence / machine learning (AI / ML) model, and / or there is at least one available (or effective) artificial intelligence / machine learning (AI / ML) model, then the user equipment is selected from the time slot The semi-persistent CSI reporting is performed on the (periodically configured) PUCCH resource starting from the first time slot after the time slot; otherwise, optionally, the user equipment starts from the time slot The semi-persistent CSI reporting is performed on the (periodically configured) PUCCH resource starting from the first time slot after the HARQ feedback information is received. Wherein, μ represents the subcarrier spacing configuration information corresponding to the PUCCH carrying HARQ feedback information or the PUCCH carrying semi-persistent CSI reporting. The meaning of X can be:

[0177] At least as determined by the inference delay / time / latency of the AI / ML model;

[0178] X is a value related to the minimum (or maximum) inference time of the artificial intelligence / machine learning (AI / ML) model;

[0179] ■ X is a value related to the (artificial intelligence / machine learning) capability of the user device, and is a configured or predefined numerical value representing time.

[0180] X may not be a value that directly represents time, but rather a unitless numerical value that indirectly represents time, and the length of time is represented only by its value. That is, a larger value of X indicates a longer delay.

[0181] Alternatively, if the user equipment (generating the CSI report) uses an artificial intelligence / machine learning (AI / ML) model, and / or there is at least one available (or effective) artificial intelligence / machine learning (AI / ML) model, then the user equipment selects the time slot (or, n+X (ms)) after the first time slot (periodically configured) PUCCH resources to perform the semi-persistent CSI reporting; otherwise, optionally, the user equipment from the time slot The semi-persistent CSI reporting is performed on the (periodically configured) PUCCH resource starting from the first time slot after the HARQ feedback information is received. Wherein, μ represents the subcarrier spacing configuration information corresponding to the PUCCH carrying HARQ feedback information or the PUCCH carrying semi-persistent CSI reporting. The meaning of X can be:

[0182] At least as determined by the inference delay / time / latency of the AI / ML model;

[0183] X is a value related to the minimum (or maximum) inference time of the artificial intelligence / machine learning (AI / ML) model;

[0184] ■ X is a value related to the (artificial intelligence / machine learning) capability of the user device, and is a configured or predefined numerical value representing time.

[0185] X may not be a value that directly represents time, but rather a unitless numerical value that indirectly represents time, and the length of time is represented only by its value. That is, a larger value of X indicates a longer delay.

[0186] As another example, if the configuration information of the semi-persistent CSI reporting includes configuration information about artificial intelligence / machine learning (AI / ML), the configuration information may optionally be in the form of:

[0187] ■ ID of the CSI reconstruction model;

[0188] ■ ID of the CSI generated model;

[0189] ■ IDs of the paired CSI generation model and reconstruction model;

[0190] The ID of the dataset used to train the model.

[0191] ■The training process ID for training the model.

[0192] Then, the user equipment from the time slot The semi-persistent CSI reporting is performed on the (periodically configured) PUCCH resource starting from the first time slot after the time slot; otherwise, optionally, the user equipment starts from the time slot The semi-persistent CSI reporting is performed on the (periodically configured) PUCCH resource starting from the first time slot after the HARQ feedback information is received. Wherein, μ represents the subcarrier spacing configuration information corresponding to the PUCCH carrying HARQ feedback information or the PUCCH carrying semi-persistent CSI reporting. The meaning of X can be:

[0193] At least as determined by the inference delay / time / latency of the AI / ML model;

[0194] X is a value related to the minimum (or maximum) inference time of the artificial intelligence / machine learning (AI / ML) model;

[0195] ■ X is a value related to the (artificial intelligence / machine learning) capability of the user device, and is a configured or predefined numerical value representing time.

[0196] X is not a value that directly represents time, but a unitless numerical value used to indirectly represent time. The length of time is simply represented by its value. In other words, a larger value of X indicates a longer delay.

[0197] As another example, if the configuration information of the semi-persistent CSI reporting includes configuration information about artificial intelligence / machine learning (AI / ML), the configuration information may optionally be in the form of:

[0198] ■ ID of the CSI reconstruction model;

[0199] ■ ID of the CSI generated model;

[0200] ■ IDs of the paired CSI generation model and reconstruction model;

[0201] The ID of the dataset used to train the model.

[0202] ■The training process ID for training the model.

[0203] Then, the user equipment from the time slot (or, n+X (ms)) after the first time slot (periodically configured) PUCCH resources to perform the semi-persistent CSI reporting; otherwise, optionally, the user equipment from the time slot The semi-persistent CSI reporting is performed on the (periodically configured) PUCCH resource starting from the first time slot after the HARQ feedback information is received. Wherein, μ represents the subcarrier spacing configuration information corresponding to the PUCCH carrying HARQ feedback information or the PUCCH carrying semi-persistent CSI reporting. The meaning of X can be:

[0204] At least as determined by the inference delay / time / latency of the AI / ML model;

[0205] X is a value related to the minimum (or maximum) inference time of the artificial intelligence / machine learning (AI / ML) model;

[0206] ■ X is a value related to the (artificial intelligence / machine learning) capability of the user device, and is a configured or predefined numerical value representing time.

[0207] X is not a value that directly represents time, but a unitless numerical value used to indirectly represent time. The length of time is simply represented by its value. In other words, a larger value of X indicates a longer delay.

[0208] Figure 2 1 is a block diagram showing the user equipment UE involved in the present invention. Figure 2As 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, a volatile memory (such as a random access memory (RAM), a hard disk drive (HDD), a non-volatile memory (such as a flash memory), or other memory. The memory 202 stores program instructions. When executed by the processor 201, the instructions may execute the above-described method performed by the user equipment as described in detail in the present invention.

[0209] The method of the present invention and the related devices have been described above in conjunction with the preferred embodiments. Those skilled in the art will understand that the method shown above is only exemplary, and the various embodiments described above can be combined with each other when no contradiction occurs. The method of the present invention is not limited to the steps and sequence shown above. The network node and user equipment shown above may include more modules, for example, modules that can be developed or developed in the future and can be used for base stations, MMEs, or UEs, etc. The various identifiers shown above are only exemplary and not restrictive, and the present invention is not limited to the specific information elements used as examples of these identifiers. Those skilled in the art can make many changes and modifications based on the teachings of the illustrated embodiments.

[0210] It should be understood that the above embodiments of the present invention can be implemented through software, hardware, or a combination of software and hardware. For example, the various components within the base station and user equipment in the above embodiments can be implemented through 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 the like.

[0211] In this application, "base station" refers to a mobile communication data and control switching center with high transmission power and wide coverage area, including functions such as resource allocation and scheduling, and data reception and transmission. "User equipment" refers to a user's mobile terminal, such as a mobile phone or laptop, that can communicate wirelessly with a base station or micro base station.

[0212] In addition, the embodiments of the present invention disclosed herein can be implemented on a computer program product. More specifically, the computer program product is a product as follows: having a computer-readable medium, on which computer program logic is encoded, and when executed on a computing device, the computer program logic provides relevant operations to implement the above-mentioned 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 arrangement of the present invention is typically provided as software, code and / or other data structures arranged or encoded on a computer-readable medium such as an optical medium (e.g., CD-ROM), a floppy disk or a hard disk, or other media such as firmware or microcode on one or more ROM or RAM or PROM chips, or downloadable software images, shared databases, etc. in one or more modules. Software or firmware or this configuration can be installed on a computing device so that one or more processors in the computing device execute the technical solutions described in the embodiments of the present invention.

[0213] In addition, each functional module or each feature of the base station equipment and terminal equipment used in each of the above embodiments can be implemented or executed by a circuit, and the circuit is generally one or more integrated circuits. The circuit designed to perform the various functions described in this specification may include a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC) or a general-purpose integrated circuit, a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, or a discrete hardware component, or any combination of the above devices. The general-purpose processor may be a microprocessor, or the processor may be an existing processor, a controller, a microcontroller or a state machine. The general-purpose processor or each circuit may be configured by a digital circuit, or may be configured by a logic circuit. In addition, when, due to advances in semiconductor technology, an advanced technology that can replace current integrated circuits emerges, the present invention may also use the integrated circuit obtained using the advanced technology.

[0214] Although the present invention has been described above in conjunction with the preferred embodiments of the present invention, it will be understood by those skilled in the art that various modifications, substitutions, and changes may be made to the present invention without departing from the spirit and scope of the present invention. Therefore, the present invention should not be limited by the above-described embodiments, but should be limited by the appended claims and their equivalents.

Claims

1. A method performed by a user equipment, comprising: receiving a media access control layer control element MAC CE sent by a network, where the MAC CE carries semi-persistent CSI reporting indication information related to reporting of channel state information CSI; Sending a physical uplink control channel (PUCCH) to the network in the first time slot; and sending a CSI report to a network on a PUCCH resource starting from a second time slot delayed by a given delay time relative to the first time slot, In any of the following cases, the given delay time is determined based on a delay parameter related to use of the AI / ML model by the user equipment: The user equipment uses the artificial intelligence / machine learning AI / ML model when generating the CSI report; There exists at least one valid AI / ML model for generation of the CSI report by the user equipment; The semi-persistent CSI reporting configuration information includes configuration information of the AI / ML model.

2. The method according to claim 1, wherein The given delay time is greater than 3ms.

3. The method according to claim 1, wherein The delay parameter is determined by any of the following methods: The delay parameter is determined according to an inference time of the user equipment using the AI / ML model to perform inference; The delay parameter is the maximum value among the inference times of multiple user devices using the AI / ML model to perform inference; The delay parameter is a minimum value among the inference times of multiple user devices using the AI / ML model to perform inference; The delay parameter is a value configured by the network through an RRC parameter; The delay parameter is a predefined given value.

4. The method according to any one of claims 1 to 3, wherein When the delay parameter is set to X, The given delay time is given by The value represented by Indicates the number of time slots contained in a subframe.

5. The method according to any one of claims 1 to 3, wherein When the delay parameter is set to X, The given delay time is given by The value represented by Indicates the number of time slots contained in a subframe.

6. The method according to any one of claims 1 to 3, wherein The AI / ML model configuration information includes at least one of the following: Identification of the CSI reconstruction model; Identification of the CSI generation model; Identification of paired CSI generation and reconstruction models; The identity of the dataset on which the model was trained; The training process identifier for training the model.

7. A user equipment, comprising: processor; as well as a memory storing instructions; The instructions, when executed by the processor, perform the method according to any one of claims 1 to 6.

Images