Data request method and apparatus for ai / ML model in beam management

Abstract

The present disclosure provides a data request method and apparatus for an AI / ML model in beam management. The method comprises: user equipment sending a data request message to a network device, wherein the data request message is used to request the network device to send a target reference signal, and the target reference signal is used by the user equipment to perform data collection for an AI / ML model in beam management.

Description

Data request method and device for AI / ML models in beam management

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 2024101750028, filed on February 7, 2024, entitled “Data request method and device for AI / ML model in beam management”, which is incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates to the field of wireless communication technologies, and more particularly to a method and device for requesting data for an AI / ML model in beam management. Background Art

[0004] In New Radio (NR) downlink beam management, network equipment scans the terminal's receive beam in each downlink transmit beam direction. The terminal (User Equipment, UE) finds the optimal receive beam pair by measuring the reference signal received power (RSRP) of the reference signal on each transmit beam and receive beam pair, and uses it for subsequent downlink channel / signal reception. To alleviate the high signal overhead of the Channel State Information-Reference Signal (CSI-RS) / Synchronization Signal and PBCH Block (SSB) in beam management, a beam management method based on artificial intelligence (AI) / machine learning (ML) is proposed. This method uses AI / ML models to predict the optimal downlink beam or beam pair.

[0005] Before using an AI / ML model for prediction, it is necessary to train the AI / ML model, and during the training process, the performance of the AI / ML model needs to be evaluated. The 3rd Generation Partnership Project (3GPP) has proposed a performance monitoring method, which is to judge the performance of the AI / ML model by comparing the actual measurement results of the terminal with the model inference results. Currently, for performance monitoring methods triggered by the terminal, the relevant technology lacks the design of the terminal-triggered performance monitoring process and the design method of request signaling. Summary of the Invention

[0006] In response to the problems existing in the related technologies, the embodiments of the present disclosure provide a data request method and device for an AI / ML model in beam management.

[0007] In a first aspect, an embodiment of the present disclosure provides a data request method for an AI / ML model in beam management, which is applied to a terminal and includes:

[0008] Sending a data request message to a network device; the data request message is used to request the network device to send a target reference signal; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0009] In some embodiments, the data request message includes one or more of the following:

[0010] Identification information of AI / ML models;

[0011] Function identification information of AI / ML models;

[0012] Resource collection identification information of AI / ML models;

[0013] trigger identification information or configuration identification information;

[0014] Reference signal collection information for AI / ML models;

[0015] Performance monitoring performance indicator information;

[0016] Time requirement information of target reference signal;

[0017] Periodic type information of the target reference signal;

[0018] Periodic information of the target reference signal;

[0019] Number information of target reference signals;

[0020] Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result;

[0021] Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

[0022] In some embodiments, the data request message indicates the target reference signal based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information.

[0023] In some embodiments, the method further comprises:

[0024] receiving a data response message sent by the network device, and determining, based on the data response message, whether the network device sends the target reference signal; or,

[0025] Receive target reference signal related information sent by the network device, and determine whether the network device sends the target reference signal based on the target reference signal related information.

[0026] In some embodiments, the data response message includes one or more of the following:

[0027] Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal;

[0028] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0029] Identification information of the target AI / ML model;

[0030] Function identification information of the target AI / ML model.

[0031] In some embodiments, determining, based on the data response message, whether the network device sends the target reference signal includes:

[0032] When a data response message sent by the network device is received within the first time window, determining that the network device sends the target reference signal;

[0033] If no data response message sent by the network device is received within the first time window, it is determined that the network device does not send the target reference signal.

[0034] In some embodiments, determining, based on the target reference signal related information, whether the network device sends the target reference signal includes:

[0035] When receiving target reference signal related information sent by the network device within the second time window, determining that the network device sends the target reference signal;

[0036] If no target reference signal related information sent by the network device is received within the second time window, it is determined that the network device does not send the target reference signal.

[0037] In some embodiments, sending a data request message to the network device includes:

[0038] receiving data request configuration information sent by the network device;

[0039] Based on the data request configuration information, a data request message is sent to the network device.

[0040] In some embodiments, the data request configuration information includes one or more of the following:

[0041] trigger identification information or configuration identification information;

[0042] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0043] Time domain information of the reference signal;

[0044] Frequency domain information of the reference signal.

[0045] In some embodiments, the data request message is sent based on one or more of a physical uplink control channel PUCCH, a physical uplink shared channel PUSCH, and a media access control layer control element MAC CE.

[0046] In a second aspect, an embodiment of the present disclosure further provides a data request method for an AI / ML model in beam management, which is applied to a network device, including:

[0047] receiving a data request message sent by a terminal;

[0048] Based on the data request message, a target reference signal is determined; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0049] In some embodiments, the data request message includes one or more of the following:

[0050] Identification information of AI / ML models;

[0051] Function identification information of AI / ML models;

[0052] Resource collection identification information of AI / ML models;

[0053] trigger identification information or configuration identification information;

[0054] Reference signal collection information for AI / ML models;

[0055] Performance monitoring performance indicator information;

[0056] Time requirement information of target reference signal;

[0057] Periodic type information of the target reference signal;

[0058] Periodic information of the target reference signal;

[0059] Number information of target reference signals;

[0060] Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result;

[0061] Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

[0062] In some embodiments, determining the target reference signal based on the data request message includes:

[0063] The target reference signal is determined based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

[0064] In some embodiments, after determining the target reference signal, the method further includes one or more of the following:

[0065] Sending a data response message to the terminal;

[0066] sending target reference signal related information to the terminal;

[0067] Sending the target reference signal to the terminal.

[0068] In some embodiments, the data response message includes one or more of the following:

[0069] Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal;

[0070] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0071] Identification information of the target AI / ML model;

[0072] Function identification information of the target AI / ML model.

[0073] In some embodiments, the sending a data response message to the terminal includes:

[0074] Within the first time window, a data response message is sent to the terminal.

[0075] In some embodiments, the sending target reference signal related information to the terminal includes:

[0076] In the second time window, target reference signal related information is sent to the terminal.

[0077] In some embodiments, the method further comprises:

[0078] Sending data request configuration information to the terminal.

[0079] In some embodiments, the data request configuration information includes one or more of the following:

[0080] trigger identification information or configuration identification information;

[0081] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0082] Time domain information of the reference signal;

[0083] Frequency domain information of the reference signal.

[0084] In some embodiments, the data response message is sent based on one or more of a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH, and a media access control layer control element MAC CE.

[0085] In a third aspect, an embodiment of the present disclosure further provides a terminal, including a memory, a transceiver, and a processor:

[0086] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0087] Sending a data request message to a network device; the data request message is used to request the network device to send a target reference signal; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0088] In some embodiments, the data request message includes one or more of the following:

[0089] Identification information of AI / ML models;

[0090] Function identification information of AI / ML models;

[0091] Resource collection identification information of AI / ML models;

[0092] trigger identification information or configuration identification information;

[0093] Reference signal collection information for AI / ML models;

[0094] Performance monitoring performance indicator information;

[0095] Time requirement information of target reference signal;

[0096] Periodic type information of the target reference signal;

[0097] Periodic information of the target reference signal;

[0098] Number information of target reference signals;

[0099] Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result;

[0100] Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

[0101] In some embodiments, the data request message indicates the target reference signal based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information.

[0102] In some embodiments, the operations further include:

[0103] receiving a data response message sent by the network device, and determining, based on the data response message, whether the network device sends the target reference signal; or,

[0104] Receive target reference signal related information sent by the network device, and determine whether the network device sends the target reference signal based on the target reference signal related information.

[0105] In some embodiments, the data response message includes one or more of the following:

[0106] Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal;

[0107] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0108] Identification information of the target AI / ML model;

[0109] Function identification information of the target AI / ML model.

[0110] In some embodiments, determining, based on the data response message, whether the network device sends the target reference signal includes:

[0111] When a data response message sent by the network device is received within the first time window, determining that the network device sends the target reference signal;

[0112] If no data response message sent by the network device is received within the first time window, it is determined that the network device does not send the target reference signal.

[0113] In some embodiments, determining, based on the target reference signal related information, whether the network device sends the target reference signal includes:

[0114] When receiving target reference signal related information sent by the network device within the second time window, determining that the network device sends the target reference signal;

[0115] If no target reference signal related information sent by the network device is received within the second time window, it is determined that the network device does not send the target reference signal.

[0116] In some embodiments, sending a data request message to the network device includes:

[0117] receiving data request configuration information sent by the network device;

[0118] Based on the data request configuration information, a data request message is sent to the network device.

[0119] In some embodiments, the data request configuration information includes one or more of the following:

[0120] trigger identification information or configuration identification information;

[0121] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0122] Time domain information of the reference signal;

[0123] Frequency domain information of the reference signal.

[0124] In some embodiments, the data request message is sent based on one or more of a physical uplink control channel PUCCH, a physical uplink shared channel PUSCH, and a media access control layer control element MAC CE.

[0125] In a fourth aspect, an embodiment of the present disclosure further provides a network device, including a memory, a transceiver, and a processor:

[0126] A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

[0127] receiving a data request message sent by a terminal;

[0128] Based on the data request message, a target reference signal is determined; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0129] In some embodiments, the data request message includes one or more of the following:

[0130] Identification information of AI / ML models;

[0131] Function identification information of AI / ML models;

[0132] Resource collection identification information of AI / ML models;

[0133] trigger identification information or configuration identification information;

[0134] Reference signal collection information for AI / ML models;

[0135] Performance monitoring performance indicator information;

[0136] Time requirement information of target reference signal;

[0137] Periodic type information of the target reference signal;

[0138] Periodic information of the target reference signal;

[0139] Number information of target reference signals;

[0140] Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result;

[0141] Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

[0142] In some embodiments, determining the target reference signal based on the data request message includes:

[0143] The target reference signal is determined based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

[0144] In some embodiments, after determining the target reference signal, the operations further include one or more of the following:

[0145] Sending a data response message to the terminal;

[0146] sending target reference signal related information to the terminal;

[0147] Sending the target reference signal to the terminal.

[0148] In some embodiments, the data response message includes one or more of the following:

[0149] Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal;

[0150] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0151] Identification information of the target AI / ML model;

[0152] Function identification information of the target AI / ML model.

[0153] In some embodiments, the sending a data response message to the terminal includes:

[0154] Within the first time window, a data response message is sent to the terminal.

[0155] In some embodiments, the sending target reference signal related information to the terminal includes:

[0156] In the second time window, target reference signal related information is sent to the terminal.

[0157] In some embodiments, the operations further include:

[0158] Sending data request configuration information to the terminal.

[0159] In some embodiments, the data request configuration information includes one or more of the following:

[0160] trigger identification information or configuration identification information;

[0161] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0162] Time domain information of the reference signal;

[0163] Frequency domain information of the reference signal.

[0164] In some embodiments, the data response message is sent based on one or more of a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH, and a media access control layer control element MAC CE.

[0165] In a fifth aspect, an embodiment of the present disclosure further provides a data request device for an AI / ML model in beam management, which is applied to a terminal and includes:

[0166] The first sending unit is used to send a data request message to a network device; the data request message is used to request the network device to send a target reference signal; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0167] In a sixth aspect, embodiments of the present disclosure further provide a data request device for an AI / ML model in beam management, applied to a network device, including:

[0168] A second receiving unit, configured to receive a data request message sent by a terminal;

[0169] The second determination unit is used to determine a target reference signal based on the data request message; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0170] In the seventh aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the data request method for the AI / ML model in beam management as described in the first aspect, or to execute the data request method for the AI / ML model in beam management as described in the second aspect.

[0171] In an eighth aspect, an embodiment of the present disclosure further provides a non-transitory readable storage medium, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the data request method for the AI / ML model in beam management as described in the first aspect, or to execute the data request method for the AI / ML model in beam management as described in the second aspect.

[0172] In the ninth aspect, an embodiment of the present disclosure further provides a communication device, in which a computer program is stored, and the computer program is used to enable the communication device to execute the data request method of the AI / ML model in beam management as described in the first aspect, or to execute the data request method of the AI / ML model in beam management as described in the second aspect.

[0173] In the tenth aspect, an embodiment of the present disclosure further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the data request method for the AI / ML model in beam management as described in the first aspect, or execute the data request method for the AI / ML model in beam management as described in the second aspect.

[0174] In the eleventh aspect, an embodiment of the present disclosure further provides a chip product, in which a computer program is stored, and the computer program is used to enable the chip product to execute the data request method of the AI / ML model in beam management as described in the first aspect, or to execute the data request method of the AI / ML model in beam management as described in the second aspect.

[0175] The embodiments of the present disclosure provide a method and apparatus for requesting data for an AI / ML model in beam management. When a terminal needs to collect data for the AI / ML model in beam management, the terminal can send a data request message to a network device to request the network device to send a target reference signal for the terminal to collect data, thereby enabling the terminal to actively trigger the data collection process for the AI / ML model in beam management. BRIEF DESCRIPTION OF THE DRAWINGS

[0176] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0177] FIG1 is a flowchart of a method for requesting data for an AI / ML model in beam management according to an embodiment of the present disclosure;

[0178] FIG2 is a second flow chart of a method for requesting data for an AI / ML model in beam management according to an embodiment of the present disclosure;

[0179] FIG3 is a schematic diagram of a process of triggering performance monitoring by a terminal according to an embodiment of the present disclosure;

[0180] FIG4 is a second schematic diagram of a process of triggering performance monitoring by a terminal according to an embodiment of the present disclosure;

[0181] FIG5 is a third flow diagram of terminal-triggered performance monitoring according to an embodiment of the present disclosure;

[0182] FIG6 is a fourth flow chart of terminal-triggered performance monitoring according to an embodiment of the present disclosure;

[0183] FIG7 is a fifth flow chart of terminal-triggered performance monitoring according to an embodiment of the present disclosure;

[0184] FIG8 is a schematic structural diagram of a terminal provided in an embodiment of the present disclosure;

[0185] FIG9 is a schematic diagram of the structure of a network device provided in an embodiment of the present disclosure;

[0186] FIG10 is a schematic diagram of a structure of a data requesting device for an AI / ML model in beam management according to an embodiment of the present disclosure;

[0187] FIG11 is a second structural diagram of the data request device for the AI / ML model in beam management provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0188] In the embodiments of the present disclosure, the term "and / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0189] In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar thereto.

[0190] In the embodiments of the present disclosure, "determine B based on A" means that the factor A must be considered when determining B. It is not limited to "B can be determined based on A alone", and should also include: "determine B based on A and C", "determine B based on A, C and E", "determine C based on A, and further determine B based on C", etc. It can also include taking A as a condition for determining B, for example, "when A meets the first condition, use the first method to determine B"; for example, "when A meets the second condition, determine B", etc.; for example, "when A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor in determining B, for example, "when A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0191] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0192] In order to better understand the various embodiments of the present disclosure, a brief introduction to the related technologies of the embodiments of the present disclosure is first given.

[0193] Current AI / ML-based beam management research focuses on two sub-use cases: spatial prediction and temporal prediction. BM-case 1 involves spatial prediction of downlink beams, using measurement results from SetB to predict the optimal beam in SetA. BM-case 2 involves temporal prediction of downlink beams, using past measurement results from SetB to predict the optimal beam in SetA in the future.

[0194] For model performance parameters, currently include:

[0195] (1) Key Performance Indicators (KPIs) related to beam prediction accuracy, such as Top-K / 1 beam prediction accuracy.

[0196] (2) Link performance-related KPIs, such as throughput, Layer 1 Reference Signal Received Power (L1-RSRP), Layer 1 Signal to Interference plus Noise Ratio (L1-SINR), and Block Error Rate (BLER).

[0197] (3) Performance parameters based on AI / ML data distribution.

[0198] (4) L1-RSRP difference based on measured RSRP and predicted RSRP.

[0199] For model monitoring types, currently they include:

[0200] (1) Model monitoring based on the model level, such as model monitoring based on model identification (ID).

[0201] (2) Function-level model monitoring. For example, the base station sends a set of configuration information for implementing an AI / ML model function. The UE has a model ID for implementing the AI / ML model function. For example, mode #1 to model #4 are all for implementing the 8-prediction 32 beam prediction function.

[0202] In the current CSI-RS measurement and reporting framework, the base station configures periodic, semi-periodic, and aperiodic reference signals for the UE for CSI-RS measurement and reporting. For network-triggered performance monitoring, a straightforward approach is for the base station to configure SetA for the terminal, which the UE uses to measure and obtain the true optimal beam. Furthermore, SetB is configured for the UE to infer the optimal beam based on the AI / ML model. The terminal compares the measured optimal beam with the optimal beam inferred by the AI / ML model to obtain AI / ML performance monitoring metrics.

[0203] However, for UE-triggered performance monitoring, the first thing to do is to solve the design problem of the UE sending request signaling, and the second is the operation of the base station after receiving the request signaling. In the existing NR system, there is no similar design that can be reused. Based on this situation, the present disclosure proposes a data request method and device for AI / ML models in beam management.

[0204] FIG1 is a flow chart of a method for requesting data for an AI / ML model in beam management according to an embodiment of the present disclosure. As shown in FIG1 , the method is applied to a terminal and includes the following steps:

[0205] Step 100: Send a data request message to the network device; the data request message is used to request the network device to send a target reference signal; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0206] Specifically, the network device in the embodiment of the present disclosure may be an access network device (e.g., a base station), and the target reference signal refers to a reference signal that the terminal desires to obtain for collecting data for the AI / ML model in beam management. The performance monitoring, model reasoning, model training, and model modification of the AI / ML model can be performed in subsequent processes based on the data collected by the terminal. The processing procedures for performance monitoring, model reasoning, model training, and model modification of the AI / ML model may refer to existing or future related technologies and are not elaborated in the embodiment of the present disclosure.

[0207] In an embodiment of the present disclosure, when a terminal needs to collect data for an AI / ML model in beam management, the terminal may send a data request message to a network device, where the data request message is used to request the network device to send a target reference signal.

[0208] In some embodiments, the terminal may send a data request message based on one or more of a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), and a media access control layer control element (MAC CE).

[0209] After receiving the data request message, the network device can determine the target reference signal that the terminal wants to obtain and perform subsequent processing based on the resource conditions in the network.

[0210] The embodiment of the present disclosure provides a data request method for the AI / ML model in beam management. When a terminal needs to collect data for the AI / ML model in beam management, the terminal can send a data request message to a network device to request the network device to send a target reference signal for the terminal to collect data, so that the terminal can actively trigger the data collection process for the AI / ML model in beam management.

[0211] In some embodiments, the data request message may include one or more of the following:

[0212] (1) Identification information of the AI / ML model.

[0213] Specifically, the data request message may include identification information of one or more AI / ML models, and the network device may determine that the reference signal associated with the identification of the one or more AI / ML models is the target reference signal.

[0214] The association between the identifier of the AI / ML model and the reference signal may be configured or pre-configured by a network device. The association may be an association between the identifier of each AI / ML model and each reference signal set. In some implementations, for the BM case-2 sub-use case, the association may also be an association between the identifier of each AI / ML model and each reference signal and the time domain information of each reference signal, thereby indicating the time domain information of the target reference signal based on the identifier of the AI / ML model.

[0215] For example, the terminal collects data for the AI / ML model based on the measurement of the setA set and the setB set. The relationship between the AI / ML model ID and the reference signal has been established between the network device and the terminal. For example, Model#1 is associated with the setA set and the setB set. If it is the BM case-1 sub-use case, when Model#1 is included in the data request message, it means that the terminal requests the network device to send the reference signals included in the setA set and the setB set. If it is the BM case-2 sub-use case, the data request message contains Model#1 and can also indicate the time domain information of the reference signals in the setA set and the setB set.

[0216] For another example, the network device configures AI / ML model data collection based on setB set measurement based on Radio Resource Control (RRC) signaling, or configures AI / ML model data collection based on setA set and setB set measurement.

[0217] If RRC signaling configures an AI / ML model to measure based on setB, the terminal can request the transmission of the reference signals included in setB using the AI / ML model ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model ID in the data request message can also indicate the time domain information of the reference signals in setB.

[0218] If RRC signaling configures an AI / ML model to measure based on setA and setB, the terminal can request the transmission of the reference signals included in setA and setB using the AI / ML model ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model ID in the data request message can also indicate the time domain information of the reference signals in setA and setB.

[0219] (2) Functional identification information of the AI / ML model.

[0220] Specifically, the data request message may include function identification information of one or more AI / ML models, and the network device may determine that the reference signal associated with the function identification of the one or more AI / ML models is the target reference signal.

[0221] The association relationship between the function identifier of the AI / ML model and the reference signal may be configured or pre-configured by a network device. The association relationship may be an association relationship between the function identifier of each AI / ML model and each reference signal set. In some implementations, for the BM case-2 sub-use case, the association relationship may also be an association relationship between the function identifier of each AI / ML model and each reference signal and the time domain information of each reference signal, so that the time domain information of the target reference signal can be indicated according to the function identifier of the AI / ML model.

[0222] For example, the terminal collects data for the AI / ML model based on the measurement of the setA set and the setB set. The relationship between the AI / ML model function ID and the reference signal has been established between the network device and the terminal. For example, model function #1 is associated with the setA set and the setB set. If it is the BM case-1 sub-use case, when the data request message includes model function #1, it means that the terminal requests the network device to send the reference signals included in the setA set and the setB set. If it is the BM case-2 sub-use case, the data request message includes model function #1 and can also indicate the time domain information of the reference signals in the setA set and the setB set.

[0223] For another example, the network device configures AI / ML model data collection based on setB set measurement based on RRC signaling, or configures AI / ML model data collection based on setA set and setB set measurement.

[0224] If RRC signaling configures an AI / ML model to measure based on the setB set, the terminal can request the transmission of the reference signals included in the setB set using the AI / ML model function ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model function ID in the data request message can also indicate the time domain information of the reference signals in the setB set.

[0225] If RRC signaling configures an AI / ML model to measure based on setA and setB, the terminal can request the transmission of the reference signals included in setA and setB using the AI / ML model function ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model function ID in the data request message can also indicate the time domain information of the reference signals in setA and setB.

[0226] (3) Resource collection identification information of AI / ML models.

[0227] Specifically, the data request message may include resource set identification information of one or more AI / ML models, and the network device may determine that the reference signal resource set corresponding to the reference signal resource set identification of the one or more AI / ML models is the target reference signal.

[0228] Among them, the resource collection identifier of each AI / ML model can be configured or pre-configured through network equipment.

[0229] (4) Trigger identification information or configuration identification information.

[0230] Specifically, the data request message may include one or more trigger identification information, or the data request message may include one or more configuration identification information, the trigger identification information is used to indicate that the reference signal associated with the one or more trigger identifications is the target reference signal, and the configuration identification information is used to indicate that the reference signal associated with the one or more configuration identifications is the target reference signal.

[0231] The association between the trigger identifier / configuration identifier and the reference signal may be configured or pre-configured by a network device. In some implementations, the association may also be an association between each trigger identifier / configuration identifier and each reference signal, the time domain information of each reference signal, and the frequency domain information of each reference signal, thereby indicating what time and frequency domain resources the target reference signal occupies based on the trigger identifier / configuration identifier.

[0232] For example, trigger ID#1 can be configured to associate the reference signals of setA and setB for AI / ML model 1, their frequency domain positions in the time slot, and the time slot offset from the data request message. When trigger ID#1 is included in the data request message, it indicates that the terminal requests the network device to send the reference signals of setA and setB at the corresponding time-frequency domain positions.

[0233] (5) Reference signal set information for AI / ML models.

[0234] Specifically, the data request message may include reference signal set information of one or more AI / ML models, and the network device may determine the reference signal set of the one or more AI / ML models as the target reference signal.

[0235] For example, the reference signal set information of the AI / ML model may be setB; or, the reference signal set information of the AI / ML model may be setA; or, the reference signal set information of the AI / ML model may be setA and setB.

[0236] The reference signal set information of the AI / ML model can be optional information based on the terminal capabilities, or configured based on high-layer signaling.

[0237] When the data request message also indicates an AI / ML model, in some implementations, the reference signal set information of the AI / ML model can be applied to all AI / ML models indicated by the data request message; in some implementations, the reference signal set information of the AI / ML model can be applied to a certain AI / ML model. If multiple AI / ML models are indicated in the data request message, each AI / ML model can be associated with one reference signal set information.

[0238] In some embodiments, the reference signal set information of the AI / ML model can be indicated based on a bit map, for example, where the first bit represents setA, one state indicates indicating set A, and another state indicates not indicating setA; another bit identifies setB, one state indicates indicating setB, and another state indicates not indicating setB.

[0239] In some implementations, the reference signal set information of the AI / ML model may be indicated using 1 bit, where one state represents setB and the other state represents both setA and setB.

[0240] (6) Performance monitoring performance indicator information.

[0241] Specifically, the data request message may include performance monitoring performance indicator information, which is used to instruct the terminal what performance indicators to use to monitor the performance of the AI / ML model. The network device can determine the target reference signal based on the performance indicators.

[0242] Performance monitoring performance indicator information can be optional information based on terminal capabilities, or configured based on high-layer signaling.

[0243] In some implementations, different numerical values ​​may be used to indicate different performance indicators. For example, when the performance monitoring indicator information is a value of 1, indicating that the optimal beam probability is used as the model performance calculation indicator, the network device may determine setA and setB as target reference signals. When the performance monitoring indicator information is a value of 2, indicating that the RSRP difference of setB is used as the model performance calculation indicator, the network device may determine setB as the target reference signal.

[0244] (7) Time requirement information of target reference signal.

[0245] Specifically, the data request message may include time requirement information of the target reference signal, which is used to indicate at what time the terminal wants the network device to send the target reference signal. The network device can determine whether the target reference signal can be sent and within what time period the target reference signal can be sent based on the time requirement information of the target reference signal.

[0246] In some implementations, operations of the network device corresponding to different target reference signal time requirement information may be pre-set or configured by the network device.

[0247] For example, the time requirement information of the target reference signal is represented by the reference signal priority. The reference signal priority includes two types: high priority and low priority.

[0248] When the terminal's time requirement for the target reference signal is high priority, it means that the terminal's request for performance monitoring is urgent. When the network device determines to send the reference signal, it will send the reference signal to the terminal within a set time interval, that is, the reference signal will be sent to the terminal as soon as possible; when the terminal's time requirement for the target reference signal is low priority, it means that the terminal's request for performance monitoring is low urgency. When the network device determines to send the signal, it will send the reference signal to the terminal at an appropriate time, that is, the sending time depends on the implementation of the network device.

[0249] (8) Periodic type information of the target reference signal.

[0250] Specifically, the data request message may include the periodic type information of the target reference signal, which is used to indicate the periodic type of the target reference signal that the terminal wants the network device to send. The network device can determine whether the target reference signal of this periodic type can be sent and what periodic type of target reference signal to send based on the periodic type information of the target reference signal and the resource situation.

[0251] The period type information of the target reference signal may include one or more of an aperiodic reference signal, a semi-periodic reference signal, and a periodic reference signal.

[0252] In some implementations, the terminal's requirements for reference signal periodicity can be ranked, with the requirements ranking from smallest to largest: aperiodic reference signal < semi-periodic reference signal < periodic reference signal. A network device can select and transmit reference signals with a lower level than the terminal's requirements, but cannot select and transmit reference signals with a higher level than the terminal's requirements.

[0253] For example, the terminal requests a semi-periodic reference signal from the network device. Based on the resource situation in the network, the network device may send the semi-periodic reference signal or the aperiodic reference signal, but may not send the periodic reference signal.

[0254] In some implementations, the terminal sends the requested reference signal periodicity type to the network device, and the network device directly sends the reference signal according to the type requested by the terminal. For example, if the terminal requests a semi-periodic reference signal from the network device, if the network device decides to send the target reference signal, it sends it according to the semi-periodic reference signal type.

[0255] (9) Periodic information of the target reference signal.

[0256] Specifically, the data request message may include the period information of the target reference signal, which is used to indicate the period at which the terminal wants the network device to send the target reference signal. The network device can determine whether the target reference signal can be sent with this period and at what period the target reference signal can be sent based on the period information of the target reference signal and the resource situation.

[0257] In some implementations, the period information of the target reference signal may be a period length expected by the terminal, such as a value among several candidate periods. The period length of the reference signal actually sent by the network device may be different from the period requested by the terminal.

[0258] In some implementations, the period information of the target reference signal may be a period length required by the terminal, such as a value among several candidate periods. The period length of the reference signal actually sent by the network device may be the same as the period requested by the terminal.

[0259] (10) Information on the number of target reference signals.

[0260] Specifically, the data request message may include target reference signal number information, which is used to indicate the number of times the terminal wants the network device to send the target reference signal. The network device can determine whether the target reference signal can be sent that number of times and at what number of times the target reference signal can be sent based on the target reference signal number information and resource conditions.

[0261] In some implementations, the target reference signal frequency information may be the frequency expected by the terminal, such as a value among several candidate frequencies. The number of reference signals actually sent by the network device may be different from the number requested by the terminal.

[0262] In some implementations, the target reference signal frequency information may be the frequency required by the terminal, such as a value among several candidate frequencies. The number of reference signals actually sent by the network device may be the same as the number requested by the terminal.

[0263] (11) Performance indicator indication information: The performance indicator indication information is used to indicate whether the terminal reports the performance indicator result.

[0264] Specifically, the data request message may include performance indicator indication information for indicating whether the terminal reports the performance indicator result. The network device may determine whether to configure performance indicator result reporting resources for the terminal based on the performance indicator indication information.

[0265] (12) Actual measurement indication information: The actual measurement indication information is used to instruct the terminal whether to report the actual measurement result.

[0266] Specifically, the data request message may include actual performance measurement information for indicating whether the terminal reports the actual measurement result. The network device may determine whether to configure actual measurement result reporting resources for the terminal based on the actual measurement indication information.

[0267] In some embodiments, the data request message may indicate a target reference signal based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information.

[0268] Specifically, the terminal may indicate the target reference signal in the form of the data request message itself, that is, the data request message may indicate different target reference signals through different request signaling-specific formats, different request signaling scrambling sequences, or different request signaling-specific identification information.

[0269] For example, if the network device configures an AI / ML beam management function for the terminal, such as the function of predicting the optimal beam among 32 beams using 8 beams, the data request message does not need to include the function ID. Instead, the request for the reference signal associated with this function can be indicated by requesting a dedicated signaling format, requesting a signaling scrambling sequence, or requesting dedicated signaling identification information. In the case of BM case-2, the time domain information of setB and / or setA can also be indicated by requesting a dedicated signaling format, requesting a signaling scrambling sequence, or requesting dedicated signaling identification information.

[0270] In some embodiments, the method further comprises:

[0271] receiving a data response message sent by the network device, and determining whether the network device sends a target reference signal based on the data response message; or,

[0272] Receive target reference signal related information sent by the network device, and determine whether the network device sends the target reference signal based on the target reference signal related information.

[0273] Specifically, after sending the data request message, the terminal may determine whether the network device will send the target reference signal according to the data response message or target reference signal related information sent by the network device.

[0274] In some implementations, after receiving a data request message sent by a terminal, the network device may send a data response message to the terminal. The terminal may determine whether the network device sends a target reference signal through the data response message. This method provides the network device with a method for flexibly determining the sending time of the target reference signal.

[0275] In some embodiments, the data response message may be sent based on one or more of a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), and a MAC CE.

[0276] In some embodiments, the data response message may include one or more of the following:

[0277] (1) Reference signal indication information: The reference signal indication information is used to indicate whether to send a target reference signal.

[0278] Specifically, the data response message may include reference signal indication information, which may directly indicate whether the network device should transmit the target reference signal. For example, if the network device sends a "confirmed" reference signal indication to the terminal, it indicates that the network device will respond to the terminal's request. If the network device cannot transmit the reference signal, it sends a "non-confirmed" reference signal indication to the terminal, indicating that the network device will not respond to the terminal's request.

[0279] (2) Request message indication information: The request message indication information is used to indicate the data request message corresponding to the data response message.

[0280] Specifically, the data response message may include request message indication information, which may indicate the data request message to which the data response message corresponds. For example, if a terminal sends multiple data request messages, the network device may reply with multiple data response messages, each of which includes request message indication information, so that the terminal can determine the data request message to which each data response message corresponds.

[0281] (3) Identification information of the target AI / ML model.

[0282] Specifically, the data response message may include identification information of a target AI / ML model, where the target AI / ML model refers to an AI / ML model to which the network device can send a corresponding target reference signal.

[0283] For example, a terminal sends a data request message to a network device. The data request message includes the identification information of multiple AI / ML models, namely Model #1, Model #2, and Model #3, indicating that the terminal requests data collection for these models. After receiving the data request message, the network device determines, based on resource availability, that it can send the reference signal associated with Model #1, but cannot send the reference signals associated with Model #2 and Model #3 within a certain period of time. In this case, the network device can confirm the transmission of the reference signal for Model #1 and include Model #1 in the data response message, allowing the terminal to confirm that the network device can send the reference signal associated with Model #1.

[0284] (4) Functional identification information of the target AI / ML model.

[0285] Specifically, the data response message may include functional identification information of the target AI / ML model, where the target AI / ML model refers to an AI / ML model to which the network device can send a corresponding target reference signal.

[0286] For example, a terminal sends a data request message to a network device. The data request message includes the function identification information of multiple AI / ML models, namely model function #1, model function #2, and model function #3. That is, the terminal requests data collection for the models of these functions. After receiving the data request message, the network device determines that it can send the reference signal associated with model function #1 based on the resource situation, but cannot send the reference signals associated with model function #2 and model function #3 within a certain period of time. In this case, the network device can confirm the transmission of the reference signal of model function #1 and carry model function #1 in the data response message, so that the terminal can determine that the network device can send the reference signal associated with model function #1.

[0287] In some embodiments, determining whether the network device sends a target reference signal based on the data response message includes:

[0288] When a data response message sent by the network device is received within the first time window, determining that the network device sends a target reference signal;

[0289] If no data response message sent by the network device is received within the first time window, it is determined that the network device does not send the target reference signal.

[0290] Specifically, the first time window can be set in advance. The first time window can be in time slots, and its value can be high-level configuration / protocol provisions / defined based on terminal capabilities. The starting point of the first time window can be the moment when the terminal sends a data request message, or the moment when the network device receives the data request message, or other reasonable moments set according to actual conditions.

[0291] The terminal may determine whether the network device sends the target reference signal according to whether a data response message sent by the network device can be received within the first time window.

[0292] If the terminal receives a data response message sent by the network device within the first time window, the terminal can determine that the network device sends a target reference signal; if the terminal does not receive a data response message sent by the network device within the first time window, the terminal can determine that the network device does not send a target reference signal.

[0293] In some embodiments, determining whether the network device sends the target reference signal based on the target reference signal related information includes:

[0294] When receiving target reference signal related information sent by the network device within the second time window, determining that the network device sends the target reference signal;

[0295] If the target reference signal related information sent by the network device is not received within the second time window, it is determined that the network device does not send the target reference signal.

[0296] Specifically, a second time window can be set in advance. The second time window can be in time slots, and its value can be high-level configuration / protocol provisions / defined based on terminal capabilities. The starting point of the second time window can be the moment when the terminal sends a data request message, or the moment when the network device receives the data request message, or other reasonable moments set according to actual conditions.

[0297] The terminal may determine whether the network device sends the target reference signal based on whether the target reference signal related information sent by the network device can be received within the second time window.

[0298] If the terminal receives the target reference signal related information sent by the network device within the second time window, the terminal can determine that the network device sends the target reference signal; if the terminal does not receive the target reference signal related information sent by the network device within the second time window, the terminal can determine that the network device does not send the target reference signal.

[0299] In some embodiments, sending a data request message to a network device includes:

[0300] Receiving data request configuration information sent by a network device;

[0301] Based on the data request configuration information, a data request message is sent to the network device.

[0302] Specifically, the terminal may first receive data request configuration information sent by the network device, where the data request configuration information is information used to directly trigger the network device to send a target reference signal.

[0303] In some embodiments, the data request configuration information may include one or more of the following:

[0304] (1) Trigger identification information or configuration identification information. After receiving data request configuration information containing trigger identification information or configuration identification information, the terminal may carry the trigger identification information or configuration identification information in the data request message, so that the network device, after receiving the data request message carrying the trigger identification information or configuration identification information, may directly trigger the transmission of the reference signal set associated with the trigger identification information or the reference signal set associated with the configuration identification information.

[0305] (2) Reference signal set information associated with trigger identifier information, or reference signal set information associated with configuration identifier information. The data request configuration information may include reference signal set information associated with trigger identifier information, or reference signal set information associated with configuration identifier information, so that after receiving the data request configuration information, the terminal can select the corresponding trigger identifier or configuration identifier based on the target reference signal to be received.

[0306] (3) Reference signal time domain information. The data request configuration information may include the time domain information of each reference signal. After receiving the data request configuration information, the terminal can determine the time domain resource within which to receive the target reference signal sent by the network device based on the time domain information of the target reference signal to be received.

[0307] (4) Reference signal frequency domain information. The data request configuration information may include the frequency domain information of each reference signal. After receiving the data request configuration information, the terminal can determine the frequency domain resource in which to receive the target reference signal sent by the network device based on the time domain information of the target reference signal to be received.

[0308] Therefore, after receiving the data request configuration information, the terminal may send a data request message to the network device according to the data request configuration information, thereby triggering the network device to directly send the target reference signal.

[0309] By sending data request configuration information through the network device, the terminal can directly trigger the network device to send the target reference signal. This process is simpler and the network device can respond in a timely manner.

[0310] FIG2 is a second flow chart of a method for requesting data for an AI / ML model in beam management according to an embodiment of the present disclosure. As shown in FIG2 , the method is applied to a network device and includes the following steps:

[0311] Step 200: Receive a data request message sent by a terminal.

[0312] Step 201: Determine a target reference signal based on the data request message; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0313] Specifically, the network device in the embodiment of the present disclosure may be an access network device (e.g., a base station), and the target reference signal refers to a reference signal that the terminal desires to obtain for collecting data for the AI / ML model in beam management. The performance monitoring, model reasoning, model training, and model modification of the AI / ML model can be performed in subsequent processes based on the data collected by the terminal. The processing procedures for performance monitoring, model reasoning, model training, and model modification of the AI / ML model may refer to existing or future related technologies and are not elaborated in the embodiment of the present disclosure.

[0314] In an embodiment of the present disclosure, when a terminal needs to collect data for an AI / ML model in beam management, the terminal may send a data request message to a network device, where the data request message is used to request the network device to send a target reference signal.

[0315] In some embodiments, the terminal may send a data request message based on one or more of PUCCH, PUSCH and MAC CE.

[0316] After receiving the data request message, the network device can determine the target reference signal that the terminal wants to obtain and perform subsequent processing based on the resource conditions in the network.

[0317] The disclosed embodiments provide a data request method for AI / ML models in beam management. When a terminal needs to collect data for the AI / ML model in beam management, it can send a data request message to a network device to request the network device to send a target reference signal for the terminal to collect data. The network device can determine the target reference signal based on the data request message and perform subsequent processing based on network resources. This allows the terminal to proactively trigger the data collection process for the AI / ML model in beam management.

[0318] In some embodiments, the data request message may include one or more of the following:

[0319] (1) Identification information of the AI / ML model.

[0320] Specifically, the data request message may include identification information of one or more AI / ML models, and the network device may determine that the reference signal associated with the identification of the one or more AI / ML models is the target reference signal.

[0321] The association between the identifier of the AI / ML model and the reference signal may be configured or pre-configured by a network device. The association may be an association between the identifier of each AI / ML model and each reference signal set. In some implementations, for the BM case-2 sub-use case, the association may also be an association between the identifier of each AI / ML model and each reference signal and the time domain information of each reference signal, thereby indicating the time domain information of the target reference signal based on the identifier of the AI / ML model.

[0322] For example, the terminal collects data for the AI / ML model based on the measurement of the setA set and the setB set. The relationship between the AI / ML model ID and the reference signal has been established between the network device and the terminal. For example, Model#1 is associated with the setA set and the setB set. If it is the BM case-1 sub-use case, when Model#1 is included in the data request message, it means that the terminal requests the network device to send the reference signals included in the setA set and the setB set. If it is the BM case-2 sub-use case, the data request message contains Model#1 and can also indicate the time domain information of the reference signals in the setA set and the setB set.

[0323] For another example, the network device configures AI / ML model data collection based on setB set measurement based on Radio Resource Control (RRC) signaling, or configures AI / ML model data collection based on setA set and setB set measurement.

[0324] If RRC signaling configures an AI / ML model to measure based on setB, the terminal can request the transmission of the reference signals included in setB using the AI / ML model ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model ID in the data request message can also indicate the time domain information of the reference signals in setB.

[0325] If RRC signaling configures an AI / ML model to measure based on setA and setB, the terminal can request the transmission of the reference signals included in setA and setB using the AI / ML model ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model ID in the data request message can also indicate the time domain information of the reference signals in setA and setB.

[0326] (2) Functional identification information of the AI / ML model.

[0327] Specifically, the data request message may include function identification information of one or more AI / ML models, and the network device may determine that the reference signal associated with the function identification of the one or more AI / ML models is the target reference signal.

[0328] The association relationship between the function identifier of the AI / ML model and the reference signal may be configured or pre-configured by a network device. The association relationship may be an association relationship between the function identifier of each AI / ML model and each reference signal set. In some implementations, for the BM case-2 sub-use case, the association relationship may also be an association relationship between the function identifier of each AI / ML model and each reference signal and the time domain information of each reference signal, so that the time domain information of the target reference signal can be indicated according to the function identifier of the AI / ML model.

[0329] For example, the terminal collects data for the AI / ML model based on the measurement of the setA set and the setB set. The relationship between the AI / ML model function ID and the reference signal has been established between the network device and the terminal. For example, model function #1 is associated with the setA set and the setB set. If it is the BM case-1 sub-use case, when the data request message includes model function #1, it means that the terminal requests the network device to send the reference signals included in the setA set and the setB set. If it is the BM case-2 sub-use case, the data request message includes model function #1 and can also indicate the time domain information of the reference signals in the setA set and the setB set.

[0330] For another example, the network device configures AI / ML model data collection based on setB set measurement based on RRC signaling, or configures AI / ML model data collection based on setA set and setB set measurement.

[0331] If RRC signaling configures an AI / ML model to measure based on the setB set, the terminal can request the transmission of the reference signals included in the setB set using the AI / ML model function ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model function ID in the data request message can also indicate the time domain information of the reference signals in the setB set.

[0332] If RRC signaling configures an AI / ML model to measure based on setA and setB, the terminal can request the transmission of the reference signals included in setA and setB using the AI / ML model function ID in the data request message. If it is the BM case-2 sub-use case, the AI / ML model function ID in the data request message can also indicate the time domain information of the reference signals in setA and setB.

[0333] (3) Resource collection identification information of AI / ML models.

[0334] Specifically, the data request message may include resource set identification information of one or more AI / ML models, and the network device may determine that the reference signal resource set corresponding to the reference signal resource set identification of the one or more AI / ML models is the target reference signal.

[0335] Among them, the resource collection identifier of each AI / ML model can be configured or pre-configured through network equipment.

[0336] (4) Trigger identification information or configuration identification information.

[0337] Specifically, the data request message may include one or more trigger identification information, or the data request message may include one or more configuration identification information, the trigger identification information is used to indicate that the reference signal associated with the one or more trigger identifications is the target reference signal, and the configuration identification information is used to indicate that the reference signal associated with the one or more configuration identifications is the target reference signal.

[0338] The association between the trigger identifier / configuration identifier and the reference signal may be configured or pre-configured by a network device. In some implementations, the association may also be an association between each trigger identifier / configuration identifier and each reference signal, the time domain information of each reference signal, and the frequency domain information of each reference signal, thereby indicating what time and frequency domain resources the target reference signal occupies based on the trigger identifier / configuration identifier.

[0339] For example, trigger ID#1 can be configured to associate the reference signals of setA and setB for AI / ML model 1, their frequency domain positions in the time slot, and the time slot offset from the data request message. When trigger ID#1 is included in the data request message, it indicates that the terminal requests the network device to send the reference signals of setA and setB at the corresponding time-frequency domain positions.

[0340] (5) Reference signal set information for AI / ML models.

[0341] Specifically, the data request message may include reference signal set information of one or more AI / ML models, and the network device may determine the reference signal set of the one or more AI / ML models as the target reference signal.

[0342] For example, the reference signal set information of the AI / ML model may be setB; or, the reference signal set information of the AI / ML model may be setA; or, the reference signal set information of the AI / ML model may be setA and setB.

[0343] The reference signal set information of the AI / ML model can be optional information based on the terminal capabilities, or configured based on high-layer signaling.

[0344] When the data request message also indicates an AI / ML model, in some implementations, the reference signal set information of the AI / ML model can be applied to all AI / ML models indicated by the data request message; in some implementations, the reference signal set information of the AI / ML model can be applied to a certain AI / ML model. If multiple AI / ML models are indicated in the data request message, each AI / ML model can be associated with one reference signal set information.

[0345] In some embodiments, the reference signal set information of the AI / ML model can be indicated based on a bit map, for example, where the first bit represents setA, one state indicates indicating set A, and another state indicates not indicating setA; another bit identifies setB, one state indicates indicating setB, and another state indicates not indicating setB.

[0346] In some implementations, the reference signal set information of the AI / ML model may be indicated using 1 bit, where one state represents setB and the other state represents both setA and setB.

[0347] (6) Performance monitoring performance indicator information.

[0348] Specifically, the data request message may include performance monitoring performance indicator information, which is used to instruct the terminal what performance indicators to use to monitor the performance of the AI / ML model. The network device can determine the target reference signal based on the performance indicators.

[0349] Performance monitoring performance indicator information can be optional information based on terminal capabilities, or configured based on high-layer signaling.

[0350] In some implementations, different numerical values ​​may be used to indicate different performance indicators. For example, when the performance monitoring indicator information is a value of 1, indicating that the optimal beam probability is used as the model performance calculation indicator, the network device may determine setA and setB as target reference signals. When the performance monitoring indicator information is a value of 2, indicating that the RSRP difference of setB is used as the model performance calculation indicator, the network device may determine setB as the target reference signal.

[0351] (7) Time requirement information of target reference signal.

[0352] Specifically, the data request message may include time requirement information of the target reference signal, which is used to indicate at what time the terminal wants the network device to send the target reference signal. The network device can determine whether the target reference signal can be sent and within what time period the target reference signal can be sent based on the time requirement information of the target reference signal.

[0353] In some implementations, operations of the network device corresponding to different target reference signal time requirement information may be pre-set or configured by the network device.

[0354] For example, the time requirement information of the target reference signal is represented by the reference signal priority. The reference signal priority includes two types: high priority and low priority.

[0355] When the terminal's time requirement for the target reference signal is high priority, it means that the terminal's request for performance monitoring is urgent. When the network device determines to send the reference signal, it will send the reference signal to the terminal within a set time interval, that is, the reference signal will be sent to the terminal as soon as possible; when the terminal's time requirement for the target reference signal is low priority, it means that the terminal's request for performance monitoring is low urgency. When the network device determines to send the signal, it will send the reference signal to the terminal at an appropriate time, that is, the sending time depends on the implementation of the network device.

[0356] (8) Periodic type information of the target reference signal.

[0357] Specifically, the data request message may include the periodic type information of the target reference signal, which is used to indicate the periodic type of the target reference signal that the terminal wants the network device to send. The network device can determine whether the target reference signal of this periodic type can be sent and what periodic type of target reference signal to send based on the periodic type information of the target reference signal and the resource situation.

[0358] The period type information of the target reference signal may include one or more of an aperiodic reference signal, a semi-periodic reference signal, and a periodic reference signal.

[0359] In some implementations, the terminal's requirements for reference signal periodicity can be ranked, with the requirements ranking from smallest to largest: aperiodic reference signal < semi-periodic reference signal < periodic reference signal. A network device can select and transmit reference signals with a lower level than the terminal's requirements, but cannot select and transmit reference signals with a higher level than the terminal's requirements.

[0360] For example, the terminal requests a semi-periodic reference signal from the network device. Based on the resource situation in the network, the network device may send the semi-periodic reference signal or the aperiodic reference signal, but may not send the periodic reference signal.

[0361] In some implementations, the terminal sends the requested reference signal periodicity type to the network device, and the network device directly sends the reference signal according to the type requested by the terminal. For example, if the terminal requests a semi-periodic reference signal from the network device, if the network device decides to send the target reference signal, it sends it according to the semi-periodic reference signal type.

[0362] (9) Periodic information of the target reference signal.

[0363] Specifically, the data request message may include the period information of the target reference signal, which is used to indicate the period at which the terminal wants the network device to send the target reference signal. The network device can determine whether the target reference signal can be sent with this period and at what period the target reference signal can be sent based on the period information of the target reference signal and the resource situation.

[0364] In some implementations, the period information of the target reference signal may be a period length expected by the terminal, such as a value among several candidate periods. The period length of the reference signal actually sent by the network device may be different from the period requested by the terminal.

[0365] In some implementations, the period information of the target reference signal may be a period length required by the terminal, such as a value among several candidate periods. The period length of the reference signal actually sent by the network device may be the same as the period requested by the terminal.

[0366] (10) Information on the number of target reference signals.

[0367] Specifically, the data request message may include target reference signal number information, which is used to indicate the number of times the terminal wants the network device to send the target reference signal. The network device can determine whether the target reference signal can be sent that number of times and at what number of times the target reference signal can be sent based on the target reference signal number information and resource conditions.

[0368] In some implementations, the target reference signal frequency information may be the frequency expected by the terminal, such as a value among several candidate frequencies. The number of reference signals actually sent by the network device may be different from the number requested by the terminal.

[0369] In some implementations, the target reference signal frequency information may be the frequency required by the terminal, such as a value among several candidate frequencies. The number of reference signals actually sent by the network device may be the same as the number requested by the terminal.

[0370] (11) Performance indicator indication information: The performance indicator indication information is used to indicate whether the terminal reports the performance indicator result.

[0371] Specifically, the data request message may include performance indicator indication information for indicating whether the terminal reports the performance indicator result. The network device may determine whether to configure performance indicator result reporting resources for the terminal based on the performance indicator indication information.

[0372] (12) Actual measurement indication information: The actual measurement indication information is used to instruct the terminal whether to report the actual measurement result.

[0373] Specifically, the data request message may include actual performance measurement information for indicating whether the terminal reports the actual measurement result. The network device may determine whether to configure actual measurement result reporting resources for the terminal based on the actual measurement indication information.

[0374] In some embodiments, determining a target reference signal based on the data request message includes:

[0375] The target reference signal is determined based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

[0376] Specifically, the terminal can indicate the target reference signal in the form of the data request message itself. That is, the data request message can indicate different target reference signals using different request signaling-specific formats, different request signaling scrambling sequences, or different request signaling-specific identification information. Thus, the network device can determine the target reference signal based on the request signaling-specific format, request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

[0377] For example, if the network device configures an AI / ML beam management function for the terminal, such as the function of predicting the optimal beam among 32 beams using 8 beams, the data request message does not need to include the function ID. Instead, the request for the reference signal associated with this function can be indicated by requesting a dedicated signaling format, requesting a signaling scrambling sequence, or requesting dedicated signaling identification information. In the case of BM case-2, the time domain information of setB and / or setA can also be indicated by requesting a dedicated signaling format, requesting a signaling scrambling sequence, or requesting dedicated signaling identification information.

[0378] In some embodiments, after determining the target reference signal, the method further includes one or more of the following:

[0379] Sending a data response message to the terminal;

[0380] Sending target reference signal related information to the terminal;

[0381] Send a target reference signal to the terminal.

[0382] Specifically, after determining the target reference signal that the terminal wants to obtain, the network device may perform subsequent processing according to the target reference signal and resource conditions in the network.

[0383] In the case of determining not to transmit the target reference signal, the network device may transmit a data response message indicating that the target reference signal is not to be transmitted, or may not transmit a data response message.

[0384] In the case of determining to send the target reference signal, the network device may perform one or more operations of sending a data response message indicating to send the target signal, sending target reference related information, and sending the target reference signal.

[0385] Target reference signal-related information refers to the signaling for configuring / activating / triggering the target reference signal, which can be used to notify the terminal network device of the time domain information, frequency domain information, and period of sending the target reference signal. Target reference signal-related information can include the identification information of the AI / ML model requested by the terminal, the function identification information of the AI / ML model requested by the terminal, or related information of other data request messages.

[0386] In some implementations, after receiving a data request message sent by a terminal, the network device may send a data response message to the terminal. The terminal may determine whether the network device sends a target reference signal through the data response message. This method provides the network device with a method for flexibly determining the sending time of the target reference signal.

[0387] In some embodiments, the data response message may be sent based on one or more of PDCCH, PDSCH and MAC CE.

[0388] In some embodiments, the data response message may include one or more of the following:

[0389] (1) Reference signal indication information: The reference signal indication information is used to indicate whether to send a target reference signal.

[0390] Specifically, the data response message may include reference signal indication information, which may directly indicate whether the network device should transmit the target reference signal. For example, if the network device sends a "confirmed" reference signal indication to the terminal, it indicates that the network device will respond to the terminal's request. If the network device cannot transmit the reference signal, it sends a "non-confirmed" reference signal indication to the terminal, indicating that the network device will not respond to the terminal's request.

[0391] (2) Request message indication information: The request message indication information is used to indicate the data request message corresponding to the data response message.

[0392] Specifically, the data response message may include request message indication information, which may indicate the data request message to which the data response message corresponds. For example, if a terminal sends multiple data request messages, the network device may reply with multiple data response messages, each of which includes request message indication information, so that the terminal can determine the data request message to which each data response message corresponds.

[0393] (3) Identification information of the target AI / ML model.

[0394] Specifically, the data response message may include identification information of a target AI / ML model, where the target AI / ML model refers to an AI / ML model to which the network device can send a corresponding target reference signal.

[0395] For example, a terminal sends a data request message to a network device. The data request message includes the identification information of multiple AI / ML models, namely Model #1, Model #2, and Model #3, indicating that the terminal requests data collection for these models. After receiving the data request message, the network device determines, based on resource availability, that it can send the reference signal associated with Model #1, but cannot send the reference signals associated with Model #2 and Model #3 within a certain period of time. In this case, the network device can confirm the transmission of the reference signal for Model #1 and include Model #1 in the data response message, allowing the terminal to confirm that the network device can send the reference signal associated with Model #1.

[0396] (4) Functional identification information of the target AI / ML model.

[0397] Specifically, the data response message may include function identification information of the target AI / ML model, where the target AI / ML model refers to an AI / ML model to which the network device can send a corresponding target reference signal.

[0398] For example, a terminal sends a data request message to a network device. The data request message includes the function identification information of multiple AI / ML models, namely model function #1, model function #2, and model function #3. That is, the terminal requests data collection for the models of these functions. After receiving the data request message, the network device determines that it can send the reference signal associated with model function #1 based on the resource situation, but cannot send the reference signals associated with model function #2 and model function #3 within a certain period of time. In this case, the network device can confirm the transmission of the reference signal of model function #1 and carry model function #1 in the data response message, so that the terminal can determine that the network device can send the reference signal associated with model function #1.

[0399] In the case of determining to send the target reference signal, the network device may then send the target reference signal related information and the target reference signal in sequence.

[0400] In some embodiments, sending a data response message to a terminal includes:

[0401] Within the first time window, a data response message is sent to the terminal.

[0402] Specifically, the first time window can be set in advance. The first time window can be in time slots, and its value can be high-level configuration / protocol provisions / defined based on terminal capabilities. The starting point of the first time window can be the moment when the terminal sends a data request message, or the moment when the network device receives the data request message, or other reasonable moments set according to actual conditions.

[0403] The terminal may determine whether the network device sends the target reference signal according to whether a data response message sent by the network device can be received within the first time window.

[0404] If the terminal receives a data response message sent by the network device within the first time window, the terminal can determine that the network device sends a target reference signal; if the terminal does not receive a data response message sent by the network device within the first time window, the terminal can determine that the network device does not send a target reference signal.

[0405] In some implementations, after receiving a data request message sent by a terminal, the network device may not send a data response message to the terminal, but may directly send target reference signal related information to the terminal. Compared with the method of sending a data response, this can reduce the interaction process between the network device and the terminal and save resources.

[0406] In some embodiments, sending target reference signal related information to the terminal includes:

[0407] In the second time window, target reference signal related information is sent to the terminal.

[0408] Specifically, a second time window can be set in advance. The second time window can be in time slots, and its value can be high-level configuration / protocol provisions / defined based on terminal capabilities. The starting point of the second time window can be the moment when the terminal sends a data request message, or the moment when the network device receives the data request message, or other reasonable moments set according to actual conditions.

[0409] The terminal may determine whether the network device sends the target reference signal based on whether the target reference signal related information sent by the network device can be received within the second time window.

[0410] If the terminal receives the target reference signal related information sent by the network device within the second time window, the terminal can determine that the network device sends the target reference signal; if the terminal does not receive the target reference signal related information sent by the network device within the second time window, the terminal can determine that the network device does not send the target reference signal.

[0411] In some embodiments, the method further comprises:

[0412] Send data request configuration information to the terminal.

[0413] Specifically, before the terminal sends a data request message, the network device may first send data request configuration information to the terminal. The data request configuration information is information used to directly trigger the network device to send a target reference signal.

[0414] In some embodiments, the data request configuration information may include one or more of the following:

[0415] (1) Trigger identification information or configuration identification information. After receiving data request configuration information containing trigger identification information or configuration identification information, the terminal may carry the trigger identification information or configuration identification information in the data request message, so that the network device, after receiving the data request message carrying the trigger identification information or configuration identification information, may directly trigger the transmission of the reference signal set associated with the trigger identification information or the reference signal set associated with the configuration identification information.

[0416] (2) Reference signal set information associated with trigger identifier information, or reference signal set information associated with configuration identifier information. The data request configuration information may include reference signal set information associated with trigger identifier information, or reference signal set information associated with configuration identifier information, so that after receiving the data request configuration information, the terminal can select the corresponding trigger identifier or configuration identifier based on the target reference signal to be received.

[0417] (3) Reference signal time domain information. The data request configuration information may include the time domain information of each reference signal. After receiving the data request configuration information, the terminal can determine the time domain resource within which to receive the target reference signal sent by the network device based on the time domain information of the target reference signal to be received.

[0418] (4) Reference signal frequency domain information. The data request configuration information may include the frequency domain information of each reference signal. After receiving the data request configuration information, the terminal can determine the frequency domain resource in which to receive the target reference signal sent by the network device based on the time domain information of the target reference signal to be received.

[0419] Therefore, after receiving the data request configuration information, the terminal may send a data request message to the network device according to the data request configuration information, thereby triggering the network device to directly send the target reference signal.

[0420] By sending data request configuration information through the network device, the terminal can directly trigger the network device to send the target reference signal. This process is simpler and the network device can respond in a timely manner.

[0421] The methods provided in the various embodiments of the present disclosure are based on the same application concept, so the implementation of each method can refer to each other, and the repeated parts will not be repeated.

[0422] The following describes the methods provided in the above embodiments of the present disclosure by way of examples of specific application scenarios.

[0423] Example 1:

[0424] Example 1-1: FIG3 is a flow chart of a terminal triggering performance monitoring according to an embodiment of the present disclosure. As shown in FIG3 , the specific steps are as follows:

[0425] Step 1: The terminal sends a first request signaling to the base station.

[0426] The first request signaling includes one or more AI / ML model identification numbers or AI / ML function indications. This identification number information is used to indicate the reference signal information associated with the AI / ML model or function, including SetA reference signals and / or SetB reference signals. If the AI / ML model or function is for BM-case 2, then this identification number also includes time domain information of the associated reference signal.

[0427] For example, AI / ML model performance monitoring is based on measurements of setA and setB. The base station and UE have established a relationship between the AI / ML model ID or function ID and the reference signal. For example, Model#1 is used for the BM case-1 sub-use case, associating the setA set and the setB set. When Model#1 is indicated in the first request signaling, the UE requests the base station to send the reference signals included in the setA set and the setB set. If it is the BM case-2 sub-use case, the time domain information of the setA and setB reference signals is also indicated.

[0428] For example, the base station configures AI / ML model performance monitoring based on setB measurements or both setA and setB measurements based on RRC signaling. If the RRC signaling configuration is based on setB measurements, the AI / ML model ID or function indicates the association with the setB reference signal. If this is the BM case-2 sub-use case, the time domain information of the setB reference signal is also indicated. If the RRC configuration is based on setA and setB measurements, the AI / ML model ID or function indicates the association with the setA and setB reference signals. If this is the BM case-2 sub-use case, the time domain information of the setA and setB reference signals is also indicated.

[0429] For example, if the base station configures an AI / ML beam management function for the terminal, such as predicting the optimal beam among 32 beams using 8 beams, the request signaling does not need to include a function ID. Instead, the request signaling uses a dedicated format, a scrambling sequence, or dedicated identification information to indicate the reference signal associated with the requested function. For the BM case-2 sub-use case, the time domain information for setB and / or setA is also indicated.

[0430] For example, the base station configures more than one AI / ML beam management function for the terminal. For example, Function 1 predicts the optimal beam among 32 beams using 8 beams, corresponding to AI / ML IDs 1 to 10. Function 2 predicts the optimal beam among 32 narrow beams using 8 wide beams, corresponding to AI / ML IDs 21 to 16. The request signaling can indicate the reference signal corresponding to the requested function by setting the function ID, function-specific scrambling signaling, or the corresponding model ID.

[0431] In addition, the first request signaling may also include the following information:

[0432] 1. RS signal set information: setB, or setA, or setA and setB. This is optional information based on terminal capabilities or configured based on higher-layer signaling.

[0433] Alt.1: RS signal aggregate information applies to all AI / ML models indicated by the request information.

[0434] Alt.2: RS signal set information applies to one AI / ML model. If the request information indicates multiple AI / ML models, each AI / ML model has corresponding RS signal set information.

[0435] The indication method of setA and setB can be based on the bit map, for example, the first bit represents setA, one state indicates indicating set A, and the other state indicates not indicating setA; another bit identifies setB, one state indicates indicating setB, and the other state indicates not indicating setB.

[0436] Alternatively, 1 bit is used for indication, where one state represents setB, and the other state represents setA and setB.

[0437] 2. Performance monitoring performance indicator information: The terminal reports the performance monitoring performance indicator information to the base station, and the base station determines the reference signal set to be sent based on this information.

[0438] For example, when the performance monitoring indicator value is 1, it indicates that the optimal beam probability is used as the model performance calculation indicator. Therefore, after the base station determines to send the reference signal set, it will send setA and setB. When the performance monitoring indicator value is 2, it indicates that the RSRP difference of setB is used as the model performance calculation indicator. Therefore, after the base station determines to send the reference signal, it will send setB. This is optional information based on UE capabilities or higher-layer signaling configuration.

[0439] 3. Time requirement of the requested RS: The terminal reports the time requirement of requesting RS to the base station, and the base station determines the time to send the reference signal set based on this information.

[0440] For example, reference signal priorities include high and low priorities. When the time requirement for requesting an RS is high, it indicates that the terminal is requesting performance monitoring with urgency. Once the base station determines to send the signal, it will send the reference signal to the terminal within a time interval of no more than T1, that is, as soon as possible. When the time requirement for requesting an RS is low, it indicates that the terminal is not requesting performance monitoring with urgency. Once the base station determines to send the signal, it will send the reference signal to the base station at an appropriate time, meaning that the transmission time is entirely determined by the base station's implementation.

[0441] 4. The requested RS period type: one or more of aperiodic RS, semi-periodic RS, and periodic RS.

[0442] Alt.1: The terminal sends the expected reference signal period type to the base station. The base station determines the type of reference signal to be sent and the time configuration based on this information and resource conditions. An optional method is to classify the terminal's needs from small to large as aperiodic RS < semi-periodic RS < periodic RS. The base station can choose to send a signal that is lower than the terminal's demand level, but cannot choose to send a signal that is higher than the terminal's demand level. For example, the terminal requests a semi-periodic RS from the base station. Based on the resource conditions in the network, the base station can send it according to the semi-periodic RS or the aperiodic RS. However, the base station cannot send it according to the periodic RS.

[0443] Alt.2: The terminal sends the requested reference signal periodicity type to the base station, and the base station sends the reference signal according to the type requested by the terminal. For example, if the terminal requests a semi-periodic RS from the base station, if the base station decides to send a reference signal, it must send it according to the semi-periodic RS type.

[0444] 5. Requested RS period: When the terminal request type is periodic transmission or semi-periodic transmission, the terminal may send the expected RS period in some embodiments.

[0445] Alt.1: The terminal sends the expected cycle length to the base station, for example, a value from several candidate cycles. The actual reference signal cycle length sent by the base station may be different from the cycle requested by the terminal.

[0446] Alt.2: The terminal sends the required cycle length to the base station, for example, a value from several candidate cycles. The reference signal cycle length actually sent by the base station can be the same as the cycle requested by the terminal.

[0447] 6. Requested RS number: When the terminal request type is semi-periodic signal transmission, the terminal may optionally send the requested RS number to the base station.

[0448] For example, when the requested RS number is 2, the base station triggers 2 aperiodic RS transmissions.

[0449] The requested RS number can be the number expected by the terminal, or can be understood as the number of RS transmissions required by the terminal. A method similar to Alt.1 and Alt.2 in the above-mentioned RS request cycle can be adopted.

[0450] 7. Whether to report performance indicators: When the terminal sends a request to report performance indicators to the base station, if the base station determines to send RS, it is necessary to configure or indicate performance indicator reporting resources.

[0451] 8. Whether to report actual measurement: When the terminal sends a request to report actual measurement to the base station, if the base station determines to send RS, it is necessary to configure or indicate actual measurement reporting resources.

[0452] Step 2: Based on the received request signaling, the base station determines whether it can send a reference signal. If it can, the base station sends a "confirmation" message to the terminal, indicating that the base station will respond to the terminal's request. If it cannot, the base station sends a "non-confirmation" message to the terminal, indicating that the base station will not respond to the terminal's request. This confirmation message may include information related to the terminal's request signaling. For example, the association relationship between the requested AI / ML model identifier and the request signaling may be represented by a predefined identifier, or the association relationship may be represented by a predefined identifier.

[0453] Step 3: The base station configures / activates / triggers the transmission of reference signals to the terminal based on the request. For example, the terminal requests the reference signal sets setA and setB for AI / ML model #1, where the RS signal type is aperiodic. After the base station sends an acknowledgment to the terminal, it triggers the transmission of the reference signal sets setA and setB at the appropriate time-frequency location based on the base station's implementation, notifying the terminal of the reference signal information.

[0454] Step 4: The base station sends a reference signal at the indicated time-frequency position.

[0455] Step 5: If the base station configures the terminal to report measurement quantities or performance indicators, the terminal reports reference signal measurement results and / or calculated performance indicators and / or events at the indicated location.

[0456] Example 1-2: FIG4 is a second flowchart of terminal-triggered performance monitoring provided in an embodiment of the present disclosure. As shown in FIG4 , in this embodiment, only step 2 is different from Example 1-1, and the other steps are the same.

[0457] Step 2: Based on the received request signaling, the base station determines whether the reference signal associated with each requested model or function can be transmitted. If the reference signal associated with one or more AI / ML models or functions can be transmitted, the base station sends the corresponding AI / ML model identification number or function identification to the terminal. In other words, the base station can confirm the performance monitoring request for some models in the request signaling.

[0458] For example, a terminal sends a request signaling to the base station, including AI / ML model #1, model #2, and model #3, requesting performance monitoring of these models. The base station receives the request signaling and, based on resource availability, determines that it can transmit the reference signal associated with model #1, but cannot transmit the reference signals associated with models #2 and 3 for a period of time. The base station sends a confirmation to the terminal that the reference signal for AI / ML model #1 has been transmitted, and the terminal begins preparing to perform performance monitoring on model #1.

[0459] Example 1-3: Figure 5 is the third flowchart of the terminal-triggered performance monitoring provided in the embodiment of the present disclosure. As shown in Figure 5, in this embodiment, step 2 is different from Example 1-1 and Example 1-2, and the other steps are the same.

[0460] Step 2: The base station determines whether the reference signal of the requested AI / ML model can be sent based on the received first request signaling. If the reference signal of the requested AI / ML model can be sent, the base station sends a confirmation signal within a predefined or configured time window. This signal includes a confirmation signal (for example, an AI / ML identifier or a request identifier), or an identifier of one or more determined AI / ML models / functions. If the reference signal of the requested AI / ML model cannot be sent, the base station will not send any signal for feedback. When the base station does not receive a response signal from the base station or does not receive the AI / ML ID within the predefined or configured window, it is considered that the request has not been confirmed by the base station.

[0461] The time window is in time slots, and its value may be configured by a higher layer / protocol specification / defined based on UE capabilities. The starting point of this window is the moment when the terminal sends the first request signaling.

[0462] Example 2: Figure 6 is a fourth schematic diagram of a terminal-triggered performance monitoring process according to an embodiment of the present disclosure. As shown in Figure 6, compared to Example 1, this solution does not require the base station to send a confirmation response signal to the terminal. If the base station confirms that it can send the reference signal requested by the terminal, it simply sends the reference signal within a preconfigured or configured time window. Otherwise, the reference signal is not sent.

[0463] Step 1: The terminal sends a first request signaling to the base station.

[0464] Step 2: The base station determines whether it can send a reference signal based on the received request signaling. If the reference signal can be sent, the base station sends signaling for configuring / activating / triggering the reference signal for the requested AI / ML model or function within a predefined / configured time window. This signaling may optionally include the requested AI / ML model identifier or function identifier or request signaling-related information. If the reference signal cannot be sent, the base station will not respond to the terminal's request signal, and the terminal will not receive signaling for configuring / activating / triggering the reference signal for the requested AI / ML model or function within the predefined / configured time window.

[0465] The subsequent steps are the same as those in Example 1.

[0466] Embodiment 3: FIG7 is a fifth flow chart of terminal-triggered performance monitoring according to an embodiment of the present disclosure, as shown in FIG7 , including the following steps:

[0467] Step 1: The base station configures first request signaling configuration information for the terminal, where the first request signaling configuration information includes a trigger identifier or a configuration identifier and a reference signal set associated with the identifier, frequency domain information of the reference signal, and time domain information.

[0468] Step 2: The terminal sends a first request signaling, wherein the first request signaling includes at least a configured trigger identifier or configuration identifier, and optional options include time domain information of the requested reference signal, period information, whether to include a CSI report, etc.

[0469] Step 3: When the base station receives the first request signaling, it sends the reference signal according to the triggering identifier in the first request signaling.

[0470] For example, the first request signaling includes trigger ID#1. Based on the base station's configuration, trigger ID#1 is associated with the reference signals of setA and setB for AI / ML model 1, along with their frequency domain positions in the time slot and their time slot offset relative to the request information. Based on the configuration, the base station transmits the RS on the corresponding time-frequency resources, and the terminal performs reference signal measurements.

[0471] The request signaling in the above embodiments may be carried by one or more of the following signals or channels: PUCCH, PUSCH and MAC CE. The response information sent by the base station to the terminal includes one or more of the following signals or channels: PDCCH, PDSCH and MAC CE.

[0472] The methods and devices provided in the various embodiments of the present disclosure are based on the same application concept. Since the methods and devices solve problems based on similar principles, the implementation of the devices and methods can refer to each other, and the repeated parts will not be repeated.

[0473] FIG8 is a schematic structural diagram of a terminal provided by an embodiment of the present disclosure. As shown in FIG8 , the terminal includes a memory 820 , a transceiver 810 , and a processor 800 ; wherein the processor 800 and the memory 820 may also be physically arranged separately.

[0474] The memory 820 is used to store computer programs; the transceiver 810 is used to send and receive data under the control of the processor 800.

[0475] In FIG8 , the bus architecture may include any number of interconnected buses and bridges, specifically various circuits of one or more processors represented by processor 800 and memory represented by memory 820, linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described in this disclosure. The bus interface provides an interface. The transceiver 810 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and other transmission media. For different user devices, the user interface 830 may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0476] The processor 800 is responsible for managing the bus architecture and general processing, and the memory 820 can store data used by the processor 800 when performing operations.

[0477] The processor 800 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0478] The processor 800 calls the computer program stored in the memory 820 to execute any of the methods provided in the embodiments of the present disclosure according to the obtained executable instructions, for example:

[0479] Send a data request message to the network device; the data request message is used to request the network device to send a target reference signal; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0480] In some embodiments, the data request message includes one or more of the following:

[0481] Identification information of AI / ML models;

[0482] Function identification information of AI / ML models;

[0483] Resource collection identification information of AI / ML models;

[0484] trigger identification information or configuration identification information;

[0485] Reference signal collection information for AI / ML models;

[0486] Performance monitoring performance indicator information;

[0487] Time requirement information of target reference signal;

[0488] Periodic type information of the target reference signal;

[0489] Periodic information of the target reference signal;

[0490] Number information of target reference signals;

[0491] Performance indicator indication information, which is used to instruct the terminal whether to report the performance indicator result;

[0492] The actual measurement indication information is used to instruct the terminal whether to report the actual measurement result.

[0493] In some embodiments, the data request message indicates the target reference signal based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information.

[0494] In some embodiments, the method further comprises:

[0495] receiving a data response message sent by the network device, and determining whether the network device sends a target reference signal based on the data response message; or,

[0496] Receive target reference signal related information sent by the network device, and determine whether the network device sends the target reference signal based on the target reference signal related information.

[0497] In some embodiments, the data response message includes one or more of the following:

[0498] Reference signal indication information, where the reference signal indication information is used to indicate whether to send a target reference signal;

[0499] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0500] Identification information of the target AI / ML model;

[0501] Function identification information of the target AI / ML model.

[0502] In some embodiments, determining whether the network device sends a target reference signal based on the data response message includes:

[0503] When a data response message sent by the network device is received within the first time window, determining that the network device sends a target reference signal;

[0504] If no data response message sent by the network device is received within the first time window, it is determined that the network device does not send the target reference signal.

[0505] In some embodiments, determining whether the network device sends the target reference signal based on the target reference signal related information includes:

[0506] When receiving target reference signal related information sent by the network device within the second time window, determining that the network device sends the target reference signal;

[0507] If the target reference signal related information sent by the network device is not received within the second time window, it is determined that the network device does not send the target reference signal.

[0508] In some embodiments, sending a data request message to a network device includes:

[0509] Receiving data request configuration information sent by a network device;

[0510] Based on the data request configuration information, a data request message is sent to the network device.

[0511] In some embodiments, the data request configuration information includes one or more of the following:

[0512] trigger identification information or configuration identification information;

[0513] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0514] Time domain information of the reference signal;

[0515] Frequency domain information of the reference signal.

[0516] In some embodiments, the data request message is sent based on one or more of a physical uplink control channel PUCCH, a physical uplink shared channel PUSCH, and a medium access control layer control element MAC CE.

[0517] FIG9 is a schematic structural diagram of a network device provided in an embodiment of the present disclosure. As shown in FIG9 , the network device includes a memory 920 , a transceiver 910 , and a processor 900 ; wherein the processor 900 and the memory 920 may also be physically arranged separately.

[0518] The memory 920 is used to store computer programs; the transceiver 910 is used to send and receive data under the control of the processor 900.

[0519] In FIG9 , the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 900 and memory represented by memory 920. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described in this disclosure. The bus interface provides an interface. The transceiver 910 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, or the like.

[0520] The processor 900 is responsible for managing the bus architecture and general processing, and the memory 920 can store data used by the processor 900 when performing operations.

[0521] The processor 900 may be a CPU, an ASIC, an FPGA, or a CPLD, and the processor may also adopt a multi-core architecture.

[0522] The processor 900 calls the computer program stored in the memory 920 to execute any of the methods provided in the embodiments of the present disclosure according to the obtained executable instructions, for example:

[0523] receiving a data request message sent by a terminal;

[0524] Based on the data request message, the target reference signal is determined; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0525] In some embodiments, the data request message includes one or more of the following:

[0526] Identification information of AI / ML models;

[0527] Function identification information of AI / ML models;

[0528] Resource collection identification information of AI / ML models;

[0529] trigger identification information or configuration identification information;

[0530] Reference signal collection information for AI / ML models;

[0531] Performance monitoring performance indicator information;

[0532] Time requirement information of target reference signal;

[0533] Periodic type information of the target reference signal;

[0534] Periodic information of the target reference signal;

[0535] Number information of target reference signals;

[0536] Performance indicator indication information, which is used to instruct the terminal whether to report the performance indicator result;

[0537] The actual measurement indication information is used to instruct the terminal whether to report the actual measurement result.

[0538] In some embodiments, determining a target reference signal based on the data request message includes:

[0539] The target reference signal is determined based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

[0540] In some embodiments, after determining the target reference signal, the method further includes one or more of the following:

[0541] Sending a data response message to the terminal;

[0542] Sending target reference signal related information to the terminal;

[0543] Send a target reference signal to the terminal.

[0544] In some embodiments, the data response message includes one or more of the following:

[0545] Reference signal indication information, where the reference signal indication information is used to indicate whether to send a target reference signal;

[0546] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0547] Identification information of the target AI / ML model;

[0548] Function identification information of the target AI / ML model.

[0549] In some embodiments, sending a data response message to a terminal includes:

[0550] Within the first time window, a data response message is sent to the terminal.

[0551] In some embodiments, sending target reference signal related information to the terminal includes:

[0552] In the second time window, target reference signal related information is sent to the terminal.

[0553] In some embodiments, the method further comprises:

[0554] Send data request configuration information to the terminal.

[0555] In some embodiments, the data request configuration information includes one or more of the following:

[0556] trigger identification information or configuration identification information;

[0557] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0558] Time domain information of the reference signal;

[0559] Frequency domain information of the reference signal.

[0560] In some embodiments, the data response message is sent based on one or more of a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH, and a media access control layer control element MAC CE.

[0561] It should be noted here that the above-mentioned terminals and network devices provided in the embodiments of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiments and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those in the method embodiments will not be described in detail here.

[0562] FIG10 is a schematic diagram of a data request device for an AI / ML model in beam management according to an embodiment of the present disclosure. The device is applied to a terminal. As shown in FIG10 , the device includes:

[0563] The first sending unit 1000 is used to send a data request message to the network device; the data request message is used to request the network device to send a target reference signal; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0564] In some embodiments, the data request message includes one or more of the following:

[0565] Identification information of AI / ML models;

[0566] Function identification information of AI / ML models;

[0567] Resource collection identification information of AI / ML models;

[0568] trigger identification information or configuration identification information;

[0569] Reference signal collection information for AI / ML models;

[0570] Performance monitoring performance indicator information;

[0571] Time requirement information of target reference signal;

[0572] Periodic type information of the target reference signal;

[0573] Periodic information of the target reference signal;

[0574] Number information of target reference signals;

[0575] Performance indicator indication information, which is used to instruct the terminal whether to report the performance indicator result;

[0576] The actual measurement indication information is used to instruct the terminal whether to report the actual measurement result.

[0577] In some embodiments, the data request message indicates the target reference signal based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information.

[0578] In some embodiments, the apparatus further includes a first receiving unit and a first determining unit:

[0579] The first receiving unit is configured to receive a data response message sent by the network device, and the first determining unit is configured to determine whether the network device sends a target reference signal based on the data response message; or

[0580] The first receiving unit is configured to receive target reference signal related information sent by the network device, and the first determining unit is configured to determine whether the network device sends the target reference signal based on the target reference signal related information.

[0581] In some embodiments, the data response message includes one or more of the following:

[0582] Reference signal indication information, where the reference signal indication information is used to indicate whether to send a target reference signal;

[0583] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0584] Identification information of the target AI / ML model;

[0585] Function identification information of the target AI / ML model.

[0586] In some embodiments, determining whether the network device sends a target reference signal based on the data response message includes:

[0587] When a data response message sent by the network device is received within the first time window, determining that the network device sends a target reference signal;

[0588] If no data response message sent by the network device is received within the first time window, it is determined that the network device does not send the target reference signal.

[0589] In some embodiments, determining whether the network device sends the target reference signal based on the target reference signal related information includes:

[0590] When receiving target reference signal related information sent by the network device within the second time window, determining that the network device sends the target reference signal;

[0591] If the target reference signal related information sent by the network device is not received within the second time window, it is determined that the network device does not send the target reference signal.

[0592] In some embodiments, sending a data request message to a network device includes:

[0593] Receiving data request configuration information sent by a network device;

[0594] Based on the data request configuration information, a data request message is sent to the network device.

[0595] In some embodiments, the data request configuration information includes one or more of the following:

[0596] trigger identification information or configuration identification information;

[0597] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0598] Time domain information of the reference signal;

[0599] Frequency domain information of the reference signal.

[0600] In some embodiments, the data request message is sent based on one or more of a physical uplink control channel PUCCH, a physical uplink shared channel PUSCH, and a medium access control layer control element MAC CE.

[0601] FIG11 is a second structural diagram of a data request device for an AI / ML model in beam management according to an embodiment of the present disclosure. The device is applied to a network device. As shown in FIG11 , the device includes:

[0602] The second receiving unit 1100 is configured to receive a data request message sent by a terminal;

[0603] The second determination unit 1110 is configured to determine a target reference signal based on the data request message; the target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

[0604] In some embodiments, the data request message includes one or more of the following:

[0605] Identification information of AI / ML models;

[0606] Function identification information of AI / ML models;

[0607] Resource collection identification information of AI / ML models;

[0608] trigger identification information or configuration identification information;

[0609] Reference signal collection information for AI / ML models;

[0610] Performance monitoring performance indicator information;

[0611] Time requirement information of target reference signal;

[0612] Periodic type information of the target reference signal;

[0613] Periodic information of the target reference signal;

[0614] Number information of target reference signals;

[0615] Performance indicator indication information, which is used to instruct the terminal whether to report the performance indicator result;

[0616] The actual measurement indication information is used to instruct the terminal whether to report the actual measurement result.

[0617] In some embodiments, determining a target reference signal based on the data request message includes:

[0618] The target reference signal is determined based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

[0619] In some embodiments, the apparatus further includes a second sending unit configured to, after determining the target reference signal, perform one or more of the following:

[0620] Sending a data response message to the terminal;

[0621] Sending target reference signal related information to the terminal;

[0622] Send a target reference signal to the terminal.

[0623] In some embodiments, the data response message includes one or more of the following:

[0624] Reference signal indication information, where the reference signal indication information is used to indicate whether to send a target reference signal;

[0625] Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message;

[0626] Identification information of the target AI / ML model;

[0627] Function identification information of the target AI / ML model.

[0628] In some embodiments, sending a data response message to a terminal includes:

[0629] Within the first time window, a data response message is sent to the terminal.

[0630] In some embodiments, sending target reference signal related information to the terminal includes:

[0631] In the second time window, target reference signal related information is sent to the terminal.

[0632] In some embodiments, the apparatus further includes a third sending unit, configured to:

[0633] Send data request configuration information to the terminal.

[0634] In some embodiments, the data request configuration information includes one or more of the following:

[0635] trigger identification information or configuration identification information;

[0636] Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information;

[0637] Time domain information of the reference signal;

[0638] Frequency domain information of the reference signal.

[0639] In some embodiments, the data response message is sent based on one or more of a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH, and a media access control layer control element MAC CE.

[0640] It should be noted that the division of units in the embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0641] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0642] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0643] In some embodiments, a non-transitory readable storage medium is also provided, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the data request method of the AI / ML model in beam management provided by the above-mentioned method embodiments.

[0644] Specifically, the above-mentioned non-transitory readable storage medium provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0645] It should be noted that the non-transitory readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid-state drives (SSDs)), etc.

[0646] In some embodiments, a processor-readable storage medium is also provided, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the data request method of the AI / ML model in beam management provided by the above-mentioned method embodiments.

[0647] Specifically, the processor-readable storage medium provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiments and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as those of the method embodiment will not be described in detail here.

[0648] In some embodiments, a computer-readable storage medium is further provided, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute the data request method of the AI / ML model in beam management provided by the above-mentioned method embodiments.

[0649] Specifically, the above-mentioned computer-readable storage medium provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0650] In some embodiments, a communication device is also provided, in which a computer program is stored, and the computer program is used to enable the communication device to execute the data request method of the AI / ML model in beam management provided by the above-mentioned method embodiments.

[0651] Specifically, the above-mentioned communication device provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0652] In some embodiments, a chip product is also provided, in which a computer program is stored. The computer program is used to enable the chip product to execute the data request method of the AI / ML model in beam management provided by the above-mentioned method embodiments.

[0653] Specifically, the above-mentioned chip product provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned method embodiments, and can achieve the same technical effects. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0654] The technical solution provided by the embodiment of the present disclosure can be applicable to a variety of systems, especially 5G systems. For example, the applicable system can be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new air interface (NR) system, etc. These various systems include terminal equipment and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0655] The terminal involved in the embodiments of the present disclosure may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal may also be different. For example, in a 5G system, the terminal may be called User Equipment (UE). A wireless terminal device can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a radio access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, or a user device, but is not limited in the embodiments of the present disclosure.

[0656] The network device involved in the embodiments of the present disclosure may be a base station, which may include multiple cells providing services to terminals. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in an access network that communicates with a wireless terminal device through one or more sectors on an air interface, or may be called another name. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present disclosure may be a base transceiver station (BTS) in the Global System for Mobile communications (GSM) or code division multiple access (CDMA), a network device (NodeB) in wide-band code division multiple access (WCDMA), an evolutionary Node B (eNB or e-NodeB) in the long term evolution (LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), a home evolved Node B (HeNB), a relay node, a femto, a pico, etc., and is not limited in the embodiments of the present disclosure. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be geographically separated.

[0657] Network devices and terminal devices can each use one or more antennas for Multiple Input Multiple Output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). Depending on the configuration and number of antenna combinations, MIMO transmission can be 2D-MIMO, 3D-MIMO, FD-MIMO, or massive-MIMO. It can also use diversity transmission, precoding, or beamforming.

[0658] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0659] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0660] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0661] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0662] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. A data request method for an artificial intelligence or machine learning AI / ML model in beam management, applied to a terminal, comprising: Sending a data request message to a network device; The data request message is used to request the network device to send a target reference signal; The target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

2. The data request method for the AI / ML model in beam management according to claim 1, wherein: The data request message includes one or more of the following: Identification information of AI / ML models; Function identification information of AI / ML models; Resource collection identification information of AI / ML models; trigger identification information or configuration identification information; Reference signal collection information for AI / ML models; Performance monitoring performance indicator information; Time requirement information of target reference signal; Periodic type information of the target reference signal; Periodic information of the target reference signal; Number information of target reference signals; Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result; Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

3. The data request method for the AI / ML model in beam management according to claim 1, wherein: The data request message indicates the target reference signal based on a request signaling dedicated format, a request signaling scrambling sequence, or request signaling dedicated identification information.

4. The data request method for the AI / ML model in beam management according to any one of claims 1 to 3, wherein: The method further comprises: receiving a data response message sent by the network device, and determining, based on the data response message, whether the network device sends the target reference signal; or, Receive target reference signal related information sent by the network device, and determine whether the network device sends the target reference signal based on the target reference signal related information.

5. The data request method for the AI / ML model in beam management according to claim 4, wherein: The data response message includes one or more of the following: Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal; Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message; Identification information of the target AI / ML model; Function identification information of the target AI / ML model.

6. The data request method for AI / ML model in beam management according to claim 4, wherein: The determining, based on the data response message, whether the network device sends the target reference signal includes: When a data response message sent by the network device is received within the first time window, determining that the network device sends the target reference signal; If no data response message sent by the network device is received within the first time window, it is determined that the network device does not send the target reference signal.

7. The data request method for AI / ML model in beam management according to claim 4, wherein: The determining, based on the target reference signal related information, whether the network device sends the target reference signal includes: When receiving target reference signal related information sent by the network device within the second time window, determining that the network device sends the target reference signal; If the target reference signal related information sent by the network device is not received within the second time window, it is determined that the network device does not send the target reference signal.

8. The data request method for the AI / ML model in beam management according to any one of claims 1 to 3, wherein: The sending of a data request message to the network device includes: receiving data request configuration information sent by the network device; Based on the data request configuration information, a data request message is sent to the network device.

9. The data request method for the AI / ML model in beam management according to claim 8, wherein: The data request configuration information includes one or more of the following: trigger identification information or configuration identification information; Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information; Time domain information of the reference signal; Frequency domain information of the reference signal.

10. The data request method for the AI / ML model in beam management according to any one of claims 1 to 3, wherein: The data request message is sent based on one or more of a physical uplink control channel PUCCH, a physical uplink shared channel PUSCH, and a media access control layer control element MAC CE.

11. A data request method for an artificial intelligence or machine learning AI / ML model in beam management, applied to a network device, comprising: receiving a data request message sent by a terminal; determining a target reference signal based on the data request message; The target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

12. The data request method for the AI / ML model in beam management according to claim 11, wherein: The data request message includes one or more of the following: Identification information of AI / ML models; Function identification information of AI / ML models; Resource collection identification information of AI / ML models; trigger identification information or configuration identification information; Reference signal collection information for AI / ML models; Performance monitoring performance indicator information; Time requirement information of target reference signal; Periodic type information of the target reference signal; Periodic information of the target reference signal; Number information of target reference signals; Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result; Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

13. The data request method for AI / ML model in beam management according to claim 11, wherein: The determining the target reference signal based on the data request message includes: The target reference signal is determined based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

14. The data request method for an AI / ML model in beam management according to claim 11, wherein: After determining the target reference signal, the method further includes one or more of the following: Sending a data response message to the terminal; sending target reference signal related information to the terminal; Sending the target reference signal to the terminal.

15. The data request method for the AI / ML model in beam management according to claim 14, wherein: The data response message includes one or more of the following: Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal; Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message; Identification information of the target AI / ML model; Function identification information of the target AI / ML model.

16. The data request method for an AI / ML model in beam management according to claim 14, wherein: The sending a data response message to the terminal includes: Within the first time window, a data response message is sent to the terminal.

17. The data request method for an AI / ML model in beam management according to claim 14, wherein: The sending target reference signal related information to the terminal includes: In the second time window, target reference signal related information is sent to the terminal.

18. The data request method for an AI / ML model in beam management according to any one of claims 11 to 14, wherein: The method further comprises: Sending data request configuration information to the terminal.

19. The data request method for an AI / ML model in beam management according to claim 18, wherein: The data request configuration information includes one or more of the following: trigger identification information or configuration identification information; Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information; Time domain information of the reference signal; Frequency domain information of the reference signal.

20. The data request method for an AI / ML model in beam management according to any one of claims 14 to 16, wherein: The data response message is sent based on one or more of a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH and a media access control layer control element MAC CE.

21. A terminal comprising a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Sending a data request message to a network device; the data request message is used to request the network device to send a target reference signal; the target reference signal is used by the terminal to collect data for an artificial intelligence or machine learning AI / ML model in beam management.

22. The terminal according to claim 21, wherein: The data request message includes one or more of the following: Identification information of AI / ML models; Function identification information of AI / ML models; Resource collection identification information of AI / ML models; trigger identification information or configuration identification information; Reference signal collection information for AI / ML models; Performance monitoring performance indicator information; Time requirement information of target reference signal; Periodic type information of the target reference signal; Periodic information of the target reference signal; Number information of target reference signals; Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result; Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

23. The terminal according to claim 21, wherein: The data request message indicates the target reference signal based on a request signaling dedicated format, a request signaling scrambling sequence, or request signaling dedicated identification information.

24. The terminal according to any one of claims 21 to 23, wherein: The operations further include: receiving a data response message sent by the network device, and determining, based on the data response message, whether the network device sends the target reference signal; or, Receive target reference signal related information sent by the network device, and determine whether the network device sends the target reference signal based on the target reference signal related information.

25. The terminal according to claim 24, wherein: The data response message includes one or more of the following: Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal; Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message; Identification information of the target AI / ML model; Function identification information of the target AI / ML model.

26. The terminal according to claim 24, wherein: The determining, based on the data response message, whether the network device sends the target reference signal includes: When a data response message sent by the network device is received within the first time window, determining that the network device sends the target reference signal; If no data response message sent by the network device is received within the first time window, it is determined that the network device does not send the target reference signal.

27. The terminal according to claim 24, wherein: The determining, based on the target reference signal related information, whether the network device sends the target reference signal includes: When receiving target reference signal related information sent by the network device within the second time window, determining that the network device sends the target reference signal; If the target reference signal related information sent by the network device is not received within the second time window, it is determined that the network device does not send the target reference signal.

28. The terminal according to any one of claims 21 to 23, wherein: The sending of a data request message to the network device includes: receiving data request configuration information sent by the network device; Based on the data request configuration information, a data request message is sent to the network device.

29. The terminal according to claim 28, wherein: The data request configuration information includes one or more of the following: trigger identification information or configuration identification information; Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information; Time domain information of the reference signal; Frequency domain information of the reference signal.

30. The terminal according to any one of claims 21 to 23, wherein: The data request message is sent based on one or more of a physical uplink control channel PUCCH, a physical uplink shared channel PUSCH, and a media access control layer control element MAC CE.

31. A network device comprising a memory, a transceiver, and a processor: A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: receiving a data request message sent by a terminal; Based on the data request message, a target reference signal is determined; the target reference signal is used by the terminal to collect data for an artificial intelligence or machine learning AI / ML model in beam management.

32. The network device according to claim 31, wherein: The data request message includes one or more of the following: Identification information of AI / ML models; Function identification information of AI / ML models; Resource collection identification information of AI / ML models; trigger identification information or configuration identification information; Reference signal collection information for AI / ML models; Performance monitoring performance indicator information; Time requirement information of target reference signal; Periodic type information of the target reference signal; Periodic information of the target reference signal; Number information of target reference signals; Performance indicator indication information, the performance indicator indication information is used to indicate whether the terminal reports the performance indicator result; Actual measurement indication information, where the actual measurement indication information is used to indicate whether the terminal reports an actual measurement result.

33. The network device according to claim 31, wherein: The determining the target reference signal based on the data request message includes: The target reference signal is determined based on a request signaling-specific format, a request signaling scrambling sequence, or request signaling-specific identification information of the data request message.

34. The network device according to claim 31, wherein After determining the target reference signal, the operations further include one or more of the following: Sending a data response message to the terminal; sending target reference signal related information to the terminal; Sending the target reference signal to the terminal.

35. The network device according to claim 34, wherein: The data response message includes one or more of the following: Reference signal indication information, where the reference signal indication information is used to indicate whether to send the target reference signal; Request message indication information, where the request message indication information is used to indicate the data request message corresponding to the data response message; Identification information of the target AI / ML model; Function identification information of the target AI / ML model.

36. The network device according to claim 34, wherein: The sending a data response message to the terminal includes: Within the first time window, a data response message is sent to the terminal.

37. The network device according to claim 34, wherein: The sending target reference signal related information to the terminal includes: In the second time window, target reference signal related information is sent to the terminal.

38. The network device according to any one of claims 31 to 34, wherein: The operations further include: Sending data request configuration information to the terminal.

39. The network device according to claim 38, wherein: The data request configuration information includes one or more of the following: trigger identification information or configuration identification information; Reference signal set information associated with the trigger identification information, or reference signal set information associated with the configuration identification information; Time domain information of the reference signal; Frequency domain information of the reference signal.

40. The network device according to any one of claims 34 to 36, wherein: The data response message is sent based on one or more of a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH and a media access control layer control element MAC CE.

41. A data request device for an artificial intelligence or machine learning AI / ML model in beam management, applied to a terminal, comprising: A first sending unit, configured to send a data request message to a network device; The data request message is used to request the network device to send a target reference signal; The target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

42. A data request device for an artificial intelligence or machine learning AI / ML model in beam management, applied to a network device, comprising: A second receiving unit, configured to receive a data request message sent by a terminal; a second determining unit, configured to determine a target reference signal based on the data request message; The target reference signal is used by the terminal to collect data for the AI / ML model in beam management.

43. A non-transitory readable storage medium storing a computer program, wherein the computer program is used to enable a processor to execute the data request method for an artificial intelligence or machine learning AI / ML model in beam management as described in any one of claims 1 to 10.

44. A non-transitory readable storage medium storing a computer program, wherein the computer program is used to enable a processor to execute the data request method for an artificial intelligence or machine learning AI / ML model in beam management as described in any one of claims 11 to 20.

Images