Communication device and communication method

Abstract

NOT VISIBLE DUE TO STATUS OF PATENT

Description

Communication device and communication method

[0001] The present disclosure relates to a communication device and a communication method.

[0002] In recent years, the expansion and diversification of wireless services has led to the expectation of rapid development of the Internet of Things (IoT). Mobile communications are now being used in a wide range of applications, from smartphones and other information terminals to automobiles, homes, home appliances, and industrial equipment. To support this diversification, significant improvements in the performance and functionality of mobile communication systems are required, addressing various requirements, such as increased system capacity, an increased number of connected devices, and low latency. Fifth-generation mobile communication systems (5G) boast high-capacity and ultra-high-speed data transfer (eMBB: enhanced Mobile Broadband), massive machine-type communication (mMTC: massive Machine-Type Communication), and ultra-reliable and low-latency communication (URLLC), providing flexible wireless communications to meet diverse needs.

[0003] The 3rd Generation Partnership Project (3GPP), an international standardization organization, is working on the specification of New Radio (NR) as one of the 5G wireless interfaces.

[0004] RP-221348, “Revised SID: Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface,” Qualcomm (Moderator), June 2022.3GPP TS 38.214, “NR Physical layer procedures for data (Release 18),” December 2023.

[0005] However, there is room for improvement in the efficiency of wireless communications.

[0006] Non-limiting embodiments of the present disclosure contribute to providing a communication device and a communication method that can improve the efficiency of wireless communication.

[0007] A communication device according to one embodiment of the present disclosure includes a control circuit that determines control information relating to implementation-specific conditions or circumstances of a communication device or a communication partner in measuring channel state information during data collection for an artificial intelligence model for predicting channel state information, and a transmission circuit that transmits the control information to the communication partner.

[0008] These comprehensive or specific aspects may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a recording medium, or may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

[0009] According to an embodiment of the present disclosure, it is possible to improve the efficiency of wireless communication.

[0010] Further advantages and benefits of one embodiment of the present disclosure will become apparent from the specification and drawings. Such advantages and / or benefits may be provided by some embodiments and features described in the specification and drawings, respectively, but not necessarily all of them may be provided to obtain one or more identical features.

[0011] Figure showing an example of Channel State Information (CSI) prediction using Artificial Intelligence (AI) / Machine Learning (ML) technologyBlock diagram showing an example of data collection on the terminal sideBlock diagram showing an example of data collection on the network sideFigure showing an example when timeRestrictionForChannelMeasurements is set to "notConfigured"Figure showing an example when timeRestrictionForChannelMeasurements is set to "Configured"Figure showing an example of the relationship between transmit precoding and CSI prediction in NRBlock diagram showing an example of the configuration of a part of a base stationBlock diagram showing an example of the configuration of a part of a terminalFigure showing an example of CSI reportingFigure showing an example of the operation of a terminal and a base stationFigure showing an example of information about CSI measurement timeFigure showing an example of information about CSI measurement timeFigure showing an example of information about transmit precodingFigure showing an example of the operation of a terminal and a base stationFigure showing an example of information about transmit precodingFigure showing an example of information about transmit precodingFigure showing an example of information about transmit precodingFigure showing an example of CSI measurement period, CSI reporting period, and transmit precodingFigure showing an example of the operation of a terminal and a base stationFigure showing an example of information about receive filtersFigure showing an example of the operation of a terminal and a base stationSounding Reference 1. A diagram showing an example of data collection on the network side using Signal (SRS) 2. A diagram showing an example of information about a transmit filter 3. A diagram showing an example of the operation of a terminal and a base station 4. A block diagram showing an example of the configuration of a base station 5. A block diagram showing an example of the configuration of a terminal 6. A diagram of an example architecture of a 3GPP NR system 7. A diagram of an example functional division in 5G O-RAN

[0012] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0013] The basic functions of eMBB or URLLC were specified in Release 15. From Release 16 onwards, URLLC has been extended to include Industrial IoT, Vehicle-to-Everything (V2X), and Non-Terrestrial Networks (NTNs) including satellites. The extended specifications of 3GPP have been called "5G-Advanced" since Release 18 (also called Rel. 18).

[0014] Furthermore, advances in artificial intelligence (AI) technologies such as machine learning (ML) have been remarkable, and their application to mobile communications is also being considered. 3GPP is also studying and standardizing the application of AI / ML to various applications, and has begun studying the application of AI / ML to wireless interfaces since Release 18 (see, for example, Non-Patent Document 1). Representative use cases of AI / ML under consideration include channel state information (CSI) feedback, beam control, and position estimation.

[0015] In NR, for example, an access scheme based on Orthogonal Frequency Division Multiplexing (OFDM) is adopted for downlink communication. Furthermore, Multiple-Input Multiple Output (MIMO) is adopted to improve communication quality or increase data rates. To effectively utilize the performance of MIMO, closed-loop control is introduced, in which channel estimation is performed on the terminal (e.g., also called user equipment (UE)) side, and CSI is fed back to the base station (e.g., also called gNB). The base station applies transmit precoding and other techniques based on the fed-back CSI to perform downlink communication.

[0016] For example, when a wireless channel fluctuates over time due to factors such as the movement of a terminal, the wireless channel may fluctuate between the time the terminal estimates the channel and the time the base station actually performs downlink communication. In this case, a difference may occur between the channel used in the calculation of transmit precoding at the base station (e.g., the channel estimated and fed back by the terminal) and the channel used when the base station actually performs transmission. This difference in channel may be a factor that degrades the performance of downlink communication to which precoding is applied.

[0017] In Release 18, the application of AI / ML technologies to the radio interface is being considered, for example, for CSI feedback (CSI reporting), with time-domain CSI prediction (CSI prediction) using AI / ML technologies at the terminal side. As shown in Figure 1, CSI prediction involves inputting multiple historical CSI samples measured by the terminal into an AI / ML model, and outputting future CSI (predicted CSI). By feeding back the predicted CSI from the terminal to the base station, it is expected to mitigate downlink performance degradation due to the difference between the channel used by the base station to calculate transmit precoding (the channel estimated and fed back by the terminal) and the actual channel used by the base station for transmission.

[0018] For example, the training and operation (e.g., performance monitoring) of an AI / ML model for CSI prediction using AI / ML technology requires consideration of data collection procedures or mechanisms. In CSI prediction using terminal-side AI / ML technology, data collection may be performed on the terminal side, where the terminal performs training on the AI / ML model, or data collection may be performed on the network side (e.g., base station), where the network trains the AI / ML model, and then transfers the AI / ML model (or the dataset used to train the AI / ML model) to the terminal side.

[0019] When data collection is performed on the terminal side, the network configures the terminal's CSI measurement by notifying the terminal of a reference signal configuration for CSI measurement, such as a CSI Reference Signal (CSI-RS). Here, the terminal's CSI measurement may be initiated or triggered by the network, or may be requested by the terminal. For example, as shown in FIG. 2, the terminal uses CSI measured over multiple measurement occasions (also referred to as "CSI measurement occasions" or "CSI-RS measurement occasions") as input data for an AI / ML model to output (calculate) predicted CSI. At least for data collection for training, the measurement time may be long (e.g., several minutes or hours) to collect a sufficient data set.

[0020] When data collection is performed on the network side, the network notifies the terminal of a reference signal configuration for CSI measurement, such as CSI-RS, to configure CSI measurement for the terminal. The terminal reports measured CSI (e.g., training data or ground-truth CSI) to the network, for example, as shown in FIG. 3. Here, the ground-truth CSI from the terminal may be reported for each CSI measurement sample, as shown in FIG. 3, or for each group including multiple samples. In sample-by-sample reporting, there is a one-to-one correspondence between CSI measurements and CSI reports, and one CSI report includes ground-truth CSI generated by one CSI measurement. In group-by-group reporting, one CSI report includes ground-truth CSI generated by multiple CSI measurements. The network side uses CSI measured on the terminal side over multiple measurement occasions (CSI measurement occasions) over time as input data for an AI / ML model to output predicted CSI. At least for data collection for training, measurement times can be long (e.g., minutes or hours) to collect a sufficient data set.

[0021] In existing CSI measurement in NR (see, for example, Non-Patent Document 2), when "timeRestrictionForChannelMeasurements," a parameter indicated (configured) by Radio Resource Control (RRC) in Layer 3, is set to "notConfigured," the terminal uses a Non-Zero Power (NZP) CSI-RS that is temporally earlier than the CSI reference resource for CSI measurement (channel measurement), as shown in FIG. 4, to estimate CSI in the CSI reference resource, and reports the estimated CSI in slot n. In such a configuration, since the terminal measures CSI using multiple CSI-RSs that are earlier than the CSI reference resource, the network needs to set (or maintain) the same transmit precoder (or transmit precoding) used for transmitting the CSI-RS in the section in which the terminal measures CSI.

[0022] On the other hand, in the case of CSI measurement in existing NR, when "timeRestrictionForChannelMeasurements" is set to "Configured," the terminal estimates CSI for the CSI reference resource using the latest NZP CSI-RS that is earlier in time than the CSI reference resource for CSI measurement (i.e., without using other NZP CSI-RS), as shown in Fig. 5. In this configuration, since the terminal measures CSI using one CSI-RS earlier than the CSI reference resource, the network can change the transmit precoder used for transmitting the CSI-RS for each CSI report (or CSI measurement occasion).

[0023] In the following description, the above-mentioned transmission precoder or transmission precoding (hereinafter also referred to as transmission precoding / transmission precoder) will be described as an example of precoding in the digital domain in a standard specification, but the transmission precoding / transmission precoder is not limited to precoding in the digital domain in a standard specification. The transmission precoding / transmission precoder may be precoding in the digital domain specific to the implementation of a base station or a network, beamforming in the antenna / analog domain, or a combination of these.

[0024] In existing NR, depending on the setting of "timeRestrictionForChannelMeasurements" as "notConfigured" or "Configured" as described above, the network side supports either 1) applying the same transmit precoding to the transmission of multiple CSI-RSs, or 2) enabling the transmit precoding to be changed for each CSI-RS. Since CSI prediction uses measurement results from multiple CSI measurement occasions in the time domain to calculate predicted CSI, it is assumed that the transmit precoding applied to CSI-RSs is the same within the measurement window for calculating predicted CSI.

[0025] Therefore, for example, as shown in FIG. 6, in existing NR, when "timeRestrictionForChannelMeasurements" is set to "Configured," the network may change the transmit precoding applied to the CSI-RS, and therefore CSI prediction is not possible. On the other hand, as shown in FIG. 6, when "timeRestrictionForChannelMeasurements" is set to "notConfigured," the network always applies the same transmit precoding to the CSI-RS, and therefore CSI prediction on the terminal side is possible (enabled), but the network's transmit precoder configuration is limited. Even when CSI prediction on the terminal side is enabled, it would be effective in terms of network operation to enable the network side to change the transmit precoding as needed, but this is difficult to achieve in existing NR.

[0026] Furthermore, the settings of the receive filters that a terminal applies to receive CSI-RS or the settings of the transmit filters that a terminal applies to transmit a Sounding Reference Signal (SRS) may not be limited to the settings specified in the standard specifications but may be specific to the terminal's implementation. For example, when data collection and AI / ML model training are performed on the network side, information that is terminal implementation-dependent, such as the terminal's transmit and receive filters, may be useful for training or managing the AI / ML model.

[0027] In a non-limiting embodiment of the present disclosure, a method for matching assumptions (or a method for achieving a common understanding) regarding precoding or transmit / receive filters when measuring CSI between a network and a terminal is described. This allows the network side to change transmit precoding as needed, even when multiple time-domain CSI measurement opportunities are used for, for example, AI / ML model training, AI / ML inference, and AI / ML model monitoring, as typified by CSI prediction, thereby enabling flexible network operation and AI / ML model training or management that takes into account implementation-specific transmit / receive filter settings of the terminal.

[0028] Non-limiting embodiments of the present disclosure will be described below.

[0029] Note that CSI prediction refers to the prediction of CSI using multiple CSI-RSs. For example, in CSI prediction, CSI measurements obtained in multiple CSI measurement occasions temporally preceding the CSI reference resource are used to predict CSI beyond the CSI reference resource. In the following, CSI prediction is described as an example of the target of the AI / ML model, but the target of the AI / ML model is not limited to CSI prediction and can also be applied to other use cases using multiple CSI measurement occasions in the time domain (e.g., time-domain beam prediction, space-frequency-time domain CSI compression, etc.).

[0030] [Overview of Communication System] A communication system according to an aspect of the present disclosure includes, for example, at least one base station and at least one terminal.

[0031] FIG. 7 is a block diagram showing a configuration example of a portion of a base station 100 according to an embodiment of the present disclosure, and FIG. 8 is a block diagram showing a configuration example of a portion of a terminal 200 according to an embodiment of the present disclosure.

[0032] In the base station 100 (e.g., corresponding to a communication device) shown in Fig. 7, a control unit (e.g., corresponding to a control circuit) determines control information related to implementation-specific conditions or situations of the communication device (e.g., base station 100) or a communication counterpart (e.g., terminal 200) in measuring channel state information in data collection for an artificial intelligence model (AI / ML model) for predicting channel state information (e.g., CSI prediction). A communication unit (e.g., corresponding to a transmission circuit) transmits the control information to the communication counterpart (e.g., terminal 200).

[0033] Furthermore, in the base station 100 (e.g., corresponding to a communication device), a communication unit (e.g., corresponding to a receiving circuit) receives control information related to implementation-specific conditions or situations of a communication partner (e.g., terminal 200) in measuring channel state information in data collection for an artificial intelligence model (AI / ML model) for predicting channel state information (e.g., CSI prediction). A control unit (e.g., corresponding to a control circuit) controls the data collection (or learning and updating of the AI / ML model) based on the control information.

[0034] In the terminal 200 (e.g., corresponding to a communication device) shown in Fig. 8, a control unit (e.g., corresponding to a control circuit) determines control information related to implementation-specific conditions or situations of the communication device (e.g., terminal 200) or a communication counterpart (e.g., base station 100) in measuring channel state information in data collection for an artificial intelligence model (AI / ML model) for predicting channel state information (e.g., CSI prediction). A communication unit (e.g., corresponding to a transmission circuit) transmits the control information to the communication counterpart (e.g., base station 100 or a network).

[0035] Furthermore, in the terminal 200 (e.g., corresponding to a communication device), a communication unit (e.g., corresponding to a receiving circuit) receives control information regarding implementation-specific conditions or situations of a communication partner (e.g., a base station 100 or a network) in measuring channel state information in data collection for an artificial intelligence model (AI / ML model) for predicting channel state information (e.g., CSI prediction). A control unit (e.g., corresponding to a control circuit) controls the data collection (or learning and updating of the AI / ML model) based on the control information.

[0036] (First Embodiment) In this embodiment, it is assumed that data collection is performed on the network side (base station 100 side).

[0037] The network (for example, base station 100) notifies terminal 200 of a reference signal configuration for CSI measurement, such as CSI-RS, to configure CSI measurement for terminal 200.

[0038] Terminal 200 reports measured CSI (e.g., training data or ground-truth CSI) to the network. Here, reporting of ground-truth CSI from terminal 200 may be performed for each CSI measurement sample (e.g., CSI measurement occasion) or for each group including multiple samples. In CSI reporting for each sample, there is a one-to-one correspondence between CSI measurements and CSI reports, and one CSI report includes ground-truth CSI generated by one CSI measurement. Furthermore, in CSI reporting for each group, one CSI report includes ground-truth CSI generated by multiple CSI measurements. Furthermore, in CSI reporting for each group, multiple CSI reference resources may be configured for one CSI report. For example, a CSI reference resource may be configured for each of multiple CSI measurements and ground-truth CSI generation corresponding to one CSI report.

[0039] In this embodiment, terminal 200 explicitly or implicitly reports information related to the CSI measurement time to the network. Furthermore, terminal 200 reports the CSI to the network without averaging the CSI measurement values.

[0040] The network maintains information about transmit precoding applied in each CSI measurement occasion. In addition to the information about transmit precoding, the network maintains information about non-averaged CSI measurements and CSI measurement times reported from terminal 200. This allows the network to identify the relationship between the transmit precoding applied by the network and ground-truth CSI report data (e.g., CSI-RS transmission occasions) from terminal 200.

[0041] Furthermore, in this embodiment, even when CSI prediction is performed, the network can set "timeRestrictionForChannelMeasurements" to "Configured" and operate to change transmission precoding as needed.

[0042] In per-sample CSI reporting, there is a one-to-one correspondence between CSI measurements and CSI reports, and one CSI report includes ground-truth CSI generated by one CSI measurement. Therefore, terminal 200 does not need to explicitly report information related to the CSI measurement time. The network can identify the CSI reference resource and the CSI measurement occasion used by terminal 200 for CSI measurement based on the timing (e.g., slot position) at which terminal 200 transmits the CSI report. This allows the network to identify the relationship between the CSI measurement occasion and the transmit precoding.

[0043] In group-based CSI reporting, for example, if the number of CSIs (e.g., "N") to be reported by a CSI report is preset by RRC or the like, terminal 200 does not need to explicitly report information related to the CSI measurement time. For example, the network can identify the CSI reference resource N before the timing (e.g., slot position) at which terminal 200 transmits the CSI report and the CSI measurement occasion used by terminal 200 for CSI measurement. This allows the network to identify the relationship between the CSI measurement occasion and the transmit precoding.

[0044] For example, when the number of CSIs reported by terminal 200 is variable for each CSI report, terminal 200 may explicitly add information about the CSI measurement time to each CSI report. For example, the information about the CSI measurement time may be a frame, slot, or symbol number, or a timestamp (e.g., YY-MM-DD HH:MM:SS).

[0045] In this embodiment, after training or updating of the AI / ML model on the network side, the network transmits (e.g., forwards or distributes) the AI / ML model or a dataset used for training the AI / ML model to the terminal 200 for model identification. Training of the AI / ML model on the network side is performed under specific assumptions (additional conditions) regarding parameters related to the input and output (hereinafter also referred to as input / output) of the transmit precoding and the AI / ML model. For example, the assumptions regarding the transmit precoding can be consistent between the network and the terminal via the identified AI / ML model or dataset. For example, the assumptions regarding the parameters related to the input / output of the transmit precoding and the AI / ML model may be an assumption that the same transmit precoding is applied to the input for calculating predicted CSI and the output predicted CSI, or an assumption that a specific pattern of transmit precoding is applied to the input for calculating predicted CSI and the output predicted CSI.

[0046] FIG. 9 is a diagram showing an example of a ground-truth CSI report according to the present embodiment.

[0047] As shown in FIG. 9 , in per-sample CSI reporting, terminal 200 reports information about CSI measurement times (e.g., #0, #1, #2) to the network when reporting CSI measurements measured for each sample. In per-sample CSI reporting, CSI measurements are reported for each sample, so the CSI measurements are not averaged. As shown in FIG. 9 , the network holds information about transmit precoding (e.g., #A, #A, #B) applied at each CSI measurement occasion (e.g., corresponding to a CSI measurement sample). Thus, the network can identify the relationship between the CSI measurement occasion and the transmit precoding based on the information about the transmit precoding and the information about the CSI measurement time from terminal 200. In the example of FIG. 9 , the network can identify that CSI measurement times #0 and #1 correspond to transmit precoding #A, and that CSI measurement time #2 corresponds to transmit precoding #B. Note that, as described above, in per-sample CSI reporting, information about the CSI measurement time does not need to be reported.

[0048] As shown in FIG. 9 , in group-based CSI reporting, terminal 200 reports CSI measurements measured for each of multiple samples included in a group without averaging them. Furthermore, when reporting CSI for each group, terminal 200 reports information about CSI measurement times (e.g., #N-3, #N-2, #N-1) to the network. As shown in FIG. 9 , the network holds information about transmit precoding (e.g., #C, #C, #D) applied to each CSI measurement occasion (e.g., corresponding to a CSI measurement sample). Therefore, the network can identify the relationship between the CSI measurement occasion and the transmit precoding based on the information about the transmit precoding and the information about the CSI measurement time from terminal 200. In the example of FIG. 9 , the network can identify that CSI measurement times #N-3 and #N-2 correspond to transmit precoding #C and that CSI measurement time #N-1 corresponds to transmit precoding #D. As described above, in group-based CSI reporting, if the number of samples N in a group is set in advance, information related to the CSI measurement time does not need to be reported.

[0049] 9 , the network can identify the status (e.g., correspondence) of the CSI measurement occasion with respect to the transmit precoding applied to the CSI-RS by reporting the information on the CSI measurement time from terminal 200. That is, the information on the CSI measurement time transmitted from terminal 200 to the network is information on the condition or status of the transmit precoding applied by the network at each CSI measurement occasion (e.g., the condition or status of the transmit precoding specific to the network implementation).

[0050] By identifying the correspondence between the CSI measurement occasions and the transmit precoding, the network can use CSI measurements (e.g., CSI measurements for the time intervals #0 and #1 in FIG. 9 or CSI measurements for the time intervals #N-3 and #N-2 in FIG. 9 ) based on the CSI-RS transmitted using the same transmit precoding (e.g., #A or #C in FIG. 9 ) as input data to the AI / ML model for outputting predicted CSI. Furthermore, as shown in FIG. 9 , the network can change the transmit precoding for each CSI-RS even when training or updating of the AI / ML model for CSI prediction is performed within the time intervals #0 to #N-1 (measurement interval and reporting interval).

[0051] [Example of Operation of Base Station 100 and Terminal 200] FIG. 10 is a flowchart showing an example of operation of base station 100 (referred to as base station / network) and terminal 200 according to this embodiment.

[0052] In FIG. 10, the base station / network transmits configuration related to CSI measurement and reporting to the terminal 200 (S101).

[0053] Terminal 200 measures CSI based on the configuration related to CSI measurement and reporting (S102). Terminal 200 transmits a CSI report to the base station / network based on the CSI measurement result (S103). When reporting CSI, terminal 200 reports information related to the CSI measurement time to the base station / network.

[0054] The base station / network collects data on an AI / ML model for outputting predicted CSI, for example, based on information on transmit precoding applied to the CSI-RS and information on the CSI measurement time reported from the terminal 200 (S104), and uses the collected data to train and update the AI / ML model (S105).The base station / network then transmits (or transfers or distributes) the AI / ML model or a data set of the AI / ML model to the terminal 200 (S106).

[0055] Thus, in this embodiment, in data collection for an AI / ML model for CSI prediction, terminal 200 transmits information regarding the CSI-RS measurement time to the network as control information regarding the implementation-specific conditions of the base station / network or terminal 200 in CSI measurement (e.g., the relationship between transmit precoding and CSI measurement occasions).

[0056] This allows the base station / network to identify the relationship between transmit precoding and CSI measurement occasions when measuring CSI. Therefore, according to this embodiment, assumptions regarding transmit precoding can be aligned (or matched) between the network and terminal 200 via the identified AI / ML model or dataset. This allows the network to change transmit precoding as needed, even when multiple time-domain CSI measurement occasions are used for AI / ML model training, AI / ML inference, and AI / ML model monitoring. For example, even when "timeRestrictionForChannelMeasurements" is set to "Configured," the network can perform CSI prediction while changing the transmit precoding applied to the CSI-RS.

[0057] Therefore, according to this embodiment, even when CSI prediction is effective, the efficiency of wireless communication can be improved by making it possible to change transmission precoding at any time on the network side.

[0058] Furthermore, according to this embodiment, assumptions regarding the network's transmit precoding and additional information (additional conditions) when learning other AI / ML models are shared between the network and terminal 200 via the AI / ML model or dataset, so the network does not need to explicitly disclose transmit precoding and other additional information on the network side to terminal 200.

[0059] (Modification of First Embodiment) Note that, when information on the CSI measurement time is explicitly added to each CSI report, the information on the CSI measurement time is not limited to the example shown in FIG. 9 .

[0060] For example, as shown in FIG. 11, the information regarding the CSI measurement time may be information indicating the time interval (gap) from the previous CSI measurement time (for example, 0, N, or M).

[0061] Alternatively, as shown in FIG. 12 , the information related to the CSI measurement time may be information indicating the number of a CSI measurement or report (measurement / report) relative to a certain reference time. For example, the reference times (certain time 1 and certain time 2 in FIG. 12 ) may be predefined or set periodically. For example, the time at the beginning of a frame may be predefined as the reference time, or a specific frame position, slot position, or symbol position may be set periodically. Furthermore, the reference time may be the time of a CSI report, and the measurement / report number relative to the reference time may be information indicating the number of the CSI measurement value (before or after) the report is based on from the reference time.

[0062] These modifications can reduce overhead compared to reporting information related to CSI measurement times using frame numbers, slot numbers, symbol numbers, timestamps, or the like.

[0063] Second Embodiment In this embodiment, it is assumed that data collection is performed on the terminal 200 side.

[0064] The network (e.g., base station 100) notifies terminal 200 of a reference signal configuration for CSI measurement, such as CSI-RS, to configure CSI measurement of terminal 200. CSI measurement of terminal 200 may be initiated or triggered by the network side, or may be requested by terminal 200, for example.

[0065] In this embodiment, the network transmits (or provides) information regarding transmit precoding to be applied to CSI-RS to terminal 200. For example, the information regarding transmit precoding to be applied to CSI-RS may be explicit information regarding the transmit precoder to be applied to each CSI-RS. The explicit information regarding the transmit precoder may be, for example, information regarding the transmit precoding vector to be applied to each CSI-RS. For example, the network may notify terminal 200 in advance of information regarding a set of transmit precoding vectors, and may notify terminal 200, using an index, which transmit precoding vector from the set of transmit precoding vectors has been applied to each CSI-RS.

[0066] Terminal 200 determines which transmit precoding is applied to each CSI measurement occasion based on information about the transmit precoding applied to the CSI-RS, thereby enabling terminal 200 to determine the relationship between the transmit precoding applied by the network and the CSI measurement values ​​(e.g., CSI measurement occasions).

[0067] Therefore, the learning and updating of the AI / ML model on the terminal 200 side can be performed under specific assumptions regarding parameters related to the input / output of the transmit precoding and the AI / ML model. For example, the specific assumption regarding parameters related to the input / output of the transmit precoding and the AI / ML model may be an assumption that the transmit precoding applied to the input for calculating the predicted CSI and the output predicted CSI is the same, or an assumption that transmit precoding is applied in a specific pattern to the input for calculating the predicted CSI and the output predicted CSI.

[0068] FIG. 13 is a diagram illustrating an example of information related to CSI measurement and transmit precoding at each CSI measurement occasion according to the present embodiment.

[0069] 13, terminal 200 collects CSI measurement data (e.g., input data for an AI / ML model) using information related to transmit precoding from the network side. For example, terminal 200 uses data measured using a CSI-RS (or at a CSI measurement occasion) to which the same transmit precoding (#A or #C in the example of FIG. 13) is applied based on the information related to transmit precoding as learning input data for an AI / ML model for outputting (calculating) predicted CSI.

[0070] 13 , by notification of information related to transmit precoding from the network, terminal 200 can identify the status of transmit precoding applied to CSI-RS at each CSI measurement occasion (e.g., correspondence with CSI measurement occasions). That is, the information related to transmit precoding notified from the network to terminal 200 is information related to the condition or status of transmit precoding applied by the network at each CSI measurement occasion (e.g., the condition or status of transmit precoding specific to the network implementation).

[0071] [Example of Operation of Base Station 100 and Terminal 200] FIG. 14 is a flowchart showing an example of operation of base station 100 (referred to as base station / network) and terminal 200 according to this embodiment.

[0072] In FIG. 14, the base station / network transmits configuration related to CSI measurement and reporting to the terminal 200 (S201).

[0073] Terminal 200 measures CSI based on the settings related to CSI measurement and reporting (S202).

[0074] The base station / network notifies, for example, terminal 200 of information related to transmit precoding applied to CSI-RS (S203). The notification of the information related to transmit precoding may be an explicit notification. Furthermore, the notification of the information related to transmit precoding may be performed at a timing prior to S102.

[0075] The terminal 200 collects data for an AI / ML model to output predicted CSI based on the CSI measurement results and information related to transmit precoding (S204), and uses the collected data to train and update the AI / ML model (S205).

[0076] Thus, in this embodiment, in data collection for an AI / ML model for CSI prediction, the network (e.g., a base station) transmits information regarding transmit precoding applied to CSI-RS to terminal 200 as control information regarding the implementation-specific circumstances of the network or terminal 200 in CSI measurement (e.g., the relationship between transmit precoding and CSI measurement occasions).

[0077] This allows terminal 200 to identify the relationship between transmit precoding and CSI measurement occasions when measuring CSI. Therefore, according to the present embodiment, assumptions regarding transmit precoding can be made consistent (or matched) between the network and terminal 200. This enables the network to change transmit precoding as needed even when multiple time-domain CSI measurement occasions are used for AI / ML model training, AI / ML inference, and AI / ML model monitoring. For example, even when "timeRestrictionForChannelMeasurements" is set to "Configured," it becomes possible to perform CSI prediction while changing the transmit precoding applied to the CSI-RS by the network.

[0078] Therefore, according to this embodiment, even when CSI prediction is effective, the efficiency of wireless communication can be improved by making it possible to change transmission precoding at any time on the network side.

[0079] Third Embodiment In this embodiment, it is assumed that data collection is performed on the terminal 200 side.

[0080] The network (e.g., base station 100) notifies terminal 200 of a reference signal configuration for CSI measurement, such as CSI-RS, to configure CSI measurement of terminal 200. CSI measurement of terminal 200 may be initiated or triggered by the network side, or may be requested by terminal 200, for example.

[0081] The wireless channel observable by CSI measurement in terminal 200 corresponds to the combined output of digital domain precoding, antenna / analog domain beamforming, and the propagation channel. Therefore, explicit information about the transmit precoding itself, as described in the second embodiment, is not necessarily beneficial for data collection and AI / ML model training on the terminal 200 side. While detailed information about the combination of digital domain precoding and antenna / analog domain beamforming may be provided to terminal 200 from the network, such information may be confidential information related to the network implementation, and thus is open to discussion.

[0082] In this embodiment, the network transmits (or provides) information regarding transmit precoding applied to CSI-RS to terminal 200. For example, the information regarding transmit precoding applied to CSI-RS in this embodiment is information regarding a change in transmit precoding, instead of explicit information as in embodiment 2. For example, the information regarding a change in transmit precoding may be relative information between CSI measurement occasions (e.g., adjacent CSI measurement occasions) regarding transmit precoding applied in each CSI-RS transmission opportunity.

[0083] For example, the information related to transmit precoding (relative information related to a transmit precoding change) may be any of the following information:

[0084] <Option 1> In Option 1, the information related to transmit precoding is information indicating whether the transmit precoding is changed between CSI measurement occasions (e.g., adjacent CSI measurement occasions) (e.g., whether the transmit precoding is the same or different).

[0085] 15 , the network transmits relative information between CSI measurement occasions, regarding whether the transmit preceding between CSI measurement occasions is the same or different, to terminal 200. For example, the information regarding whether the transmit preceding between CSI measurement occasions is the same or different may be 1-bit information (0 or 1) corresponding to each CSI measurement occasion (for example, "0" if the transmit preceding is the same, and "1" if the transmit preceding is different, or vice versa).

[0086] Information regarding whether the transmit precoding between CSI measurement occasions is the same or different may be provided to terminal 200 via, for example, any downlink signal. The downlink signal may be, for example, at least one of RRC, Medium Access Control-Control Element (MAC-CE), and Downlink Control Information (DCI).

[0087] Furthermore, the timing at which information regarding whether transmit preceding between CSI measurement occasions is the same or different may be provided to terminal 200 may be, for example, when a CSI-RS configuration for data collection is configured, at a timing during a data collection period, or after data collection is completed. Furthermore, information regarding multiple CSI measurement occasions may be collectively notified to terminal 200 as information regarding whether transmit preceding between CSI measurement occasions is the same or different.

[0088] <Option 2> In Option 2, the information related to transmit precoding is information related to the timing of changing transmit precoding among a plurality of CSI measurement occasions (for example, the CSI measurement occasion at which the transmit precoding is changed).

[0089] 16 , the network transmits information (relative information) related to the timing of changing the transmission preceding to the terminal 200. For example, the information related to the timing of changing the transmission preceding may be information indicating a frame number, a slot number, or a symbol number, or may be information indicating a timestamp (for example, YY-MM-DD HH:MM:SS).

[0090] Furthermore, the information regarding the timing of changing transmission precoding may be, for example, the number of a CSI measurement occasion relative to a certain reference time. For example, the reference time may be defined in advance or may be set periodically. For example, the beginning of a frame may be defined in advance as the reference time, or a specific frame position, slot position, or symbol position may be set periodically. Furthermore, the reference time may be the time of CSI reporting. The number of a CSI measurement occasion relative to the reference time may be information indicating the number of the CSI measurement occasion relative to (before or after) the reference time.

[0091] Furthermore, the terminal 200 may identify, for example, the CSI measurement opportunity immediately before (or immediately after, a certain time before, or a certain time after) receiving information (notification from the network) regarding the timing of changing the transmission precoding as the timing of changing the transmission precoding.

[0092] Information regarding the timing of changing the transmission precoding may be provided to terminal 200 via any downlink signal (for example, at least one of RRC, MAC-CE, and DCI), for example.

[0093] Furthermore, the timing at which information regarding the timing to change the transmit preceding may be provided to terminal 200 may be, for example, when the CSI-RS configuration for data collection is set, at a timing during a data collection period, or after data collection is completed. Furthermore, information regarding a plurality of change timings may be notified to terminal 200 collectively as information regarding the timing to change the transmit preceding.

[0094] <Option 3> In Option 3, the information on transmit precoding is information on a pattern of timing for changing transmit precoding in multiple CSI measurement occasions.

[0095] For example, as shown in FIG. 17 , the network transmits information (relative information) regarding a timing pattern for changing transmit precoding to terminal 200. For example, the information regarding the timing pattern for changing transmit precoding may be relative information regarding how many CSI measurement occasions the same transmit precoding is applied to. For example, in the example shown in FIG. 17 , the information regarding the timing pattern for changing transmit precoding may be [2, 3, 1, 1]. Terminal 200 identifies a transmit precoding pattern [#A, #A, #B, #B, #B, #C, #D] to be applied to CSI-RS transmission in each CSI measurement occasion based on the information [2, 3, 1, 1] regarding the timing pattern for changing transmit precoding.

[0096] Information regarding the timing pattern for changing the transmission precoding may be provided to terminal 200 via any downlink signal (for example, at least one of RRC, MAC-CE, and DCI), for example.

[0097] Furthermore, the timing at which information regarding the timing pattern for changing the transmit precoding is provided to terminal 200 may be when a CSI-RS configuration is configured for data collection, at a timing during a data collection period, or after data collection is completed. Furthermore, information regarding a plurality of change timing patterns may be notified collectively to terminal 200 as information regarding the timing pattern for changing the transmit precoding, or a periodic timing pattern for changing the transmit precoding may be notified by information regarding one timing pattern for changing the transmit precoding.

[0098] An example of relative information related to transmit precoding according to this embodiment has been described above.

[0099] The operations of base station 100 (referred to as base station / network) and terminal 200 according to this embodiment may be similar to the operation example according to embodiment 2 ( FIG. 14 ). However, in S203 of FIG. 14 , the information related to transmit precoding applied to CSI-RS transmission notified from the base station / network to terminal 200 is relative information related to a change in transmit precoding.

[0100] Thus, in this embodiment, in data collection for an AI / ML model for CSI prediction, the network (e.g., a base station) transmits to terminal 200 information related to the transmit precoding applied to CSI-RS (e.g., information related to changes in transmit precoding) as control information related to the implementation-specific situation of the network or terminal 200 in CSI measurement (e.g., the relationship between transmit precoding and CSI measurement occasions).

[0101] This allows terminal 200 to identify the relative relationship of transmit precoding for each CSI measurement occasion. Therefore, terminal 200 can learn and update the AI / ML model under specific assumptions regarding parameters related to the transmit precoding and the input / output of the AI / ML model. For example, the specific assumption regarding parameters related to the transmit precoding and the input / output of the AI / ML model may be an assumption that the same transmit precoding is applied to the input for calculating the predicted CSI and the output predicted CSI, or an assumption that transmit precoding is applied in a specific pattern to the input for calculating the predicted CSI and the output predicted CSI.

[0102] Furthermore, according to the present embodiment, even if the network does not explicitly disclose information related to precoding (e.g., non-disclosed information related to the implementation of transmit precoding in the network), assumptions related to transmit precoding can be made consistent (or matched) between the network and terminal 200 by using relative information between CSI measurement occasions related to transmit precoding. This allows the network to change transmit precoding as needed even when multiple time-domain CSI measurement occasions are used for AI / ML model training, AI / ML inference, and AI / ML model monitoring. For example, even when "timeRestrictionForChannelMeasurements" is set to "Configured," CSI prediction can be performed while changing the transmit precoding applied to the CSI-RS by the network.

[0103] Therefore, according to this embodiment, even when CSI prediction is effective, the efficiency of wireless communication can be improved by making it possible to change transmission precoding at any time on the network side.

[0104] (Note to Embodiments 2 and 3) Terminal 200 may perform CSI measurement by time-averaging CSI-RS samples to which the same transmit precoding is applied. In some cases, time-averaging multiple CSI-RS samples can be expected to improve the accuracy of channel measurement and estimation.

[0105] (Note to the third embodiment) In addition, in the information regarding the timing pattern for changing the transmission precoding, the CSI-RS opportunities to which the same transmission precoding is applied do not have to be consecutive. For example, the transmission precoding change pattern may be cyclic, such as transmission precoding #A, #B, #C, #A, #B, #C ...

[0106] (Fourth Embodiment) In this embodiment, it is assumed that data collection is performed on the terminal 200 side.

[0107] The network (e.g., base station 100) notifies terminal 200 of a reference signal configuration for CSI measurement, such as CSI-RS, to configure CSI measurement of terminal 200. CSI measurement of terminal 200 may be initiated or triggered by the network side, or may be requested by terminal 200, for example.

[0108] In CSI prediction, for example, [k, k+W meas A CSI-RS measurement window of [k -1] may be set. For example, it is assumed that CSI measurement samples measured in CSI measurement occasions within the CSI-RS measurement period are used as input data to an AI / ML model for predicting CSI output. Here, k indicates the first CSI measurement occasion (e.g., time information) within the CSI-RS measurement period, and W meas indicates the CSI-RS measurement period length.

[0109] Also, for the output of the AI / ML model (e.g., predicted CSI), for example, [l, l+W CSI A CSI reporting window of [W −1] may be set. For example, it is assumed that the CSI corresponding to the CSI measurement occasion within the CSI reporting interval is calculated as the predicted CSI. Here, l denotes the CSI measurement occasion (e.g., time information) corresponding to the leading predicted CSI within the CSI reporting interval, and W CSI indicates the CSI reporting interval length.

[0110] The parameters related to the CSI-RS measurement period and the parameters related to the CSI reporting period described above can be considered as additional information (additional conditions) when terminal 200 learns and updates the AI / ML model, for example.

[0111] In this embodiment, terminal 200 reports additional information (additional conditions) to the network when terminal 200 performs learning and updating of an AI / ML model. For example, in the case of CSI prediction, terminal 200 may report parameters related to the CSI-RS measurement period and parameters related to the CSI reporting period to the network as additional information. This information may be reported to the network during a function or model identification procedure from terminal 200.

[0112] FIG. 18 is a diagram illustrating an example of a CSI-RS measurement period, a CSI reporting period, and transmission precoding in this embodiment. In the example of FIG. 18, terminal 200 reports parameters related to at least one of the CSI-RS measurement period and the CSI reporting period to the network. Also, in the example of FIG. 18, terminal 200 measures CSI using CSI-RS at CSI measurement occasions (times #0, #1, and #2) within the CSI-RS measurement period, for example, and uses the CSI measurement samples as input data to an AI / ML model for predicted CSI output. Also, in the example of FIG. 18, terminal 200 calculates predicted CSI at CSI measurement occasions (times #3 and #4) within the CSI reporting period, for example, and reports the predicted CSI samples to the network.

[0113] The network (for example, base station 100) may be configured to apply (or maintain) the same precoding (transmission precoding #B in the example of FIG. 18 ) in intervals corresponding to the CSI-RS measurement interval and CSI reporting interval reported from terminal 200. Furthermore, it is assumed that terminal 200 applies (or maintains) the same transmission precoding in the CSI-RS measurement interval and CSI reporting interval related to CSI reporting.

[0114] This allows the assumptions regarding CSI measurement occasions and transmission precoding within the CSI reporting interval to be consistent (or matched) between the network and terminal 200, so that terminal 200 can use multiple time-domain CSI measurement occasions for learning an AI / ML model, inference using the AI / ML model, and monitoring the AI / ML model.

[0115] As shown in Fig. 18 , by reporting additional information (e.g., information related to the CSI-RS measurement interval and the CSI reporting interval) from terminal 200 to the network, the network and terminal 200 can identify the conditions or situations of transmit precoding assumed in each CSI measurement occasion and CSI reporting occasion (e.g., the correspondence between the CSI-RS measurement interval and the CSI reporting interval). In other words, the additional information reported from terminal 200 to the network is information related to the situation of transmit precoding applied by the network in the CSI-RS measurement interval and the CSI reporting interval (e.g., the situation of transmit precoding specific to the implementation of the network).

[0116] [Example of Operation of Base Station 100 and Terminal 200] FIG. 19 is a flowchart showing an example of operation of base station 100 (referred to as base station / network) and terminal 200 according to this embodiment.

[0117] 19 , terminal 200 reports additional information to the network when training and updating the AI / ML model on terminal 200 side (S301). For example, in the case of CSI prediction, terminal 200 may report parameters related to the CSI-RS measurement period and parameters related to the CSI reporting period as additional information.

[0118] The base station / network transmits configuration regarding CSI measurement and reporting to the terminal 200 (S302).

[0119] Terminal 200 measures CSI based on the configuration related to CSI measurement and reporting (S303). At this time, the base station / network may apply the same transmit precoding to the interval including the CSI-RS measurement interval and the CSI reporting interval corresponding to the additional information. Furthermore, terminal 200 may assume the application of the same transmit precoding to the interval including the CSI-RS measurement interval and the CSI reporting interval corresponding to the additional information.

[0120] Based on the CSI measurement results, the terminal 200 collects data for an AI / ML model to output predicted CSI (S304), and uses the collected data to train and update the AI / ML model (S305).

[0121] As described above, in the present embodiment, in data collection for the AI / ML model for CSI prediction, terminal 200 transmits to the network additional information (e.g., parameters related to the CSI-RS measurement interval and CSI reporting interval) used when learning and updating the AI / ML model on the terminal 200 side, as control information related to the implementation-specific circumstances of the network or terminal 200 in CSI measurement (e.g., the relationship between transmit precoding and the CSI-RS measurement interval and CSI reporting interval).

[0122] This allows the network and terminal 200 to specify (or assume) the transmit precoding to be applied (or that the same transmit precoding will be applied) in the CSI measurement period and the CSI reporting period. Therefore, the assumptions regarding the transmit precoding can be made consistent (or matched) between the network and terminal 200, and the AI / ML model can be trained and updated on the terminal 200 side under specific assumptions regarding the transmit precoding or parameters related to the input and output of the AI / ML model.

[0123] Furthermore, according to the present embodiment, the network can perform an operation in which the same transmit precoding is maintained within the CSI-RS measurement interval and CSI reporting interval reported from terminal 200, while the transmit precoding is changed as needed within other CSI-RS measurement intervals and CSI reporting intervals, thereby improving operational flexibility compared to a case in which the same transmit precoding is always applied. Thus, for example, even when "timeRestrictionForChannelMeasurements" is set to "Configured," it becomes possible to perform CSI prediction while changing the transmit precoding applied to CSI-RS by the network.

[0124] Therefore, according to this embodiment, even when CSI prediction is effective, the efficiency of wireless communication can be improved by making it possible to change transmission precoding at any time on the network side.

[0125] Fifth Embodiment In this embodiment, it is assumed that data collection is performed on the network side (base station 100 side).

[0126] As described above, in addition to (or instead of) the standard specification settings, the settings of the receive filter (e.g., spatial receive filter) that terminal 200 applies to receiving CSI-RS may be settings specific to the implementation of terminal 200. For example, when data collection for an AI / ML model is performed on the network side and training of the AI / ML model is also performed on the network side, information that is dependent on the implementation of terminal 200, such as the receive filter settings, may be useful for training and managing the AI / ML model.

[0127] However, detailed information about the spatial receive filters on the terminal 200 side may be confidential information related to the implementation of the terminal 200, so it is debatable whether to provide such information from the terminal 200 to the network.

[0128] The receive filter of terminal 200 may include, for example, precoding in the digital domain, beamforming in the antenna / analog domain, or panel / antenna switching. Furthermore, if terminal 200 has multiple panels, the receive filter of terminal 200 may be configured with one Rx filter for each panel, or may be an overall Rx filter for the entire terminal including multiple panels. Antenna switching may also include cases where terminal 200 adjusts the number of antennas for reasons such as power saving, where a foldable terminal operates with different antennas in the closed and unfolded states, or where the terminal is connected to an external antenna such as a vehicle.

[0129] Here, compared to the case where terminal 200 provides at least specific information regarding the receive filter to the network, providing relative information regarding the receive filter setting (e.g., information regarding whether the receive filter is the same or different between CSI measurement occasions) may not pose a problem in terms of information disclosure.

[0130] Therefore, in this embodiment, relative information regarding receive filters between CSI measurement occasions is used as terminal-side auxiliary information or additional condition for data collection on the network side. For example, terminal 200 reports relative information regarding receive filters applied in multiple CSI measurement occasions (e.g., adjacent CSI measurement occasions) to the network.

[0131] For example, the relative information regarding the receive filter between CSI measurement occasions may be information regarding whether there is a change (e.g., whether the receive filter is the same or different) between measurement occasions (e.g., adjacent measurement occasions) of the CSI-RS or synchronization signal block (SSB).

[0132] Terminal 200 reports measured CSI (e.g., training data or ground-truth CSI) to a network (e.g., base station 100). Here, reporting of ground-truth CSI from terminal 200 may be performed for each CSI measurement sample or for each group including multiple samples. In sample-by-sample reporting, CSI measurements and CSI reports correspond one-to-one, and one CSI report includes ground-truth CSI generated by one CSI measurement. In group-by-group CSI reporting, one CSI report includes ground-truth CSI generated by multiple CSI measurements. In group-by-group CSI reporting, multiple CSI reference resources may be configured for one CSI report. For example, a CSI reference resource may be configured for each of multiple CSI measurements and ground-truth CSI generation corresponding to one CSI report.

[0133] Furthermore, terminal 200 reports relative information regarding the receive filter between CSI measurement occasions to the network as terminal-side auxiliary information or additional information.

[0134] FIG. 20 is a diagram illustrating an example of relative information regarding receive filters between CSI measurement occasions according to the present embodiment.

[0135] As shown in Fig. 20 , relative information about the receive filters (e.g., information about whether the receive filters between CSI measurement occasions are the same or different) may be reported from terminal 200 to the network along with a CSI report including ground-truth CSI generated by CSI measurement. For example, the relative information about the receive filters may be one-bit information (0 or 1) corresponding to each CSI measurement occasion (e.g., "0" if the receive filters are the same and "1" if the receive filters are different, or vice versa).

[0136] The relative information regarding the receive filters may be reported from terminal 200 via any uplink signal (e.g., RRC, MAC-CE, Uplink Control Information (UCI)). Furthermore, the timing at which the relative information regarding the receive filters is reported from terminal 200 may be the same as the timing of a CSI report including ground-truth CSI, may be during a data collection period, or may be after data collection is completed. Furthermore, as the relative information regarding the receive filters, information regarding whether the receive filters are the same or different between CSI measurement occasions may be reported together across multiple CSI measurement occasions.

[0137] As shown in Fig. 20 , the network can identify the status of the receive filter (e.g., the correspondence with the CSI measurement occasion) that is applied to the reception of CSI-RS at terminal 200 by notification of information related to the receive filter from terminal 200. In other words, the receive filter information reported from terminal 200 to the network is information related to the condition or status of the receive filter that is applied at terminal 200 at each CSI measurement occasion (e.g., the condition or status of the receive filter that is specific to the implementation of terminal 200).

[0138] By identifying the correspondence between the CSI measurement occasions and the receive filters of the terminal 200, the network can use the CSI reports based on the CSI-RS received at the terminal 200 using the same receive filters, for example as shown in FIG. 20 , as input data to the AI / ML model for outputting the predicted CSI.

[0139] [Example of Operation of Base Station 100 and Terminal 200] FIG. 21 is a flowchart showing an example of operation of base station 100 (referred to as base station / network) and terminal 200 according to this embodiment.

[0140] In FIG. 21, the base station / network transmits configuration related to CSI measurement and reporting to the terminal 200 (S401).

[0141] Terminal 200 measures CSI based on the configuration related to CSI measurement and reporting (S402). Terminal 200 transmits a CSI report to the base station / network based on the CSI measurement result (S403). When reporting CSI, terminal 200 reports information related to the CSI measurement time to the base station / network, as in the first embodiment.

[0142] Terminal 200 reports information about the receive filter applied to receive CSI-RS (for example, relative information between CSI measurement occasions) to the network (S404).

[0143] The base station / network collects data for an AI / ML model for outputting predicted CSI, for example, based on information on transmit precoding applied to CSI-RS transmission, information on the CSI measurement time reported from terminal 200, and information on the receive filter reported from terminal 200 (S405), and uses the collected data to train and update the AI / ML model (S406).The base station / network then transmits (or transfers or distributes) the AI / ML model or a dataset of the AI / ML model to terminal 200 (S407).

[0144] Thus, in the embodiment, in data collection for an AI / ML model for CSI prediction, terminal 200 transmits information related to the receive filter to the network as control information related to the implementation-specific situation of the base station / network or terminal 200 in CSI measurement (e.g., the relationship between the receive filter of terminal 200 and the CSI measurement occasion).

[0145] This allows the base station / network to identify the relationship (relative relationship) between the receive filter of terminal 200 when measuring CSI and the CSI measurement occasion. Thus, according to the present embodiment, the network side can perform learning and updating of the AI / ML model under specific assumptions regarding the receive filter of terminal 200 and parameters related to the input / output of the AI / ML model. For example, the specific assumption regarding the parameters related to the receive filter and the input / output of the AI / ML model may be an assumption that the receive filter applied to the input for calculating predicted CSI and the predicted CSI to be output are the same.

[0146] Furthermore, according to this embodiment, even if the terminal 200 does not disclose detailed implementation information regarding the receive filter, the assumptions regarding the receive filter of the terminal 200 can be made consistent (or matched) between the network and the terminal 200.

[0147] Therefore, according to the present embodiment, even when CSI prediction is enabled, the efficiency of wireless communication can be improved by making it possible to change the CSI-RS reception filter on terminal 200 side.

[0148] (Variation of Embodiment 5) The relative information regarding the receive filters between CSI measurement occasions is not limited to the information regarding whether the receive filters are the same or different between the CSI measurement occasions described above, and may be, for example, the receive filter change timing or the receive filter change timing pattern, similar to <Option 2> and <Option 3> in Embodiment 3.

[0149] For example, the information regarding the timing of changing the receive filter may be information indicating a frame number, a slot number, or a symbol number, or may be information indicating a timestamp (for example, YY-MM-DD HH:MM:SS).

[0150] Furthermore, the information regarding the timing of changing the receive filter may be, for example, the number of a CSI measurement occasion relative to a certain reference time. For example, the reference time may be defined in advance or may be set periodically. For example, the beginning of a frame may be defined in advance as the reference time, or a specific frame position, slot position, or symbol position may be set periodically. Furthermore, the reference time may be the time of CSI reporting. The number of a CSI measurement occasion relative to the reference time may be information indicating the number of the CSI measurement occasion relative to (before or after) the reference time.

[0151] Furthermore, the network may identify the CSI measurement opportunity immediately before (or immediately after, a certain time before, or a certain time after) when information regarding the timing of changing the receive filter (notification from terminal 200) is reported as the timing of changing the receive filter in terminal 200.

[0152] Furthermore, when the receive filter is changed, terminal 200 may report a notification regarding the timing of the receive filter change at the same timing as the CSI report of ground-truth CSI, and when the receive filter is not changed, terminal 200 may not need to report information regarding the timing of the receive filter change.

[0153] Furthermore, for example, the information regarding the receive filter change timing pattern may be information regarding the number of CSI measurement occasions for which the same receive filter is applied. Furthermore, as the information regarding the receive filter change timing pattern, information regarding a plurality of change timing patterns may be collectively reported from terminal 200, or a periodic receive filter change timing pattern may be reported using information regarding one receive filter change timing pattern.

[0154] Sixth Embodiment In this embodiment, it is assumed that data collection is performed on the network side (base station 100 side).

[0155] When reciprocity between downlink and uplink is established, as in Time Division Duplex (TDD), a sounding reference signal (e.g., a Sounding Reference Signal (SRS)) can be used to acquire downlink CSI in the network, as shown in Fig. 22. In this case, it may be unnecessary to provide CSI-RS-based CSI feedback.

[0156] In addition to (or instead of) a standard specification setting, the setting of a transmit filter (e.g., transmit precoding or beamforming) that terminal 200 applies to transmitting an SRS may be a setting specific to the implementation of terminal 200. For example, when data collection for an AI / ML model is performed on the network side and training of the AI / ML model is performed on the network side, information that is dependent on the implementation of terminal 200, such as the setting of a transmit filter, may be useful for training and management of the AI / ML model.

[0157] However, detailed information about the spatial transmit filters on the terminal 200 side may be confidential information related to the implementation of the terminal 200, so it is debatable whether to provide such information from the terminal 200 to the network.

[0158] The transmission filter of the terminal 200 may include, for example, precoding in the digital domain, beamforming in the antenna / analog domain, or panel / antenna switching.

[0159] Here, compared to providing specific information about at least the transmission filter from terminal 200 to the network, providing relative information about the transmission filter setting (e.g., information about whether the transmission filter is the same or different between SRS transmission opportunities) may not pose a problem from the perspective of information disclosure.

[0160] Therefore, in this embodiment, relative information regarding transmit filters between SRS transmission opportunities is used as terminal-side auxiliary information or additional condition for network-side data collection. For example, terminal 200 reports relative information regarding transmit filters applied in multiple SRS measurement occasions between multiple SRS transmission opportunities (e.g., adjacent SRS transmission opportunities) to the network.

[0161] For example, relative information regarding transmit filters between SRS transmission opportunities may be information regarding whether there is a change (eg, whether the transmit filters are the same or different) between SRS transmission opportunities (eg, adjacent transmission opportunities).

[0162] The network notifies terminal 200 of SRS configuration, such as an SRS period or SRS resources, and configures SRS transmission for terminal 200. Terminal 200 transmits SRS at the configured SRS transmission opportunities and transmission resources. Terminal 200 also reports relative information regarding transmission filters between SRS transmission opportunities to the network as terminal-side auxiliary information or additional information.

[0163] FIG. 23 is a diagram showing an example of relative information regarding transmission filters between SRS transmission opportunities in this embodiment.

[0164] 23, terminal 200 reports relative information about the transmit filters (e.g., information about whether the transmit filters are the same or different between SRS transmission opportunities) to the network. For example, the relative information about the transmit filters may be 1-bit information (0 or 1) corresponding to each SRS transmission opportunity (e.g., "0" if the transmit filters are the same, and "1" if they are different, or vice versa).

[0165] The relative information regarding the transmit filter may be reported from terminal 200 via any uplink signal (e.g., RRC, MAC-CE, UCI). Furthermore, the timing at which the relative information regarding the transmit filter is reported from terminal 200 may be during a data collection period or after data collection is completed. Furthermore, as the relative information regarding the transmit filter, information regarding whether the transmit filters are the same or different between multiple SRS transmission opportunities may be reported together.

[0166] 23 , by notification of information related to the transmission filter from terminal 200, the network can identify the status of the transmission filter (e.g., the correspondence with the SRS transmission opportunity) that is applied to the transmission of SRS by terminal 200. In other words, the information related to the transmission filter reported from terminal 200 to the network is information related to the conditions or status of the transmission filter that is applied by terminal 200 at each SRS transmission opportunity (e.g., the conditions or status of the transmission filter that is specific to the implementation of terminal 200).

[0167] By identifying the correspondence between SRS transmission opportunities and the transmit filters of terminal 200, the network can use measurements based on SRS transmitted using the same transmit filters in terminal 200 as input data to the AI / ML model to output predicted CSI, for example, as shown in Figure 23.

[0168] [Example of Operation of Base Station 100 and Terminal 200] FIG. 24 is a flowchart showing an example of operation of base station 100 (referred to as base station / network) and terminal 200 according to this embodiment.

[0169] In FIG. 24, the base station / network transmits settings related to SRS transmission to the terminal 200 (S501).

[0170] The terminal 200 transmits the SRS based on the settings related to the SRS transmission (S502), and the base station / network measures the SRS (S503).

[0171] Terminal 200 reports information about the transmission filter applied to the SRS transmission of terminal 200 (for example, relative information between SRS transmission opportunities) to the network (S504).

[0172] The base station / network collects data for an AI / ML model for outputting predicted CSI, for example, based on the SRS measurement results and relative information about the transmit filter reported from the terminal 200 (S505), and uses the collected data to train and update the AI / ML model (S506).The base station / network then transmits (or transfers or distributes) the AI / ML model or a data set of the AI / ML model to the terminal 200 (S507).

[0173] Thus, in the embodiment, in data collection for an AI / ML model for CSI prediction, terminal 200 transmits information regarding the transmit filter to the network as control information regarding the implementation-specific circumstances of the base station / network or terminal 200 in CSI measurement (e.g., the relationship between the transmit filter of terminal 200 and SRS transmission opportunities).

[0174] This allows the base station / network to identify the relationship (relative relationship) between the transmit filter of terminal 200 and the SRS transmission opportunity when measuring CSI. Therefore, the network side can perform learning and updating of the AI / ML model under specific assumptions regarding the parameters related to the transmit filter of terminal 200 and the input / output of the AI / ML model. For example, the specific assumption regarding the parameters related to the transmit filter and the input / output of the AI / ML model may be an assumption that the transmit filter applied to the input for calculating predicted CSI and the output predicted CSI is the same.

[0175] Furthermore, according to this embodiment, even if terminal 200 does not disclose detailed implementation information about the transmission filter, assumptions about the transmission filter of terminal 200 can be made consistent (matched) between the network and terminal 200.

[0176] Therefore, according to the present embodiment, even when CSI prediction is enabled, the efficiency of wireless communication can be improved by making it possible to change the CSI-RS reception filter on terminal 200 side.

[0177] (Variant of embodiment 6) The relative information regarding the transmission filter between SRS transmission opportunities is not limited to information regarding whether the transmission filters are the same or different between the SRS transmission opportunities described above, and may be, for example, the timing of changing the transmission filter or the timing pattern of changing the transmission filter, similar to <Option 2> and <Option 3> in embodiment 3.

[0178] For example, the information regarding the timing of changing the transmit filter may be information indicating a frame number, a slot number, or a symbol number, or may be information indicating a timestamp (for example, YY-MM-DD HH:MM:SS).

[0179] Furthermore, the information regarding the timing of changing the transmission filter may be, for example, the number of an SRS transmission opportunity relative to a certain reference time. For example, the reference time may be defined in advance or may be set periodically. For example, the beginning of a frame may be defined in advance as the reference time, or a specific frame position, slot position, or symbol position may be set periodically. Furthermore, the reference time may be the time at which information regarding the timing of changing the transmission filter is reported. The number of the SRS transmission opportunity relative to the reference time may be information indicating the number of the SRS transmission opportunity relative to (before or after) the reference time.

[0180] The network may also identify the SRS transmission opportunity immediately before (or immediately after, a certain time before, or a certain time after) when a notification regarding the timing to change the transmission filter is reported as the timing to change the transmission filter in terminal 200.

[0181] Furthermore, the terminal 200 may report a notification regarding the timing of changing the transmission filter when the transmission filter is changed, and may not report a notification regarding the timing of changing the transmission filter when the transmission filter is not changed.

[0182] [Configuration of Base Station] Fig. 25 is a block diagram showing an example configuration of base station 100. In Fig. 25, base station 100 has a control unit 101, a signal generation unit 102, a transmission unit 103, a reception unit 104, an extraction unit 105, a demodulation unit 106, and a decoding unit 107.

[0183] At least one of the control unit 101, the signal generation unit 102, the extraction unit 105, the demodulation unit 106, and the decoding unit 107 shown in Fig. 25 may be included in the control unit shown in Fig. 7. Also, at least one of the transmission unit 103 and the reception unit 104 shown in Fig. 25 may be included in the communication unit shown in Fig. 7.

[0184] Control unit 101 determines, for example, control information related to CSI measurement and reporting by terminal 200 or control information related to SRS transmission, and outputs the determined control information to signal generation unit 102. The control information may include, for example, a reference signal configuration for CSI measurement such as CSI-RS, a CSI report configuration for terminal 200 to report CSI, an SRS configuration such as an SRS periodicity and SRS resources, and information related to notification or reporting of information (additional information or auxiliary information) for matching (or for achieving a common understanding between the network and terminal 200) assumptions related to transmit precoding or transmit / receive filters during CSI measurement.

[0185] Furthermore, the control unit 101 may output, for example, CSI measurement data (e.g., measurement values ​​based on a CSI report or an SRS) or auxiliary information input from the decoding unit 107 to a function for processing AI / ML (e.g., a data collection function or an AI / ML model learning function). Note that the function for processing AI / ML may be included in the base station 100 or may be included in a node different from the base station 100.

[0186] Furthermore, the control unit 101 determines, for example, information for the terminal 200 to receive a downlink signal, and outputs the determined information to the signal generation unit 102. The information for the terminal 200 to receive a downlink signal may include, for example, information on resource allocation of a downlink data channel (e.g., PDSCH: Physical Downlink Shared Channel) or a downlink control channel (e.g., PDCCH: Physical Downlink Control Channel), and information on a coding and modulation scheme (e.g., MCS: Modulation and Coding Scheme).

[0187] Furthermore, the control unit 101 determines information for the terminal 200 to transmit an uplink signal, for example, and outputs the determined information to the signal generation unit 102, the extraction unit 105, the demodulation unit 106, and the decoding unit 107. The information for the terminal 200 to transmit an uplink signal may include, for example, information on resource allocation of an uplink data channel (e.g., a Physical Uplink Shared Channel (PUSCH)) or an uplink control channel (e.g., a Physical Uplink Control Channel (PUCCH)), and information on a coding / modulation scheme (e.g., MCS). Furthermore, the information for transmitting an uplink signal may include, for example, information on a CSI report or an auxiliary information report.

[0188] The signal generation unit 102 generates a data signal or a control signal bit sequence using, for example, information input from the control unit 101, and applies encoding as necessary. The signal generation unit 102 also modulates the encoded bit sequence to generate a modulated signal (for example, a symbol sequence), and maps the modulated signal to the radio resource specified by the control unit 101. The signal generation unit 102 outputs the mapped signal to the transmission unit 103.

[0189] The transmitting unit 103 performs, for example, OFDM or other transmission waveform generation processing on the signal input from the signal generating unit 102. Furthermore, in the case of OFDM transmission using a cyclic prefix (CP), for example, the transmitting unit 103 performs an inverse fast Fourier transform (IFFT) processing on the signal and adds a CP to the signal after the IFFT. Furthermore, the transmitting unit 103 performs, for example, RF processing such as D / A conversion or up-conversion on the signal and transmits the radio signal to the terminal 200 via an antenna.

[0190] The receiving unit 104 performs RF processing such as downconvert or A / D conversion on an uplink signal received from the terminal 200 via an antenna. In addition, in the case of OFDM transmission, the receiving unit 104 performs Fast Fourier Transform (FFT) processing on the received signal, and outputs the resulting frequency domain signal to the extracting unit 105.

[0191] The extraction unit 105 extracts, for example, based on information input from the control unit 101, a radio resource portion from which an uplink signal (for example, a PUSCH or a PUCCH) is transmitted, from the received signal input from the receiving unit 104, and outputs the extracted radio resource portion to the demodulation unit 106.

[0192] The demodulation unit 106 demodulates the uplink signal (for example, PUSCH or PUCCH) input from the extraction unit 105, for example, based on information input from the control unit 101. The demodulation unit 106 outputs the demodulation result to the decoding unit 107, for example.

[0193] The decoding unit 107 performs error correction decoding on the uplink signal (for example, PUSCH or PUCCH) based on, for example, the information input from the control unit 101 and the demodulation result input from the demodulation unit 106, and obtains a decoded received bit sequence. For example, if the decoded received bit sequence includes a CSI report or an auxiliary information report from the terminal 200, the decoding unit 107 outputs the information to the control unit 101.

[0194] [Terminal Configuration] Fig. 26 is a block diagram showing an example configuration of a terminal 200 according to an embodiment of the present disclosure. For example, in Fig. 26, the terminal 200 includes a receiving unit 201, an extracting unit 202, a demodulating unit 203, a decoding unit 204, a control unit 205, a signal generating unit 206, and a transmitting unit 207.

[0195] At least one of the extraction unit 202, demodulation unit 203, decoding unit 204, control unit 205, and signal generation unit 206 shown in Fig. 26 may be included in the control unit shown in Fig. 8. Also, at least one of the reception unit 201 and transmission unit 207 shown in Fig. 26 may be included in the communication unit shown in Fig. 8.

[0196] The receiving unit 201 receives, for example, a downlink signal (e.g., a downlink data signal or a downlink control signal) from the base station 100 via an antenna, and performs RF processing such as downconvert or A / D conversion on the radio received signal to obtain a received signal (baseband signal). Furthermore, when receiving an OFDM signal, the receiving unit 201 performs FFT processing on the received signal to convert it into the frequency domain. The receiving unit 201 outputs the received signal to the extracting unit 202.

[0197] Extraction section 202 extracts a radio resource portion that may include a downlink control signal from the received signal input from receiving section 201, based on, for example, information about the radio resource of the downlink control signal input from control section 205, and outputs the extracted radio resource portion to demodulation section 203. Furthermore, extraction section 202 extracts a radio resource portion that includes a downlink data signal, based on information about the radio resource of the data signal input from control section 205, and outputs the extracted radio resource portion to demodulation section 203. Furthermore, extraction section 202 extracts, for example, a radio resource portion that includes a CSI-RS, and outputs the extracted radio resource portion to control section 205.

[0198] The demodulation unit 203 demodulates the signal (for example, PDCCH or PDSCH) input from the extraction unit 202 based on information input from the control unit 205 , for example, and outputs the demodulation result to the decoding unit 204 .

[0199] The decoding unit 204 performs error correction decoding of the PDCCH or PDSCH using, for example, information input from the control unit 205 and the demodulation result input from the demodulation unit 203, and obtains, for example, a control signal or a downlink data signal. The decoding unit 204 outputs the control signal to the control unit 205.

[0200] The control unit 205 identifies information related to downlink transmission based on, for example, information obtained from the control signal input from the decoding unit 204, and outputs the information to the extraction unit 202, the demodulation unit 203, and the decoding unit 204. The control unit 205 also identifies information related to uplink transmission based on, for example, information obtained from the control signal input from the decoding unit 204, and outputs the information to the signal generation unit 206. The control unit 205 also generates information related to CSI reporting using the CSI measurement results based on the CSI-RS input from the extraction unit 202 using the method described above, and outputs the information to the signal generation unit 206. The control unit 205 also generates information related to SRS transmission or auxiliary information reporting, and outputs the information to the signal generation unit 206.

[0201] Furthermore, the control unit 205 may output the CSI measurement results and auxiliary information from the network (e.g., base station 100) to a function for processing AI / ML (e.g., a data collection function and an AI / ML model learning function). Note that the function for processing AI / ML may be included in the terminal 200 or may be included in an external device (e.g., a server) connected to the terminal 200.

[0202] The signal generation unit 206 generates an uplink data signal, an uplink control signal, or an SRS based on the CSI report, information related to SRS transmission or auxiliary information report, or information related to uplink transmission input from the control unit 205, encodes and modulates the bit string of the generated signal, and maps it to radio resources. The signal generation unit 206 outputs the uplink signal onto which the signal is mapped to, for example, the transmission unit 207. Note that coding and modulation do not need to be applied to the SRS.

[0203] The transmitter 207 generates a transmission signal waveform, such as OFDM, for the signal input from the signal generator 206. Furthermore, in the case of OFDM transmission or DFT-s-OFDM transmission using a CP, for example, the transmitter 207 performs IFFT processing on the signal and adds a CP to the signal after IFFT. Alternatively, when the transmitter 207 generates a single-carrier waveform such as a DFT-s-OFDM waveform, a DFT unit (not shown) may be added before the signal generator 206. Furthermore, the transmitter 207 performs RF processing, such as D / A conversion and up-conversion, on the transmission signal, and transmits the radio signal to the base station 100 via an antenna.

[0204] The above describes the embodiments according to non-limiting examples of the present disclosure.

[0205] Note that the fact that the terminal 200 cannot know the implementation-specific transmission precoding on the network side is not limited to use cases of CSI feedback, but is common to use cases in which an AI / ML model is applied to a radio interface. The CSI prediction described in one embodiment of the present disclosure is an example of a use case in which AI / ML is applied, and use cases in which an AI / ML model is applied are not limited to CSI prediction. For example, other use cases in which an AI / ML model is applied include CSI compression, a combination of CSI compression and prediction, beam prediction in the spatial or time domain, and positioning.

[0206] Furthermore, the fact that the network cannot know the implementation-specific transmit / receive filters on the terminal 200 side is not limited to use cases of CSI feedback, but is common to use cases in which an AI / ML model is applied to a radio interface. The CSI prediction described in one embodiment of the present disclosure is an example of a use case in which AI / ML is applied, and use cases in which an AI / ML model is applied are not limited to CSI prediction. For example, other use cases in which an AI / ML model is applied include CSI compression, a combination of CSI compression and prediction, beam prediction in the spatial or temporal domain, and positioning.

[0207] Furthermore, an embodiment of the present disclosure is not limited to the case where "timeRestrictionForChannelMeasurements" is "Configured" and may be applied to other settings. For example, an embodiment of the present disclosure may be applied to the case where "timeRestrictionForChannelMeasurements" is "notConfigured."

[0208] (Supplementary Note) Information indicating whether the terminal 200 supports the functions, operations, or processes described in each of the above-described embodiments and each supplementary note may be transmitted (or notified) from the terminal 200 to the base station 100, for example, as capability information or capability parameters of the terminal 200.

[0209] The capability information may include an information element (IE) that individually indicates whether or not the terminal 200 supports at least one of the functions, operations, or processes described in the above-described embodiments, modifications, and supplements. Alternatively, the capability information may include an information element that indicates whether or not the terminal 200 supports a combination of any two or more of the functions, operations, or processes described in the above-described embodiments, modifications, and supplements.

[0210] For example, the base station 100 may determine (or decide or assume) the functions, operations, or processes that the terminal 200 that transmitted the capability information supports (or does not support) based on the capability information received from the terminal 200. The base station 100 may perform operations, processes, or control according to the determination result based on the capability information. For example, the base station 100 may control processing related to an AI / ML model based on the capability information received from the terminal 200.

[0211] Note that the fact that terminal 200 does not support some of the functions, operations, or processes described in the above-described embodiments, modifications, and supplementary notes may be interpreted as meaning that such some of the functions, operations, or processes are restricted in terminal 200. For example, information or a request regarding such restrictions may be notified to base station 100.

[0212] Information regarding the capabilities or limitations of terminal 200 may, for example, be defined in a standard, or may be implicitly notified to base station 100 in association with information known at base station 100 or information transmitted to base station 100.

[0213] The above has described the embodiments, modifications, and supplementary notes according to a non-limiting example of the present disclosure.

[0214] (Control Signal) In the present disclosure, a downlink control signal (or downlink control information) related to an embodiment of the present disclosure may be, for example, a signal (or information) transmitted in a Physical Downlink Control Channel (PDCCH) of a physical layer, or a signal (or information) transmitted in a Medium Access Control Control Element (MAC CE) or Radio Resource Control (RRC) of a higher layer. Furthermore, the signal (or information) is not limited to being notified by a downlink control signal, but may be predefined in a specification (or standard) or preconfigured in a base station and a terminal.

[0215] In the present disclosure, an uplink control signal (or uplink control information) related to an embodiment of the present disclosure may be, for example, a signal (or information) transmitted in a PUCCH of a physical layer, or a signal (or information) transmitted in a MAC CE or RRC of a higher layer. Furthermore, the signal (or information) is not limited to being notified by an uplink control signal, but may be predefined in a specification (or standard) or preconfigured in a base station and a terminal. Furthermore, the uplink control signal may be replaced with, for example, uplink control information (UCI), 1st stage sidelink control information (SCI), or 2nd stage SCI.

[0216] (Base Station) In an embodiment of the present disclosure, the base station may be a Transmission Reception Point (TRP), a cluster head, an access point, a Remote Radio Head (RRH), an eNodeB (eNB), a gNodeB (gNB), a Base Station (BS), a Base Transceiver Station (BTS), a parent device, a gateway, or the like. In sidelink communication, a terminal may play the role of a base station. Instead of a base station, a relay device that relays communication between an upper node and a terminal may be used. Alternatively, a roadside unit may be used.

[0217] (Uplink / Downlink / Sidelink) An embodiment of the present disclosure may be applied to, for example, any of the uplink, downlink, and sidelink. For example, an embodiment of the present disclosure may be applied to a Physical Uplink Shared Channel (PUSCH), a Physical Uplink Control Channel (PUCCH), or a Physical Random Access Channel (PRACH) in the uplink, a Physical Downlink Shared Channel (PDSCH), a PDCCH, or a Physical Broadcast Channel (PBCH) in the downlink, or a Physical Sidelink Shared Channel (PSSCH), a Physical Sidelink Control Channel (PSCCH), or a Physical Sidelink Broadcast Channel (PSBCH) in the sidelink.

[0218] The PDCCH, PDSCH, PUSCH, and PUCCH are examples of a downlink control channel, a downlink data channel, an uplink data channel, and an uplink control channel, respectively. The PSCCH and PSSCH are examples of a sidelink control channel and a sidelink data channel. The PBCH and PSBCH are examples of a broadcast channel, and the PRACH is an example of a random access channel.

[0219] (Data Channel / Control Channel) An embodiment of the present disclosure may be applied to, for example, either a data channel or a control channel. For example, the channel in an embodiment of the present disclosure may be replaced with any of the data channels PDSCH, PUSCH, and PSSCH, or the control channels PDCCH, PUCCH, PBCH, PSCCH, and PSBCH.

[0220] (Reference Signal) In one embodiment of the present disclosure, a reference signal is, for example, a signal known by both a base station and a mobile station, and may also be called a Reference Signal (RS) or a pilot signal. The reference signal may be any of a Demodulation Reference Signal (DMRS), a Channel State Information - Reference Signal (CSI-RS), a Tracking Reference Signal (TRS), a Phase Tracking Reference Signal (PTRS), a Cell-specific Reference Signal (CRS), or a Sounding Reference Signal (SRS).

[0221] (Time Interval) In one embodiment of the present disclosure, the unit of time resource is not limited to one or a combination of slots and symbols, but may be, for example, a time resource unit such as a frame, a superframe, a subframe, a slot, a time slot, a subslot, a minislot, a symbol, an Orthogonal Frequency Division Multiplexing (OFDM) symbol, a Single Carrier-Frequency Division Multiplexing Access (SC-FDMA) symbol, or another time resource unit. Furthermore, the number of symbols included in one slot is not limited to the number of symbols exemplified in the above-mentioned embodiment, and may be another number of symbols.

[0222] (Frequency Band) An embodiment of the present disclosure may be applied to either a licensed band or an unlicensed band.

[0223] (Communication) An embodiment of the present disclosure may be applied to communication between a base station and a terminal (Uu link communication), communication between terminals (Sidelink communication), or Vehicle to Everything (V2X) communication. For example, the channel in an embodiment of the present disclosure may be replaced with any of PSCCH, PSSCH, Physical Sidelink Feedback Channel (PSFCH), PSBCH, PDCCH, PUCCH, PDSCH, PUSCH, or PBCH.

[0224] An embodiment of the present disclosure may be applied to a terrestrial network, a non-terrestrial network (NTN) using a satellite or a high altitude pseudo satellite (HAPS), or a terrestrial network in which transmission delay is large compared to the symbol length or slot length, such as a network with a large cell size or an ultra-wideband transmission network.

[0225] (SBFD) In ​​one embodiment of the present disclosure, operations on uplink, downlink, and sidelink symbols may be applied to symbols (e.g., SBFD symbols) on which SBFD (Subband Non-Overlapping Full Duplex, Subband Full Duplex) operations or controls are performed. In SBFD symbols, a frequency domain (or frequency resource, frequency band) is divided into multiple frequency domains (e.g., subbands, RB sets, subbands, or sub-BWPs (Bandwidth Parts)). A terminal transmits and receives in different directions (e.g., downlink or uplink) in units of subbands, which are the divided domains. In SBFD symbols, a terminal may transmit and receive in one direction, either uplink or downlink, but not in the other direction. On the other hand, a base station may be capable of transmitting and receiving on both the uplink and downlink simultaneously. SBFD symbols may have a smaller frequency domain available for downlink use than symbols that transmit and receive only downlink use. Also, SBFD symbols may have a smaller frequency domain available for uplink use than symbols that transmit and receive only uplink use.

[0226] In addition, in the SBFD symbol, a terminal may transmit and receive uplink and downlink simultaneously. In this case, the frequency domain in which the terminal transmits and the frequency domain in which the terminal receives may not be adjacent, but may be separated by a frequency interval (also called a frequency gap).

[0227] In addition, different transmission and reception directions in subband units, which are divided areas, may include transmission and reception of side links.

[0228] (XDD: Cross Division Duplex) In one embodiment of the present disclosure, the operation for uplink, downlink, and sidelink symbols may be applied to symbols (e.g., full duplex symbols) where full duplex operation or control is performed. In a full duplex symbol, both the terminal and the base station can simultaneously transmit and receive on the uplink and downlink. In a full duplex symbol, the terminal and the base station may simultaneously transmit and receive in an available frequency region (or frequency resource, frequency band), or may simultaneously transmit and receive in a partial frequency region (i.e., transmission or reception may be performed in other frequency regions). In this case, the frequency region in which the base station or terminal transmits and receives may not be adjacent, but may have a frequency interval (also called a frequency gap). Furthermore, for the purpose of, for example, reducing interference, either the terminal or the base station may simultaneously transmit and receive (i.e., the other may transmit or receive).

[0229] In addition, full duplex operation may be applied to an operation in which a terminal can simultaneously transmit and receive sidelinks, or to an operation in which a terminal can simultaneously transmit and receive sidelinks and uplinks or downlinks.

[0230] (Antenna Port) In one embodiment of the present disclosure, an antenna port refers to a logical antenna (antenna group) consisting of one or more physical antennas. For example, an antenna port does not necessarily refer to a single physical antenna, but may refer to an array antenna consisting of multiple antennas. For example, the number of physical antennas that an antenna port is composed of is not specified, and the antenna port may be specified as the smallest unit by which a terminal station can transmit a reference signal. Furthermore, an antenna port may also be specified as the smallest unit by which a weighting of a precoding vector is multiplied.

[0231] <5G NR System Architecture and Protocol Stack> The 5G NR system architecture generally assumes an NG-RAN (Next Generation - Radio Access Network) equipped with gNBs. The gNBs provide UE-side termination of the NG radio access user plane (SDAP / PDCP / RLC / MAC / PHY) and control plane (RRC) protocols. The gNBs are connected to each other via an Xn interface. The gNBs are also connected to a Next Generation Core (NGC) via a Next Generation (NG) interface, more specifically to an Access and Mobility Management Function (AMF) (e.g., a specific core entity that performs AMF) via an NG-C interface, and to a User Plane Function (UPF) (e.g., a specific core entity that performs UPF) via an NG-U interface. The NG-RAN architecture is shown in Figure 27 (see, for example, 3GPP TS 38.300 v15.6.0, section 4).

[0232] <RRC connection setup and reconfiguration procedure> This shows the NAS part of the interaction between the UE, gNB, and AMF (5GC entity) when the UE transitions from RRC_IDLE to RRC_CONNECTED (see TS 38.300 v15.6.0).

[0233] RRC is a higher layer signaling protocol used to configure the UE and gNB. The AMF prepares UE context data (including, for example, PDU session context, security keys, UE radio capabilities, UE security capabilities, etc.) and sends it to the gNB along with an INITIAL CONTEXT SETUP REQUEST. The gNB then activates AS security together with the UE. This is done by the gNB sending a SecurityModeCommand message to the UE, and the UE responding with a SecurityModeComplete message to the gNB. The gNB then sends an RRCReconfiguration message to the UE, and upon receiving an RRCReconfigurationComplete from the UE, the gNB performs reconfiguration to set up Signaling Radio Bearer 2 (SRB2) and Data Radio Bearer (DRB). For signaling-only connections, the steps related to RRCReconfiguration are omitted because SRB2 and DRB are not set up. Finally, the gNB notifies the AMF that the setup procedure is complete with an INITIAL CONTEXT SETUP RESPONSE.

[0234] Therefore, the present disclosure provides a 5th Generation Core (5GC) entity (e.g., AMF, SMF, etc.) that includes: a control circuit that, upon operation, establishes a Next Generation (NG) connection with a gNodeB; and a transmitter that, upon operation, transmits an initial context setup message to the gNodeB via the NG connection so that a signaling radio bearer between the gNodeB and a user equipment (UE) is set up. Specifically, the gNodeB transmits Radio Resource Control (RRC) signaling, including a resource allocation configuration information element (IE), to the UE via the signaling radio bearer. The UE then transmits in uplink or receives in downlink based on the resource allocation configuration.

[0235] <QoS Control> The 5G Quality of Service (QoS) model is based on QoS flows and supports both QoS flows that require a guaranteed flow bit rate (Guaranteed Bit Rate QoS flows (GBR)) and QoS flows that do not require a guaranteed flow bit rate (non-GBR QoS flows). Thus, at the NAS level, a QoS flow is the finest granularity of QoS classification in a PDU session. A QoS flow is identified within a PDU session by a QoS Flow ID (QFI) carried in an encapsulation header over the NG-U interface.

[0236] For each UE, 5GC establishes one or more PDU sessions. For each UE, the NG-RAN establishes, for example, at least one Data Radio Bearer (DRB) for each PDU session. Additional DRBs for the QoS flows of that PDU session can be configured later (when this is up to the NG-RAN). The NG-RAN maps packets belonging to different PDU sessions to different DRBs. NAS-level packet filters in the UE and 5GC associate UL and DL packets with QoS flows, while AS-level mapping rules in the UE and NG-RAN associate UL and DL QoS flows with DRBs.

[0237] (Open-RAN) The base station described in each embodiment (for example, a 5G NR base station called a gNB) may be configured with three functional modules: a Centralized Unit (CU), a Distributed Unit (DU), and a Radio Unit (RU).

[0238] A CU may be referred to as a centralized node, aggregation node, central station, aggregation station, or centralized unit. A DU may be referred to as an O-RAN Distributed Unit (O-DU), distributed node, distributed station, or distributed unit. An RU may be referred to as an O-RAN Radio Unit (O-RU), radio equipment, radio node, radio station, antenna unit, or radio unit.

[0239] There are several split options for the functional split configuration (or functional split point) between CU, DU, and RU. The term "functional split point" is sometimes referred to as "split," "option," or "split option."

[0240] Examples of "division options" include the following division options 1 to 8. The functions of the base station described in each embodiment may be divided into a CU, a DU, and an RU by any of the following division options 1 to 8. For example, the CU, DU, and RU may be functionally divided, or the functions may be divided only between the CU and DU or only between the DU and RU. (1) Segmentation option 1: Between RRC (radio resource control) and PDCP (2) Segmentation option 2: Between PDCP and RLC (High-RLC) (3) Segmentation option 3: Between High-RLC and Low-RLC (4) Segmentation option 4: Between RLC (Low-RLC) and MAC (High-MAC) (5) Segmentation option 5: Between High-MAC and Low-MAC (6) Segmentation option 6: Between MAC (Low-MAC) and PHY (High-PHY) (7) Segmentation option 7: Between High-PHY and Low-PHY (8) Segmentation option 8: Between PHY (Low-PHY) and RF

[0241] The functional split point between the CU and O-DU may be split option 2. The section between the CU and O-DU is called midhaul, and the F1 interface is specified by 3GPP. The section between the O-DU and O-RU is called fronthaul, and the functional split point may be split option 7-2x, which is adopted as the O-RAN fronthaul specification.

[0242] Figure 28 shows an example of functionally dividing the gNB base station functions into CU, O-DU, and O-RU using Split Option 2 and Split Option 7-2x.

[0243] The CU may have, for example, a radio resource control (RRC) function, a service data adaptation protocol (SDAP) function, and a packet data convergence protocol (PDCP) function.

[0244] The O-DU may include, for example, a radio link control (RLC) function, a MAC function, and a higher physical layer (HIGH-PHY) function. The HIGH-PHY function may include an encoding function, a scrambling function, a modulation function, a layer mapping function, a precoding function, and a resource element (RE) mapping function for downlink (DL) transmission. The HIGH-PHY function may also include a decoding function, a descrambling function, a demodulation function, a layer demapping function, and a resource element (RE) demapping function for uplink (UL) reception.

[0245] The O-RU may have, for example, a LOW-PHY function and an RF function. The LOW-PHY function may also have, for downlink transmission, a beamforming function, an IFFT (Inverse First Fourier Transform) + CP (Cyclic Prefix) assignment function, and a D / A (Digital to Analog) conversion function. The LOW-PHY function may also have, for uplink reception, an A / D (Analog to Digital) conversion function, a CP removal + FFT (First Fourier Transform) function, and a beamforming function.

[0246] In addition, if the O-DU does not have a precoding function, the O-RU may have a precoding function.

[0247] The O-RU may have functionality related to LBT (listen before talk).

[0248] The evolving Common Public Radio Interface (eCPRI) is specified as the communication method between the O-DU and O-RU in Split Option 7-2x. In Split Option 7-2x, eCPRI transmits and receives sampling sequences of the in-phase (I) and quadrature (Q) components of OFDM signals in the frequency domain, as well as information used for beamforming in antennas and time synchronization signals.

[0249] Information transmitted by the signals described in each embodiment (PDCCH, PUCCH, PDSCH, PUSCH, MAC CE, RRC, etc.) may be transmitted between the O-DU and the O-RU via the eCPRI User Plane (U-Plane) or Control Plane (C-Plane).

[0250] When the functions described in each embodiment are performed in the O-RU by functional division, the O-DU may control the O-RU by transmitting information for controlling the functions via a control signal (e.g., eCPRI) between the O-DU and the O-RU.

[0251] When the functions described in each embodiment are performed in the O-DU by functional division, the O-RU may receive the results of the functions performed in the O-DU via a control signal (e.g., eCPRI) and control the O-RU based on the received results.

[0252] The CU, O-DU, and O-RU may be deployed in physically different devices with their respective functions connected by optical fiber or the like, or some or all of their functions may be deployed in the same physical device.

[0253] The CU and O-DU may be logical entities implemented as software running on a server in the cloud or the like as a virtualized RAN (virtual Radio Access Network: vRAN). Also, some or all of the functions of the CU and O-DU may be provided as a virtualized network function (Network Functions Virtualization: NFV) service.

[0254] The transceiver does not have to be a radio transceiver, but may be, for example, a network transceiver, an optical transceiver, etc. The radio resources allocated by the O-DU may be resources for wireless communication between the O-RU and the UE.

[0255] The present disclosure can be realized in software, hardware, or software in conjunction with hardware.

[0256] Each functional block used in the description of the above embodiments may be partially or entirely realized as an LSI, which is an integrated circuit, and each process described in the above embodiments may be partially or entirely controlled by a single LSI or a combination of LSIs. The LSI may be composed of individual chips, or may be composed of a single chip that includes some or all of the functional blocks. The LSI may have data input and output. Depending on the degree of integration, the LSI may also be called an IC, system LSI, super LSI, or ultra LSI.

[0257] The integrated circuit method is not limited to LSI, and may be realized by a dedicated circuit, a general-purpose processor, or a dedicated processor. Also, a field programmable gate array (FPGA) that can be programmed after LSI manufacturing, or a reconfigurable processor that can reconfigure the connections and settings of circuit cells within the LSI, may be used. The present disclosure may be realized as digital processing or analog processing.

[0258] Furthermore, if an integrated circuit technology that can replace LSI emerges due to advances in semiconductor technology or other derivative technologies, it is natural that such technology may be used to integrate functional blocks. The application of biotechnology, etc. is also a possibility.

[0259] The present disclosure may be implemented in any type of apparatus, device, or system (collectively referred to as a communications apparatus) that has a communications function. The communications apparatus may include a radio transceiver and processing / control circuitry. The radio transceiver may include a receiver and a transmitter, or both functions. The radio transceiver (transmitter and receiver) may include a radio frequency (RF) module and one or more antennas. The RF module may include an amplifier, an RF modulator / demodulator, or the like. Non-limiting examples of communication devices include telephones (e.g., cell phones, smartphones), tablets, personal computers (PCs) (e.g., laptops, desktops, notebooks), cameras (e.g., digital still / video cameras), digital players (e.g., digital audio / video players), wearable devices (e.g., wearable cameras, smartwatches, tracking devices), game consoles, digital book readers, telehealth / telemedicine devices, communication-enabled vehicles or mobile transportation (e.g., cars, airplanes, ships), and combinations of the above devices.

[0260] The communication devices are not limited to portable or mobile devices, but also include any kind of non-portable or fixed equipment, devices, and systems, such as smart home devices (such as home appliances, lighting equipment, smart meters or measuring devices, control panels, etc.), vending machines, and any other "things" that may exist on an IoT (Internet of Things) network.

[0261] Communications include data communications via cellular systems, wireless LAN systems, communication satellite systems, and the like, as well as data communications via combinations of these.

[0262] A communications apparatus also includes devices such as controllers and sensors connected or coupled to a communications device that performs the communications functions described in this disclosure, such as controllers and sensors that generate control and data signals used by the communications device to perform the communications functions of the communications apparatus.

[0263] The communication apparatus also includes infrastructure facilities, such as base stations, access points, and any other apparatus, device, or system that communicates with or controls the various apparatuses listed above, but are not limited to these.

[0264] A communication device according to one embodiment of the present disclosure includes a control circuit that determines control information relating to implementation-specific conditions or circumstances of a communication device or a communication partner in measuring channel state information during data collection for an artificial intelligence model for predicting channel state information, and a transmission circuit that transmits the control information to the communication partner.

[0265] In one embodiment of the present disclosure, the control information is information regarding conditions or situations for at least one of a transmit precoding applied to a reference signal for measuring the channel state information in a base station, a receive filter applied to receiving the reference signal for measurement in a terminal, and a transmit filter applied to transmitting a reference signal for sounding in the terminal.

[0266] In one embodiment of the present disclosure, the communication device is the terminal, the data collection is performed by the base station, the control information is information regarding the measurement time of the measurement reference signal, and the transmission circuit reports the measurement value of the channel state information to the base station without averaging.

[0267] In one embodiment of the present disclosure, the communication device is the base station, the data collection is performed in the terminal, and the control information is information regarding the transmit precoding applied to transmission of the measurement reference signal.

[0268] In one embodiment of the present disclosure, the information regarding the transmit precoding is information regarding a change in the transmit precoding applied to multiple measurement occasions of the measurement reference signal.

[0269] In one embodiment of the present disclosure, the information regarding a change in the transmit precoding is information indicating whether or not the transmit precoding has been changed between the plurality of measurement occasions.

[0270] In one embodiment of the present disclosure, the information regarding a change in the transmit precoding is information indicating a measurement occasion in which the transmit precoding is changed among the plurality of measurement occasions.

[0271] In one embodiment of the present disclosure, the information regarding a change in the transmit precoding is information indicating a pattern of timings for changing the transmit precoding in the plurality of measurement occasions.

[0272] In one embodiment of the present disclosure, the communication device is the terminal, the data collection is performed at the terminal, and the control information is additional information used when learning and updating the artificial intelligence model at the terminal.

[0273] In one embodiment of the present disclosure, the communication device is the terminal, the data collection is performed by the base station, and the control information is relative information between the multiple measurement occasions regarding the receive filters applied in the multiple measurement occasions of the measurement reference signal.

[0274] In one embodiment of the present disclosure, the communication device is the terminal, the data collection is performed at the base station, and the control information is relative information between the multiple transmission opportunities regarding the transmission filter applied at the multiple transmission opportunities of the sounding reference signal.

[0275] A communication device according to one embodiment of the present disclosure includes a receiving circuit for receiving control information relating to implementation-specific conditions or circumstances of a communication device or a communication partner in measuring channel state information in data collection for an artificial intelligence model for predicting channel state information, and a control circuit for controlling the data collection based on the control information.

[0276] In a communication method according to one embodiment of the present disclosure, a communication device determines control information relating to implementation-specific conditions or circumstances of the communication device or a communication partner in measuring the channel state information during data collection for an artificial intelligence model for predicting channel state information, and transmits the control information to the communication partner.

[0277] In a communication method according to one embodiment of the present disclosure, a communication device receives control information regarding implementation-specific conditions or circumstances of the communication device or a communication partner in measuring channel state information during data collection for an artificial intelligence model for predicting channel state information, and controls the data collection based on the control information.

[0278] In a communication method according to one embodiment of the present disclosure, a base station receives control information regarding at least one of the computational processing volume and power consumption due to the use of an artificial intelligence model on the terminal side, and controls the use of the artificial intelligence model on the terminal side based on the control information.

[0279] The disclosures of the specification, drawings and abstract contained in Japanese Patent Application No. 2024-022160, filed February 16, 2024, are incorporated herein by reference in their entirety.

[0280] One embodiment of the present disclosure is useful in wireless communication systems.

[0281] 100 Base station 101, 205 Control unit 102, 206 Signal generation unit 103, 207 Transmission unit 104, 201 Reception unit 105, 202 Extraction unit 106, 203 Demodulation unit 107, 204 Decoding unit 200 Terminal

Claims

1. A communication device comprising: a control circuit for determining control information relating to implementation-specific conditions or circumstances of a communication device or a communication partner in measuring channel state information during data collection for an artificial intelligence model for predicting channel state information; and a transmission circuit for transmitting the control information to the communication partner.

2. The communication device according to claim 1, wherein the control information is information relating to conditions or situations for at least one of a transmit precoding applied to a reference signal for measurement of the channel state information in a base station, a receive filter applied to reception of the reference signal for measurement in a terminal, and a transmit filter applied to transmission of a reference signal for sounding in the terminal.

3. The communication device according to claim 2, wherein the communication device is the terminal, the data collection is performed by the base station, the control information is information relating to a measurement time of the measurement reference signal, and the transmission circuit reports the measurement value of the channel state information to the base station without averaging.

4. The communication device according to claim 2, wherein the communication device is the base station, the data collection is performed by the terminal, and the control information is information regarding the transmit precoding applied to transmission of the measurement reference signal.

5. The communication device according to claim 4, wherein the information related to the transmission precoding is information related to a change in the transmission precoding applied to the measurement reference signal at a plurality of measurement occasions.

6. The communication device according to claim 5, wherein the information relating to a change in the transmit precoding is information indicating whether or not the transmit precoding has been changed between the plurality of measurement occasions.

7. The communication device according to claim 5, wherein the information relating to a change in the transmit precoding is information indicating a measurement occasion at which the transmit precoding is changed among the plurality of measurement occasions.

8. The communication device according to claim 5, wherein the information relating to the change of the transmit precoding is information indicating a pattern of timing for changing the transmit precoding in the plurality of measurement occasions.

9. The communication device according to claim 2, wherein the communication device is the terminal, the data collection is performed at the terminal, and the control information is additional information used when learning and updating the artificial intelligence model at the terminal.

10. The communication device according to claim 2, wherein the communication device is the terminal, the data collection is performed by the base station, and the control information is relative information between the multiple measurement occasions regarding the receive filter applied in the multiple measurement occasions of the measurement reference signal.

11. The communication device according to claim 2, wherein the communication device is the terminal, the data collection is performed by the base station, and the control information is relative information between the plurality of transmission opportunities regarding the transmission filter applied at the plurality of transmission opportunities of the sounding reference signal.

12. A communications device comprising: a receiving circuit for receiving control information relating to implementation-specific conditions or circumstances of a communications device or a communications partner in measuring channel state information in data collection for an artificial intelligence model for predicting channel state information; and a control circuit for controlling the data collection based on the control information.

13. A communications method, comprising: a communications device, in data collection for an artificial intelligence model for predicting channel state information, determining control information relating to implementation-specific conditions or circumstances of the communications device or a communications partner in measuring the channel state information; and transmitting the control information to the communications partner.

14. A communications method, in which a communications device receives control information relating to implementation-specific conditions or circumstances of the communications device or a communications partner in measuring channel state information during data collection for an artificial intelligence model for predicting channel state information, and controls the data collection based on the control information.