Reference signal resource prediction measurements

Abstract

Examples of the present disclosure relate to measurements for reference signal resource prediction. A first message associated with measurements for reference signal resource prediction is received, and measurements for reference signal resource prediction are performed in accordance with the first message. A second message associated with measurements for reference signal resource prediction is received. Inference of one or more reference signal resource predictions using the measurements is performed. The reference signal resource predictions are reported in accordance with the second message.

Description

Cross-references to related applications

[0001] This application claims priority and benefit to EP application No. 25156072.8, filed on February 5, 2025, the contents of which are incorporated herein by reference in their entirety. Technical Field

[0002] Examples of this disclosure relate to measurements used for reference signal resource prediction. Some non-periodic reports relate to measurements used for reference signal resource prediction. Background Technology

[0003] In communication networks, models such as artificial intelligence (AI) or machine learning (ML) models can be used to predict reference signal resources. When the prediction is in the time domain, a sufficient gap is needed between the triggering of the measurement and the reporting of the measurement to allow historical data to be collected for the model. Summary of the Invention

[0004] According to some, but not all, examples of this disclosure, an apparatus is provided, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to at least: receive a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; perform the measurement for the reference signal resource prediction based on the first message; receive a second message, wherein the second message is associated with the measurement for the reference signal resource prediction; perform inference using the measurement to obtain one or more reference signal resource predictions; and report the reference signal resource prediction based on the second message.

[0005] Inference can be performed using machine learning models.

[0006] The measurement performed based on the first message can be used as input to the machine learning model, and one or more reference signal resource predictions can be provided as output to the machine learning model.

[0007] Reference signal resource predictions can be made for multiple future time instances.

[0008] Reference signal resource prediction can include beam prediction.

[0009] The processor and memory may also be configured to enable the device to determine the association between the second message and the first message, such that a report made based on the second message is related to a measurement made based on the first message.

[0010] The first message can be associated with the second message through a trigger state.

[0011] A trigger state can have a structure, and the structure can include a parameter that indicates the ID of the trigger state.

[0012] The first message may be associated with the first trigger state, and the second message may be associated with the second trigger state, and the first and second trigger states are associated by at least one of the following: a list of trigger states or the ID of the trigger state.

[0013] The first and second messages can be associated with the same trigger state.

[0014] When the trigger state is activated for the first time, the UE can be instructed to perform measurements for reference signal resource prediction, and when the trigger state is activated for the second time, the UE can be instructed to perform reports for reference signal resource prediction.

[0015] When the trigger state is activated for the first time, the UE can be instructed to perform measurements for reference signal resource prediction, and when the trigger state is activated for the second time, the UE can be instructed to perform inference.

[0016] The first message can be associated with the first trigger state, and the second message can be associated with the second trigger state, and the first and second trigger states are associated through a Channel State Information (CSI) report configuration.

[0017] The CSI report configuration for the first and second trigger states can refer to at least one of the following: the same set of reference signal resources or the same set of reference signal resources used for prediction.

[0018] The processor and memory can also be configured to enable the device to perform a CSI report receiving configuration.

[0019] The processor and memory can also be configured to enable the device to perform a configuration that receives a list including one or more trigger states.

[0020] The first message can be a downlink control information (DCI) message, and the second message can also be a DCI message.

[0021] Measurements can be reported in the Channel State Information (CSI) report.

[0022] Predicting measurements for reference signal resources can involve repeated measurements across multiple time instances.

[0023] Measurements can be performed within a time window based on the received CSI report.

[0024] The processor and memory can also be configured to enable the device to perform recorded measurements based on a time window indicated in the first message; and to update a set of measurements using the most recently recorded measurements.

[0025] According to some, but not all, examples of this disclosure, a method is provided, comprising: receiving a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing the measurement for the reference signal resource prediction based on the first message; receiving a second message, wherein the second message is associated with the measurement for the reference signal resource prediction; performing inference using the measurement to obtain one or more reference signal resource predictions; and reporting the reference signal resource predictions based on the second message.

[0026] According to some, but not all, examples of this disclosure, a computer program is provided comprising computer program instructions for causing a device to perform at least the following operations or for performing at least the following operations: receiving a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing the measurement for the reference signal resource prediction according to the first message; receiving a second message, wherein the second message is associated with the measurement for the reference signal resource prediction; using the measurement to perform inference to obtain one or more reference signal resource predictions; and reporting the reference signal resource predictions according to the second message.

[0027] According to various, but not necessarily all, embodiments, an apparatus is provided, comprising: at least one processor; and at least one memory; the at least one memory storing instructions that, when executed by said at least one processor, cause the apparatus to perform at least a portion of one or more methods described herein.

[0028] According to various, but not necessarily all, embodiments, an apparatus is provided that includes components for performing at least a portion of one or more methods described herein. The description of functions and / or actions should also be considered as disclosing any components suitable for performing those functions and / or actions. The functions and / or actions described herein can be performed using any suitable method and in any suitable manner.

[0029] Examples claimed in the appended claims are provided according to various, but not necessarily all, embodiments.

[0030] While the examples and optional features described above in this disclosure are described separately, it should be understood that they are included within this disclosure in all possible combinations and permutations. It should be understood that various examples of this disclosure may include any or all of the features described with respect to other examples of this disclosure, and vice versa. Furthermore, it should be understood that any one or more features in any combination may be implemented by, included in, or performed by the desired means, method, and / or instructions, as appropriate. The description of the function should also be considered as disclosing any components suitable for performing that function. Attached Figure Description

[0031] Some examples will now be described with reference to the accompanying drawings, in which: Figure 1 An example network is shown; Figure 2A and 2B The prediction operation is shown; Figures 3A to 3C Example methods are shown; Figure 4 Example signaling is shown; Figure 5 Example signaling is shown; Figure 6 A sample link to the trigger status ID is shown; Figure 7 A sample link to the trigger status ID is shown; Figure 8 A sample link to the trigger status ID is shown; Figure 9 The prediction operation is shown; and Figure 10 An example controller is shown.

[0032] The accompanying drawings are not necessarily drawn to scale. For clarity and simplicity, some features and views in the drawings may be shown schematically to scale or enlarged. For example, the dimensions of some elements in the drawings may be enlarged relative to other elements to aid illustration. Appropriate reference numerals are used in the drawings to indicate corresponding features. For clarity, not all reference numerals need to be shown in all drawings.

[0033] Detailed description

[0034] Detailed Implementation

[0035] Figure 1 An example of a communication network 100 to which the present disclosure can be applied is shown. Communication network 100 is a cellular communication network. The communication network includes a network access node 102. The network access node 102 provides one or more cells 104. Cells 104 can define the coverage area or service area of ​​the corresponding network access node 102.

[0036] Network access node 102 can provide radio access to a communication network to one or more user equipment (UE) 106. Radio access may include downlink (DL) communication from network access node 102 to UE 106 and uplink (UL) communication from UE 106 to network access node 102. Examples of uplink channels include a Physical Uplink Control Channel (PUCCH) for transmitting control information and a Physical Uplink Shared Channel (PUSCH) for transmitting data to network access node 102. Examples of downlink channels include a Physical Downlink Control Channel (PDCCH) for transmitting control information and a Physical Downlink Shared Channel (PDSCH) for transmitting data to UE 106.

[0037] There can be multiple UEs 106 in network 100. Each UE 106 can be served by the same or different network access nodes 102.

[0038] If the communication network 100 includes multiple network access nodes 102, the network access nodes 102 can connect to each other via an interface. The LTE specification refers to this interface as the X2 interface. The interface between an LTE node and a 5G node, or between two 5G nodes, can be referred to as the Xn interface.

[0039] Network access node 102 can also connect to the core network 108 of communication network 100 via another interface. Core network 108 may include core network nodes. The LTE specification designates the core network as the Evolved Packet Core (EPC), and the core network may include entities such as Mobility Management Entities (MMEs) and gateway nodes. The MME can handle the mobility of terminal devices in a tracking area containing multiple cells and handle signaling connections between terminal devices (such as UE 106 and core network 108). Gateway nodes can handle data routing in and to / from terminal devices (such as UE 106) within core network 108. The 5G specification designates the core network as the 5G Core (5GC). The 5G Core may include, for example, Access and Mobility Management Functions (AMFs) and User Plane Functions / Gateways (UPFs) and other functions. The AMF can handle Non-Access Stratum (NAS) signaling, NAS encryption & integrity protection, registration management, connection management, mobility management, access authentication and authorization, and termination of security context management. For example, UPF nodes can support packet routing and forwarding, packet inspection, and Quality of Service (QoS) processing. In other types of networks, other types of entities can be provided within the core network 108.

[0040] In the communication network 100, models such as artificial intelligence (AI) or machine learning (ML) models can be used to predict reference signal resources. Reference signal resources may include beams or any other resources used for communication between UE 106 and network access node 102.

[0041] There are two distinct use cases for predicting reference signal resources. The first use case is spatial domain prediction. In the spatial domain, prediction is based on a set of measurements that does not contain historical information. The second use case is temporal domain prediction. In the temporal domain, prediction is based on a set of measurements that does contain historical information.

[0042] For beam prediction, measurements and predictions can be based on two sets of beams. Set A is the complete set of beams on which the predictions will operate. Set B is the set of beams on which the measurements will be input into the model. Set B may include Layer 1 Reference Signal Received Power (L1-RSRP) or any other suitable beams. Set B may be different from set A (for both spatial and temporal predictions), or it may be a subset of set A (for both spatial and temporal predictions), or it may be the same as set A (for temporal predictions).

[0043] Figure 2A and 2B The operation of prediction for reference signal resources is illustrated. In these examples, the prediction is beam prediction. UE 106 reports the measurement and / or prediction results for a given set of beams.

[0044] Figure 2A The operation for beam prediction is illustrated, where the model is in network 100. For example, the model can be implemented by network access node 102, core network 108, or any other suitable entity or combination of entities in network 100.

[0045] UE 106 receives downlink control information (DCI) 200. DCI can be received via PDCCH. DCI triggers aperiodic reporting of measurements. Measurements are reported via PUSCH 206.

[0046] Measurements are taken during observation window 202. Observation window 202 needs to be long enough to collect sufficient historical data for the model to perform inference. Observation window 202 may include the reception of multiple resource sets 204. In this case, resource set 204 includes beam set B, and multiple measurement instances can be combined in a single report. Time interval 208 is used for report preparation.

[0047] The measurement report is sent to Network 100. Network 100 uses the measurement as input to the model to obtain predictions for N future time instances. N can be any integer greater than or equal to 1.

[0048] Figure 2BThe operation for beam prediction is illustrated, with the model in UE 106. UE 106 receives downlink control information (DCI) 200. DCI can be received via PDCCH. DCI triggers aperiodic reporting of measurements. Measurements are reported via PUSCH 206.

[0049] Measurements are taken during observation window 202, which can be used as follows: Figure 2A As shown. In this case, UE 106 performs inference 210. UE 106 uses measurements collected during observation window 202 to perform inference 210. UE 106 uses the measurements as input to the model to perform inference 210 and obtain predictions for N future time instances. N can be any integer greater than or equal to 1.

[0050] Time interval 212 is used for reasoning, and time interval 208 is used for report preparation.

[0051] The forecast report is sent to network 100 via PUSCH 206.

[0052] exist Figure 2A and Figure 2B In the two examples shown, a significant time gap is required between the reception of DCI 200 and the transmission of PUSCH 206. This time gap is needed to provide a sufficient observation window and allow UE 106 to prepare reports. If the model is implemented by UE 106, the time gap also needs to allow UE 106 to perform inference. The required time gap could be approximately 100 ms. However, the DCI scheduling CSI reports has a timing dependency indicated by the K2 parameter, which is configured by RRC signaling. The maximum duration is 32 time slots, corresponding to 4 ms with a 120 kHz subcarrier spacing (SCS) for the FR2 band. Therefore, considering the duration of the observation window, the duration is much shorter than the time gap required for prediction operations, which is approximately ~100 ms. If this approach is used, the K2 value should be increased to a very large value.

[0053] However, the K2 parameter also determines the offset in the time slot between the PDCCH carrying DCI 200 and the corresponding transmission of the reporting PUSCH 206. The K2 parameter plays a crucial role in scheduling. During the interval between DCI and PUSCH transmissions, no subsequent DCI can schedule an earlier PUSCH. Therefore, due to the deterministic nature of K2, UE106 is not expected to be configured to schedule out-of-order PUSCH transmissions. This also limits the complexity of UE106 implementation and avoids the problems associated with Hybrid Automatic Repeat Request (HARQ) retransmissions.

[0054] Therefore, when the delay between the DCI and the actual CSI report exceeds K2, it can lead to invalid or failed CSI reports. On the other hand, a large value of K2 can severely reduce uplink throughput due to limitations on PUSCH transmission.

[0055] Examples of this disclosure provide methods and apparatus for addressing these issues and supporting aperiodic (AP) reporting for time reference signal resource prediction.

[0056] In the examples disclosed herein, UE 106 can be configured to receive CSI RS resources corresponding to a set of beams (or other reference signal resources (set B) used for measurement). UE 106 performs measurements on set B and reports these measurements or predictions (obtained from model inference based on these measurements) to network 100 in a CSI report. The CSI-RS configuration can be periodic CSI-RS (P CSI-RS), semi-persistent CSI-RS (SP CSI-RS), or aperiodic CSI-RS (AP CSI-RS).

[0057] For AP CSI-RS configuration, UE 106 can be configured to measure multiple time instances of CSI RS corresponding to set B.

[0058] For P CSI-RS, SP CSI-RS, and AP CSI-RS configurations, messages such as DCI messages can trigger aperiodic CSI reporting, where UE 106 reports multiple measured or predicted time instances in a single CSI report. In the UE-side model, UE 106 reports predicted beam information for multiple time instances in a single CSI report. In the NW-side model, UE 106 reports measured beam information for multiple time instances in a single CSI report.

[0059] Figures 3A to 3C Example methods that can be used in the examples of this disclosure are shown. These methods can be implemented by UE 106 or by any other suitable means.

[0060] exist Figure 3A In the example, at box 300, the method includes receiving a first message. The first message is associated with a measurement for a reference signal resource prediction. The reference signal resource prediction may include beam prediction.

[0061] The first message may include a downlink control information (DCI) message. DCI messages can be received via the PDCCH.

[0062] At box 302, the method includes performing measurements for a reference signal resource prediction based on a first message. Performing measurements for the reference signal resource prediction may include repeating measurements over multiple time instances. Measurements may be performed within a time window based on received CSI reports. In some examples, measurements may be made for a set of resources, B.

[0063] No reports are expected or executed during the measurement triggered by the first message.

[0064] In block 304, the method includes receiving a second message. The second message is associated with a measurement predicted for a reference signal resource. The second message may trigger a report of the measurement made based on the first message.

[0065] The second message may include a downlink control information (DCI) message. The DCI message can be received via the PDCCH. The second message may be received at a later time after the first message.

[0066] In box 306, the method includes reporting at least one of a measurement or a reference signal resource prediction based on a second message. In an example where the model is implemented by a network, the measurement may be reported. In an example where the model is implemented by a UE 106, the prediction may be reported.

[0067] In some examples, measurements or predictions are reported in the Channel State Information (CSI) report. CSI reports can be sent via PUSCH or through any other suitable means.

[0068] In some examples, the method may include preparing a report that includes measurements or forecasts. Preparing the report may include recording measurements based on a time window and updating a set of measurements with the most recently recorded measurement. The time window may be indicated in the first message, in the CSI configuration, or via any other suitable means.

[0069] In the example of the model implementation in UE 106, the method may include implementing a machine learning model, wherein the measurement performed according to the first message is used as input to the machine learning model, and one or more reference signal resource predictions are provided as output of the machine learning model. The predictions can then be provided in a report at box 306. Alternatively, if the model is implemented by network 100, the measurement can be reported to an entity including the machine learning model to enable reference signal resource predictions to be made. Reference signal resource predictions can be made for multiple future time instances.

[0070] In some examples, UE 106 can determine the correlation between the second message and the first message such that a report made based on the second message is related to a measurement made based on the first message. Any suitable means or process can be used to determine the correlation.

[0071] In some examples, a first message can be associated with a second message through a trigger state. The trigger state can have a structure, and the structure can include a parameter indicating the ID of the trigger state.

[0072] In some examples, a first message may be associated with a first trigger state, and a second message may be associated with a second trigger state. The UE 106 can then determine that the first and second trigger states are associated through a trigger state list and / or the ID of the trigger state. The trigger state list may include trigger states not associated with reference signal resource prediction. The trigger state list may be received in the configuration.

[0073] In some examples, the first and second messages can be associated with the same trigger state. In such an example, when the trigger state is activated for the first time, UE 106 is instructed to perform measurements for reference signal resource prediction. When the trigger state is activated a second time, UE 106 is instructed to perform a report.

[0074] In some examples, a first message may be associated with a first trigger state, and a second message may be associated with a second trigger state. The first and second trigger states may be associated via a Channel State Information (CSI) reporting configuration. In such examples, the CSI reporting configurations for the first and second trigger states may reference the same set of reference signal resources or the same set of reference signal resources for prediction. In such examples, the device may receive a CSI reporting configuration.

[0075] exist Figure 3B In the example, at box 310, the method includes receiving a first message. The first message is associated with a measurement for a reference signal resource prediction. The reference signal resource prediction may include beam prediction.

[0076] The first message may include a downlink control information (DCI) message. DCI messages can be received via the PDCCH.

[0077] At box 312, the method includes performing measurements for a reference signal resource prediction based on a first message. Performing measurements for the reference signal resource prediction may include repeating measurements over multiple time instances. Measurements may be configured to be performed within a time window based on received CSI reports. In some examples, measurements may be made for a set of resources B.

[0078] No reports are expected or executed during the measurement triggered by the first message.

[0079] In box 314, the method includes receiving a second message. The second message is associated with a measurement predicted for a reference signal resource. The second message can trigger inference using a report of measurements made based on the first message and predictions made using inference.

[0080] The second message may include a downlink control information (DCI) message. The DCI message can be received via the PDCCH. The second message may be received at a later time after the first message.

[0081] At box 316, the method includes using measurements to perform inference to obtain predictions for one or more reference signal resources. Inference can be implemented using models such as AI / ML models. Inference can take measurements as input and provide predictions of reference signal resources as output. Predictions can be provided for multiple future time instances.

[0082] In some examples, inference can be triggered by a second message. In other examples, the reporting of the inferred prediction can be triggered by a second message, but UE 106 can perform inference before the second message is received.

[0083] At box 318, the method includes reporting a reference signal resource prediction based on a second message. In some examples, the prediction is reported in a Channel State Information (CSI) report. The CSI report may be sent via PUSCH or by any other suitable means.

[0084] exist Figure 3C In the example, at box 320, the method includes receiving a first message. The first message is associated with a measurement for a reference signal resource prediction. The reference signal resource prediction may include beam prediction, where a beam refers to a downlink (DL) transmitter (Tx) beam, a DL receiver (Rx) beam, or a DL Tx-Rx beam pair.

[0085] The first message may include a downlink control information (DCI) message. DCI messages can be received via the PDCCH.

[0086] At box 322, the method includes performing measurements for a reference signal resource prediction based on a first message. Performing measurements for the reference signal resource prediction may include repeating measurements over multiple time instances. Measurements may be performed within a time window based on received CSI reports. In some examples, measurements may be made for a set of resources B.

[0087] No reports are expected or executed during the measurement triggered by the first message.

[0088] In box 324, the method includes receiving a second message. The second message may include a downlink control information (DCI) message. The DCI message may be received via the PDCCH. The second message may be received at a later time as the first message. The second message is associated with a measurement for a reference signal resource prediction.

[0089] In box 326, the method includes determining an association between a first message and a second message. This association ensures that a report triggered by the second message is associated with a reference signal resource measured in response to the first message. Any suitable means can be used to associate the second message with the first message. In some examples, a trigger state can be used to associate the corresponding message.

[0090] In box 328, the method includes reporting at least one of a reference signal resource prediction or a measurement of the reference signal resource prediction based on a second message. In an example where the model is implemented by the network, the measurement can be reported. In an example where the model is implemented by UE 106, the prediction can be reported.

[0091] In some examples, measurements or predictions are reported in the Channel State Information (CSI) report. CSI reports can be sent via PUSCH or through any other suitable means.

[0092] Figure 4 Example signaling that can be used in the examples of this disclosure is shown. Figure 4 In the example, network 100 performs the prediction.

[0093] At box 400, network 100 configures RRC configuration to UE 106. The RRC configuration may include a trigger state list. The trigger state list can associate one or more trigger states with a specific set of Reference Signal (RS) resources. The trigger state list may include higher-layer parameters. CSI-AperiodicTriggerStateList The trigger state list can include non-periodic trigger states. CSI-AperiodicTriggerState A list. CSI-AperiodicTriggerStateList Each trigger state in the table includes at least a resource set ID indicating the channel measurement. CSI-ReportConfig .

[0094] In some examples, a first trigger state can be defined as a measurement trigger state. The measurement trigger state triggers the execution of a measurement. The first trigger state may have a first ID (e.g., ID=1). A second trigger state can be defined as a reporting trigger state. The reporting trigger state triggers the reporting of measurements. The second trigger state may have a second ID (e.g., ID=2). A list of trigger states can link the first and second trigger states, such that UE 106 performs RS measurements based on the first trigger state and reports them aperiodically based on the second trigger state.

[0095] In other examples, a link between measurement and reporting can be established at the DCI message level. In this case, the first and second messages can be associated with the same trigger state. When the trigger state is activated for the first time, UE 106 is instructed to perform a measurement, and when the trigger state is activated for the second time, UE 106 is instructed to report the measurement.

[0096] At box 402, UE 106 receives a first message from network 100. The first message may be a DCI message. The first message may include a CSI request field set to a predefined trigger state ID (e.g., ID=1) to activate the measurement trigger state. For example: DCI message: CSI request field = 1 (measurement triggered status).

[0097] At box 404, network 100 transmits aperiodic RS resources as configured. UE 106 can use these RS resources to perform measurements based on the first message. Using a single aperiodic trigger, network 100 can transmit multiple time instances of the RS resources. The RS resources may include a set of resources B. RS resources can be transmitted for a time window. The time window needs to be long enough for UE 106 to observe sufficient resources for model inference.

[0098] At box 406, UE 106 performs RS measurement. UE 106 may determine the RS resource to be measured based on the trigger state ID received in the first message. Based on the aperiodic offset (X) associated with the RS resource, when UE 106 receives the first message 106, UE 106 measures the RS for each time instance for the duration of the time window over X time slots following the time slot. There is no report of RS measurement based on the first message when the RS measurement is performed.

[0099] In box 408, UE 106 determines the measurement. Determining the measurement can include repeating measurements for set B across multiple time instances within a time window.

[0100] In some examples, the UE may receive periodic (P)CSI-RS or semi-persistent (SP)CSI-RS resources. In this case, network 100 configures UE 106 to record multiple measurements based on the observation window length and update the set of measurements with the most recently recorded measurement. For example, the observation window may have a duration of 80 ms. The recorded measurements may include RSRP values ​​for a set B of three time instances T, T-40ms, and T-80ms.

[0101] At box 410, UE 106 receives a second message from network 100. The second message can be a DCI message. The second message is linked to the first message. For example, the second message can have the same CSI request field or can have a different trigger status ID for reporting (e.g., ID=2). For example: DCI message: CSI request field = 2 (report triggered status).

[0102] In box 412, UE 106 links the first message and the second message. Messages can be linked based on the trigger state ID. UE 106 can also prepare a measurement report. A report can be prepared based on the first message and the second message. UE 106 can determine the measurement corresponding to the observation window associated with the first message and the second message.

[0103] In step 414, UE 106 sends a report of the RS measurement to network 100. The report can be transmitted via PUSCH. The report can be sent according to instructions associated with the second message. For example: Report Measurement: RSRP values ​​for set B in the observation window.

[0104] At box 416, network 100 performs inference based on the reported RS measurement. Network 100 can use a model such as an AI / ML model to perform inference. The output of the inference may include one or more predictions for future time instances.

[0105] At box 418, network 100 sends an indication to UE 106. This indication is based on the output of inference. The indication may include a Transport Configuration Information (TCI) indication, a TCI activation indication, or another message used to trigger measurements and reporting of refined reference signal resource information, or any other suitable indication.

[0106] Figure 5 Example signaling that can be used in the examples of this disclosure is shown. Figure 5 In the example, UE 106 performs prediction. In this example, boxes 400 to 410 are as follows: Figure 4 As shown and as described above. Corresponding reference numerals have been used for the corresponding boxes.

[0107] In box 500, UE 106 links the first message and the second message. The messages can be linked based on the trigger state ID. UE 106 can also determine the RS resource to be predicted. The RS resource to be predicted can be determined based on the first message and the second message. UE 106 can determine the RS resource to be predicted corresponding to the observation window associated with the first message and the second message.

[0108] In box 502, UE 106 performs inference based on the determined RS measurements. UE 106 can use a model such as an AI / ML model to perform inference. The output of the inference can include one or more predictions for future time instances. For example, UE 106 can use measurements for set B as input to a model to predict beam information for set A. For example: AI / ML model inference: Predicting beam information for set A based on the historical RSRP values ​​of set B.

[0109] At step 504, UE 106 transmits a prediction report to network 100. The report can be transmitted via PUSCH. The report can be transmitted according to instructions associated with the second message. For example: The report predicts the predicted beam information for set A across multiple time instances.

[0110] At box 418, network 100 sends an instruction to UE 106. This is similar to... Figure 4 Box 418 is shown. This indication is based on the output of the prediction report. This indication may include a Transmission Configuration Information (TCI) indication, a TCI activation indication, or another message or any other suitable indication used to trigger measurements and reporting of refined reference signal resource information.

[0111] Figure 6 The operation of predicting a reference signal resource that can be used in the examples of this disclosure is illustrated. Figure 5 In the example, the model is in UE 106, and UE 106 reports a set of predictions to network 106. A similar set of operations can be used for the case where the model is in network 100 and the UE reports that set of measurements.

[0112] UE 106 receives first message 402. First message 402 may include DCI information. DCI can be received via PDCCH. First message 402 triggers a measurement of the resource without requiring any measurement report.

[0113] RS resource 404 is periodically transmitted by network 100. UE 106 uses RS resource 404 to perform measurements during observation window 600.

[0114] In some examples, network 100 can configure UE 106 to record multiple measurements based on the length of observation window 600, and update the group of measurements with the latest measurement.

[0115] Then, UE 106 receives the second message 410. The second message 410 is received after the first message 402. The first message can be received after the observation window 600. The second message 402 may include DCI information. The DCI can be received via PDCCH. The second message 408 triggers a prediction report based on the measurement triggered by the first message 402.

[0116] The second message 410 is linked to the first message 402. The second message 408 can be linked to the first message by triggering a state ID or any other suitable means or process. Linking the second message 410 to the first message 402 enables the UE 106 to determine the RS resource to be predicted.

[0117] Then, UE 106 performs inference based on the determined RS measurements. UE 106 can use models such as AI / ML models to perform inference. The output of the inference can include one or more predictions for future time instances. For example, measurements can be performed for set B and used to predict beam information for set A. Time period 602 is used for inference.

[0118] Then, UE 106 can prepare a report based on the forecast and send a report 504 including the forecast to network 100. A time period 604 is used for report preparation. The forecast can be sent via PUSCH. The forecast can be sent according to the instructions in the second message 410.

[0119] This disclosure provides an example that solves the problem of K2 parameter constraints. (Compared to...) Figure 2A and Figure 2B Compared to the K2 parameters shown, Figure 6 In the example, the K2 parameter 606 is significantly reduced. Figure 6 In the example, the K2 parameter does not need to include observation window 600. This allows for efficient scheduling of UE 106 because it avoids out-of-order PUSCH transmissions. This is achieved through the use of first message 402 and second message 410.

[0120] The first and second messages can be linked to allow the appropriate resource to be measured and the corresponding measurement or prediction to be reported. In some examples, a trigger state can be used to link the corresponding measurement.

[0121] In the example disclosed herein, UE 106 is configured with a trigger state list. UE 106 can be configured with a trigger state list using RRC or any other suitable signaling.

[0122] The trigger state list includes one or more trigger states. Different types of trigger states can trigger different types of actions. In the examples disclosed herein, at least some of the trigger states can be used to trigger the execution of a measurement and to trigger the reporting of a measurement or prediction. These types of trigger states include a set of parameters and / or conditions that indicate when the UE 106 performs a measurement for beam prediction or reporting a measurement or beam prediction.

[0123] The trigger state can be associated with a CSI report configuration used for inference. The CSI report configuration for inference can include a first set of RS resources for beam measurement (or measurement of other reference signal resources) and a second set of RS resources for beam prediction (or prediction of other reference signal resources). In an example of the Network 100 implementation model, the CSI report configuration can configure an observation window 600 for pre-forming measurements and a window 604 for preparing measurement reports and / or any other relevant parameters. In an example of the UE 106 implementation model, the CSI report configuration can configure an observation window 600 for pre-forming measurements, a window 602 for performing inference, and a window 604 for preparing measurement reports and / or any other relevant parameters.

[0124] Figure 7 The diagram schematically illustrates a first example of a link that triggers a status ID. A first message 402 is associated with a first CSI request X, and a second message 410 is associated with a second CSI request Y.

[0125] UE 106 is configured with a trigger state list 700. Trigger state list 700 includes multiple trigger states. Figure 7 In the example, a first trigger state 702 and a second trigger state 704 are shown. In other examples, the trigger state list 700 may include other trigger states.

[0126] exist Figure 7 In the example, the first trigger state 702 is associated with performing a measurement, and the second trigger state 704 is associated with reporting a measurement or prediction. Some other trigger states in the trigger state list 700 may involve operations other than measurement and reporting.

[0127] When UE 106 receives the first message 402, this message includes a first CSI request. UE 106 uses the CSI request in the first message 402 and the trigger state list 700 to determine the trigger state associated with the first message 402. In this case, the first trigger state 702 is associated with the first message 402, and therefore this triggers UE 106 to begin performing measurements. The first message 402 does not trigger UE 106 to perform any measurement or prediction reports.

[0128] When UE 106 receives the second message 410, the message includes a second CSI request. UE 106 uses the CSI request in the second message 410 and the trigger state list 700 to determine the trigger state associated with the second message 410.

[0129] In this case, a new parameter is included in the trigger state structure to indicate the linked trigger state ID and to provide a direct link or association between the first message 402 and the second message 410. Thus, the trigger state of the first message 402 is directly linked to the trigger state of the second message 410, with the new parameter added to the trigger state structure to indicate the linked trigger state ID. Arrow 706 indicates an explicit link between the first trigger state 702 and the second trigger state 704.

[0130] UE 106 determines that the second message 410 is associated with the first message 402, and therefore, in response to the second message 410, UE 106 sends a report or prediction based on the measurement made in response to the first message.

[0131] Figure 8 A second example of a link that triggers a status ID is illustrated schematically. First message 402 is associated with a first CSI request X, and second message 410 is associated with a second CSI request Y.

[0132] In this second example, UE 106 is also configured with a trigger state list 700. Trigger state list 700 includes multiple trigger states. Figure 8 In the example shown, a single trigger state 800 is illustrated. In other examples, the trigger state list 700 may include other trigger states.

[0133] In this example, the same trigger state 800 is associated with both the first message 402 and the second message 410. In this example, when UE 106 receives the first message 402, the message includes a first CSI request. UE 106 uses the CSI request in the first message 402 and the trigger state list 700 to determine the trigger state 800 associated with the first message 402.

[0134] When UE 106 receives the second message 410, this message includes a second CSI request. UE 106 uses the CSI request in the second message 410 and the trigger state list 700 to determine the trigger state 800 associated with the second message 410. In this case, the trigger state list 700 indicates that two CSI requests are associated with the same trigger state 800. Thus, the trigger state 800 of the first message 402 has the same ID as the trigger state 800 of the second message 410 in the trigger state list 700.

[0135] UE 106 knows that when trigger state 800 is activated for the second time, UE 106 must report the measurements made after trigger state 800 was activated for the first time.

[0136] Figure 9 A third example of a link that triggers a status ID is illustrated schematically. First message 402 is associated with a first CSI request X, and second message 410 is associated with a second CSI request Y.

[0137] In this third example, UE 106 is also configured with a trigger state list 700. Trigger state list 700 includes multiple trigger states. Figure 9 In the example, a first trigger state 900 and a second trigger state 902 are shown. In other examples, the trigger state list 700 may include other trigger states.

[0138] In this example, the first trigger state 900 is associated with performing a measurement, and the second trigger state 902 is associated with reporting a measurement or prediction. Trigger states 900 and 902 are linked via CSI reporting configuration 904.

[0139] The first message 402 is received by UE 106 and includes a first CSI request. UE 106 uses the CSI request in the first message 402 and the trigger state list 700 to determine the trigger state 900 associated with the first message 402. Trigger state 900 is linked to CSI report configuration ID 904. CSI report configuration ID 904 is linked to a specific RS resource set.

[0140] UE 106 is configured with CSI report configuration list 908. The CSI report configuration list associates CSI report configuration IDs 904 and 906 with RS resource sets. UE 106 can use CSI report configuration list 908 to determine the RS resources associated with the first trigger state 900.

[0141] When UE 106 receives the second message 410, the second message 410 includes a second CSI request. UE 106 uses the CSI request in the second message 410 and the trigger state list 700 to determine the trigger state 902 associated with the second message 410. In this case, trigger state 902 is associated with the second CSI report configuration ID 906. UE 106 uses the CSI report configuration list 908 to determine that the second CSI report ID 906 is associated with the same RS resource set as the first CSI report ID 904. Therefore, UE 106 knows which measurements to report.

[0142] Figure 10An example controller 1000 is shown. Controller 1000 can be housed within UE 106 or any other suitable entity. Implementation of controller 1000 can be as a controller circuit system. Controller 1000 can be implemented solely in hardware, have certain aspects in software comprising only firmware, or be a combination of hardware and software (including firmware). Controller 1000 can provide means for implementing this disclosure, which can be provided as part of means for implementing this disclosure.

[0143] like Figure 9 As shown, the controller 1000 can be implemented using instructions that implement hardware functions, for example, by using executable instructions of a computer program 1006 in a general-purpose or special-purpose processor 1002, which can be stored on a machine-readable storage medium (disk, memory, etc.) to be executed by such processor 1002.

[0144] Processor 1002 is configured to read from and write to memory 1004. Processor 1002 may also include an output interface and an input interface, through which data and / or commands are output by processor 1002 and through which data and / or commands are input to processor 1002.

[0145] Memory 1004 stores instructions, programs 1006, or code that control the operation of the device when loaded into processor 1002. The instructions, programs 1006, or code provide logic and routines that enable the device to perform the methods shown in the figures, and processor 1002 can load and execute the instructions, programs 1006, or code by reading memory 1004.

[0146] In some examples where the controller 1000 is provided within an apparatus for controlling a first wireless electronic system, the controller thus includes components for: receiving 300 a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing 302 a measurement for the reference signal resource prediction based on the first message; receiving 304 a second message, wherein the second message is associated with a measurement for the reference signal resource prediction; and reporting 306, based on the second message, at least one of the following: the measurement for the reference signal resource prediction; or the reference signal resource prediction.

[0147] In some examples where the controller 1000 is provided within an apparatus for controlling a first wireless electronic system, the controller thus includes components for: receiving 310 a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing 312 a measurement for the reference signal resource prediction based on the first message; receiving 314 a second message, wherein the second message is associated with a measurement for the reference signal resource prediction; performing 316 inference using the measurement to obtain one or more reference signal resource predictions; and reporting 318 a reference signal resource prediction based on the second message.

[0148] In some examples where the controller 1000 is provided within an apparatus for controlling a first wireless electronic system, the controller thus includes components for: receiving 320 a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing 322 a measurement for the reference signal resource prediction based on the first message; receiving 324 a second message, wherein the second message is associated with a measurement for the reference signal resource prediction; determining 326 an association between the first message and the second message; and reporting 328 at least one of the following based on the association between the first message and the second message: a measurement for the reference signal resource prediction; or a reference signal resource prediction, wherein the determined association ensures that the report made based on the second message is related to the measurement made based on the first message.

[0149] Instructions, program 1006, or code can reach the device via any suitable delivery mechanism 1008. Delivery mechanism 1008 can be, for example, a machine-readable medium, a computer-readable medium, a non-transitory computer-readable storage medium, a computer program product, a memory device, a recording medium (such as an optical disc read-only memory (CD-ROM) or a digital versatile disc (DVD) or solid-state storage), or an article of manufacture that includes or tangibly embodies the computer program 1006. The delivery mechanism can be a signal configured to reliably transmit the computer program 1006. The device can propagate or transmit the computer program 1006 as a computer data signal.

[0150] As used herein, the term “non-transient” refers to a limitation on the medium itself, which is tangible rather than signal-based, rather than a limitation on the persistence of data storage (e.g., RAM versus ROM).

[0151] Computer program 1006 may include computer program instructions for causing the device to perform at least the following operations or for performing at least the following operations: receiving 300 a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing 302 a measurement for a reference signal resource prediction according to the first message; receiving 304 a second message, wherein the second message is associated with a measurement for a reference signal resource prediction; and reporting 306 at least one of the following according to the second message: a measurement for a reference signal resource prediction; or a reference signal resource prediction.

[0152] Computer program 1006 may include computer program instructions for causing the device to perform at least the following or for performing at least the following operations: receiving 310 a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing 312 a measurement for the reference signal resource prediction based on the first message; receiving 314 a second message, wherein the second message is associated with a measurement for the reference signal resource prediction; performing 316 inference using the measurement to obtain one or more reference signal resource predictions; and reporting 318 a reference signal resource prediction based on the second message.

[0153] Computer program 1006 may include computer program instructions for causing the apparatus to perform at least the following or for performing at least the following operations: receiving 320 a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing 322 a measurement for the reference signal resource prediction based on the first message; receiving 324 a second message, wherein the second message is associated with a measurement for the reference signal resource prediction; determining 326 an association between the first message and the second message; and reporting 328 at least one of the following based on the association between the first message and the second message: a measurement for the reference signal resource prediction; or a reference signal resource prediction, wherein the determined association ensures that the report made based on the second message is related to the measurement made based on the first message.

[0154] Computer program instructions may be included in a computer program, a non-transitory computer-readable medium, a computer program product, or a machine-readable medium. In some, but not all, examples, computer program instructions may be distributed across more than one computer program.

[0155] Although memory 1004 is shown as a single component / circuit system, it can be implemented as one or more separate components / circuit systems, some or all of which may be integrated / removable and / or provide permanent / semi-permanent / dynamic / cached storage.

[0156] Although processor 1002 is shown as a single component / circuit system, it can be implemented as one or more separate component / circuit systems, some or all of which may be integrated / removable. Processor 1002 may be a single-core or multi-core processor.

[0157] References to “computer-readable storage medium,” “computer program product,” “computer program tangibly embodied,” or “controller,” “computer,” “processor,” etc., should be understood to encompass not only computers with different architectures (such as single / multiprocessor architectures and sequential (von Neumann) / parallel architectures) but also special-purpose circuits (such as field-programmable gate arrays (FPGAs), special-purpose circuits (ASICs), signal processing devices, and other processing circuit systems, including quantum processing circuit systems). References to computer programs, instructions, code, etc., should be understood to encompass software used in programmable processors or firmware, such as, for example, the programmable content of hardware devices, whether instructions for processors or configuration settings for fixed-function devices, gate arrays, or programmable logic devices, etc.

[0158] As used in this application, the term "circuit system" may refer to one or more of the following: hardware circuit system implementations only (such as implementations only in analog and / or digital circuit systems) and combinations of hardware circuits and software, such as (where applicable): combinations of analog, digital and / or quantum hardware circuits with software / firmware, any or all portions of a hardware processor (including digital and / or quantum processors) with software and memory, which work together to enable a device such as a mobile device, computing device or server to perform various functions, and any or all portions of hardware circuits (such as microprocessors and / or quantum processors) that require software (e.g., firmware) to operate, but the software may be absent when it is not required to operate.

[0159] This definition of circuit system applies to all uses of the term in this application, including in any claim. As another example, as used in this application, the term circuit system also covers implementations of only hardware circuitry or processors (or processors) or a portion thereof and their accompanying software and / or firmware. For example, and if applicable to elements of the claims, the term circuit system also covers baseband integrated circuits or processor integrated circuits for use in mobile devices or servers, cellular network devices, or other computing or networking devices.

[0160] The boxes shown in the accompanying drawings may represent steps in the method and / or code segments in computer program 1006. The illustration of a particular order of boxes does not necessarily imply a desired or preferred order of blocks, and the order and arrangement of boxes may vary. Furthermore, some boxes may be omitted.

[0161] Where structural features have been described, they can be replaced by components that perform one or more functions of the structural features, whether or not the function or those functions are explicitly or implicitly described.

[0162] The above examples can be applied to enable the implementation of the following components: automotive systems; telecommunications systems; electronic systems including consumer electronics; distributed computing systems; media systems for generating or rendering media content including audio, visual, and audiovisual content, as well as mixed, mediated, virtual, and / or augmented reality media content; personal systems including personal health systems or personal fitness systems; navigation systems; user interfaces, also known as human-machine interfaces; networks including cellular networks, non-cellular networks, and optical networks; self-organizing networks; the Internet of Things; the Internet of Things; virtualized networks; and related software and services.

[0163] According to the examples of this disclosure, the device can be provided in an electronic device (e.g., a mobile terminal). However, it should be understood that a mobile terminal is merely an illustration of an electronic device that will benefit from implementations of this disclosure and should therefore not be construed as limiting the scope of this disclosure to the same level. While in some implementation examples the device can be provided in a mobile terminal, other types of electronic devices (such as, but not limited to, mobile communication devices, handheld portable electronic devices, wearable computing devices, portable digital assistants (PDAs), pagers, mobile computers, desktop computers, televisions, gaming devices, laptop computers, cameras, video recorders, GPS devices, and other types of electronic systems) can readily adopt the examples of this disclosure. Furthermore, devices can readily adopt the examples of this disclosure regardless of their intention to provide mobility.

[0164] The term "includes" is used in this document in a non-exclusive sense of inclusion. That is, any reference to X that includes Y indicates that X may include only one Y or may include more than one Y. If the intention is to use "includes" with an exclusive sense, it will be made clear in the context by referring to "only one...".

[0165] In this specification, the terms “connection,” “coupling,” and “communication,” and their derivatives, mean operatively connecting / coupling / communicating. It should be understood that any number or combination of intermediate components (including none) may be present to provide direct or indirect connection / coupling / communication. Any such intermediate component may include hardware and / or software components.

[0166] As used herein, the term "determine" (and its grammatical variations) can include, in particular: calculation, processing, derivation, measurement, investigation, identification, lookup (e.g., searching in a table, database, or other data structure), ascertainment, etc. Furthermore, "determine" can include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), obtaining, etc. Additionally, "determine" can include parsing, selecting, picking, building, etc.

[0167] Various examples have been referenced in this specification. Descriptions of features or functions of an example indicate which features or functions exist in that example. Whether explicitly stated or not, the use of the terms “example,” “for example,” or “may” in the text indicates that, whether described as an example or not, such features or functions exist in at least the described example, and that, whether described as an example or not, they may, but not necessarily, exist in some or all other examples. Therefore, “example,” “for example,” or “may” refers to a specific instance of a class of examples. An instance’s properties may be properties of only that instance, or properties of the class, or properties of a subclass of the class, which includes some but not all instances of the class. Therefore, it is implicitly disclosed that features described with reference to one example, and not another, may be used as part of a working composition in that other example, but not necessarily in that other example.

[0168] As used herein, “at least one of the following:” and “at least one” and similar wording, wherein a list of two or more elements connected by “and” or “or” means at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0169] Although examples have been described in the preceding paragraphs with reference to various examples, it should be understood that modifications may be made to the given examples without departing from the scope of the claims.

[0170] The features described above can be used in combinations other than those explicitly described above.

[0171] Although the functionality has been described with reference to certain features, these functions can be performed by other features regardless of whether they are described or not.

[0172] The description of features (such as means or components of means) configured to perform a function or for performing a function should also be considered to disclose a method for performing that function. For example, the description of a means configured to perform one or more actions or for performing one or more actions should also be considered to disclose a method for performing the one or more actions with or without the means.

[0173] Although features have been described with reference to some examples, these features may exist in other examples, whether or not they are described.

[0174] The terms “a,” “an,” or “the” as used in this document have an inclusive rather than exclusive meaning. That is, unless the context clearly indicates the opposite, any reference to X that includes one / the Y indicates that X may include only one Y or may include more than one Y. If the exclusive meaning of “a,” “an,” or “the” is intended to be used, it will be clearly described in the context. In some cases, the use of “at least one” or “one or more” may be used to emphasize an inclusive meaning, but the absence of these terms should not be taken as an indication of any exclusive meaning.

[0175] The presence of a feature (or combination of features) in a claim is a reference to that feature or combination of features itself, as well as features that achieve substantially the same technical effect (equivalent features). Equivalent features include, for example, features that are variations and achieve substantially the same result in substantially the same manner. Equivalent features include, for example, features that perform substantially the same function in substantially the same manner to achieve substantially the same result.

[0176] In this specification, adjectives or adjective phrases have been used to describe the characteristics of various examples. Such descriptions of the characteristics of an example indicate that the characteristic exists precisely in some examples and in other examples that are substantially as described.

[0177] As used herein, the terms “at least one” and “one or more” mean “any one of at least one” and “any one of one or more”, respectively.

[0178] However, the foregoing description describes some examples of this disclosure. Those skilled in the art will recognize possible alternative structural and methodological features that provide functionality equivalent to specific examples of such structures and features described above, and for the sake of brevity and clarity, these structures and features have been omitted from the foregoing description. Nevertheless, unless such alternative structural or methodological features are expressly excluded in the foregoing description of examples of this disclosure, the foregoing description should be understood to implicitly include references to such alternative structural and methodological features that provide equivalent functionality.

[0179] Although efforts have been made in the foregoing specification to draw attention to those features deemed important, an applicant may seek protection by means of the claims for any patentable feature or combination of features referenced above and / or shown in the drawings, whether or not they have been emphasized.

[0180] Furthermore, the various implementations of this disclosure can be described with reference to the following terms, and their features can be combined in any reasonable manner.

[0181] Clause 1. An apparatus for communication, comprising: at least one processor; and at least one memory storing instructions, which, when executed by the at least one processor, cause the apparatus to at least: receive a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; perform the measurement for the reference signal resource prediction according to the first message; receive a second message, wherein the second message is associated with the measurement for the reference signal resource prediction; perform inference using the measurement to obtain one or more reference signal resource predictions; and report the reference signal resource predictions according to the second message.

[0182] Clause 2. The apparatus according to Clause 1, wherein the inference is performed using a machine learning model.

[0183] Clause 3. The apparatus according to Clause 2, wherein the measurement performed according to the first message is used as input to the machine learning model, and the one or more reference signal resource predictions are provided as outputs of the machine learning model.

[0184] Clause 4. The apparatus according to Clause 1, wherein the reference signal resource prediction is made for multiple future time instances.

[0185] Clause 5. The apparatus according to Clause 1, wherein the reference signal resource prediction includes beam prediction.

[0186] Clause 6. The apparatus according to Clause 1, wherein the processor and the memory are further configured to cause the apparatus to determine an association between the second message and the first message, such that the report made based on the second message relates to the measurement made based on the first message.

[0187] Clause 7. The apparatus according to Clause 1, wherein the first message is associated with the second message via a trigger state.

[0188] Clause 8. The apparatus according to Clause 7, wherein the trigger state has a structure and the structure includes a parameter indicating an ID of the trigger state.

[0189] Clause 9. The apparatus according to Clause 7, wherein the first message is associated with a first trigger state, and the second message is associated with a second trigger state, and the first trigger state and the second trigger state are associated by at least one of: a list of trigger states; or an ID of the trigger state.

[0190] Clause 10. The apparatus according to Clause 7, wherein the first message and the second message are associated with the same trigger state.

[0191] Clause 11. The apparatus according to Clause 10, wherein when the trigger state is activated for a first time, the UE is instructed to perform the measurement for the reference signal resource prediction, and when the trigger state is activated for a second time, the UE is instructed to perform the report of the reference signal resource prediction.

[0192] Clause 12. The apparatus according to Clause 10, wherein when the trigger state is activated for a first time, the UE is instructed to perform the measurement for the prediction of the reference signal resource, and when the trigger state is activated for a second time, the UE is instructed to perform the inference.

[0193] Clause 13. The apparatus according to Clause 7, wherein the first message is associated with a first trigger state, and the second message is associated with a second trigger state, and the first trigger state and the second trigger state are associated via a Channel State Information (CSI) report configuration.

[0194] Clause 14. The apparatus according to Clause 13, wherein the CSI report configuration of the first trigger state and the second trigger state refers to at least one of the following: the same set of reference signal resources; or the same set of reference signal resources used for prediction.

[0195] Clause 15. A method for communication, comprising: receiving a first message, wherein the first message is associated with a measurement for a reference signal resource prediction; performing the measurement for the reference signal resource prediction according to the first message; receiving a second message, wherein the second message is associated with the measurement for the reference signal resource prediction; using the measurement to perform inference to obtain one or more reference signal resource predictions; and reporting the reference signal resource predictions according to the second message.

Claims

1. A device for communication, comprising: At least one processor; as well as At least one memory, the at least one memory storing instructions, the instructions, when executed by the at least one processor, cause the device to perform at least the following: Receive a first message, wherein the first message is associated with a measurement for a prediction of reference signal resources; Perform the measurement for the prediction of the reference signal resources based on the first message; Receive a second message, wherein the second message is associated with the measurement predicted for the reference signal resource; The measurements are used to perform inference to obtain one or more reference signal resource predictions; as well as The reference signal resource prediction shall be reported based on the second message.

2. The apparatus of claim 1, wherein the inference is performed using a machine learning model.

3. The apparatus of claim 2, wherein the measurement performed according to the first message is used as input to the machine learning model, and the one or more reference signal resource predictions are provided as outputs of the machine learning model.

4. The apparatus of claim 1, wherein the reference signal resource prediction is made for multiple future time instances.

5. The apparatus of claim 1, wherein the reference signal resource prediction includes beam prediction.

6. The apparatus of claim 1, wherein the processor and the memory are further configured to cause the apparatus to determine an association between the second message and the first message, such that the report made based on the second message relates to the measurement made based on the first message.

7. The apparatus of claim 1, wherein the first message is associated with the second message via a trigger state.

8. The apparatus of claim 7, wherein the trigger state has a structure, and the structure includes a parameter indicating an ID of the trigger state.

9. The apparatus of claim 7, wherein the first message is associated with a first trigger state, and the second message is associated with a second trigger state, and the first trigger state and the second trigger state are associated by at least one of the following: Trigger status list; or The ID of the trigger state.

10. The apparatus of claim 7, wherein the first message and the second message are associated with the same trigger state.

Images