System and method for handling measurements for data collection considering conflict conditions

Abstract

A system and method for processing resource measurements for data collection are disclosed. The method includes, based on a user equipment (UE) being configured with more than one bandwidth part (BWP) and a first BWP of the more than one BWP being activated, recording, by the UE, a first channel state information (CSI) measurement result associated with a first resource corresponding to the first BWP as an entry of an artificial intelligence / machine learning (AI / ML) dataset, and transmitting, by the UE, the first CSI measurement result from the UE based on the AI / ML dataset.

Description

[0001] Cross-reference to related applications This application claims priority to U.S. Provisional Application No. 63 / 774,289, filed March 19, 2025, and U.S. Patent Application No. 19 / 561,364, filed March 9, 2026, the entire disclosure of which is incorporated herein by reference as if fully set forth herein. Technical Field

[0002] Aspects of some embodiments of this disclosure relate generally to communication. For example, aspects of some embodiments of this disclosure relate to improvements to systems and methods for performing measurements for data collection. Background Technology

[0003] In the communications field, beam management (BM) can be performed in a communication system to predict the optimal beam for a given UE to communicate with the network (NW). In some systems, artificial intelligence / machine learning (AI / ML) models can be used to predict the optimal beam. For example, a network node may include an NW-side model (e.g., an NW AI / ML model) trained based on collected data to predict the optimal beam for a given UE. To train the NW-side model for beam management use cases, the NW may configure a given UE to collect data for training. For example, a network node may configure the UE to perform measurements of Channel State Information Reference Signal (CSI-RS) resources and record the measurement results to collect data for AI / ML training on the NW-side model. Once the NW (e.g., the network node) requests a UE report using (e.g., by sending) an on-demand request, the recorded measurement results can be sent. For example, the UE can be configured to periodically log measurement results based on CSI-RS resources (e.g., based on periodic resources), store the measurement results in a log (e.g., a list, table, etc.), and send one or more of the logs or measurement results to the NW (e.g., to a network node) upon NW request. The NW can use the logs (e.g., using data from the logs) to train an AI / ML model for beam prediction. Summary of the Invention

[0004] Aspects of some embodiments of this disclosure provide improved systems and methods for performing data collection that can be used to train AI / ML models for beam management.

[0005] According to some embodiments of this disclosure, a method for data collection includes: based on a user equipment (UE) being configured with more than one bandwidth portion (BWP) and a first BWP being activated, the UE performing a recording of a first channel state information (CSI) measurement result associated with a first resource corresponding to the first BWP as an entry in an artificial intelligence / machine learning (AI / ML) dataset, and the UE transmitting the first CSI measurement result from the UE based on the AI / ML dataset.

[0006] AI / ML datasets may include data indicating that a second CSI measurement was not performed.

[0007] The method may further include: based on the deactivation of a second BWP among more than one BWP, the UE does not perform recording of a second CSI measurement result associated with the second BWP for AI / ML data collection.

[0008] The method may also include: the UE sending data indicating why the recording of the second CSI measurement result was not performed.

[0009] The method may further include: based on a second resource for AI / ML data collection corresponding to a measurement gap, the UE does not perform a second measurement for AI / ML data collection, wherein the second measurement is associated with a second resource.

[0010] The method may further include: based on the second resource for AI / ML data collection corresponding to an inactive discontinuous reception (DRX) period, the UE does not perform a second measurement for AI / ML data collection, wherein the second measurement is associated with the second resource.

[0011] The method may further include: based on a second resource for AI / ML data collection corresponding to an active discontinuous reception (DRX) period and a recording mask, the UE does not perform a second measurement configured for AI / ML data collection, wherein the second measurement is associated with the second resource.

[0012] The method may further include: based on a second resource for AI / ML data collection corresponding to an inactive discontinuous reception (DRX) period and configuring an inactive recording state for the UE, the UE performs a second measurement for AI / ML data collection, wherein the second measurement is associated with the second resource.

[0013] The method may further include: based on the second resource measurement time for AI / ML data collection corresponding to an inactive discontinuous transmission (DTX) period, the UE does not perform a second measurement for AI / ML data collection, wherein the second measurement is associated with the second resource measurement time.

[0014] The method may further include: a resource window corresponding to a second resource for AI / ML data collection and an inactive discontinuous reception (DRX) period and a third resource for AI / ML data collection, wherein the third resource corresponds to an active DRX period: the UE does not perform a second measurement for AI / ML data collection associated with the second resource, and the UE does not perform a third measurement for AI / ML data collection associated with the third resource.

[0015] According to other embodiments of this disclosure, a method for data collection includes: based on the activation of a secondary cell (SCell), a user equipment (UE) performing the recording of CSI measurement results associated with the SCell for artificial intelligence / machine learning (AI / ML) data collection, in order to perform AI / ML data collection.

[0016] The method may also include: based on the deactivation of the SCell, the UE does not perform recording of the second CSI measurement results used for AI / ML data collection.

[0017] The method may also include: the UE sending data indicating that the measurement was not performed.

[0018] The method may further include: performing measurements configured for AI / ML data collection by the UE on a primary / secondary cell (PSCell) where the bandwidth portion (BWP) is activated and the serving cell is not a deactivated secondary cell group (SCG) to collect AI / ML data.

[0019] According to other embodiments of this disclosure, a system for data collection includes a user equipment (UE), wherein the UE is configured to perform the following operations: based on the UE being configured to have more than one bandwidth portion (BWP) and a first BWP being activated, recording a first channel state information (CSI) measurement result corresponding to a first resource associated with the first BWP as an entry in an artificial intelligence / machine learning (AI / ML) dataset, and transmitting the first CSI measurement result from the UE based on the AI / ML dataset.

[0020] The UE can be configured to not record the second CSI measurement results associated with the second BWP for AI / ML data collection, based on the deactivation of the second BWP among more than one BWP.

[0021] The UE can be configured to send data indicating why the recording of the second CSI measurement result was not performed.

[0022] The UE can be configured to perform a second measurement configured for AI / ML data collection based on a second resource for AI / ML data collection corresponding to an inactive discontinuous reception (DRX) period and with an inactive recording state configured for the UE, wherein the second measurement is associated with the second resource.

[0023] The UE can be configured to not perform a second measurement configured for AI / ML data collection, based on a second resource for AI / ML data collection corresponding to an inactive discontinuous reception (DRX) period, wherein the second measurement is associated with the second resource.

[0024] The UE can be configured to perform AI / ML data collection by recording second CSI measurement results associated with the secondary cell (SCell) for AI / ML data collection, based on the activation of the secondary cell (SCell). Attached Figure Description

[0025] In the following sections, aspects of the subject matter disclosed herein will be described with reference to exemplary embodiments shown in the accompanying drawings.

[0026] Figure 1A This is a block diagram depicting a system including a UE and a network node for processing resource measurements for data collection, according to some embodiments of the present disclosure.

[0027] Figure 1B This describes some embodiments according to the present disclosure. Figure 1A A block diagram illustrating an example operation of the inference process for beam management performed by an AI / ML model in the system.

[0028] Figure 2 This is a block diagram illustrating example operations of a data collection process for a network-side model according to some embodiments of the present disclosure.

[0029] Figure 3 This is a block diagram depicting example operations for skipping measurements used for data collection during bandwidth portion (BWP) switching, according to some embodiments of the present disclosure.

[0030] Figure 4 This is a block diagram depicting example operations for skipping measurements for data collection due to measurement gaps, according to some embodiments of the present disclosure.

[0031] Figure 5A This is a block diagram depicting example operations for skipping measurements used for data collection in discontinuous reception (DRX) according to some embodiments of the present disclosure.

[0032] Figure 5BThis is a block diagram depicting example operations for skipping measurements used for data collection in DRX when a recording mask is enabled, according to some embodiments of the present disclosure.

[0033] Figure 5C This is a block diagram depicting example operations for performing measurements for data collection in a DRX during inactive periods, according to some embodiments of the present disclosure.

[0034] Figure 6 This is a block diagram depicting a system for skipping measurements for data collection when a secondary cell (SCell) is deactivated, according to some embodiments of the present disclosure.

[0035] Figure 7 This is a block diagram depicting example operations for skipping measurements used for data collection in discontinuous transmission (DTX) according to some embodiments of the present disclosure.

[0036] Figure 8A This is a diagram illustrating an example of time-domain prediction according to some embodiments of the present disclosure.

[0037] Figure 8B This is a block diagram depicting example operations for skipping measurements for data collection in a resource measurement window according to some embodiments of the present disclosure.

[0038] Figure 9A and Figure 9B This is a diagram depicting a table illustrating values ​​for reporting measurement results and skipped measurement results according to some embodiments of the present disclosure.

[0039] Figure 10 This is a block diagram of an electronic device in a network environment according to some embodiments of the present disclosure.

[0040] Figure 11 This is a flowchart depicting example operations of a method for data collection according to some embodiments of the present disclosure. Detailed Implementation

[0041] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of this disclosure. However, those skilled in the art will understand that various aspects of the disclosure may be practiced without these specific details. In other instances, well-known methods, processes, components, and circuits have not been described in detail so as not to obscure the subject matter of this disclosure.

[0042] Throughout this specification, references to “an embodiment” or “an embodiment” mean that a particular feature, structure, or characteristic described in connection with that embodiment may be included in at least one embodiment disclosed herein. Therefore, the phrases “in an embodiment,” “in an embodiment,” or “according to an embodiment” (or other phrases with similar meanings) appearing in various places throughout this specification may not necessarily refer to the same embodiment. Furthermore, particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In this regard, as used herein, the word “exemplary” means “serving as an example, instance, or illustration.” Any embodiment described herein as “exemplary” should not be construed as necessarily preferred or advantageous over other embodiments. Additionally, particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Furthermore, depending on the context discussed herein, singular terms may include corresponding plural forms, and plural terms may include corresponding singular forms.

[0043] It should also be noted that the various figures shown and discussed herein (including component illustrations) are for illustrative purposes only and are not drawn to scale. For example, the dimensions of some components may be exaggerated relative to others for clarity. Furthermore, reference numerals are repeated in the figures where appropriate to indicate corresponding and / or similar components.

[0044] The terminology used herein is for the purpose of describing some exemplary embodiments only and is not intended to limit the claimed subject matter. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. It will also be understood that when the term "comprising" is used in this specification, it specifies the presence of the stated feature, integer, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0045] It should be understood that when an element or layer is referred to as being on, "connected to," or "bonded to" another element or layer, the element may be directly on, directly connected to, or bonded to the other element or layer, or there may be intermediate elements or layers. Conversely, when an element is referred to as being "directly" on, "directly connected to," or "directly bonded to" another element or layer, there are no intermediate elements or layers. Similar reference numerals always refer to similar elements. As used herein, the terms "and" and "and / or" include any one and all combinations of one or more of the associated listed items.

[0046] As used herein, the terms “first,” “second,” etc., serve as labels for the nouns that follow them and do not imply any kind of ordering (e.g., spatial, temporal, logical, etc.) unless explicitly defined as such. Furthermore, the same reference numerals may be used in two or more figures to refer to parts, components, blocks, circuits, units, or modules having the same or similar functions. However, this usage is merely for simplicity of description and ease of discussion; it does not imply that the construction or architectural details of such components or units are identical in all embodiments, or that such commonly referenced parts / modules are the only way to implement some of the exemplary embodiments disclosed herein.

[0047] Each of the terms “processing circuit” and “means for processing” is used herein to refer to any suitable combination of hardware, firmware, and software for processing data or digital signals. Processing circuit hardware may include, for example, application-specific integrated circuits (ASICs), general-purpose or special-purpose central processing units (CPUs), digital signal processors (DSPs), graphics processing units (GPUs), and programmable logic devices (such as field-programmable gate arrays (FPGAs)). In processing circuitry, as used herein, each function is performed by hardware configured (i.e., hardwired) to perform that function, or by more general-purpose hardware (such as a CPU) configured to run instructions stored in a non-transitory storage medium. Processing circuitry may be fabricated on a single printed circuit board (PCB) or distributed across several interconnected PCBs. Processing circuitry may include other processing circuitry; for example, processing circuitry may include two processing circuits, an FPGA and a CPU, interconnected on a PCB.

[0048] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this subject pertains. It will also be understood that terms such as those defined in common dictionaries shall be interpreted as having a meaning consistent with their meaning in the context of the relevant field and shall not be interpreted in an idealized or overly formal sense unless expressly defined herein.

[0049] As used herein, the term "module" refers to any combination of software, firmware, and / or hardware configured to provide the functionality described herein in conjunction with modules. For example, software may be implemented as a software package, code, and / or instruction set or instructions, and the term "hardware" as used in any implementation described herein may include, for example, components, hardwired circuitry, programmable circuitry, state machine circuitry, and / or firmware storing instructions executed by programmable circuitry, either individually or in any combination. Modules may be implemented collectively or individually as part of a larger system of circuitry, such as, but not limited to, integrated circuits (ICs), system-on-a-chip (SoCs), components, etc.

[0050] As mentioned above, in the field of communications, beam management (BM) can be performed in a communication system to predict the optimal beam for a user equipment (UE) to communicate with the network. For example, the optimal beam can be determined based on predicted or measured signal strength, signal-to-interference-plus-noise ratio, channel conditions, interference, etc. In some systems, artificial intelligence / machine learning (AI / ML) models can be used to predict the optimal beam. For example, network nodes may include network (NW) side models trained based on collected data (e.g., NWAI / ML models) to predict the optimal beam for a given UE.

[0051] To train an NW-side model for beam management use cases, the NW can configure a given UE to collect data for training. For example, a network node can configure the UE to perform measurements of Channel State Information Reference Signal (CSI-RS) resources and record the measurements to collect data for AI / ML training on the NW-side model. The recorded measurements can be sent once the NW (e.g., the network node) requests a report using an on-demand request (e.g., by sending). For example, the UE can be configured to periodically record measurements based on CSI-RS resources (e.g., based on periodic resources), store the measurements in a log (e.g., a list, table, etc.), and send one or more of the logs or measurements to the NW (e.g., to the network node) upon request. The NW can use the logs (e.g., using data from the logs) to train an AI / ML model for beam prediction.

[0052] For beam management prediction use cases, one or more CSI resource sets can be configured by the NW for measurement configuration. Based on a given model algorithm on the NW side, different measurement results can be recorded according to the NW reporting configuration.

[0053] Aspects of some embodiments of this disclosure provide improved systems and methods for performing data collection for training AI / ML models for beam management. However, embodiments of this disclosure are not limited thereto, and aspects of some embodiments of this disclosure are generally applicable to other use cases that provide the use of periodic measurements / recordings to perform measurements for data collection and report the recorded measurement results to an NW or other entity (e.g., a server).

[0054] Various aspects of embodiments of this disclosure provide improvements in beam management through coordinated measurement skipping and reporting, thereby relatively improving UE performance and beam prediction.

[0055] In some embodiments, the UE can efficiently handle resource measurements based on some resource and bandwidth portion (BWP) switching correspondence (e.g., consistency).

[0056] In some embodiments, the UE can efficiently process resource measurements based on a set of resources corresponding to measurement gaps.

[0057] In some embodiments, the UE can efficiently process resource measurements based on some resources corresponding to discontinuous reception (DRX) operations.

[0058] In some embodiments, the UE can efficiently process resource measurements based on the correspondence between some resources and the activation / deactivation of secondary cells (SCells).

[0059] In some embodiments, the UE can efficiently process resource measurements based on some resource measurement time corresponding to discontinuous transmission (DTX) operations.

[0060] In some embodiments, the UE can efficiently process resource measurements based on a resource window corresponding to some resources.

[0061] In some embodiments, the UE can efficiently process resource measurement reports based on the fact that some resource measurements are skipped (e.g., not performed).

[0062] Figure 1A This is a block diagram depicting a system 1 comprising a UE 105 and a network node 110 (e.g., a network-side gNodeB (gNB), an Operation and Management Entity (OAM), etc.) for processing resource measurements for data collection according to some embodiments of the present disclosure.

[0063] Reference Figure 1A UE 105 may be able to receive DL transmission 10 from network node 110 and may be able to send UL transmission 20 to network node 110. UE 105 may include radio device 115 and means for processing. The means for processing may include processing circuitry 120, which may perform the various methods disclosed herein. UE 105 may correspond to electronic device 1001 (see...). Figure 10 Radio device 115 may correspond to communication module 1090 (see...). Figure 10 Processing circuitry 120 may correspond to processor 1020 (see...). Figure 10 As used herein, the term "UE" is broadly used to refer to electronic communication devices. For example, a UE may include computers, mobile phones, tablets, vehicles, satellites, IoT devices, etc.

[0064] In some embodiments, an AI / ML model 50 in system 1 (e.g., in network node 110) may be trained based on data received from UE 105. For example, the AI / ML model 50 may be trained based on data from UE 105 to predict the optimal beam for performing communication with UE 105. In some embodiments, network node 110 may periodically request data measurements from UE 105. In some embodiments, UE 105 may be configured to perform measurements on periodic resources (e.g., Channel State Information Reference Signal (CSI RS) resources), record the measurement results, and send the measurement results to network node 110. For example, UE 105 may store the measurement results over time and send multiple measurement results together to network node 110 (e.g., in a list or table). The measurement results may then be used to train the AI / ML model 50 for beam management.

[0065] Figure 1B This describes some embodiments according to the present disclosure. Figure 1A A block diagram of an example operation performed by AI / ML model 50 in System 1 for beam management.

[0066] In beam management, two scenarios (e.g., two sub-scenarios) are supported: (i) BM-Case 1: Spatial downlink beam prediction for beam set A based on measurement results of beam set B; and (ii) BM-Case 2: Temporal downlink beam prediction for beam set A based on historical measurement results of beam set B. Both NW-side and UE-side models can be used for beam management. As used herein, an NW-side model refers to a model located on the NW side (e.g., in network node 110). The NW-side model can be trained by the NW and used by the NW to perform inference (e.g., perform beam prediction). As used herein, a UE-side model refers to a model located on the UE side (e.g., in a device or UE server). The UE-side model can be trained by UE 105 and used by UE 105 to perform inference. Using the UE-side model, UE 105 can report prediction results to the NW based on the output of the UE-side model. Using the NW-side model, the NW can predict one or more of the top-performing beams (e.g., the top 1 / N beams) based on measurements of the reported set B. In summary, the AI / ML model 50 can receive the following as input: (a) measurements based on beam set B (for BM-case 1) or (b) measurements based on beam set B at historical time instances (for BM-case 2) (Operation 1001). The AI / ML model 50 can output (e.g., infer) the probability that each beam in set A is the top-performing beam (e.g., the best beam) from the predicted Layer 1 (L1) Reference Signal Received Power (RSRP) measurements (Operation 1002). Based on the output of the AI / ML model 50, system 1 (e.g., UE 105 or network node 110) can obtain the top 1 / N beams in beam set A (Operation 1003).

[0067] Although this application focuses primarily on the NW-side model, it should be understood that this disclosure is not limited thereto, and aspects of some embodiments of this disclosure may provide improvements to both the UE-side model and the NW-side model.

[0068] In some embodiments, UE 105 may be configured to perform periodic measurements (e.g., RSRP). Periodic measurements may be interrupted due to conflicting conditions such as existing UE operations (e.g., BWP handover, measurement gaps, DRX operations, SCell activation / deactivation, DTX operations, and resource windows). Aspects of some embodiments of this disclosure define UE behavior when a given conflicting condition (e.g., a given conflicting UE operation) occurs.

[0069] Figure 2 This is a block diagram illustrating example operations of a data collection process for a network-side AI / ML model according to some embodiments of the present disclosure.

[0070] Reference Figure 2To train the AI / ML model 50, the NW (e.g., network node 110) can collect data. The entity used for data collection can be a gNB or OAM. For specific data, the NW can also be configured to collect data from the UE 105.

[0071] In some embodiments, because multiple measurements can be collected over a specific period of time, a measurement framework similar to the Minimum Driven Test (MDT) framework can be utilized. For example, UE 105 may store a dataset of measurements that are recorded (e.g., recorded L1 measurements) and may report multiple instances of the recorded measurements to the NW upon request. Because multiple instances of data can be reported, Radio Resource Control (RRC) signaling may be more desirable than other types of signaling (e.g., L1 signaling, Media Access Control (MAC) Control Element (CE) signaling, etc.). That is, in some embodiments, the NW may use RRC signaling to request recorded measurements.

[0072] In some embodiments, the entire process supporting UE data collection for NW-side model training may include one or more of the following operations. As a basic process, UE 105 may receive a measurement configuration for enabling AI / ML functions / function groups (FGs) for data collection and measurement recording. As used herein, measurement recording may refer to UE 105 performing measurements in multiple instances (e.g., at different times) and storing the measurement results in UE 105's memory until UE 105 reaches its memory size limit or until UE 105 reports the recorded measurement results to network node 110 (e.g., gNB) upon request. In some embodiments, network node 110 configures (e.g., explicitly configures) UE 105 to begin (e.g., immediately begin) corresponding data collection and recording (if supported). In some embodiments, UE 105 stores the recorded training data at the AS layer with the minimum access stratum (AS) layer memory size supported by UE 105. If UE 105 reaches its buffer limit, UE 105 may stop performing measurements for data collection purposes and may stop recording.

[0073] In some embodiments, periodic measurement recording can be supported for the training data collection process once network node 110 (e.g., gNB) provides resources and reporting configuration. In some embodiments, system 1 can perform (e.g., specify) on-demand reporting of recorded measurement results. In some embodiments, periodic reporting of recorded data may not be supported due to a large number of results that may not be immediately utilized (e.g., a large amount of measurement result data). In some embodiments, request messages (e.g., RRC request messages, such as UEInformationRequest) and / or response messages (e.g., RRC response messages, such as UEInformationResponse) can be used for on-demand reporting of AI / ML training data collection.

[0074] In some embodiments, network node 110 may send configuration information to UE 105 (operation 2001). For example, the configuration information may include RRC reconfiguration data for data collection configuration. UE 105 may perform a first measurement for data collection (e.g., RSRP_1) (operation 2002). As discussed in further detail below, in some embodiments, based on the occurrence of a conflict condition (e.g., conflict function CF) of UE 105, UE 105 may skip (e.g., may be configured not to perform) one or more measurements for data collection (operation 2003X). UE 105 may perform an nth measurement for data collection (e.g., RSRP_n) (operation 2004). Network node 110 may send a request message (e.g., UEInformationRequest) to request a report from UE 105 (operation 2005). UE 105 may send a response message (e.g., UEInformationResponse) to report the recorded measurement results (operation 2006). See below for reference. Figure 9A and Figure 9B As discussed in further detail, in some embodiments, UE 105 may send: Measurement Result Data (MRD) (e.g., an AI / ML dataset), wherein the Measurement Result Data MRD includes data indicating the results of a first measurement (e.g., RSRP_1), an nth measurement (e.g., RSRP_n), and one or more intermediate measurements (e.g., RSRP_2) occurring between the first and nth measurements; and data indicating which measurements (e.g., RSRP_3 and RSRP_4) were skipped. In some embodiments, the Measurement Result Data MRD may include data indicating why each of the skipped measurements was skipped.

[0075] In some embodiments, a given request message may include (e.g., may contain) one or more recorded measurement entries in chronological order (e.g., starting from the earliest measurement entry stored in the memory of UE 105). In some embodiments, the given request message may include an availability indication if data also exists that can be used for transmission. For example, UE 105 may measure the RSRP of a CSI resource. UE 105 may store log entries including RSRP_1 to RSRP_k of recorded measurement entries, where RSRP_1 was measured at time t1 (on the first CSI resource after configuration data collection), and RSRP_k was measured at time tk. As used herein, given the periodicity of configuring CSI-RS resources, "t1" refers to the first CSI-RS resource timing at configuration, and "tk" refers to the k-th timing.

[0076] In some embodiments, for BM-Case 1, each instance of the report may include one or more of the following three types of content for data collection: Type 1: All L1-RSRPs measured based on resources configured for UE 105 (for set A / B); Type 2: All L1-RSRPs measured based on resources configured for UE 105 (for set B), and beam information of K beams based on some resources configured for UE 105 (for set A); Type 3: All L1-RSRPs measured based on resources configured for UE 105 (for set B), and beam information and L1-RSRPs of K beams based on some resources configured for UE 105 (for set A). For Type 2 and Type 3, the K beams may be the beam with the maximum K L1-RSRPs measured based on resources (for set A) in one instance, where K is configured by NW.

[0077] Figure 3 This is a block diagram depicting example operations for skipping measurements used for data collection during bandwidth portion (BWP) switching, according to some embodiments of the present disclosure.

[0078] Reference Figure 3In a 5G NR system, BWP handover can be used to configure different bandwidths (referred to as BWPs) for a given UE 105. Each BWP may differ from the system bandwidth but may be matched to the bandwidth capabilities of UE 105. Furthermore, when there is little (e.g., when there is no) service activity, BWP handover can be used to save UE power consumption by using a BWP with a smaller bandwidth. In some embodiments, network node 110 (e.g., gNB) can configure up to four dedicated BWPs for UE 105 in connected mode, which may or may not include an initial BWP (e.g., BWP1). During BWP handover, of the up to four BWPs, only one BWP can be active at a given time, and UE 105 can transmit and receive on the active BWP (e.g., only on the active BWP). BWP activation can be indicated via RRC, via downlink control information (DCI), or via a BWP inactivity timer.

[0079] As discussed above, if (for example, when) UE 105 is configured with existing UE functions (e.g., having as referred to) Figure 2 If the UE 105 has both conflicting functions (CF) and data collection, then in the event that the UE 105 cannot perform data recording (e.g., cannot perform measurements for data collection to train AI / ML model 50), the UE 105 may handle conflicting situations (e.g., conflicting functions (CF)) according to various aspects of embodiments of this disclosure.

[0080] In the current CSI resource configuration, a BWP identifier (e.g., BWP-ID) can be indicated to UE 105, and UE 105 can start or stop CSI reporting based on the active BWP. That is, UE 105 can use the BWP identifier to measure CSI only for the active BWP. Therefore, UE 105 can measure only the CSI resources associated with the active BWP.

[0081] Similarly, in some embodiments, data collection logging can be adjusted based on the active BWP, even if there may be no corresponding CSI report. That is, UE 105 can start or stop performing measurements based on the active BWP. If the CSI-RS resource used for data collection to train the AI / ML model 50 is associated with the active BWP, UE 105 can perform measurements for data collection. Otherwise, UE 105 can skip performing measurements for the corresponding CSI-RS resource (set).

[0082] For example, and still refer to Figure 3First resource R1 (e.g., CSI-RS resource) and second resource R2 may correspond to an active second bandwidth portion BWP2 (e.g., may be consistent with an active second bandwidth portion BWP2). Therefore, UE 105 may perform measurements on first resource R1 and second resource R2, wherein first resource R1 and second resource R2 are configured to be associated with AI / ML data collection for data collection on the second bandwidth portion BWP2 (e.g., associated with a second bandwidth portion BWP2 for data collection). That is, if the associated / overlapping BWP is active, the UE may perform / record resource measurements. In contrast, BWP switching may occur after measurements are performed on first resource R1 and second resource R2, causing the second bandwidth portion BWP2 to become inactive (e.g., not active) and the third bandwidth portion BWP3 to become active. Therefore, UE 105 may skip (e.g., may not perform) measurements on the third resource R3 and fourth resource R4 corresponding to the inactive second bandwidth portion BWP2. That is, if the associated / overlapping BWP is not active, the UE may skip the measurements. In some embodiments, resource R may be configured by network node 110 as a periodic resource, such that network node 110 may expect measurements of measurement data associated with each resource R from the UE.

[0083] In some embodiments, based on a given BWP being activated, based on the BWP for the serving cell (e.g., an active downlink (DL) BWP) not being a dormant BWP, and based on the serving cell not being a primary / secondary cell (PSCell) of a deactivated secondary cell group (SCG), UE 105 may perform measurements associated with the BWP configured for AI / ML data collection to perform AI / ML data collection. In some embodiments, if a given activated BWP is active, UE 105 may perform channel state information (CSI) recording. In other words, in some embodiments, based on UE 105 being configured with more than one BWP, and a first BWP among the more than one BWP being activated, UE 105 may perform recording of a first CSI measurement result corresponding to the first BWP associated with a first resource (e.g., a first CSI resource). In some embodiments, based on AI / ML data collection associated with a first BWP (e.g., associated with the first BWP) configured for UE 105, UE 105 can perform a first CSI measurement corresponding to the first BWP and can record (e.g., save) the result of the first CSI measurement (e.g., the first CSI measurement result) as an entry in an AI / ML dataset (e.g., an AI / ML record). In some embodiments, UE 105 can send the first CSI measurement result from UE based on the AI / ML dataset. For example, UE 105 can send the first CSI measurement result to network node 110 (see FIG. 1A). Network node 110 can use the first CSI measurement result to train AI / ML model 50.

[0084] Reference Figure 3 The active DL BWP switches from BWP1 to BWP2 and then to BWP3. BWP activation can be based on a given scheduling policy and channel conditions. A dormant BWP refers to a special BWP that UE 105 does not utilize for monitoring the Physical Downlink Control Channel (PDCCH). UE 105 can be configured with up to four BWPs (configured BWPs), of which only one BWP is active at a time. Active BWPs can be switched dynamically or semi-statically. One of the configured BWPs can be configured as a dormant BWP (e.g., it can be configured as a dormant BWP). If a given BWP is switched to a dormant BWP, UE 105 can stop monitoring the PDCCH to save power. In some embodiments, UE 105 can support dual connectivity configured with a primary cell group (MCG) and a secondary cell group (SCG). That is, UE 105 can be considered connected to two different network nodes 110 (e.g., two different gNBs). Each network node 110 (e.g., each gNB) can be configured with carrier aggregation (CA). Therefore, MCG and SCG can be referred to as cell groups.

[0085] Figure 4This is a block diagram depicting example operations for skipping measurements for data collection due to measurement gap MG, according to some embodiments of the present disclosure.

[0086] Reference Figure 4 Measurement gaps (MGs) can be used to perform radio resource management (RRM) for the handover process, during which UE 105 can perform inter-frequency measurements, intra-frequency measurements, or inter-Radio Access Technology (RAT) measurements. Depending on the capabilities of a given UE 105, UE 105 may not perform intra-frequency / inter-frequency / inter-RAT measurements when transmitting or receiving with the serving cell. To facilitate such measurements by UE 105, network node 110 may introduce one or more measurement gaps (MGs). During a measurement gap (MG), it is anticipated that UE 105 will not transmit or receive signals with the serving cell, but will instead perform measurements. The period or length of the measurement gap can be configured by network node 110 (e.g., by gNB). During a measurement gap (MG), UE 105 may perform measurements on neighboring cells, preventing UE 105 from receiving or transmitting with the serving cell. For example, during an active measurement gap (MG), UE 105 may be configured to suspend transmission and reception to switch radio frequency (RF) or bandwidth in order to perform inter-frequency / inter-RAT or intra-frequency measurements.

[0087] In some embodiments, for data collection used to train the AI / ML model 50, UE 105 may also stop performing measurements and recording measurement results during measurement gaps MG. For example, a first resource R1 for AI / ML data collection may correspond to a first measurement gap MG1 (e.g., may be consistent with the first measurement gap MG1), and a fourth resource R4 for AI / ML data collection may correspond to a second measurement gap MG2. Based on the fact that the first resource R1 and the fourth resource R4 correspond to measurement gaps MG, UE 105 may not perform measurements configured for AI / ML data collection on the first resource R1 and the fourth resource R4. In contrast, because the second resource R2 and the third resource R3 do not correspond to measurement gaps MG, UE 105 may perform measurements for data collection on the second resource R2 and the third resource R3.

[0088] In other words, during an active measurement gap MG, a UE 105 (e.g., a MAC entity) can be configured not to perform measurements configured for AI / ML data collection on one or more serving cells in the corresponding frequency range of the measurement gap MG configured by measGapConfig (as specified in TS 38.331).

[0089] In some embodiments, if a given UE 105 supports two independent measurement gaps (MPs) for New Radio (NR) frequency range 1 (FR1) and frequency range 2 (FR2), the UE 105 can continue to perform measurements and record measurement results for data collection to train the AI / ML model 50 even if the associated serving cell is not part of the measurement gap operation. That is, if the network node 110 (e.g., gNB) configures the FR2 gap, meaning the measurement gap (MG) is applied to the serving cell on the FR2 frequency carrier, the UE 105 can still perform measurements and record data for data collection to train the AI / ML model 50 if the serving cell is on FR1.

[0090] Figure 5A This is a block diagram depicting example operations for skipping measurements used for data collection in discontinuous reception (DRX) according to some embodiments of the present disclosure.

[0091] Reference Figure 5A In NR, Discontinuous Reception (DRX) can be enabled for UE power saving. During DRX operation, UE105 can be configured by NW to activate a wake-up timer (such as a DRX-enabled duration timer). drx-onDurationTimer UE 105 is woken up during each DRX cycle. For example, UE 105 can be woken up while the DRX-On Duration Timer is running. The wake-up time (while the wake-up timer is running) can be referred to as the active time. During the active time, UE 105 can monitor the PDCCH and stop sending some uplink signals (e.g., the Physical Uplink Control Channel (PUCCH)). If PDCCH reception is present, it can be interrupted via an inactive timer IAT (e.g., another DRX timer, such as the DRX-Inactive Timer). Drx- InactivityTimer This extends the active time. In other words, to conserve UE battery power, UE 105 can be configured to sleep and wake based on the wake-up pulse (WP) during DRX operation. Upon waking, UE 105 can monitor the PDCCH to see if any data has been received. When the PDCCH includes data, the inactivity timer (IAT) can extend the wake-up time (e.g., extend the active time).

[0092] In some embodiments, if (e.g., only if) UE 105 is active, then (e.g., configurable by NW) UE 105 may be allowed to perform measurements for data collection. For example, if UE 105 is not active, then UE 105 may skip performing (e.g., may not perform) measurements for data collection.

[0093] For example, and still refer to Figure 5AUE 105 may perform measurements for data collection on the first resource R1, the second resource R2, the fourth resource R4, and the sixth resource R6, because these resources correspond to active time / active operation (also known as wake-up time or wake-up operation) (e.g., consistent with active time / active operation). In such an embodiment, UE 105 may not perform measurements for data collection on the third resource R3 or the fifth resource R5, because these resources correspond to inactive time / inactive operation (also known as sleep time or sleep operation).

[0094] Figure 5B This is a block diagram depicting example operations for skipping measurements for data collection in DRX when the Record Masking (LM) is enabled, according to some embodiments of the present disclosure.

[0095] Figure 5C This is a block diagram depicting example operations for performing measurements for data collection in a DRX during inactive periods, according to some embodiments of the present disclosure.

[0096] In some systems, DRX operation may be more complex (e.g., not simple or efficient) from the perspective of operating UE 105 because the active time may be variable, depending on the reception of the PDCCH in the NR. For example, in DRX operation, if UE 105 is not in an active time, then according to the CSI mask (e.g., csi-Mask The network node 110 (e.g., gNB) configuration may allow CSI reporting to be enabled for durations other than the specified duration (e.g., not limited to the specified duration). drx-onDurationTimer (Running).

[0097] In some embodiments, to account for the variability of activity time, signaling can be used to limit the measurements and recording of measurement results used for data collection to train the AI / ML model 50 during DRX operations.

[0098] For example, and refer to Figure 5B In some embodiments, signaling (e.g., one-bit signaling, such as...) logging- Mask ) can be used to indicate when a wake-up timer (such as drx-onDurationTimer Can measurements be skipped when they expire? How can this signaling be used in conjunction with existing CSI reports? csi-Mask Same or similar. For example, if NW is configured with a record mask LM (e.g., logging-Mask ), then UE 105 can only wake up the timer (e.g., drx-onDurationTimer While running, UE 105 performs measurements and records measurement results for data collection to train AI / ML model 50. Otherwise, whenever UE 105 is able to perform measurements (e.g., if UE 105 is in an active period, as referenced...) Figure 5A(As discussed), UE 105 can perform measurements. For example, with reference above... Figure 5A The methods for measuring the second resource R2 discussed differ. In some embodiments, the measurement of the second resource R2 may be skipped (e.g., not performed) because the second resource R2 corresponds to a recording mask LM configured to correspond to an inactive timer IAT (e.g., consistent with a recording mask LM configured to correspond to an inactive timer IAT). For example, the recording mask LM may begin at the end of the wake-up pulse WP and extend to the end of the inactive timer IAT.

[0099] Reference Figure 5C In some embodiments, signaling (e.g., one-bit signaling, such as...) can be used. logging- InActive This indicates whether measurements can be skipped when UE 105 is not in an active period. For example, if NW configures an inactive recording state for UE 105 (e.g., ... logging-InActive If UE 105 is not active, then UE 105 can perform measurements and measurement result recording for data collection, regardless of whether UE 105 is active. Otherwise, if UE 105 is not active, UE 105 may be allowed to skip measurements and measurement result recording for data collection to train AI / ML model 50, as referred to Figure 5A and Figure 5B This is under discussion. In this embodiment where an inactive recording state is configured, UE power savings may be reduced, but the inactive recording state enables data collection with reduced interruptions (e.g., minimal interruptions). For example, referring to the above... Figure 5A and Figure 5B The method discussed for skipping the measurement of the third resource R3 and the fifth resource R5 differs from that mentioned above. Figure 5B The methods for skipping the measurement of the second resource R2 discussed differ. In some embodiments, UE 105 may perform measurements of the second resource R2, the third resource R3, and the fifth resource R5 because network node 110 has configured UE 105 to measure during active periods and wake up during inactive periods to perform measurements and recordings for data collection.

[0100] Figure 6 This is a block diagram depicting a system 1' according to some embodiments of the present disclosure for skipping measurements for data collection when secondary cell (SCell) 110b is deactivated.

[0101] Reference Figure 6If CA is supported, network node 110 (e.g., gNB) can activate and deactivate SCell 110b based on service conditions or channel conditions. If NW deactivates SCell 110b, UE 105 can stop some operations associated with the SCell, including stopping the reception of downlink signaling.

[0102] In some embodiments, to conform to the state of SCell 110b, UE 105 may suspend resource measurements (e.g., CSI-RS resources) and measurement result recording for training AI / ML model 50 based on the deactivation of SCell 110b. That is, UE 105 may not perform CSI recording for SCell 110b based on the deactivation of SCell 110b. For example, network node 110 may deactivate SCell 110b, resulting in no operation on component carriers used for carrier aggregation (e.g., the second component carrier CC2 associated with the second frequency f2). UE 105 may be configured to not perform measurements when SCell 110b is deactivated and to perform measurements when SCell 110b is activated.

[0103] Figure 7 This is a block diagram depicting example operations for skipping measurements used for data collection in discontinuous transmission (DTX) according to some embodiments of the present disclosure.

[0104] Reference Figure 7 In some systems, DTX (e.g., cell DTX) can be used to save power consumption on the NW side. In some embodiments, cell DTX operation controls the downlink allocation of the UE's monitoring and configuration of the PDCCH (e.g., under RRC_CONNECTED). Activation or deactivation of cell DTX operation can be achieved through lower-layer signaling or RRC configuration of related parameters (e.g., cellDTX- DRX-Cycle / cellDTX-DRX-onDurationTimer The UE 105 can determine this by monitoring network node 110 (e.g., gNB) to enable downlink signal transmission via PDCCH if the serving cell is in the cell DTX active period (AP). If the UE 105 is in the cell DTX inactive period (IAP), the UE 105 can stop monitoring network node 110 (e.g., gNB) to disable downlink signal transmission via PDCCH. In other words, during DTX, network node 110 may not transmit signals during the inactive period (IAP).

[0105] During cell DTX operation, network node 110 (e.g., gNB) may not transmit downlink signals including resources (e.g., CSI resources) during the cell DTX inactive period IAP. In some embodiments, to avoid incorrect measurements when network node 110 does not transmit downlink signals, UE 105 may (e.g., by network node 110) be configured to perform measurement result recording only when network node 110 transmits resources (e.g., CSI resources) during the active period AP.

[0106] For example, network node 110 may instruct whether to disable CSI resources for data collection during one or more cell DTX inactive period IAPs. If network node 110 stops transmitting CSI resources during cell DTX inactive period IAPs, UE 105 may stop performing measurements and recording of measurement results for data collection to train AI / ML model 50 if the corresponding serving cell is not in cell DTX active period APs. For example, for each serving cell configured with cell DTX, if cell DTX operation is activated and the serving cell is not in cell DTX active period APs, the MAC entity (e.g., UE 105) may be configured not to perform measurements for CSI resources for data collection. In other words, in some embodiments, UE 105 may not perform measurements for data collection during inactive period IAPs during DTXs, and UE 105 may perform measurements for data collection during active period APs. For example, UE 105 may not perform measurements at a time tx (e.g., resource measurement time tx) corresponding to (e.g., consistent with) the inactive period IAP.

[0107] Figure 8A This is a diagram illustrating an example of time-domain prediction according to some embodiments of the present disclosure.

[0108] Figure 8B This is a block diagram depicting example operations for skipping measurements for data collection in a resource measurement window according to some embodiments of the present disclosure.

[0109] Reference Figure 8A In some embodiments, in beam management scenario 2 (also known as BM-scenario 2 or time-domain downlink beam prediction), one or more beams can be predicted for multiple future time instances based on beam measurements taken in the past at multiple time instances. For example, a first number Mt RSs may be referred to as set B (e.g., input data), and the prediction results for Pt time instances may be referred to as set A (e.g., inference results).

[0110] For time-domain prediction, different models (e.g., different AI / ML models 50) can be trained based on different sets A and B pairs. Therefore, in some embodiments, network node 110 (e.g., gNB) can request UE 105 to collect data based on (e.g., assumed) specific pairs (e.g., specific sets A and B pairs), such that UE 105 provides measurement results in units of sets A and B. In some embodiments, to define the units of sets A and B, a measurement window MW (also referred to as a resource measurement window or resource window) can be used for measurement. In some embodiments, a given measurement window may include one or more windows. For example, more than one window can be used when sets A and B are different (e.g., when two resource instance sets are not adjacent to each other). For resources R1, R2, and R3 associated with set B and used to predict resources in set A, the measurement window MW may have an Mt value of 3. For example, set A may have a Pt value of 2 for prediction results for resources R4 and R5. The measurement window MW may also have a time period Tper that indicates the amount of time from the last resource in set B to the first prediction result (e.g., for resource R4).

[0111] In some embodiments, when configuring a measurement window (MW), a skipping rule may be followed to avoid sending redundant data. For example, because network node 110 (e.g., gNB) may not use measurement results if not all measurement results within the window are available, UE 105 may skip the entire window instead of just skipping each measurement opportunity.

[0112] For example, and refer to Figure 8B In the DRX scenario, a measurement window MW can be defined as having two measurement instances as a window length WL. UE 105 can skip all measurements within each measurement window MW that has one or more measurements configured to be skipped based on another rule (e.g., based on the method discussed above). For example, UE 105 can be configured to skip the measurement of the third resource R3 at t3 and the measurement of the fifth resource R5 at t5 based on the fact that the third resource R3 and the fifth resource R5 correspond to inactive periods (e.g., consistent). In some embodiments, UE 105 can also skip the measurement of the fourth resource R4 at t4 based on the fact that the fourth resource R4 at t4 corresponds to the same measurement window MW (e.g., MW2) as the third resource R3 skipped at t3. UE 105 can also skip the measurement of the sixth resource R6 at t6 based on the fact that the sixth resource R6 at t6 corresponds to the same measurement window MW (e.g., MW3) as the fifth resource R5 skipped at t5.

[0113] In other words, in some embodiments, if an opportunity for a measurement used for data collection is not available during the active time, UE 105 may skip all measurements for all resources R in a given measurement window MW, because if the entire group of resources R within a given measurement window MW is unavailable, the measurement would be useless.

[0114] Figure 9A and Figure 9B This is a diagram depicting a table illustrating values ​​for reporting measurement results and skipped measurement results according to some embodiments of the present disclosure.

[0115] Reference Figure 9A and Figure 9B Because data collection can be used for model training on the NW side, AI / ML model 50 can be improved by providing the NW with information (e.g., accuracy information) instructing the UE 105 whether (e.g., when) to skip measurements and measurement result recordings used for data collection. Figure 1A The training quality of the network node 110 may be affected by the UE 105 providing measurements taken in multiple time instances in chronological order. Therefore, if there is no additional information provided by the UE 105 indicating that measurements have been skipped, model training may be negatively impacted by training on a corrupted dataset.

[0116] In some embodiments, to avoid negatively impacting the training of the AI / ML model 50, the measurement result data MRD (see Figure 2 The field in the measurement result field is reserved for missing values. Figure 9A and Figure 9B One of the measurements listed in the table (e.g., in place of missing measurements) indicates one or more skipped measurements and measurement result records used for data collection to train the AI / ML model 50.

[0117] The L1 synchronization signal RSRP (SS-RSRP) and CSI-RSRP reporting range can be defined as -140 to -40 dBm (dB-mW), with a resolution of 1 dB. According to TS38.133, only reporting values ​​from RSRP_18 to RSRP_113 may be used. In some embodiments, reserved bits (e.g., RSRP_0 or RSRP_127) may be defined to indicate that a given measurement result is unavailable due to skipped measurements. Therefore, in some embodiments, the Measurement Result Data (MRD) may include reporting values ​​(e.g., RSRP_18 to RSRP_113) for measurements performed for data collection, and may include reporting values ​​RSRP_0 or RSRP_127 for skipped measurements.

[0118] In some embodiments, UE 105 may transmit Measurement Result Data (MRD) including time information indicating that a measurement skip has occurred. In some situations (e.g., BWP handover, SCell deactivation, or DRX operation), UE 105 may skip measurements used for data collection for an extended period. However, if a skip occurs for an extended period, indicating a skip using reserved bits (e.g., RSRP_0 or RSRP_127) as discussed above may not be suitable or efficient in terms of signaling overhead. Therefore, instead of using reserved bits to indicate a skip, in some embodiments, UE 105 may indicate time information indicating whether a measurement has been skipped or started.

[0119] For example, in some embodiments, the measurement result data MRD may indicate a start time and an end time, which indicate when a measurement was skipped. For example, an absolute time encoded in YY-MM-DD HH:MM:SS format (e.g., indicating year-month-day hour:minute:second) and using binary-coded decimal (BCD) may be used to provide the start and end times. In some embodiments, to reduce signaling overhead (e.g., because a 48-bit BCD can be used to encode YY-MM-DD HH:MM:SS according to the current RRC signaling), relative time information may be used instead of absolute time information. For example, a reference to the relative time may be reported by UE 105, or indicated by network node 110 (e.g., gNB), or defined as the time when UE 105 receives the RRC reconfiguration message or the time of the first CSI-RS resource after receiving the RRC reconfiguration message.

[0120] In some embodiments, the Measurement Result Data (MRD) may indicate the start time of each measurement. In some embodiments, because measurements are performed periodically with a configured cycle, the NW can estimate how many measurements were skipped by using two consecutive start times and the number of measurements performed in the time instance. For example, in some embodiments, the relative time may be indicated by the system frame number (SFN) and the number of time slots (e.g., n time slots) counted after the first CSI-RS resource opportunity in the time domain upon reconfiguration. Alternatively, in some embodiments, the relative time may be defined as the number of CSI-RS resource opportunities (e.g., n times) after the first CSI-RS resource opportunity in the time domain upon reconfiguration.

[0121] As discussed above, if UE 105 indicates to skip measurements for data collection, UE 105 may also indicate the reason for skipping the measurements, because the NW may not track (e.g., may not track accurately) the state of UE 105. In some embodiments, in addition to conflict events (e.g., conflicting functions CF) discussed above, UE 105 may skip measurements for data collection for several other reasons. One situation may be when recording based on Layer 3 (L3) events is applied. In some embodiments, L3 can be used for switching measurements. If the NW enables L3 event-based recording, UE 105 may stop measurements for data collection if the serving cell quality is better than or worse than a threshold. Another situation may be when UE 105 is allowed to stop recording due to its internal state (e.g., full memory or low UE power). For example, UE 105 may stop recording based on the UE's memory reaching a maximum storage threshold or the UE 105's power level reaching a minimum UE power level threshold. In some embodiments, UE 105 may indicate the reason for skipping measurements based on a code representing each reason.

[0122] Figure 10 This is a block diagram of an electronic device 1001 in a network environment 1000 according to some embodiments of the present disclosure.

[0123] Reference Figure 10 In network environment 1000, electronic device 1001 (e.g., UE) can communicate with electronic device 1002 via a first network 1098 (e.g., a short-range wireless communication network), or with electronic device 1004 or server 1008 via a second network 1099 (e.g., a long-range wireless communication network). Electronic device 1001 can communicate with electronic device 1004 via server 1008. Electronic device 1001 may include processor 1020, memory 1030, input device 1050, sound output device 1055, display device 1060, audio module 1070, sensor module 1076, interface 1077, connection terminal 1078, haptic module 1079, camera module 1080, power management module 1088, battery 1089, communication module 1090, user identification module (SIM) 1096, or antenna module 1097. In one embodiment, at least one of the aforementioned components (e.g., display device 1060 or camera module 1080) may be omitted from electronic device 1001, or one or more other components may be added to electronic device 1001. Some of the aforementioned components may be implemented as a single integrated circuit (IC). For example, sensor module 1076 (e.g., fingerprint sensor, iris sensor, or illuminance sensor) may be embedded in display device 1060 (e.g., display).

[0124] The processor 1020 can run software (e.g., program 1040) to control at least one other component (e.g., hardware or software component) of the electronic device 1001 combined with the processor 1020, and can perform various data processing or calculations.

[0125] As at least part of the data processing or computation, processor 1020 may store commands or data received from another component (e.g., sensor module 1076 or communication module 1090) in volatile memory 1032, process the commands or data stored in volatile memory 1032, and store the result data in non-volatile memory 1034. Processor 1020 may include a main processor 1021 (e.g., a central processing unit (CPU) or application processor (AP)) and an auxiliary processor 1023 (e.g., a graphics processing unit (GPU), image signal processor (ISP), sensor hub processor, or communication processor (CP)) that is operationally independent of or combined with the main processor 1021. Additionally or optionally, auxiliary processor 1023 may be adapted to consume less power than the main processor 1021 or to perform specific functions. Auxiliary processor 1023 may be implemented separately from the main processor 1021 or as part of the main processor 1021.

[0126] When the main processor 1021 is inactive (e.g., in sleep mode), the auxiliary processor 1023 (not the main processor 1021) can control at least some of the functions or states associated with at least one component of the electronic device 1001 (e.g., display device 1060, sensor module 1076, or communication module 1090). Alternatively, when the main processor 1021 is active (e.g., running an application), the auxiliary processor 1023 can work with the main processor 1021 to control at least some of the functions or states associated with at least one component of the electronic device 1001 (e.g., display device 1060, sensor module 1076, or communication module 1090). The auxiliary processor 1023 (e.g., an image signal processor or a communication processor) can be implemented as part of another component (e.g., camera module 1080 or communication module 1090) that is functionally associated with the auxiliary processor 1023.

[0127] Memory 1030 may store various data used by at least one component of electronic device 1001 (e.g., processor 1020 or sensor module 1076). The various data may include, for example, software (e.g., program 1040) and input or output data for commands associated with it. Memory 1030 may include volatile memory 1032 or non-volatile memory 1034. Non-volatile memory 1034 may include internal memory 1036 and / or external memory 1038.

[0128] The program 1040 may be stored as software in the memory 1030, and the program 1040 may include, for example, an operating system (OS) 1042, middleware 1044, or application 1046.

[0129] Input device 1050 can receive commands or data from outside electronic device 1001 (e.g., a user) that will be used by other components of electronic device 1001 (e.g., processor 1020). Input device 1050 may include, for example, a microphone, mouse, or keyboard.

[0130] The sound output device 1055 can output sound signals to the outside of the electronic device 1001. The sound output device 1055 may include, for example, a speaker or a receiver. The speaker can be used for general purposes such as playing multimedia or playing records, and the receiver can be used to receive incoming calls. The receiver can be implemented separately from the speaker or as part of the speaker.

[0131] Display device 1060 can visually provide information to the outside of electronic device 1001 (e.g., to a user). Display device 1060 may include, for example, a display, a holographic device, or a projector, and control circuitry for controlling a respective one of the display, holographic device, and projector. Display device 1060 may include touch circuitry adapted to detect touch or sensor circuitry (e.g., a pressure sensor) adapted to measure the intensity of the force generated by the touch.

[0132] The audio module 1070 can convert sound into electrical signals and vice versa. The audio module 1070 can obtain sound via the input device 1050, or output sound via the sound output device 1055 or headphones of the external electronic device 1002 that is directly (e.g., wired) or wirelessly connected to the electronic device 1001.

[0133] Sensor module 1076 can detect the operating state of electronic device 1001 (e.g., power or temperature) or the environmental state outside electronic device 1001 (e.g., user state), and then generate an electrical signal or data value corresponding to the detected state. Sensor module 1076 may include, for example, a gesture sensor, gyroscope sensor, atmospheric pressure sensor, magnetic sensor, accelerometer, grip sensor, proximity sensor, color sensor, infrared (IR) sensor, biometric sensor, temperature sensor, humidity sensor, or illuminance sensor.

[0134] Interface 1077 may support one or more specific protocols used to enable electronic device 1001 to be directly (e.g., wired) or wirelessly connected to external electronic device 1002. Interface 1077 may include, for example, a High Definition Multimedia Interface (HDMI), a Universal Serial Bus (USB) interface, a Secure Digital Card (SD) interface, or an audio interface.

[0135] Connection end 1078 may include a connector, through which electronic device 1001 can be physically connected to external electronic device 1002. Connection end 1078 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0136] The haptic module 1079 can convert electrical signals into mechanical stimuli (e.g., vibration or motion) or electrical stimuli that can be recognized by a user through his touch or kinesthesia. The haptic module 1079 may include, for example, a motor, a piezoelectric element, or an electrical stimulator.

[0137] Camera module 1080 can capture still or moving images. Camera module 1080 may include one or more lenses, an image sensor, an image signal processor, or a flash. Power management module 1088 manages the power supply to electronic device 1001. Power management module 1088 may be implemented as at least part of, for example, a power management integrated circuit (PMIC).

[0138] Battery 1089 may power at least one component of electronic device 1001. Battery 1089 may include, for example, a non-rechargeable primary battery, a rechargeable accumulator, or a fuel cell.

[0139] Communication module 1090 can support the establishment of a direct (e.g., wired) or wireless communication channel between electronic device 1001 and external electronic devices (e.g., electronic device 1002, electronic device 1004, or server 1008), and perform communication via the established communication channel. Communication module 1090 may include one or more communication processors operating independently of processor 1020 (e.g., AP), and support direct (e.g., wired) or wireless communication. Communication module 1090 may include wireless communication module 1092 (e.g., cellular communication module, short-range wireless communication module, or Global Navigation Satellite System (GNSS) communication module) or wired communication module 1094 (e.g., local area network (LAN) communication module or power line communication (PLC) module). A corresponding one of these communication modules can communicate via a first network 1098 (e.g., a short-range communication network, such as Bluetooth). TMThe wireless communication module 1092 communicates with external electronic devices via a second network 1099 (e.g., a long-range communication network, such as a traditional cellular network, the Internet, or a computer network (e.g., a LAN or a wide area network (WAN)) or a Wi-Fi Direct or Infrared Data Association (IrDA) standard. These various types of communication modules can be implemented as a single component (e.g., a single IC) or as multiple components separate from each other (e.g., multiple ICs). The wireless communication module 1092 can use user information (e.g., an International Mobile Subscriber Identity (IMSI)) stored in the SIM 1096 to identify or verify the electronic device 1001 in a communication network (such as a first network 1098 or a second network 1099).

[0140] Antenna module 1097 can transmit or receive signals or power to or from the outside of electronic device 1001 (e.g., external electronic device). Antenna module 1097 may include one or more antennas, and in this case, at least one antenna suitable for a communication scheme used in a communication network (such as first network 1098 or second network 1099) can be selected, for example, by communication module 1090 (e.g., wireless communication module 1092). Signals or power can then be transmitted or received between communication module 1090 and external electronic device via the selected at least one antenna.

[0141] Instructions or data can be sent or received between electronic device 1001 and external electronic device 1004 via server 1008 connected to the second network 1099. Each of electronic device 1002 and electronic device 1004 can be a device of the same type as electronic device 1001, or a device of a different type. All or some operations of the operation performed on electronic device 1001 can be performed on one or more of external electronic devices 1002, external electronic device 1004, or server 1008. For example, if electronic device 1001 is required to automatically perform a function or service, or is required to perform a function or service in response to a request from a user or another device, electronic device 1001 may request the one or more external electronic devices to perform at least a portion of the function or service instead of running the function or service, or electronic device 1001 may request the one or more external electronic devices to perform at least a portion of the function or service in addition to running the function or service. Upon receiving the request, the one or more external electronic devices may perform at least a portion of the requested function or service, or perform additional functions or services related to the request, and send the result of the execution to electronic device 1001. Electronic device 1001 may provide the result as at least a partial response to the request, either with further processing or without further processing. For this purpose, technologies such as cloud computing, distributed computing, or client-server computing may be used.

[0142] As discussed above, processing circuit 120 (see...) Figure 1A It can perform the various methods disclosed herein and can correspond to the above references. Figure 10 The processor 1020 is discussed. For example, processor 1020 can execute method 11000, which is referred to below. Figure 11 Further details to be discussed. Radio equipment 115 (see...) Figure 1A This can correspond to communication module 1090 (see...) Figure 10 ).

[0143] Figure 11 This is a flowchart depicting example operations of a data collection method 11000 according to some embodiments of the present disclosure. Although Figure 11 Various operations in a method for processing resource measurements for data collection are illustrated, but the embodiments of this disclosure are not limited thereto, and the method may include additional or fewer operations, or the order of operations may vary, without departing from the spirit and scope of the embodiments of this disclosure, unless otherwise stated or implied.

[0144] Reference Figure 11Method 11000 may include one or more of the following operations: Based on UE 105 being configured with more than one BWP and the first BWP of more than one BWP (e.g., as...). Figure 3 BWP2 (as shown) is activated, and UE 105 performs recording with the first resource (e.g., such as...). Figure 3 The first resource R1 or the second resource R2 shown is associated with and corresponds to the first CSI measurement result of the first BWP, as an entry in the AI / ML dataset (operation 11001).

[0145] For example, as referenced above Figure 3 As discussed, the first resource R1 (e.g., CSI-RS resource) and the second resource R2 may correspond to an active second bandwidth portion BWP2 (e.g., may be consistent with an active second bandwidth portion BWP2). Therefore, UE 105 may perform measurements on the first resource R1 and the second resource R2, wherein the first resource R1 and the second resource R2 are configured to be associated with AI / ML data collection for data collection in the second bandwidth portion BWP2. In some embodiments, based on the AI / ML data collection configured to be associated with the first BWP (e.g., AI / ML data collection associated with the first BWP), UE 105 may perform a first CSI measurement corresponding to the first BWP, and the result of the first CSI measurement (e.g., the first CSI measurement result) may be recorded (e.g., saved) as an entry in an AI / ML dataset (e.g., an AI / ML record).

[0146] UE 105 can send the first CSI measurement result from UE 105 based on an AI / ML dataset (e.g., it can send...). Figure 2 The measurement results data (MRD) (Operation 11002).

[0147] For example, as referenced above Figure 2 As discussed in Figure 9, UE 105 may transmit Measurement Result Data (MRD), which includes data indicating the results of a first measurement (e.g., RSRP_1), an nth measurement (e.g., RSRP_n), one or more intermediate measurements occurring between the first and nth measurements (e.g., RSRP_2), and data indicating which measurements were skipped (e.g., RSRP_3 and RSRP_4). (Refer to the above...) Figure 3 In some embodiments, UE 105 may send a first CSI measurement result from the UE based on an AI / ML dataset. For example, UE 105 may send the first CSI measurement result to network node 110 (see Figure 1). Network node 110 may use the first CSI measurement result to train AI / ML model 50.

[0148] Based on SCell (e.g., Figure 6 If SCell 110b is deactivated, UE 105 may not perform the recording of the second CSI measurement results for AI / ML data collection (operation 11003).

[0149] For example, as referenced above Figure 6 In order to comply with the state of SCell 110b, based on the deactivation of SCell 110b, UE 105 can be configured to suspend the measurement and measurement result recording of resources (e.g., CSI-RS resources) used for training AI / ML model 50.

[0150] UE 105 can send data indicating why the second CSI measurement result was not performed (Operation 11004).

[0151] For example, as referenced above Figure 9A and Figure 9B As discussed, if UE 105 indicates to skip measurements used for data collection, UE 105 may also indicate the reason for skipping the measurements, because NW may not be tracking (e.g., may not be tracking accurately) the state of UE 105.

[0152] Based on resources used for AI / ML data collection (e.g., Figure 4 The R1 or R4 corresponds to the measurement gap MG, and the UE105 may not perform the third measurement configured for AI / ML data collection (Operation 11005).

[0153] For example, as referenced above Figure 4 As discussed, during the active measurement gap MG, UE 105 can be configured to suspend transmission and reception to switch radio frequency (RF) or bandwidth to perform inter-frequency / inter-RAT or intra-frequency measurements. For data collection used to train the AI / ML model 50, UE 105 can also stop performing measurements and recording measurement results during the measurement gap MG.

[0154] Based on resources used for AI / ML data collection (e.g., Figure 5A For R3 or R5, corresponding to inactive DRX periods, UE 105 may not perform the fourth measurement configured for AI / ML data collection (Operation 11006).

[0155] For example, as referenced above Figure 5A The discussion suggests that if (e.g., only if) UE 105 is active, then (e.g., configurable by the NW) UE 105 may be allowed to perform measurements for data collection. For example, if UE 105 is not active, then UE 105 may skip performing (e.g., may not perform) measurements for data collection.

[0156] Based on resources used for AI / ML data collection (e.g., Figure 7 The time period (tx) corresponds to the inactive DTX period, and UE 105 may not perform the fifth measurement configured for AI / ML data collection (operation 11007).

[0157] For example, as referenced above Figure 7 As discussed, in order to avoid incorrect measurements when network node 110 does not send downlink signals, UE 105 may (e.g., by network node 110) be configured to perform measurement result recording only when network node 110 sends resources (e.g., CSI resources) during the active period AP.

[0158] Based on the resources used for AI / ML data collection, corresponding to inactive DRX periods and including those resources (e.g., Figure 8B R3) and another resource for AI / ML data collection (e.g., Figure 8B The resource window of R4 (e.g., Figure 8B Corresponding to the measurement window MW2 (which corresponds to the active DRX period), UE 105 may not perform measurements associated with that resource or the other resource that are configured for AI / ML data collection (Operation 11008).

[0159] For example, as referenced above Figure 8A and Figure 8B As discussed, UE 105 may also skip the measurement of the fourth resource R4 at t4, based on the fact that the fourth resource R4 at t4 corresponds to the same measurement window MW (e.g., MW2) as the third resource R3 skipped at t3.

[0160] The embodiments of the subject matter and operations described in this specification may be implemented in digital electronic circuits, or in computer software, firmware, or hardware (including the structures disclosed in this specification and their equivalents), or in a combination of one or more of these. Embodiments of the subject matter described in this specification may be implemented as one or more computer programs (i.e., one or more modules of computer program instructions) encoded on a computer storage medium for execution by or control of the operation of a data processing device. Optionally or additionally, the program instructions may be encoded in artificially generated propagating signals (e.g., machine-generated electrical, optical, or electromagnetic signals) generated to encode information for transmission to a suitable receiver device for execution by the data processing device. The computer storage medium may be a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination thereof, or may be included in a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination thereof. Furthermore, although the computer storage medium is not a propagating signal, it may be a source or destination of computer program instructions encoded in artificially generated propagating signals. Computer storage media may also be one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices), or may be included in one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices). Additionally, the operations described herein can be implemented as operations performed by a data processing device on data stored on one or more computer-readable storage devices or received from other sources.

[0161] While this specification may contain numerous specific implementation details, these details should not be construed as limiting the scope of any claimed subject matter, but rather as descriptions of features specific to particular embodiments. Specific features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments. Furthermore, although features may be described above as functioning in a particular combination and even initially claimed in this way, one or more features from a claimed combination may be removed from the combination in some cases, and the claimed combination may be for sub-combinations or variations thereof.

[0162] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring that these operations be performed in the specific order shown or sequentially, or that all of the shown operations be performed to achieve the desired result. In certain situations, multitasking and parallel processing may be advantageous. Furthermore, the separation of the various system components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0163] Therefore, specific embodiments of the subject matter have been described herein. Other embodiments are within the scope of the appended claims. In some cases, the actions set forth in the claims can be performed in a different order and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing may be advantageous.

[0164] As those skilled in the art will recognize, modifications and variations can be made to the innovative concepts described herein across a wide range of applications. Therefore, the scope of the claimed subject matter should not be limited to any of the specific exemplary teachings discussed above, but is defined by the appended claims.

Claims

1. A method for data collection, comprising: based on: The user equipment (UE) is configured with more than one bandwidth portion (BWP); as well as The first BWP of the more than one BWP is activated. The UE executes a record of the first channel state information (CSI) measurement result associated with the first resource and the first BWP, as an entry in the artificial intelligence / machine learning (AI / ML) dataset; and The UE sends the first CSI measurement result from the UE based on the AI / ML dataset.

2. The method as described in claim 1, wherein, The AI / ML dataset includes data indicating that a second CSI measurement was not performed.

3. The method of claim 1, further comprising: Since the second BWP in the more than one BWP is deactivated, the UE does not perform the recording of the second CSI measurement results associated with the second BWP for AI / ML data collection.

4. The method of claim 3, further comprising: The UE sends data indicating why the recording of the second CSI measurement result was not performed.

5. The method of claim 1, further comprising: Based on the second resource for AI / ML data collection corresponding to the measurement gap, The UE does not perform a second measurement for AI / ML data collection, wherein the second measurement is associated with the second resource.

6. The method of claim 1, further comprising: The second resource used for AI / ML data collection corresponds to the inactive, discontinuous DRX reception periods. The UE does not perform a second measurement for AI / ML data collection, wherein the second measurement is associated with the second resource.

7. The method of claim 1, further comprising: The second resource used for AI / ML data collection corresponds to the discontinuous reception DRX period of the activity and corresponds to the recording mask. The UE does not perform a second measurement configured for AI / ML data collection, wherein the second measurement is associated with the second resource.

8. The method of claim 1, further comprising: Based on the second resource used for AI / ML data collection, which corresponds to the inactive discontinuous reception DRX period and an inactive recording state is configured for the UE, The UE performs a second measurement for AI / ML data collection, wherein the second measurement is associated with the second resource.

9. The method of claim 1, further comprising: The second resource measurement time for AI / ML data collection corresponds to the inactive, discontinuous DTX transmission periods. The UE does not perform a second measurement for AI / ML data collection, wherein the second measurement is associated with the second resource measurement time.

10. The method of claim 1, further comprising: The resource window corresponds to a second resource for AI / ML data collection and an inactive, discontinuous DRX reception period, as well as a resource window that includes the second resource and a third resource for AI / ML data collection, wherein the third resource corresponds to an active DRX period: The UE does not perform the second measurement associated with the second resource for AI / ML data collection; and The UE does not perform the third measurement associated with the third resource for AI / ML data collection.

11. A method for data collection, comprising: Based on the activation of the secondary cell SCell. The user equipment (UE) performs the recording of CSI measurement results associated with the SCell for AI / ML data collection.

12. The method of claim 11, further comprising: Based on the deactivation of the SCell. The UE does not perform the recording of the second CSI measurement results used for AI / ML data collection.

13. The method of claim 12, further comprising: The UE sends data indicating that the measurement was not performed.

14. The method of claim 12, further comprising: based on: The bandwidth portion of BWP is activated; as well as The serving cell is not the primary and secondary cell PSCell of the deactivated secondary cell group SCG. The UE performs measurements associated with the BWP configured for AI / ML data collection to perform AI / ML data collection.

15. A system comprising: User equipment (UE), wherein the UE is configured to perform the following operations: based on: The UE is configured with more than one bandwidth portion (BWP); and The first BWP of the more than one BWP is activated. Record the first channel state information (CSI) measurement results associated with the first resource corresponding to the first BWP as entries in the artificial intelligence / machine learning (AI / ML) dataset; and The first CSI measurement result is sent from the UE based on the AI / ML dataset.

16. The system of claim 15, wherein, The UE is configured as follows: Since the second BWP in the more than one BWP is deactivated, the recording of the second CSI measurement results associated with the second BWP for AI / ML data collection is not performed.

17. The system of claim 16, wherein, The UE is configured to send data indicating why the recording of the second CSI measurement result was not performed.

18. The system of claim 15, wherein, The UE is configured as follows: Based on the second resource used for AI / ML data collection, which corresponds to the inactive discontinuous reception DRX period and an inactive recording state is configured for the UE, Perform a second measurement configured for AI / ML data collection, wherein the second measurement is associated with the second resource.

19. The system of claim 15, wherein, The UE is configured as follows: The second resource used for AI / ML data collection corresponds to the inactive, discontinuous DRX reception periods. The second measurement configured for AI / ML data collection is not performed, wherein the second measurement is associated with the second resource.

20. The system of claim 15, wherein, The UE is configured as follows: Based on the activation of the secondary cell SCell. Recording of a second CSI measurement result associated with the SCell for AI / ML data collection is performed to perform AI / ML data collection.

Images