Method and apparatus for artificial intelligence / machine learning data collection in wireless communication

Abstract

Methods and apparatus for Artificial Intelligence (AI) / Machine Learning (ML) data collection in wireless communication are provided. The method includes receiving, from a base station (BS), a first configuration for data collection, the first configuration including a measurement resource configuration, a threshold value, and a timer value, performing measurements based on the measurement resource configuration, and in response to a condition, which is determined based on the threshold value and the timer value, being met, storing a measurement result for AI / ML model training.

Description

METHOD AND APPARATUS FOR ARTIFICIAL INTELLIGENCE / MACHINE LEARNING DATA COLLECTION IN WIRELESS COMMUNICATION

[0001] The present disclosure relates to wireless communication, and in particular, to methods and apparatus for Artificial Intelligence (AI) / Machine Learning (ML) data collection in wireless communication.

[0002] Various efforts have been made to improve different aspects of wireless communication for the cellular wireless communication systems, such as the 5thGeneration (5G) New Radio (NR) system, by improving data rate, latency, reliability, and mobility. The 5G NR system is designed to provide flexibility and configurability to optimize network services and types, accommodating various use cases, such as enhanced Mobile Broadband (eMBB), massive Machine-Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC). As the demand for radio access continues to increase, however, there exists a need for further improvements in the art.Summery of Invention

[0003] The present disclosure relates to wireless communication, and in particular, to methods and apparatus for Artificial Intelligence (AI) / Machine Learning (ML) data collection in wireless communication.

[0004] According to a first aspect of the present disclosure, a User Equipment (UE) is provided. The UE includes at least one processor and at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the UE to receive, from a base station (BS), a first configuration for data collection, the first configuration including a measurement resource configuration, a threshold value, and a timer value, perform measurements based on the measurement resource configuration, and in response to a condition, which is determined based on the threshold value and the timer value, being met, store a measurement result for Artificial Intelligence / Machine Learning (AI / ML) model training.

[0005] In some implementations of the first aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to receive, from the BS, a second configuration indicating whether the UE is allowed to request a data collection configuration.

[0006] In some implementations of the first aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to, in response to receiving the first configuration, store the first configuration or replace a previously stored configuration with the first configuration.

[0007] In some implementations of the first aspect of the present disclosure, the measurement result includes at least one of a value of Reference Signal Received Power (RSRP), a value of Reference Signal Received Quality (RSRQ), or a value of Signal-to-Interference-plus-Noise Ratio (SINR).

[0008] In some implementations of the first aspect of the present disclosure, the timer value indicates a timing when the UE starts or stops storing the measurement result.

[0009] In some implementations of the first aspect of the present disclosure, a unit of the timer value is milliseconds.

[0010] In some implementations of the first aspect of the present disclosure, the measurement resource configuration includes time / frequency information of radio resources, a reference signal configuration, and beam information, the reference signal configuration includes Synchronization Signal / Physical Broadcast Channel (PBCH) Block (SSB) information and Channel State Information Reference Signal (CSI-RS) information, and the time / frequency information of the radio resources includes periodicity information.

[0011] In some implementations of the first aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to transmit, to the BS, a Radio Resource Control (RRC) message including information related to data collection, where the information related to data collection includes power state information and memory state information, a value of the power state information is determined by the UE based on a power state of the UE, and a value of the memory state information is determined by the UE based on a remaining memory state of the UE.

[0012] According to a second aspect of the present disclosure, a method performed by a User Equipment (UE) for Artificial Intelligence / Machine Learning (AI / ML) data collection is provided. The method includes receiving, from a base station (BS), a first configuration for data collection, the first configuration including a measurement resource configuration, a threshold value, and a timer value, performing measurements based on the measurement resource configuration, and in response to a condition, which is determined based on the threshold value and the timer value, being met, storing a measurement result for AI / ML model training.

[0013] According to a third aspect of the present disclosure, a Base Station (BS) is provided. The BS includes at least one processor and at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the BS to transmit, to a User Equipment (UE), a first configuration for data collection, the first configuration including a measurement resource configuration, a threshold value, and a timer value, where the measurement resource configuration is for configuring measurements to be performed by the UE, and the threshold value and the timer value are for determining a condition for storing a measurement result at the UE.

[0014] In some implementations of the third aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the BS to transmit, to the UE, a second configuration indicating whether the UE is allowed to request a data collection configuration.

[0015] In some implementations of the third aspect of the present disclosure, the measurement result includes at least one of a value of Reference Signal Received Power (RSRP), a value of Reference Signal Received Quality (RSRQ), or a value of Signal-to-Interference-plus-Noise Ratio (SINR).

[0016] In some implementations of the third aspect of the present disclosure, the timer value indicates a timing when the UE starts or stops storing the measurement result.

[0017] In some implementations of the third aspect of the present disclosure, a unit of the timer value is milliseconds.

[0018] In some implementations of the third aspect of the present disclosure, the measurement resource configuration includes time / frequency information of radio resources, a reference signal configuration, and beam information, the reference signal configuration includes Synchronization Signal / Physical Broadcast Channel (PBCH) Block (SSB) information and Channel State Information Reference Signal (CSI-RS) information, and the time / frequency information of the radio resources includes periodicity information.

[0019] Aspects of the present disclosure are best understood from the following detailed disclosure when read with the accompanying drawings. Various features are not drawn to scale. Dimensions of various features may be arbitrarily increased or reduced for clarity of discussion.

[0020] FIG. 1 is a schematic diagram illustrating UE-request data collection, according to an example implementation of the present disclosure.

[0021] FIG. 2 is a schematic diagram illustrating NW-initiated data collection, according to an example implementation of the present disclosure.

[0022] FIG. 3 is a schematic diagram illustrating a method for AI / ML data collection at a UE, according to an example implementation of the present disclosure.

[0023] FIG. 4 is a block diagram illustrating a node for wireless communications, in accordance with various aspects of the present disclosure.

[0024] Some of the abbreviations in the present application are defined as follows and, unless otherwise specified, the abbreviations have the following meanings: Abbreviation　　　　　　　　Full name 3GPP　　　　　　　　　　　　3rd Generation Partnership Project 6G　　　　　　　　　　　　　　　　Sixth Generation AC　　　　　　　　　　　　　　　　Additional Condition AI / ML　　　　　　　　　　　　Artificial Intelligence / Machine Learning AM　　　　　　　　　　　　　　　　Acknowledgement Mode / Acknowledged Mode ARFCN　　　　　　　　　　　　Absolute Radio Frequency Channel Number BA　　　　　　　　　　　　　　　　Bandwidth Adaptation BFD　　　　　　　　　　　　　　　　Beam Failure Detection BFR　　　　　　　　　　　　　　　　Beam Failure Recovery BM　　　　　　　　　　　　　　　　Beam Management BS　　　　　　　　　　　　　　　　Base Station BWP　　　　　　　　　　　　Bandwidth Part CA　　　　　　　　　　　　　　　　Carrier Aggregation CCCH　　　　　　　　　　　　Common Control Channel CD-SSB　　　　　　　　　　　　Cell-Defining SSB CE　　　　　　　　　　　　　　　　Control Element　　　　 CHO　　　　　　　　　　　　Conditional Handover CORESET　　　　　　　　Control Resource Set CPAC　　　　　　　　　　　　Conditional PSCell Addition or Change CPC　　　　　　　　　　　　　　　　Conditional PSCell Change CQI　　　　　　　　　　　　　　　　Channel Quality Indicator C-RNTI　　　　　　　　　　　　Cell-Radio Network Temporary Identifier CSI　　　　　　　　　　　　　　　　Channel State Information CSI-RS　　　　　　　　　　　　Channel State Information-Reference Signal DAPS　　　　　　　　　　　　Dual Active Protocol Stack DC　　　　　　　　　　　　　　　　Dual Connectivity DCI　　　　　　　　　　　　　　　　Downlink Control Information DL　　　　　　　　　　　　　　　　Downlink DL-DCCH　　　　　　　　Downlink-Dedicated Control Channel DRX　　　　　　　　　　　　Discontinuous Reception FR　　　　　　　　　　　　　　　　Frequency Range ID　　　　　　　　　　　　　　　　Identifier / Identity IE　　　　　　　　　　　　　　　　Information Elements L1　　　　　　　　　　　　　　　　Layer-1 L2　　　　　　　　　　　　　　　　Layer-2 L3　　　　　　　　　　　　　　　　Layer-3 LBT　　　　　　　　　　　　　　　　Listen Before Talk LCM　　　　　　　　　　　　Life Cycle Management LTM　　　　　　　　　　　　L1 / L2 Triggered Mobility MAC　　　　　　　　　　　　Medium Access Control MAC CE　　　　　　　　　　　　Medium Access Control Control Element MCG　　　　　　　　　　　　Master Cell Group MCS　　　　　　　　　　　　Modulation Coding Scheme MDT　　　　　　　　　　　　Minimum Drive Test MIB　　　　　　　　　　　　　　　　Master Information Block MIMO　　　　　　　　　　　　Multiple Input Multiple Output NR　　　　　　　　　　　　　　　　New Radio NW　　　　　　　　　　　　　　　　Network NW-AC　　　　　　　　　　　　Network-side Additional Condition NZP　　　　　　　　　　　　　　　　Non-Zero-Power OD-SSB　　　　　　　　　　　　On-Demand SSB PBCH　　　　　　　　　　　　Physical Broadcast CHannel PCell　　　　　　　　　　　　Primacy Cell PDCCH　　　　　　　　　　　　Physical Downlink Control CHannel PDSCH　　　　　　　　　　　　Physical Downlink Shared CHannel PHY　　　　　　　　　　　　Physical Layer PRACH　　　　　　　　　　　　Physical Random Access CHannel PUCCH　　　　　　　　　　　　Physical Uplink Control CHannel PUSCH　　　　　　　　　　　　Physical Uplink Shared CHannel RA　　　　　　　　　　　　　　　　Random Access RAN　　　　　　　　　　　　Radio Access Network RAR　　　　　　　　　　　　Random Access Response RB　　　　　　　　　　　　　　　　Resource Block RE　　　　　　　　　　　　　　　　Resource Element Rel　　　　　　　　　　　　　　　　Release RNTI　　　　　　　　　　　　Radio Network Temporary Identifier RLC　　　　　　　　　　　　　　　　Radio Link Control RLC-SAP　　　　　　　　Radio Link Control - Service Access Point RLM　　　　　　　　　　　　Radio Link Monitoring RRC　　　　　　　　　　　　Radio Resource Control RRM　　　　　　　　　　　　Radio Resource Management RSRP　　　　　　　　　　　　Reference Signal Received Power RSRQ　　　　　　　　　　　　Reference Signal Received Quality SCell　　　　　　　　　　　　Secondary Cell SCG　　　　　　　　　　　　　　　　Secondary Cell Group SCS　　　　　　　　　　　　　　　　SubCarrier Spacing S-CPAC　　　　　　　　　　　　Subsequent Conditional PSCell Addition or Change SINR　　　　　　　　　　　　Signal to Inference and Noise Ratio SNR　　　　　　　　　　　　　　　　Signal to Noise Ratio SR　　　　　　　　　　　　　　　　Scheduling Request SRB　　　　　　　　　　　　　　　　Signaling Radio Bearer SS　　　　　　　　　　　　　　　　Search Space SSB　　　　　　　　　　　　　　　　Synchronization Signal Block TM　　　　　　　　　　　　　　　　Transparent Mode UCI　　　　　　　　　　　　　　　　Uplink Control Information UE　　　　　　　　　　　　　　　　User Equipment UL　　　　　　　　　　　　　　　　Uplink UL-DCCH　　　　　　　　Uplink Dedicated Control Channel

[0025] The following contains specific information related to implementations of the present disclosure. The drawings and their accompanying detailed disclosure are merely directed to implementations. However, the present disclosure is not limited to these implementations. Other variations and implementations of the present disclosure will be obvious to those skilled in the art.

[0026] Unless noted otherwise, like or corresponding elements among the drawings may be indicated by like or corresponding reference numerals. Moreover, the drawings and illustrations in the present disclosure are generally not to scale and are not intended to correspond to actual relative dimensions.

[0027] For consistency and ease of understanding, like features may be identified (although, in some examples, not illustrated) by the same numerals in the drawings. However, the features in different implementations may be different in other respects and shall not be narrowly confined to what is illustrated in the drawings.

[0028] References to “one implementation,” “an implementation,” “example implementation,” “various implementations,” “some implementations,” “implementations of the present application,” etc., may indicate that the implementation(s) of the present application so described may include a particular feature, structure, or characteristic, but not every possible implementation of the present application necessarily includes the particular feature, structure, or characteristic. Further, repeated use of the phrase “in one implementation,” or “in an example implementation,” “an implementation,” do not necessarily refer to the same implementation, although they may. Moreover, any use of phrases like “implementations” in connection with “the present application” are never meant to characterize that all implementations of the present application must include the particular feature, structure, or characteristic, and should instead be understood to mean “at least some implementations of the present application” includes the stated particular feature, structure, or characteristic.

[0029] The term “coupled” is defined as connected, whether directly or indirectly through intervening components, and is not necessarily limited to physical connections. The term “comprising,” when utilized, means “including, but not necessarily limited to”; it specifically indicates open-ended inclusion or membership in the so-described combination, group, series, and the equivalent.

[0030] The expression “at least one of A, B and C” or “at least one of the following: A, B and C” means “only A, or only B, or only C, or any combination of A, B and C.” The terms “system” and “network” may be used interchangeably. The term “and / or” is only an association relationship for describing associated objects and represents that three relationships may exist such that A and / or B may indicate that A exists alone, A and B exist at the same time, or B exists alone. The character “ / ” generally represents that the associated objects are in an “or” relationship.

[0031] For the purposes of explanation and non-limitation, specific details, such as functional entities, techniques, protocols, and standards, are set forth for providing an understanding of the disclosed technology. In other examples, detailed disclosure of well-known methods, technologies, systems, and architectures are omitted so as not to obscure the present disclosure with unnecessary details.

[0032] Persons skilled in the art will immediately recognize that any network function(s) or algorithm(s) disclosed may be implemented by hardware, software, or a combination of software and hardware. Disclosed functions may correspond to modules which may be software, hardware, firmware, or any combination thereof.

[0033] A software implementation may include computer executable instructions stored on a computer-readable medium, such as memory or other type of storage devices. One or more microprocessors or general-purpose computers with communication processing capability may be programmed with corresponding executable instructions and perform the disclosed network function(s) or algorithm(s).

[0034] The microprocessors or general-purpose computers may include Application-Specific Integrated Circuits (ASICs), programmable logic arrays, and / or one or more Digital Signal Processor (DSPs). Although some of the disclosed implementations are oriented to software installed and executing on computer hardware, alternative implementations implemented as firmware, as hardware, or as a combination of hardware and software are well within the scope of the present disclosure. The computer-readable medium includes but is not limited to Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory, Compact Disc Read-Only Memory (CD-ROM), magnetic cassettes, magnetic tape, magnetic disk storage, or any other equivalent medium capable of storing computer-readable instructions.

[0035] A radio communication network architecture such as a Long-Term Evolution (LTE) system, an LTE-Advanced (LTE-A) system, an LTE-Advanced Pro system, or a 5G NR Radio Access Network (RAN) typically includes at least one base station (BS), at least one UE, and one or more optional network elements that provide connection within a network. The UE communicates with the network such as a Core Network (CN), an Evolved Packet Core (EPC) network, an Evolved Universal Terrestrial RAN (E-UTRAN), a 5G Core (5GC), or an internet via a RAN established by one or more BSs.

[0036] A UE may include, but is not limited to, a mobile station, a mobile terminal or device, or a user communication radio terminal. The UE may be a portable radio equipment that includes, but is not limited to, a mobile phone, a tablet, a wearable device, a sensor, a vehicle, or a Personal Digital Assistant (PDA) with wireless communication capability. The UE is configured to receive and transmit signals over an air interface to one or more cells in a RAN. A UE may be referred to as a PHY / MAC / RLC / PDCP / SDAP entity. The PHY / MAC / RLC / PDCP / SDAP entity may be referred to as the UE.

[0037] The BS may be configured to provide communication services according to at least a Radio Access Technology (RAT) such as Worldwide Interoperability for Microwave Access (WiMAX), Global System for Mobile communications (GSM) that is often referred to as 2G, GSM Enhanced Data rates for GSM Evolution (EDGE) RAN (GERAN), General Packet Radio Service (GPRS), Universal Mobile Telecommunication System (UMTS) that is often referred to as 3G based on basic wideband-code division multiple access (W-CDMA), high-speed packet access (HSPA), LTE, LTE-A, evolved LTE (eLTE) that is LTE connected to 5GC, NR (often referred to as 5G), and / or LTE-A Pro. However, the scope of the present disclosure is not limited to these protocols.

[0038] The BS may include, but is not limited to, a node B (NB) in the UMTS, an evolved node B (eNB) in LTE or LTE-A, a radio network controller (RNC) in UMTS, a BS controller (BSC) in the GSM / GERAN, an ng-eNB in an Evolved Universal Terrestrial Radio Access (E-UTRA) BS in connection with 5GC, a next generation Node B (gNB) in the 5G-RAN, or any other apparatus capable of controlling radio communication and managing radio resources within a cell. The BS may serve one or more UEs via a radio interface.

[0039] The BS may be operable to provide radio coverage to a specific geographical area using multiple cells forming the RAN. The BS may support the operations of the cells. Each cell may be operable to provide services to at least one UE within its radio coverage.

[0040] A software implementation of the technical solutions provided in the present disclosure may include computer-executable instructions and / or Artificial Intelligence (AI) / Machine Learning (ML) module(s) stored on a computer-readable medium, such as a memory or other type of storage devices. One or more microprocessors or general-purpose computers with communication processing capability may be programmed with the corresponding computer-executable instructions and may perform the disclosed network function(s), AI / ML module(s), or algorithm(s). The AI / ML module(s) may be implemented with a supervised learning approach, a semi-supervised learning approach, an unsupervised learning approach (e.g., a Transductive approach and an Inductive approach), a federated learning approach, or a Reinforcement Learning (RL) approach, but the present disclosure is not limited thereto. The computer-executable instructions associated with the AI module(s) and / or the ML module(s) may include but are not limited to, data management instructions (e.g., collection instructions, validation instructions, etc.), model monitoring and management instructions (e.g., network (NW) Key Performance Indicators (KPIs) monitoring, model input / output monitoring, model selection / switching / update / upload / download, model (de)activation, model identification, functionality selection, etc.), and / or pre-process input instructions.

[0041] In some implementations, the UE may be an AI / ML-enabled device and / or an AI / ML capable device that may be equipped with AI module(s) and / or ML module(s).

[0042] In some implementations, the BS may be an AI / ML-enabled device and / or an AI / ML capable device that may be equipped with AI module(s) and / or ML module(s).

[0043] Each cell (often referred to as a serving cell) may provide services to serve one or more UEs within its radio coverage, such that each cell schedules the DL (and optionally UL resources) to at least one UE within its radio coverage for DL (and optionally UL packet transmissions from the UE). The BS may communicate with one or more UEs in the radio communication system via the plurality of cells.

[0044] A cell may allocate sidelink (SL) resources for supporting the Proximity Service (ProSe) or Vehicle to Everything (V2X) service. Each cell may have overlapped coverage areas with other cells.

[0045] In Multi-RAT Dual Connectivity (MR-DC) cases, the primary cell of a Master Cell Group (MCG) or a Secondary Cell Group (SCG) may be referred to as a Special Cell (SpCell). A Primary Cell (PCell) may include the SpCell of an MCG. A Primary SCG Cell (PSCell) may include the SpCell of an SCG. MCG may include a group of serving cells associated with the Master Node (MN), including the SpCell and optionally one or more Secondary Cells (SCells). An SCG may include a group of serving cells associated with the Secondary Node (SN), including the SpCell and optionally one or more SCells.

[0046] As described above, the frame structure for NR supports flexible configurations for accommodating various next generation (e.g., 5G) communication requirements, such as Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC), while fulfilling high reliability, high data rate, and low latency requirements. The Orthogonal Frequency-Division Multiplexing (OFDM) technology in the 3GPP may serve as a baseline for an NR waveform. The scalable OFDM numerology, such as adaptive sub-carrier spacing, channel bandwidth, and Cyclic Prefix (CP), may also be used.

[0047] Two coding schemes may be considered for NR, specifically Low-Density Parity-Check (LDPC) code and Polar Code. The coding scheme adaption may be configured based on channel conditions and / or service applications.

[0048] At least the DL transmission data, a guard period, and UL transmission data should be included in a transmission time interval (TTI) of a single NR frame. The respective portions of the DL transmission data, the guard period, and the UL transmission data should also be configurable based on, for example, the network dynamics of NR. SL resources may also be provided in an NR frame to support ProSe services or V2X services.

[0049] Any two or more of the following paragraphs, (sub)-bullets, points, actions, behaviors, terms, or claims described in the present disclosure may be combined logically, reasonably, and properly to form a specific method.

[0050] Any sentence, paragraph, (sub)-bullet, point, action, behaviors, terms, or claims described in the present disclosure may be implemented independently and separately to form a specific method.

[0051] Dependency, e.g., “based on”, “more specifically”, “preferably”, “in one embodiment”, “in some implementations”, etc., in the present disclosure is just one possible example which would not restrict the specific method.

[0052] “A and / or B” in the present disclosure may refer to either A or B, both A and B, or at least one of A and B.

[0053] In this disclosure, “X / Y” may encompass the meanings of “X or Y,” “X and Y,” and “X and / or Y,” as indicated by two or more of the sentences, paragraphs, sub-bullets, points, actions, behaviors, terms, alternatives, aspects, examples, embodiments, or claims described in the following invention(s).

[0054] One aspect of the present disclosure may be applied in various contexts, including communications, communication equipment (such as mobile telephone apparatus, base station apparatus, wireless LAN apparatus, and / or sensor devices), integrated circuits (such as communication chips), and software programs, among others.

[0055] The terms “an antenna port” and “antenna ports,” as discussed in the present disclosure, may refer to “an antenna port used for transmission of PUSCH(s) / PUCCH(s)” and “antenna ports used for transmission of PUSCH(s) / PUCCH(s),” respectively.

[0056] Some of the terms, definitions, and / or abbreviations included in the present disclosure may either be sourced from existing documents (such as those from ETSI, ITU, or other sources) or may be newly created by experts from the 3GPP whenever there was a need for a precise vocabulary.

[0057] In the present disclosure, although the term “gNB” may have been used throughout the document, it should be understood that the term “gNB” may be replaced by any other type of BS (e.g., an eNB). Multiple PLMNs may operate on the unlicensed spectrum. Multiple PLMNs may share the same unlicensed carrier. The PLMNs may be public or private. Public PLMNs may include the operators or virtual operators, which may provide radio services to the public subscribers. Public PLMNs may own the licensed spectrum and may support the radio access technology on the licensed spectrum as well. Private PLMNs may include the micro-operators, factories, or enterprises, which may provide radio services to the private users (e.g., employees or machines). In some implementations, public PLMNs may support more deployment scenarios, such as carrier aggregation between licensed band NR (PCell) and NR-U (SCell), dual connectivity between licensed band LTE (PCell) and NR-U (PSCell), stand-alone NR-U, an NR cell with DL in unlicensed band and UL in licensed band, and dual connectivity between licensed band NR (PCell) and NR-U (PSCell). In some implementations, private PLMNs may mainly support the stand-alone unlicensed radio access technology (e.g., stand-alone NR-U).

[0058] Additionally, in the present disclosure, the term “reference signal” may broadly encompass various types of signals. When referring to “the sequence of signals” or “the sequence of reference signals,” these terms may be used interchangeably. The reference signal may be used for measurement, synchronization, and / or cell identification purposes. The reference signal may include, but may not be limited to, synchronization signals, discovery signals, tracking signals, measurement signals, pilot signals, beacon signals, or any other signals that may be transmitted by the cell for the UE to detect, measure, and / or decode. In some implementations, the reference signal may refer to any signal that may enable the UE to identify whether a cell may support AI / ML features, 6G and beyond RAT, or specific AI / ML use cases. The reference signal may also include composite signals that may combine multiple signal types or signal components for enhanced detection and measurement capabilities. Furthermore, the reference signal may include both periodic signals and aperiodic signals, where the periodic signals may be transmitted at regular intervals and the aperiodic signals may be transmitted based on specific triggers or conditions. The flexibility in signal types may allow the network to optimize the signaling overhead while providing sufficient information for AI / ML-capable UEs to perform efficient cell selection and reselection procedures.

[0059] Examples of some selected terms in the present disclosure are provided as follows.

[0060] The network, cell, camped cell, serving cell, base station, gNB, eNB and ng-eNB may be used interchangeably. In some implementations, some of these items may refer to the same network entity.

[0061] The RAT may include NR, LTE, E-UTRA connected to 5GC, LTE connected to 5GC, E-UTRA connected to EPC, LTE connected to EPC, and 6G RAT. The proposed mechanism may be applied for UEs in public networks, or in private networks, e.g., NPN, SNPN, or PNI-NPN.

[0062] The proposed mechanism may be used for licensed frequency and / or unlicensed frequency.

[0063] System information may refer to MIB, SIB1, and other SI. Minimum SI may include MIB and SIB1. Other SI may refer to SIB3, SIB4, SIB5, and other SIBs.

[0064] Dedicated signaling may refer to (but not limited to) RRC message(s). For example, RRC (Connection) Setup Request message, RRC (Connection) Setup message, RRC (Connection) Setup Complete message, RRC (Connection) Reconfiguration message, RRC Connection Reconfiguration message including the mobility control information, RRC Connection Reconfiguration message without the mobility control information inside, RRC Reconfiguration message including the configuration with sync, RRC Reconfiguration message without the configuration with sync inside, RRC (Connection) Reconfiguration Complete message, RRC (Connection) Resume Request message, RRC (Connection) Resume message, RRC (Connection) Resume Complete message, RRC (Connection) Reestablishment Request message, RRC (Connection) Reestablishment message, RRC (Connection) Reestablishment Complete message, RRC (Connection) Reject message, RRC (Connection) Release message, RRC System Information Request message, UE Assistance Information message, UE Capability Enquiry message, and UE Capability Information message.The RRC_CONNECTED UE, RRC_INACTIVE UE, and RRC_IDLE UE may apply the proposed implementations.

[0065] The UE may be served by a cell, e.g., a serving cell. The serving cell may serve an RRC_CONNECTED UE. The serving cell may be a suitable cell.

[0066] The PCell may be the MCG cell, operating on the primary frequency, in which the UE either performs the initial connection establishment procedure or initiates the connection re-establishment procedure.

[0067] The PSCell may be, for dual connectivity operation, the SCG cell in which the UE performs random access when performing the Reconfiguration with Sync procedure.

[0068] For a UE in RRC_CONNECTED not configured with CA / DC, there may be only one serving cell including the primary cell. For a UE in RRC_CONNECTED configured with CA / DC, the serving cells may be used to denote the set of cells including the Special Cell and all secondary cells.

[0069] The Secondary Cell may be, for a UE configured with CA, a cell providing additional radio resources on top of the Special Cell.

[0070] The Special Cell may refer to the PCell of the MCG or the PSCell of the SCG for Dual Connectivity operation, otherwise the Special Cell may refer to the PCell.

[0071] The serving cell, TRP associated with the PCI of the serving cell, TRP associated with the serving cell, TRP of a serving cell and TRP of the serving cell may be applied interchangeably.

[0072] The target cell, target serving cell, TRP associated with a PCI different from the PCI of the serving cell, and TRP associated with the target cell may be applied interchangeably. A target serving cell may be identified by a PCI or a PCI index. A UE may be configured with at most 1, 4, 8, or 32 PCI indices. Each PCI index may identify a target serving cell of the UE.

[0073] The candidate cell, neighboring cell and candidate target cell may be applied interchangeably.

[0074] The serving cell in the implementations may be a PCell, SCell or PSCell.

[0075] The target cell in the implementations may be a PCell, SCell or PSCell.

[0076] An inter-cell to the serving cell of the UE may be a neighboring cell, a cell other than the serving cell or a cell with PCI different from the PCI of the serving cell. If the UE can perform the inter-cell beam management, the UE may be in coverage of the inter-cell.

[0077] The reference signal may refer to SSB, CSI-RS, TRS, PT-RS, SRS, and DM-RS.

[0078] A timer may be running once the timer is started, until the timer is stopped or until the timer expires; otherwise the timer may not be running. A timer may be started if the timer is not running or restarted if the timer is running. A timer may always be started or restarted from the initial value of the timer. The duration of a timer may not be updated until the timer is stopped or expires, e.g., due to BWP switching. When the MAC entity applies zero value for a timer, the timer may be started and immediately expire unless explicitly stated otherwise.

[0079] An ML model may be a manageable representation of an ML model algorithm. An ML model algorithm may be a mathematical algorithm through which running a set of input data can generate a set of inference output. An ML model may include metadata. Metadata may include, e.g., information related to the trained model, and applicable runtime context.

[0080] ML model training may be a process performed by an ML training function to take training data, run the training data through an ML model algorithm, derive the associated loss and adjust the parameterization of that ML model iteratively based on the computed loss and generate the trained ML model.

[0081] ML model initial training may be a process of an initial version of an ML model.

[0082] ML model re-training may be a process of training a previous version of an ML model and generating a new version. A new version of a trained ML model may support the same type of inference as the previous version of the ML model, where the data type of inference input and data type of inference output may remain unchanged between the two versions of the ML model, but parameter values may be different for the re-trained model.

[0083] ML model joint training may be a process of training a group of ML models.

[0084] An ML training function may be a logical function with ML model training capabilities.

[0085] ML model testing may be a process of testing an ML model using testing data.

[0086] An ML testing function may be a logical function with ML model testing capabilities.

[0087] AI / ML inference may be a process of running a set of input data through a trained ML model to produce a set of output data, such as predictions. The inference may represent the process to realize the AI capabilities by utilizing a trained ML model and other AI enablers if needed, hence the AI / ML prefix may be used when referring to inference as compared to training and testing.

[0088] An AI / ML inference function may be a logical function that may employ trained ML models to conduct inference.

[0089] AI / ML inference emulation may be running the inference process to evaluate the performance of an ML model in an emulation environment before deploying the ML model into the target environment.

[0090] ML model deployment may be a process of making a trained ML model available for use in the target environment.

[0091] A Network-side AI / ML model may be an AI / ML Model whose inference may be performed entirely at the network.

[0092] A UE-side AI / ML model may be an AI / ML Model whose inference may be performed entirely at the UE.

[0093] A Two-sided AI / ML model may be paired AI / ML Models over which joint inference may be performed, where joint inference may include AI / ML Inference whose inference may be performed jointly across the UE and the network, where the first part of inference may be firstly performed by the UE and then the remaining part may be performed by the gNB, or vice versa.

[0094] A UE supporting AI / ML features may support at least one of AI / ML use cases. A UE supporting a specific AI / ML use case may be supposed to support AI / ML features.

[0095] A cell supporting AI / ML features may support at least one of AI / ML use cases. A cell supporting a specific AI / ML use case may be supposed to support AI / ML features.

[0096] The application of AI / ML to wireless communications has raised attention in recent years and may be expected to be one of the key features in 6G. Currently, the AI / ML in wireless communications may be limited to implementation-based approaches, e.g., the AI / ML may be implemented at the network side, at the UE side, or both at the network side and at the UE side.

[0097] In 3GPP Rel-18, applying AI / ML technology to the NR air-interface has been studied. In 3GPP Rel-19 normative work, AI / ML for the air-interface has been considered in beam management, positioning accuracy enhancement and CSI feedback enhancement. Moreover, AI / ML for mobility enhancement may also be studied in the AI / ML E2E framework. AI / ML may be expected to be widely used in the next-generation radio access network for different use cases.

[0098] Data may be the input of the AI / ML models for different use cases. Thus, the design of the data collection procedure may be further investigated to enable efficient AI / ML model training and inference in wireless communication systems.

[0099] To complete the data collection in AI / ML for the NR air interface, determining how the UE knows whether the network supports UE-request data collection and / or NW-initiated data collection may be an issue. In some implementations, the network may need to signal the support capability to enable the UE to determine which data collection mechanism may be available. In addition, the detailed design of the UE-request data collection may be worthy of investigation, including how the UE may transmit the data collection request, the content of the data collection request, how the data collection configuration may be transmitted, the content of the data collection configuration, how the acknowledgement message / indicator may be transmitted, and the content of the acknowledgement message / indicator.

[0100] Scenarios

[0101] In this disclosure, several implementations may be proposed to enable the UE to perform data collection for AI / ML purposes, e.g., AI / ML training, AI / ML inference, AI / ML beam management use cases, and AI / ML positioning use cases. There may be two main scenarios, namely the UE-request data collection, as shown in FIG. 1, and the NW-initiated data collection, as shown in FIG. 2. In some implementations, these two scenarios may provide flexible mechanisms for initiating data collection based on different network deployment requirements and use case needs.

[0102] FIG. 1 is a schematic diagram illustrating UE-request data collection, according to an example implementation of the present disclosure. In FIG. 1, a signaling flow between a UE and a BS may be illustrated to demonstrate the UE-request data collection procedure. The procedure may include multiple actions that enable the UE to request data collection configuration from the network and subsequently perform data collection for AI / ML purposes.

[0103] In action 102, the UE may transmit a data collection request to the BS. The data collection request may be transmitted as a message, an information element, or an indicator to the serving cell. The data collection request may include various parameters such as the associated ID, the model ID, the resource types, the UE battery / power / energy state, the UE memory state, and other relevant information that may help the BS determine appropriate data collection configurations for the UE.

[0104] In action 104, the BS may transmit a data collection configuration to the UE in response to the reception of the data collection request. The serving cell may transmit the data collection configuration after processing the UE's request and determining suitable configuration parameters. The UE may receive an RRC message and / or an information element including the data collection configuration from the serving cell. In some implementations, the data collection configuration may include various parameters such as measurement resource configurations, threshold values, timer values, and data collection report configurations that may enable the UE to perform appropriate data collection for the specific AI / ML use case.

[0105] In action 106, the UE may transmit an acknowledgement message / indicator to the serving cell. The acknowledgement message / indicator may indicate whether the UE accepts or rejects the data collection configuration. In some implementations, this action may be optional, as indicated by the possibility that the UE may or may not transmit the acknowledgement message / indicator to the serving cell. If the UE determines that the UE accepts the data collection configuration, the UE may apply the data collection configuration. The acknowledgement may include an acceptance indication or a rejection indication, and in case of rejection, the acknowledgement may include a cause value indicating the reason for rejection.

[0106] Following action 106, the UE may perform data collection as shown in action 108. Based on the applied data collection configuration, the UE may perform the data collection according to the configured parameters. The data collection may involve measuring reference signals, storing measurement results when threshold conditions are met, and collecting data according to the configured timer values and measurement resource configurations.

[0107] In action 110, the collected data may be used for AI / ML model training. The UE or the network may utilize the collected data to train AI / ML models for various use cases such as beam management, positioning enhancement, or CSI feedback enhancement. In some implementations, if the UE determines that the UE rejects or partially rejects the data collection configuration in action 106, the UE may not apply the data collection configuration or the UE may partially apply the data collection configuration. The partial application may occur when the UE has limited resources or when certain configuration parameters may not be supported by the UE's current capability.

[0108] The UE-request data collection procedure illustrated in FIG. 1 may enable the UE to actively participate in the data collection process by initiating the request when the UE determines that data collection may be beneficial or necessary for AI / ML operations. This UE-initiated approach may provide flexibility in scenarios where the UE has better knowledge of the local conditions or requirements for AI / ML model training.

[0109] Specifically, in FIG. 1, the UE may transmit a message, an information element, or an indicator to the serving cell for the data collection request. The serving cell may transmit the data collection configuration to the UE in response to the reception of the data collection request. The UE may receive an RRC message and / or an information element including the data collection configuration from the serving cell after the UE transmits the data collection request to the serving cell. In some implementations, the data collection configuration may include various parameters such as measurement resource configurations, threshold values, and timer values that may enable the UE to perform appropriate data collection for the specific AI / ML use case. Afterwards, the UE may or may not transmit an acknowledgement message and / or indicator to the serving cell to indicate whether the UE accepts or rejects the data collection configuration. If the UE determines that the UE accepts the data collection configuration, the UE may apply the data collection configuration. Based on the data collection configuration, the UE may therefore perform the data collection. The collected data may be used for the AI / ML model training. In some implementations, if the UE determines that the UE rejects or partially rejects the data collection configuration, the UE may not apply the data collection configuration or the UE may partially apply the data collection configuration. The partial application may occur when the UE has limited resources or when certain configuration parameters may not be supported by the UE's current capability.

[0110] FIG. 2 is a schematic diagram illustrating NW-initiated data collection, according to an example implementation of the present disclosure. In FIG. 2, a signaling flow between a UE and a BS may be illustrated to demonstrate the NW-initiated data collection procedure. The procedure may show how the network may proactively initiate data collection without requiring a prior request from the UE.

[0111] In action 202, the BS may transmit a data collection configuration to the UE. The serving cell may transmit the RRC message and / or the information element including the data collection configuration to the UE without receiving the UE's request in advance. In some implementations, this proactive configuration from the network may enable faster deployment of AI / ML data collection when the network determines that data collection may be beneficial for improving system performance. The data collection configuration may include various parameters such as measurement resource configurations, threshold values, timer values, and data collection report configurations that may be determined by the network based on system requirements or AI / ML model training needs.

[0112] In action 204, the UE may transmit an acknowledgement message / indicator to the BS. After reception of the data collection configuration, the UE may transmit the acknowledgement message / indicator to the serving cell to indicate whether the UE accepts or rejects the data collection configuration. In some implementations, this action may be optional, as the UE may or may not transmit the acknowledgement message / indicator based on the configuration received or the UE's implementation. If the UE determines that the UE accepts the data collection configuration, the UE may apply the data collection configuration. The acknowledgement message / indicator may include an acceptance indication, a rejection indication, or a partial rejection indication. In case of rejection or partial rejection, the acknowledgement may include a cause value such as 'power', 'memory', or 'RS' to indicate the reason for the rejection.

[0113] Following action 204, the UE may perform data collection as shown in action 206. Based on the data collection configuration received from the network, the UE may perform the data collection according to the configured parameters. The data collection may involve performing measurements on configured reference signals, applying threshold conditions for data storage, and following timer configurations for data collection duration. The UE may collect data at specified time / frequency resources and according to the measurement resource configuration provided by the network.

[0114] In action 208, the collected data may be used for AI / ML model training. The collected data may be used for the AI / ML model training and / or AI / ML model inference. The network or the UE may utilize the collected data for various AI / ML use cases such as beam management, positioning accuracy enhancement, CSI feedback enhancement, or mobility enhancement. In some implementations, if the UE determines in action 204 that the UE rejects or partially rejects the data collection configuration, the UE may not apply the data collection configuration or the UE may partially apply the data collection configuration based on the UE's capabilities and resource availability.

[0115] The NW-initiated data collection procedure illustrated in FIG. 2 may enable the network to proactively configure data collection at the UE when the network determines that such data collection may be necessary for system optimization or AI / ML model training. This network-initiated approach may be particularly beneficial in scenarios where the network has a broader view of system requirements and can coordinate data collection across multiple UEs for comprehensive AI / ML model training. The procedure may also reduce signaling overhead by eliminating the need for the UE to request data collection configuration when the network already knows that data collection is required.

[0116] Specifically, in FIG. 2, the UE may receive an RRC message and / or an information element including the data collection configuration from the serving cell. The serving cell may transmit the RRC message and / or the information element including the data collection configuration to the UE without receiving the UE's request in advance. The data collection configuration from the network may enable faster deployment of AI / ML data collection when the network determines that data collection may be beneficial for improving system performance. After reception of the data collection configuration, the UE may or may not transmit an acknowledgement message and / or an indicator to the serving cell to indicate whether the UE accepts or rejects the data collection configuration. If the UE determines that the UE accepts the data collection configuration, the UE may apply the data collection configuration. Based on the data collection configuration, the UE may therefore perform the data collection. The collected data may be used for the AI / ML model training and / or AI / ML model inference. In some implementations, if the UE determines that the UE rejects or partially rejects the data collection configuration, the UE may not apply the data collection configuration or the UE may partially apply the data collection configuration.

[0117] UE-request data collection or NW-initiated data collection

[0118] In some implementations, the serving cell or the NW may transmit an RRC message or L1 / L2 signaling (e.g., DCI, MAC CE) or broadcast system information to the UE, where the RRC message, L1 / L2 signaling, or system information may include various indicators to inform the UE about the data collection capabilities and permissions. For example, the RRC message, L1 / L2 signaling, or system information may include at least one of the following indications:

[0119] (1)　　　　an indication indicating whether the serving cell would (proactively) provide the data collection configuration,

[0120] (2)　　　　an indication indicating that the serving cell would (proactively) provide the data collection configuration,

[0121] (3)　　　　an indication indicating that the serving cell would not (proactively) provide the data collection configuration,

[0122] (4)　　　　an indication indicating whether the UE can (or is allowed to) transmit the data collection request to the serving cell,

[0123] (5)　　　　an indication indicating that the UE can (or is allowed to) transmit the data collection request to the serving cell,

[0124] (6)　　　　an indication indicating that the UE cannot (or is not allowed to) transmit the data collection request to the serving cell,

[0125] (7)　　　　an indication indicating whether the UE is allowed to perform the UE-request data collection,

[0126] (8)　　　　 an indication indicating that the UE is allowed to perform the UE-request data collection,

[0127] (9) an indication indicating that the UE is not allowed to perform the UE-request data collection,

[0128] (10) an indication indicating whether the serving cell supports the UE-request data collection,

[0129] (11) an indication indicating that the serving cell supports the UE-request data collection,

[0130] (12) an indication indicating that the serving cell does not support the UE-request data collection,

[0131] (13) an indication indicating whether the serving cell supports NW-initiated data collection,

[0132] (14) an indication indicating that the serving cell supports the NW-initiated data collection,

[0133] (15) an indication indicating that the serving cell does not support the NW-initiated data collection, or

[0134] (16) a parameter that is used for the UE-request data collection.

[0135] In some implementations, when the UE receives the information indicating whether the serving cell would (proactively) provide the data collection configuration, the UE may determine whether the serving cell would (proactively) provide the data collection configuration based on the received information. The determination may enable the UE to understand whether the UE needs to request the data collection configuration or wait for the network to provide the configuration proactively.

[0136] In some implementations, the information indicating whether the serving cell would (proactively) provide the data collection configuration may be a Boolean indicator, an ENUMERATED format {supported}, an ENUMERATED format {true}, an ENUMERATED format {supported, not supported}, or an ENUMERATED format {enabled, disabled}. These different format options may provide flexibility in how the network signals the capability to different UE implementations.

[0137] In some implementations, when the UE receives the information indicating whether the serving cell would (proactively) provide the data collection configuration, the UE may determine that the serving cell would (proactively) provide the data collection configuration according to the received information. For example, if the information is present with a value of '1', 'true', 'supported', or 'enabled', the UE may determine that the serving cell would (proactively) provide the data collection configuration. The presence of these positive indicators may signal to the UE that the network will initiate the data collection configuration without requiring a request from the UE.

[0138] In some implementations, when the UE receives the information indicating whether the serving cell would (proactively) provide the data collection configuration, the UE may determine that the serving cell would not (proactively) provide the data collection configuration according to the received information. For example, if the information is absent, has a value of '0', 'not supported', or 'disabled', the UE may determine that the serving cell would not (proactively) provide the data collection configuration. These negative indicators or the absence of the information may signal to the UE that the UE needs to initiate the data collection request if data collection is required for AI / ML purposes.

[0139] In some implementations, when the UE receives the information indicating that the serving cell would (proactively) provide the data collection configuration, the UE may determine that the serving cell would (proactively) provide the data collection configuration according to the information. This determination may enable the UE to prepare for receiving the data collection configuration without needing to send a request first. In some implementations, when the UE receives the information with an absent value / indication or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the serving cell would not (proactively) provide the data collection configuration according to the information.

[0140] In some implementations, when the UE receives the information indicating that the serving cell would not (proactively) provide the data collection configuration, the UE may determine that the serving cell would not (proactively) provide the data collection configuration according to the information. In some implementations, when the UE receives the information with an absent value or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the serving cell would (proactively) provide the data collection configuration according to the information. This default behavior may ensure backward compatibility with UEs that may not fully support the signaling mechanisms.

[0141] In some implementations, when the UE receives the information indicating whether the UE can or is allowed to transmit the data collection request to the serving cell, the UE may determine whether the UE can or is allowed to transmit the data collection request to the serving cell. In some implementations, the information indicating whether the UE can or is allowed to transmit the data collection request to the serving cell may be a Boolean indicator, an ENUMERATED format {allowed}, or an ENUMERATED format {allowed, not allowed}. In some implementations, when the UE receives the information indicating whether the UE can or is allowed to transmit the data collection request to the serving cell, the UE may determine that the UE can or is allowed to transmit the data collection request to the serving cell according to the information. For example, if the information is present, has a value of '1', or 'allowed', the UE may determine that the UE can or is allowed to transmit the data collection request to the serving cell. In some implementations, if the information is present, has a value of '1', or 'allowed', the UE may transmit the data collection request to the serving cell. In some implementations, if the information is present, has a value of '1', or 'allowed', the UE may transmit the data collection request to the serving cell within a predefined time duration. The predefined time duration may ensure that the request is transmitted in a timely manner while allowing the UE flexibility in scheduling the transmission. In some implementations, when the UE receives the information indicating whether the UE can or is allowed to transmit the data collection request to the serving cell, the UE may determine that the UE cannot or is not allowed to transmit the data collection request to the serving cell according to the information. For example, if the information is absent, has a value of '0', or 'not allowed', the UE may determine that the UE cannot or is not allowed to transmit the data collection request to the serving cell.

[0142] In some implementations, when the UE receives the information indicating that the UE can or is allowed to transmit the data collection request to the serving cell, the UE may determine that the UE can or is allowed to transmit the data collection request to the serving cell. In some implementations, when the UE receives the information with an absent value or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the UE cannot or is not allowed to transmit the data collection request to the serving cell.

[0143] In some implementations, when the UE receives the information indicating that the UE cannot or is not allowed to transmit the data collection request to the serving cell, the UE may determine that the UE cannot or is not allowed to transmit the data collection request to the serving cell. In some implementations, when the UE receives the information with an absent value / indication or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the UE can or is allowed to transmit the data collection request to the serving cell.

[0144] In some implementations, when the UE determines that the UE can or is allowed to transmit the data collection request to the serving cell, the UE may transmit the data collection request to the serving cell, or the UE may transmit the data collection request to the serving cell within a predefined time duration. The transmission of the data collection request may initiate the UE-request data collection procedure.

[0145] In some implementations, when the UE receives the information indicating whether the UE is allowed to perform the UE-request data collection, the UE may determine whether the UE is allowed to perform the UE-request data collection to the serving cell. In some implementations, the information indicating whether the UE is allowed to perform the UE-request data collection may be a Boolean indicator, an ENUMERATED format {allowed}, or an ENUMERATED format {allowed, not allowed}. In some implementations, when the UE receives the information indicating whether the UE is allowed to perform the UE-request data collection, the UE may determine that the UE is allowed to perform the UE-request data collection to the serving cell according to the information. For example, if the information is present, has a value of '1', or 'allowed', the UE may determine that the UE is allowed to perform the UE-request data collection to the serving cell. In some implementations, when the UE receives the information indicating whether the UE is allowed to perform the UE-request data collection, the UE may determine that the UE is not allowed to perform the UE-request data collection to the serving cell according to the information. For example, if the information is absent, has a value of '0', or 'not allowed', the UE may determine that the UE is not allowed to perform the UE-request data collection to the serving cell.

[0146] In some implementations, when the UE receives the information indicating that the UE is allowed to perform the UE-request data collection, the UE may determine that the UE is allowed to perform the UE-request data collection to the serving cell. The UE may further determine that the serving cell allows or implements the UE-request data collection. In some implementations, when the UE receives the information with an absent value / indication or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the UE is not allowed to perform the UE-request data collection to the serving cell. The UE may further determine that the serving cell does not allow or does not implement the UE-request data collection.

[0147] In some implementations, when the UE receives the information indicating that the UE is not allowed to perform the UE-request data collection, the UE may determine that the UE is not allowed to perform the UE-request data collection to the serving cell. The UE may further determine that the serving cell does not allow or does not implement the UE-request data collection. In some implementations, when the UE receives the information with an absent value or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the UE is allowed to perform the UE-request data collection to the serving cell. The UE may further determine that the serving cell allows or implements the UE-request data collection.

[0148] In some implementations, when the UE receives the information indicating whether the serving cell supports the UE-request data collection, the UE may determine whether the serving cell supports the UE-request data collection. In some implementations, the information indicating whether the serving cell supports the UE-request data collection may be a Boolean indicator, an ENUMERATED format {supported}, an ENUMERATED format {supported, not supported}, an ENUMERATED format {true}, or an ENUMERATED format {enabled, disabled}. In some implementations, when the UE receives the information indicating whether the serving cell supports the UE-request data collection, the UE may determine that the serving cell supports the UE-request data collection according to the information. For example, if the information is present, has a value of '1', 'true', 'supported', or 'enabled', the UE may determine that the serving cell supports the UE-request data collection. In some implementations, when the UE receives the information indicating whether the serving cell supports the UE-request data collection, the UE may determine that the serving cell does not support the UE-request data collection according to the information. For example, if the information is absent, has a value of '0', 'not supported', or 'disabled', the UE may determine that the serving cell does not support the UE-request data collection.

[0149] In some implementations, when the UE receives the information indicating that the serving cell supports the UE-request data collection, the UE may determine that the serving cell supports the UE-request data collection according to the information. In some implementations, when the UE receives the information with an absent value or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the serving cell does not support the UE-request data collection according to the information.

[0150] In some implementations, when the UE receives the information indicating that the serving cell does not support the UE-request data collection, the UE may determine that the serving cell does not support the UE-request data collection according to the information. In some implementations, when the UE receives the information with an absent value or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the serving cell supports the UE-request data collection according to the information.

[0151] In some implementations, when the UE receives the information indicating whether the serving cell supports the NW-initiated data collection, the UE may determine whether the serving cell supports the NW-initiated data collection. In some implementations, the information indicating whether the serving cell supports the NW-initiated data collection may be a Boolean indicator, an ENUMERATED format {supported}, an ENUMERATED format {true}, an ENUMERATED format {supported, not supported}, or an ENUMERATED format {enabled, disabled}. In some implementations, when the UE receives the information indicating whether the serving cell supports the NW-initiated data collection, the UE may determine that the serving cell supports the NW-initiated data collection according to the information. For example, if the information is present, has a value of '1', 'true', 'supported', or 'enabled', the UE may determine that the serving cell supports the NW-initiated data collection. In some implementations, when the UE receives the information indicating whether the serving cell supports the NW-initiated data collection, the UE may determine that the serving cell does not support the NW-initiated data collection according to the information. For example, if the information is absent, has a value of '0', 'not supported', or 'disabled', the UE may determine that the serving cell does not support the NW-initiated data collection.

[0152] In some implementations, when the UE receives the information indicating that the serving cell supports the NW-initiated data collection, the UE may determine that the serving cell supports the NW-initiated data collection according to the information. In some implementations, when the UE receives the information with an absent value or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the serving cell does not support the NW-initiated data collection according to the information.

[0153] In some implementations, when the UE receives the information indicating that the serving cell does not support the NW-initiated data collection, the UE may determine that the serving cell does not support the NW-initiated data collection according to the information. In some implementations, when the UE receives the information with an absent value or when the UE does not receive the information but the UE receives the RRC message, L1 / L2 signaling, and / or broadcast system information that is supposed to carry this information, the UE may determine that the serving cell supports the NW-initiated data collection according to the information.

[0154] In some implementations, the fact that the UE determines that the serving cell only supports the UE-request data collection may implicitly imply that the UE determines that the serving cell does not support the NW-initiated data collection. The UE may therefore perform the UE-request data collection and transmit the data collection request. This implicit determination may simplify the signaling overhead by allowing the network to signal only one capability when the capabilities are mutually exclusive. In some implementations, the fact that the UE determines that the serving cell does not support the NW-initiated data collection may implicitly imply that the UE determines that the serving cell only supports the UE-request data collection. The UE may therefore perform the UE-request data collection and transmit the data collection request.

[0155] In some implementations, the fact that the UE determines that the serving cell only supports the NW-initiated data collection may implicitly imply that the UE determines that the serving cell or serving RAN does not support the UE-request data collection. The UE may therefore perform the NW-initiated data collection without transmitting the data collection request. In some implementations, the fact that the UE determines that the serving cell does not support the UE-request data collection may implicitly imply that the UE determines that the serving cell only supports the NW-initiated data collection. The UE may therefore perform the NW-initiated data collection without transmitting the data collection request.

[0156] In some implementations, when the UE receives the information used for the UE-request data collection, the UE may determine that the serving cell supports the UE-request data collection. According to the information used for the UE-request data collection, the UE may further determine the time / frequency resources to transmit the data collection request and / or determine the content in the data collection request. The determination of time / frequency resources may ensure that the data collection request is transmitted using appropriate radio resources that minimize interference with other transmissions. Afterwards, the UE may transmit the data collection request to the serving cell.

[0157] Data collection configuration

[0158] In some implementations, the UE may receive an RRC message, e.g., a new RRC message, which includes or is the data collection configuration. The UE may receive the RRC message via SRB1 or SRB2 from the serving cell. The use of SRB1 or SRB2 may depend on the current RRC state of the UE and the priority of the data collection configuration. The UE may receive the RRC message by DL-DCCH. For example, the DL-DCCH-Message class, which is the set of RRC messages that may be sent from the network to the UE on the downlink DCCH logical channel, may include the new RRC message including the data collection configuration. The UE may receive the new RRC message with RLC AM entity or AM RLC entity. For example, the RLC-SAP used for the new RRC message including the data collection configuration may be AM. The use of AM mode may ensure reliable delivery of the data collection configuration. In some additional implementations, the RLC-SAP used for data collection may be configured in the data collection configuration. In addition, for one data collection configuration, only one RLC operation mode (e.g., AM, UM, or TM) may be configured to the UE to maintain consistency in the data collection procedure.

[0159] In some implementations, the UE may receive the RRC Reconfiguration message including the data collection configuration. The RRC Reconfiguration message may be an existing message that is extended to carry the data collection configuration, which may provide backward compatibility with existing RRC procedures.

[0160] In some implementations, upon receiving the data collection configuration, the UE may store the received data collection configuration, and / or the UE may apply the received data collection configuration. The UE may replace the stored data collection configuration with the received data collection configuration. The replacement mechanism may ensure that the UE always uses the most recent configuration provided by the network.

[0161] The content in the received data collection configuration may depend on the AI / ML use cases where the data collection is performed. In some implementations, different AI / ML use cases may require different types of data or different collection parameters to achieve optimal model performance. The content in the received data collection configuration may also depend on whether the configuration is for a UE-side AI / ML model, an NW-side AI / ML model, or a two-sided AI / ML model, and whether the UE reports the partial results of data collection to the NW.

[0162] In some implementations, the received data collection configuration may include the contents such as the measurement resource configuration, the data unit, the threshold values, the timer values, the associated IDs, the data collection report configuration, and the information for the acknowledgement message. Each of these components may serve a specific purpose in enabling efficient and effective data collection for AI / ML applications.

[0163] In some implementations, when the UE receives the data collection configuration including the measurement resource configuration, where the measurement resource configurations may include the time / frequency information of radio resources, the reference signal configuration, and the beam information used for the UE to perform measurements and / or beam management, the UE may apply the measurement resource configuration and / or replace the stored measurement resource configuration with the received measurement resource configuration. The measurement resource configuration may include or be the set B resource configuration. The time information, the time / frequency information of radio resources, and the beam information may be associated to ensure coordinated measurement procedures.

[0164] The time information may include the start time (or the absolute start time) of the radio resources, the offset time to the start time of the radio resources, the end time (or the absolute end time) of the radio resources, and the offset time to the end time of the radio resources to be measured. The time information may also include the periodicity at which the radio resources occur. The unit of the time information may be in frame, subframe, slot, mini-slot, symbol, second, or millisecond.

[0165] For example, the UE may start to perform the data collection and / or measurement at the (absolute) start time of the radio resources after the UE determines that the time information includes the (absolute) start time of the radio resources.

[0166] For example, the UE may start to perform the data collection and / or measurement at the (absolute) start time of the radio resources plus or minus the offset time to the start time of the radio resources after the UE determines the (absolute) start time of the radio resources and / or the offset time to the start time of the radio resources.

[0167] For example, the UE may stop performing the data collection and / or measurement at the (absolute) end time of the radio resources after the UE determines that the time information includes the (absolute) end time of the radio resources.

[0168] For example, the UE may stop performing the data collection and / or measurement at the (absolute) end time of the radio resources plus or minus the offset time to the end time of the radio resources after the UE determines the (absolute) end time and / or the offset time to the end time of the radio resources.

[0169] For example, if the (absolute) end time of the radio resources is absent, the UE may keep performing the data collection and / or measurement until receiving a signaling (e.g., an RRC message, a MAC CE, or a DCI) that indicates the UE to stop performing the data collection and / or measurement. This continuous collection mode may enable long-term data gathering for AI / ML model training purposes.

[0170] For example, if the (absolute) end time of the radio resources is absent, the UE may stop performing the data collection and / or measurement based on the UE's implementation. In addition, if the UE stops the data collection and / or measurement, the UE may transmit a signalling (e.g., a UCI, a MAC CE, or an RRC signalling) to indicate to the network that the UE has stopped the data collection and / or measurement.

[0171] For example, if the (absolute) end time of the radio resources is present, the UE may stop performing the data collection and / or measurement at any time before the (absolute) end time based on the UE's implementation. In addition, if the UE stops the data collection and / or measurement before the (absolute) end time, the UE may transmit a signalling (e.g., a UCI, a MAC CE, or an RRC signalling) to indicate to the network that the UE has stopped the data collection and / or measurement.

[0172] The time information may include the (absolute) start time, the offset time to the start time, the (absolute) end time, and the offset time to the end time for the UE to perform the data collection and / or measurement. The time information may also include the periodicity at which the radio resources occur. The unit of the time information may be in frame, subframe, slot, mini-slot, symbol, second, or millisecond.

[0173] For example, the UE may start to perform the data collection and / or measurement at the (absolute) start time after the UE determines that the time information includes the (absolute) start time for the UE to perform the data collection and / or measurement.

[0174] For example, the UE may start to perform the data collection and / or measurement at the (absolute) start time plus or minus the offset time to the start time after the UE determines the (absolute) start time and / or the offset time to the start time for the UE to perform the data collection and / or measurement. In some implementations, the offset time to the start time may correspond to the time value of periodicity, though this correspondence is not limiting.

[0175] For example, the UE may start to perform the data collection from a time point where the time point begins after a given time offset from when the UE receives the data collection configuration, and the UE may perform the data collection periodically based on the time information.

[0176] For example, the UE may stop performing the data collection and / or measurement at the (absolute) end time after the UE determines that the time information includes the (absolute) end time for the UE to perform the data collection and / or measurement.

[0177] For example, the UE may stop performing the data collection and / or measurement at the (absolute) end time plus or minus the offset time to the end time after the UE determines the (absolute) end time and / or the offset time to the end time for the UE to perform the data collection and / or measurement.

[0178] The reference signal configuration may include the information of SSB, CSI-RS, TRS, and / or PRS used for the UE to perform the data collection and / or measurement. These different reference signals may provide diverse measurement opportunities suitable for various AI / ML use cases.

[0179] The beam information may include the associated TCI state information (e.g., the TCI state ID, the joint TCI state ID, the TCI state type, or the DL TCI state ID) or the associated RS information (the SSB index and / or the CSI-RS index) used for the UE to perform measurements.

[0180] If the UE determines that some fields in the measurement resource configuration are absent, the UE may release or clear the stored values for the fields and / or keep storing and use the stored values for the fields.

[0181] In some implementations, when the UE receives the data collection configuration including the data unit information, where the data unit information may be the unit of the data that the UE collects and / or stores, the UE may apply the data unit information and / or replace the stored data unit information with the received data unit information. The data unit information may include or be the RSRP, the RSRQ, the SINR, or the SNR. If the UE determines that some fields in the data unit information are absent, the UE may release or clear the stored values for the fields and / or keep storing and use the stored values for the fields.

[0182] In some implementations, when the UE receives the data collection configuration including the threshold value information, where the threshold value information may include the threshold values above or below (and equal to) which the UE stores the collected data and / or collects the data, the UE may apply the threshold value information and / or replace the stored threshold value information with the received threshold value information. The unit of the threshold values may be RSRP, RSRQ, SNR, SINR, frame, subframe, slot, mini-slot, symbol, second, or millisecond. For example, among the collected data, the UE may store the collected or measured data whose values are above and / or equal to the threshold value. For example, the UE may collect the data which are measured for a period and the period is above and / or equal to a threshold value of time. If the UE determines that some fields in the threshold value information are absent, the UE may release or clear the stored values for the fields and / or keep storing and use the stored values for the fields.

[0183] In some implementations, when the UE receives the data collection configuration including the timer value information, where the timer value information may include the timer values used for the UE to determine when to start and / or stop the data collection and the offset timer values used for the UE to determine when to start and / or stop the data collection, the UE may apply the timer value information and / or replace the stored timer value information with the received timer value information. The timer value information may include the timer values during which the UE performs the data collection, the (absolute) time point or a time point calculated based on the offset timer value and a reference time point when the UE starts the data collection, and / or the (absolute) time point or a time point calculated based on the offset timer value and a reference time point when the UE stops the data collection. The unit of the timer values may be frame, subframe, slot, mini-slot, symbol, second, or millisecond.

[0184] For example, when the UE receives the timer value information, the UE may set a timer with the corresponding received timer value and then start the timer and start the data collection. The UE may stop the running timer when the UE stops performing the data collection or when the UE receives the instruction (e.g., an RRC message, a MAC CE, a DCI, or an indication) from the NW to stop performing the data collection.

[0185] For example, when the UE determines that the timer value is the offset timer value used for the UE to start the data collection, the UE may apply the offset timer value and / or the UE may determine a start time according to a reference time and the offset timer value, such as the reference time plus or minus the offset timer value. The UE may start to perform the data collection at the start time. The reference time may be, though not limited to, when the UE receives the data collection configuration, the (absolute) start time provided by the serving cell in the data collection configuration, or when the UE starts to perform the measurements.

[0186] For example, when the UE determines that the timer value is the offset timer value used for the UE to stop the data collection, the UE may apply the offset timer value and / or the UE may determine a stop time according to a reference time and the offset timer value, such as the reference time plus or minus the offset timer value. The UE may stop performing the data collection at the stop time. The reference time may be, though not limited to, when the UE receives the data collection configuration, the (absolute) stop or end time provided by the serving cell in the data collection configuration, or when the UE starts to perform the measurements.

[0187] In some implementations, when the UE receives the data collection configuration including the data collection report configuration, where the data collection report configuration may include information used for the UE to determine whether, when, or how to transmit the acknowledgement message / indicator to the serving cell, the UE may apply the data collection report configuration and / or replace the stored data collection report configuration with the received data collection report configuration. If the UE determines that some fields in the data collection report configuration are absent, the UE may release or clear the stored values for the fields and / or keep storing and use the stored values for the fields.

[0188] The data collection report configuration may include the information indicating whether the UE is allowed to or is required to transmit the acknowledgement message / indicator. The information may be a Boolean indicator or in a format of ENUMERATED {allowed} or in a format of ENUMERATED {allowed, not allowed}.

[0189] If the UE receives the information and the information is '1' or 'allowed', the UE may determine that the UE is allowed to or is required to transmit the acknowledgement message / indicator to the serving cell in response to the reception of the data collection configuration.

[0190] If the UE receives the information and the information is '0' or 'not allowed' or is an absent value, or if the UE receives the data collection report configuration with the absent or empty information, the UE may determine that the UE is not allowed or is not required to transmit the acknowledgement message / indicator to the serving cell in response to the reception of the data collection configuration.

[0191] The data collection report configuration may include the information indicating whether the UE is allowed to or is required to determine autonomously whether to transmit the acknowledgement message / indicator. The information may be a Boolean indicator or in a format of ENUMERATED {allowed} or in a format of ENUMERATED {allowed, not allowed}.

[0192] If the UE receives the information and the information is '1' or 'allowed', the UE may determine that the UE is allowed to determine autonomously whether to transmit the acknowledgement message / indicator to the serving cell in response to the reception of the data collection configuration.

[0193] If the UE receives the information and the information is '0' or 'not allowed' or is an absent value, or if the UE receives the data collection report configuration with the absent or empty information, the UE may determine that the UE is not allowed to determine autonomously whether to transmit the acknowledgement message / indicator to the serving cell in response to the reception of the data collection configuration.

[0194] In some implementations, if the UE determines that the UE is allowed to determine autonomously whether to transmit the acknowledgement message / indicator to the serving cell, the UE may ignore the information indicating whether the UE is allowed to or is required to transmit the acknowledgement message / indicator.

[0195] In some implementations, if the UE determines that the UE is not allowed to determine autonomously whether to transmit the acknowledgement message / indicator to the serving cell, the UE may determine based on the information indicating whether the UE is allowed to or is required to transmit the acknowledgement message / indicator.

[0196] The data collection report configuration may include the information indicating the time / frequency information of radio resources for the UE to transmit the acknowledgement message / indicator. For example, the UE may transmit a UCI as the acknowledgement message / indicator on the radio resources indicated by the time / frequency information of radio resources to the serving cell.

[0197] The data collection report configuration may include the information indicating the time / frequency information of radio resources for the UE to transmit the data collection results, such as the raw collected data or the data generated based on the collected data. For example, the UE may transmit the data collection results on the radio resources indicated by the time / frequency information of radio resources to the serving cell.

[0198] The data collection report configuration may include the information indicating the property of the collected data for the UE to transmit the data collection results. The information indicating the property of the collected data may include the periodicity, the duration, the order, and / or the statistical properties.

[0199] The periodicity may indicate how often the collected data is reported. The unit of the periodicity may be frame, subframe, second, millisecond, slot, mini-slot, or symbol.

[0200] The duration may indicate the period where the data is collected to be reported. The unit of the duration may be frame, subframe, second, millisecond, slot, mini-slot, or symbol.

[0201] The order may be in the format of ENUMERATED{ascending, descending}. If the value is 'ascending', the data to be reported may be arranged ascendingly. If the value is 'descending', the data to be reported may be arranged descendingly. If the value is absent, the order of the data to be reported may not be specified and may be based on UE implementation or based on time series.

[0202] The statistical properties may be in the format of ENUMERATED{median, average}. If the value is 'medium' (or 'median'), the data to be reported may be the medium / median value. For example, the data to be reported may be the medium / median among collected data or among collected data in a duration. If the value is 'average', the data to be reported may be the average value. For example, the data to be reported may be the average value among collected data or among collected data in a duration.

[0203] Data collection request

[0204] In some implementations, the UE may transmit an RRC message, e.g., a new RRC message, which includes or is the data collection request configuration / message. The UE may transmit the RRC message via SRB1 or SRB2 to the serving cell. The UE may transmit the RRC message by UL-DCCH. For example, the UL-DCCH-Message class, which is the set of RRC messages that may be sent from the UE to the network on the uplink DCCH logical channel, may include the new RRC message including the data collection request. The UE may transmit the new RRC message with RLC AM entity. For example, the RLC-SAP used for the new RRC message including the data collection request may be AM.

[0205] In some implementations, the UE may transmit an RRC message, e.g., a new RRC message, which includes or is the data collection request configuration / message. The UE may transmit the RRC message via SRB0 to the serving cell. The UE may transmit the RRC message by CCCH. For example, the CCCH-Message class, which is the set of RRC messages that may be sent from the UE to the network on the CCCH logical channel, may include the new RRC message including the data collection request configuration / indication. The UE may transmit the new RRC message with RLC TM entity. For example, the RLC-SAP used for the new RRC message including the data collection request may be TM.

[0206] In some implementations, the UE may set the corresponding information as the content in the data collection request and then submit the data collection request for transmission to lower layers.

[0207] The content in the data collection request may include one or more associated IDs, the model ID, the resource types, the UE battery / power / energy state, the UE memory state, the duration to collect data, and / or the capability of support of AI / ML function. These parameters may enable the network to configure appropriate data collection parameters tailored to the UE's capabilities and current state.

[0208] For example, the associated ID may indicate the corresponding use case, the AI / ML model for inference / training, the AI / ML functions, the AI / ML parameters, and / or the AI / ML settings that are related to the data collection. For example, the collected data may be applied for the corresponding use case, the AI / ML model for inference / training, the AI / ML functions, the AI / ML parameters, and / or the AI / ML settings which are indicated by the associated ID. The UE may indicate the associated ID for the data collection via the data collection request to the serving cell.

[0209] For example, the model ID may indicate the corresponding AI / ML model for inference / training or the AI / ML functions that are related to the data collection. For example, the collected data may be applied for the corresponding AI / ML model for inference / training or the AI / ML functions. The UE may indicate the model ID for the data collection request to the serving cell.

[0210] For example, the resource types may indicate the measured resources for data collection. The resource types may be the SSB, the CSI-RS, the TRS, or the PRS. The format of the resource types may be ENUMERATED{'SSB', 'CSI-RS', 'TRS', 'PRS'}. For instance, if the UE indicates the resource types to be 'SSB' in the content of the data collection request, this indication may mean that the UE would request the data collection based on SSB resources.

[0211] For example, the UE battery / power / energy state may indicate the UE status for data collection. The format may be ENUMERATED{'high', 'low'} or ENUMERATED{'high', 'medium', 'low'}. If the UE sets the content of the UE battery / power / energy state to be 'low', this setting may mean that the UE battery / power / energy state for data collection is low.

[0212] For example, the UE may expect the serving cell to configure the data collection configuration to the UE by considering the UE's data collection request and the UE's battery / power / energy state. This consideration may ensure that the data collection does not excessively drain the UE's battery resources.

[0213] For example, when the UE indicates that the UE battery / power / energy state is 'low', the UE may expect to receive information from the serving cell, where the information indicates the UE to fall back to a non-AI / ML procedure or indicates the UE not to perform the AI / ML models and / or AI / ML models for data collection.

[0214] For example, the UE memory state may indicate the UE status for data collection. The format may be ENUMERATED{'high', 'low'} or ENUMERATED{'high', 'medium', 'low'}. If the UE sets the content of the UE memory state to be 'low', this setting may mean that the UE's remaining memory for data collection, such as for storing the collected data, is low.

[0215] The UE may transmit the data collection request to the serving cell. After transmitting the data collection request, the serving cell may provide the data collection configuration, including setting the values in the data collection configuration, based on the information that the serving cell receives in the data collection request. The UE may receive the data collection configuration in response to the transmission of the data collection request.

[0216] In the UE-request data collection mechanism, the UE may transmit the data collection request to the serving cell. Upon the UE-request data collection being triggered, the UE may transmit the data collection request to the serving cell. The triggering conditions may depend on various factors such as the UE's capability, the AI / ML use case requirements, or network conditions.

[0217] Acknowledgement message / indicator

[0218] In some implementations, the UE may transmit an RRC message, e.g., a new RRC message, which includes or is the acknowledgement message / indicator. The UE may transmit the RRC message via SRB1 or SRB2 to the serving cell. The UE may transmit the RRC message by UL-DCCH. For example, the UL-DCCH-Message class, which is the set of RRC messages that may be sent from the UE to the network on the uplink DCCH logical channel, may include the new RRC message including the acknowledgement message / indicator. The UE may transmit the new RRC message with RLC AM entity. For example, the RLC-SAP used for the new RRC message including the acknowledgement message / indicator may be AM.

[0219] In some implementations, the acknowledgement message / indicator may be used for the rejection of the data collection configuration and / or the acceptance of the data collection configuration. This dual purpose may provide flexibility in the UE's response to the network's configuration.

[0220] In some implementations, if the UE determines that the UE can accept all the configurations in the data collection configuration, the UE may transmit the acknowledgement message / indicator to the serving cell, with the content of the acknowledgement message / indicator indicating the acceptance. For example, if the UE configures the configuration in the data collection configuration successfully, the UE may transmit the acknowledgement message / indicator to the serving cell, with the content of the acknowledgement message / indicator indicating the acceptance.

[0221] In some implementations, if the UE determines that the UE can accept all the configurations in the data collection configuration, the UE may not transmit the acknowledgement message / indicator to the serving cell. This implicit acceptance mechanism may reduce signaling overhead when the configuration is successfully applied.

[0222] In some implementations, if the UE determines that the UE cannot accept all the configurations in the data collection configuration, the UE may transmit the acknowledgement message / indicator to the serving cell, with the content of the acknowledgement message / indicator indicating the rejection. For example, if the UE partially configures the configuration in the data collection configuration successfully or if the UE cannot configure all the configurations in the data collection configuration successfully, the UE may transmit the acknowledgement message / indicator to the serving cell, with the content of the acknowledgement message / indicator indicating the rejection.

[0223] In some implementations, a Boolean indicator, an ENUMERATED{'accept', 'reject'}, an ENUMERATED{'accept'}, and / or an ENUMERATED{'reject'} may be included in the acknowledgement message / indicator.

[0224] In a case where the UE sets the content of the acknowledgement message / indicator indicating the acceptance, the UE may set the Boolean indicator to '1' or the field to be 'accept', or the UE may leave the field to be absent. The UE may then submit the acknowledgement message / indicator for transmission to lower layers.

[0225] In a case where the UE sets the content of the acknowledgement message / indicator indicating the rejection, the UE may set the Boolean indicator to '0' or the field to be 'reject', or the UE may leave the field to be absent. The UE may then submit the acknowledgement message / indicator for transmission to lower layers.

[0226] In a case where the UE sets the content of the acknowledgement message / indicator indicating the rejection, the UE may set the cause value in the content of the acknowledgement message / indicator. The cause value may be in the format of ENUMERATED{'power', 'memory', 'RS', spare1}. The cause value may indicate the reason for rejection. For example, if the UE sets the cause value to be 'power', the UE may indicate that the rejection of the data collection configuration is due to the UE battery / power / energy issue. For example, if the UE sets the cause value to be 'memory', the UE may indicate that the rejection of the data collection configuration is due to the UE memory issue.

[0227] In some implementations, after the UE transmits the acknowledgement message / indicator to the serving cell or after the UE submits the acknowledgement message / indicator to the lower layers, the UE may start to perform the data collection. This immediate start may ensure timely data collection for the AI / ML model training or inference.

[0228] In some implementations, after the UE transmits the acknowledgement message / indicator with the content indicating acceptance to the serving cell or after the UE submits the acknowledgement message / indicator with the content indicating acceptance to the lower layers, the UE may start to perform the data collection.

[0229] In some implementations, when the UE determines that the serving cell would not (proactively) provide the data collection configuration, the UE may need to transmit the data collection request for the data collection configuration when the UE determines to perform the data collection. This determination may trigger the UE-request data collection procedure.

[0230] In some implementations, when the UE determines that the serving cell would not (proactively) provide the data collection configuration, the UE may determine that the serving cell does not support the AI / ML model or does not support data collection for AI / ML models. This determination may influence the UE's subsequent behavior regarding AI / ML-related procedures.

[0231] FIG. 3 is a schematic diagram illustrating a method 300 for AI / ML data collection at a UE, according to an example implementation of the present disclosure. Although actions 302, 304, and 306 are illustrated, as separate actions, represented as independent blocks in FIG. 3, these separately illustrated actions should not be construed as to be necessarily order-dependent. The order in which the actions are performed in FIG. 3 is not intended to be construed as a limitation, and any number of the disclosed blocks may be combined in any order to implement the method, or an alternative method. Each of actions 302, 304, and 306 may be performed independent of the other actions, and may be omitted in some implementations of the present disclosure. Moreover, the method / process 300 may be combined with other procedures / methods described in the present disclosure. The method 300 may be performed by a UE, with each action of the method 300 corresponding to an operation executed by the UE.

[0232] In action 302, the UE may receive, from a BS, a first configuration for data collection, where the first configuration may include a measurement resource configuration, a threshold value, and a timer value. For example, the first configuration may be received through an RRC message via SRB1 or SRB2. In some implementations, this action may correspond to either action 104 in FIG. 1 for UE-request data collection or action 202 in FIG. 2 for NW-initiated data collection. The measurement resource configuration may include time / frequency information of radio resources, reference signal configurations including SSB information and CSI-RS information, and beam information for the UE to perform measurements. For example, the measurement resource configuration may include or be the set B resource configuration as described in the specification. The threshold value may indicate conditions for determining when to store measurement results, and may be expressed in units such as RSRP, RSRQ, SINR, or SNR. For example, the threshold value may define that only measurement results with RSRP values above -110 dBm are stored for AI / ML training, thereby ensuring that only high-quality measurements are collected. The timer value may indicate timing parameters for the data collection, including when the UE starts or stops storing the measurement results, and may be expressed in units such as milliseconds, frames, subframes, or slots. For example, the timer value may specify that the UE starts data collection 100 milliseconds after receiving the configuration and continues for a duration of 500 milliseconds.

[0233] In some implementations, prior to receiving the first configuration in action 302, the UE may have received a second configuration from the BS indicating whether the UE is allowed to request a data collection configuration. This second configuration may enable the UE to determine whether the UE should follow the UE-request data collection procedure or wait for the NW-initiated data collection procedure. For instance, if the second configuration indicates that the UE is allowed to transmit the data collection request, the UE may have transmitted a data collection request including information such as the UE battery / power / energy state, the UE memory state, and the desired resource types before receiving the first configuration.

[0234] In action 304, the UE may perform measurements based on the measurement resource configuration. The measurements may be performed on the configured reference signals at the specified time / frequency resources. The UE may measure various parameters such as RSRP, RSRQ, SINR, or SNR according to the measurement resource configuration. In some implementations, the measurements may be performed according to the time information included in the measurement resource configuration, which may include an absolute start time, an offset time to the start time, an absolute end time, and an offset time to the end time. For example, if the measurement resource configuration specifies SSB-based measurements with a periodicity of 20 milliseconds, the UE may perform RSRP measurements on SSB resources every 20 milliseconds starting from the configured start time. The measurements may be performed periodically based on the periodicity information included in the time / frequency information of the radio resources. The UE may utilize the beam information, which may include TCI state information such as TCI state ID, joint TCI state ID, TCI state type, or DL TCI state ID, or RS information such as SSB index and / or CSI-RS index, to perform the measurements with appropriate beam configurations. For instance, the UE may perform measurements on specific beams identified by TCI state IDs to collect beam-specific data for AI / ML-based beam management applications.

[0235] In action 306, in response to a condition being met, which is determined based on the threshold value and the timer value, the UE may store a measurement result for AI / ML model training. The condition may be evaluated by comparing the measured values against the threshold value. For example, the UE may store the measurement result when the measured value exceeds or equals the threshold value. In some implementations, the condition may involve multiple criteria, such as the measurement value exceeding the RSRP threshold and the measurement being performed within the time window defined by the timer value. The timer value may control when this storage operation occurs, such as defining a time window during which the UE stores measurement results or indicating specific start and stop times for data storage. For example, the timer value may indicate that the UE stores measurement results only during a specific 5-second window when the network traffic is expected to be representative of typical usage patterns. The stored measurement results may subsequently be used for training AI / ML models for various use cases including beam management, positioning accuracy enhancement, or CSI feedback enhancement.

[0236] In some implementations, following action 306, the UE may transmit an acknowledgement message / indicator to the BS, similar to action 106 in FIG. 1 or action 204 in FIG. 2. The acknowledgement message may indicate whether the UE has successfully applied the data collection configuration and started storing measurement results. If the UE cannot meet the conditions due to resource limitations, the UE may transmit a rejection with a cause value such as 'power' if the UE battery state is low or 'memory' if the UE has insufficient storage for the measurement results.

[0237] In some implementations, the UE may also transmit the stored measurement results to the BS according to a data collection report configuration if such configuration is provided. The data collection report configuration may specify the periodicity for reporting, such as every 100 milliseconds, the order of reported data such as ascending or descending based on measurement values, and statistical properties such as reporting the average or median of collected measurements. For example, the UE may report the median RSRP value of all stored measurements every 500 milliseconds to reduce the reporting overhead while providing representative data for AI / ML training.

[0238] In some implementations, the UE may receive, from the BS, a second configuration indicating whether the UE is allowed to request a data collection configuration.

[0239] In some implementations, in response to receiving the first configuration, the UE may store the first configuration or replace a previously stored configuration with the first configuration.

[0240] In some implementations, the measurement result may include at least one of a value of RSRP, a value of RSRQ, or a value of SINR.

[0241] In some implementations, the timer value may indicate a timing when the UE starts or stops storing the measurement result.

[0242] In some implementations, a unit of the timer value may be milliseconds.

[0243] In some implementations, the measurement resource configuration may include time / frequency information of radio resources, a reference signal configuration, and beam information. The reference signal configuration may include SSB information and CSI-RS information, and the time / frequency information of the radio resources may include periodicity information.

[0244] In some implementations, the UE may transmit, to the BS, an RRC message including information related to data collection. The information related to data collection may include power state information and memory state information, a value of the power state information is determined by the UE based on a power state of the UE, and a value of the memory state information is determined by the UE based on a remaining memory state of the UE.

[0245] The method 300 illustrated in FIG. 3 may provide a systematic approach for the UE to perform AI / ML data collection based on network configurations. The method 300 may ensure that data collection is performed efficiently with appropriate measurement configurations and storage conditions, thereby providing high-quality data for AI / ML model training while considering the UE's resource constraints. The flexibility in configuration parameters may allow the network to adapt the data collection procedure based on different AI / ML use cases, whether for UE-side models, NW-side models, or two-sided models, while the threshold and timer mechanisms may ensure that only relevant and timely data is collected for effective model training.

[0246] It should also be noted that the network device, such as the BS, may perform methods / actions corresponding to those performed by the UE. For example, the receiving actions performed by the UE may correspond to the transmitting / configuring actions of the network device; the transmitting actions performed by the UE may correspond to the receiving actions of the network device. That is, the network device and the UE may have reciprocally aligned roles in transmission and reception. For example, the BS may transmit, to a UE, a first configuration for data collection, the first configuration including a measurement resource configuration, a threshold value, and a timer value, where the measurement resource configuration is for configuring measurements to be performed by the UE, and the threshold value and the timer value are for determining a condition for storing a measurement result at the UE.

[0247] FIG. 4 is a block diagram illustrating node 400 for wireless communications, in accordance with various aspects of the present disclosure. As illustrated in FIG. 4, node 400 may include transceiver 420, processor 428, memory 434, one or more presentation components 438, and at least one antenna 436. Node 400 may also include a radio frequency (RF) spectrum band module, a BS communications module, a network communications module, and a system communications management module, Input / Output (I / O) ports, I / O components, and a power supply (not illustrated in FIG. 4).

[0248] Each of the components may directly or indirectly communicate with each other over one or more buses 440. Node 400 may be a UE or a BS that performs various functions disclosed with reference to FIGs. 1 to 3.

[0249] Transceiver 420 has transmitter 422 (e.g., transmitting / transmission circuitry) and receiver 424 (e.g., receiving / reception circuitry) and may be configured to transmit and / or receive time and / or frequency resource partitioning information. Transceiver 420 may be configured to transmit in different types of subframes and slots including, but not limited to, usable, non-usable, and flexibly usable subframes and slot formats. Transceiver 420 may be configured to receive data and control channels.

[0250] Node 400 may include a variety of computer-readable media. Computer-readable media may be any available media that may be accessed by node 400 and include volatile (and / or non-volatile) media and removable (and / or non-removable) media.

[0251] The computer-readable media may include computer-storage media and communication media. Computer-storage media may include both volatile (and / or non-volatile media), and removable (and / or non-removable) media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or data.

[0252] Computer-storage media may include RAM, ROM, EPROM, EEPROM, flash memory (or other memory technology), CD-ROM, Digital Versatile Disks (DVD) (or other optical disk storage), magnetic cassettes, magnetic tape, magnetic disk storage (or other magnetic storage devices), etc. Computer-storage media may not include a propagated data signal. Communication media may typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanisms and include any information delivery media.

[0253] The term “modulated data signal” may mean a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. Communication media may include wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, and other wireless media. Combinations of any of the aforementioned listed components should also be included within the scope of computer-readable media.

[0254] Memory 434 may include computer-storage media in the form of volatile and / or non-volatile memory. Memory 434 may be removable, non-removable, or a combination thereof. Example memory may include solid-state memory, hard drives, optical-disc drives, etc. As illustrated in FIG. 4, memory 434 may store a computer-readable and / or computer-executable instructions 432 (e.g., software codes) that are configured to, when executed, cause processor 428 to perform various functions disclosed herein, for example, with reference to FIGs. 1 to 3. Alternatively, instructions 434 may not be directly executable by processor 428 but may be configured to cause node 400 (e.g., when compiled and executed) to perform various functions disclosed herein.

[0255] Processor 428 (e.g., having processing circuitry) may include an intelligent hardware device, e.g., a Central Processing Unit (CPU), a microcontroller, an ASIC, etc. Processor 428 may include memory. Processor 428 may process data 430 and instructions 432 received from memory 434, and information transmitted and received via transceiver 420, the baseband communications module, and / or the network communications module. Processor 428 may also process information to send to transceiver 420 for transmission via antenna 436 to the network communications module for transmission to a CN.

[0256] One or more presentation components 438 may present data indications to a person or another device. Examples of presentation components 438 may include a display device, a speaker, a printing component, a vibrating component, etc.

[0257] In view of the present disclosure, it is obvious that various techniques may be used for implementing the disclosed concepts without departing from the scope of those concepts. Moreover, while the concepts have been disclosed with specific reference to certain implementations, a person of ordinary skill in the art may recognize that changes may be made in form and detail without departing from the scope of those concepts. As such, the disclosed implementations are to be considered in all respects as illustrative and not restrictive. It should also be understood that the present disclosure is not limited to the particular implementations disclosed and many rearrangements, modifications, and substitutions are possible without departing from the scope of the present disclosure.

Claims

1. A User Equipment (UE), the UE comprising: 　　　　at least one processor; and 　　　　at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the UE to: 　　　　receive, from a base station (BS), a first configuration for data collection, the first configuration comprising a measurement resource configuration, a threshold value, and a timer value; 　　　　perform measurements based on the measurement resource configuration; and 　　　　in response to a condition, which is determined based on the threshold value and the timer value, being met, store a measurement result for Artificial Intelligence / Machine Learning (AI / ML) model training.

2. The UE according to claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　receive, from the BS, a second configuration indicating whether the UE is allowed to request a data collection configuration.

3. The UE according to claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　in response to receiving the first configuration, store the first configuration or replace a previously stored configuration with the first configuration.

4. The UE according to claim 1, wherein the measurement result comprises at least one of: a value of Reference Signal Received Power (RSRP), a value of Reference Signal Received Quality (RSRQ), or a value of Signal-to-Interference-plus-Noise Ratio (SINR).

5. The UE according to claim 1, wherein the timer value indicates a timing when the UE starts or stops storing the measurement result.

6. The UE according to claim 1, wherein a unit of the timer value is milliseconds.

7. The UE according to claim 1, wherein: 　　　　the measurement resource configuration comprises time / frequency information of radio resources, a reference signal configuration, and beam information, 　　　　the reference signal configuration comprises Synchronization Signal / Physical Broadcast Channel (PBCH) Block (SSB) information and Channel State Information Reference Signal (CSI-RS) information, and 　　　　the time / frequency information of the radio resources comprises periodicity information.

8. The UE according to claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　transmit, to the BS, a Radio Resource Control (RRC) message comprising information related to data collection, 　　　　wherein: 　　　　the information related to data collection comprises power state information and memory state information, 　　　　a value of the power state information is determined by the UE based on a power state of the UE, and 　　　　a value of the memory state information is determined by the UE based on a remaining memory state of the UE.

9. A method performed by a User Equipment (UE) for Artificial Intelligence / Machine Learning (AI / ML) data collection, the method comprising: 　　　　receiving, from a base station (BS), a first configuration for data collection, the first configuration comprising a measurement resource configuration, a threshold value, and a timer value; 　　　　performing measurements based on the measurement resource configuration; and 　　　　in response to a condition, which is determined based on the threshold value and the timer value, being met, storing a measurement result for AI / ML model training.

10. A Base Station (BS), the BS comprising: 　　　　at least one processor; and 　　　　at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the BS to: 　　　　transmit, to a User Equipment (UE), a first configuration for data collection, the first configuration comprising a measurement resource configuration, a threshold value, and a timer value, wherein: 　　　　the measurement resource configuration is for configuring measurements to be performed by the UE, and 　　　　the threshold value and the timer value are for determining a condition for storing a measurement result at the UE.

11. The BS according to claim 10, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the BS to: 　　　　transmit, to the UE, a second configuration indicating whether the UE is allowed to request a data collection configuration.

12. The BS according to claim 10, wherein the measurement result comprises at least one of: a value of Reference Signal Received Power (RSRP), a value of Reference Signal Received Quality (RSRQ), or a value of Signal-to-Interference-plus-Noise Ratio (SINR).

13. The BS according to claim 10, wherein the timer value indicates a timing when the UE starts or stops storing the measurement result.

14. The BS according to claim 10, wherein a unit of the timer value is milliseconds.

15. The BS according to claim 10, wherein: 　　　　the measurement resource configuration comprises time / frequency information of radio resources, a reference signal configuration, and beam information, 　　　　the reference signal configuration comprises Synchronization Signal / Physical Broadcast Channel (PBCH) Block (SSB) information and Channel State Information Reference Signal (CSI-RS) information, and 　　　　the time / frequency information of the radio resources comprises periodicity information.

Images