UE assistance information for performing data collection for CSI prediction, beam management and positioning
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-06
- Publication Date
- 2026-08-13
Smart Images

Figure CN2025076006_13082026_PF_FP_ABST
Abstract
Description
UE ASSISTANCE INFORMATION FOR PERFORMING DATA COLLECTION FOR CSI PREDICTION, BEAM MANAGEMENT AND POSITIONINGBACKGROUND
[0001] Wireless communication networks provide integrated communication platforms and telecommunication services to wireless user devices. Example telecommunication services include telephony, data (e.g., voice, audio, and / or video data) , messaging, internet-access, and / or other services. The wireless communication networks have wireless access nodes that exchange wireless signals with the wireless user devices using wireless network protocols, such as protocols described in various telecommunication standards promulgated by the Third Generation Partnership Project (3GPP) . Example wireless communication networks include code division multiple access (CDMA) networks, time division multiple access (TDMA) networks, frequency-division multiple access (FDMA) networks, orthogonal frequency-division multiple access (OFDMA) networks, Long Term Evolution (LTE) , and Fifth Generation New Radio (5G NR) . The wireless communication networks facilitate mobile broadband service using technologies such as OFDM, multiple input multiple output (MIMO) , advanced channel coding, massive MIMO, beamforming, and / or other features.SUMMARY
[0002] In an aspect, a method for wireless communication includes sending a request for channel state information (CSI) reference signal (RS) having a configuration that enables training of an artificial intelligence or machine learning (AI / ML) model for estimation of channel quality; and receiving the CSI-RS having the configuration, the CSI-RS enabling training of the AI / ML model to estimate the channel quality.
[0003] In some implementations, the request indicates preferred timing information for a CSI-RS measurement window or a prediction window. In some implementations, the request indicates a speed of a device that generated the request, and wherein the timing information indicates a CSI-RS time domain separation in the CSI-RS measurement window. In some implementations, the timing information indicates a CSI-RS resource set periodicity. In some implementations, the timing information indicates CSI-RS burst periodicity. In some implementations, the timing information indicates one or more of: a value for a number of CSI-RSs included in each CSI-RS burst for the measurement window or for the prediction window; a length of the measurement window in a time domain; a length of the prediction window in the time domain; a separation in the time domain between the measurement window and the prediction window; and a spacing in the time domain of the CSI-RSs in the CSI-RS burst for the measurement window or for the prediction window. In some implementations, the configuration of the CSI-RS is aperiodic. In some implementations, the configuration of the CSI-RS is semi-periodic. In some implementations, the request indicates a density for CSI-RS resource mapping. In some implementations, the request indicates a preferred frequency domain allocation for the CSI-RS. In some implementations, the preferred frequency domain allocation is based on a channel prediction per resource block, a channel prediction per sub-band, a covariance matrix prediction, or an eigen-vector prediction. In some implementations, request indicates an association identifier representing a timing and spatial domain of a remote device.
[0004] In an aspect, a method for wireless communication includes sending a request for beam configuration information for training of an artificial intelligence or machine learning (AI / ML) model configured to perform beam management operations; and receiving the beam configuration information that enables training of the AI / ML model to perform the beam management operations.
[0005] In some implementations, the beam configuration information indicates a size of set A beams and a size of set B beams. In some implementations, the beam configuration information indicates a ratio of a size of set A beams to a size of set B beams. In some implementations, the beam configuration information includes a value of the CSI-RS density based user equipment link quality for set A beams and set B beams. In some implementations, the beam configuration information includes an association identifier representing a mapping between beams from set A and beams from set B. In some implementations, the beam configuration information includes an association identifier representing physical beam information including at least one of a beam direction, a beam 3-dB bandwidth, or a port mapping. In some implementations, the request indicates a configuration of receiver beam sweeping, the request indicating a number of repetitions for sweeping set A beams and set B beams. In some implementations, the request indicates a configuration of receiver beam sweeping, the request indicating a number of repetitions for sweeping B beams only. In some implementations, the request indicates a user equipment configuration that enables a network to configure a network side AI / ML model for beam management.
[0006] In an aspect, a method for wireless communication includes sending a request indicating a preferred downlink positioning reference signal (DL-PRS) configuration or network positioning information for training of an artificial intelligence or machine learning (AI / ML) model configured to generate device positioning information; and receiving DL-PRS information that enables training of the AI / ML model to generate the device positioning information. In some implementations, the request indicates a preferred on-demand DL-PRS configuration, a configuration for DL-PRS bandwidth aggregation, and an associated priority. In some implementations, the request indicates a preferred DL-PRS configuration for a candidate transmission / reception point (TRP) . In some implementations, the request indicates which DL-PRS resource sets across DL-PRS positioning frequency layers are linked for DL-PRS bandwidth aggregation. In some implementations, the request indicates a spatial direction of DL-PRS resources of TRPs associated with a base station. In some implementations, the request indicates a preferred validity area associated with a user equipment.
[0007] In some implementations, the request indicates preferred cell information including a physical cell identifier, global cell identifier, or PRS identifier of a candidate TRS for measurement. In some implementations, the request indicates preferred geographic coordinates of one or more TRPs served by a base station. In some implementations, the request indicates an association identifier that represents positioning information for a remote device. In some implementations, the request indicates preferred beam information including synchronization signal blocks (SSBs) of preferred beams, TRP beam information, or angle assistance information. In some implementations, the request indicates line of sight or non-line of sight (LOS / NLOS) information or a preferred positioning reference unit (PRU) . In some implementations, the DL-PRS information is represented by a single associated identifier. In some implementations, the DL-PRS information is represented by a set of associated identifiers. In some implementations, the device is a user equipment, and wherein the request is sent from the user equipment to a location management function (LMF) .
[0008] In an aspect, a system comprises one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations of the foregoing operations. In an aspect, a system comprises one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations of the foregoing operations. In an aspect, a non-transitory computer storage medium is encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations of the method of any of foregoing operations. In an aspect, an apparatus comprises one or more baseband processors configured to perform operations of the method of any of the foregoing operations.
[0009] In an aspect, an apparatus or user equipment includes one or more processors configured for wireless communication to perform operations comprising: preparing, for transmission by transmission circuitry, a request for channel state information (CSI) reference signal (RS) having a configuration that enables training of an artificial intelligence or machine learning (AI / ML) model for estimation of channel quality; and receiving, through receiver circuitry, the CSI-RS having the configuration, the CSI-RS enabling training of the AI / ML model to estimate the channel quality. In some implementations, the beam configuration information indicates a size of set A beams and a size of set B beams. In some implementations, the beam configuration information indicates a ratio of a size of set A beams to a size of set B beams. In some implementations, the beam configuration information includes a value of the CSI-RS density based user equipment link quality for set A beams and set B beams. In some implementations, the beam configuration information includes an association identifier representing a mapping between beams from set A and beams from set B. In some implementations, the beam configuration information includes an association identifier representing physical beam information including at least one of a beam direction, a beam 3-dB bandwidth, or a port mapping. In some implementations, the request indicates a configuration of receiver beam sweeping, the request indicating a number of repetitions for sweeping set A beams and set B beams. In some implementations, the request indicates a configuration of receiver beam sweeping, the request indicating a number of repetitions for sweeping B beams only. In some implementations, the request indicates a user equipment configuration that enables a network to configure a network side AI / ML model for beam management.
[0010] In an aspect, an apparatus or user equipment includes one or more processors configured for wireless communication to perform operations comprising: preparing, for transmission using transmitter circuitry, a request for beam configuration information for training of an artificial intelligence or machine learning (AI / ML) model configured to perform beam management operations; and receiving, through receiver circuitry, the beam configuration information that enables training of the AI / ML model to perform the beam management operations.
[0011] In an aspect, an apparatus or user equipment includes one or more processors configured for wireless communication to perform operations comprising: preparing, for transmission using transmitter circuitry, a request indicating a preferred downlink positioning reference signal (DL-PRS) configuration or network positioning information for training of an artificial intelligence or machine learning (AI / ML) model configured to generate device positioning information; and receiving, through receiver circuitry, DL-PRS information that enables training of the AI / ML model to generate the device positioning information. In some implementations, the request indicates preferred cell information including a physical cell identifier, global cell identifier, or PRS identifier of a candidate TRS for measurement. In some implementations, the request indicates preferred geographic coordinates of one or more TRPs served by a base station. In some implementations, the request indicates an association identifier that represents positioning information for a remote device. In some implementations, the request indicates preferred beam information including synchronization signal blocks (SSBs) of preferred beams, TRP beam information, or angle assistance information. In some implementations, the request indicates line of sight or non-line of sight (LOS / NLOS) information or a preferred positioning reference unit (PRU) . In some implementations, the DL-PRS information is represented by a single associated identifier. In some implementations, the DL-PRS information is represented by a set of associated identifiers. In some implementations, the device is a user equipment, and wherein the request is sent from the user equipment to a location management function (LMF) .
[0012] In an aspect, one or more processors are configured to perform operations for wireless communication, the operations comprising: encoding or preparing, for transmission using transmitter circuitry, a request for channel state information (CSI) reference signal (RS) having a configuration that enables training of an artificial intelligence or machine learning (AI / ML) model for estimation of channel quality; and decoding the CSI-RS having the configuration, the CSI-RS enabling training of the AI / ML model to estimate the channel quality.
[0013] In an aspect, one or more processors are configured to perform operations for wireless communication, the operations comprising: encoding or preparing, for transmission using transmitter circuitry, a request for beam configuration information for training of an artificial intelligence or machine learning (AI / ML) model configured to perform beam management operations; and decoding the beam configuration information that enables training of the AI / ML model to perform the beam management operations.
[0014] In an aspect, one or more processors are configured to perform operations for wireless communication, the operations comprising: encoding or preparing, for transmission using transmitter circuitry, a request indicating a preferred downlink positioning reference signal (DL-PRS) configuration or network positioning information for training of an artificial intelligence or machine learning (AI / ML) model configured to generate device positioning information; and decoding DL-PRS information that enables training of the AI / ML model to generate the device positioning information.
[0015] The details of one or more embodiments of these systems and methods are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of these systems and methods will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE FIGURES
[0016] FIG. 1 illustrates a wireless network.
[0017] FIG. 2 illustrates timing diagrams for channel state information reference signal (CSI-RS) measurements.
[0018] FIG. 3 illustrates timing diagrams for UE preference information for beam management.
[0019] FIG. 4 illustrates timing diagrams for UE preference information for beam management.
[0020] FIG. 5 illustrates an example process for communication of UE assistance information.
[0021] FIGS. 6A-6C each illustrates an example process for communication of UE preference information.
[0022] FIG. 7 illustrates a user equipment (UE) , according to some implementations.
[0023] FIG. 8 illustrates an access node, according to some implementations.DETAILED DESCRIPTION
[0024] This disclosure describes systems and methods for generation and signaling of UE assistance information (UAI) that is used by the UE to establish a communications link with a cellular network (such as a new radio (NR) or other 3GPP network) . The UE generates the UAI to request data from the network that assists the UE in collection of information to measure the UE’s environment. The collected information can describe channel conditions for one or more beams that the UE can then select for communication with a remote device of the network (such as a base station) . To assist the UE to collect the information describing the UE’s environment, the UE can generate a request (e.g., a trigger) to the network to perform data collection. The content of the request from the UE depends on the purpose for which the data are collected, as subsequently described.
[0025] This disclosure describes the content and signaling of the UE’s request for information from the network that allows for UE information collection. The request includes the UAI. The UE can train a model, such as an artificial intelligence or machine learning (AI / ML) model, after collecting the information describing the UE’s environment based on the network’s reply to the UAI. In an aspect, the UE can perform training of a UE-side AI / ML model for various purposes. For example, the UE can use the collected data to UE to train a UE-specific model to assist the UE for generation of a channel state information (CSI) prediction, for performing beam management operations (such as beam selection) , and / or for determining the UE’s positioning information. In some implementations, the UE transmits the UAI to the network (or a remote server) , and the network uses the UAI to collect data for the UE for training and / or execution of a UE-side model for performing one or more operations. In an aspect, the UE can send the measurements that are collected back to the network to allow the network to train a network-side model. For example, the network side model can be used for beam management operations.
[0026] The UE can send a request for data collection to the network to support a UE-side AI / ML model for performing CSI prediction at the UE, beam management, and / or positioning. For each of these contexts, the UE may request and process assistance information for categorizing the data collection for the UE. Specifically, the assistance information may specify an associated identifier (ID) that is indicative of (or a proxy of) base station-specific measurement information from the network that would otherwise be considered proprietary. For example, the associated ID can include a unique ID that represents a pre-determined / pre-specified set of one or more assistance data parameters. The network may send the requested information in radio resource control (RRC) configuration information for UE-side data collection, such as in either a layer 1 (L1) CSI configuration information or in an enhanced MDT configuration. In some implementations, the UE can request the UE-side data collection, and the request can indicate a suggested CSI resource or associated ID. In some implementations, for beam management for a UE-side model, the data collection related configuration (s) (e.g., measurement resources configuration) and associated ID (s) can be included in training data collection configuration. In some implementations, the UE can request the data from the network to perform UE-side model training. In some implementations, the network can provide the data for training the UE-side model at any point in time, with or without a UE request.
[0027] The network can control initiation and configuration for data collection for the UE-side model. The network can determine when to start or stop data collection and send the configuration information. The network can determine whether the UE is allowed to initiate a request for data collection. In some implementations, an indication from UE to network may be provided when the UE cannot perform data collection based on received configuration.
[0028] To collect data for training the UE-side model for positioning, several configurations are possible for the downlink (DL) Positioning Reference Signal PRS configuration for collecting training data. In a first option, the UE initiates the data collection for model training. The UE generates a request to a location management function (LMF) on a preferred DL PRS configuration for training data collection, such as an on-demand PRS. The LMF determines the DL PRS configuration for training data collection and provides the assistance data to the UE. In a second option, the LMF initiates the data collection for model training. The LMF determines the DL PRS configuration for training data collection and provides the assistance data to the UE. The UE can be a PRU and / or a non-PRU UE. The DL PRS configurations in the assistance data from LMF to UE are based on DL PRS configuration coordinated between the LMF and a base station (e.g., a next-generation node, gNB) .
[0029] This disclosure describes the content of the UAI for each of CSI prediction, beam management, and positioning. This disclosure describes the content and signaling of the UE request for each of these contexts, including selection of UE preference information. The preference information indicates to the network, in the request for data collection, what data are to be collected by the UE (e.g., how to perform measurements at the UE side) for use in the UE-side model. The network can provide the RS to enable this data collection. For example, for data collection at the UE for the UE-side model, the UE sends preferred RS configuration to the network so that the network can configure and transmit the RS correspondingly. The UE performs measurement and collection those data. For network side data collection, the UE sends these measurements back to the network.
[0030] FIG. 1 illustrates a wireless network 100, according to some implementations. The wireless network 100 includes a UE 102 and a base station 104 connected via one or more channels 106A, 106B across an air interface 108. The UE 102 and base station 104 communicate using a system that supports controls for managing the access of the UE 102 to a network via the base station 104.
[0031] In some implementations, the wireless network 100 may be a Non-Standalone (NSA) network that incorporates Long Term Evolution (LTE) and Fifth Generation (5G) New Radio (NR) communication standards as defined by the Third Generation Parmership Project (3GPP) technical specifications. For example, the wireless network 100 may be a E-UTRA (Evolved Universal Terrestrial Radio Access) -NR Dual Connectivity (EN-DC) network, or a NR-EUTRA Dual Connectivity (NE-DC) network. However, the wireless network 100 may also be a Standalone (SA) network that incorporates only 5G NR. Furthermore, other types of communication standards are possible, including future 3GPP systems (e.g., Sixth Generation (6G) ) systems, Institute of Electrical and Electronics Engineers (IEEE) 802.11 technology (e.g., IEEE 802.11a; IEEE 802.1 lb; IEEE 802.1 lg; IEEE 802.11-2007; IEEE 802.1 ln; IEEE 802.11-2012; IEEE 802.1 lac; or other present or future developed IEEE 802.11 technologies) , IEEE 802.16 protocols (e.g., WMAN, WiMAX, etc. ) , or the like. While aspects may be described herein using terminology commonly associated with 5G NR, aspects of the present disclosure can be applied to other systems, such as 3G, 4G, and / or systems subsequent to 5G (e.g., 6G) .
[0032] In the wireless network 100, the UE 102 and any other UE in the system may be, for example, laptop computers, smartphones, tablet computers, machine-type devices such as smart meters or specialized devices for healthcare, intelligent transportation systems, or any other wireless devices with or without a user interface. In network 100, the base station 104 provides the UE 102 network connectivity to a broader network (not shown) . This UE 102 connectivity is provided via the air interface 108 in a base station service area provided by the base station 104. In some implementations, such a broader network may be a wide area network operated by a cellular network provider or may be the Intemet. Each base station service area associated with the base station 104 is supported by antennas integrated with the base station 104. The service areas are divided into a number of sectors associated with certain antennas. Such sectors may be physically associated with fixed antennas or may be assigned to a physical area with tunable antennas or antenna settings adjustable in a beamforming process used to direct a signal to a particular sector.
[0033] The UE 102 includes control circuitry 110 coupled with transmit circuitry 112 and receive circuitry 114. The transmit circuitry 112 and receive circuitry 114 may each be coupled with one or more antennas. The control circuitry 110 may include various combinations of application-specific circuitry and baseband circuitry. The transmit circuitry 112 and receive circuitry 114 may be adapted to transmit and receive data, respectively, and may include radio frequency (RF) circuitry or front-end module (FEM) circuitry.
[0034] In various implementations, aspects of the transmit circuitry 112, receive circuitry 114, and control circuitry 110 may be integrated in various ways to implement the operations described herein. The control circuitry 110 may be adapted or configured to perform various operations such as those described elsewhere in this disclosure related to a UE.
[0035] The transmit circuitry 112 can perform various operations described in this specification. Additionally, the transmit circuitry 112 may transmit a plurality of multiplexed uplink physical channels. The plurality ofuplink physical channels may be multiplexed according to time division multiplexing (TDM) or frequency division multiplexing (FDM) along with carrier aggregation. The transmit circuitry 112 may be configured to receive block data from the control circuitry 110 for transmission across the air interface 108.
[0036] The receive circuitry 114 can perform various operations described in this specification. Additionally, the receive circuitry 114 may receive a plurality of multiplexed downlink physical channels from the air interface 108 and relay the physical channels to the control circuitry 110. The plurality of downlink physical channels may be multiplexed according to TDM or FDM along with carrier aggregation. The transmit circuitry 112 and the receive circuitry 114 may transmit and receive both control data and content data (e.g., messages, images, video, etc. ) structured within data blocks that are carried by the physical channels.
[0037] FIG. 1 also illustrates the base station 104. In implementations, the base station 104 may be an NG radio access network (RAN) or a 5G RAN, an E-UTRAN, a non-terrestrial cell, or a legacy RAN, such as a UTRAN or GERAN. As used herein, the term “NG RAN” or the like may refer to the base station 104 that operates in an NR or 5G wireless network 100, and the term “E-UTRAN” or the like may refer to a base station 104 that operates in an LTE or 4G wireless network 100. The UE 102 utilizes connections (or channels) 106A, 106B, each of which includes a physical communications interface or layer.
[0038] The base station 104 circuitry may include control circuitry 116 coupled with transmit circuitry 118 and receive circuitry 120. The transmit circuitry 118 and receive circuitry 120 may each be coupled with one or more antennas that may be used to enable communications via the air interface 108. The transmit circuitry 118 and receive circuitry 120 may be adapted to transmit and receive data, respectively, to any UE connected to the base station 104. The transmit circuitry 118 may transmit downlink physical channels includes of a plurality of downlink subframes. The receive circuitry 120 may receive a plurality of uplink physical channels from various UEs, including the UE 102.
[0039] In FIG. 1, the one or more channels 106A, 106B are illustrated as an air interface to enable communicative coupling, and can be consistent with cellular communications protocols, such as a GSM protocol, a CDMA network protocol, a UMTS protocol, a 3GPP LTE protocol, an Advanced long term evolution (LTE-A) protocol, a LTE-based access to unlicensed spectrum (LTE-U) , a 5G protocol, a NR protocol, an NR-based access to unlicensed spectrum (NR-U) protocol, and / or any of the other communications protocols discussed herein. In implementations, the UE 102 may directly exchange communication data via a ProSe interface. The ProSe interface may alternatively be referred to as a sidelink (SL) interface and may include one or more logical channels, including but not limited to a Physical Sidelink Control Channel (PSCCH) , a Physical Sidelink Control Channel (PSCCH) , a Physical Sidelink Discovery Channel (PSDCH) , and a Physical Sidelink Broadcast Channel (PSBCH) .
[0040] As previously discussed, the UAI can include information for use in several different contexts, including CSI prediction, beam management, and positioning. For example, for CSI prediction, the UAI can include parameter values for a measurement window and a prediction window. For example, for beam management, the UAI can include information specifying a number of minimum repetitions for UE receive (Rx) beam sweeping, in addition to set A and set B related parameters. For example, for performing positioning, the UAI can include the on-demand PRS for a preferred PRS configuration. These examples are subsequently described in further detail.
[0041] The UE can send the UAI to the network to indicate to the network a UE preference for one or more conditions for sending the CSI-RS to enable the UE to perform a measurement for the UE-side model data collection. For example, the preference may specify a RS configuration that enables UE measurement. In some implementations, UE measurements are sent back to the network and the network trains a network-side AI / ML model.
[0042] The UE preference can be based on the specific UE-side model and related to training or execution of the UE-side model. In an example, a first UE-preference for a beam management model can be different from a second preference for a positioning model. For example, for beam management, the UAl can indicate a quasi-co-location (QCL) relationship between set A and set B beams. The QCL relationship indicates how the UE should apply a receiver beam for measurement. The UAI can indicate the preference (e.g., report the preference) to the network for UE data collection. In another example, for positing, the UAI indicates a preferred DL PRS configuration, preferred general location information, preferred implicit assistance information, preferred angle / beam information, and / or preferred miscellaneous information to allow the UE to collect data to train the UE-side model.
[0043] FIG. 2 illustrates timing diagrams 200, 202, 204 for channel state information reference signal (CSI-RS) measurements that are used for CSI prediction. The timing diagrams 200, 202, 204 show parameters P, K, L, m, TRS, Tpred, d, and N that are used in CSI-RS configuration. The UE can send the network its preferred values for these parameters as preference data for timing, frequency, density, etc. as subsequently described. The parameters P, K, L, m, TRS, Tpred, d, and N are defined as follows. P represents a burst periodicity between CSI-RS bursts. P represents a burst periodicity between CSI-RS bursts, where each CSI-RS burst includes CSI-RS resources in measurement window and CSI-RS resources in prediction window. K is the CSI-RS resources in the measurement window, in a same CSI-RS resource set where the separation between 2 consecutive aperiodic CSI-RS resources is m slot (s) for the CSI-RS resources, m is the offset between two adjacent CSI-RS resources for the CMR in slots, within the measurement window. Trs represents a time of the end of a reference signal in measurement window. Tpred represents a time for the start of the prediction window, where a CSI-RS burst that is used as a ground truth for a predicted CSI-RS burst for training the AI / ML model, d is the offset between two adjacent CSI-RS resources for the CMR in slots, within the prediction window. L represents the time separation between the first predicted channel and the last measured channel. L represents the time difference between Tpred and Trs. N4 represents the number of CSI-RS resources in the prediction window.
[0044] The UE request for a preferred RS configuration for CSI prediction is now described. The CSI prediction can be performed by a UE-side model. For CSI prediction, the UAI can include preference information that indicates to the network how the network should configure the RS and transmit the RS over the wireless channel to the UE for enabling UE measurement. The UE performs a measurement based on the CSI-RS in measurement window and prediction window respectively. Those measurements are the ground truth information used for model training. The UE requests ground truth information for model training. After training, when deployed in the network, during inference, the UE only has the measurement window when executing the model.
[0045] The UE preference information enables the UE-side model to predict the CSI condition, as previously described. The UAI preference include CSI reference signal (RS) related configuration information including time domain information, density information, frequency domain information, and association ID information.
[0046] The time domain information includes values for the following parameters. The parameters are related to a UE speed. For example, the network configures the UE with two different CSI-RS configurations for UE to choose from. The UE speed (and Doppler factor) can affect the type of requested CSI-RS configuration. Ifthe UE is at high speed (above a speed threshold) , the UE may prefer a first CSI-RS configuration. If the UE is at a low speed (below a speed threshold) , the UE may prefer a second, different CSI-RS configuration. The UE will send the preferred CSI-RS configuration, and the network can transmit the CSI-RS based on UE's recommendation.
[0047] The time domain information can specify a UE prediction capability based on a prediction window length and a CSI-RS time domain separation value. For example, the UE can specify a prediction window the measurement window, indicating how many past samples the UE is requesting and how many samples are produced in the future, which can be specific to UE implementation. For example, if the measurement window is longer, the UE can improve prediction performance but there is increased complexity (e.g., more memory and processing bandwidth are needed) . The UE preference information can specify the measurement window lengths and then the measurement. For example, the CSI-RS domain separation can indicate that the UE traces back past 20 milliseconds, and each CSI-RS is separated by five milliseconds. In another example, the UE can trace back ten milliseconds and each CSI-RS is separated by 2.5 milliseconds.
[0048] The time domain information can specify a UE preference for a periodic, semi-periodic or aperiodic CSI-RS. The time domain information can include a value of a separation of CSI-RS bursts or a CSI-RS burst periodicity. This value is use for a UE model trained for aperiodic-CSI-RS or periodic CSI-RS. The preference can balance requirements for UE memory usage and sampling efficiency. Sampling efficiency refers to the UE collecting different, informative samples rather than redundant CSI-RS measurements such that each measurement provides new information that helps improve the prediction. Diverse data can be more likely when a minimum separation value P is introduced between CSI-RS bursts. The UE can avoid buffering unneeded data and avoid using redundant data to train the model. For example, diverse data can be averaged together to denoise the data and improve the model training.
[0049] The time domain information can differ depending on whether the UAI is for a periodic CSI-RS configuration for an aperiodic CSI-RS configuration. For a periodic CSI-RS configuration, the UAI indicates a CSI-RS resource set preferred periodicity. The UE partitions the received periodic CSI-RS into a measurement window and a prediction window based on UE implementation. For example, when the UE is moving at a speed such as 30 kilometers per hour and using frequency range 1 (FR1) such as 4 gigahertz (GHz) , the UE can send a preferred periodicity as 5 milliseconds. For an aperiodic-CSI-RS configuration, the UE can send preferred values for K, m, L, N4 and d to the network. For a semi-periodic CSI-RS configuration, the UE can send a preferred value for each of K, m, L, N4 and d to the network. In some implementations, the UAI can include a value of the CSI-RS burst periodicity, P. In some implementations, the UE can perform multiple measurements, separated by P time.
[0050] The density information included in the UAI for CSI-RS prediction includes the following parameters. The density information includes a value for UE signal to noise ratio (SINR) . The SINR parameter is related to how accurate a given UE measurement will be. The UE is in a low SINR range such that the SINR value falls below a predefmed threshold value, the CSI-RS pattern and / or density should be increased. The UAI can assist the network to increase the CSI-RS density and / or pattern. The measured data can be averaged together to denoise the data and improve the model training.
[0051] For the density information, in the CSI-RS-ResourceMappingconfiguration, the density value can be considered as 3, 1, or 0.5. The UE can request a higher density to improve channel estimation accuracy in certain situations, such as at a cell edge. Example preference data are shown below:
[0052]
[0053] The frequency domain information included in the UAI for CSI-RS prediction includes the following parameters. The frequency domain information includes a parameter indicating a number of resource blocks (RBs) that the CSI-RS occupies. The number parameter is related to a UE-side model for determination of time and frequency domain information.
[0054] The frequency domain allocation can depend on a UE model design and pre-processing. When time-frequency domain information is used, the particular preferred minimum RB bandwidth can depend on at least two factors. A first factor includes whether the channel is predicted per RB or per sub-band. A second factor includes whether the prediction is a channel prediction, covariance matrix prediction, or eigen-vector prediction. Based on these factors, the UAI preference information can recommend a particular preferred minimum RB bandwidth to the network. The frequency domain preference information can include the following.
[0055] CSI-FrequencyOccupation : : = SEQUENCE { startingRB INTEGER (0. . . maxNrofPhysicalResourceBlocks-1) , nrofRBs INTEGER (24. . . maxNrofPhysicalResourceBlocksPlus 1) , ... }
[0056] The UAI for CSI-RS prediction can include an association ID parameter. The association ID is used by the UE-side model when the model determines time and spatial domain information, such as spatial domain information across antenna ports. For example, the network antenna port mapping may be proprietary and hidden from the UE. The network can instead represent different port configurations using a virtual mapping with an association ID that does not explicitly include all information (like antenna mappings to ports, etc. ) . When the UE uses a spatial domain correlation for the AI model design, the preference information requests an association identifier.
[0057] FIG. 3 and FIG. 4 each illustrates timing diagrams for beam management configurations. The UE preference information is now described for the UE-side model for beam management by the UE. The preference information of the UE can include set A and set B related configuration information. The timing diagram 300 of FIG. 3 illustrates example CSI-RS resource sets of set A beams related to SSB bursts of set B beams. The timing diagram 302 illustrates example aperiodic RS transmission with repetition configuration information for beam sweeping for set A and set B, as subsequently described. Timing diagram 400 illustrates an example configuration of aperiodic CSI-RS transmissions for set A and set B including a quasi-co-location QCL relationship per resource, as subsequently described.
[0058] The configuration information indicates values for the sizes of set A and set B beams because the ratio of set A beams to set B beams can impact UE performance. For example, a UE using four beams to predict 32 beams will not be as accurate as a UE using 8 beams to predict 32 beams. The UE indicates the beam set size ratio in the preference information so that the network can provide the corresponding information for beam management. For example, if the network is optimized for using eight beams to produce 32 beams, but the network only provides four beams, then UE performance will not be optimized. Additionally or alternatively, the preference information for beam management can include a parameter indicating a request for a value of the CSI-RS density based UE link quality for set A and set B beams.
[0059] The preference information can include the association ID if these data were previously collected for set A and set B beams and when the UE-side model will use the dataset. The association ID for beam management is different from the association ID for CSI prediction. For beam management, the association ID represents the mapping between beams from set A and beams from set B. For example, the mapping can be between a wide beam and narrow beams. The association ID is proxy information so that the network can indicate the beam configuration to the UE without including detailed information such as beam direction, the three dB bandwidth of the beam, or other physical beam information. The association ID represents this physical beam information to the UE, and the UE can select / train the UE-side AI / ML model based on the received value of the association ID.
[0060] The preference information for beam management can include UE receiver beam related information. For example, the UE can indicate that receiver beam sweeping is to be performed (for a network prediction) , and the preference information can include a number of repetitions for each of the set A beams and set B beams separately. To enable UE Rx beam sweeping, the network configures the beams for set A and set B to repeat enough times for the UE to measure the beams in a complete sweep and identify the best Rx beam. The UE indicates a preferred repetition number to enable Rx beam sweeping. In some implementations, if set B beams or set A beams are for periodic reference signals, such as synchronization signal blocks, (SSB) , a number of repetitions is not needed because the UE can sweep the beams using any number of the repetitions.
[0061] In some implementations, the UE performs sweeping for set B and not set A. In this case, if each resource in set A is configured with QCL type D to one of the resources in set B, the UE does not request repetition data for set A beams because the UE can use the UE receiver beam for QCLd set A beams. This can occur for a wide beam to narrow beam prediction. For example, the set A beams are each configured as a QCL source for a wide beam. When the narrow beams are configured, the UE measures the wide beam using a beam sweep, and subsequently for measurement of the set A beams, the best beam of set B is used, and there does not need to be a set A beam sweep anymore. In some implementations, the repetition can be a set repetition, or each resource within the set repetition is ON.
[0062] Data collection for a network-side model for beam management can also be performed. In some implementations, for a SSB or CSI-RS configuration for network-side data collection, a set A resource set and a set B resource set are configured. Optionally, an association ID links the two resources. For the set A resource, the network can configure the QCL source configuration when the network ensure that the UE uses use the receiver beam for QCLd beams for inference and performance monitoring. The UAI includes the UE preferences for sending to the network for network-side models so that the UE can measure correspondingly and send the measurements to the network.
[0063] UE preference information is now described for the UE-side model for positioning prediction by the UE. In some implementations, the preference information is for positioning case 1 in which UE position indication is explicit. The UE preference information for positioning related to UE side condition includes five classes of information, as now described.
[0064] The first class of information (class 1) for position prediction by the UE-side model includes preferred DL PRS configuration information. In class 1, the UE indicates preference information all together. The UE preference information includes preferred on-demand DL-PRS-configurations, possibly together with information on desired configurations for DL-PRS bandwidth aggregation and associated priority. The UE preference information includes preferred individual DL PRS configurations. The UE preference information includes any DL-PRS configuration of candidate NR TRPs, which are identified by preferred general location information. The UE preference information includes an indication of which DL-PRS resource sets across DL-PRS positioning frequency layers should be linked for DL-PRS bandwidth aggregation. The UE preference information includes spatial direction information, such as azimuth, elevation, and so forth, of the DL-PRS Resources of the TRPs served by the base station, when the information is available. The UE preference information includes a listing of a preferred PRS / PRS aggregation priority. The UE preference information includes explicit information signaled corresponding to this class.
[0065] The second class of information (class 2) for position prediction by the UE-side model includes preferred general location information. The UE indicates preferences for individual downlink PRS configurations as a separate individual entities. The UE indicates downlink PRS configuration for candidate set of TRPs. The UE can indicate preferred general location information. The UE can indicate which of the PRS resource sets across the frequency should be linked. The UE can indicate a spatial direction and / or also indicate the PRS priority list. For example, the class 2 UE preference information includes a preferred validity area of the assistance data, such as using the area cell list if available. The UE preference information includes preferred cell specific information. The preferred cell specific information can include preferred physical cell IDs (PCIs) , global cell IDs (GCIs) , ARFCN, and PRS IDs of candidate NR TRPs for measurement, if available. The UE preference information includes preferred geographical coordinates of the TRPs served by the base station. The preferred geographical coordinates can include a transmission reference location for each DL-PRS resource ID, reference location for the transmitting antenna of the reference TRP, and / or relative locations for transmitting antennas of other TRPs. The UE preference information includes implicit information or an associated ID corresponding to this class that includes a proxy ID for representing sets of class 2 information (such as positioning / spatial information) for the UE to use for training / execution of the UE-side model. The UE indicates for class 2 information that, for its model, a set of preferred general locations to which that the UE maps, and the network can respond either explicitly with the positioning / spatial data or implicitly with associated ID value (s) .
[0066] The third class of information (class 3) for position prediction by the UE-side model includes preferred implicit information. The class 3 preference information can include an association ID ifthese data were previously collected and when the UE-side model uses these data for the prediction. In some implementations, the class 3 preference information includes the association ID when the association ID is associated with known non-explicit information.
[0067] The fourth class of information (class 4) for position prediction by the UE-side model includes preferred angle and / or beam information. The preferred beam information can include the SSBs of preferred beams. The preferred beam information can include TRP beam / antenna information (including azimuth angle, zenith angle and relative power between PRS resources per angle per TRP) of preferred beams.The angle information can include the mean and tolerance of expected angle assistance information. The class 4 information can include any implicit information and / or the associated ID information corresponding to this class.
[0068] The fifth class of information (class 5) for position prediction by the UE-side model includes miscellaneous information. This information can include existing LOS / NLOS information and / or preferred PRUs for PRU assistance information.
[0069] The associated IDs provided by the network can cover one or more classes or various combinations thereof. The various information indicated in each class can be combined in different ways either explicitly (by the UE requesting multiple classes) or implicitly by associated IDs. In some implementations, a single associated ID can represent information from multiple classes.
[0070] FIG. 5 illustrates an example process 500 for communication of UE assistance information for indication of UE preference data for positioning. The signaling of AI / ML positioning UAI information is now described. The UE can send the preference information described previously to the network for the UE-side model example so that the UE-side model has data for training and / or execution. The signaling from the UE to the network can be as follows. In a first option, the UE sends one associated ID that can cover all the implicit requested information. In a second option, the UE sends more than one identifier with each associated ID covering one or more classes of information. For example, an identifier with the associated ID can indicate location information only or, in another example, location and angle information together.
[0071] The UE or LMF may request the UAI using a procedure such as an on-demand PRS procedure. The procedure can be as follows. In step 502, the UE requests assistance information using AI / ML RequestAssistanceInformation information in the LPP. In step 504, the LMF responds to the UE with AI / ML provideAssistanceInformation information that may include explicit and implicit information such as the associated ID. In step 506, the UE indicates the AI / ML preference data based on the on-demand PRS request / response procedure or an equivalent on-demand UAI request / response procedure. The request procedure can be class specific, associated ID specific, or UAI-element specific.
[0072] FIG. 6A illustrates an example process 600 for communication of UE preference information. For clarity of presentation, the description that follows generally describes process 600 in the context of the other figures in this description. For example, process 600 can be performed by UE 102 of FIG. 1. It will be understood that process 600 can be performed, for example, by any suitable system, environment, software, hardware, or a combination of systems, environments, software, and hardware, as appropriate. In some implementations, various steps of method 600 can be run in parallel, in combination, in loops, or in any order. The process 600 includes sending (602) a request for channel state information (CSI) reference signal (RS) having a configuration that enables training of an artificial intelligence or machine learning (AI / ML) model for estimation of channel quality. The process 600 includes receiving (604) the CSI-RS having the configuration, the CSI-RS enabling training of the AI / ML model to estimate the channel quality. In some implementations, the process 600 includes training (606) the AI / ML model to estimate the channel quality.
[0073] FIG. 6B illustrates an example process 620 for communication of UE preference information. For clarity of presentation, the description that follows generally describes process 620 in the context of the other figures in this description. For example, process 620 can be performed by UE 102 of FIG. 1. It will be understood that process 620 can be performed, for example, by any suitable system, environment, software, hardware, or a combination of systems, environments, software, and hardware, as appropriate. In some implementations, various steps of method 620 can be run in parallel, in combination, in loops, or in any order. The process 620 includes sending (622) a request for beam configuration information for training of an artificial intelligence or machine learning (AI / ML) model configured to perform beam management operations. The process 620 includes receiving (624) the beam configuration information that enables training of the AI / ML model to perform the beam management operations. In some implementations, the process 620 includes training (626) the AI / ML model to perform the beam management operations.
[0074] FIG. 6C illustrates an example process 640 for communication of UE preference information. For clarity of presentation, the description that follows generally describes process 640 in the context of the other figures in this description. For example, process 640 can be performed by UE 102 of FIG. 1. It will be understood that process 640 can be performed, for example, by any suitable system, environment, software, hardware, or a combination of systems, environments, software, and hardware, as appropriate. In some implementations, various steps of method 640 can be run in parallel, in combination, in loops, or in any order. The process 600 includes sending (640) a request indicating a preferred downlink positioning reference signal (DL-PRS) configuration or network positioning information for training of an artificial intelligence or machine learning (AI / ML) model configured to generate device positioning information. The process 640 includes receiving (642) DL-PRS information that enables training of the AI / ML model to generate the device positioning information. The process 640 can include training the AI / ML model to generate the device positioning information.
[0075] FIG. 7 illustrates a UE 700, according to some implementations. The UE 700 may be similar to and substantially interchangeable with UE 102 of FIG. 1.
[0076] The UE 700 may be any mobile or non-mobile computing device, such as, for example, mobile phones, computers, tablets, industrial wireless sensors (for example, microphones, pressure sensors, thermometers, motion sensors, accelerometers, inventory sensors, electric voltage / current meters, etc. ) , video devices (for example, cameras, video cameras, etc. ) , wearable devices (for example, a smart watch) , relaxed-IoT devices.
[0077] The UE 700 may include processors 702, RF interface circuitry 704, memory / storage 706, user interface 708, sensors 710, driver circuitry 712, power management integrated circuit (PMIC) 714, antenna structure 716, and battery 718. The components of the UE 700 may be implemented as integrated circuits (ICs) , portions thereof, discrete electronic devices, or other modules, logic, hardware, software, firmware, or a combination thereof. The block diagram of FIG. 7 is intended to show a high-level view of some of the components of the UE 700. However, some of the components shown may be omitted, additional components may be present, and different arrangement of the components shown may occur in other implementations.
[0078] The components of the UE 700 may be coupled with various other components over one or more interconnects 720, which may represent any type of interface, input / output, bus (local, system, or expansion) , transmission line, trace, optical connection, etc. that allows various circuit components (on common or different chips or chipsets) to interact with one another.
[0079] The processors 702 may include processor circuitry such as, for example, baseband processor circuitry (BB) 722A, central processor unit circuitry (CPU) 722B, and graphics processor unit circuitry (GPU) 722C. The processors 702 may include any type of circuitry or processor circuitry that executes or otherwise operates computer-executable instructions, such as program code, software modules, or functional processes from memory / storage 706 to cause the UE 700 to perform operations as described herein.
[0080] In some implementations, the baseband processor circuitry 722A may access a communication protocol stack 724 in the memory / storage 706 to communicate over a 3GPP compatible network. In general, the baseband processor circuitry 722A may access the communication protocol stack to: perform user plane functions at a physical (PHY) layer, medium access control (MAC) layer, radio link control (RLC) layer, packet data convergence protocol (PDCP) layer, service data adaptation protocol (SDAP) layer, and PDU layer; and perform control plane functions at a PHY layer, MAC layer, RLC layer, PDCP layer, RRC layer, and a non-access stratum layer. In some implementations, the PHY layer operations may additionally / alternatively be performed by the components of the RF interface circuitry 704. The baseband processor circuitry 722A may generate or process baseband signals or waveforms that carry information in 3GPP-compatible networks. In some implementations, the waveforms for NR may be based cyclic prefix orthogonal frequency division multiplexing (OFDM) “CP-OFDM” in the uplink or downlink, and discrete Fourier transform spread OFDM “DFT-S-OFDM” in the uplink.
[0081] In some examples, measurement data from the UE 700 can be fed to AI / ML logic 726. The AI / ML logic 726 can include one or more learning-based and / or non-learning-based models for perceiving, synthesizing, and inferring information. Persons skilled in the art will appreciate that the AI / ML logic 726 can include any suitable number of processes to enable the UE to perform beam management operations, CSI prediction, or generate a positioning estimate based on input UE measurement data.
[0082] Persons of ordinary skill in the art will appreciate that AI / ML logic 726 can include any suitable machine learning models that are well-known or widely available such as regression techniques, classification techniques, neural networks, and deep learning networks. In instances where AI / ML logic 726 comprises a machine-learning based model, AI / ML logic 726 can be trained to perform beam management operations, generate a CSI prediction, or generate positioning estimates for one or more UEs based on UE measurement data using one or more well-known or widely available training techniques such as supervised learning, semi-supervised learning, unsupervised learning, and / or reinforcement learning techniques. The training data can include the aforementioned UE measurement data.
[0083] The memory / storage 706 may include one or more non-transitory, computer-readable media that includes instructions (for example, communication protocol stack 724) that may be executed by one or more of the processors 702 to cause the UE 700 to perform various operations described herein. The memory / storage 706 include any type of volatile or non-volatile memory that may be distributed throughout the UE 700. In some implementations, some of the memory / storage 706 may be located on the processors 702 themselves (for example, L1 and L2 cache) , while other memory / storage 706 is external to the processors 702 but accessible thereto via a memory interface. The memory / storage 706 may include any suitable volatile or non-volatile memory such as, but not limited to, dynamic random access memory (DRAM) , static random access memory (SRAM) , erasable programmable read only memory (EPROM) , electrically erasable programmable read only memory (EEPROM) , Flash memory, solid-state memory, or any other type of memory device technology.
[0084] The RF interface circuitry 704 may include transceiver circuitry and radio frequency front module (RFEM) that allows the UE 700 to communicate with other devices over a radio access network. The RF interface circuitry 704 may include various elements arranged in transmit or receive paths. These elements may include, for example, switches, mixers, amplifiers, filters, synthesizer circuitry, control circuitry, etc.
[0085] In the receive path, the RFEM may receive a radiated signal from an air interface via antenna structure 716 and proceed to filter and amplify (with a low-noise amplifier) the signal. The signal may be provided to a receiver of the transceiver that downconverts the RF signal into a baseband signal that is provided to the baseband processor of the processors 702.
[0086] In the transmit path, the transmitter of the transceiver up-converts the baseband signal received from the baseband processor and provides the RF signal to the RFEM. The RFEM may amplify the RF signal through a power amplifier prior to the signal being radiated across the air interface via the antenna 716. In various implementations, the RF interface circuitry 704 may be configured to transmit / receive signals in a manner compatible with NR access technologies.
[0087] The antenna 716 may include antenna elements to convert electrical signals into radio waves to travel through the air and to convert received radio waves into electrical signals. The antenna elements may be arranged into one or more antenna panels. The antenna 716 may have antenna panels that are omnidirectional, directional, or a combination thereof to enable beamforming and multiple input, multiple output communications. The antenna 716 may include microstrip antennas, printed antennas fabricated on the surface of one or more printed circuit boards, patch antennas, phased array antennas, etc. The antenna 716 may have one or more panels designed for specific frequency bands including bands in FR1 or FR2.
[0088] The user interface 708 includes various input / output (I / O) devices designed to enable user interaction with the UE 700. The user interface 708 includes input device circuitry and output device circuitry. Input device circuitry includes any physical or virtual means for accepting an input including, inter alia, one or more physical or virtual buttons (for example, a reset button) , a physical keyboard, keypad, mouse, touchpad, touchscreen, microphones, scanner, headset, or the like. The output device circuitry includes any physical or virtual means for showing information or otherwise conveying information, such as sensor readings, actuator position (s) , or other like information. Output device circuitry may include any number or combinations of audio or visual display, including, inter alia, one or more simple visual outputs / indicators (for example, binary status indicators such as light emitting diodes “LEDs” and multi-character visual outputs) , or more complex outputs such as display devices or touchscreens (for example, liquid crystal displays “LCDs, ” LED displays, quantum dot displays, projectors, etc. ) , with the output of characters, graphics, multimedia objects, and the like being generated or produced from the operation of the UE 700.
[0089] The sensors 710 may include devices, modules, or subsystems whose purpose is to detect events or changes in its environment and send the information (sensor data) about the detected events to some other device, module, subsystem, etc. Examples of such sensors include, inter alia, inertia measurement units including accelerometers, gyroscopes, or magnetometers; microelectromechanical systems or nanoelectromechanical systems including 3-axis accelerometers, 3-axis gyroscopes, or magnetometers; level sensors; temperature sensors (for example, thermistors) ; pressure sensors; image capture devices (for example, cameras or lensless apertures) ; light detection and ranging sensors; proximity sensors (for example, infrared radiation detector and the like) ; depth sensors; ambient light sensors; ultrasonic transceivers; microphones or other like audio capture devices; etc.
[0090] The driver circuitry 712 may include software and hardware elements that operate to control particular devices that are embedded in the UE 700, attached to the UE 700, or otherwise communicatively coupled with the UE 700. The driver circuitry 712 may include individual drivers allowing other components to interact with or control various input / output (I / O) devices that may be present within, or connected to, the UE 700. For example, driver circuitry 712 may include a display driver to control and allow access to a display device, a touchscreen driver to control and allow access to a touchscreen interface, sensor drivers to obtain sensor readings of sensor circuitry 710 and control and allow access to sensor circuitry 710, drivers to obtain actuator positions of electro-mechanic components or control and allow access to the electro-mechanic components, a camera driver to control and allow access to an embedded image capture device, audio drivers to control and allow access to one or more audio devices.
[0091] The PMIC 714 may manage power provided to various components of the UE 700. In particular, with respect to the processors 702, the PMIC 714 may control power-source selection, voltage scaling, battery charging, or DC-to-DC conversion.
[0092] In some implementations, the PMIC 714 may control, or otherwise be part of, various power saving mechanisms of the UE 700. A battery 718 may power the UE 700, although in some examples the UE 700 may be mounted deployed in a fixed location and may have a power supply coupled to an electrical grid. The battery 718 may be a lithium ion battery, a metal-air battery, such as a zinc-air battery, an aluminum-air battery, a lithium-air battery, and the like. In some implementations, such as in vehicle-based applications, the battery 718 may be a typical lead-acid automotive battery.
[0093] FIG. 8 illustrates an access node 800 (e.g., a base station or gNB) , according to some implementations. The access node 800 may be similar to and substantially interchangeable with base station 104. The access node 800 may include processors 802, RF interface circuitry 804, core network (CN) interface circuitry 806, memory / storage circuitry 808, and antenna structure 810.
[0094] The components of the access node 800 may be coupled with various other components over one or more interconnects 812. The processors 802, RF interface circuitry 804, memory / storage circuitry 808 (including communication protocol stack 814) , antenna structure 810, and interconnects 812 may be similar to like-named elements shown and described with respect to FIG. 7. For example, the processors 802 may include processor circuitry such as, for example, baseband processor circuitry (BB) 816A, central processor unit circuitry (CPU) 816B, and graphics processor unit circuitry (GPU) 816C.
[0095] In some examples, measurement data from a UE (such as UE 700) can be fed to AI / ML logic 818. The AI / ML logic 818 can include one or more learning-based and / or non-learning-based models for perceiving, synthesizing, and inferring information. Persons skilled in the art will appreciate that the AI / ML logic 818 can include any suitable number of processes to enable the access node to perform beam management operations or generate positioning estimates for one or more UEs based on input UE measurement data.
[0096] Persons of ordinary skill in the art will appreciate that AI / ML logic 818 can include any suitable machine learning models that are well-known or widely available such as regression techniques, classification techniques, neural networks, and deep learning networks. In instances where AI / ML logic 818 comprises a machine-learning based model, AI / ML logic 818 can be trained to perform beam management operations or generate positioning estimates for one or more UEs based on UE measurement data using one or more well-known or widely available training techniques such as supervised learning, semi-supervised learning, unsupervised learning, and / or reinforcement learning techniques. The training data can include the aforementioned UE measurement data.
[0097] The CN interface circuitry 806 may provide connectivity to a core network, for example, a 5th Generation Core network (5GC) using a 5GC-compatible network interface protocol such as carrier Ethernet protocols, or some other suitable protocol. Network connectivity may be provided to / from the access node 800 via a fiber optic or wireless backhaul. The CN interface circuitry 806 may include one or more dedicated processors or FPGAs to communicate using one or more of the aforementioned protocols. In some implementations, the CN interface circuitry 806 may include multiple controllers to provide connectivity to other networks using the same or different protocols.
[0098] As used herein, the terms “access node, ” “access point, ” or the like may describe equipment that provides the radio baseband functions for data and / or voice connectivity between a network and one or more users. These access nodes can be referred to as BS, gNBs, RAN nodes, eNBs, NodeBs, RSUs, TRxPs or TRPs, and so forth, and can include ground stations (e.g., terrestrial access points) or satellite stations providing coverage within a geographic area (e.g., a cell) . As used herein, the term “NG RAN node” or the like may refer to an access node 800 that operates in an NR or 5G system (for example, a gNB) , and the term “E-UTRAN node” or the like may refer to an access node 800 that operates in an LTE or 4G system (e.g., an eNB) . According to various implementations, the access node 800 may be implemented as one or more of a dedicated physical device such as a macrocell base station, and / or a low power (LP) base station for providing femtocells, picocells or other like cells having smaller coverage areas, smaller user capacity, or higher bandwidth compared to macrocells.
[0099] In some implementations, all or parts of the access node 800 may be implemented as one or more software entities running on server computers as part of a virtual network, which may be referred to as a CRAN and / or a virtual baseband unit pool (vBBUP) . In V2X scenarios, the access node 800 may be or act as a “Roadside Unit. ” The term “Roadside Unit” or “RSU” may refer to any transportation infrastructure entity used for V2X communications. An RSU may be implemented in or by a suitable RAN node or a stationary (or relatively stationary) UE, where an RSU implemented in or by a UE may be referred to as a “UE-type RSU, ” an RSU implemented in or by an eNB may be referred to as an “eNB-type RSU, ” an RSU implemented in or by a gNB may be referred to as a “gNB-type RSU, ” and the like.
[0100] Various components may be described as performing a task or tasks, for convenience in the description. Such descriptions should be interpreted as including the phrase “configured to. ” Reciting a component that is configured to perform one or more tasks is expressly intended not to invoke 35 U.S.C.§ 112 (f) interpretation for that component.
[0101] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, or methods as set forth in the example section below. For example, the baseband circuitry as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth below. For another example, circuitry associated with a UE, base station, network element, etc. as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth below in the example section.
[0102] Any of the above-described examples may be combined with any other example (or combination of examples) , unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.
[0103] Although the embodiments above have been described in considerable detail, numerous variations and modifications will become apparent to those skilled in the art once the above disclosure is fully appreciated. It is intended that the following claims be interpreted to embrace all such variations and modifications.
[0104] It is well understood that the use of personally identifiable information should follow privacy policies and practices that are generally recognized as meeting or exceeding industry or governmental requirements for maintaining the privacy of users. In particular, personally identifiable information data should be managed and handled so as to minimize risks of unintentional or unauthorized access or use, and the nature of authorized use should be clearly indicated to users.
[0105] Some embodiments described herein can include use of learning and / or non-learning-based process (es) . The use can include collecting, pre-processing, encoding, labeling, organizing, analyzing, recommending and / or generating data. Entities that collect, share, and / or otherwise utilize user data should provide transparency and / or obtain user consent when collecting such data. The present disclosure recognizes that the use of the data in the AI / ML models for CSI prediction, beam management, and / or positioning estimation processes can be used to benefit users.
[0106] For example, the data can be used to train models that can be deployed to improve performance, accuracy, and / or functionality of applications and / or services. Accordingly, the use of the data enables the AI / ML models for CSI prediction, beam management, and / or positioning estimation processes to adapt and / or optimize operations to provide more personalized, efficient, and / or enhanced user experiences. Such adaptation and / or optimization can include tailoring content, recommendations, and / or interactions to individual users, as well as streamlining processes, and / or enabling more intuitive interfaces. Further beneficial uses of the data in the AI / ML models for CSI prediction, beam management, and / or positioning estimation processes are also contemplated by the present disclosure.
[0107] The present disclosure contemplates that, in some embodiments, data used by [AI / ML models for CSI prediction, beam management, and / or positioning estimation processes includes publicly available data. To protect user privacy, data may be anonymized, aggregated, and / or otherwise processed to remove or to the degree possible limit any individual identification. As discussed herein, entities that collect, share, and / or otherwise utilize such data should obtain user consent prior to and / or provide transparency when collecting such data. Furthermore, the present disclosure contemplates that the entities responsible for the use of data, including, but not limited to data used in association with AI / ML models for CSI prediction, beam management, and / or positioning estimation processes, should attempt to comply with well-established privacy policies and / or privacy practices.
Claims
1.A method for wireless communication, comprising:sending a request for channel state information (CSI) reference signal (RS) having a configuration that enables training of an artificial intelligence or machine learning (AI / ML) model for estimation of channel quality; andreceiving the CSI-RS having the configuration, the CSI-RS enabling training of the AI / ML model to estimate the channel quality.2.The method of claim 1, wherein the request indicates preferred timing information for a CSI-RS measurement window or a prediction window.3.The method of claim 2, wherein the request indicates a speed of a device that generated the request, and wherein the timing information indicates a CSI-RS time domain separation in the CSI-RS measurement window.4.The method of claim 2 or 3, wherein the timing information indicates a CSI-RS resource set periodicity.5.The method of any of claim 2 through claim 4, wherein the timing information indicates CSI-RS burst periodicity.6.The method any of claim 2 through claim 5, wherein the timing information indicates one or more of: a value for a number of CSI-RSs included in each CSI-RS burst for the measurement window or for the prediction window; a length of the measurement window in a time domain; a length of the prediction window in the time domain; a separation in the time domain between the measurement window and the prediction window; and a spacing in the time domain of the CSI-RSs in the CSI-RS burst for the measurement window or for the prediction window.7.The method of any of claim 2 through claim 6, wherein the configuration of the CSI-RS is aperiodic.8.The method of any of claim 2 through claim 7, wherein the configuration of the CSI-RS is semi-periodic.9.The method of any of claim 2 through claim 8, wherein the request indicates a density for CSI-RS resource mapping.10.The method of any of claim 2 through claim 9, wherein the request indicates a preferred frequency domain allocation for the CSI-RS.11.The method of claim 10, wherein the preferred frequency domain allocation is based on a channel prediction per resource block, a channel prediction per sub-band, a covariance matrix prediction, or an eigen-vector prediction.12.The method of any of claim 2 through claim 11, wherein the request indicates an association identifier representing a timing and spatial domain of a remote device.13.A method for wireless communication, comprising:sending a request for beam configuration information for training of an artificial intelligence or machine learning (AI / ML) model configured to perform beam management operations; andreceiving the beam configuration information that enables training of the AI / ML model to perform the beam management operations.14.The method of claim 13, wherein the beam configuration information indicates a size of set A beams and a size of set B beams.15.The method of any of claim 13 through claim 14, wherein the beam configuration information indicates a ratio of a size of set A beams to a size of set B beams.16.The method of any of claim 13 through claim 15, wherein the beam configuration information includes a value of the CSI-RS density based user equipment link quality for set A beams and set B beams.17.The method of any of claim 13 through claim 16, wherein the beam configuration information includes an association identifier representing a mapping between beams from set A and beams from set B.18.The method of any of claim 13 through claim 17, wherein the beam configuration information includes an association identifier representing physical beam information including at least one of a beam direction, a beam 3-dB bandwidth, or a port mapping.19.The method of any of claim 13 through claim 18, wherein the request indicates a configuration of receiver beam sweeping, the request indicating a number of repetitions for sweeping set A beams and set B beams.20.The method of any of claim 13 through claim 19, wherein the request indicates a configuration of receiver beam sweeping, the request indicating a number of repetitions for sweeping B beams only.21.The method of any of claim 13 through claim 20, wherein the request indicates a user equipment configuration that enables a network to configure a network side AI / ML model for beam management.22.A method for wireless communication, comprising:sending a request indicating a preferred downlink positioning reference signal (DL-PRS) configuration or network positioning information for training of an artificial intelligence or machine learning (AI / ML) model configured to generate device positioning information; andreceiving DL-PRS information that enables training of the AI / ML model to generate the device positioning information.23.The method of claim 22, wherein the request indicates a preferred on-demand DL-PRS configuration, a configuration for DL-PRS bandwidth aggregation, and an associated priority.24.The method of claim 22 or claim 23, wherein the request indicates a preferred DL-PRS configuration for a candidate transmission / reception point (TRP) .25.The method of any of claim 22 through claim 24, wherein the request indicates which DL-PRS resource sets across DL-PRS positioning frequency layers are linked for DL-PRS bandwidth aggregation.26.The method of any of claim 22 through claim 25, wherein the request indicates a spatial direction of DL-PRS resources of TRPs associated with a base station.27.The method of any of claim 22 through claim 26, wherein the request indicates a preferred validity area associated with a user equipment.28.The method of any of claim 22 through claim 27, wherein the request indicates preferred cell information including a physical cell identifier, global cell identifier, or PRS identifier of a candidate TRS for measurement.29.The method of any of claim 22 through claim 28, wherein the request indicates preferred geographic coordinates of one or more TRPs served by a base station.30.The method of any of claim 22 through claim 29, wherein the request indicates an association identifier that represents positioning information for a remote device.31.The method of any of claim 22 through claim 30, wherein the request indicates preferred beam information including synchronization signal blocks (SSBs) of preferred beams, TRP beam information, or angle assistance information.32.The method of any of claim 22 through claim 31, wherein the request indicates line of sight or non-line of sight (LOS / NLOS) information or a preferred positioning reference unit (PRU) .33.The method of any of claim 22 through claim 32, wherein the DL-PRS information is represented by a single associated identifier.34.The method of any of claim 22 through claim 33, wherein the DL-PRS information is represented by a set of associated identifiers.35.The method of any of claim 22 through claim 34, wherein the device is a user equipment, and wherein the request is sent from the user equipment to a location management function (LMF) .36.One or more processors configured to, when executing instructions stored in memory, perform the method of any preceding claim.37.A non-transitory computer storage medium encoded with instructions that, when executed by one or more processors, cause the one or more processors to perform the method of any of claims 1 to 35.38.A system comprising one or more processors and one or more storage devices on which are stored instructions that are operable, when executed by the one or more processors, to cause the one or more computers to perform the method of any of claims 1 to 35.39.An apparatus comprising one or more baseband processors configured to perform the method of any of claims 1 to 35.