Radio resource management measurement enhancement

Abstract

An apparatus configured to process a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, one of a beam angle or a Synchronization Signal Block (SSB) index associated with each probing Tx beam, and a size of a full Tx beam pattern comprising a full set of Tx beams, wherein the plurality of probing Tx beams are a subset of full set of Tx beams, perform measurements on reference signals transmitted using each probing Tx beam to obtain measured radio resource management (RRM) values and determine, using an artificial intelligence (AI) / machine learning (ML) model, determined RRM values for Tx beams in the full set of Tx beams that are not included in the probing Tx beams, wherein inputs to the AI / ML model comprise the measured RRM values for each probing Tx beam and the beam angle or SSB index associated with each probing Tx beam.

Description

Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 Radio Resource Management Measurement Enhancement Inventors: Konstantinos Sarrigeorgidis, Jie Cui and Yang Tang Priority / Incorporation By Reference

[0001] This application claims priority to U.S. Provisional Application Serial No. 63 / 579,374 filed on August 29, 2023, and entitled “Radio Resource Management Measurement Enhancement,” the entirety of which is incorporated by reference herein. Background

[0002] In traditional beam management, a user equipment (UE) performs measurements (e.g., Layer-3 Reference Signal Received Power (L3-RSRP) measurements) across a set of Transmission (Tx) and Reception (Rx) beam pairs. For example, when the number of Tx beams is M and the number of Rx beams is N, the UE will measure all MxN beam pairs and then select the best beam.

[0003] This leads to a large measurement overhead. To provide an example, the overhead of reference signals (RS) used for radio resource management (RRM) (e.g., Synchronization Signal Blocks (SSBs) and Channel State Information RS (CSI-RS)) is high in the current New Radio (NR) design. For example, when the SS / PBCH Block Measurement Timing Configuration (SMTC) periodicity is 20ms, the related SMTC overhead in frequency range 2 (FR2) is 25%. There is a need to reduce the overhead related to RRM measurements. Summary

[0004] Some example embodiments are related to an apparatus having processing circuitry configured to process, based on signaling received from a base station, a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams,Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 one of a beam angle or a Synchronization Signal Block (SSB) index associated with each probing Tx beam, and a size of a full Tx beam pattern comprising a full set of Tx beams for the base station, wherein the plurality of probing Tx beams are a subset of full set of Tx beams, perform measurements on reference signals transmitted using each probing Tx beam to obtain measured radio resource management (RRM) values for each probing beam and determine, using an artificial intelligence (AI) / machine learning (ML) model, determined RRM values for Tx beams in the full set of Tx beams that are not included in the probing Tx beams, wherein inputs to the AI / ML model comprise at least the measured RRM values for each probing Tx beam and the beam angle or SSB index associated with each probing Tx beam.

[0005] Other example embodiments are related to an apparatus having processing circuitry configured to generate, for transmission to a user equipment (UE), a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, one of a beam angle or a Synchronization Signal Block (SSB) index associated with each probing Tx beam, and a size of a full Tx beam pattern comprising a full set of Tx beams, wherein the probing Tx beams are a subset of full set of Tx beams, generate, for transmission to the UE, reference signals on each of the probing Tx beams and process, based on signaling received from the UE, a beam report identifying each of a predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding angle domain or SSB index.

[0006] Still further example embodiments are related to an apparatus having processing circuitry configured to generate, for transmission to a user equipment (UE), a probingAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 transmission (Tx) beam pattern comprising a plurality of probing Tx beams, wherein the probing Tx beams are a subset of a full set of Tx beams, generate, for transmission to the UE, reference signals on each of the probing Tx beams, process, based on signaling received from the UE, measured radio resource management (RRM) values for each probing beam, a corresponding reception (Rx) beam used to receive each of the probing Tx beams and a beam angle for the corresponding Rx beam and determine, using an artificial intelligence (AI) / machine learning (ML) model, determined RRM values for Tx beams in the full set of Tx beams that are not included in the probing Tx beams, wherein inputs to the AI / ML model comprise at least the measured RRM values for each probing Tx beam and the beam angle associated with each corresponding Rx beam.

[0007] Additional example embodiments are related to an apparatus having processing circuitry configured to process, based on signaling received from a base station, a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, wherein the probing Tx beams are a subset of a full set of Tx beams used by the base station, perform measurements on reference signals transmitted on each of the probing Tx beams to obtain measured radio resource management (RRM) values for each of the probing Tx beams and generate, for transmission to the base station, the measured RRM values for each probing beam, a corresponding reception (Rx) beam used to receive each of the probing Tx beams and a beam angle for the corresponding Rx beam. Brief Description of the Drawings

[0008] Fig. 1 shows an example network arrangement according to various example embodiments.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0009] Fig. 2 shows an example user equipment (UE) according to various example embodiments.

[0010] Fig. 3 shows an example base station according to various example embodiments.

[0011] Fig. 4 shows an example method for performing RRM measurements according to various example embodiments.

[0012] Fig. 5 shows an example of RRM measurement interpolation for cells with a same Tx pattern but different probing beams according to various example embodiments.

[0013] Fig. 6 shows an example of RRM measurement interpolation for cells with a different Tx pattern and different probing beams according to various example embodiments.

[0014] Fig. 7 shows an example of RRM measurement interpolation when an artificial intelligence (AI) and / or machine learning (ML) model is resident on a UE according to various example embodiments.

[0015] Fig. 8 shows an example of RRM measurement interpolation when an AI / ML model is resident on a serving cell according to various example embodiments. Detailed Description

[0016] The example embodiments may be further understood with reference to the following description and the related appended drawings, wherein like elements are provided with the same reference numerals. The example embodiments relate to enhancingAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 RRM measurements and processing to reduce overhead related to the RRM measurements. Specifically, enhancements may relate to the use of artificial intelligence (AI) and / or machine learning (ML) to enhance the RRM measurements and processing. As will be described in greater detail below, the AI / ML may be implemented on the UE side or on the network side (e.g., at a base station).

[0017] The example embodiments are described with regard to a user equipment (UE). However, reference to a UE is merely provided for illustrative purposes. The example embodiments may be utilized with any electronic component that may establish a connection to a network and is configured with the hardware, software, and / or firmware to perform RRM measurements. Therefore, the UE as described herein is used to represent any appropriate type of electronic component.

[0018] The example embodiments are also described with regard to a fifth generation (5G) New Radio (NR) network that may configure a UE to perform RRM measurements. However, reference to a 5G NR network is merely provided for illustrative purposes. The example embodiments may be utilized with any appropriate type of network including legacy cellular networks (e.g., Long Term Evolution (LTE) networks, future evolutions of the cellular network (e.g., 5G-Advanced, 6G, etc.) or any other type of network where RRM type measurements are performed for the purpose of bean management.

[0019] Throughout this description, it may be described that certain operations are performed by one or more machine learning models or a series of machine learning models. Those skilled in the art will understand that there are many different types of machine learning models. For example, the example machineAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 learning models may include classifier models, regression models, multitask learning models (MTL), etc. The resulting AI system described below may include some or all of the above machine learning components or any other type of machine learning model that may be applied to determine the expected outcome of the AI system. It should be understood that any reference to one or more (or a series) of machine learning models may refer to a single machine learning model or a group of machine learning models. In addition, it should also be understood that the machine learning models described as performing different operations may be the same machine learning model or different machine learning models.

[0020] Throughout this description, the RRM measurements are described as Layer-3 Reference Signal Received Power (L3-RSRP) measurements that are performed on Channel State Information reference signals (CSI-RS) or Synchronization Signal Blocks (SSBs). However, this is only an example, as the example embodiments may be used with any type of RRM measurement on any type of reference signals.

[0021] As stated above, traditional beam management has a large overhead associated with the number of measurements and beam sweeping that needs to be performed. The example embodiments implement an AI / ML model at either the UE side or the network side to reduce the number of measurements and beam sweeping that is used to perform RRM measurements such as L3- RSRP measurements. The reduced number of RRM measurements is based on a probing Tx codebook that is a reduced set of Tx beams from a full Tx codebook used by a serving cell.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0022] In addition, the example embodiments provide a generic AI / ML model that may be used for a serving cell and neighbor cells that have different Tx patterns and / or different probing Tx codebooks. The example embodiments are described in greater detail below.

[0023] Fig. 1 shows an example network arrangement 100 according to various example embodiments. The example network arrangement 100 includes a UE 110. The UE 110 may be any type of electronic component that is configured to communicate via a network, e.g., mobile phones, tablet computers, desktop computers, smartphones, phablets, embedded devices, wearables, Internet of Things (IoT) devices, etc. An actual network arrangement may include any number of UEs being used by any number of users. Thus, the example of a single UE 110 is merely provided for illustrative purposes.

[0024] The UE 110 may be configured to communicate with one or more networks. In the example of the network arrangement 100, the network with which the UE 110 may wirelessly communicate is a 5G NR radio access network (RAN) 120. However, the UE 110 may also communicate with other types of networks (e.g., sixth generation (6G) RAN, 5G cloud RAN, a next generate RAN (NG-RAN), a legacy cellular network, a wireless local area network (WLAN), etc.) and the UE 110 may also communicate with networks over a wired connection. Therefore, the UE 110 may have a 5G NR chipset to communicate with the NR RAN 120 and, optionally, any other appropriate type of chipset to communicate with other types of networks.

[0025] The 5G NR RAN 120 may be a portion of a cellular network that may be deployed by a network carrier (e.g.,Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 Verizon, AT&T, Sprint, T-Mobile, etc.). The 5G NR RAN 120 may include cells and base stations that are configured to send and receive traffic from UEs that are equipped with the appropriate cellular chip set. In this example, the 5G NR RAN 120 includes the gNB 120A. However, reference to a gNB is merely provided for illustrative purposes, the example embodiments may be utilized with any appropriate type of access node (e.g., Node Bs, eNodeBs, HeNBs, eNBs, gNBs, gNodeBs, macrocells, microcells, small cells, femtocells, etc.).

[0026] Any association procedure may be performed for the UE 110 to connect to the 5G NR RAN 120. For example, as discussed above, the 5G NR RAN 120 may be associated with a particular network carrier where the UE 110 and / or the user thereof has a contract and credential information (e.g., stored on a SIM card). Upon detecting the presence of the 5G NR RAN 120, the UE 110 may transmit the corresponding credential information to associate with the 5G NR RAN 120. More specifically, the UE 110 may associate with a specific cell (e.g., the gNB 120A).

[0027] The network arrangement 100 also includes a cellular core network 130, the Internet 140, an IP Multimedia Subsystem (IMS) 150, and a network services backbone 160. The cellular core network 130 may refer an interconnected set of components that manages the operation and traffic of the cellular network. The cellular core network 130 also manages the traffic that flows between the cellular network and the Internet 140. The IMS 150 may be generally described as an architecture for delivering multimedia services to the UE 110 using the IP protocol. The IMS 150 may communicate with the cellular core network 130 and the Internet 140 to provide the multimedia services to the UE 110. The network services backbone 160 is in communicationAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 either directly or indirectly with the Internet 140 and the cellular core network 130. The network services backbone 160 may be generally described as a set of components (e.g., servers, network storage arrangements, etc.) that implement a suite of services that may be used to extend the functionalities of the UE 110 in communication with the various networks.

[0028] Fig. 2 shows an example UE 110 according to various example embodiments. The UE 110 will be described with regard to the network arrangement 100 of Fig. 1. The UE 110 may include a processor 205, a memory arrangement 210, a display device 215, an input / output (I / O) device 220, a transceiver 225 and other components 230. The other components 230 may, for example, multiple panels each comprising one or more antenna elements, an audio input device, an audio output device, a power supply, a data acquisition device, ports to electrically connect the UE 110 to other electronic devices, etc.

[0029] The processor 205 may be configured to execute a plurality of engines of the UE 110. For example, the engines may include a RRM measurement engine 235. The RRM measurement engine 235 may perform various operations related to RRM measurements including, but not limited to, measuring reference signals transmitted by cells based on a probing Tx codebook, executing an AI / ML model to interpolate measurement results from the Tx codebook to a full Tx codebook, and report actual and interpolated measurement results to a serving cell. These example operations are described in further detail below.

[0030] The above referenced engine 235 being an application (e.g., a program) executed by the processor 205 is merely provided for illustrative purposes. The functionality associatedAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 with the engine 235 may also be represented as a separate incorporated component of the UE 110 or may be a modular component coupled to the UE 110, e.g., an integrated circuit with or without firmware. For example, the integrated circuit may include input circuitry to receive signals and processing circuitry to process the signals and other information. The engines may also be embodied as one application or separate applications. In addition, in some UEs, the functionality described for the processor 205 is split among two or more processors such as a baseband processor and an applications processor. The example embodiments may be implemented in any of these or other configurations of a UE.

[0031] The memory arrangement 210 may be a hardware component configured to store data related to operations performed by the UE 110. The display device 215 may be a hardware component configured to show data to a user while the I / O device 220 may be a hardware component that enables the user to enter inputs. The display device 215 and the I / O device 220 may be separate components or integrated together such as a touchscreen.

[0032] The transceiver 225 may be a hardware component configured to establish a connection with the 5G NR-RAN 120, an LTE-RAN (not pictured), a legacy RAN (not pictured), a WLAN (not pictured), etc. Accordingly, the transceiver 225 may operate on a variety of different frequencies or channels (e.g., set of consecutive frequencies). The transceiver 225 includes circuitry configured to transmit and / or receive signals (e.g., control signals, data signals). Such signals may be encoded with information implementing any one of the methods described herein. The processor 205 may be operably coupled to theAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 transceiver 225 and configured to receive from and / or transmit signals to the transceiver 225. The processor 205 may be configured to encode and / or decode signals (e.g., signaling from a base station of a network) for implementing any one of the methods described herein.

[0033] Fig. 3 shows an example base station 300 according to various example embodiments. The base station 300 may represent the gNB 120A or any other access node through which the UE 110 may establish a connection to the 5G NR network 120.

[0034] The base station 300 may include a processor 305, a memory arrangement 310, an input / output (I / O) device 315, a transceiver 320 and other components 325. The other components 325 may include, for example, an audio input device, an audio output device, a battery, a data acquisition device, ports to electrically connect the base station 300 to other electronic devices and / or power sources, etc.

[0035] The processor 305 may be configured to execute a plurality of engines of the base station 300. For example, the engines may include a RRM measurement engine 330. The RRM measurement engine 330 may perform various operations related to RRM measurements including, but not limited to, defining a full Tx codebook and a probing Tx codebook for the cell, executing an AI / ML model to interpolate measurement results from the Tx codebook to a full Tx codebook, and selecting a beam pair for use by a UE. These example operations are described in further detail below.

[0036] The above noted engine 330 being an application (e.g., a program) executed by the processor 305 is only example. TheAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 functionality associated with the engine 330 may also be represented as a separate incorporated component of the base station 300 or may be a modular component coupled to the base station 300, e.g., an integrated circuit with or without firmware. For example, the integrated circuit may include input circuitry to receive signals and processing circuitry to process the signals and other information. In addition, in some base stations, the functionality described for the processor 305 is split among a plurality of processors (e.g., a baseband processor, an applications processor, etc.). The example embodiments may be implemented in any of these or other configurations of a base station.

[0037] The memory arrangement 310 may be a hardware component configured to store data related to operations performed by the base station 300. The I / O device 315 may be a hardware component or ports that enable a user to interact with the base station 300.

[0038] The transceiver 320 may be a hardware component configured to exchange data with the UE 110 and any other UE in the network arrangement 100. The transceiver 320 may operate on a variety of different frequencies or channels (e.g., set of consecutive frequencies). The transceiver 320 includes circuitry configured to transmit and / or receive signals (e.g., control signals, data signals). Such signals may be encoded with information implementing any one of the methods described herein. The processor 305 may be operably coupled to the transceiver 320 and configured to receive from and / or transmit signals to the transceiver 320. The processor 305 may be configured to encode and / or decode signals (e.g., signaling from a UE) for implementing any one of the methods described herein.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0039] Fig. 4 shows an example method 400 for performing RRM measurements according to various example embodiments. In an example embodiment, the RRM measurements may implement artificial intelligence (AI) / machine learning (ML). The method 400 will be described with reference to the network arrangement of Fig. 1, e.g., the UE 110 will be performing RRM measurements on RS transmitted by the gNB 120A.

[0040] In 405, a full Tx codebook is defined for the gNB 120A. The full Tx codebook represents the entire set of Tx beams used by the gNB 120A. For example, as described above, the gNB 120A may implement M Tx beams. The full Tx codebook represents these M Tx beams.

[0041] In 410, a probing codebook is defined for the gNB 120A. The probing codebook represents a sparse subset of the full Tx codebook (e.g., a subset of the M Tx beams) or another set of beams with wider beam widths used to form spatial beams and compute RSRP values as input to an AI / ML model.

[0042] In 415, the UE 110 performs beam measurements based on the probing codebook. For example, the gNB 120A transmits RS (e.g., SSB or CSI-RS) based on the probing codebook and the UE 110 performs measurements (e.g., L3-RSRP measurements) on the transmitted RS. Thus, in the example embodiments, instead of performing the measurements on the entire Tx codebook, the UE 110 is only performing measurements on the Tx beams defined in the probing codebook (e.g., less measurements).

[0043] In 420, the RRM measurements of the probing beams are input into an AI / ML model. The AI / ML model may be resident onAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 the UE 110 or the gNB 120A. For example, if the AI / ML model is resident on the UE 110, the UE 110 may input the RRM measurements of the probing beams directly into the AI / ML model. If the AI / ML model is resident on the gNB 120A, the UE 110 may report the RRM measurements of the probing beams to the gNB 120A, which may then input the RRM measurements of the probing beams into the AI / ML model.

[0044] In 425, the AI / ML model generates results for the entire codebook. For example, using the L3-RSRP measurement values for the probing Tx beams (and possibly additional information described below), the AI / ML model may generate L3- RSRP measurement values for the entire Tx codebook.

[0045] Once the UE 110 and / or the gNB 120A have the RSRP measurement values for the entire Tx codebook, the UE 110 and the gNB 120A may then use the actual RSRP values (e.g., from the probing Tx beam measurements) and the interpolated RSRP values (e.g., for the Tx beams not included in the probing Tx codebook) to select a beam pair for the UE 110 in the normal manner.

[0046] The size of the full Tx codebook, the size of the probing codebook and / or the beam widths may be different between the serving cell (e.g., the gNB 120A) and any neighbor cells (not shown). In the example embodiments, the AI / ML model is generic enough to be reemployed when the number of inputs / outputs as well as the beam widths differ between different gNB implementations (serving and neighbor cells for L3 measurements).

[0047] Fig. 5 shows an example of RRM measurement interpolation for cells with a same Tx pattern but differentAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 probing beams according to various example embodiments. Fig. 5 shows an example of the operations 420 and 425 for two cells 500 and 510. In this example, it may be considered that the cell 500 is a serving cell and the cell 510 is a neighbor cell. It may also be considered that both of these cells 500 and 510 have the same Tx pattern, e.g., the full Tx codebook for the cells 500 and 510 is the same. This is shown by the two grids having the same Tx pattern, e.g., M Tx beams shown in the horizontal and N Tx beams shown in the vertical.

[0048] In this example, it may also be considered that the cells 500 and 510 have a different probing codebook. This is illustrated in Fig. 5 as the stars that are shown in each of the grids. As described above, the probing codebook is a subset of Tx beams from the fill Tx codebook. In this example, the stars may represent the probing Tx beams for each of the cells 500 and 510. Each probing codebook includes KNKMprobing beams. As can be seen from Fig. 5, the probing Tx beams are different for each cell 500 and 510. However, as will be described in greater detail below, the same AI / ML model 520 will be used to interpolate the entire Tx codebook for both cells 500 and 510.

[0049] In the example of Fig. 5, the AI / ML model 520 will be trained using data from the cell 500 but this model may also be used for interpolation of RRM measurements for the cell 510 as will be described below. Because the AI / ML model 520 is trained using data from the cell 500 and its corresponding probing codebook, this data may be biased based on the spatial directions of the data from the beams, e.g., the beamforming angles (Θn,Φm) of each of the probing beams, when used to train the AI / ML model 520. Thus, as will be described below, in the example embodiments, the input to the AI / ML model 520 will beAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 augmented with additional information for each of the RRM measurements in addition to the L3-RSRP values. Specifically, the beamforming angles (Θn,Φm) or the SSB index of each of the measured probing beams will also be input into the AI / ML model for the purposes of interpolation.

[0050] Thus, the UE 110 will perform the RRM measurements (e.g., L3-RSRP measurements) on the KNKM probing beams of the cell 500 and the KNKMprobing beams of the cell 510. As shown in Fig. 5, the results of these RRM measurements for both of the cells 500 and 510 will be input into the same AI / ML model 520. In addition, the beamforming angles (Θn,Φm) of each of the probing beams are also input into the AI / ML model 520. If the AI / ML model 520 is implemented at the UE 110, the network (e.g., the serving cell 500) may signal the beamforming angles (Θn,Φm) of the probing beams to the UE 110. If the AI / ML model 520 is implemented on the network side (e.g., the serving cell 500), the serving cell 500 will have the beamforming angles (Θn,Φm) of the probing beams for itself and may also receive the beamforming angles (Θn,Φm) of the probing beams from the neighbor cell 510.

[0051] The AI / ML model 520 will then use the input of the probing beam RRM measurements and the beamforming angles (Θn,Φm) of the probing beams to generate a full set of RRM measurements for the Tx beams not included in the subset of the probing codebook. The UE 110 and / or the serving cell 500 may then use the full set of RRM measurements to select a beam pair for the UE 110 in the normal manner. This process will be described in greater detail below.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0052] Fig. 6 shows an example of RRM measurement interpolation for cells with a different Tx pattern and different probing beams according to various example embodiments. Fig. 6 again shows an example of the operations 420 and 425 for two cells 600 and 610. In this example, it may be considered that the cell 600 is a serving cell and the cell 610 is a neighbor cell. Unlike Fig. 5, the cells 600 and 610 have a different Tx pattern, e.g., the full Tx codebook for the cells 600 and 610 is different. This is shown by the grid for the cell 600 having a different number of M Tx beams in the horizontal and the N Tx beams in the vertical than the grid for the cell 610.

[0053] In addition, the cells 600 and 610 have different probing codebooks. This is illustrated in Fig. 6 as the stars that are shown in each of the grids. In the example of Fig. 6, the interpolation of the AI / ML model 620 with respect to the cell 600 will not be further described as it is similar to the interpolation described above with reference to the cells 500 and 510.

[0054] However, because the Tx pattern and the probing codebook is different for the cell 610, additional processing may be used during the interpolation process so that the same AI / ML model 620 that was trained using data from the cell 600 may be used. In this example, the additional processing is represented by the pre-processing layer 630 and the post- processing layer 640.

[0055] Thus, the UE 110 will perform the RRM measurements (e.g., L3-RSRP measurements) on the KNKM probing beams of the cell 610. These RRM measurements and the beamforming anglesAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 (Θn,Φm) of each of the probing beams for the cell 610 will be input into the pre-processing layer 630. In addition, the pre- processing layer 630 will either receive or understand from receiving the RRM measurements, the size of the probing codebook of the cell 610. The pre-processing layer 630 may also receive the input / output sizes of the AI / ML model 620. Using this information, the pre-processing layer 630 may map the probing angles of the KNKM probing beams of the cell 610 to reference probing angles to result in the output of the pre-processing layer 630. The output of the pre-processing layer 630 will be a number of outputs (e.g., RSRP value and beamforming angles (Θn,Φm)) that correspond to the number of inputs used for the AI / ML model 620. Another manner of stating this is that the pre- processing layer 630 up-samples the L3-RSRP measurements on the KNKMprobing beams of the cell 610 using the mapping of the probing angles to the reference angles such that the AI / ML model 620 receives the number of inputs it is expecting to perform the spatial interpolation.

[0056] The AI / ML model 620 will then perform the spatial interpolation as described above using the output of the pre- processing layer 630 as the input to the AI / ML model 620. The AI / ML model 620 will then use the input of the probing beam RRM measurements and the beamforming angles (Θn,Φm) to generate a full set of RRM measurements. However, since this full set of RRM measurements is more than the number of Tx beams in the Tx pattern of the cell 610, this full set of RRM measurements may be down-sampled to result in the set of RRM measurements for the Tx pattern of the cell 600. This down-sampling may be performed by the post-processing layer 640.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0057] In this example, the post-processing layer 640 will receive as input, the output of the AI / ML model 620 (e.g., the full set of RRM measurements) and the size of the Tx codebook of the cell 610. The post-processing layer 640 may use this information to down-sample the full set of RRM measurements output by the AI / ML model 620 to result in a set of interpolated values corresponding to the size of the Tx codebook for the cell 610.

[0058] For example, since the Tx codebook for the reference AI / ML model is known in terms of its beam angles in the vertical and horizontal domain and the associated RSRP values, the interpolated RSRP values of the reduced Tx codebook of the cell 610 at the known beam angles of the cell 610 may be determined using, for example, a bicubic interpolation or any other near neighbor-based interpolation. This interpolation could be static or dynamic based on training / learning with additional AI / ML layers.

[0059] Thus, in this example, the pre-processing layer 630 and the post-processing layer 640 allow the same AI / ML model 620. To be used for cells that have different size Tx codebooks and different probing Tx codebooks. The pre-processing layer 630 and the post-processing layer 640 may be considered to interpolation layers that are specific to the Tx codebook beam pattern and size for the cell, e.g., the cell 610 that has a different Tx codebook size and probing codebook than that used to train the AI / ML model.

[0060] In some examples, the pre-processing layer 630 and the post-processing layer 640 may be fixed, e.g., the weights used for the up-sampling and down-sampling may be fixed based on theAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 size of the Tx patterns. In other examples, the pre-processing layer 630 and the post-processing layer 640 may be trained. The use of the pre-processing layer 630 and the post-processing layer 640 may be considered to be model transfer in deep learning where the reference AI / ML model is transferred to the design and the two additional layers (e.g., the pre-processing layer 630 and the post-processing layer 640) are fine tuned. This is possible because the learning domain is the same, e.g., spatial beam prediction.

[0061] Again, if the AI / ML model 620, the pre-processing layer 630 and the post-processing layer 640 are implemented at the UE 110, the information used for the operations may be signaled to the UE 110 by the network.

[0062] Fig. 7 shows an example of RRM measurement interpolation when an AI / ML model is resident on a UE according to various example embodiments. The call flow of Fig. 7 is shown as occurring between the gNB 120A (e.g., a serving cell) and the UE 110.

[0063] Similar to that described above, the grid in the upper left of Fig. 7 may be considered to show the Tx pattern of the gNB 120A with stars representing the probing Tx codebook for the gNB 120A. In 710, the gNB 120A transmits the probing beam pattern based on the probing Tx codebook. In addition, as described above, the gNB 120A may also signal the beamforming angles (Θn,Φm) (or SSB indices) of the probing beams and / or the size of Tx codebook. Examples of how this information may be used by the UE 110 when implementing the AI / ML model was described above.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0064] The UE 110 may measure the L3-RSRP of each of the Tx probing beams transmitted by the gNB 120A and input these L3- RSRP measurements along with the beamforming angles (Θn,Φm) into an AI / ML model to generate the full set of L3-RSRP measurement results for the full Tx codebook of the gNB 120A. This is illustrated as the inputs and outputs of the AI / ML model on the right side of the call flow.

[0065] It should be understood that the UE 110 also scans its own Rx beams when performing the L3-RSRP of each of the Tx probing beams. This is illustrated in Fig. 7 as the three (3) grids showing the Rx beam 1 through Rx beam m. The axis below the grids shows that the Tx beam pattern may be considered to be the x-axis and y-axis as described above with reference to Figs. 5 and 6 and the Rx beam patterns may be considered to be the z- axis (e.g., the various Rx beam sweeping performed to receive the probing Tx beams).

[0066] Based on the interpolation performed by the AI / ML model, the UE 110 may identify the top K beam pairs (e.g., the beam pairs that have the highest RSRP values). In this example, it may be considered that the value of K is 4. However, this is only an example and other values of K may be used. In this example, the top beam pairs are shown in the grids on the right as circles. In this example, the circles indicate a beam pair comprising a Tx beam and Rx beam 1, two beam pairs comprising a Tx beam and Rx beam 2 and a beam pair comprising a Tx beam and Rx beam m for a total of K=4 beam pairs.

[0067] In 720, the UE 110 will report the K Tx beams to the gNB 120A, e.g., the Tx beams of the beam pairs described above. This reporting may also include the angle domain or SSB index ofAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 the beams. For example, referring to the grid for the Rx beam 1, one of the top K beam pairs has a Tx angle domain of 4,4 (e.g., from the bottom left square may be considered to be angle domain 0,0). The Tx grid may also correspond to an SSB index and thus, instead of the angle domain, the value of the SSB index for the corresponding square may be reported. The gNB 120A receives the K Tx beams. These K=4 Tx beams are shown as the circles in the lower grid on the left side of Fig. 7.

[0068] In 730, the gNB 120A transmits the top K Tx beams and the UE 110 performs measurements on the top K beams using the corresponding top K Rx beams of the beam pairs as described above. Since these top K Tx beams may have been identified based on the interpolation of the AI / ML model, the UE 110 may not have previously measured the SSB or CSI-RS of one or more of these top K Tx beams. In 730, the measurements of the top K Tx beams are actual measurements of the L3-RSRP for these Tx beams.

[0069] In 740, the UE 110 reports the beam quality for the top K Tx beams to the gNB 120A. The gNB 120A may select the ‘best’ Tx beam, e.g., the Tx beam with the highest L3-RSRP value. However, the ‘best’ beam may be selected based on any criteria and is not limited to only the highest L3-RSRP value.

[0070] In 750, the gNB 120A will report the selected Tx beam to the UE 110 and the UE 110 will use the Tx,Rx beam pair for reception until a further selection of a Tx,Rx beam pair occurs.

[0071] Fig. 8 shows an example of RRM measurement interpolation when an AI / ML model is resident on a serving cell according to various example embodiments. The call flow of Fig.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 8 is shown as occurring between the serving cell (e.g., gNB 120A) and the UE 110.

[0072] In 810, the gNB 120A transmits the probing beam pattern based on the probing Tx codebook. The UE 110 may measure the L3-RSRP of each of the Tx probing beams transmitted by the gNB 120A. In 820, the UE 110 reports the beam quality of the Tx probing beams to the gNB 120A. In this example, when the UE 110 reports the beam quality, the UE 110 reports the beam pairs to the gNB 120A including the Rx beam used to receive each Tx probing beam with an identification encoding the angle domain of the Rx beam. Similar to the process described above, the angle domain of the Rx beam for the Tx,Rx beam pair may be an input into the AI / ML model to be used for the interpolation of the full set of RRM measurements.

[0073] In 830, the gNB 120A inputs the RRM measurement information from the Tx probing beams into the AI / ML model to generate the full set of RRM measurements for the Tx pattern of the gNB 120A. Based on the full set of RRM measurements, the gNB 120A may select the top K Tx beams.

[0074] In 840, the gNB 120A transmits the top K Tx beams. In addition, the gNB 120A will also report the Rx beam for the top K Tx beams, e.g., the Rx beam that the UE 110 should use when measuring the corresponding Tx beam. The UE 110 performs measurements on the top K beams using the corresponding Rx beam of the beam pair as reported by the gNB 120A. Similar to the operations of Fig. 7, since these top K Tx beams may have been identified based on the interpolation of the AI / ML model, the UE 110 may not have previously measured the SSB or CSI-RS of one or more of these top K Tx beams. In 840, the measurements of theAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 top K Tx beams are actual measurements of the L3-RSRP for these Tx beams.

[0075] In 850, the UE 110 reports the beam quality for the top K Tx beams to the gNB 120A. The gNB 120A may select the ‘best’ Tx beam, e.g., the Tx beam with the highest L3-RSRP value. However, the ‘best’ beam may be selected based on any criteria and is not limited to only the highest L3-RSRP value.

[0076] In 860, the gNB 120A will report the selected Tx beam to the UE 110 and the UE 110 will use the Tx,Rx beam pair for reception until a further selection of a Tx,Rx beam pair occurs.

[0077] Implementing the above example embodiments may enhance RRM measurement performance in a variety of manners. For example, the spatial beam interpolation performed by the AI / ML model may reduce delays associated with L3 measurements by minimizing the Tx / Rx beam sweeping set. This may reduce the SMTC window. In another example, there may be a reduced number of L3 measurements by periodically skipping the Tx / Rx beam sweeping based on temporal beam prediction. In this scenario, the SMTC periodicity may be increased. In further examples, minimizing the L3 measurements may reduce scheduling restrictions, which may increase throughput. Examples

[0078] In a first example, a method, comprising processing, based on signaling received from a base station, a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, one of a beam angle or a Synchronization Signal Block (SSB) index associated with each probing Tx beam, and a size of a full Tx beam pattern comprising a full set of Tx beams for theAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 base station, wherein the plurality of probing Tx beams are a subset of full set of Tx beams, performing measurements on reference signals transmitted using each probing Tx beam to obtain measured radio resource management (RRM) values for each probing beam and determining, using an artificial intelligence (AI) / machine learning (ML) model, determined RRM values for Tx beams in the full set of Tx beams that are not included in the probing Tx beams, wherein inputs to the AI / ML model comprise at least the measured RRM values for each probing Tx beam and the beam angle or SSB index associated with each probing Tx beam.

[0079] In a second example, the method of the first example, wherein the measurements are performed using reception (Rx) beam sweeping.

[0080] In a third example, the method of the second example, further comprising selecting a predetermined number of the full set of Tx beams based on the measured RRM values and determined RRM values and generating, for transmission to the base station, a beam report identifying each of the predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding angle domain or SSB index.

[0081] In a fourth example, the method of the third example, wherein each of the predetermined number of Tx beams corresponds to the predetermined number of highest determined Reference Signal Received Power (RSRP) of the measured RRM values or the determined RRM values.

[0082] In a fifth example, the method of the third example, further comprising performing second measurements on referenceAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 signals transmitted using the predetermined number of the Tx beams, generating, for transmission to the base station, a further beam report comprising the second measured RRM values for the predetermined number of the Tx beams and processing, based on signaling received from the base station, a beam indication message indicating one of the Tx beams of the full set of Tx beams to be used for reception of signals from the base station.

[0083] In a sixth example, the method of the first example, further comprising processing, based on signaling received from the base station, a second probing Tx beam pattern comprising a second plurality of probing Tx beams transmitted by a neighbor base station and one of a beam angle or a SSB index associated with each second probing Tx beam, wherein a second full Tx beam pattern comprising a second full set of Tx beams for the neighbor base station is the same as the full Tx beam pattern of the base station, wherein the second probing Tx beams are a subset of full set of second Tx beams and the second probing Tx beam pattern is different from the probing Tx beam pattern, performing second measurements on reference signals transmitted using each second probing Tx beam to obtain second measured RRM values for each second probing beam and determining, using the AI / ML model, second determined RRM values for Tx beams in the second full set of Tx beams that are not included in the second probing Tx beams, wherein inputs to the AI / ML model comprise at least the second measured RRM values for each second probing Tx beam and the beam angle or SSB index associated with each second probing Tx beam.

[0084] In a seventh example, the method of the first example, further comprising processing, based on signaling received fromAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 the base station, a second probing Tx beam pattern comprising a second plurality of probing Tx beams transmitted by a neighbor base station and one of a beam angle or a SSB index associated with each second probing Tx beam, wherein a second full Tx beam pattern comprising a second full set of Tx beams for the neighbor base station is different from the full Tx beam pattern of the base station, wherein the second probing Tx beams are a subset of full set of second Tx beams and the second probing Tx beam pattern is different from the probing Tx beam pattern, performing second measurements on reference signals transmitted using each second probing Tx beam to obtain second measured RRM values for each second probing beam, pre-processing the second measured RRM values and corresponding beam angles or SSB indices to obtain pre-processed second measured RRM values and corresponding beam angles or SSB indices to match an expected number of inputs for the AI / ML model, determining, using the AI / ML model, second determined RRM values, wherein inputs to the AI / ML model comprise at least the pre-processed second measured RRM values and corresponding beam angles or SSB indices and post-processing the second determined RRM values and corresponding beam angles or SSB indices to obtain post- processed second determined RRM values and corresponding beam angles or SSB indices to match a number of second Tx beams in the second full set of Tx beams that are not included in the second probing Tx beams.

[0085] In an eighth example, the method of the seventh example, wherein the pre-processing the second measured RRM values and corresponding beam angles or SSB indices is based on mapping of the beam angle or SSB index associated with each second probing Tx to reference angles associated with the Tx beams of the base station.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0086] In a ninth example, the method of the seventh example, wherein the post-processing the second determined RRM values and corresponding beam angles or SSB indices is based on a bicubic interpolation or a near neighbor based interpolation.

[0087] In a tenth example, the method of the first example, wherein the measured RRM values comprise Layer-3 Reference Signal Received Power (L3-RSRP) measurements.

[0088] In an eleventh example, the method of the first example, wherein the reference signals comprise Channel State Information reference signals (CSI-RS) or SSBs.

[0089] In a twelfth example, a processor configured to perform any of the methods of the first through eleventh examples.

[0090] In a thirteenth example, a user equipment (UE) configured to perform any of the methods of the first through eleventh examples.

[0091] In a fourteenth example, a method, comprising generating, for transmission to a user equipment (UE), a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, one of a beam angle or a Synchronization Signal Block (SSB) index associated with each probing Tx beam, and a size of a full Tx beam pattern comprising a full set of Tx beams, wherein the probing Tx beams are a subset of full set of Tx beams, generating, for transmission to the UE, reference signals on each of the probing Tx beams and processing, based on signaling received from the UE, a beam report identifying eachAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 of a predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding angle domain or SSB index.

[0092] In a fifteenth example, the method of the fourteenth example, further comprising generating, for transmission to the UE, reference signals on each of the predetermined number of Tx beams.

[0093] In a sixteenth example, the method of the fifteenth example, further comprising processing, based on signaling received from the UE, a further beam report comprising the measured values for the reference signals transmitted using the predetermined number of the Tx beams, selecting, based on the measured values, one of the predetermined number of the Tx beams and generating, for transmission to the UE, a beam indication message indicating the one of the Tx beams to be used by the UE for reception of signals.

[0094] In a seventeenth example, the method of the fourteenth example, wherein the reference signals comprise Channel State Information reference signals (CSI-RS) or SSBs.

[0095] In an eighteenth example, the method of the fourteenth example, wherein each of the predetermined number of Tx beams corresponds to the predetermined number of highest determined Reference Signal Received Power (RSRP) values determined by the UE.

[0096] In a nineteenth example, a processor configured to perform any of the methods of the fourteenth through eighteenth examples.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0097] In a twentieth example, a base station configured to perform any of the methods of the fourteenth through eighteenth examples.

[0098] In a twenty first example, a method, comprising generating, for transmission to a user equipment (UE), a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, wherein the probing Tx beams are a subset of a full set of Tx beams, generating, for transmission to the UE, reference signals on each of the probing Tx beams, processing, based on signaling received from the UE, measured radio resource management (RRM) values for each probing beam, a corresponding reception (Rx) beam used to receive each of the probing Tx beams and a beam angle for the corresponding Rx beam and determining, using an artificial intelligence (AI) / machine learning (ML) model, determined RRM values for Tx beams in the full set of Tx beams that are not included in the probing Tx beams, wherein inputs to the AI / ML model comprise at least the measured RRM values for each probing Tx beam and the beam angle associated with each corresponding Rx beam.

[0099] In a twenty second example, the method of the twenty first example, further comprising selecting a predetermined number of the full set of Tx beams based on the measured RRM values and determined RRM values and generating, for transmission to the UE, a beam report identifying each of the predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding Rx beam and beam angle for the Rx beam and generating, for transmission to the UE, reference signals on each of the predetermined number of Tx beams.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0100] In a twenty third example, the method of the twenty second example, wherein each of the predetermined number of Tx beams corresponds to the predetermined number of highest determined Reference Signal Received Power (RSRP) of the measured RRM values or the determined RRM values.

[0101] In a twenty fourth example, the method of the twenty second example, further comprising processing, based on signaling received from the UE, a further beam report comprising the measured values for the reference signals transmitted using the predetermined number of the Tx beams, selecting, based on the measured values, one of the predetermined number of the Tx beams and generating, for transmission to the UE, a beam indication message indicating the one of the Tx beams to be used by the UE for reception of signals.

[0102] In a twenty fifth example, the method of the twenty first example, further comprising generating, for transmission to the UE, a second probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams to be transmitted by a neighbor base station, wherein the second probing Tx beams are a subset of a second full set of Tx beams used by the neighbor base station, wherein the second full set of Tx beams of the neighbor base station is the same as the full set of Tx beams, wherein the second probing Tx beam pattern is different from the probing Tx beam pattern, processing, based on signaling received from the UE, second measured RRM values for each second probing beam, a corresponding Rx beam used to receive each of the second probing Tx beams and a beam angle for the corresponding Rx beam and determining, using the AI / ML model, second determined RRM values for Tx beams in the second full set of Tx beams that are not included in the second probing Tx beams, wherein inputs toAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 the AI / ML model comprise at least the second measured RRM values for each second probing Tx beam and the beam angle associated with each corresponding Rx beam.

[0103] In a twenty sixth example, the method of the twenty first example, further comprising generating, for transmission to the UE, a second probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams to be transmitted by a neighbor base station, wherein the second probing Tx beams are a subset of a second full set of Tx beams used by the neighbor base station, wherein the second full set of Tx beams for the neighbor base station is different from the full set of Tx beams, wherein the second probing Tx beam pattern is different from the probing Tx beam pattern, processing, based on signaling received from the UE, second measured RRM values for each second probing beam, a corresponding Rx beam used to receive each of the second probing Tx beams and a beam angle for the corresponding Rx beam, pre-processing the second measured RRM values and corresponding beam angle to obtain pre-processed second measured RRM values and corresponding beam angles to match an expected number of inputs for the AI / ML model, determining, using the AI / ML model, second determined RRM values, wherein inputs to the AI / ML model comprise at least the pre-processed second measured RRM values and corresponding beam angles and post-processing the second determined RRM values and corresponding beam angles to obtain post-processed second determined RRM values and corresponding beam angles to match a number of second Tx beams in the second full set of Tx beams that are not included in the second probing Tx beams.

[0104] In a twenty seventh example, the method of the twenty sixth example, wherein the pre-processing the second measuredAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 RRM values and corresponding beam angles is based on mapping of the beam angle associated with each of the corresponding Rx beams to reference angles associated with the Tx beams.

[0105] In a twenty eighth example, the method of the twenty sixth example, wherein the post-processing the second determined RRM values and corresponding beam angles or SSB indices is based on a bicubic interpolation or a near neighbor based interpolation.

[0106] In a twenty ninth example, the method of the twenty first example, wherein the measured RRM values comprise Layer-3 Reference Signal Received Power (L3-RSRP) measurements.

[0107] In a thirtieth example, the method of the twenty first example, wherein the reference signals comprise Channel State Information reference signals (CSI-RS) or SSBs.

[0108] In a thirty first example, a processor configured to perform any of the methods of the twenty first through thirtieth examples.

[0109] In a thirty second example, a base station configured to perform any of the methods of the twenty first through thirtieth examples.

[0110] In a thirty third example, a method, comprising processing, based on signaling received from a base station, a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, wherein the probing Tx beams are a subset of a full set of Tx beams used by the base station, performing measurements on reference signals transmitted on each of theAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 probing Tx beams to obtain measured radio resource management (RRM) values for each of the probing Tx beams and generating, for transmission to the base station, the measured RRM values for each probing beam, a corresponding reception (Rx) beam used to receive each of the probing Tx beams and a beam angle for the corresponding Rx beam.

[0111] In a thirty fourth example, the method of the thirty third example, further comprising processing, based on signaling received from the base station, a beam report identifying each of a predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding Rx beam and beam angle for the Rx beam.

[0112] In a thirty fifth example, the method of the thirty fourth example, further comprising performing measurements on reference signals transmitted on each of the predetermined number of Tx beams to obtain second measured RRM values for each of the predetermined number of Tx beams, generating, for transmission to the base station, a further beam report comprising the second measured values and processing, based on signaling received from the base station, a beam indication message indicating the one of the predetermined number of Tx beams to be used by the UE.

[0113] In a thirty sixth example, the method of the thirty third example, wherein the reference signals comprise Channel State Information reference signals (CSI-RS) or SSBs.

[0114] In a thirty seventh example, a processor configured to perform any of the methods of the thirty third through thirty sixth examples.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1

[0115] In a thirty eighth example, a user equipment (UE) configured to perform any of the methods of the thirty third through thirty sixth examples.

[0116] Those skilled in the art will understand that the above-described example embodiments may be implemented in any suitable software or hardware configuration or combination thereof. An example hardware platform for implementing the example embodiments may include, for example, an Intel x86 based platform with compatible operating system, a Windows OS, a Mac platform and MAC OS, a mobile device having an operating system such as iOS, Android, etc. The example embodiments described above may be embodied as a program containing lines of code stored on a non-transitory computer readable storage medium that, when compiled, may be executed on a processor or microprocessor.

[0117] Although this application described various embodiments each having different features in various combinations, those skilled in the art will understand that any of the features of one embodiment may be combined with the features of the other embodiments in any manner not specifically disclaimed or which is not functionally or logically inconsistent with the operation of the device or the stated functions of the disclosed embodiments.

[0118] 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 identifiableAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 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.

[0119] It will be apparent to those skilled in the art that various modifications may be made in the present disclosure, without departing from the spirit or the scope of the disclosure. Thus, it is intended that the present disclosure cover modifications and variations of this disclosure provided they come within the scope of the appended claims and their equivalent.

Claims

Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 What is Claimed:

1. An apparatus comprising processing circuitry configured to: process, based on signaling received from a base station, a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, one of a beam angle or a Synchronization Signal Block (SSB) index associated with each probing Tx beam, and a size of a full Tx beam pattern comprising a full set of Tx beams for the base station, wherein the plurality of probing Tx beams are a subset of full set of Tx beams; perform measurements on reference signals transmitted using each probing Tx beam to obtain measured radio resource management (RRM) values for each probing beam; and determine, using an artificial intelligence (AI) / machine learning (ML) model, determined RRM values for Tx beams in the full set of Tx beams that are not included in the probing Tx beams, wherein inputs to the AI / ML model comprise at least the measured RRM values for each probing Tx beam and the beam angle or SSB index associated with each probing Tx beam.

2. The apparatus of claim 1, wherein the processing circuitry is configured to perform the measurements using reception (Rx) beam sweeping.

3. The apparatus of claim 2, wherein the processing circuitry is further configured to: select a predetermined number of the full set of Tx beams based on the measured RRM values and determined RRM values; and generate, for transmission to the base station, a beam report identifying each of the predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding angle domain or SSB index.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 4. The apparatus of claim 3, wherein each of the predetermined number of Tx beams corresponds to the predetermined number of highest determined Reference Signal Received Power (RSRP) of the measured RRM values or the determined RRM values.

5. The apparatus of claim 3, wherein the processing circuitry is further configured to: perform second measurements on reference signals transmitted using the predetermined number of the Tx beams to obtain second measured RRM values; generate, for transmission to the base station, a further beam report comprising the second measured RRM values for the predetermined number of the Tx beams; and process, based on signaling received from the base station, a beam indication message indicating one of the Tx beams of the full set of Tx beams to be used for reception of signals from the base station.

6. The apparatus of claim 1, wherein the processing circuitry is further configured to: process, based on signaling received from the base station, a second probing Tx beam pattern comprising a second plurality of probing Tx beams transmitted by a neighbor base station and one of a beam angle or a SSB index associated with each second probing Tx beam, wherein a second full Tx beam pattern comprising a second full set of Tx beams for the neighbor base station is a same pattern as the full Tx beam pattern of the base station, wherein the second probing Tx beams are a subset of full set of second Tx beams and the second probing Tx beam pattern is different from the probing Tx beam pattern;Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 perform second measurements on reference signals transmitted using each second probing Tx beam to obtain second measured RRM values for each second probing beam; and determine, using the AI / ML model, second determined RRM values for Tx beams in the second full set of Tx beams that are not included in the second probing Tx beams, wherein inputs to the AI / ML model comprise at least the second measured RRM values for each second probing Tx beam and the beam angle or SSB index associated with each second probing Tx beam.

7. The apparatus of claim 1, wherein the processing circuitry is further configured to: process, based on signaling received from the base station, a second probing Tx beam pattern comprising a second plurality of probing Tx beams transmitted by a neighbor base station and one of a beam angle or a SSB index associated with each second probing Tx beam, wherein a second full Tx beam pattern comprising a second full set of Tx beams for the neighbor base station is different from the full Tx beam pattern of the base station, wherein the second probing Tx beams are a subset of full set of second Tx beams and the second probing Tx beam pattern is different from the probing Tx beam pattern; perform second measurements on reference signals transmitted using each second probing Tx beam to obtain second measured RRM values for each second probing beam; pre-process the second measured RRM values and corresponding beam angles or SSB indices to obtain pre-processed second measured RRM values and corresponding beam angles or SSB indices to match an expected number of inputs for the AI / ML model; determine, using the AI / ML model, second determined RRM values, wherein inputs to the AI / ML model comprise at least theAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 pre-processed second measured RRM values and corresponding beam angles or SSB indices; and post-process the second determined RRM values and corresponding beam angles or SSB indices to obtain post- processed second determined RRM values and corresponding beam angles or SSB indices to match a number of second Tx beams in the second full set of Tx beams that are not included in the second probing Tx beams.

8. The apparatus of claim 7, wherein the processing circuitry is configured to pre-process the second measured RRM values and corresponding beam angles or SSB indices based on mapping of the beam angle or SSB index associated with each second probing Tx to reference angles associated with the Tx beams of the base station.

9. The apparatus of claim 7, wherein the processing circuitry is configured to post-process the second determined RRM values and corresponding beam angles or SSB indices based on a bicubic interpolation or a near neighbor based interpolation.

10. The apparatus of claim 1, wherein the measured RRM values comprise Layer-3 Reference Signal Received Power (L3-RSRP) measurements.

11. The apparatus of claim 1, wherein the reference signals comprise Channel State Information reference signals (CSI-RS) or SSBs.

12. An apparatus comprising processing circuitry configured to: generate, for transmission to a user equipment (UE), a probing transmission (Tx) beam pattern comprising a plurality ofAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 probing Tx beams, one of a beam angle or a Synchronization Signal Block (SSB) index associated with each probing Tx beam, and a size of a full Tx beam pattern comprising a full set of Tx beams, wherein the probing Tx beams are a subset of full set of Tx beams; generate, for transmission to the UE, reference signals on each of the probing Tx beams; and process, based on signaling received from the UE, a beam report identifying each of a predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding angle domain or SSB index.

13. The apparatus of claim 12, wherein the processing circuitry is further configured to: generate, for transmission to the UE, reference signals on each of the predetermined number of Tx beams.

14. The apparatus of claim 13, wherein the processing circuitry is further configured to: process, based on signaling received from the UE, a further beam report comprising measured values for the reference signals transmitted using the predetermined number of the Tx beams; select, based on the measured values, one of the predetermined number of the Tx beams; and generate, for transmission to the UE, a beam indication message indicating the one of the Tx beams to be used by the UE for reception of signals.

15. The apparatus of claim 12, wherein the reference signals comprise Channel State Information reference signals (CSI-RS) or SSBs.Attorney Docket No. 30134 / 86002 Ref. No. P64160WO1 16. The apparatus of claim 12, wherein each of the predetermined number of Tx beams corresponds to the predetermined number of highest determined Reference Signal Received Power (RSRP) values determined by the UE.

17. An apparatus comprising processing circuitry configured to: process, based on signaling received from a base station, a probing transmission (Tx) beam pattern comprising a plurality of probing Tx beams, wherein the probing Tx beams are a subset of a full set of Tx beams used by the base station; perform measurements on reference signals transmitted on each of the probing Tx beams to obtain measured radio resource management (RRM) values for each of the probing Tx beams; and generate, for transmission to the base station, the measured RRM values for each probing beam, a corresponding reception (Rx) beam used to receive each of the probing Tx beams and a beam angle for the corresponding Rx beam.

18. The apparatus of claim 17, wherein the processing circuitry is further configured to: process, based on signaling received from the base station, a beam report identifying each of a predetermined number of the full set of Tx beams, wherein each of the predetermined number of Tx beams is reported with a corresponding Rx beam and beam angle for the Rx beam.

19. The apparatus of claim 18, wherein the processing circuitry is further configured to: perform measurements on reference signals transmitted on each of the predetermined number of Tx beams to obtain secondAttorney Docket No. 30134 / 86002 Ref. No. P64160WO1 measured RRM values for each of the predetermined number of Tx beams; generate, for transmission to the base station, a further beam report comprising the second measured RRM values; and process, based on signaling received from the base station, a beam indication message indicating the one of the predetermined number of Tx beams to be used.

20. The apparatus of claim 17, wherein the reference signals comprise Channel State Information reference signals (CSI-RS) or SSBs.

Images