Systems and methods of artificial intelligence based beam management

Abstract

A first wireless communication device may include one or more processors. The one or more processors may be configured to receive, via a transceiver from a base station over a wireless network, a first set of beams. The one or more processors may be configured to generate output data relating to a second set of beams as a set of candidate beams for beamforming by executing, with measurement data of the first set of beams as input data, a first model that has been learned using training data. The one or more processors may be configured to transmit, via the transceiver to the base station, one or more signal relating to the output data

Description

[0001] Atorney Docket No.: 121439-1417 (P211162US00)

[0002] SYSTEMSAND METHODS OF ARTIFICIAL INTELLIGENCE

[0003] BASED BEAM MANAGEMENT

[0004] CROSS-REFERENCE TO RELATED APPLICATION

[0005] This application claims priority to U.S. Provisional Patent Application No. 63 / 680,944 filed on August 8, 2025, which is incorporated by reference herein in its entirety for all purposes.

[0006] FIELD OF DISCLOSURE

[0007] The present disclosure is generally related to cellular radio, including but not limited to, systems and methods for beam management.

[0008] BACKGROUND

[0009] Beam management is increasingly used in wireless communication systems, with support expanding across a variety of devices and network configurations. Different beams may offer advantages depending on conditions, such as short-range coverage or high-mobility environments. To support low-latency communication, systems may evaluate and compare beam performance to select an optimal option. For example, devices can measure attributes like signal strength or quality across multiple beams to determine the most suitable one.

[0010] SUMMARY

[0011] Various embodiments disclosed herein relate to a user device including one or more processors. In some embodiments, the one or more processors may be configured to receive, via a transceiver from a base station over a wireless network, a first set of beams. The one or more processors may be configured to generate output data relating to a second set of beams as a set of candidate beams for beamforming by executing, with measurement data of the first set of beams as input data, a first model that has been learned using training data. The one or more processors may be configured to transmit, via the transceiver to the base station, one or more signal relating to the output data.

[0012] In some embodiments, the second set of beams may comprise one or more reference signals relating to one or more downlink transmission configuration indicator (TCI) states each of which may be linked to a corresponding source reference signal.

[0013] In some embodiments, the one or more signals may be transmitted using uplink control information (UCI) or medium access control control element (MAC-CE) to trigger transmission of the one or more reference signals by the base station.

[0014] In some embodiments, the one or more processors may be further configured to detect one or more events among a plurality of events relating to performance of the first model, and in response to the detecting, transmit, to the base station, a notification of the one or more

[0015] 1

[0016] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) events.

[0017] In some embodiments, the plurality of events may comprise at least one of (1) an event indicating that a link quality measurement value of a predicted beam as a result of beam indication is lower than a predefined threshold, (2) an event indicating that a difference between that a link quality measurement value of a predicted beam as a result of beam indication and a link quality measurement value of another beam is greater than a predefined threshold, (3) an event indicating that a difference between a predicted reference signal received power (RSRP) of a predicted beam as a result of beam indication and a measured RSRP of the predicted beam is greater than a predefined threshold, (4) an event indicating that a model accuracy of the first model based on the measurement data of the first set of beams is smaller than a predefined percentage, or (5) an event indicating that a difference between a predicted RSRP of the first set of beams and a measured RSRP of the first set of beams is greater than a predefined threshold.

[0018] In some embodiments, the one or more signals may indicate a request for transmission of a subset of reference signals which are mapped to transmission configuration indicator (TCI) states of the second set of beams, and the one or more processors are configured to receive, from the base station, the subset of reference signals and perform a performance monitoring of the first model using the subset of reference signals.

[0019] In some embodiments, the output data may comprise predicted measurement data of the second set of beams. In some examples, to perform the performance monitoring of the first model, the one or more processors may be configured to compare measurement data of the subset of reference signals with the predicted measurement data corresponding to the subset of reference signals.

[0020] In some embodiments, the one or more processors may be further configured to receive, via the transceiver from the base station, a subset of the second set of beams, and transmit, via the transceiver to the base station, a report relating to reference signal received power (RSRP) of the subset of the second set of beams.

[0021] In some embodiments, the report may include a RSRP difference between a predicted beam as a result of beam indication and the subset of the second set of beams.

[0022] In some embodiments, the one or more processors may be further configured to receive, via the transceiver from the base station, a beam indication including one or more transmission configuration indicator (TCI) states which are linked to the second set of beams and are not activated TCI states.

[0023] Various embodiments disclosed herein are related to a method, including receiving.

[0024] 2

[0025] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) by one or more processors of a user device via a transceiver from a base station over a wireless network, a first set of beams. The method may include generating, by the one or more processors, output data relating to a second set of beams as a set of candidate beams for beamforming by executing, with measurement data of the first set of beams as input data, a first model that has been learned using training data. The method may include transmitting, by the one or more processors via the transceiver to the base station, one or more signal relating to the output data.

[0026] BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are not intended to be drawn to scale. Like reference numbers and designations in the various drawings indicate like elements. For purposes of clarity, not every component can be labeled in even’ drawing.

[0028] FIG. 1 is a diagram of an example wireless communication system, according to an example implementation of the present disclosure.

[0029] FIG. 2 is a block diagram of a computing environment according to an example implementation of the present disclosure.

[0030] FIG. 3 is a block diagram of beam evaluation and setup, according to an example implementation of the present disclosure.

[0031] FIG. 4 is a sequence diagram showing beam management, according to an example implementation of the present disclosure.

[0032] FIG. 5 is a block diagram of model performance monitoring, according to an example implementation of the present disclosure.

[0033] FIG. 6 is a flowchart showing an example method of artificial intelligence based beam management, according to an example implementation of the present disclosure.

[0034] DETAILED DESCRIPTION

[0035] Before turning to the figures, which illustrate certain embodiments in detail, it should be understood that the present disclosure is not limited to the details or methodology set forth in the description or illustrated in the figures. It should also be understood that the terminology used herein is for the purpose of description only and should not be regarded as limiting.

[0036] FIG. 1 illustrates an example wireless communication system 100. The wireless communication system 100 may include a base station 110 (also referred to as “a wireless communication node 110” or “a station 110”) and one or more user equipment (UEs) 120 (also referred to as “wireless communication devices 120” or “terminal devices 120”). The base station 110 and the UEs 120 may communicate through wireless commination links

[0037] 3

[0038] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00)

[0039] 130A, 130B, 130C. The wireless communication link 130 may be a cellular communication link conforming to 3G, 4G, 5G or other cellular communication protocols or a Wi-Fi communication protocol. In one example, the wireless communication link 130 supports, employs or is based on an orthogonal frequency division multiple access (OFDMA). In one aspect, the UEs 120 are located within a geographical boundary with respect to the base station 110, and may communicate with or through the base station 110. In some embodiments, the wireless communication system 100 includes more, fewer, or different components than shown in FIG. 1. For example, the wireless communication system 100 may include one or more additional base stations 110 than shown in FIG. 1.

[0040] In some embodiments, the UE 120 may be a user device such as a mobile phone, a smart phone, a personal digital assistant (PDA), tablet, laptop computer, wearable computing device, etc. Each UE 120 may communicate with the base station 1 10 through a corresponding communication link 130. For example, the UE 120 may transmit data to a base station 110 through a wireless communication link 130, and receive data from the base station 110 through the wireless communication link 130. Example data may include audio data, image data, text, etc. Communication or transmission of data by the UE 120 to the base station 110 may be referred to as an uplink communication. Communication or reception of data by the UE 120 from the base station 110 may be referred to as a dow nlink communication. In some embodiments, the UE 120 A includes a wireless interface 122, a processor 124, a memory device 126, and one or more antennas 128. These components may be embodied as hardware, software, firmware, or a combination thereof. In some embodiments, the UE 120 A includes more, fewer, or different components than shown in FIG. 1. For example, the UE 120 may include an electronic display and / or an input device. For example, the UE 120 may include additional antennas 128 and wireless interfaces 122 than shown in FIG. 1.

[0041] The antenna 128 may be a component that receives a radio frequency (RF) signal and / or transmit a RF signal through a wireless medium. The RF signal may be at a frequency between 200 MHz to 100 GHz. The RF signal may have packets, symbols, or frames corresponding to data for communication. The antenna 128 may be a dipole antenna, a patch antenna, a ring antenna, or any suitable antenna for wireless communication. In one aspect, a single antenna 128 is utilized for both transmitting the RF signal and receiving the RF signal. In one aspect, different antennas 128 are utilized for transmitting the RF signal and receiving the RF signal. In one aspect, multiple antennas 128 are utilized to support multiple-in, multiple-out (MIMO) communication.

[0042] 4

[0043] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00)

[0044] The wireless interface 122 includes or is embodied as a transceiver for transmitting and receiving RF signals through a wireless medium. The wireless interface 122 may communicate with a wireless interface 112 of the base station 1 10 through a wireless communication link 130A. In one configuration, the wireless interface 122 is coupled to one or more antennas 128. In one aspect, the wireless interface 122 may receive the RF signal at the RF frequency received through antenna 128, and downconvert the RF signal to a baseband frequency (e.g., 0~I GHz). The wireless interface 122 may provide the downconverted signal to the processor 124. In one aspect, the wireless interface 122 may receive a baseband signal for transmission at a baseband frequency from the processor 124, and upconvert the baseband signal to generate a RF signal. The wireless interface 122 may transmit the RF signal through the antenna 128.

[0045] The processor 124 is a component that processes data. The processor 124 may be embodied as field programmable gate array (FPGA), application specific integrated circuit (ASIC), a logic circuit, etc. The processor 124 may obtain instructions from the memory device 126, and executes the instructions. In one aspect, the processor 124 may receive downconverted data at the baseband frequency from the wireless interface 122, and decode or process the downconverted data. For example, the processor 124 may generate audio data or image data according to the downconverted data, and present an audio indicated by the audio data and / or an image indicated by the image data to a user of the UE 120 A. In one aspect, the processor 124 may generate or obtain data for transmission at the baseband frequency, and encode or process the data. For example, the processor 124 may encode or process image data or audio data at the baseband frequency, and provide the encoded or processed data to the wireless interface 122 for transmission.

[0046] The memory device 126 is a component that stores data. The memory device 126 may be embodied as random access memory (RAM), flash memory, read only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, a hard disk, a removable disk, a CD-ROM, or any device capable for storing data. The memory’ device 126 may be embodied as a non-transitory computer readable medium storing instructions executable by the processor 124 to perform various functions of the UE 120A disclosed herein. In some embodiments, the memory device 126 and the processor 124 are integrated as a single component.

[0047] In some embodiments, each of the UEs 120B. .. 120N includes similar components of the UE 120 A to communicate with the base station 110. Thus, detailed description of duplicated portion thereof is omitted herein for the sake of brevity.

[0048] 5

[0049] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00)

[0050] In some embodiments, the base station 110 may be an evolved node B (eNB), a serving eNB. a target eNB, a femto station, or a pico station. The base station 110 may be communicatively coupled to another base station 110 or other communication devices through a wireless communication link and / or a wired communication link. The base station 110 may receive data (or a RF signal) in an uplink communication from a UE 120. Additionally or alternatively, the base station 110 may provide data to another UE 120, another base station, or another communication device. Hence, the base station 110 allows communication among UEs 120 associated with the base station 110, or other UEs associated with different base stations. In some embodiments, the base station 110 includes a wireless interface 112, a processor 114. a memory device 116, and one or more antennas 118. These components may be embodied as hardware, software, firmware, or a combination thereof. In some embodiments, the base station 110 includes more, fewer, or different components than shown in FIG. 1. For example, the base station 110 may include an electronic display and / or an input device. For example, the base station 110 may include additional antennas 118 and wireless interfaces 112 than shown in FIG. 1.

[0051] The antenna 118 may be a component that receives a radio frequency (RF) signal and / or transmit a RF signal through a wireless medium. The antenna 118 may be a dipole antenna, a patch antenna, a ring antenna, or any suitable antenna for wireless communication. In one aspect, a single antenna 118 is utilized for both transmitting the RF signal and receiving the RF signal. In one aspect, different antennas 118 are utilized for transmitting the RF signal and receiving the RF signal. In one aspect, multiple antennas 1 18 are utilized to support multiple-in, multiple-out (MIMO) communication.

[0052] The wireless interface 112 includes or is embodied as a transceiver for transmitting and receiving RF signals through a wireless medium. The wireless interface 112 may communicate with a wireless interface 122 of the UE 120 through a wireless communication link 130. In one configuration, the wireless interface 112 is coupled to one or more antennas 118. In one aspect, the wireless interface 112 may receive the RF signal at the RF frequency received through antenna 118, and downconvert the RF signal to a baseband frequency (e.g.. 0~l GHz). The wireless interface 112 may provide the downconverted signal to the processor 124. In one aspect, the wireless interface 122 may receive a baseband signal for transmission at a baseband frequency from the processor 114, and upconvert the baseband signal to generate a RF signal. The wireless interface 112 may transmit the RF signal through the antenna 118.

[0053] The processor 114 is a component that processes data. The processor 114 may be

[0054] 6

[0055] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) embodied as FPGA, ASIC, a logic circuit, etc. The processor 114 may obtain instructions from the memory’ device 116, and executes the instructions. In one aspect, the processor 114 may receive downconverted data at the baseband frequency from the wireless interface 112, and decode or process the downconverted data. For example, the processor 114 may generate audio data or image data according to the downconverted data. In one aspect, the processor 114 may generate or obtain data for transmission at the baseband frequency, and encode or process the data. For example, the processor 114 may encode or process image data or audio data at the baseband frequency, and provide the encoded or processed data to the wireless interface 112 for transmission. In one aspect, the processor 114 may set, assign, schedule, or allocate communication resources for different UEs 120. For example, the processor 114 mayset different modulation schemes, time slots, channels, frequency bands, etc. for UEs 120 to avoid interference. The processor 114 may generate data (or UL CGs) indicating configuration of communication resources, and provide the data (or UL CGs) to the wireless interface 112 for transmission to the UEs 120.

[0056] The memory device 116 is a component that stores data. The memory device 116 may be embodied as RAM, flash memory', ROM, EPROM, EEPROM, registers, a hard disk, a removable disk, a CD-ROM, or any device capable for storing data. The memory- device 1 16 may be embodied as a non-transitory computer readable medium storing instructions executable by the processor 114 to perform various functions of the base station 110 disclosed herein. In some embodiments, the memory device 116 and the processor 114 are integrated as a single component.

[0057] In some embodiments, communication between the base station 110 and the UE 120 is based on one or more layers of Open Systems Interconnection (OSI) model. The OSI model may include layers including: a physical layer, a Medium Access Control (MAC) layer, a Radio Link Control (RLC) layer, a Packet Data Convergence Protocol (PDCP) layer, a Radio Resource Control (RRC) layer, a Non Access Stratum (NAS) layer or an Internet Protocol (IP) layer, and other layer.

[0058] Various operations described herein can be implemented on computer systems. FIG. 2 shows a block diagram of a representative computing sy stem 214 usable to implement the present disclosure. In some embodiments, the source devices 110 and the sink device 120 are implemented by the computing system 214. Computing system 214 can be implemented, for example, as a consumer device such as a smartphone, other mobile phone, tablet computer, wearable computing device (e.g., smart watch, eyeglasses, head wearable display), desktop computer, laptop computer, or implemented with distributed computing devices. In some

[0059] 7

[0060] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) embodiments, the computing system 214 can include conventional computer components such as processors 216, storage device 218, network interface 220, user input device 222, and user output device 224.

[0061] Network interface 220 can provide a connection to a wide area network (e.g., the Internet) to which WAN interface of a remote server system is also connected. Network interface 220 can include a wired interface (e.g., Ethernet) and / or a wireless interface implementing vanous RF data communication standards such as Wi-Fi, Bluetooth, or cellular data network standards (e g., 3G, 4G, 5G, 60 GHz, LTE, etc ).

[0062] The network interface 220 may include a transceiver to allow the computing system 214 to transmit and receive data from a remote device using a transmitter and receiver. The transceiver may be configured to support transmission / reception supporting industry standards that enables bi-directional communication. An antenna may be attached to transceiver housing and electrically coupled to the transceiver. Additionally or alternatively, a multi-antenna array may be electrically coupled to the transceiver such that a plurality of beams pointing in distinct directions may facilitate in transmitting and / or receiving data.

[0063] A transmitter may be configured to wirelessly transmit frames, slots, or symbols generated by the processor unit 216. Similarly, a receiver may be configured to receive frames, slots or symbols and the processor unit 216 may be configured to process the frames. For example, the processor unit 216 can be configured to determine a type of frame and to process the frame and / or fields of the frame accordingly.

[0064] User input device 222 can include any device (or devices) via which a user can provide signals to computing system 214; computing system 214 can interpret the signals as indicative of particular user requests or information. User input device 222 can include any or all of a keyboard, touch pad. touch screen, mouse or other pointing device, scroll wheel, click wheel, dial, button, switch, keypad, microphone, sensors (e.g., a motion sensor, an eye tracking sensor, etc.), and so on.

[0065] User output device 224 can include any device via which computing system 214 can provide information to a user. For example, user output device 224 can include a display to display images generated by or delivered to computing system 214. The display can incorporate various image generation technologies, e.g., a liquid crystal display (LCD), lightemitting diode (LED) including organic light-emitting diodes (OLED), projection system, cathode ray tube (CRT), or the like, together with supporting electronics (e.g., digital -to- analog or analog-to-digital converters, signal processors, or the like). A device such as a touchscreen that function as both input and output device can be used. Output devices 224

[0066] 8

[0067] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) can be provided in addition to or instead of a display. Examples include indicator lights, speakers, tactile "‘display"’ devices, printers, and so on.

[0068] Some implementations include electronic components, such as microprocessors, storage and memory that store computer program instructions in a computer readable storage medium (e.g., non-transitory computer readable medium). Many of the features described in this specification can be implemented as processes that are specified as a set of program instructions encoded on a computer readable storage medium. When these program instructions are executed by one or more processors, they cause the processors to perform various operation indicated in the program instructions. Examples of program instructions or computer code include machine code, such as is produced by a compiler, and files including higher-level code that are executed by a computer, an electronic component, or a microprocessor using an interpreter. Through suitable programming, processor 216 can provide various functionality for computing system 214, including any of the functionality7described herein as being performed by a server or client, or other functionality associated with message management services.

[0069] It will be appreciated that computing system 214 is illustrative and that variations and modifications are possible. Computer systems used in connection with the present disclosure can have other capabilities not specifically described here. Further, while computing system 214 is described with reference to particular blocks, it is to be understood that these blocks are defined for convenience of description and are not intended to imply a particular physical arrangement of component parts. For instance, different blocks can be located in the same facility7, in the same server rack, or on the same motherboard. Further, the blocks need not correspond to physically distinct components. Blocks can be configured to perform various operations, e.g., by programming a processor or providing appropriate control circuitry, and various blocks might or might not be reconfigurable depending on how the initial configuration is obtained. Implementations of the present disclosure can be realized in a variety of apparatus including electronic devices implemented using any combination of circuitry and software.

[0070] Embodiments in the present disclosure can provide useful techniques for providing a mechanism for supporting artificial intelligence (Al) / machine learning (ML) models for beam management in cellular radio air interface (5G and / or beyond-5G) for both temporal and spatial domain beam management which addresses the configuration of a measurement set of beams (e.g., a “set B of beams”) and a model output set of beams (e.g.. a “set A of beams”). Embodiments in the present disclosure can also provide useful techniques for

[0071] 9

[0072] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) providing support AI / ML model performance monitoring, model selection and / or switching, and / or beam indication of predicted beams and data collection Embodiments in the present disclosure can contribute to reducing measurement complexity, overhead and latency of legacy beam management mechanisms for cellular air interface. The term “set A of beams” may refer to a full set of beams that can be used to transmit and receive information from a base station to user equipment (UE). The “set A of beams” may be mapped to the output of an artificial intelligence model for beam monitoring. The term “set B of beams” may refer to a subset of beams, such as a subset of the “set A of beams,” that are measured by the UE as part of beam sweep phase. The “set B of beams” may be provided as input to the artificial intelligence model.

[0073] Disclosed herein are related systems and methods for beam management. A base station (e.g., next-generation Node B (gNB)) and user device (e.g., user equipment (UE)) may evaluate beams to select an optimal beam for transmission. For example, the base station can transmit a set of reference signals on available dow nlink beams and the user device can evaluate performance metrics of the reference signals. In response to identifying a beam with optimal performance metrics, the base station can select that beam for downlink transmissions. In some examples, an artificial intelligence model may be used to predict performance metrics that have not been measured. As an example, the artificial intelligence model can predict performance metrics for beams for which the base station did not send a reference signal. As another example, the artificial intelligence model can predict performance metrics for a future time period based on measurements from a prior period. Based on these predictions, the base station can select an unmeasured beam as the optimal downlink beam. This may reduce netw ork resources associated with beam management, as the base station and user device may measure fewer beams. However, in some cases, the artificial intelligence model may produce inaccurate predictions. For instance, it might predict that a beam will perform better or worse than it actually does. This can lead the base station to select a suboptimal beam, potentially reducing transmission performance. For example, using a less suitable beam may result in increased latency, which can degrade the overall quality of service and impact time-sensitive applications.

[0074] Systems and methods according to some implementations can monitor performance of an artificial intelligence model for beam management to determine when predictions have become inaccurate. The predictions of the artificial intelligence model may trigger a performance monitoring event. For example, performance metrics of a selected beam, on their own or in comparison to performance metrics of a set of configuration beams that are

[0075] 10

[0076] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) periodically measured, can satisfy a monitoring threshold. Either the base station or the user device can determine that the selected beam satisfies the monitoring threshold. In response to this determination, either system can trigger the performance monitoring event. The base station can then transmit an additional set of beams (e.g., different from the set of configuration beams) to be measured by the user device. The user device or the base station can also execute the artificial intelligence model to predict performance metrics of the additional set of beams. Based on the comparison of the measured performance metrics and predicted performance metrics, the base station or user device can determine that the artificial intelligence model should be switched to a new model or that beam management should be switched back to conventional (e.g., non-artificial intelligence based) beam management.

[0077] FIG. 3 is a block diagram of beam evaluation and setup, according to an example implementation of the present disclosure. Base station 302 and user device 304 may execute a series of steps 350-364 to designate a beam for beamforming. For example, base station 302 may initiate beam sweeping to transmit multiple candidate beams across different directions. This may be performed when user device 304 establishes a connection (e.g., initially or as part of re-connecting) or to improve an existing connection with user device 304. User device 304 can then measure the qualify' of each received beam and report the results back to base station 302. In response to this feedback, base station 302 can designate the optimal beam for a communication link with user device 304.

[0078] A set of beams can refer to a predefined set of communication channels. Each beam can be configured with specific parameters such as direction, width, and power, which can allow the base station to cover different spatial sectors efficiently. For example, beams can operate at different frequencies, where higher frequencies can support higher data rates but may have shorter range. Certain beams may be a better fit based on attributes of user device 304 or the environment in which the communications are being transmitted within. For example, a narrow, high-gain beam may be better for environments with a clear line-of-sight between user device 304 and base station 302, while a wider, lower-frequency beam may be more effective for a cluttered or obstructed environment. In some examples, selecting a more optimal beam may reduce latency in transmissions between user device 304 and base station 302.

[0079] Base station 302 may be a network node that facilitates wireless communication by transmitting and receiving signals between user devices and a network. For example, base station 302 can manage attributes of transmissions, such as transmission power, modulation scheme, resource block allocation, and / or the like. In an example, base station 302 may be a

[0080] 11

[0081] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) next-generation Node B (gNB) of a 5G network. For example, base station 302 can manage wireless communication between the 5G core network and user equipment, such as user device 304. As part of managing the 5G core network, base station 302 can manage which beam user device 304 transmits information on. For example, base station 302 may select a beam from a predefined set of candidate beams based on signal quality measurements.

[0082] User device 304 may be a device that receives and transmits information to a network. For example, user device 304 may be user equipment (UE). such as a smartphone, tablet, laptop, set of smart glasses, or Internet of Things (loT) sensor that can connect to the network to enable communication and / or data access. In an example, user device 304 may include a transceiver with which information can be transmitted and received from base station 302 over the network. The transceiver may be an electronic device that enables two-way communication. In an example, user device 304 and base station 302 may communicate according to network protocol of the netw ork. For example, user device 304 and base station 302 may communicate using standardized 5G signaling procedures, such as beam reporting, scheduling requests, and channel quality feedback.

[0083] At step 350, user device 304 and base station 302 may communicate on a pair of beams, with a first beam for transmitting data (e.g., downlink from base station 302 to user device 304) and a second beam for receiving data (e.g., uplink from user device 304 to base station 302). In an example, base station 302 may designate a downlink beam based on a previous report indicating performance metrics (e.g., power) of a set of candidate beams. Base station 302 may designate the candidate beam associated with the best performance metrics as the downlink beam.

[0084] At step 352, base station 302 can transmit reference signals. For example, base station 302 can periodically transmit reference signals to user device 304. Base station 302 may designate certain beams as associated with the physical layer (e.g., Layer 1). The reference signals may be transmitted on the designated beams to allow user device 304 to evaluate signal quality across multiple spatial directions. User device 304 can then use these measurements to assist in selecting or confirming the optimal beam for communication.

[0085] At step 354, user device 304 can monitor the reference signals transmitted by base station 302. For example, based on reference signals received from base station 302, user device 304 can measure quality metrics such as signal power (e.g., Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Signal-to- Interference-plus-Noise Ratio (SINR). and / or the like). User device 304 may compare these quality metrics to determine which beam is the most optimal. As an example, a beam that has

[0086] 12

[0087] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) a higher RSRP may be more optimal than a beam with a lower RSRP. In an example, user device 304 may generate a report based on the reference signals.

[0088] At step 356, user device 304 may transmit the report to base station 302. In this example, user device 304 may wait for a periodic reporting instance to transmit the report to base station 302. This report can inform base station 302 decisions on whether to change beams designated for receiving and transmitting information to user device 304.

[0089] At step 358, base station 302 may send an indication of a new beam for transmitting and / or receiving data. For example, in response to receiving a report that indicates another beam would be more optimal (e.g., result in lower latency), base station 302 can designate this beam for communications. This process may involve beamforming techniques to dynamically select or adjust the beam direction. In an example, base station 302 can designate the beam using downlink control information (DL DO). This may allow user device 304 to align reception or transmission with the indicated beam for subsequent communications.

[0090] At step 360, user device 304 may acknowledge the change in designated beams for communications. For example, user device 304 can send an acknowledgement frame indicating successful reception of the beam switch command and readiness to receive or transmit data using the newly designated beam.

[0091] At step 362, user device 304 and base station 302 may reconfigure their transmission and / or reception parameters to initiate communication using the newly designated beam. For example, switching beams may involve processing and coordination of parameters (e.g., updated beamforming weights, antenna port mappings, timing alignment, and / or the like).

[0092] At step 364, user device 304 and base station 302 may communicate using the new beam indicated by base station 302. This may be the same or similar to step 350. In some examples, base station 302 can continue to periodically transmit reference signals. As a result, selected beams for transmitting and / or receiving data may continue to change based on measured values (e.g., power, and / or the like) of the reference signals.

[0093] FIG. 4 is a sequence diagram showing beam management, according to an example implementation of the present disclosure. For example, beams may be managed in the temporal or spatial domain. Temporal domain management may involve dynamically updating beam configurations over time. Spatial domain management may involve directing beams toward specific physical locations or angles. In temporal domain management, inferences may be used to predict future measurements of a beam. In spatial domain management, inferences may be used to predict unmeasured beams. In either case, the

[0094] 13

[0095] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) machine learning model may reduce usage of network resources associated with measuring beams.

[0096] At step 450, base station 302 can transmit reference signal to user device 304. For example, base station 302 may transmit Channel State Information Reference Signals (CSI- RSs) to user device 304 to enable user device 304 to perform channel quality measurements across different beams. Base station 302 may be associated with downlink beams 402. The downlink beams may be a predefined set of beams from which a beam can be selected for transmissions from base station 302 to user device 304. In examples where beams are managed in the spatial domain, base station 302 can transmit the reference signal on a subset 402a of downlink beams 402. In examples where beams are managed in the temporal domain, reference signals may be transmitted to user device 304 on at least one of the downlink beams 402 within a defined observation window (e.g., a specific period of time allocated for measurement).

[0097] At step 452, user device 304 can perform measurements on received reference beams and transmit a report to base station 302. For example, to step 356 of FIG. 3, user device 304 can generate a report indicating parameters (e.g., latency, and / or the like) of transmitted reference beams. In an example, user device 304 may identify an optimal beam. The optimal beam may be identified based on a parameter. For example, the optimal beam may be the beam associated with the highest power (e.g., RSRP). In this example, user device 304 can perform Layer 1 measurement on the optimal beam. User device 304 can then transmit a layer 1 report with Layer 1 RSRP. In examples where beams are managed in the temporal domain, user device 304 can generate a report that indicates time instances associated with the measurements.

[0098] At step 454, base station 302 can execute an artificial intelligence model to predict measurement values based on the report received from user device 304. For example, the artificial intelligence model may be trained to predict measurement values that are not included in the report based on the report. In some examples, user device 304 may execute the artificial intelligence model. For example, user device 304 can execute the artificial intelligence model and transmit the output along with the report to base station 302. In examples where beams are managed in the spatial domain, the artificial intelligence model may predict measurement values for beams that were not measured (e.g., beams that are not part of the subset 402a of downlink beams 402). As a result, the artificial intelligence model can identify an unmeasured beam from downlink beams 402 as the optimal beam. For example, the artificial intelligence model can select beam 402b as the beam with the lowest

[0099] 14

[0100] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) latency. In examples, where beams are managed in the spatial domain, the artificial intelligence model can predict measurement values outside the time window of the observation window. For example, the artificial intelligence model can predict how the measurement values change over time based on the measurement values within the observation window included in the report. This may be predicted for the one or more beams included in the report. As a result, the artificial intelligence model can identify which beams should be used for transmissions during a prediction window, where the prediction window is a period of time that is subsequent to the observation window.

[0101] At step 456, base station 302 can execute transmissions according to the predictions of the artificial intelligence model. For example, in the spatial domain, base station 302 may execute communications on the beam that the artificial intelligence model has predicted to have optimal predicted performance metrics. For example, base station can execute downlink transmissions on beam 402b in response to the artificial intelligence model predicting that beam 402b has the most optimal metrics (e.g., highest RSRP, SINR, and / or the like). As another example, in the temporal domain, base station 302 may change which beam is used over a period of time for downlink transmissions according to the predictions of the artificial intelligence model.

[0102] FIG. 5 is a block diagram of model performance monitoring, according to an example implementation of the present disclosure. For example, user device 304 can execute an artificial intelligence model to predict measurements (e.g., RSRP) for beams. However, in some examples, the predictions may be inaccurate. For example, the predictions may be inaccurate due to insufficient training data, changing environment conditions, or unaccounted for variables. Base station 302 and / or user device 304 may be configured to monitor the artificial intelligence model to determine if predictions are inaccurate. For example, either base station 302 or user device 304 may trigger monitoring of an additional set of beams in response to determining that a threshold performance condition has been met.

[0103] In some embodiments, base station 302 may be associated with a second set of beams that can be used to train, re-train, and / or evaluate the artificial intelligence model. For example, when either base station 302 or user device 304 triggers a performance monitoring event (e g., in response to determining that the threshold performance condition has been met), the second set of beams may be measured, in addition to a first set of beams (e.g., a set B of beams). The first set of beams may be conventional configuration beams (e.g., CSI-RS beams used for Channel State Information Resource Configuration (CSIResouceConfig) and the second set of beams may not overlap with the first set of beams. In an example, the

[0104] 15

[0105] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) second set of beams can include an identifier that links it to the first set of beams. In some examples, data collected based on the second set of beams can be used to train the artificial intelligence model. In these examples, user device 304 can assume that when the second set of beams is activated for training, the beams will be transmitted using reference signals linked via Quasi-Co-Location (QCL) to Transmission Configuration Indicator (TCI) states of the second set. As an example, each beam in the second set of beams can be associated with a TCI state that indicates to a user device how that beam is configured. The TCI state can point to a QCL source, which can indicate which reference signal to expect and measure. When user device 304 activates the second set of beams, it can determine which reference signals to expect based on this information. In an example, user device 304 may transmit an uplink signal to base station 302 to trigger transmission of reference signals linked to all TCI sets associated with the second set of beams. Additionally, or alternatively, user device 304 may transmit an uplink signal to base station 302 to trigger transmission of reference signals associated with a subset of TCI states of the second set of beams. The subset of TCI states can be different from the first set of beams.

[0106] In some embodiments, base station 304 may indicate a beam index that is part of the second set of beams, but is not one of the activated TCI states. For example, current TCI framework may support a predetermined number of activated TCI states. Active TCI states may be currently configured beam directions that the user device can use for receiving downlink transmissions. The active TCI states may include the first set of beams. In an example, base station 304 may indicate a dormant beam without activating the TCI state by using MAC-CE. This may reduce latency of indicating the dormant beam. For example, the TCI states may include a set of dormant TCI state linked to the second set of beams. These states may be measured by user device 304 as part of model training or performance monitoring, but may not be a part of the first set of beams. In an example, the dormant TCI state may be indexed by addition of a new bit in the beam indication DL DCI format. In an example, the dormant TCI states can be indexed by the active TCI states by extending the DCI indication field. Alternatively, the dormant TCI states may be part of a separate list. For example. TCI states can include a single bit indication of whether a TCI state is dormant or active. As a result, base station 304 can indicate a dormant TCI state will be used for transmissions by indexing it as part of a control message (e.g., MAC-CE).

[0107] In response to determining that the monitoring threshold for triggering performance monitoring has been met, user device 304 may transmit a report and / or signal of the performance monitoring event. These may be transmitted on an uplink resource dedicated for

[0108] 16

[0109] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) performance monitoring. The uplink resource may be linked to the event type. The signal of the performance monitoring event can include an event identifier that indicates a type of event (e.g., predicted beam being below a threshold, predicted beam satisfying a threshold difference from the first set of beams, and / or the like) that has been triggered. The report can include measurements associated with the first set of beams and / or predicted beam. Alternatively, base station 302 may trigger the performance monitoring event. For example, in response to determining that the link quality satisfies a monitoring threshold, base station 302 can configure user device 304 to monitor the artificial intelligence model. In this example, base station 302 can determine that user device 304 satisfies the monitoring threshold based on the report provided by user device 304.. In response to either base station 302 or user device 304 determining that the artificial intelligence model satisfies the monitoring threshold, user device 304 and base station 302 may monitor the performance of the artificial intelligence model.

[0110] The monitoring threshold may include a variety of events that indicate potential degradation in model performance. As an example, the monitoring threshold may include a measured quality of a current link (e.g., selected by the artificial intelligence model) being less than a threshold. As another example, the monitoring threshold can include a difference between predictions and measurements of a current beam or the first set of beams. For example, predictions may be generated for the first set of beams, in addition to measurements taken by user device 304. Similarly, predictions and measurements may be generated and collected, respectively, for the current beam selected by the artificial intelligence model. The monitoring threshold can include a threshold amount or percentage of difference between the predictions and the measurements. In some examples, the thresholds may be associated with conditions, such as a time window or number of occurrence times. As an example, user device 304 can determine that the monitoring threshold for triggering performance monitoring has been met based on a predicted performance metric for the current beam being worse than a measured performance metric for the current beam for a threshold amount of time.

[0111] Steps 550-558 can represent performance monitoring triggered by user device 304. At step 550, user device 304 may transmit a signal to base station 302 to transmit all or a subset of reference signal resources associated with a second set of beams. For example, user device 304 may transmit this request in response to determining that the artificial intelligence model satisfies the monitoring threshold. As an example, the monitoring threshold may be that the predicted performance metrics generated by the artificial intelligence model of a current

[0112] 17

[0113] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) beam are worse than a threshold or worse than measured beams by a threshold, or predictions associated with the first set of beams are worse than the measured values of those beams. The requested reference signal resources may be linked to TCI sates (e.g., beam directions) in the second set of beams (e.g., set A of beams). In an example, the request may be carried via uplink control information (UCI) or medium access control control element (MAC-CE). The request can indicate which beam indexes or TCI states corresponding to the reference signals should be transmitted.

[0114] At step 552, base station 302 can transmit the second set of beams. For example, base station 302 can transmit reference signals requested by user device 304 that represent the second set of beams along with the first set of beams. The first set of beams can represent conventional configuration beams, and the second set of beams can represent additional beams of which the measurements can be used to evaluate model performance during a performance monitoring event. In an example where the base station 302 triggers performance monitoring, base station 302 may transmit the second set of beams without a request from user device 304. In this example, base station 302 may transmit the second set of beams in response to determining that the artificial intelligence model satisfies a monitoring threshold, rather than in response to a request from user device 304.

[0115] At step 554, user device 304 can execute the artificial intelligence model to generate a prediction and transmit a report based on the prediction to base station 302. For example, user device 304 may execute the artificial intelligence model (e.g.. step 454 of FIG. 4) to generate a prediction of performance metrics (e.g., RSRP, and / or the like). In some examples, user device 304 can determine an accuracy of the predictions of the artificial intelligence model based on the prediction. User device 304 can generate a report based on the prediction generated by the artificial intelligence model and the measured performance metrics. For example, the report can include predicted performance metrics for a current beam that the artificial intelligence model has predicted to be the best beam and measured performance metrics of the second set of beams. Additionally, or alternatively, the report can indicate an accuracy of the artificial intelligence model.

[0116] In some embodiments, the artificial intelligence model may be on the network side. For example, the artificial intelligence model may be executed by base station 302. In this example, base station 302 can transmit the second set of beams. Base station 302 may then receive, from user device 304, a report indicating performance metrics of a current beam (e.g., that the artificial intelligence model has indicated to be the best choice) and the beams in the second set of beams.

[0117] 18

[0118] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00)

[0119] At step 556, base station 302 can evaluate whether the artificial intelligence model satisfies the failure threshold and transmit an instruction to user device 304 based on the evaluation. For example, base station 302 can determine that the artificial intelligence model satisfies the failure threshold (e.g., performance is suboptimal) based on the report indicating model accuracy below a threshold percentage or model predictions are a threshold distance from the measured performance metrics. In response to determining that the artificial intelligence model satisfies the failure threshold, base station 302 can transmit an instruction that instructs user device 304 to switch to another identified model. For example, the artificial intelligence model may be a second model, and user device 304 may be associated with a plurality of artificial intelligence models including the second model. The various artificial intelligence models may have different parameters (e.g., weights, and / or the like) or be different types of models (e.g., neural network, linear regression, decision tree, and / or the like). In some examples, base station 302 can identify a first model for generating predictions. For example, base station 302 may select the first model from a list (e.g., ranking) of the plurality of artificial intelligence models or select the first model based on the report provided at step 554. As an example, base station 302 can select the better model based on which beam satisfied the failure condition.

[0120] At step 558, user device 304 may switch models according to the instruction provided by base station 302. For example, in response to receiving an instruction to switch predictions from a first model to a second model, user device 304 may switch predictions to the second model. Alternatively, user device 304 and base station 302 may switch to non-artificial intelligence based beam management in response to the instruction provided by base station 302. In an example, user device 304 may transmit an indication to switch to another model or non-artificial intelligence beam management in response to determining that model failure has occurred. In this example, user device 304 may determine that model failure has occurred based on the output of the model satisfying a failure threshold. For example, based on comparing the model output including predicted performance metrics to the measured performance metrics, the user device can determine that the model has failed. Alternatively, base station 302 may determine that model failure has occurred based on the report provided by user device 304. In an example where base station 302 manages model switching, user device 304 can request switching to another model or non-artificial beam management. In an example, where user device 304 manages model switching, user device 304 can transmit a notification that beam management will be switched to another model or non-artificial intelligence beam management.

[0121] 19

[0122] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00)

[0123] FIG. 6 is a flowchart showing an example method 600 of artificial intelligence based beam management, according to an example implementation of the present disclosure. In some embodiments, this method may be performed by a user device (e.g., user device 304 of FIG. 3). For example, the method may be performed by the user device that is in communication with a base station (e.g., base station 302 of FIG. 3). In this example, the user device and the base station may be configured to execute uplink and downlink communications over a pair of beams.

[0124] In some embodiments, the user device may communicate with the base station via a beam indicated by a beam indication. For example, the base station may transmit downlink communications to the user device on a predicted beam that an artificial intelligence model has predicted to be associated with the highest performance metric of a set of candidate beams. In an example, the base station may designate a beam, such as the predicted beam, for communications by transmitting a beam indication that indicates the transmission configuration indicator (TCI) state on which downlink or uplink communications will be executed. A TCI state can indicate a beam along with spatial parameters of transmissions on that beam, such as beam direction and reference signal configuration. In an example, the user device and the base station may be associated with a set of active TCI states that are currently configured for use, and there may be a preset number of active TCI states that the user device and base station can designate. Some beams that have been measured by the user device may not be included in the active TCI states due to the limited number of active TCI states that can be configured between the user device and the base station. In an example, the base station may indicate dormant (e.g., not active) TCI states as part of the beam indication. As an example, a second set of beams (e.g., a set A of beams) used for training or evaluating models may correspond to dormant states that have been measured but are not currently configured as active TCI states. The base station may extend a number of bits included in the beam indication to include an indication of dormant states or add another bit that indicates whether a TCI state is dormant or active. This may allow the base station to indicate one of the dormant states as part of the beam indication.

[0125] At step 602, the user device may receive a first of beams from a base station. For example, the user device may receive a first set of beams (e.g., a set B of beams) associated with conventional configuration of beams. The first set of beams may be periodically received from the base station to evaluate whether executing transmissions on a beam other than the predicted beam may improve performance (e.g., reduce latency). In an example, the user device may include a transceiver. The transceiver may be an electronic device that

[0126] 20

[0127] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) combines both a transmitter and a receiver in a single unit, enabling it to send and receive signals over a communication channel. In this example, the first set of beams may be received from the base station via the transceiver.

[0128] At step 604, the user device may generate output data relating to the second set of beams. For example, the user device may provide measurement data associated with the first set of beams (e.g., set B of beams) as input to cause the first model to generate the output data. In this example, the user device may generate measurement data such as RSRP or signal -to-interference-plus-noise ratio (SINR) by measuring the first set of beams transmitted by the base station. The user device can then execute the first model on the measurement data associated with the first set of beams, which can generate output data including a prediction of measurement data associated with the second set of beams. The output data may include data such as predicted RSRP or predicted SINR. Alternatively, the user device may provide the measurement data to the base station and the base station may execute the first model. In an example, the second set of beams may represent a set of candidate beams for beamforming. Beamforming may refer to focusing a wireless signal in a direction, which can improve signal strength and may reduce interference. In an example, the second set of beams may represent candidate beams that can be selected as a beam for communications between the user device and the base station. A candidate beam may be selected as the predicted beam based on the output of the first model. Specifically, the candidate beam may be selected as the predicted beam based on output data predicting that it has the best performance metrics (e g., RSRP).

[0129] In some embodiments, the second set of beams may include one or more reference signals that relate to TCI states. In an example, the second set of beams may be independent of the first set of beams, and therefore may include different TCI states. In this example, the second set of beams may include an identifier that links beams in the second set of beams to corresponding beams in the first set of beams. In an example the second set of beams may be configured outside of conventional CSIResourceConfig and may include quasi-co-location (QCL) source reference signals, such as QCL Type D (e.g., Same timing and frequency offset) or QCL Type A (e.g.. same Doppler shift and delay spread) source reference signals.

[0130] At step 606, the user device may transmit one or more signals relating to the output data to the base station. For example, the user device can transmit a report comprising the measurement data and / or a notification of an event. As an example, the user device can compile a report including the measurement data of the first set of beams and / or the predicted measurement data associated with the second set of beams. Additionally, or alternatively, the

[0131] 21

[0132] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) one or more signals can include a notification. For example, in response to determining that an event, such as a deterioration in model performance has occurred, the user device may transmit a notification to the base station.

[0133] In some embodiments, the one or more signals may trigger a performance monitoring event. For example, the user device can detect one or more events among a plurality of events relating to performance of a first model that indicate model performance may have deteriorated (e.g., monitoring thresholds). In response to detecting an event indicating that performance may have deteriorated, the user device can transmit a notification of the one or more events to the base station. For example, in response to determining that the output of the first model satisfies an event (e.g., monitoring threshold), the user device can transmit a notification of this determination to the base station as the signal relating to the output data. This notification may trigger the performance monitoring event.

[0134] In some embodiments, the plurality of events may include various events associated with measurement values of the predicted beam and / or a beam from the first set of beams (e.g., the set of beams measured by the user device). The user device can determine that performance of the first model has deteriorated in response to detecting one or more of the plurality of events. In an example, the plurality of events may include a first event associated with link quality. The first event may indicate that a link quality measurement of the predicted beam is lower than a predefined threshold. For example, as transmissions are received over the predicted beam, the user device may determine measurement values of the predicted beam in response to the transmission.

[0135] In an example, the plurality of events can include a second event indicating that a difference between the measurement value of the predicted beam and the measurement value of another beam (e.g., a beam from the first set of beams) is greater than a predefined threshold. For example, the base station may periodically transmit the first set of beams to determine if another beam would improve performance. In response to determining that a measurement value associated with one of the beams in the first set of beams is greater than the measurement value of the predicted beam on which communications are currently being transmitted, the user device can detect the second event.

[0136] In an example, the plurality of events can include a third event indicating that a difference between a predicted measurement value and a received measurement value for the predicted beam is greater than a predefined threshold. For example, the user device may detect the third event in response to determining that a difference between a predicted received signal received power (RSRP) of the predicted beam and a measured RSRP of the

[0137] 22

[0138] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) predicted beam satisfies the predefined threshold.

[0139] In an example, the plurality of events can include a fourth event associated with model accuracy. The user device may generate predicted values (e.g., by executing the first model) and measured values associated with the first set of beams based on the reference signals transmitted by the base station. An accuracy may be determined based on the predicted and measured values, and the user device can detect the fourth event if the accuracy is smaller than a predefined percentage.

[0140] In an example, the plurality of events can include a fifth event associated with a difference between predictions and measured values associated with the first set of beams. In an example, the artificial intelligence model can generate predicted values and measured values for the first set of beams. As an example, the first model can generate a predicted RSRP of the first set of beams and the user device can generate a measured RSRP of the first set of beams. The user device may detect the fifth event in response to determining that the difference between the predicted RSRP and the measured RSRP of the first set of beams is greater than a predefined threshold.

[0141] In some embodiments, the one or more signals may trigger transmission of one or more reference signals by the base station. In an example, the one or more signals may be transmitted using uplink control information (UCI) or medium access control control element (MAC-CE) to trigger transmission of the one or more reference signals by the base station. This mechanism may allow the user device to trigger model performance monitoring. For example, the user device may monitor the performance of the first model based on reference signals received in response to the one or more signals.

[0142] In some embodiments, the one or more signals may be a request for transmission of the subset of signals. For example, the user device may trigger model performance monitoring by transmitting a request for the subset of reference signals associated with the second set of beams. As an example, in response to detecting an event that indicates the performance of the model may have deteriorated, the user device may trigger model performance monitoring by transmitting the one or more signals. In this example the one or more signals may indicate a request for transmission of a subset of reference signals are mapped to TCI states of the second set of beams. In response to the request, the base station may transmit the subset of reference signals. The user device can then receive the subset of reference signals and perform performance monitoring of the first model based on this subset of reference signals. In an alternative example, the base station may detect the event and trigger model performance monitoring. In this example, the base station may transmit the

[0143] 23

[0144] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) subset of reference signals mapped to TCI states of the second set of beams in response to detecting the event.

[0145] In some embodiments, performance monitoring can include comparing measured and predicted data associated with the reference signals. For example, the output data may include predicted measurement data of the second set of beams. As part of performance monitoring, the user device may compare measurement data and predicted data. For example, the user device may generate measurement data by measuring the subset of reference signals received from the base station. The user device can then compare the predicted measurement data generated by the first model with the measurement data.

[0146] In some embodiments, the user device can transmit a report indicating measured data associated with the second set of beams as part of performance monitoring. For example, the user device can receive a subset of the second set of beams from the base station via the transceiver. The user device can then measure RSRP of the subset of the second set of beams. For example, the user device can measure a power level of the received signals transmitted over the subset of the second beams. The user device can then generate a report indicating the RSRP of the subset of the second set of beams and transmit the report to the base station. In an example, the report may include an RSRP difference between the predicted beam and the subset of the second set of beams.

[0147] Having now described some illustrative implementations, it is apparent that the foregoing is illustrative and not limiting, having been presented by way of example. In particular, although many of the examples presented herein involve specific combinations of method acts or system elements, those acts and those elements can be combined in other ways to accomplish the same objectives. Acts, elements and features discussed in connection with one implementation are not intended to be excluded from a similar role in other implementations or implementations.

[0148] The hardware and data processing components used to implement the various processes, operations, illustrative logics, logical blocks, modules and circuits described in connection with the embodiments disclosed herein may be implemented or performed with a general purpose single- or multi-chip processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, or, any conventional processor, controller, microcontroller, or state machine. A processor also may be implemented as a

[0149] 24

[0150] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. In some embodiments, particular processes and methods may be performed by circuitry that is specific to a given function. The memory (e.g., memory, memory unit, storage device, etc.) may include one or more devices (e.g., RAM, ROM, Flash memory, hard disk storage, etc.) for storing data and / or computer code for completing or facilitating the various processes, layers and modules described in the present disclosure. The memory may be or include volatile memory or non-volatile memory, and may include database components, object code components, script components, or any other type of information structure for supporting the various activities and information structures described in the present disclosure. According to an exemplary embodiment, the memory is communicably connected to the processor via a processing circuit and includes computer code for executing (e.g., by the processing circuit and / or the processor) the one or more processes described herein.

[0151] The present disclosure contemplates methods, systems and program products on any machine-readable media for accomplishing various operations. The embodiments of the present disclosure may be implemented using existing computer processors, or by a special purpose computer processor for an appropriate system, incorporated for this or another purpose, or by a hardwired system. Embodiments within the scope of the present disclosure include program products comprising machine-readable media for carrying or having machine-executable instructions or data structures stored thereon. Such machine-readable media can be any available media that can be accessed by a general purpose or special purpose computer or other machine with a processor. By way of example, such machine- readable media can comprise RAM, ROM, EPROM, EEPROM, or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code in the form of machine-executable instructions or data structures and which can be accessed by a general purpose or special purpose computer or other machine with a processor. Combinations of the above are also included within the scope of machine-readable media. Machine-executable instructions include, for example, instructions and data w hich cause a general purpose computer, special purpose computer, or special purpose processing machines to perform a certain function or group of functions.

[0152] The phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of ‘"including’' “comprising” “having” “containing” “involving” “characterized by” “characterized in that” and variations thereof

[0153] 25

[0154] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) herein, is meant to encompass the items listed thereafter, equivalents thereof, and additional items, as well as alternate implementations consisting of the items listed thereafter exclusively. In one implementation, the systems and methods described herein consist of one, each combination of more than one, or all of the described elements, acts, or components.

[0155] Any references to implementations or elements or acts of the systems and methods herein referred to in the singular can also embrace implementations including a plurality of these elements, and any references in plural to any implementation or element or act herein can also embrace implementations including only a single element. References in the singular or plural form are not intended to limit the presently disclosed systems or methods, their components, acts, or elements to single or plural configurations. References to any act or element being based on any information, act or element can include implementations where the act or element is based at least in part on any information, act, or element.

[0156] Any implementation disclosed herein can be combined with any other implementation or embodiment, and references to "an implementation,’" “some implementations,” “one implementation” or the like are not necessarily mutually exclusive and are intended to indicate that a particular feature, structure, or characteristic described in connection with the implementation can be included in at least one implementation or embodiment. Such terms as used herein are not necessarily all referring to the same implementation. Any implementation can be combined with any other implementation, inclusively or exclusively, in any manner consistent with the aspects and implementations disclosed herein.

[0157] Where technical features in the drawings, detailed description or any claim are followed by reference signs, the reference signs have been included to increase the intelligibility of the drawings, detailed description, and claims. Accordingly, neither the reference signs nor their absence have any limiting effect on the scope of any claim elements.

[0158] Systems and methods described herein may be embodied in other specific forms without departing from the characteristics thereof. References to “approximately,” “about” “substantially” or other terms of degree include variations of + / -10% from the given measurement, unit, or range unless explicitly indicated otherwise. Coupled elements can be electrically, mechanically, or physically coupled with one another directly or with intervening elements. Scope of the systems and methods described herein is thus indicated by the appended claims, rather than the foregoing description, and changes that come within the meaning and range of equivalency of the claims are embraced therein.

[0159] The term “coupled” and variations thereof includes the joining of two members directly or indirectly to one another. Such joining may be stationary (e.g., permanent or fixed)

[0160] 26

[0161] 4900-1232-7508 1 Atorney Docket No.: 121439-1417 (P211162US00) or moveable (e.g., removable or releasable). Such joining may be achieved with the two members coupled directly with or to each other, with the two members coupled with each other using a separate intervening member and any additional intermediate members coupled with one another, or with the two members coupled with each other using an interv ening member that is integrally formed as a single unitary body with one of the two members. If “coupled” or variations thereof are modified by an additional term (e.g., directly coupled), the generic definition of “coupled” provided above is modified by the plain language meaning of the additional term (e g., “directly coupled” means the joining of two members without any separate intervening member), resulting in a narrower definition than the generic definition of “coupled” provided above. Such coupling may be mechanical, electrical, or fluidic.

[0162] References to “or” can be construed as inclusive so that any terms described using “or” can indicate any of a single, more than one, and all of the described terms. A reference to “at least one of ‘A’ and ‘B’” can include only ‘A’, only ‘B’, as well as both ‘A’ and ‘B’. Such references used in conjunction with “comprising” or other open terminology7can include additional items.

[0163] Modifications of described elements and acts such as variations in sizes, dimensions, structures, shapes and proportions of the various elements, values of parameters, mounting arrangements, use of materials, colors, orientations can occur without materially departing from the teachings and advantages of the subject matter disclosed herein. For example, elements shown as integrally formed can be constructed of multiple parts or elements, the position of elements can be reversed or otherwise varied, and the nature or number of discrete elements or positions can be altered or varied. Other substitutions, modifications, changes and omissions can also be made in the design, operating conditions and arrangement of the disclosed elements and operations without departing from the scope of the present disclosure.

[0164] References herein to the positions of elements (e.g., “top,” “bottom,” “above,” “below ”) are merely used to describe the orientation of various elements in the FIGURES. The orientation of various elements may differ according to other exemplary embodiments, and that such variations are intended to be encompassed by the present disclosure.

[0165] 27

[0166] 4900-1232-7508 1

Claims

Atorney Docket No.: 121439-1417 (P211162US00)CLAIMSWhat is claimed is:

1. A user device comprising: one or more processors configured to: receive, via a transceiver from a base station over a wireless network, a first set of beams; generate output data relating to a second set of beams as a set of candidate beams for beamforming by executing, with measurement data of the first set of beams as input data, a first model that has been learned using training data; and transmit, via the transceiver to the base station, one or more signal relating to the output data.

2. The user device according to claim 1, wherein the second set of beams comprise one or more reference signals relating to one or more dow nlink transmission configuration indicator (TCI) states each of which is linked to a corresponding source reference signal.

3. The user device according to claim 2, wherein the one or more signals are transmitted using uplink control information (UCI) or medium access control control element (MAC-CE) to trigger transmission of the one or more reference signals by the base station.

4. The user device according to claim 1, wherein the one or more processors are configured to: detect one or more events among a plurality of events relating to performance of the first model; and in response to the detecting, transmit, to the base station, a notification of the one or more events.

5. The user device according to claim 4, wherein the plurality' of events comprise at least one of (1) an event indicating that a link quality measurement value of a predicted beam as a result of beam indication is lower than a predefined threshold, (2) an event indicating that a difference between that a hnk quality measurement value of a predicted beam as a result of beam indication and a link quality measurement value of another beam is greater than a predefined threshold, (3) an event indicating that a difference between a predicted reference signal received power (RSRP) of a predicted beam as a result of beam indication and a measured RSRP of the predicted beam is greater than a predefined threshold, (4) an event indicating that a model accuracy of the first284900-1232-7508 1Atorney Docket No.: 121439-1417 (P211162US00) model based on the measurement data of the first set of beams is smaller than a predefined percentage, or (5) an event indicating that a difference between a predicted RSRP of the first set of beams and a measured RSRP of the first set of beams is greater than a predefined threshold.

6. The user device according to claim 1, wherein the one or more signals indicate a request for transmission of a subset of reference signals which are mapped to transmission configuration indicator (TCI) states of the second set of beams; and the one or more processors are configured to receive, from the base station, the subset of reference signals and perform a performance monitoring of the first model using the subset of reference signals.

7. The user device according to claim 6, wherein the output data comprises predicted measurement data of the second set of beams, and in performing the performance monitoring of the first model, the one or more processors are configured to: compare measurement data of the subset of reference signals with the predicted measurement data corresponding to the subset of reference signals.

8. The user device according to claim 1, wherein the one or more processors are configured to: receive, via the transceiver from the base station, a subset of the second set of beams; and transmit, via the transceiver to the base station, a report relating to reference signal received power (RSRP) of the subset of the second set of beams.

9. The user device according to claim 8, wherein the report includes an RSRP difference between a predicted beam as a result of beam indication and the subset of the second set of beams.

10. The user device according to claim 1, wherein the one or more processors are configured to: receive, via the transceiver from the base station, a beam indication including one or more transmission configuration indicator (TCI) states which are linked to the second set of beams and are not activated TCI states.

11. A method comprising: receiving, by one or more processors of a user device via a transceiver from a base station over a wireless network, a first set of beams;294900-1232-7508 1Atorney Docket No.: 121439-1417 (P211162US00) generating, by the one or more processors, output data relating to a second set of beams as a set of candidate beams for beamforming by executing, with measurement data of the first set of beams as input data, a first model that has been learned using training data: and transmitting, by the one or more processors via the transceiver to the base station, one or more signal relating to the output data.

12. The method according to claim 11, wherein the second set of beams comprise one or more reference signals relating to one or more downlink transmission configuration indicator (TCI) states each of which is linked to a corresponding source reference signal.

13. The method according to claim 12, wherein the one or more signals are transmitted using uplink control information (UCI) or medium access control control element (MAC-CE) to trigger transmission of the one or more reference signals by the base station.

14. The method according to claim 11, further comprising: detecting one or more events among a plurality of events relating to performance of the first model: and in response to the detecting, transmitting, to the base station, a notification of the one or more events.

15. The method according to claim 14, wherein the plurality of events comprise at least one of (1) an event indicating that a link quality measurement value of a predicted beam as a result of beam indication is lower than a predefined threshold, (2) an event indicating that a difference between that a link quality measurement value of a predicted beam as a result of beam indication and a link quality' measurement value of another beam is greater than a predefined threshold, (3) an event indicating that a difference between a predicted reference signal received power (RSRP) of a predicted beam as a result of beam indication and a measured RSRP of the predicted beam is greater than a predefined threshold, (4) an event indicating that a model accuracy of the first model based on the measurement data of the first set of beams is smaller than a predefined percentage, or (5) an event indicating that a difference between a predicted RSRP of the first set of beams and a measured RSRP of the first set of beams is greater than a predefined threshold.

16. The method according to claim 11, wherein the one or more signals indicate a request for transmission of a subset of reference signals which are mapped to transmission configuration indicator (TCI) states of304900-1232-7508 1Atorney Docket No.: 121439-1417 (P211162US00) the second set of beams; and the method further comprises receiving, from the base station, the subset of reference signals and perform a performance monitoring of the first model using the subset of reference signals.

17. The method according to claim 16, wherein the output data comprises predicted measurement data of the second set of beams, and performing the performance monitoring of the first model comprises: comparing measurement data of the subset of reference signals with the predicted measurement data corresponding to the subset of reference signals.

18. The method according to claim 11, further comprising: receiving, via the transceiver from the base station, a subset of the second set of beams; and transmitting, via the transceiver to the base station, a report relating to reference signal received power (RSRP) of the subset of the second set of beams.

19. The method according to claim 18, wherein the report includes an RSRP difference between a predicted beam as a result of beam indication and the subset of the second set of beams.

20. The method according to claim 11, further comprising: receiving, via the transceiver from the base station, a beam indication including one or more transmission configuration indicator (TCI) states which are linked to the second set of beams and are not activated TCI states.314900-1232-7508 1

Images