Method and apparatus for determining probe size for ai / ml-based beam management in mobile communications

Description

1 / 23 METHOD AND APPARATUS FOR DETERMINING PROBE SIZE FOR AI / ML-BASED BEAM MANAGEMENT IN MOBILE COMMUNICATIONS Cross-reference to related request(s)

[0001] This application is part of a non-provisional application claiming the benefit of priority of U.S. Patent Application No. 63 / 502,132, filed May 15, 2023, the contents of which are incorporated herein by reference in their entirety. Field of invention

[0002] This disclosure relates generally to mobile communications and, more particularly, to the determination of probe beam size for beam management based on artificial intelligence (AI) / machine learning (ML) in mobile communications. Description of the state of the art

[0003] Unless otherwise indicated in this document, the approaches described in this section do not constitute prior art with respect to the claims listed below and are not admitted as prior art by inclusion in this section.

[0004] In wireless communications, such as mobile communications under the 3rd Generation Partnership Project (3GPP) standards, a user equipment (UE) and a base station (e.g., gNB) need to find the best beam to communicate with each other; however, the overhead of exhaustive beam scanning can be significantly increased as the number of available beams increases. Thus, beamforming is a technique that can increase downlink throughput (DL) and is therefore essential for millimeter wave (mmWave) technology in future wireless systems. Compared to the existing exhaustive beam scanning procedure, an AI / ML-based solution can provide a faster way to obtain Petition 870250090131, dated 03 / 10 / 2025, p. 15 / 55 2 / 23 information from the best beam. For example, AI / ML-based beam management can reduce the number and time required for Layer 1 reference signal received power measurements (L1-RSRP).

[0005] In mobile communications under 3GPP standards, the concept of “spatial beam prediction” refers to the inference of ideal communication beams using power measurements from probe beams. The number of probe beams is less than the number of communication beams. During operation with respect to spatial beam prediction, network 120 and / or UE 110 measures the received power of all beams in the probe beam codebook. Then, network 120 and / or UE 110 infers the ideal communication beams from the received reference signal power (RSRP) of the probe beam. Additionally, the concept of “temporal beam prediction” refers to the prediction of future optimal beam indices using beam measurements on probe beams from previous instants. The RSRP of one or more beams can be predicted with an entry from the RSRP history.In discussions on 3GPP, the set of beams being measured as AI / ML input (probing beams) is referred to as the "B-set" of beams. The set of beams being predicted as AI / ML output (usually communication beams) is referred to as the "A-set" of beams.

[0006] In general, the size of Set B controls the accuracy of beam prediction and the beam measurement overhead performance of AI / ML-based beam management. For example, in spatial beam prediction with measurement of 4, 8, or 16 Set B beams (which are probe beams) to predict the best beam(s) among 32 communication beams (i.e., Set A beams), the performance of measuring a Set B size equal to 16 for Petition 870250090131, dated 03 / 10 / 2025, p. 16 / 55 3 / 23 inputs to the AI / ML model tend to always be superior to those of a Set B size equal to 8. Similarly, the performance of measuring a Set B size equal to 8 tends to always be superior to that of a Set B size equal to 4. As can be seen, a larger Set B size tends to result in greater beam prediction accuracy (e.g., due to more input information to the AI / ML model), but with greater beam measurement overhead (e.g., due to more beams for the UE to measure). On the other hand, a smaller Set B size tends to result in lower beam prediction accuracy (e.g., due to less input information to the AI / ML model), but with less beam measurement overhead (e.g., due to fewer beams for the UE to measure). However, currently there is no mechanism for the UE to dynamically determine the size of Set B.Therefore, there is a need for a solution to determine the probe beam size for AI / ML-based beam management in mobile communications. Summary of the invention

[0007] The following summary is merely illustrative and is not intended to be limiting in any way. That is, the following summary is provided to introduce concepts, highlights, benefits, and advantages of the novel and non-obvious techniques described in this document. Selected implementations are described in more detail below in the detailed description. Thus, the following summary is not intended to identify essential features of the claimed subject matter, nor is it intended to be used to determine the scope of the claimed subject matter.

[0008] One objective of this disclosure is to propose solutions or schemes that address the issues mentioned above regarding the determination of probe beam size for AI / ML-based beam management in communications. Petition 870250090131, dated 03 / 10 / 2025, page 17 / 55 4 / 23 mobile. It is believed that implementing one or more of the schemes proposed here could prevent or otherwise alleviate the problems described herein.

[0009] In one aspect, a method may involve determining a UE throughput. The method may also involve adjusting the size of a set of reference signal (RS) features configured for the UE to measure as an input to an AI / ML model based on the UE throughput.

[0010] In another aspect, a method may involve determining a UE location. The method may also involve adjusting the size of a set of RS features configured for the UE to measure as an input to an AI / ML model based on the UE location.

[0011] In yet another aspect, a device deployable in a UE may include a transceiver configured to communicate wirelessly and a processor coupled to the transceiver. The processor may determine a throughput or location of a UE. The processor may also adjust the size of a set of RS features configured for the UE to measure as an input to an AI / ML model based on the throughput or location of the UE.

[0012] It is noteworthy that, although the description given here may be in the context of certain radio access technologies, networks and network topologies such as LongTerm Evolution (LTE), LTE-Advanced, LTE-Advanced Pro, 5a Generation (5G), New Radio (NR), Internet of Things (IoT) and Narrow Band Internet of Things (NB-IoT), Industrial Internet of Things (IIoT), and 6th Generation (6G), the proposed concepts, schemes and any variations / derivations thereof can be implemented in, for and by other types of radio access technologies, networks and network topologies. Thus, the scope of this disclosure is not limited to the examples presented here. Petition 870250090131, dated 03 / 10 / 2025, page 18 / 55 5 / 23 described. Brief description of the figures

[0013] The accompanying drawings are included to provide a better understanding of the disclosure and are incorporated into and form part of this disclosure. The drawings illustrate implementations of the disclosure and, together with the description, serve to explain the principles of the disclosure. It is appreciated that the drawings are not necessarily to scale, as some components may be shown out of proportion to the size in the actual implementation in order to clearly illustrate the concept of this disclosure.

[0014] FIG. 1 is a diagram that represents an example of a beam management procedure scenario according to implementations of the present disclosure.

[0015] FIG. 2 is a diagram that represents an example of a scenario under a proposed scheme according to this disclosure.

[0016] FIG. 3 is a diagram that represents an example of a scenario under a proposed scheme according to this disclosure.

[0017] FIG. 4 is a diagram that represents an example of a scenario under a proposed scheme according to this disclosure.

[0018] FIG. 5 is a diagram that represents an example of a scenario under a proposed scheme according to this disclosure.

[0019] FIG. 6 is a diagram that represents an example of a scenario under a proposed scheme according to this disclosure.

[0020] FIG. 7 is a diagram representing an example of a communication system containing an example of a communication device and an example of a network device according to an implementation of this disclosure. Petition 870250090131, dated 03 / 10 / 2025, p. 19 / 55 6 / 23

[0021] FIG. 8 is a diagram that represents an example of a process according to an implementation of the present disclosure.

[0022] FIG. 9 is a diagram that represents an example of a process according to an implementation of the present disclosure. Detailed description of preferred implementations

[0023] Detailed embodiments and implementations of the claimed materials are disclosed herein. However, it should be understood that the embodiments and implementations disclosed are merely illustrative of the claimed materials, which can be carried out in various ways. This disclosure can, however, be carried out in many different ways and should not be interpreted as limited to the exemplary embodiments and implementations set forth herein. On the contrary, these exemplary embodiments and implementations are provided so that the description of this disclosure is complete and comprehensive and fully conveys the scope of this disclosure to those skilled in the art. In the following description, details of well-known features and techniques may be omitted to avoid unnecessarily obscuring the embodiments and implementations presented. Overview

[0024] Implementations according to this disclosure refer to various techniques, methods, schemes, and / or solutions related to probe beam size determination for AI / ML-based beam management in mobile communications. According to this disclosure, several possible solutions can be implemented separately or in combination. That is, although these possible solutions may be described separately below, two or more of these possible solutions may be implemented in one combination or another. Petition 870250090131, dated 03 / 10 / 2025, page 20 / 55 7 / 23

[0025] FIG. 1 illustrates an example of a 100 network environment in which various solutions and schemes according to this disclosure can be implemented. FIGS. 2 ~ FIG. 9 illustrate examples of implementation of various proposed schemes in the 100 network environment according to this disclosure. The following description of various proposed schemes is provided with reference to FIGS. 1 ~ FIG. 9.

[0026] With reference to FIG. 1, the network environment 100 may involve a UE 110, such as a mobile device or smartphone, in wireless communication with a wireless network 120 as part of a communication network. The wireless network 120 may be a public terrestrial mobile network (PLMN) including 5G / NR and LTE domains. The UE 110 may be in wireless communication or attempting to establish wireless communication with the wireless network 120 via a base station or network node 125 (e.g., an eNB, gNB, or transmit-receive point (TRP)). In the network environment 100, the UE 110 and the wireless network 120 via the network node 125 may implement various schemes related to enhancing probe beam size determination for AI / ML-based beam management in mobile communications, as described herein.It is noteworthy that, although the various proposed schemes may be described individually or separately below, in real-world implementations some or all of the proposed schemes may be used or otherwise implemented together. Naturally, each of the proposed schemes may be used or otherwise implemented individually or separately.

[0027] FIG. 2 illustrates an example of scenario 200 of a simulation of a cumulative distribution function of UE transfer rate, in which UEs are distributed in different locations. After the normalized user transfer rate is greater than 0.8, the performance of Petition 870250090131, dated 03 / 10 / 2025, page 21 / 55 Using four probe beams is almost the same as using 16 probe beams and close to exhaustive beam scanning. Thus, there is no need to use a larger number of probe beams when the UE throughput is high. Furthermore, a lower throughput usually indicates that a UE is on the edge of a cell. A throughput distribution analysis like the one shown in FIG. 2 allows determining the size of Set B (or the number of probe beams, where these beams are for the UE to measure as input to an AI / ML model) based on the throughput of a UE or the location of the UE.

[0028] FIG. 3 illustrates an example of scenario 300 under a proposed scheme according to this disclosure. Scenario 300 may refer to determining the size of Set B based on the throughput of an UE. With reference to FIG. 3. Network 120 and / or UE 110 can maintain monitoring of the current throughput (e.g., downlink throughput) of UE 110. Optionally, if UE 110 detects that its current throughput drops to a certain level, UE 110 can send a request to Network 120 for a Lifecycle Management (LCM) change from Set B to a new Set B. Once UE 110's current throughput drops to a certain level, Network 120 can signal UE 110 an LCM decision to change Set B. UE 110 or Network 120 can change its AI / ML model and / or reporting configuration and behavior according to the new Set B.For example, network 120 can change the radio resource control (RRC) settings according to the new Set B. Additionally, in the case of an AI / ML model on the network side, network 120 can change to another AI / ML model according to the new Set B. Furthermore, in the case of an AI / ML model on the network side, UE 110 can change its... Petition 870250090131, dated 03 / 10 / 2025, page 22 / 55 9 / 23 Measurement behavior and signal reporting to report a measurement of the new Set B. Alternatively, in the case of an AI / ML model on the UE side, UE 110 can switch to another AI / ML model and signal measurement behavior according to the new Set B.

[0029] FIG. 4 illustrates an example of scenario 400 under the proposed scheme with respect to determining the size of Set B based on the throughput of a UE. With reference to FIG. 4, normalized throughputs can be separated into three regions of high, medium, and low throughput. In the case where the throughput of UE 110 is in the high region, UE 110 can apply four beams from Set B. In the case where the throughput of UE 110 is in the medium region, UE 110 can apply sixteen beams from Set B. In the case where the throughput of UE 110 is in the low region, UE 110 can apply eight beams from Set B.

[0030] FIG. 5 illustrates an example of scenario 500 under a proposed scheme according to this disclosure. Scenario 500 may refer to determining the size of Set B based on the location of a UE. With reference to FIG. 5. Network 120 and / or UE 110 can maintain monitoring of UE 110's current throughput. Optionally, if UE 110 detects that its distance to Network 120 drops to a certain level, UE 110 can send a request to Network 120 for a change in the LCM of Set B. Once UE 110's current distance to Network 120 drops to a certain level, Network 120 can signal UE 110 an LCNM decision to change Set B. UE 110 or Network 120 can change its AI / ML model and / or reporting configuration and behavior according to the new Set B. For example, Network 120 can change RRC settings according to the new Set B. Furthermore, in the case of a Petition 870250090131, dated 03 / 10 / 2025, p. 23 / 55 10 / 23 Network-side AI / ML model, network 120 can switch to another AI / ML model according to the new Set B. Additionally, in the case of a network-side AI / ML model, UE 110 can change its reporting behavior to report a measurement from the new Set B. Alternatively, in the case of a UE-side AI / ML model, UE 110 can switch to another AI / ML model according to the new Set B.

[0031] FIG. 6 illustrates an example of scenario 600 under the proposed scheme with respect to determining the size of Set B based on the location of a UE. With reference to FIG. 6, the location of the UE in a server cell coverage area can be separated into three long, medium, and short distance regions. In the case where the UE 110 location is on the edge of the server cell (e.g., UE-network distance > 150 meters), UE 110 can apply sixteen Set B beams. In the case where the UE 110 location is in a medium distance region relative to the server cell (e.g., UE-network distance < 150 meters and > 80 meters), UE 110 can apply eight Set B beams. In the case where the UE 110 location is in a central region of the server cell (e.g., UE-network distance < 80 meters), UE 110 can apply four Set B beams.

[0032] In view of the above, certain aspects of the proposed schemes with respect to a model on the EU side can be summarized below.

[0033] In one aspect, a procedure for determining Set B (e.g., a set of reference signal (RS) features configured for a UE to measure as an input to an AI / ML model) can be based on the UE's throughput. The UE's throughput can be separated into different throughput regions, and respective (different) Set Bs can be applied to each throughput region. Either each or both Petition 870250090131, dated 03 / 10 / 2025, page 24 / 55 11 / 23 The network and / or the UE can monitor the UE's current throughput. If the UE detects that its current throughput drops to a certain level, the UE can send a request to the network for a Set B change. Once the UE's current throughput drops to a certain level, the network can initiate an LCM decision to change Set B to a new Set B. The UE or the network can change its AI / ML model and / or reporting configuration and behavior according to the new Set B.

[0034] In another aspect, a procedure for determining Set B (e.g., the set of RS resources configured for a UE to measure as an input to an AI / ML model) can be based on the UE's location. The UE's location can be separated into different distance regions, and respective (different) Set Bs can be applied to each distance region. Either or both the network and / or the UE can monitor the UE's current location. If the UE detects that its current distance to the network (e.g., server cell) falls to a certain level, the UE can send a request to the network for a Set B change. Once the UE's current distance to the network falls to a certain level, the network can signal the UE an LCM decision to change Set B to a new Set B. The UE or the network can then change its AI / ML model and / or configuration and reporting behavior according to the new Set B. Illustrative implementations

[0035] FIG. 7 illustrates an example of a 700 communication system containing at least one example of a 710 device and one example of a 720 device according to an implementation of the present disclosure. Each of the 710 and 720 devices can perform various functions to implement schemes, techniques, processes, and methods described in this document related to determining the size of Set B for management of Petition 870250090131, dated 03 / 10 / 2025, page 25 / 55 12 / 23 AI / ML-based beam in mobile communications, including the various schemes described above in relation to various proposed designs, concepts, schemes, systems and methods, including the 100 network environment, as well as processes described below.

[0036] Each of the 710 and 720 devices can be part of an electronic device, which can be a network device or an EU (e.g., EU 110), such as a portable or mobile device, a wearable device, a vehicle device or a vehicle, a wireless communication device, or a computing device. For example, each of the 710 and 720 devices can be implemented in a smartphone, a smartwatch, a personal digital assistant, an electronic control unit (ECU) in a vehicle, a digital camera, or a computing device such as a tablet, a laptop, or a notebook. Each of the 710 and 720 devices can also be part of a machine-type device, which can be an IoT device, such as a stationary or fixed device, a household appliance, a roadside unit (RSU), a wired communication device, or a computing device.For example, each of the 710 and 720 appliances can be deployed in a smart thermostat, a smart refrigerator, a smart lock, a wireless speaker, or a home control center. When deployed in or as a network appliance, the 710 and / or 720 appliances can be deployed in an eNodeB on an LTE, LTE-Advanced, or LTE-Advanced Pro network, or in a gNB or TRP on a 5G network, an NR network, or an IoT network.

[0037] In some implementations, each of the 710 and 720 devices may be implemented in the form of one or more integrated circuits (ICs) such as, for example and without limitation, one or more single-core processors, one or more multi-core processors, one or more complex instruction set processors (CISCs), or one or more Petition 870250090131, dated 03 / 10 / 2025, page 26 / 55 13 / 23 Reduced Instruction Set Processors (RISCs). In the various schemes described above, each of the 710 and 720 devices can be implemented either as a network device or as a UE. Each of the 710 and 720 devices may include at least some of those components shown in FIG. 7, such as a 712 processor and a 722 processor, respectively, for example. Each of the 710 and 720 devices may also include one or more other components not relevant to the proposed scheme of this disclosure (for example, internal power supply, display device and / or user interface device) and, therefore, such components of the 710 and 720 devices are not shown in FIG. 7 nor described below in the interest of simplicity and brevity.

[0038] In one aspect, each of the 712 and 722 processors may be implemented in the form of one or more single-core processors, one or more multi-core processors, or one or more CISC or RISC processors. That is, although a singular term “a processor” is used in this document to refer to the 712 and 722 processors, each of the 712 and 722 processors may include multiple processors in some implementations and a single processor in other implementations, according to the present disclosure. In another aspect, each of the 712 and 722 processors may be implemented in the form of hardware (and optionally firmware) with electronic components including, for example and without limitation, one or more transistors, one or more diodes, one or more capacitors, one or more resistors, one or more inductors, one or more memristors, and / or one or more varactors that are configured and arranged to achieve specific purposes according to the present disclosure.In other words, in at least some implementations, each of the 712 and 722 processors is a purpose-built machine, specifically designed, organized, and configured for that purpose. Petition 870250090131, dated 03 / 10 / 2025, page 27 / 55 14 / 23 perform specific tasks, including those related to UE behavior to determine probe beam size for AI / ML-based beam management in mobile communications, according to various implementations of this disclosure.

[0039] In some implementations, the 710 device may also include a 716 transceiver coupled to the 712 processor. The 716 transceiver may be capable of transmitting and receiving data wirelessly. In some implementations, the 716 transceiver may be capable of communicating wirelessly with different types of wireless networks of different radio access technologies (RATs). In some implementations, the 716 transceiver may be equipped with a plurality of antenna ports (not shown), such as four antenna ports. That is, the 716 transceiver may be equipped with multiple transmit antennas and multiple receive antennas for multi-input multiple-output (MIMO) wireless communications. In some implementations, the 720 device may also include a 726 transceiver coupled to the 722 processor. The 726 transceiver may include a transceiver capable of transmitting and receiving data wirelessly.In some implementations, the 726 transceiver may be able to communicate wirelessly with different types of UEs / wireless networks from different RATs. In some implementations, the 726 transceiver may be equipped with a plurality of antenna ports (not shown), such as four antenna ports. That is, the 726 transceiver may be equipped with multiple transmit antennas and multiple receive antennas for MIMO wireless communications.

[0040] In some implementations, the 710 device may also include a 714 memory coupled to the 712 processor and capable of being accessed by the 712 processor and storing data therein. In some implementations, the 720 device may also include a 724 memory coupled to the 722 processor and capable of Petition 870250090131, dated 03 / 10 / 2025, p. 28 / 55 15 / 23 to be accessed by processor 722 and store data therein. Each of the 714 and 724 memories may include a type of random access memory (RAM), such as dynamic RAM (DRAM), static RAM (SRAM), thyristor RAM (T-RAM), and / or capacitor-free RAM (ZRAM). Alternatively or additionally, each of the 714 and 724 memories may include a type of read-only memory (ROM), such as mask ROM, programmable ROM (PROM), erasable programmable ROM (EPROM), and / or electrically erasable programmable ROM (EEPROM). Alternatively or additionally, each of the 714 and 724 memories may include a type of non-volatile random access memory (NVRAM), such as flash memory, solid-state memory, ferroelectric RAM (FeRAM), magnetoresistive RAM (MRAM), and / or phase-change memory.

[0041] Each of the 710 and 720 devices can be a communication entity capable of communicating using various schemes proposed in accordance with this disclosure. For illustrative purposes and without limitation, a description of the capabilities of the 710 device, as a UE (e.g., UE 110), and of the 720 device, as a network node (e.g., network node 125) of a network (e.g., wireless network 120 as a 5G / NR mobile network), is provided below in the context of exemplary processes 800 and 900. Illustrative processes

[0042] FIG. 8 illustrates an example of an 800 process according to an implementation of this disclosure. The 800 process may represent an aspect of the implementation of several proposed designs, concepts, schemes, systems, and methods described above. More specifically, the 800 process may represent an aspect of the proposed concepts and schemes related to determining probe beam size for AI / ML-based beam management in mobile communications according to this disclosure. The 800 process may include one or more operations, actions, or Petition 870250090131, dated 03 / 10 / 2025, p. 29 / 55 16 / 23 functions as illustrated by one or more of blocks 810 and 820. Although illustrated as distinct blocks, several blocks of process 800 can be divided into additional blocks, combined into fewer blocks, or eliminated, depending on the desired implementation. Furthermore, the blocks / sub-blocks of process 800 can be executed in the order shown in FIG. 8 or, alternatively, in a different order. Additionally, one or more of the blocks / sub-blocks of process 800 can be executed repeatedly or iteratively. Process 800 can be implemented by or on devices 710 and 720, as well as any variations thereof. For illustrative purposes only and without limiting the scope, process 800 is described below in the context of device 710 as a UE (e.g., UE 110) and device 720 as a communication entity, such as a network node or base station (e.g., network node 125) of a network (e.g., wireless network 120). Process 800 can start in block 810.

[0043] In 810, process 800 may involve processor 712 of device 710 and / or processor 722 of device 720 determining a transfer rate of one UE (e.g., device 710 as UE 110). Process 800 may proceed from 810 to 820.

[0044] In 820, process 800 may involve processor 712 or processor 722 adjusting the size of a set of RS features configured for the UE to measure as an input to an AI / ML model (Set B), based on the UE's throughput.

[0045] In some implementations, in the determination, process 800 may involve processor 712 performing certain operations. For example, process 800 may involve processor 712 monitoring the current UE transfer rate. Additionally, process 800 may involve processor 712 detecting that the current transfer rate drops to a certain level. Petition 870250090131, dated 03 / 10 / 2025, page 30 / 55 17 / 23 predefined. Furthermore, process 800 may involve processor 712 sending a request to a network for an LCM change of Set B size in response to detection. In some implementations, in the tuning, process 800 may involve processor 712 performing certain operations. For example, process 800 may involve processor 712 receiving, from the network (e.g., wireless network 120 via device 720 as network node 125), a signal of an LCM decision to change Set B to a new Set B. Furthermore, process 800 may involve processor 712 altering, according to the new Set B, at least one of the following: (a) the AI / ML model and signal measurement behavior according to the new Set B, and (b) a reporting behavior to report a measurement of the new Set B.

[0046] In some implementations, in the determination phase, process 800 may involve processor 722 performing certain operations. For example, process 800 may involve processor 722 monitoring the current UE throughput. Additionally, process 800 may involve processor 722 detecting that the current throughput drops to a predefined level. Furthermore, process 800 may involve processor 722 signaling to the UE an LCM decision to change Set B to a new Set B in response to the detection. In some implementations, in the tuning phase, process 800 may involve processor 722 performing certain operations. For example, process 800 may involve processor 722 changing, according to the new Set B, at least one of the following: (a) the AI / ML model according to the new Set B, and (b) an RRC configuration according to the new Set B.

[0047] In some implementations, the size of the RS feature set may include the size of a set of Petition 870250090131, dated 03 / 10 / 2025, p. 31 / 55 18 / 23 beams that the UE measures for inference by the AI / ML model.

[0048] FIG. 9 illustrates an example of process 900 according to an implementation of the present disclosure. Process 900 may represent an aspect of the implementation of several proposed designs, concepts, schemes, systems, and methods described above. More specifically, process 900 may represent an aspect of the proposed concepts and schemes related to determining probe beam size for AI / ML-based beam management in mobile communications according to the present disclosure. Process 900 may include one or more operations, actions, or functions as illustrated by one or more of blocks 910 and 920. Although illustrated as distinct blocks, several blocks of process 900 may be divided into additional blocks, combined into fewer blocks, or eliminated, depending on the desired implementation. Furthermore, the blocks / sub-blocks of process 900 may be executed in the order shown in FIG. 9 or, alternatively, in a different order.Furthermore, one or more of the blocks / sub-blocks of process 900 can be executed repeatedly or iteratively. Process 900 can be implemented by or on devices 710 and 720, as well as any variations thereof. For illustrative purposes only and without limiting the scope, process 900 is described below in the context of device 710 as a UE (e.g., UE 110) and device 720 as a communication entity, such as a network node or base station (e.g., network node 125) of a network (e.g., wireless network 120). Process 900 can start on block 910.

[0049] In 910, process 900 may involve processor 712 of device 710 and / or processor 722 of device 720 determining a UE location (e.g., device 710 as UE 110). Process 900 may proceed from 910 to 920. Petition 870250090131, dated 03 / 10 / 2025, page 32 / 55 19 / 23

[0050] In 920, process 900 may involve processor 712 or processor 722 adjusting the size of a set of RS features configured for the UE to measure as an input to an AI / ML model (Set B), based on the UE's location.

[0051] In some implementations, during determination, process 900 may involve processor 712 performing certain operations. For example, process 900 may involve processor 712 monitoring the current distance between the UE and a server cell (e.g., appliance 720 as network node 125) of a network (e.g., wireless network 120). Additionally, process 900 may involve processor 712 detecting that the current distance drops to a predefined level. Furthermore, process 900 may involve processor 712 sending a request to the network for an LCM change of Set B size in response to the detection. In some implementations, during tuning, process 900 may involve processor 712 performing certain operations. For example, process 900 may involve processor 712 receiving, from the network, a signal of an LCM decision to change Set B to a new Set B.Furthermore, process 900 may involve processor 712 altering, in accordance with the new Set B, at least one of the following: (a) the AI / ML model and signal measurement behavior in accordance with the new Set B, and (b) a reporting behavior to report a measurement of the new Set B.

[0052] In some implementations, in the determination, process 900 may involve processor 722 performing certain operations. For example, process 900 may involve processor 722 monitoring a current distance between the UE and a server cell on the network. Additionally, process 900 may involve processor 722 detecting that the current transfer rate drops to a predefined level. Furthermore, the Petition 870250090131, dated 03 / 10 / 2025, page 33 / 55 20 / 23 Process 900 may involve processor 722 signaling to the UE an LCM decision to change Set B to a new Set B in response to detection. In some implementations, during tuning, process 900 may involve processor 722 performing certain operations. For example, process 900 may involve processor 722 changing, according to the new Set B, at least one of the following: (a) the AI / ML model according to the new Set B, and (b) an RRC configuration according to the new Set B.

[0053] In some implementations, the size of the RS feature set may include the size of a beam set that the UE measures for inference by the AI / ML model. Additional notes

[0054] The material described here sometimes illustrates different components contained within, or connected with, different other components. It should be understood that such represented architectures are merely examples, and that, in fact, many other architectures can be implemented that achieve the same functionality. In a conceptual sense, any arrangement of components to achieve the same functionality is effectively associated so that the desired functionality is achieved. Thus, any two components combined here to achieve a particular functionality can be seen as associated with each other so that the desired functionality is achieved, regardless of architectures or intermediate components.Similarly, any two components thus associated can also be seen as being operationally connected or operationally coupled to achieve the desired functionality, and any two components capable of being thus associated can also be seen as being operationally coupled to achieve the desired functionality. Specific examples of... Petition 870250090131, dated 03 / 10 / 2025, page 34 / 55 Operationally coupleable components include, but are not limited to, physically connectable and / or physically interactive components and / or wirelessly interacting and / or wirelessly interactable components and / or logically interactive and / or logically interactable components.

[0055] Furthermore, with respect to the use of substantially any plural and / or singular terms herein, those skilled in the art may translate from plural to singular and / or from singular to plural as appropriate to the context and / or application. The various singular / plural permutations may be expressly set forth in this document for the sake of clarity.

[0056] Furthermore, it will be understood by those skilled in the art that, in general, the terms used in this document, and especially in the appended claims, for example, in the bodies of the appended claims, are generally intended as open terms, for example, the term “including” should be interpreted as “including, but not limited to,” the term “possessing” should be interpreted as “possessing at least,” the term “comprises” should be interpreted as “comprises, but is not limited to,” etc. It will further be understood by those skilled in the art that, if a specific number of an introduced claim recitation is intended, such intention will be explicitly stated in the claim, and, in the absence of such recitation, no such intention is present. For example, as an aid to understanding, the appended claims may contain the use of the introductory phrases “at least one” and “one or more” to introduce claim recitations.However, the use of such phrases should not be interpreted as implying that the introduction of a claim recitation by the indefinite articles "a" or "an" limits any particular claim containing such introduced recitation to implementations containing only one such recitation. Petition 870250090131, dated 03 / 10 / 2025, p. 35 / 55 22 / 23 recitation, even when the same claim includes the introductory phrases “one or more” or “at least one” and indefinite articles such as “a” or “an”, for example, “a” and / or “an” should be interpreted as meaning “at least one” or “one or more”; the same applies to the use of definite articles used to introduce recitations of a claim. Furthermore, even if a specific number of an introduced recitation of a claim is explicitly stated, those skilled in the art will recognize that such a recitation should be interpreted as meaning at least the number recited, for example, the mere recitation of “two recitations”, without other modifiers, means at least two recitations, or two or more recitations. Moreover, in cases where a convention analogous to “at least one of A, B, and C, etc.” is used, the recitation should be interpreted as meaning at least the number recited.In general, when a convention analogous to "at least one of A, B, or C, etc." is used, it is intended that someone skilled in the art would understand the convention; for example, "a system possessing at least one of A, B, and C" would include, but not be limited to, systems that have only A, only B, only C, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.It will further be understood by those skilled in the art that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood as contemplating the possibilities of including one of the terms, any of the terms, or both terms. For example, the phrase “A or B” should be understood as... Petition 870250090131, dated 03 / 10 / 2025, p. 36 / 55 23 / 23 including the possibilities of A or B or "A and B."

[0057] From the foregoing, it will be appreciated that various implementations of the present disclosure have been described in this document for illustrative purposes, and that various modifications may be made without departing from the scope and spirit of the present disclosure. Thus, the various implementations disclosed herein are not intended to be limiting, the true scope and spirit being indicated by the following claims. Petition 870250090131, dated 03 / 10 / 2025, p. 37 / 55

Claims

1 / 5 CLAIMS 1. A method characterized in that it comprises: determining a throughput of a user equipment (UE); and adjusting the size of a set of reference signal features (RS) configured for the UE to measure as an input to an artificial intelligence (AI) / machine learning (ML) model (Set B), based on the UE throughput.

2. Method, according to claim 1, characterized in that the determination comprises the UE performing operations comprising: monitoring a current UE throughput; detecting that the current throughput falls within a predefined level; and sending a request to a network for a Lifecycle Management Change (LCM) of Set B size in response to the detection.

3. Method, according to claim 2, characterized in that the adjustment comprises the UE performing operations comprising: receiving, from the network, a signal of an LCM decision to change Set B to a new Set B; and changing, according to the new Set B, at least one of: the AI / ML model and the signal measurement behavior according to the new Set B, and a reporting behavior to report a measurement of the new Set B.

4. Method, according to claim 1, characterized in that the determination comprises a network performing operations comprising: monitoring a current UE throughput; detecting that the current throughput falls within a predefined level; and signaling to the UE a lifecycle management (LCM) decision to change Set B to a new Set B in response to the detection.

5. Method according to claim 4, characterized in that the adjustment comprises the network performing operations comprising: altering, according to the new Set B, at least one of: the AI / ML model according to the new Set B, and a radio resource control (RRC) configuration according to the new Set B.

6. Method, according to claim 1, characterized in that the size of the RS feature set comprises a size of a set of beams that the UE measures for inference by the AI / ML model.

7. A method characterized by comprising: determining a location of a user device (UD); and adjusting the size of a set of reference signal features (RS) configured for the UD to measure as an input to an artificial intelligence (AI) / machine learning (ML) model (Set B), based on the location of the UD.

8. Method, according to claim 7, characterized in that the determination comprises the UE performing operations comprising: monitoring a current distance between the UE and a server cell of a network; detecting that the current distance falls to a predefined level; and sending a request to the network for a change in the size of Set B in response to the detection.

9. Method, according to claim 8, characterized in that the adjustment comprises the UE performing operations comprising: receiving, from the network, a signal of an LCM decision to change Set B to a new Set B; and changing, according to the new Set B, at least one of: the AI / ML model and the signal measurement behavior according to the new Set B, and a reporting behavior to report a measurement of the new Set B.

10. Method, according to claim 7, characterized in that the determination comprises a network performing operations comprising: monitoring a current distance between the UE and a server cell of the network; detecting that the current distance falls within a predefined level; and signaling to the UE a lifecycle management (LCM) decision to change Set B to a new Set B in response to the detection.

11. Method, according to claim 10, characterized in that the adjustment comprises the network performing operations comprising: altering, according to the new Set B, at least one of: the AI / ML model according to the new Set B, and a radio resource control (RRC) configuration according to the new Set B.

12. Method, according to claim 7, characterized in that the size of the feature set of RS Petition 870250090131, dated 03 / 10 / 2025, page 40 / 55 4 / 5 comprises a size of a set of beams that the UE measures for inference by the AI / ML model.

13. Device characterized in that it comprises: a transceiver configured to communicate wirelessly; and a processor coupled to the transceiver and configured to perform operations comprising: determining a transfer rate or location of a user device (UD); and adjusting the size of a set of reference signal (RS) features configured for the UD to measure as an input to an artificial intelligence (AI) / machine learning (ML) model (Set B), based on the transfer rate or location of the UD.

14. Device according to claim 13, characterized in that, if the device is implemented in the UE, the determination comprises: monitoring a current transfer rate of the UE or a current distance between the UE and a server cell of a network; detecting that the current transfer rate or the current distance falls within a predefined level; and sending a request to the network for a Lifecycle Management Change (LCM) of Set B size in response to the detection.

15. Apparatus, according to claim 14, characterized in that the adjustment comprises: receiving, from the network, a signal of an LCM decision to change Set B to a new Set B; and changing, according to the new Set B, at least one of: the AI / ML model and the signal measurement behavior according to the new Set B, and a reporting behavior to report a measurement of the new Set B. Petition 870250090131, dated 10 / 03 / 2025, p. 41 / 55 5 / 5 16. Device according to claim 13, characterized in that, if the device is implemented in a network, the determination comprises: monitoring a current UE transfer rate or a current distance between the UE and a network server cell; detecting that the current transfer rate or the current distance falls within a predefined level; and signaling to the UE a lifecycle management (LCM) decision to change Set B to a new Set B in response to the detection.

17. Apparatus according to claim 16, characterized in that the adjustment comprises the network performing operations comprising: altering, in accordance with the new Set B, at least one of: the AI / ML model in accordance with the new Set B, and a radio resource control (RRC) setting in accordance with the new Set B.

18. Apparatus, according to claim 13, characterized in that the size of the RS feature set comprises a size of a beam set that the UE measures for inference by the AI / ML model. Petition 870250090131, dated 03 / 10 / 2025, pp. 42 / 55

Images