User equipment applicability reporting in artificial intelligence / machine learning-based beam management
Patent Information
- Application Number
- PCT/CN2025/085331
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-03-27
- Publication Date
- 2026-10-01
Smart Images

Figure CN2025085331_01102026_PF_FP_ABST
Abstract
Description
USER EQUIPMENT APPLICABILITY REPORTING IN ARTIFICIAL INTELLIGENCE / MACHINE LEARNING-BASED BEAM MANAGEMENTFIELD
[0001] This disclosure relates to wireless communication networks including techniques for using artificial intelligence (AI) or machine learning (ML) to improve beamforming in wireless networks.BACKGROUND
[0002] As the number of mobile devices within wireless networks, and the demand for mobile data traffic, continue to increase, changes are made to system requirements and architectures to better address current and anticipated demands. For example, some wireless communication networks may be developed to implement fifth generation (5G) or new radio (NR) technology, sixth generation (6G) technology, and so on. An aspect of such technology includes the configuring UEs by a network to perform AI / ML-based beamforming based on individual UE capabilities, current operating conditions, and so on.BRIEF DESCRIPTION OF THE DRAWINGS
[0003] The present disclosure will be readily understood and enabled by the detailed description and accompanying figures of the drawings. Like reference numerals may designate like features and structural elements. Figures and corresponding descriptions are provided as non-limiting examples of aspects, implementations, etc., of the present disclosure, and references to "an" or “one” aspect, implementation, etc., may not necessarily refer to the same aspect, implementation, etc., and may mean at least one, one or more, etc.
[0004] FIG. 1 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0005] FIG. 2 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0006] FIG. 3 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0007] FIG. 3A illustrates an example configuration for an RRCReconfiguration message, in accordance with various aspects described herein.
[0008] FIG. 4 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0009] FIG. 4A illustrates an example configuration for an RRCReconfiguration message, in accordance with various aspects described herein.
[0010] FIG. 5 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0011] FIG. 5A illustrates an example configuration for an RRCReconfiguration message, in accordance with various aspects described herein.
[0012] FIG. 6 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0013] FIG. 6A illustrates an example configuration for an RRCReconfiguration message, in accordance with various aspects described herein.
[0014] FIG. 7 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0015] FIG. 7A illustrates an example configuration for an RRCReconfiguration message, in accordance with various aspects described herein.
[0016] FIG. 8 is a message flow diagram illustrating an example applicability reporting configuration process for AI / ML-based beamforming, in accordance with various aspects described herein.
[0017] FIG. 9A illustrates an example configuration for an RRCReconfiguration message, in accordance with various aspects described herein.
[0018] FIG. 9B illustrates an example configuration for an RRCReconfiguration message, in accordance with various aspects described herein.
[0019] FIG. 10 is a diagram of an example of wireless network according to one or more implementations described herein.
[0020] FIG. 11 is a diagram of an example of components of a device according to one or more implementations described herein.DETAILED DESCRIPTION
[0021] The following detailed description refers to the accompanying drawings. Like reference numbers in different drawings may identify the same or similar features, elements, operations, etc. Additionally, the present disclosure is not limited to the following description as other implementations may be utilized, and structural or logical changes made, without departing from the scope of the present disclosure.UE AI / ML-based Beamforming Applicability Reporting Overview
[0022] One category of AI / ML-based beamforming employs an AI / ML model to infer a set of preferred base station downlink transmit beams based on measurement of a set of input beams. The set of preferred beams output by the model is denoted set A and the set of input beams is denoted set B. For example, a stationary user equipment (UE) may be able to provide the network with a set of preferred narrow downlink transmit beams (e.g., channel state information (CSI) –reference signal (RS) beams) based on measuring fewer broad beams (e.g., synchronization signal block (SSB) beams) , reducing the measurement overhead that would be otherwise necessary for beamforming.
[0023] To configure a UE to perform AI / ML model-based beamforming, the network provides inference-related parameters describing set A and set B for a particular AI / ML model to the UE. This inference configuration may be provided in the form of a report configuration message that includes information about the sets A and B as well as other information used for AI / ML model-based beamforming, such as an associated ID that may identify information about particular set of training data that was used to generate the AI / ML model.
[0024] A report configuration message configuring AI / ML-based beamforming may be provided to a UE by way of a radio resource control (RRC) Reconfiguration (RRCReconfiguration) message. The RRCReconfiguration message includes a measurement configuration component (e.g., CSI-MeasConfig information element IE) ) that may be used to configure measurement of reference signals (e.g., CSIResourceConfig IE) and configure the reporting of the measurements (e.g., CSI-ReportConfig IE) to the network by the UE. Once the UE has configured the measurements and reporting called for in the RRCReconfiguration message, the UE responds with an RRCReconfigurationComplete message that confirms the successful configuration.
[0025] However, in many instances a UE may not be able to commence inference with an AI / ML model corresponding to a configuration in an RRCReconfiguration message immediately upon transmitting the RRCReconfigurationComplete message. The UE may need time to install or train the model prior to being able to apply the model for inference. Further, for many different reasons, the UE may be able or unable to use certain configured models at certain times. For example, the UE may switch to a serving cell that does not provide appropriate reference signals for a first configured AI / ML model but does provide appropriate reference signals for a second configured AI / ML model, and so on. For this reason, as applicability status of the AI / ML models changes after the UE transmits the RRCReconfigurationComplete message, the UE may transmit applicability-related messages to the network. The applicability-related messages indicate which of the configured AI / ML models is currently applicable by the UE. The applicability-related messages may include an indication of applicable and non-applicable CSI-ReportConfigs as identified by their CSI-ReportConfigID.
[0026] Thus, the RRCReconfigurationComplete message may be used as an “initial applicability message” that, in addition to confirming configuration of AI / ML models based on the RRCReconfiguration message, reports which of the configured AI / ML models is immediately applicable by the UE. Subsequent “applicability change report” messages may be transmitted by the UE to indicate a change in applicability status of an AI / ML model after the UE has transmitted the RRCReconfigurationComplete message.
[0027] One type of applicability change report message may be a UE assistance information (UAI) message. UAI is mechanism that allows a UE to provide information to the network without having to wait for the network to request the information. In the RRC framework, the network must instruct the UE to associate different configured parameters that may have dynamic values (e.g., power preferences, device bandwidth, and so on) with UAI. This causes the UE to continuously evaluate these associated or “monitored” parameters for changes and report changes to the network by way of a UAI message. The network uses an “other configuration” component of the measurement configuration message (e.g., otherConfig IE in an RRCReconfiguration message) to indicate which parameters should be associated with UAI for UE-initiated reporting. The other configuration component may be considered as parallel to the measurement configuration component in the report configuration message (e.g., note that the CSI-MeasConfig IE is parallel to the OtherConfig IE in the RRCReconfiguration message) .
[0028] FIG. 1 is a message flow diagram outlining an example applicability reporting configuration process for AI / ML-based beamforming. At 105, the network determines to initiate AI / ML-based beamforming with a UE. The network (by way of a serving cell) transmits a capability enquiry 106 (e.g., a UECapabiltyEnquiry message) to the UE requesting that the UE provide information regarding the UE’s AI / ML-based beamforming functionalities. The UE transmits capability information 108 (e.g., a UECapabilityInformation message) to the network informing the network about particular AI / ML-based beamforming functionalities that are supported by the UE.
[0029] When the UE supports AI / ML-based beamforming, based on the UE’s reported functionalities, the network transmits a report configuration message 110 that includes AI / ML report configuration information related to one or more AI / ML models. In response the UE may provide an initial applicability report communicating which AI / ML models are currently applicable by the UE. As will be described in more detail below, there are several options for how the report configuration message 110 may identify AI / ML models or inference-related parameters for which the UE should report applicability.
[0030] In general, there are two options for the report configuration message 110. In a first option, referred to herein as option A, the report configuration message includes a list of full inference configurations. A full inference configuration may be a CSI-ReportConfig that includes configurations for all inference-related parameters needed to instantiate the related AI / ML model in the UE. In a second option, referred to herein as option B, the report configuration includes a list of inference-related parameters (e.g., sets A and B corresponding to certain beams) without providing a full set of parameters needed to instantiate the related AI / ML model in the UE.
[0031] There are trade-offs between option A and option B. For example, with option A, the UE is able to immediately begin inference with applicable AI / ML models after transmitting the initial applicability report 140, while in option B, the UE will need subsequent configuration of applicable AI / ML models. However, in option B, the signaling overhead for the report configuration message 110 is reduced, especially in the case where there are several possible AI / ML models that the UE may be able to apply, depending on its current operating condition.
[0032] At 135, the UE identifies full inference configurations (option A) or inference-related parameters (option B) indicated in the report configuration message 110 for being “monitored” (continuously evaluated) for the purposes of an applicability change report. The full inference configurations and inference-related parameters that are selected at 135for continued applicability reporting are referred to herein as monitored full inference configurations and monitored inference-related parameters. This operation may include, for example, associating the identified parameters with UAI as will be described in more detail below.
[0033] The UE transmits an initial applicability report 140 to the network indicating which of the full inference configurations (option A) or inference-related parameters (option B) are immediately applicable by the UE. In some examples described herein, the initial applicability report is an RRCReconfigurationComplete message. In other examples described herein, the initial applicability report is a UAI message.
[0034] When option B is in effect, the network may provide full inference configurations 150 for AI / ML models related to inference-related parameters indicated as applicable in the initial applicability report. The network may need to send an inference activation message 151 (e.g., including downlink control information (DCI) or media access control (MAC) control element (CE) ) to cause the UE to activate an AI / ML model indicated as applicable by the UE. At 155, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting.
[0035] At 158 the UE monitors the monitored full inference configurations or monitored inference-related parameters that were designated for monitoring at 135. When a change in applicability status of any of these the full inference configurations or inference-related parameters is detected, the UE transmits an applicability change report 160 that reports the change in applicability status.Applicability Change Report in Option A Report Configuration
[0036] In option A report configuration, when UAI is used to provide the applicability change report, the UE needs to associate selected full inference configurations with UAI. Recall that the RRC framework requires that the network use the other configuration component of the report configuration message (e.g., otherConfig IE) to cause the UE to associate parameters with UAI. Further recall that full inference configurations may be provided in option A by way of CSI-ReportConfig IEs that include inference-related parameters. CSI-ReportConfig IEs are in the measurement configuration component of the report configuration message and not in the other configuration component of the report configuration, raising an issue as to how the UE may associate full inference configurations (e.g., CSI-ReportConfigIDs) with UAI.
[0037] It is noted that in FIGs. 2-9 operation and message reference characters will be maintained between figures to indicate operations and messages whose function or content do not change between figures.
[0038] FIG. 2 is a message flow diagram outlining an example applicability change reporting process in which full inference configurations are provided in a report configuration message 210, which may be an RRCReconfiguration message. At 215, the UE implicitly (e.g., without configuration by the network) associates certain CSI-ReportConfigIDs (which identify respective CSI-ReportConfigs) with UAI so that the UE monitors these monitored CSI-ReportConfigs for the purposes of applicability reporting. In a first option, the UE implicitly associates any CSI-ReportConfigs received in message 210 that include full inference parameters (e.g., information regarding sets A / B and so) with UAI. In another option, the CSI-ReportConfig IE is adapted to include an indication indicating whether or not the CSI-ReportConfig is to be associated with UAI for applicability change reporting.
[0039] The UE transmits an initial applicability report 220, which may be an RRCReconfigurationComplete message that lists an applicability status for the full inference CSI-ReportConfigIDs in the report configuration message 210. It is noted that at 225 the UE retains non-applicable full inference configurations in case they may become applicable later. The UE also suspends the inference operation for any newly non-applicable full inference configurations.
[0040] When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of periodic, the UE may commence inference with the AI / ML model after transmitting the initial applicability report. When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 230 (e.g., including downlink control information (DCI) or media access control (MAC) control element (CE) ) to cause the UE to activate an AI / ML model indicated as applicable by the UE. At 240, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting.
[0041] At 250 the UE continuously evaluates the full inference configurations that were designated for monitoring by association with UAI at 215. When a change in applicability status of any of these the full inference configurations is detected, the UE transmits an applicability change report 260 that reports the change in applicability status. This may include UAI that reports either applicable or non-applicable status for each CSI-ReportConfigID in the set of monitored CSI-ReportConfigIDs identified at 215.
[0042] When a non-applicable AI / ML model becomes applicable, this change is reported in message 260. When the newly applicable model is associated with a CSI-ReportConfig having a report configuration type of periodic, the UE may commence inference with the newly applicable AI / ML model after transmitting the initial applicability report. When a newly applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 261 (e.g., including DCI or MAC CE to cause the UE to activate an AI / ML model indicated as newly applicable by the UE. In some examples, at 263 the UE waits for the network to send an updated full inference configuration for the newly applicable full inference configuration. At 270, the UE begins inference using the newly applicable AI / ML model as well as any still applicable AI / ML models and provides results of the inference using the configured reporting.
[0043] FIGs. 3 and 3A illustrate a second option for configuration applicability change reporting when option A report configuration is used. In this option, the report configuration message (e.g., RRCReconfiguration message) is modified as shown in FIG. 3A. In particular, the other component of the report configuration message (e.g., otherConfig IE) is used to provide a list of M CSI-ReportConfigIDs that are selected from N CSI-ReportConfigs (each having an associated CSI-ReportConfigID) configured by the measurement component (e.g., CSI-MeasConfig IE) of the report configuration message. The M indicated CSI-ReportConfigIDs are to be associated with UAI for applicability change reporting.
[0044] Turning now to FIG. 3, a message flow diagram is depicted that outlines an example applicability change reporting process in which full inference configurations are provided in a report configuration message 310, which may be an RRCReconfiguration message as illustrated in FIG. 3A. For example, the report configuration message 310 may include an other configuration component (e.g., otherConfig IE) parallel to a measurement configuration component (e.g., CSI-MeasConfig IE) . The other configuration component may indicate one or more inference-related parameters configured in the measurement configuration component by indicating a corresponding CSI report configuration ID for each full inference configuration (e.g., CSI-ReportConfigIDs) . At 315, the UE selects the full inference configurations identified in the other configuration component for monitoring for applicability change reporting.
[0045] The UE transmits an initial applicability report 220, which may be an RRCReconfigurationComplete message that lists an applicability status for the full inference CSI-ReportConfigIDs in the report configuration message 310. It is noted that at 225 the UE retains non-applicable full inference configurations in case they may become applicable later. The UE also suspends the inference operation for any newly non-applicable full inference configurations.
[0046] When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of periodic, the UE may commence inference with the AI / ML model after transmitting the initial applicability report. When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 230 (e.g., including downlink control information (DCI) or media access control (MAC) control element (CE) ) to cause the UE to activate an AI / ML model indicated as applicable by the UE. At 240, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting.
[0047] At 250 the UE monitors the full inference configurations that were designated for monitoring by association with UAI at 215. When a change in applicability status of any of these the full inference configurations is detected, the UE transmits an applicability change report 260 that reports the change in applicability status. This may include UAI that reports either applicable or non-applicable status for each CSI-ReportConfigID in the set of monitored CSI-ReportConfigIDs identified at 215.
[0048] When a non-applicable AI / ML model becomes applicable, this change is reported in message 260. When the newly applicable model is associated with a CSI-ReportConfig having a report configuration type of periodic, the UE may commence inference with the newly applicable AI / ML model after transmitting the initial applicability report. When a newly applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 261 (e.g., including DCI or MAC CE to cause the UE to activate an AI / ML model indicated as newly applicable by the UE. In some examples, at 263 the network sends an updated full inference configuration for the newly applicable full inference configuration. At 270, the UE begins inference using the newly applicable AI / ML model as well as any still applicable AI / ML models and provides results of the inference using the configured reporting.Applicability Change Report in Option B Report Configuration
[0049] When report configuration option B is effect, the report configuration message provides inference-related parameters rather than full inference configurations. The question arises as to how inference-related parameters should be configured in the report configuration message. For example, should the inference-related parameters be configured in the report configuration message’s measurement configuration component (e.g., CSI-MeasConfig IE) or the other configuration component (e.g., CSI-MeasConfig IE) .
[0050] FIGs. 4 and 4A illustrate an example in which the inference-related parameters are configured in the measurement configuration component. In this option, the report configuration message (e.g., RRCReconfiguration message) is modified as shown in FIG. 4A. In particular, the measurement configuration component of the report configuration message (e.g., CSI-MeasConfig IE) is used to provide a list of M CSI-InferenceParameters, with each CSI-InferenceParameter having an associated CSI-ReportConfigID.
[0051] Turning now to FIG. 4, a message flow diagram is depicted that outlines an example applicability change reporting process in which inference-related parameters are provided in a report configuration message 410, which may be an RRCReconfiguration message as illustrated in FIG. 4A. For example, the report configuration message 410 may include a measurement configuration component (e.g., CSI-MeasConfig IE) parallel to an other configuration component (e.g., otherConfig IE) . The measurement configuration component may configure one or more inference-related parameters (e.g., CSI-InferenceParameter) each being identified by an associated CSI report configuration ID. In one example, at 415, the UE selects the inference-related parameters configured in the measurement configuration component for monitoring for applicability change reporting. In another example, the other configuration component (e.g., otherConfig IE) indicates a list of CSI-ReportConfigIDs that identify CSI-InferenceParameters that should be associated with UAI for monitoring. In this example, at 415 the UE selects the CSI-InferenceParameters indicated in the other configuration component for association with UAI.
[0052] The UE transmits an initial applicability report 420, which may be an RRCReconfigurationComplete message that lists an applicability status for the inference-related parameters (as identified by CSI-ReportConfigIDs) listed in the report configuration message 410. The network responds by transmitting AI / ML configuration information (e.g., full inference configurations such as CSI-ReportConfigs) for the AI / ML models associated with the inference-related parameters indicated as applicable in the initial applicability report 420. The UE responds with a legacy RRCReconfigurationComplete message 435 that may not include applicability information.
[0053] The UE may commence inference with applicable AI / ML models immediately after transmitting the initial applicability report 435. At 450, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting.
[0054] At 455 the UE monitors the inference-related parameters that were designated for monitoring by association with UAI at 415. When a change in applicability status of any of these the inference-related parameters is detected, the UE transmits an applicability change report 460 that reports the change in applicability status. This may include UAI that reports either applicable or non-applicable status for each CSI-InferenceParameter in the set of monitored CSI-InferenceParameters identified at 415.
[0055] When a non-applicable inference-related parameter becomes applicable, this change is reported in message 460. The UE will not be able to begin inference at this time because the UE does not yet have a full inference configuration for the AI / ML model associated with the newly applicable inference-related parameter. The network sends a full inference configuration 463 for the newly applicable AI / ML model. The message 463 may be an RRCReconfiguration message that includes a CSI-ReportConfig with inference-related parameters. At 470, the UE begins inference using the newly applicable AI / ML model as well as any still applicable AI / ML models and provides results of the inference using the configured reporting.
[0056] FIGs. 5 and 5A illustrate an example in which the inference-related parameters are configured in the other configuration component of the report configuration message. In this option, the report configuration message (e.g., RRCReconfiguration message) is modified as shown in FIG. 5A. In particular, the other configuration component of the report configuration message (e.g., otherConfig IE) is used to provide a list of Inference Parameters, with each Inference Parameter having an associated ParaIndex. This means that a ParaIndex may be identical to a CSI-ReportConfigID. Thus, in the example of FIG. 5A, the inference-related parameters are not configured in the measurement component of the report configuration message nor are they identified by a CSI-ReportConfigID as in preceding examples.
[0057] Turning now to FIG. 5, a message flow diagram is depicted that outlines an example applicability change reporting process in which inference-related parameters are provided in a report configuration message 510, which may be an RRCReconfiguration message as illustrated in FIG. 5A. For example, the report configuration message 510 may include a measurement configuration component (e.g., CSI-MeasConfig IE) parallel to an other configuration component (e.g., otherConfig IE) . The other configuration component may configure one or more inference-related parameters (e.g., InferenceParameters) each being identified by an associated inference parameter ID (e.g., ParaIndex) . In one example, at 515, the UE selects all the inference-related parameters configured in the measurement configuration component for monitoring for applicability change reporting.
[0058] The UE transmits an initial applicability report 520, which in this example is not RRCReconfigurationComplete message but rather UAI. This is because the inference-related parameters are not configured in the measurement component of the report configuration message. The initial applicability report 520 lists an applicability status for all the inference-related parameters (as identified by ParaIndexes) listed in the report configuration message 510. The network responds by transmitting AI / ML configuration information (e.g., full inference configurations such as CSI-ReportConfigs) for the AI / ML models associated with the inference-related parameters indicated as applicable in the initial applicability report 520. The UE responds with a legacy RRCReconfigurationComplete message 435 that may not include applicability information.
[0059] The UE may commence inference with applicable AI / ML models immediately after receiving the AI / ML configuration information 430. At 450, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting.
[0060] At 555 the UE monitors the inference-related parameters that were designated for monitoring by association with UAI at 515. When a change in applicability status of any of these the inference-related parameters is detected, the UE transmits an applicability change report 460 that reports the change in applicability status. This may include UAI that reports either applicable or non-applicable status for each InferenceParameter configured by the report configuration message 510.
[0061] When a non-applicable inference-related parameter becomes applicable, this change is reported in message 460. The UE will not be able to begin inference at this time because the UE does not yet have a full inference configuration for the AI / ML model associated with the newly applicable inference-related parameter. The network sends a full inference configuration 463 for the newly applicable AI / ML model. The message 463 may be an RRCReconfiguration message that includes a CSI-ReportConfig with inference-related parameters. At 470, the UE begins inference using the newly applicable AI / ML model as well as any still applicable AI / ML models and provides results of the inference using the configured reporting.
[0062] FIGs. 6 and 6A illustrate another example in which the inference-related parameters are configured in the measurement configuration component. In this option, the report configuration message (e.g., RRCReconfiguration message) is modified as shown in FIG. 6A. In particular, the measurement configuration component of the report configuration message (e.g., CSI-MeasConfig IE) is used to provide a list of M CSI-ReportConfigs that configure a set of inference-related parameters without providing a full inference configuration. Each CSI-ReportConfig has an associated CSI-ReportConfigID. Each CSI-ReportConfig includes a reportQuantity that may be set to “pending” to indicate that the UE should select the corresponding inference-related parameter for monitoring for applicability reporting.
[0063] Turning now to FIG. 6, a message flow diagram is depicted that outlines an example applicability change reporting process in which inference-related parameters are provided in a report configuration message 610, which may be an RRCReconfiguration message as illustrated in FIG. 6A. For example, the report configuration message 610 may include a measurement configuration component (e.g., CSI-MeasConfig IE) parallel to an other configuration component (e.g., otherConfig IE) . The measurement configuration component may configure one or more inference-related parameters (e.g., CSI-ReportConfigs) each being identified by an associated CSI report configuration ID. In one example, the reportQuantity in each CSI-ReportConfig may be selectively set to pending. In this example, at 615 the UE selects the CSI-ReportConfigs having a reportQuantity set to pending for association with UAI for applicability reporting.
[0064] The UE transmits an initial applicability report 620, which may be an RRCReconfigurationComplete message that lists an applicability status for the inference-related parameters (as identified by CSI-ReportConfigIDs) listed in the report configuration message 610. The network responds by transmitting AI / ML configuration information 430 (e.g., full inference configurations such as CSI-ReportConfigs) for the AI / ML models associated with the inference-related parameters indicated as applicable in the initial applicability report 620. The UE responds with a legacy RRCReconfigurationComplete message 435 that may not include applicability information.
[0065] The UE may commence inference with applicable AI / ML models immediately after receiving the AI / ML configuration information 430. At 450, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting.
[0066] At 455 the UE monitors the inference-related parameters that were designated for monitoring by association with UAI at 615. When a change in applicability status of any of these the inference-related parameters is detected, the UE transmits an applicability change report 460 that reports the change in applicability status. This may include UAI that reports either applicable or non-applicable status for each inference-related parameter (CSI-ReportConfigID) in the set of monitored CSI-ReportConfigs identified at 615.
[0067] When a non-applicable inference-related parameter becomes applicable, this change is reported in message 460. The UE will not be able to begin inference at this time because the UE does not yet have a full inference configuration for the AI / ML model associated with the newly applicable inference-related parameter. The network sends a full inference configuration 463 for the newly applicable AI / ML model. The message 463 may be an RRCReconfiguration message that includes a CSI-ReportConfig with inference-related parameters. At 470, the UE begins inference using the newly applicable AI / ML model as well as any still applicable AI / ML models and provides results of the inference using the configured reporting.UE Behavior When Report Configuration Includes Both Full Inference Configurations and Inference-Related Parameters
[0068] The network may ensure that a UE is not provided with both full inference configurations and inference-related parameters at the same time. In other words, the network may ensure that the applicability reporting proceeds under either option A or option B, but not both option A and option B. To achieve this purpose, separate UE capabilities for option A and option B can be introduced. However, in some instances, the network may not enforce such a rule and to compensate for this possibility, the applicability reporting processes described above may be adapted as follows.
[0069] FIGs. 7 and 7A illustrate an example in which the inference-related parameters are configured in the measurement configuration component. In this option, the report configuration message (e.g., RRCReconfiguration message) is modified as shown in FIG. 7A. In particular, the measurement configuration component of the report configuration message (e.g., CSI-MeasConfig IE) is used to provide a list of M CSI-Inference Parameters, with each CSI-Inference Parameter having an associated CSI-ReportConfigID. Additionally, because options A and B are in force some of the N CSI-ReportConfigs configured by the measurement component may be full inference configurations.
[0070] Turning now to FIG. 7, a message flow diagram is depicted that outlines an example applicability change reporting process in which both full inference configurations and inference-related parameters are provided in a report configuration message 710, which may be an RRCReconfiguration message as illustrated in FIG. 7A. For example, the report configuration message 710 may include a measurement configuration component (e.g., CSI-MeasConfig IE) parallel to an other configuration component (e.g., otherConfig IE) . The measurement configuration component may configure one or more full inference configurations (e.g., full inference CSI-ReportConfigs) . The measurement configuration component may also configure one or more inference-related parameters (e.g., CSI-InferenceParameters) each being identified by an associated CSI report configuration ID. At 715, the UE selects all full inference configurations configured in the measurement configuration component for monitoring for applicability change reporting. In one example, at 715, the UE also selects all inference-related parameters configured in the measurement configuration component for monitoring for applicability change reporting. In another example, as shown in dashed line in FIG. 7A, the other configuration component (e.g., otherConfig IE) indicates a list of CSI-ReportConfigIDs that identify, by CSI-ReportConfigID, CSI-InferenceParameters that should be associated with UAI for monitoring. In this example, at 715 the UE also selects the CSI-InferenceParameters indicated in the other configuration component for association with UAI.
[0071] The UE transmits an initial applicability report 720, which may be an RRCReconfigurationComplete message that lists an applicability status for the full inference configurations and inference-related parameters (as identified by CSI-ReportConfigIDs) listed in the report configuration message 710. The network may respond by transmitting AI / ML configuration information (e.g., full inference configurations such as CSI-ReportConfigs) for the AI / ML models associated with the inference-related parameters indicated as applicable in the initial applicability report 720.
[0072] When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of periodic, the UE may commence inference with the AI / ML model after transmitting the initial applicability report at 720 or receiving the full inference configuration at 721. When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 722 (e.g., including DCI or MAC CE) to cause the UE to activate an AI / ML model indicated as applicable by the UE. At 750, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting. It is noted that the UE retains non-applicable full inference configurations in case they may become applicable later. The UE also suspends the inference operation for any newly non-applicable full inference configurations.
[0073] At 755 the UE monitors the full inference configurations and inference-related parameters that were designated for monitoring by association with UAI at 715. When a change in applicability status of any of these the full inference configurations or inference-related parameters is detected, the UE transmits an applicability change report 760 that reports the change in applicability status. This may include UAI that reports either applicable or non-applicable status for each full inference CSI-ReportConfig and CSI-InferenceParameter identified at 715.
[0074] When a non-applicable full inference configuration or inference-related parameter becomes applicable, this change is reported in message 760. The UE will not be able to begin inference at this time for newly applicable inference-related parameters because the UE may not yet have a full inference configuration for the AI / ML model associated with the newly applicable inference-related parameter. In this case, the network sends a full inference configuration 761 for the newly applicable AI / ML model. The message 761 may be an RRCReconfiguration message that includes a CSI-ReportConfig with inference-related parameters. When a newly applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 763 (e.g., including DCI or MAC CE) to cause the UE to activate the newly applicable AI / ML model. At 770, the UE begins inference using the newly applicable AI / ML model as well as any still applicable AI / ML models and provides results of the inference using the configured reporting.
[0075] FIG. 8 illustrates an example in which the inference-related parameters are configured in the other configuration component. In this option, the report configuration message (e.g., RRCReconfiguration message) is modified as shown in FIG. 5A. In particular, the other configuration component of the report configuration message (e.g., otherConfig IE) is used to provide a list of InferenceParameters, with each Inference Parameter having an associated ParaIndex. This means that a ParaIndex can be identical to a CSI-ReportConfigID. Additionally, because options A and B are in force some of the N CSI-ReportConfigs configured by the measurement component may be full inference configurations.
[0076] Turning now to FIG. 8, a message flow diagram is depicted that outlines an example applicability change reporting process in which both full inference configurations and inference-related parameters are provided in a report configuration message 810, which may be an RRCReconfiguration message as illustrated in FIG. 5A. For example, the report configuration message 810 may include a measurement configuration component (e.g., CSI-MeasConfig IE) parallel to an other configuration component (e.g., otherConfig IE) . The measurement configuration component may configure one or more full inference configurations (e.g., full inference CSI-ReportConfigs) . The other configuration component may configure one or more inference-related parameters (e.g., InferenceParameters) each being identified by an associated ParaIndex. Alternatively, the other configuration component may identify inference-related parameters (e.g., InferenceParameters) by CSI-ReportConfigIDs. In one example, at 815, the UE associates all full inference configurations and inference-related parameters configured in the measurement configuration component with UAI for monitoring and for applicability change reporting.
[0077] The UE transmits an initial applicability report 820, which may be an RRCReconfigurationComplete message that lists an applicability status for the full inference configurations (as identified by CSI-ReportConfigIDs) and inference-related parameters (as identified by ParaIndexes) listed in the report configuration message 810. It is noted in the solution of FIG. 7 both full inference configurations and inference-related parameters are identified by CSI-ReportConfigIDs in the initial applicability report and the applicability change report. Thus there is no possibility of the same CSI-ReportConfigID value referring to both a full inference configuration and an inference-related parameter. In the solution of FIG. 8, the initial applicability report 820 (and the applicability change report 860) will include both CSI-ReportConfigIDs and ParaIndexes. This sets up the possibility that a CSI-ReportConfigID identifying a full inference configuration and a ParaIndex identifying an inference-related parameter may have the same value –introducing ambiguity as to which item is being reported as applicable.
[0078] To prevent this potential ambiguity, the network may ensure that there is no overlap between configured CSI-ReportConfigID and ParaIndex values. Alternatively, in the initial applicability report and the applicability change report, augmented CSI-ReportConfigIDs and ParaIndexes may be used in which the UE includes an additional bit indicating whether the value refers to a CSI-ReportConfigID or a ParaIndex. Alternatively, CSI-ReportConfigIDs may be used to identify inference-related parameters (e.g., InferenceParameters) .
[0079] The network may respond by transmitting AI / ML configuration information 721 (e.g., full inference configurations such as CSI-ReportConfigs) for the AI / ML models associated with the inference-related parameters indicated as applicable in the initial applicability report 820.
[0080] When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of periodic, the UE may commence inference with the AI / ML model after transmitting the initial applicability report at 820 or receiving the full inference configuration at 721. When an applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 722 (e.g., including DCI or MAC CE) to cause the UE to activate an AI / ML model indicated as applicable by the UE. At 750, the UE begins inference using all applicable AI / ML models and provides results of the inference using the configured reporting. It is noted that the UE retains any non-applicable full inference configurations in case they may become applicable later. The UE also suspends the inference operation for any newly non-applicable full inference configurations.
[0081] At 855 the UE monitors the full inference configurations and inference-related parameters that were designated for monitoring by association with UAI at 815. When a change in applicability status of any of these the full inference configurations or inference-related parameters is detected, the UE transmits an applicability change report 860 that reports the change in applicability status. This may include UAI that reports either applicable or non-applicable status for each full inference CSI-ReportConfigID and ParaIndex value identified for applicability change reporting at 815. Augmented CSI-ReportConfigIDs and ParaIndexes may be used as described above.
[0082] When a non-applicable full inference configuration or inference-related parameter becomes applicable, this change is reported in message 860. The UE will not be able to begin inference at this time for newly applicable inference-related parameters because the UE may not yet have a full inference configuration for the AI / ML model associated with the newly applicable inference-related parameter. In this case, the network sends a full inference configuration 761 for the newly applicable AI / ML model. The message 761 may be an RRCReconfiguration message that includes a CSI-ReportConfig with inference-related parameters. When a newly applicable AI / ML model is associated with a CSI-ReportConfig having a report configuration type of semi-persistent or aperiodic, the network may need to send an inference activation message 763 (e.g., including DCI or MAC CE) to cause the UE to activate the newly applicable AI / ML model. At 770, the UE begins inference using the newly applicable AI / ML model as well as any still applicable AI / ML models and provides results of the inference using the configured reporting.Report Configuration Message for Configuring Data Collection Configurations
[0083] The techniques disclosed above may be extended to provide a mechanism for the network to configure a list of candidate data collection configurations and for the UE to feedback which data collection configurations are preferred. The data collection configurations may include, for example, different resource configurations for sets A and B.
[0084] In a first example illustrated in FIG. 9A, a report configuration message (e.g., RRCReconfiguration message) may be used to configure multiple CSI-ReportConfigs that each define a particular data collection scenario. Each of the CSI-ReportConfigs for data collection may be assigned a ReportConfigID. Optionally, otherConfig may indicate a list of CSI-ReportConfigs that are to be selected for applicability monitoring. In this case, applicability means that the UE prefers a certain data collection configuration. The UE may use an initial applicability report (RRCReconfigurationComplete message) and applicability change reporting (UAI) as outlined above to dynamically select and feedback CSI-ReportConfigIDs for preferred data collection configurations. The example of FIG. 2 (UE implicitly selects CSI-ReportConfigs for applicability reporting) and FIG. 3 (UE selects CSI-ReportConfigs having CSI-ReportConfigIDs listed in otherConfig) may be extended in a straightforward manner to support data collection configuration using report configuration messages and UAI.
[0085] In a second example illustrated in FIG. 9B, an otherConfig IE of a report configuration message (e.g., RRCReconfiguration message) may be used to configure multiple CSI-DataCollectionParameters that each define a particular data collection scenario. Each of the CSI-DataCollectionParameters may be assigned a ReportConfigID. The UE may use an initial applicability report (RRCReconfigurationComplete message) and applicability change reporting (UAI) as outlined above to dynamically select and feedback CSI-ReportConfigIDs for preferred data collection configurations. The example of FIG. 5 may be extended in a straightforward manner to support data collection configuration using report configuration messages and UAI.Wireless Network
[0086] FIG. 10 illustrates an example wireless network. The systems and devices of example network 100 may operate in accordance with one or more communication standards, such as 2nd generation (2G) , 3rd generation (3G) , 4th generation (4G) (e.g., long-term evolution (LTE) ) , and / or 5th generation (5G) (e.g., new radio (NR) ) communication standards of the 3rd generation partnership project (3GPP) . Additionally, or alternatively, one or more of the systems and devices of example network 100 may operate in accordance with other communication standards and protocols discussed herein, including future versions or generations of 3GPP standards (e.g., sixth generation (6G) standards, seventh generation (7G) standards, etc. ) , institute of electrical and electronics engineers (IEEE) standards (e.g., wireless metropolitan area network (WMAN) , worldwide interoperability for microwave access (WiMAX) , etc. ) , and more.
[0087] As shown, UEs 1010 may include smartphones (e.g., handheld touchscreen mobile computing devices connectable to one or more wireless communication networks) . Additionally, or alternatively, UEs 1010 may include other types of mobile or non-mobile computing devices capable of wireless communications, such as personal data assistants (PDAs) , pagers, laptop computers, desktop computers, wireless handsets, etc. In some implementations, UEs 1010 may include internet of things (IoT) devices (or IoT UEs) that may comprise a network access layer designed for low-power IoT applications utilizing short-lived UE connections. Additionally, or alternatively, an IoT UE may utilize one or more types of technologies, such as machine-to-machine (M2M) communications or machine-type communications (MTC) (e.g., to exchanging data with an MTC server or other device via a public land mobile network (PLMN) ) , proximity-based service (ProSe) or device-to-device (D2D) communications, sensor networks, IoT networks, and more. Depending on the scenario, an M2M or MTC exchange of data may be a machine-initiated exchange, and an IoT network may include interconnecting IoT UEs (which may include uniquely identifiable embedded computing devices within an Internet infrastructure) with short-lived connections. In some scenarios, IoT UEs may execute background applications (e.g., keep-alive messages, status updates, etc. ) to facilitate the connections of the IoT network.
[0088] As examples therefore, a RAN node may be an E-UTRAN Node B (e.g., an enhanced Node B, eNodeB, eNB, 4G base station, etc. ) , a next generation base station (e.g., a 5G base station, NR base station, next generation eNBs (gNB) , etc. ) . RAN nodes 1022 may include a roadside unit (RSU) , a transmission reception point (TRxP or TRP) , and one or more other types of ground stations (e.g., terrestrial access points) . In some scenarios, RAN node 1022 may be a dedicated physical device, such as a macrocell base station, and / or a low power (LP) base station for providing femtocells, picocells or other like having smaller coverage areas, smaller user capacity, or higher bandwidth compared to macrocells.
[0089] Some or all of RAN nodes 1022 may be implemented as one or more software entities running on server computers as part of a virtual network, which may be referred to as a centralized RAN (CRAN) and / or a virtual baseband unit pool (vBBUP) . In these implementations, the CRAN or vBBUP may implement a RAN function split, such as a packet data convergence protocol (PDCP) split wherein RRC and PDCP layers may be operated by the CRAN / vBBUP and other Layer 2 (L2) protocol entities may be operated by individual RAN nodes 1022; a media access control (MAC) / physical (PHY) layer split wherein RRC, PDCP, radio link control (RLC) , and MAC layers may be operated by the CRAN / vBBUP and the PHY layer may be operated by individual RAN nodes 1022; or a “lower PHY” split wherein RRC, PDCP, RLC, MAC layers and upper portions of the PHY layer may be operated by the CRAN / vBBUP and lower portions of the PHY layer may be operated by individual RAN nodes 1022. This virtualized framework may allow freed-up processor cores of RAN nodes 1022 to perform or execute other virtualized applications.
[0090] In some implementations, an individual RAN node 1022 may represent individual gNB-distributed units (DUs) connected to a gNB-control unit (CU) via individual F1 interfaces. In such implementations, the gNB-DUs may include one or more remote radio heads or radio frequency (RF) front end modules (RFEMs) , and the gNB-CU may be operated by a server (not shown) located in RAN 1020 or by a server pool (e.g., a group of servers configured to share resources) in a similar manner as the CRAN / vBBUP. Additionally, or alternatively, one or more of RAN nodes 1022 may be next generation eNBs (i.e., gNBs) that may provide evolved universal terrestrial radio access (E-UTRA) user plane and control plane protocol terminations toward UEs 1010, and that may be connected to a 5G core network (5GC) 1030 via an NG interface.
[0091] Any of the RAN nodes 1022 may terminate an air interface protocol and may be the first point of contact for UEs 1010. In some implementations, any of the RAN nodes 1022 may fulfill various logical functions for the RAN 1020 including, but not limited to, radio network controller (RNC) functions such as radio bearer management, uplink and downlink dynamic radio resource management and data packet scheduling, and mobility management. UEs 1010 may be configured to communicate using orthogonal frequency-division multiplexing (OFDM) communication signals with each other or with any of the RAN nodes 1022 over a multicarrier communication channel in accordance with various communication techniques, such as, but not limited to, an OFDMA communication technique (e.g., for downlink communications) or a single carrier frequency-division multiple access (SC-FDMA) communication technique (e.g., for uplink and ProSe or sidelink (SL) communications) , although the scope of such implementations may not be limited in this regard. The OFDM signals may comprise a plurality of orthogonal subcarriers.
[0092] In some implementations, a downlink resource grid may be used for downlink transmissions from any of the RAN nodes 1022 to UEs 1010, and uplink transmissions may utilize similar techniques. The grid may be a time-frequency grid (e.g., a resource grid or time-frequency resource grid) that represents the physical resource for downlink in each slot. Such a time-frequency plane representation is a common practice for OFDM systems, which makes it intuitive for radio resource allocation. Each column and each row of the resource grid corresponds to one OFDM symbol and one OFDM subcarrier, respectively. The duration of the resource grid in the time domain corresponds to one slot in a radio frame. The smallest time-frequency unit in a resource grid is denoted as a resource element. Each resource grid comprises resource blocks, which describe the mapping of certain physical channels to resource elements. Each resource block may comprise a collection of resource elements (REs) ; in the frequency domain, this may represent the smallest quantity of resources that currently may be allocated. There are several different physical downlink channels that are conveyed using such resource blocks.
[0093] The RAN nodes 1022 may be configured to communicate with one another via interface 1023. In implementations where the system is an LTE system, interface 1023 may be an X2 interface. The X2 interface may be defined between two or more RAN nodes 1022 (e.g., two or more eNBs / gNBs or a combination thereof) that connect to evolved packet core (EPC) or CN 1030, or between two eNBs connecting to an EPC. In some implementations, the X2 interface may include an X2 user plane interface (X2-U) and an X2 control plane interface (X2-C) . The X2-U may provide flow control mechanisms for user data packets transferred over the X2 interface and may be used to communicate information about the delivery of user data between eNBs or gNBs. For example, the X2-U may provide specific sequence number information for user data transferred from a master eNB (MeNB) to a secondary eNB (SeNB) ; information about successful in sequence delivery of PDCP packet data units (PDUs) to a UE 1010 from an SeNB for user data; information of PDCP PDUs that were not delivered to a UE 1010; information about a current minimum desired buffer size at the SeNB for transmitting to the UE user data; and the like. The X2-C may provide intra-LTE access mobility functionality (e.g., including context transfers from source to target eNBs, user plane transport control, etc. ) , load management functionality, and inter-cell interference coordination functionality.
[0094] As shown, RAN 1020 may be connected (e.g., communicatively coupled) to CN 1030. CN 1030 may comprise a plurality of network elements 1032, which are configured to offer various data and telecommunications services to customers / subscribers (e.g., users of UEs 1010) who are connected to the CN 1030 via the RAN 1020. In some implementations, CN 1030 may include an evolved packet core (EPC) , a 5G CN, and / or one or more additional or alternative types of CNs. The components of the CN 1030 may be implemented in one physical node or separate physical nodes including components to read and execute instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) . In some implementations, network function virtualization (NFV) may be utilized to virtualize any or all the above-described network node roles or functions via executable instructions stored in one or more computer-readable storage mediums (described in further detail below) . A logical instantiation of the CN 1030 may be referred to as a network slice, and a logical instantiation of a portion of the CN 1030 may be referred to as a network sub-slice. Network Function Virtualization (NFV) architectures and infrastructures may be used to virtualize one or more network functions, alternatively performed by proprietary hardware, onto physical resources comprising a combination of industry-standard server hardware, storage hardware, or switches. In other words, NFV systems may be used to execute virtual or reconfigurable implementations of one or more EPC components / functions.
[0095] As shown, CN 1030, application servers 1040, and external networks 1050 may be connected to one another via interfaces 1034, 1036, and 1038, which may include IP network interfaces. Application servers 1040 may include one or more server devices or network elements (e.g., virtual network functions (VNFs) offering applications that use IP bearer resources with CN 1030 (e.g., universal mobile telecommunications system packet services (UMTS PS) domain, LTE PS data services, etc. ) . Application servers 1040 may also, or alternatively, be configured to support one or more communication services (e.g., voice over IP (VoIP sessions, push-to-talk (PTT) sessions, group communication sessions, social networking services, etc. ) for UEs 1010 via the CN 1030. Similarly, external networks 1050 may include one or more of a variety of networks, including the Internet, thereby providing the mobile communication network and UEs 1010 of the network access to a variety of additional services, information, interconnectivity, and other network features.
[0096] UEs 1010 may communicate and establish a connection with (e.g., be communicatively coupled) with RAN 1020, which may involve one or more wireless channels 1014-1 and 1014-2, each of which may comprise a physical communications interface / layer. In some implementations, a UE may be configured with dual connectivity (DC) as a multi-radio access technology (multi-RAT) or multi-radio dual connectivity (MR-DC) , where a multiple receive and transmit (Rx / Tx) capable UE may use resources provided by different network nodes (e.g., 1022-1 and 1022-2) that may be connected via non-ideal backhaul (e.g., where one network node provides NR access and the other network node provides either E-UTRA for LTE or NR access for 5G) . In such a scenario, one network node may operate as a master node (MN) and the other as the secondary node (SN) . The MN and SN may be connected via a network interface, and at least the MN may be connected to the CN 1030. Additionally, at least one of the MN or the SN may be operated with shared spectrum channel access, and functions specified for UE 1010 can be used for an integrated access and backhaul mobile termination (IAB-MT) . Similar for UE 1001, the IAB-MT may access the network using either one network node or using two different nodes with enhanced dual connectivity (EN-DC) architectures, new radio dual connectivity (NR-DC) architectures, or the like. In some implementations, a base station (as described herein) may be an example of network node 1022.
[0097] As shown, UE 1010 may also, or alternatively, connect to access point (AP) 1016 via connection interface 1018, which may include an air interface enabling UE 1010 to communicatively couple with AP 1016. AP1016 may comprise a wireless local area network (WLAN) , WLAN node, WLAN termination point, etc. The connection 1018 may comprise a local wireless connection, such as a connection consistent with any IEEE 702.11 protocol, and AP 1016 may comprise a wireless fidelity router or other AP. While not explicitly depicted in Fig. 10, AP 1016 may be connected to another network (e.g., the Internet) without connecting to RAN 1020 or CN 1030. In some scenarios, UE 1010, RAN 1020, and AP 1016 may be configured to utilize LTE-WLAN aggregation (LWA) techniques or LTE WLAN radio level integration with IPsec tunnel (LWIP) techniques. LWA may involve UE 1010 in RRC_CONNECTED being configured by RAN 1020 to utilize radio resources of LTE and WLAN. LWIP may involve UE 1010 using WLAN radio resources (e.g., connection interface 1018) via IPsec protocol tunneling to authenticate and encrypt packets (e.g., Internet Protocol (IP) packets) communicated via connection interface 1018. IPsec tunneling may include encapsulating the entirety of original IP packets and adding a new packet header, thereby protecting the original header of the IP packets.Device
[0098] FIG. 11 is a diagram of an example of components of a device according to one or more implementations described herein. In some implementations, the device 1100 can include application circuitry 1102, baseband circuitry 1104, RF circuitry 1106, front-end module (FEM) circuitry 1108, one or more antennas 1110, and power management circuitry (PMC) 1112 coupled together at least as shown. In some implementations, the device 1100 can include fewer elements (e.g., a RAN node may not utilize application circuitry 1102, and instead include a processor / controller to process IP data received from a CN such as 5GC 1030 or an Evolved Packet Core (EPC) ) . In some implementations, the device 1100 can include additional elements such as, for example, memory / storage, display, camera, sensor (including one or more temperature sensors, such as a single temperature sensor, a plurality of temperature sensors at different locations in device 1100, etc. ) , or input / output (I / O) interface. In other implementations, the components described below can be included in more than one device (e.g., said circuitries can be separately included in more than one device for Cloud-RAN (C-RAN) implementations) .
[0099] The application circuitry 1102 can include one or more application processors. For example, the application circuitry 1102 can include circuitry such as, but not limited to, one or more single-core or multi-core processors. The processor (s) can include any combination of general-purpose processors and dedicated processors (e.g., graphics processors, application processors, etc. ) . The processors can be coupled with or can include memory / storage and can be configured to execute instructions stored in the memory / storage to enable various applications or operating systems to run on the device 1100. In some implementations, processors of application circuitry 1102 can process IP data packets received from an EPC.
[0100] The baseband circuitry 1104 can include circuitry such as, but not limited to, one or more single-core or multi-core processors. The baseband circuitry 1104 can include one or more baseband processors or control logic to process baseband signals received (e.g., measurement gap configurations and reference signals from neighboring cells when the device is associated with a UE) from a receive signal path of the RF circuitry 1106 and to generate baseband signals (e.g., measurement gap configurations for a UE when the device is associated with a RAN node) for a transmit signal path of the RF circuitry 1106. Baseband circuity 1104 can interface with the application circuitry 1102 for generation and processing of the baseband signals and for controlling operations of the RF circuitry 1106. For example, in some implementations, the baseband circuitry 1104 can include a 3G baseband processor 1104A, a 4G baseband processor 1104B, a 5G baseband processor 1104C, or other baseband processor (s) 1104D for other existing generations, generations in development or to be developed in the future (e.g., 2G, 6G, etc. ) . The baseband circuitry 1104 (e.g., one or more of baseband processors 1104A-D) can handle various radio control functions that enable communication with one or more radio networks via the RF circuitry 1106. In other implementations, some or all of the functionality of baseband processors 1104A-D can be included in modules stored in the memory 1104G and executed via a Central Processing Unit (CPU) 1104E. The radio control functions can include, but are not limited to, signal modulation / demodulation, encoding / decoding, radio frequency shifting, etc.
[0101] In some implementations, the baseband circuitry 1104 can include one or more audio digital signal processor (s) (DSP) 1104F. The audio DSPs 1104F can include elements for compression / decompression and echo cancellation and can include other suitable processing elements in other implementations. Components of the baseband circuitry can be suitably combined in a single chip, a single chipset, or disposed on a same circuit board in some implementations. In some implementations, some or all of the constituent components of the baseband circuitry 1104 and the application circuitry 1102 can be implemented together such as, for example, on a system on a chip (SOC) .
[0102] In some implementations, the baseband circuitry 1104 can provide for communication compatible with one or more radio technologies. For example, in some implementations, the baseband circuitry 1104 can support communication with a NG-RAN, an evolved universal terrestrial radio access network (EUTRAN) or other wireless metropolitan area networks (WMAN) , a wireless local area network (WLAN) , a wireless personal area network (WPAN) , etc. Implementations in which the baseband circuitry 1104 is configured to support radio communications of more than one wireless protocol can be referred to as multi-mode baseband circuitry.
[0103] RF circuitry 1106 can enable communication with wireless networks using modulated electromagnetic radiation through a non-solid medium. In various implementations, the RF circuitry 1106 can include switches, filters, amplifiers, etc. to facilitate the communication with the wireless network. RF circuitry 1106 can include a receive signal path which can include circuitry to down-convert RF signals received from the FEM circuitry 1108 and provide baseband signals to the baseband circuitry 1104. RF circuitry 1106 can also include a transmit signal path which can include circuitry to up-convert baseband signals provided by the baseband circuitry 1104 and provide RF output signals to the FEM circuitry 1108 for transmission.
[0104] In some implementations, the receive signal path of the RF circuitry 1106 can include mixer circuitry 1106A, amplifier circuitry 1106B and filter circuitry 1106C. In some implementations, the transmit signal path of the RF circuitry 1106 can include filter circuitry 1106C and mixer circuitry 1106A. RF circuitry 1106 can also include synthesizer circuitry 1106D for synthesizing a frequency for use by the mixer circuitry 1106A of the receive signal path and the transmit signal path. In some implementations, the mixer circuitry 1106A of the receive signal path can be configured to down-convert RF signals received from the FEM circuitry 1108 based on the synthesized frequency provided by synthesizer circuitry 1106D. The amplifier circuitry 1106B can be configured to amplify the down-converted signals and the filter circuitry 1106C can be a low-pass filter (LPF) or band-pass filter (BPF) configured to remove unwanted signals from the down-converted signals to generate output baseband signals. Output baseband signals can be provided to the baseband circuitry 1104 for further processing. In some implementations, the output baseband signals can be zero-frequency baseband signals, although this is not a requirement. In some implementations, mixer circuitry 1106A of the receive signal path can comprise passive mixers, although the scope of the implementations is not limited in this respect.
[0105] In some implementations, the mixer circuitry 1106A of the transmit signal path can be configured to up-convert input baseband signals based on the synthesized frequency provided by the synthesizer circuitry 1106D to generate RF output signals for the FEM circuitry 1108. The baseband signals can be provided by the baseband circuitry 1104 and can be filtered by filter circuitry 1106C.
[0106] In some implementations, the mixer circuitry 1106A of the receive signal path and the mixer circuitry 1106A of the transmit signal path can include two or more mixers and can be arranged for quadrature down conversion and up conversion, respectively. In some implementations, the mixer circuitry 1106A of the receive signal path and the mixer circuitry 1106A of the transmit signal path can include two or more mixers and can be arranged for image rejection (e.g., Hartley image rejection) . In some implementations, the mixer circuitry 1106A of the receive signal path and the mixer circuitry`1406A can be arranged for direct down conversion and direct up conversion, respectively. In some implementations, the mixer circuitry 1106A of the receive signal path and the mixer circuitry 1106A of the transmit signal path can be configured for super-heterodyne operation.
[0107] In some implementations, the output baseband signals, and the input baseband signals can be analog baseband signals, although the scope of the implementations is not limited in this respect. In some alternate implementations, the output baseband signals, and the input baseband signals can be digital baseband signals. In these alternate implementations, the RF circuitry 1106 can include analog-to-digital converter (ADC) and digital-to-analog converter (DAC) circuitry and the baseband circuitry 1104 can include a digital baseband interface to communicate with the RF circuitry 1106.
[0108] In some dual-mode implementations, a separate radio IC circuitry can be provided for processing signals for each spectrum, although the scope of the implementations is not limited in this respect.
[0109] In some implementations, frequency input can be provided by a voltage-controlled oscillator (VCO) , although that is not a requirement. Divider control input can be provided by either the baseband circuitry 1104 or the applications circuitry 1102 depending on the desired output frequency. In some implementations, a divider control input (e.g., N) can be determined from a look-up table based on a channel indicated by the applications circuitry 1102.
[0110] FEM circuitry 1108 can include a receive signal path which can include circuitry configured to operate on RF signals received from one or more antennas 1110, amplify the received signals and provide the amplified versions of the received signals to the RF circuitry 1106 for further processing. FEM circuitry 1108 can also include a transmit signal path which can include circuitry configured to amplify signals for transmission provided by the RF circuitry 1106 for transmission by one or more of the one or more antennas 1110. In various implementations, the amplification through the transmit or receive signal paths can be done solely in the RF circuitry 1106, solely in the FEM circuitry 1108, or in both the RF circuitry 1106 and the FEM circuitry 1108.
[0111] While Fig. 11 shows the PMC 1112 coupled only with the baseband circuitry 1104. In other implementations, the PMC 1112 may be additionally or alternatively coupled with, and perform similar power management operations for, other components such as, but not limited to, application circuitry 1102, RF circuitry 1106, or FEM circuitry 1108.
[0112] In some implementations, the PMC 1112 can control, or otherwise be part of, various power saving mechanisms of the device 1100. For example, if the device 1100 is in an RRC_Connected state, where it is still connected to the RAN node as it expects to receive traffic shortly, then it can enter a state known as Discontinuous Reception Mode (DRX) after a period of inactivity. During this state, the device 1100 can power down for brief intervals of time and thus save power.
[0113] If there is no data traffic activity for an extended period of time, then the device 1100 can transition off to an RRC_Idle state, where it disconnects from the network and does not perform operations such as channel quality feedback, handover, etc. The device 1100 goes into a very low power state and it performs paging where again it periodically wakes up to listen to the network and then powers down again. The device 1100 may not receive data in this state; in order to receive data, it can transition back to RRC_Connected state.
[0114] An additional power saving mode can allow a device to be unavailable to the network for periods longer than a paging interval (ranging from seconds to a few hours) . During this time, the device is totally unreachable to the network and can power down. Any data sent during this time incurs a large delay and it is assumed the delay is acceptable.
[0115] Processors of the application circuitry 1102 and processors of the baseband circuitry 1104 can be used to execute elements of one or more instances of a protocol stack. For example, processors of the baseband circuitry 1104, alone or in combination, can be used execute Layer 3, Layer 2, or Layer 6 functionality, while processors of the baseband circuitry 1104 can utilize data (e.g., packet data) received from these layers and further execute Layer 4 functionality (e.g., transmission communication protocol (TCP) and user datagram protocol (UDP) layers) . As referred to herein, Layer 3 can comprise a RRC layer, described in further detail below. As referred to herein, Layer 2 can comprise a medium access control (MAC) layer, a radio link control (RLC) layer, and a packet data convergence protocol (PDCP) layer, described in further detail below. As referred to herein, Layer 1 can comprise a physical (PHY) layer of a UE / RAN node, described in further detail below.
[0116] Above are several flow diagrams outlining example methods. In this description and the appended claims, use of the term “determine” with reference to some entity (e.g., parameter, variable, and so on) in describing a method step or function is to be construed broadly. For example, “determine” is to be construed to encompass, for example, receiving and parsing a communication that encodes the entity or a value of an entity. “Determine” should be construed to encompass accessing and reading memory (e.g., lookup table, register, device memory, remote memory, and so on) that stores the entity or value for the entity. “Determine” should be construed to encompass computing or deriving the entity or value of the entity based on other quantities or entities. “Determine” should be construed to encompass any manner of deducing or identifying an entity or value of the entity.
[0117] As used herein, the term identify when used with reference to some entity or value of an entity is to be construed broadly as encompassing any manner of determining the entity or value of the entity. For example, the term identify is to be construed to encompass, for example, receiving and parsing a communication that encodes the entity or a value of the entity. The term identify should be construed to encompass accessing and reading memory (e.g., device queue, lookup table, register, device memory, remote memory, and so on) that stores the entity or value for the entity.
[0118] As used herein, the term indicate is to be construed broadly as identifying an item, value, or quantity, to another communication device. For example, indicate may mean communicating a selection of one option among a set of options, or setting a flag or bit value in a field of a communicated signal (e.g., DCI, UCI) .Examples
[0119] Examples herein can include subject matter such as a method, means for performing acts or blocks of the method, at least one machine-readable medium including executable instructions that, when performed by a machine (e.g., a processor (e.g., processor , etc. ) with memory, an application-specific integrated circuit (ASIC) , a field programmable gate array (FPGA) , or the like) cause the machine to perform acts of the method or of an apparatus or system for concurrent communication using multiple communication technologies according to implementations and examples described.
[0120] Example 1 is a baseband processor coupled to a memory and configured to, when executing instructions stored in the memory, perform operations including receiving a report configuration message including a measurement configuration component that includes at least one full inference channel state information (CSI) report configuration that includes inference-related parameters related to an artificial intelligence / machine learning (AI / ML) -based beamforming model; selecting a set of monitored full inference CSI report configurations from the at least one full inference CSI report configuration for continuing evaluation with respect to an applicability change report; transmitting an initial applicability report indicating an applicability status for each full inference CSI report configuration in the report configuration message; evaluating each monitored full inference CSI report configuration to detect changes in applicability status; and in response to detecting a change in applicability status for a monitored full inference CSI report configuration, transmitting an applicability change report reporting an applicability status for each monitored full inference CSI report configuration.
[0121] Example 2 includes the subject matter of example 1, including or omitting optional elements, wherein the report configuration message includes an RRCReconfiguration message; the initial applicability report includes an RRCReconfigurationComplete message; and the applicability change report includes user equipment assistance information (UAI) , wherein the operations include associating each monitored full inference CSI report configuration with UAI.
[0122] Example 3 includes the subject matter of example 1, including or omitting optional elements, wherein the operations include selecting, from a plurality of CSI report configurations in the report configuration message, CSI report configurations that include the inference-related parameters for the set of monitored full inference CSI report configurations.
[0123] Example 4 includes the subject matter of example 1, including or omitting optional elements, wherein the operations include selecting, from a plurality of CSI report configurations in the report configuration message, CSI report configurations that include a full inference indicator for the set of monitored full inference CSI report configurations.
[0124] Example 5 includes the subject matter of example 1, including or omitting optional elements, wherein the report configuration message includes an other configuration component parallel to the measurement configuration component that indicates one or more CSI report configuration IDs; and the operations include selecting CSI report configurations associated with the one or more CSI report configuration IDs for the set of monitored full inference CSI report configurations.
[0125] Example 6 includes the subject matter of example 1, including or omitting optional elements, wherein the operations include, in response to a monitored full inference configuration becoming non-applicable, suspending inference operations for the AI / ML model associated with the non-applicable monitored full inference configuration; and retaining the full inference configuration for use in performing inference in response to the monitored full inference configuration becoming applicable.
[0126] Example 7 is a baseband processor coupled to a memory and configured to, when executing instructions stored in the memory, perform operations including receiving a report configuration message indicating one or more inference-related parameters related to an artificial intelligence / machine learning (AI / ML) -based beamforming model; selecting a set of monitored inference-related parameters for continuing evaluation with respect to an applicability change report from the one or more inference-related parameters; transmitting an initial applicability report indicating an applicability status for each of the inference-related parameters; evaluating each monitored inference-related parameter to detect changes in applicability status; and in response to detecting a change in applicability status for a monitored inference-related parameter, transmitting an applicability change report reporting an applicability status for each monitored inference-related parameter.
[0127] Example 8 includes the subject matter of example 7, including or omitting optional elements, wherein the report configuration message includes an RRCReconfiguration message; the initial applicability report includes an RRCReconfigurationComplete message or user equipment assistance information (UAI) ; and the applicability change report includes user UAI, wherein the operations include associating each monitored inference-related parameter with UAI.
[0128] Example 9 includes the subject matter of example 7, including or omitting optional elements, wherein the operations include selecting all of the inference-related parameters indicated in the report configuration message for the set of monitored inference-related parameters
[0129] Example 10 includes the subject matter of example 7, including or omitting optional elements, wherein the report configuration message includes an other configuration component parallel to a measurement configuration component, the other configuration component indicating one or more inference-related parameters configured in the measurement configuration component; and the operations include selecting the indicated inference-related parameters for the set of monitored inference-related parameters.
[0130] Example 11 includes the subject matter of example 10, including or omitting optional elements, wherein the other configuration component assigns a CSI report configuration ID to each inference related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned CSI report configuration ID.
[0131] Example 12 includes the subject matter of example 7, including or omitting optional elements, wherein the report configuration message includes an other configuration component parallel to a measurement configuration component, the other configuration component indicating the one or more inference-related parameters; and the operations include selecting all inference-related parameters indicated in the other configuration component for the set of monitored inference-related parameters.
[0132] Example 13 includes the subject matter of example 12, including or omitting optional elements, wherein the other configuration component assigns an inference parameter ID to each inference-related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned inference parameter ID.
[0133] Example 14 includes the subject matter of example 7, including or omitting optional elements, wherein the inference-related parameters include CSI report configurations and the operations include selecting CSI report configurations in the report configuration message that have a report quantity type of pending for the set of monitored inference-related parameters.
[0134] Example 15 is a baseband processor coupled to a memory and configured to, when executing instructions stored in the memory, perform operations including receiving a report configuration message indicating one or more channel state information (CSI) report configurations that include inference parameters and one or more inference-related parameters, wherein respective CSI report configurations and respective inference-related parameters are related to respective artificial intelligence / machine learning (AI / ML) -based beamforming models; selecting a set of monitored CSI report configurations and monitored inference-related parameters for continuing evaluation with respect to an applicability change report from the one or more inference-related parameters; transmitting an initial applicability report indicating an applicability status for each of the CSI report configurations and inference-related parameters in the report configuration message; evaluating the set of monitored CSI report configurations and monitored inference-related parameters to detect changes in applicability status; and in response to detecting a change in applicability status for a monitored CSI report configuration or a monitored inference-related parameter, transmitting an applicability change report reporting an applicability status for each monitored CSI report configuration and each monitored inference-related parameter.
[0135] Example 16 includes the subject matter of example 15, including or omitting optional elements, wherein the operations include selecting all of the inference-related parameters indicated in the report configuration message for the set of monitored inference-related parameters.
[0136] Example 17 includes the subject matter of example 15, including or omitting optional elements, wherein the report configuration message includes an other configuration component parallel to a channel state information (CSI) measurement configuration component, the other configuration component indicating one or more inference-related parameters configured in the measurement configuration component; and the operations include selecting the indicated inference-related parameters for the set of monitored inference-related parameters.
[0137] Example 18 includes the subject matter of example 17, including or omitting optional elements, wherein the other configuration component assigns a CSI report configuration ID to each inference related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned CSI report configuration ID.
[0138] Example 19 includes the subject matter of example 15, including or omitting optional elements, wherein the report configuration message includes an other configuration component parallel to a measurement configuration component, the other configuration component indicating one or more inference-related parameters; and the operations include selecting all inference-related parameters indicated by the other configuration component for the set of monitored inference-related parameters.
[0139] Example 20 includes the subject matter of example 19, including or omitting optional elements, wherein the measurement configuration component assigns a CSI report configuration ID to each CSI report configuration and the other configuration component assigns an inference parameter ID to each inference-related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned inference parameter ID and reported CSI report configurations by the assigned CSI report configuration ID.
[0140] Example 21 includes the subject matter of example 20, including or omitting optional elements, wherein the operations include identifying the reported CSI report configurations and the reported inference-related parameters in the initial applicability report or the applicability change report by augmented CSI report configuration IDs and augmented inference parameter IDs, respectively, wherein the augmented CSI report configuration IDs and the augmented inference parameter IDs include a bit that indicates either a CSI report configuration or an inference-related parameter.
[0141] Example 22 includes the subject matter of example 19, including or omitting optional elements, wherein the measurement configuration component assigns a CSI report configuration ID to each CSI report configuration and the other configuration component assigns a CSI report configuration ID to each inference-related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned CSI report configuration ID and reported CSI report configurations by the assigned CSI report configuration ID.
[0142] Example 23 is a baseband processor coupled to a memory and configured to, when executing instructions stored in the memory, perform operations including receiving a report configuration message including a measurement configuration component that indicates at least one full data collection configuration that includes resource configuration parameters related to an artificial intelligence / machine learning (AI / ML) -based beamforming model or at least one data collection parameter related to an artificial intelligence / machine learning (AI / ML) -based beamforming model, where each full data collection configuration and data collection parameter is identified by a configuration report identifier; selecting a set of monitored full data collection configurations or a set of monitored data collection parameters for continuing evaluation with respect to an applicability change report; transmitting an initial applicability report indicating an applicability status for each full data collection configuration or data collection parameter in the report configuration message; evaluating each monitored full data collection configuration or monitored data collection parameter to detect changes in applicability status; and in response to detecting a change in applicability status for a monitored full data collection configuration or monitored data collection parameter, transmitting an applicability change report reporting an applicability status for each monitored full data collection configuration or monitored data collection parameter.
[0143] Example 24 includes the subject matter of example 23, including or omitting optional elements, wherein the report configuration message include an RRCReconfiguration message; the initial applicability report includes an RRCReconfigurationComplete message; and the applicability change report includes user equipment assistance information (UAI) , wherein the operations include associating each monitored full data collection configuration or monitored data collection parameter with UAI.
[0144] Example 25 includes the subject matter of example 23, including or omitting optional elements, wherein the operations include selecting, from a plurality of data collection configurations in the report configuration message, data collection configurations that include a full data collection indicator for the set of monitored full data collection configurations.
[0145] Example 26 includes the subject matter of example 23, including or omitting optional elements, wherein the report configuration message includes an other configuration component parallel to the measurement configuration component that indicates one or more CSI report configuration IDs; and the operations include selecting full data configuration configurations and data collection parameters associated with the one or more CSI report configuration IDs for the set of monitored full data collection configurations.
[0146] Example 27 includes the subject matter of example 23, including or omitting optional elements, wherein the operations include selecting all of the data collection parameters indicated in the report configuration message for the set of monitored data collection parameters.
[0147] Example 28 includes the subject matter of example 23, including or omitting optional elements, wherein the report configuration message includes an other configuration component parallel to a measurement configuration component, the other configuration component indicating one or more data collection parameters configured in the measurement configuration component; and the operations include selecting the indicated data collection parameters for the set of monitored data collection parameters.
[0148] Example 29 is a method for performing operations of the baseband processor of examples 1-28.
[0149] Example 30 is non-transitory computer-readable medium having executable instructions stored thereon that, when executed, cause a processor to perform operations of the baseband processor of examples 1-28.
[0150] Example 31 is an apparatus of a UE including the baseband processor of examples 1-28.
[0151] The above description of illustrated examples, implementations, aspects, etc., of the subject disclosure, including what is described in the Abstract, is not intended to be exhaustive or to limit the disclosed aspects to the precise forms disclosed. While specific examples, implementations, aspects, etc., are described herein for illustrative purposes, various modifications are possible that are considered within the scope of such examples, implementations, aspects, etc., as those skilled in the relevant art can recognize.
[0152] In this regard, while the disclosed subject matter has been described in connection with various examples, implementations, aspects, etc., and corresponding Figures, where applicable, it is to be understood that other similar aspects can be used or modifications and additions can be made to the disclosed subject matter for performing the same, similar, alternative, or substitute function of the subject matter without deviating therefrom. Therefore, the disclosed subject matter should not be limited to any single example, implementation, or aspect described herein, but rather should be construed in breadth and scope in accordance with the appended claims below.
[0153] In particular regard to the various functions performed by the above described components or structures (assemblies, devices, circuits, systems, etc. ) , the terms (including a reference to a “means” ) used to describe such components are intended to correspond, unless otherwise indicated, to any component or structure which performs the specified function of the described component (e.g., that is functionally equivalent) , even though not structurally equivalent to the disclosed structure which performs the function in the herein illustrated exemplary implementations. In addition, while a particular feature may have been disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of the other implementations as may be desired and advantageous for any given or particular application.
[0154] As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or” . That is, unless specified otherwise, or clear from context, “X employs A or B”is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then “X employs A or B” is satisfied under any of the foregoing instances. In addition, the articles “a” and “an” as used in this application and the appended claims should generally be construed to mean “one or more” unless specified otherwise or clear from context to be directed to a singular form. Furthermore, to the extent that the terms “including” , “includes” , “having” , “has” , “with” , or variants thereof are used in either the detailed description and the claims, such terms are intended to be inclusive in a manner similar to the term “comprising. ” Additionally, in situations wherein one or more numbered items are discussed (e.g., a “first X” , a “second X” , etc. ) , in general the one or more numbered items can be distinct, or they can be the same, although in some situations the context may indicate that they are distinct or that they are the same.
[0155] It is well understood that the use of personally identifiable information should follow privacy policies and practices that are generally recognized as meeting or exceeding industry or governmental requirements for maintaining the privacy of users. In particular, personally identifiable information data should be managed and handled so as to minimize risks of unintentional or unauthorized access or use, and the nature of authorized use should be clearly indicated to users.
Claims
1.A baseband processor coupled to a memory and configured to, when executing instructions stored in the memory, perform operations comprising:receiving a report configuration message including a measurement configuration component that includes at least one full inference channel state information (CSI) report configuration that includes inference-related parameters related to an artificial intelligence / machine learning (AI / ML) -based beamforming model;selecting a set of monitored full inference CSI report configurations from the at least one full inference CSI report configuration for continuing evaluation with respect to an applicability change report;transmitting an initial applicability report indicating an applicability status for each full inference CSI report configuration in the report configuration message;evaluating each monitored full inference CSI report configuration to detect changes in applicability status; andin response to detecting a change in applicability status for a monitored full inference CSI report configuration, transmitting an applicability change report reporting an applicability status for each monitored full inference CSI report configuration.2.The baseband processor of claim 1, whereinthe report configuration message comprises an RRCReconfiguration message;the initial applicability report comprises an RRCReconfigurationComplete message; andthe applicability change report comprises user equipment assistance information (UAI) , wherein the operations comprise associating each monitored full inference CSI report configuration with UAI.3.The baseband processor of claim 1, wherein the operations comprise selecting, from a plurality of CSI report configurations in the report configuration message, CSI report configurations that include the inference-related parameters for the set of monitored full inference CSI report configurations.4.The baseband processor of claim 1, wherein the operations comprise selecting, from a plurality of CSI report configurations in the report configuration message, CSI report configurations that include a full inference indicator for the set of monitored full inference CSI report configurations.5.The baseband processor of claim 1, whereinthe report configuration message includes an other configuration component parallel to the measurement configuration component that indicates one or more CSI report configuration IDs; andthe operations comprise selecting CSI report configurations associated with the one or more CSI report configuration IDs for the set of monitored full inference CSI report configurations.6.The baseband processor of claim 1, wherein the operations comprise, in response to a monitored full inference configuration becoming non-applicable,suspending inference operations for the AI / ML model associated with the non-applicable monitored full inference configuration; andretaining the full inference configuration for use in performing inference in response to the monitored full inference configuration becoming applicable.7.A baseband processor coupled to a memory and configured to, when executing instructions stored in the memory, perform operations comprising:receiving a report configuration message indicating one or more inference-related parameters related to an artificial intelligence / machine learning (AI / ML) -based beamforming model;selecting a set of monitored inference-related parameters for continuing evaluation with respect to an applicability change report from the one or more inference-related parameters;transmitting an initial applicability report indicating an applicability status for each of the inference-related parameters;evaluating each monitored inference-related parameter to detect changes in applicability status; andin response to detecting a change in applicability status for a monitored inference-related parameter, transmitting an applicability change report reporting an applicability status for each monitored inference-related parameter.8.The baseband processor of claim 7, whereinthe report configuration message comprises an RRCReconfiguration message;the initial applicability report comprises an RRCReconfigurationComplete message or user equipment assistance information (UAI) ; andthe applicability change report comprises user UAI, wherein the operations comprise associating each monitored inference-related parameter with UAI.9.The baseband processor of claim 7, wherein the operations comprise selecting all of the inference-related parameters indicated in the report configuration message for the set of monitored inference-related parameters.10.The baseband processor of claim 7, whereinthe report configuration message includes an other configuration component parallel to a measurement configuration component, the other configuration component indicating one or more inference-related parameters configured in the measurement configuration component; andthe operations comprise selecting the indicated inference-related parameters for the set of monitored inference-related parameters.11.The baseband processor of claim 10, wherein the other configuration component assigns a CSI report configuration ID to each inference related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned CSI report configuration ID.12.The baseband processor of claim 7, whereinthe report configuration message includes an other configuration component parallel to a measurement configuration component, the other configuration component indicating the one or more inference-related parameters; andthe operations comprise selecting all inference-related parameters indicated in the other configuration component for the set of monitored inference-related parameters.13.The baseband processor of claim 12, wherein the other configuration component assigns an inference parameter ID to each inference-related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned inference parameter ID.14.The baseband processor of claim 7, wherein the inference-related parameters comprise CSI report configurations and the operations comprise selecting CSI report configurations in the report configuration message that have a report quantity type of pending for the set of monitored inference-related parameters.15.A baseband processor coupled to a memory and configured to, when executing instructions stored in the memory, perform operations comprising:receiving a report configuration message indicating one or more channel state information (CSI) report configurations that include inference parameters and one or more inference-related parameters, wherein respective CSI report configurations and respective inference-related parameters are related to respective artificial intelligence / machine learning (AI / ML) -based beamforming models;selecting a set of monitored CSI report configurations and monitored inference-related parameters for continuing evaluation with respect to an applicability change report from the one or more inference-related parameters;transmitting an initial applicability report indicating an applicability status for each of the CSI report configurations and inference-related parameters in the report configuration message;evaluating the set of monitored CSI report configurations and monitored inference-related parameters to detect changes in applicability status; andin response to detecting a change in applicability status for a monitored CSI report configuration or a monitored inference-related parameter, transmitting an applicability change report reporting an applicability status for each monitored CSI report configuration and each monitored inference-related parameter.16.The baseband processor of claim 15, wherein the operations comprise selecting all of the inference-related parameters indicated in the report configuration message for the set of monitored inference-related parameters.17.The baseband processor of claim 15, whereinthe report configuration message includes an other configuration component parallel to a channel state information (CSI) measurement configuration component, the other configuration component indicating one or more inference-related parameters configured in the measurement configuration component; andthe operations comprise selecting the indicated inference-related parameters for the set of monitored inference-related parameters.18.The baseband processor of claim 17, wherein the other configuration component assigns a CSI report configuration ID to each inference related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned CSI report configuration ID.19.The baseband processor of claim 15, whereinthe report configuration message includes an other configuration component parallel to a measurement configuration component, the other configuration component indicating one or more inference-related parameters; andthe operations comprise selecting all inference-related parameters indicated by the other configuration component for the set of monitored inference-related parameters.20.The baseband processor of claim 19, wherein the measurement configuration component assigns a CSI report configuration ID to each CSI report configuration and the other configuration component assigns an inference parameter ID to each inference-related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned inference parameter ID and reported CSI report configurations by the assigned CSI report configuration ID.21.The baseband processor of claim 20, wherein the operations comprise identifying the reported CSI report configurations and the reported inference-related parameters in the initial applicability report or the applicability change report by augmented CSI report configuration IDs and augmented inference parameter IDs, respectively, wherein the augmented CSI report configuration IDs and the augmented inference parameter IDs include a bit that indicates either a CSI report configuration or an inference-related parameter.22.The baseband processor of claim 19, wherein the measurement configuration component assigns a CSI report configuration ID to each CSI report configuration and the other configuration component assigns a CSI report configuration ID to each inference-related parameter and the initial applicability report and the applicability change report identify reported inference-related parameters by the assigned CSI report configuration ID and reported CSI report configurations by the assigned CSI report configuration ID.