Life cycle management for ai / ML-based positioning in wireless communication networks

Abstract

Disclosed are methods, systems, and computer-readable medium to perform operations including: receiving a request for artificial intelligence / machine learning (AI / ML) based positioning information, detecting an error associated with AI / ML based positioning, and causing transmission of non-AI / ML based positioning information.

Description

Attorney Docket No. 56990-0073W01 / P70661WO1LIFE CYCLE MANAGEMENT FOR AI / ML-BASED POSITIONING IN WIRELESS COMMUNICATION NETWORKS CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 755,455, filed February 7, 2025, the entire contents of which is incorporated herein by reference.TECHNICAL FIELD

[0002] The present disclosure relates to wireless communications, and more specifically to enhancements to support lifecycle management operations in AI / ML-based positioning.BACKGROUND

[0003] Wireless communication networks provide integrated communication platforms and telecommunication services to wireless user devices. Example telecommunication services include telephony, data (e.g., voice, audio, and / or video data), messaging, and / or other services. The wireless communication networks have wireless access nodes that exchange wireless signals with the wireless user devices using one or more wireless network protocols, such as protocols described in various telecommunication standards promulgated by the ETSI Third Generation Partnership Project (3GPP). The wireless communication networks facilitate mobile broadband service using technologies such as orthogonal frequency-division multiple access (OFDMA), multiple input multiple output (MIMO), advanced channel coding, massive MIMO, beamforming, and / or other features.Attorney Docket No. 56990-0073W01 / P70661WO1SUMMARY

[0004] The present disclosure provides enhancements to support lifecycle management operations in AI / ML-based positioning. In particular, techniques are described for falling back to legacy positioning methods upon failure of AI / ML-based positioning. In addition, mechanisms to distinguish between legacy and AI / ML-based positioning measurements are described. Also disclosed are training data pairing methods in the context of AI / ML positioning.

[0005] In general, in a first aspect, a method includes: receiving a request for artificial intelligence / machine learning (AI / ML) based positioning information, detecting an error associated with AI / ML based positioning; and causing transmission of non-AI / ML based positioning information.

[0006] In a second aspect combinable with the first aspect, the method includes: causing transmission of an indication of the error associated with the AI / ML based positioning; after causing transmission of the indication of the error, causing transmission of capability information for non-AI / ML based positioning; receiving a request for non-AI / ML based positioning information; and responsive to the request for the non-AI / ML based positioning information, causing transmission of the non-AI / ML positioning information.

[0007] In a third aspect combinable with the first or second aspects, the method includes: before receiving the request for the AI / ML based positioning information, causing transmission of capability information for AI / ML based positioning; and causing transmission of capability information for non-AI / ML based positioning.

[0008] In a fourth aspect combinable with any of the first through third aspects, the capability information for AI / ML based positioning and the capability information for non-AI / ML based positioning are transmitted within the same message.

[0009] In a fifth aspect combinable with any of the first through fourth aspects, the method includes: receiving a request for positioning capabilities; and in response to the request for positioning capabilities, transmitting both the capability information for AI / ML based positioning and the capability information for non-AI / ML based positioning.

[0010] In a sixth aspect combinable with any of the first through fifth aspects, the request includes an indication of a plurality of positioning methods including at least one AI / ML based positioning method and at least one non-AI / ML based positioning method.Attorney Docket No. 56990-0073W01 / P70661WO1

[0011] In a seventh aspect combinable with any of the first through sixth aspects, the method includes generating the non-AI / ML based positioning information based on the at least one non-AI / ML based positioning method.

[0012] In an eighth aspect combinable with any of the first through seventh aspects, the method includes: responsive to detecting the error associated with the AI / ML based positioning, causing transmission of the non-AI / ML based positioning information.

[0013] In a ninth aspect combinable with any of the first through eighth aspects, detecting the error associated with AI / ML based positioning includes detecting that an AI / ML based positioning method cannot be performed.

[0014] In a tenth aspect combinable with any of the first through ninth aspects, the method includes: causing transmission of an indication that the AI / ML based positioning method cannot be performed; responsive to the indication that AI / ML based positioning method cannot be performed, receiving a request for non-AI / ML based positioning information; and causing transmission of the non-AI / ML based positioning information.

[0015] In an eleventh aspect combinable with any of the first through tenth aspects, the method includes: monitoring an outcome of AI / ML based positioning; and causing transmission of an indication of the outcome, where the indication of the outcome includes at least one of: an indication that a user equipment (UE)-based positioning with a UE-side model cannot be performed, an indication of a success, an indication of a failure, an indication of a change in AI / ML model, or an indication of a fallback to non-AI / ML positioning.

[0016] In a twelfth aspect combinable with any of the first through eleventh aspects, the method includes: before receiving the request for the AI / ML based positioning information, causing transmission of capability information for AI / ML based positioning; causing transmission of capability information for non-AI / ML based positioning; causing transmission of an indication of the error associated with the AI / ML based positioning; after causing transmission of the indication of the error, receiving a request for non-AI / ML based positioning information; and responsive to the request for the non-AI / ML based positioning information, causing transmission of the non-AI / ML positioning information.

[0017] In a thirteenth aspect combinable with any of the first through twelfth aspects, the method includes: generating a first portion of training data for AI / ML based positioning, the training data including a first portion and a second portion, where the first portion and theAttorney Docket No. 56990-0073W01 / P70661WO1second portion are generated by different entities; and providing the first portion of the training data to at least one of an AI / ML training entity, an AI / ML inference entity, or a location management function (LMF) for pairing the first portion and the second portion.

[0018] In a fourteenth aspect combinable with any of the first through thirteenth aspects, the first portion is associated with a first time stamp and the second portion is associated with a second time stamp, and the first portion and the second portion are paired based on the first time stamp and the second time stamp.

[0019] In a fifteenth aspect combinable with any of the first through fourteenth aspects, the method is performed by a base station, and the non-AI / ML based positioning information includes an indication that the non-AI / ML based positioning information was obtained by non-AI / ML positioning.

[0020] In a sixteenth aspect combinable with any of the first through fifteenth aspects, the method is performed by a user equipment (UE).

[0021] In a seventeenth aspect combinable with any of the first through sixteenth aspects, the method is performed by one or more processors.

[0022] In an eighteenth aspect combinable with any of the first through seventeenth aspects, the method is performed by a next generation radio access network (NG-RAN) or a base station.

[0023] In general, in a nineteenth aspect, a method includes: causing transmission of a request for AI / ML based positioning information; receiving an indication of an error associated with AI / ML based positioning; and receiving non-AI / ML based positioning information.

[0024] In a twentieth aspect combinable with the nineteenth aspect, the method includes: after receiving the indication of the error, receiving capability information for non-AI / ML based positioning; causing transmission of a request for non-AI / ML based positioning information; and responsive to the request for the non-AI / ML based positioning information, receiving the non-AI / ML positioning information.

[0025] In a twenty -first aspect combinable with the nineteenth or twentieth aspects, the method includes: before causing transmission of the request for the AI / ML based positioning information, receiving capability information for AI / ML based positioning; and receiving capability information for non-AI / ML based positioning.Attorney Docket No. 56990-0073W01 / P70661WO1

[0026] In a twenty-second aspect combinable with any of the nineteenth through twenty-first aspects, the capability information for AI / ML based positioning and the capability information for non- AI / ML based positioning are received in the same message.

[0027] In a twenty -third aspect combinable with any of the nineteenth through twenty-second aspects, the method includes: transmitting a request for positioning capabilities; and in response to the request for positioning capabilities, receiving both the capability information for AI / ML based positioning and the capability information for non- AI / ML based positioning.

[0028] In a twenty-fourth aspect combinable with any of the nineteenth through twenty -third aspects, the request includes an indication of a plurality of positioning methods including at least one AI / ML based positioning method and at least one non-AI / ML based positioning method.

[0029] In a twenty -fifth aspect combinable with any of the nineteenth through twenty -fourth aspects the non-AI / ML based positioning information is generated based on the at least one non-AI / ML based positioning method.

[0030] In a twenty-sixth aspect combinable with any of the nineteenth through twenty-fifth aspects the error includes an indication that an AI / ML based positioning method cannot be performed, the method including: receiving an indication that the AI / ML based positioning method cannot be performed; responsive to the indication that the AI / ML based positioning method cannot be performed, causing transmission of a request for non-AI / ML based positioning information; and receiving the non-AI / ML based positioning information.

[0031] In a twenty-seventh aspect combinable with any of the nineteenth through twenty-sixth aspects, the method includes: receiving an indication of a monitoring outcome for AI / ML based positioning, where the indication of the monitoring outcome includes at least one of: an indication that a user equipment (UE)-based positioning with a UE-side model cannot be performed, an indication of a success, an indication of a failure, an indication of a change in AI / ML model, or an indication of a fallback to non-AI / ML positioning.

[0032] In a twenty-eighth aspect combinable with any of the nineteenth through twentyseventh aspects, the method includes: generating a first portion of training data for AI / ML based positioning, the training data including a first portion and a second portion, where the first portion and the second portion are generated by different entities; and providing the first portion of the training data to at least one of an AI / ML training entity, an AI / ML inferenceAttorney Docket No. 56990-0073W01 / P70661WO1entity, or a location management function (LMF) for pairing the first portion and the second portion.

[0033] In a twenty-ninth aspect combinable with any of the nineteenth through twenty-eighth aspects, the first portion is associated with a first time stamp and the second portion is associated with a second time stamp, and the first portion and the second portion are paired based on the first time stamp and the second time stamp.

[0034] In a thirtieth aspect combinable with any of the nineteenth through twenty-ninth aspects, the method is performed by a location management function (LMF).

[0035] In general, in a thirty-first aspect, a method includes: receiving a request for artificial intelligence or machine learning (AI / ML) based positioning information; and causing transmission of a report including positioning information, where the report specifies whether the positioning information was generated using AI / ML based positioning or non-AI / ML based positioning.

[0036] In a thirty-second aspect combinable with the thirty-first aspect, the report includes an indicator to indicate whether the positioning information was generated using AI / ML based positioning or non-AI / ML based positioning.

[0037] In a thirty-third aspect combinable with the thirty-first or thirty-second aspects, the report includes a first field for AI / ML based positioning information and a second field for non-AI / ML based positioning information.

[0038] In a thirty-fourth aspect combinable with any of the thirty-first through thirty-third aspects, a location management function (LMF) is preconfigured to expect either AI / ML based positioning information or non-AI / ML based positioning information in the report.

[0039] In general, in a thirty-fifth aspect, a method includes: generating a first portion of training data for AI / ML based positioning, the training data including a first portion and a second portion, where the first portion and the second portion are generated by different entities; and providing the first portion of the training data to at least one of an AI / ML training entity, an AI / ML inference entity, or a location management function (LMF) for pairing the first portion and the second portion.

[0040] In a thirty-sixth aspect combinable with the thirty-fifth aspect, the first portion is associated with a first time stamp and the second portion is associated with a second timeAttorney Docket No. 56990-0073W01 / P70661WO1stamp, and the first portion and the second portion are paired based on the first time stamp and the second time stamp.

[0041] In general, in a thirty-seventh aspect, one or more processors are configured to, when executing instructions stored in memory, perform the operations of any of the first through thirty-sixth aspects.

[0042] In general, in a thirty-eighth aspect, a non-transitory computer storage medium is encoded with instructions that, when executed by one or more processors, cause the one or more processors to perform the operations of any of the first through thirty-sixth aspects.

[0043] In general, in a thirty-ninth aspect, a system includes one or more processors and one or more storage devices on which are stored instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform the operations of any of the first through thirty-sixth aspects.

[0044] In general, in a fortieth aspect, an apparatus includes one or more baseband processors configured to perform the operations of any of the first through thirty-sixth aspects.

[0045] In general, in a forty-first aspect, a base station includes one or more processors configured to perform the operations of any of the first through thirty-sixth aspects.Attorney Docket No. 56990-0073W01 / P70661WO1 BRIEF DESCRIPTION OF THE FIGURES

[0046] FIG. 1 illustrates an example wireless network.

[0047] FIG.2 illustrates an example process for life cycle management (LCM) in AI / ML-based positioning.

[0048] FIGS. 3A-3F illustrate example processes for LCM in AI / ML-based positioning.

[0049] FIG. 4 illustrates a flowchart of an example method for LCM in AI / ML-based positioning.

[0050] FIG. 5 illustrates an example user equipment (UE).

[0051] FIG. 6 illustrates an example access node.Attorney Docket No. 56990-0073W01 / P70661WO1DETAILED DESCRIPTION

[0052] Wireless communication networks use a variety of techniques to estimate the position of a user equipment (UE). These positioning techniques involve the generation of measurements from configured resources by a UE (or base station), followed by the use of these measurements — either at the UE or another network entity — to estimate the UE’s position. During the measurement phase, the UE receives reference signals (e.g., positioning reference signals (PRS)) from multiple transmission reception points (TRPs) and uses these signals to generate measurements that support positioning methods. Alternatively, in the case of uplink positioning methods, the UE transmits reference signals (e.g., sounding reference signals (SRS)) to multiple TRPs, which then generate measurements to support positioning methods. Once the measurements have been generated, they are processed by the UE (e.g., in UE-based positioning) or another network entity, such as a location management function (LMF) (e.g., in UE-assisted LMF-based positioning), using one or more positioning methods, such as Time of Arrival (TOA), Angle of Arrival (AO A), Angle of Departure (AOD), or Time Difference of Arrival (TDOA).

[0053] To improve positioning accuracy, some wireless communication networks leverage artificial intelligence (Al) and machine learning (ML) techniques to calculate (or assist with calculating) a UE’ s position. AI / ML positioning techniques can be divided into two categories: direct AI / ML positioning, and AI / ML assisted positioning. In direct AEML positioning, an AI / ML model processes signal measurements collected by a UE (or TRP) to directly calculate the position of the UE. In AI / ML assisted positioning, an AI / ML model processes the signal measurements to provide intermediate measurements used for positioning, rather than directly outputting the position of the UE. Both direct AI / ML positioning and AI / ML assisted positioning can be implemented in a variety of ways. For example, direct AI / ML positioning can be implemented using UE-based positioning with a UE-side model, UE-assisted positioning with an LMF-side model, or NG-RAN-assisted positioning with an LMF-side model, among others. Similarly, AI / ML assisted positioning can be implemented using UE-assisted / LMF-based positioning with a UE-side model, or NG-RAN assisted positioning with a base station-side model, among others.

[0054] Generally, the network configures the manner in which UE positioning is performed, including whether the positioning measurements are calculated using AI / ML or legacy (e.g., non-AI / ML) techniques. However, in some cases, a UE (or another network entity) may notAttorney Docket No. 56990-0073W01 / P70661WO1be able to perform AI / ML-based positioning due to, for example, limited capabilities or incompatible configurations (e.g., PRS configurations). In such a case, the UE can report the failure of the AI / ML-based positioning. However, it may be desirable to fallback to legacy positioning methods when AI / ML-based positioning fails so that positioning information can still be obtained.

[0055] In some cases, the network may need to distinguish between legacy (e.g., non-AI / ML) positioning measurements and positioning measurements produced using AI / ML techniques. For example, in the case of AI / ML assisted positioning, the intermediate estimates produced by the AI / ML model may differ from legacy measurements, or they may be identical but their interpretation may lead to different conclusions. As a result, the network should be aware of the method used to generate the measurements so that it can properly account for these differences when calculating the UE’s position. Additionally, the network may need to know whether AI / ML methods were used to generate a positioning measurement in order to collect training data and monitor model performance. However, in some cases, a network may lack the necessary information to distinguish between legacy and AI / ML-based positioning measurements.

[0056] The present disclosure provides enhancements to support lifecycle management operations in AI / ML-based positioning. In particular, techniques are described for falling back to legacy positioning methods upon failure of AI / ML-based positioning. In this manner, positioning information for a UE can be obtained even when AI / ML-based positioning cannot be performed or otherwise fails. In addition, signaling mechanisms are described to distinguish between legacy and AI / ML-based positioning measurements, thereby facilitating UE position calculation, model performance evaluation, and training data collection. Also disclosed are training data pairing methods and definitions for supported, applicable, and activated functionalities in the context of AI / ML positioning.

[0057] FIG. 1 illustrates an example wireless network 100. The wireless network 100 includes a UE 102 and a base station 104 connected via one or more channels 106A, 106B across an air interface 108. The UE 102 and base station 104 communicate using a system that supports controls for managing the access of the UE 102 to a network via the base station 104.

[0058] In some implementations, the wireless network 100 is a Standalone (SA) network, e.g., that incorporates Fifth Generation (5G) New Radio (NR). In some other implementations, the wireless network 100 is a Non- Standalone (NSA) network that incorporates Long TermAttorney Docket No. 56990-0073W01 / P70661WO1Evolution (LTE) and 5G NR. In these implementations, the wireless network 100 may be a E-UTRA (Evolved Universal Terrestrial Radio Access)-NR Dual Connectivity (EN-DC) network, or an NR-EUTRA Dual Connectivity (NE-DC) network. Furthermore, wireless networks implementing one or more other types of communication standards are possible, including future 3GPP systems (e.g., Sixth Generation (6G)), Institute of Electrical and Electronics Engineers (IEEE) 802.11 technology, or the like. While aspects may be described herein using terminology commonly associated with 5GNR, aspects of the present disclosure can be applied to other systems, such as systems subsequent to 5G (e.g., 6G).

[0059] In the wireless network 100, the UE 102 and any other UE in the system may be, for example, any of a laptop computer, smartphone, tablet computer, machine-type device (such as smart meters or specialized devices for healthcare), intelligent transportation system, or any other wireless device. In network 100, the base station 104 provides the UE 102 network connectivity to a broader network (not shown). This UE 102 connectivity is provided via the air interface 108 in a base station service area provided by the base station 104. In some implementations, such a broader network may be a wide area network operated by a cellular network provider, or may be the Internet. Each base station service area associated with the base station 104 is supported by one or more antennas integrated with the base station 104. The service areas can be divided into a number of sectors associated with one or more particular antennas. Such sectors may be physically associated with one or more fixed antennas or may be assigned to a physical area with one or more tunable antennas or antenna settings adjustable in a beamforming process used to direct a signal to a particular sector.

[0060] The UE 102 includes control circuitry 110 coupled with transmit circuitry 112 and receive circuitry 114. The transmit circuitry 112 and receive circuitry 114 may each be coupled with one or more antennas. The control circuitry 110 may include application-specific circuitry, baseband circuitry, or any of various combinations thereof. The transmit circuitry 112 and receive circuitry 114 may be adapted to transmit and receive data, respectively, and may include radio frequency (RF) circuitry and / or front-end module (FEM) circuitry.

[0061] In various implementations, aspects of the transmit circuitry 112, receive circuitry 114, and / or control circuitry 110 may be integrated in various ways to implement the operations described herein. The control circuitry 110 may be adapted or configured to perform various operations, such as those described elsewhere in this disclosure related to a UE. For instance, the control circuitry 110 can measure reference signals and perform positioning methods,Attorney Docket No. 56990-0073W01 / P70661WO1including legacy and AI / ML-based positioning. In some examples, the control circuitry 110 can perform data pairing in accordance with the techniques described herein.

[0062] The transmit circuitry 112 can perform various operations described in this specification. For example, the transmit circuitry 112 can transmit capability information, applicable functionalities, and location information obtained via legacy and / or AI / ML-based methods. In some examples, the transmit circuitry can transmit reference signals (e.g., SRS) to one or more TRPs. Additionally, the transmit circuitry 112 may transmit using a plurality of multiplexed uplink physical channels. The plurality of uplink physical channels may be multiplexed, e.g., according to time division multiplexing (TDM) or frequency division multiplexing (FDM), and in some implementations, along with carrier aggregation. The transmit circuitry 112 may be configured to receive block data from the control circuitry 110 for transmission on the air interface 108.

[0063] The receive circuitry 114 can perform various operations described in this specification. For instance, the receive circuitry 114 can receive assistance data, requests for capability information, and requests for location information. Additionally, the receive circuitry 114 may receive a plurality of multiplexed downlink physical channels from the air interface 108 and relay the physical channels to the control circuitry 110. The plurality of downlink physical channels may be multiplexed, e.g., according to TDM or FDM, e.g., along with carrier aggregation. The transmit circuitry 112 and the receive circuitry 114 may transmit and receive, respectively, both control data and content data (e.g., messages, images, video, etc.) structured within data blocks that are carried by the physical channels.

[0064] FIG. 1 also illustrates the base station 104. In some implementations, the base station 104 may be a 5G radio access network (RAN), a next generation RAN, a E-UTRAN, a nonterrestrial cell, or a legacy RAN, such as a UTRAN. As used herein, the term “5G RAN” or the like may refer to the base station 104 that operates in an NR wireless network 100, and the term “E-UTRAN” or the like may refer to a base station 104 that operates in an LTE wireless network 100. The UE 102 utilizes connections (or channels) 106A, 106B, each of which includes a physical communications interface or layer.

[0065] The base station 104 circuitry may include control circuitry 116 coupled (directly or indirectly) with transmit circuitry 118 and / or receive circuitry 120. The transmit circuitry 118 and receive circuitry 120 may each be coupled (directly or indirectly) with one or more antennas that may be used to enable communications via the air interface 108. The transmitAttorney Docket No. 56990-0073W01 / P70661WO1circuitry 118 and receive circuitry 120 may be adapted to transmit and receive data, respectively, addressed to any UE connected to the base station 104. The receive circuitry 120 may receive a plurality of uplink physical channels from one or more UEs, including the UE 102.

[0066] In FIG. 1, the one or more channels 106A, 106B are illustrated as an air interface to enable communicative coupling, and can be consistent with cellular communications protocols, such as an LTE protocol, Advanced LTE (LTE-A) protocol, LTE-based access to unlicensed spectrum (LTE-U), NR protocol, NR-based access to unlicensed spectrum (NR-U) protocol, and / or any other communications protocol(s). In some implementations, the UE 102 may directly exchange communication data via a ProSe interface. The ProSe interface may alternatively be referred to as a sidelink (SL) interface and may include one or more logical channels, including but not limited to a Physical Sidelink Control Channel (PSCCH), a Physical Sidelink Discovery Channel (PSDCH), and a Physical Sidelink Broadcast Channel (PSBCH).

[0067] Some wireless communication networks, such as those operating in accordance with the 3GPP wireless communication standards, leverage artificial intelligence (Al) and / or machine learning (ML) techniques to calculate (or assist with calculating) a UE’s position with improved accuracy. In particular, for direct AI / ML positioning, the following use cases are supported: UE-based positioning with UE-side model (Case 1); UE-assisted / LMF-based positioning with LMF-side model (Case 2b), and NG-RAN node assisted positioning with LMF-side model (Case 3b). In addition, for AI / ML -assisted positioning, the following use cases are supported: UE-assisted / LMF-based positioning with UE-side model (Case 2a) and NG-RAN node assisted positioning with base station (e.g., gNB) side model (Case 3a).

[0068] As discussed above, the network (e.g., LMF) may configure the use of AI / ML positioning. For example, referring to FIG. 2, a process 200 for lifecycle management (LCM) in AI / ML-based positioning for Case 1 (UE-based positioning with UE-side model) is shown. In this example, the LMF initially requests the UE to report the supported functionalities for AI / ML-based positioning at the UE side using an LTE Positioning Protocol (LPP) Request Capabilities message. Such a message is defined in 3GPP TS 37.355, v. 18.4., the entire contents of which is incorporated herein by reference. Next, the UE sends an LPP Provide Capabilities message to the LMF with an indication of the supported functionalities for AI / ML-based positioning at the UE side. The LMF then sends an LPP Provide Assistance Data message (which may include, among other things, a network side additional condition). TheAttorney Docket No. 56990-0073W01 / P70661WO1UE then reports the applicable functionality for AI / ML-based positioning to the LMF by an LPP Provide Capabilities message. Next, the LMF requests the inferred AI / ML-based location information using an LPP Request Location Information message. Lastly, the UE reports the inferred AI / ML-based location information using an LPP Provide Location Information message.

[0069] In accordance with an aspect of the present disclosure, LCM processes supporting fallback to legacy positioning upon failure of AI / ML-based positioning are described. Referring to FIG. 3 A, an example process 300 for LCM in AI / ML-based positioning is shown. In this example, the LMF first requests the UE (or BS) to report the supported functionalities for AI / ML-based positioning using an LPP Request Capabilities message. Next, the UE sends an LPP Provide Capabilities message to the LMF with an indication of the supported functionalities for AI / ML-based positioning at the UE side. The LMF then sends an LPP Provide Assistance Data message (which may include, among other things, a network side additional condition). The UE then reports the applicable functionality for AI / ML-based positioning to the LMF by an LPP Provide Capabilities message. Next, the LMF requests the inferred AI / ML-based location information using an LPP Request Location Information message. However, in this example, the AI / ML-based positioning method becomes non-applicable when the LMF requests the UE location estimation. As a result, the UE may not perform the AI / ML based positioning and replies with an LPP ProvideLocationlnformation message with the error cause.

[0070] To ensure that the LMF is still able to receive an estimate of the UE’s position, the process 300 includes an LMF -based fallback to legacy positioning by effectively turning off AI / ML-based positioning and setting up legacy positioning. To do so, the LMF requests the UE (or BS) to report the supported functionalities for legacy positioning using an LPP Request Capabilities message. Next, the UE sends an LPP Provide Capabilities message to the LMF with an indication of the supported functionalities for legacy positioning at the UE side. The LMF then sends an LPP Provide Assistance Data message with assistance data, followed by a request for legacy location information using an LPP Request Location Information message. Lastly, the UE reports the legacy location information using an LPP Provide Location Information message.

[0071] Referring to FIG. 3B, an example process 310 for LCM in AI / ML-based positioning is shown. In this example, the AI / ML-based positioning and legacy positioning fallback are setAttorney Docket No. 56990-0073W01 / P70661WO1up simultaneously (but separately). Initially, the LMF requests the UE (or BS) to report the supported functionalities for AI / ML-based positioning and legacy positioning using separate LPP Request Capabilities messages. Next, the UE sends LPP Provide Capabilities messages to the LMF with an indication of the supported functionalities for AI / ML-based positioning and legacy positioning, respectively. The LMF then sends separate LPP Provide Assistance Data messages with assistance data for AI / ML and legacy. Next, the LMF requests for AI / ML-based location information using an LPP Request Location Information message. In this example, the UE detects that the AI / ML-based positioning method becomes non-applicable when the LMF requests the UE location estimation. As a result, the UE does not perform the AI / ML based positioning, and replies with an LPP ProvideLocationlnformation message with the error cause. The LMF then requests for legacy location information using an LPP Request Location Information message, and the UE reports the legacy location information using an LPP Provide Location Information message.

[0072] Referring to FIG. 3C, an example process 330 for LCM in AI / ML-based positioning is shown. In this example, the AI / ML-based positioning and legacy positioning fallback are set up simultaneously (and jointly). Initially, the LMF requests the UE (or BS) to report the supported functionalities for AI / ML-based positioning using an LPP Request Capabilities messages. In response, the UE sends an LPP Provide Capabilities message to the LMF with an indication of the supported functionalities for both AI / ML-based positioning and legacy positioning. The LMF then sends an LPP Provide Assistance Data message with assistance data for AI / ML and legacy. Note that the assistance data may work for both AI / ML and legacy positioning methods. For AI / ML based positioning Case 1, all assistance information from legacy UE-based DL-TDOA, other than info #7 (e.g., geographical coordinates of the TRPs served by the gNB), can be provided from LMF to UE, as the assistance data is a union of legacy and AI / ML with a lot of overlap.

[0073] Next, the LMF requests for AI / ML-based location information using an LPP Request Location Information message. In this example, the UE detects that the AI / ML-based positioning method becomes non-applicable when the LMF requests the UE location estimation. As a result, the UE does not perform the AI / ML based positioning, and replies with an LPP ProvideLocationlnformation message with the error cause. The LMF then explicitly requests for legacy location information using an LPP Request Location Information message, and the UE reports the legacy location information using an LPP Provide Location Information message.Attorney Docket No. 56990-0073W01 / P70661WO1

[0074] Referring to FIG. 3D, an example process 340 for LCM in AI / ML-based positioning is shown. In general, the process 340 is similar to the process 330 shown in FIG. 3 A. However, unlike the process 330 in which the LMF explicitly requests legacy location information, the UE (or BS) automatically provides the legacy positioning information if the AI / ML-based positioning fails. In other words, the LMF does not need to explicitly request the legacy location information.

[0075] Referring to FIG. 3E, an example process 350 for LCM in AI / ML-based positioning is shown. In this example, the AI / ML-based positioning and legacy positioning fallback are set up simultaneously (but separately). Initially, the LMF requests the UE (or BS) to report the supported functionalities for AI / ML-based positioning and legacy positioning using separate LPP Request Capabilities messages. Next, the UE sends LPP Provide Capabilities messages to the LMF with an indication of the supported functionalities for AI / ML-based positioning and legacy positioning, respectively. The LMF then sends separate LPP Provide Assistance Data messages with assistance data for AI / ML and legacy. In this example, the UE detects (e.g., based on the assistance data) that the AI / ML-based positioning method is non-applicable, and transmits an LPP Provide Capabilities message to the LMF reporting the non-applicability of AI / ML-based positioning (e.g., reporting “non- Al”). In some cases, the UE may report non-AI generally without detecting non-applicability based on the received assistance data. In response to the non-AI report, the LMF requests for legacy location information using an LPP Request Location Information message, and the UE reports the legacy location information using an LPP Provide Location Information message.

[0076] Note that, in some examples, the processes 320, 330 shown in FIGs. 3B, 3C can be modified such that the UE reports “non-AI” in Applicable functionalities reporting, and then the LMF directly indicates the non-AI operation in Request Location. In addition, the UE (or BS) may not be restricted to only one fallback configuration. Instead, fallback can be extended to more than one configuration (e.g., different legacy / non-AI positioning), and it can be left to the UE (or BS) implementation to select among the fallback operation. Alternatively, one or more conditions can be introduced for determining which fallback operation should be chosen by the UE. FIG. 3F depicts an example process 360 for LCM in AI / ML-based positioning with multiple legacy fallback options. In this example, the LMF requests the UE (or BS) to report the supported functionalities for AI / ML-based positioning method(s) and legacy positioning method(s) using LPP Request Capabilities message(s). Next, the UE (or BS) sends LPP Provide Capabilities message(s) to the LMF indicating the supported functionalities forAttorney Docket No. 56990-0073W01 / P70661WO1AI / ML-based positioning method(s) and legacy positioning methods. In some examples, the UE (or BS) can send the LPP Provide Capabilities message(s) without being prompted by a request and / or without any additional LMF control. The LMF sends LPP Provide Assistance Data message(s) with assistance data for AI / ML and legacy positioning. In this example, the UE detects (e.g., based on the assistance data) that the AI / ML-based positioning method is non-applicable, and transmits an LPP Provide Capabilities message to the LMF reporting the nonapplicability of AI / ML-based positioning (e.g., reporting “non-AI”). In some examples, the UE may report non-applicability generally without detecting non-applicability based on the received assistance data. The LMF then transmits LPP Request Location Information message(s) including an indication of multiple positioning methods. Specifically, in this example, the LMF transmits an LPP Request Location Information message including an indication of multiple non-AI / ML positioning methods (e.g., Legacy 1, Legacy 2, ..., Legacy N) to facilitate switching / fallback to non-AI / ML positioning. The UE reports the legacy location information obtained using one or more positioning methods (e.g., one or more of non-AI / ML positioning methods Legacy 1, Legacy 2, ... Legacy N) via an LPP Provide Location Information message. As noted above, in some examples, it is left to the UE to select among the fallback positioning methods. In some examples, one or more conditions can be introduced for determining which fallback operation should be chosen by the UE, and / or the LMF can indicate which positioning method to use or otherwise prefer.

[0077] In accordance with an aspect of the present disclosure, techniques for signaling AI / ML-based position measurements to the network (e.g., LMF) are disclosed. In general, for measurement report of AI / ML assisted positioning in e.g., Case 3a, when timing information is reported from the base station (e.g., gNB) to the LMF, the LMF shall be able to distinguish whether the timing information is obtained by a legacy (e.g., non-AI / ML) method or by an AI / ML method. To do so, explicit or implicit signaling can be used. For example, the timing measurement report from the base station can include an indicator that the timing information is obtained by AI / ML or legacy. As another example, the timing measurement report can include multiple timing fields, such as one or more first fields for legacy positioning reports and one or more second fields for AI / ML positioning reports, to distinguish between timing information obtained between legacy and AI / ML methods. In some examples, there is no autonomous change by gNB to LMF of feedback type to implicitly indicate the method used to obtain the timing information. The LMF indicates type of measurement expected (e.g.,Attorney Docket No. 56990-0073W01 / P70661WO1legacy or AI / ML), and the report includes this type of measurement unless there is an explicit functionality switch.

[0078] In general, for model performance monitoring of AI / ML positioning Case 1, the target UE side can perform a monitoring metric calculation and signal the monitoring outcome to the LMF. To support signaling of the monitoring outcome, an indicator can be defined for indicating monitoring success or monitoring failure. Alternatively, or in addition, the monitoring outcome can include one or more indicators indicating a change in the model. These indicators can indicate a successful or unsuccessful model change, and / or a change to a specific set / sub-set of models. In the latter case, signaling and / or a procedure may be used to identify model family (which can include legacy positioning method). In some examples, the monitoring outcome may indicate a fallback to legacy positioning methods. In some examples, the monitoring outcome can indicate that the target UE cannot perform, e.g., the Case 1 positioning method.

[0079] In accordance with an aspect of the present disclosure, techniques for pairing training data are described. In general, training data for AI / ML-based positioning can be broken into two parts: Part A (which can include Channel Measurement (corresponding to model input), Quality indicator (for and / or associated with measurement at least for model training), and Time stamp (for and / or associated with measurement)) and Part B (which can include Ground truth label, Quality indicator (for and / or associated with ground truth label), and Time stamp (for and / or associated with ground truth label)). For training data collection in AI / ML based positioning, if Part A and Part B are generated by different entities, the pairing between a Part A entry and a Part B entry is supported via at least: a UE identifier, and the time stamp of Part A and the time stamp of Part B. Note that time stamp granularity can be used for Part A and Part B. For example, “Measurement time” in 3GPP TS 38.455 and UTCTime in 3GPP 37.355 have different granularities. In some examples, raw data (e.g., Part A and / or Part B) can be transmitted to the AI / ML training entity (e.g., UE, LMF, NG-RAN node, vendor entity), and the pairing can be performed by the AI / ML training entity. In some examples, pairing can be performed by the AI / ML inference entity (e.g., the network entity executing the AI / ML model). In some examples, paring can be performed by the LMF. In some examples, the pairing entity can be defined according to the specific use case, such as summarized in the table below. Regardless of the pairing entity, pairing (e.g., based on the time stamps) can be left to the particular implementation, done according to the closest timing among paired parts, or doneAttorney Docket No. 56990-0073W01 / P70661WO1according to the closest timing among paired parts within configured and / or specified uncertainty and / or quality value.

[0080] In accordance with an aspect of the present disclosure, supported, applicable, and activated functionalities in the context of AI / ML-based positioning can be defined. The concept / terminology “functionality” of supported functionalities may refer to UE-capability information / parameters, such as 3GPP Rel-19 AI / ML-enabled features / feature groups. The concept / terminology “functionality” of applicable functionalities may refer to unsolicited UE capability report mechanism in LPP to report the applicable functionality in both “proactive” and “reactive” for inference configuration or a set of inference related parameters. “Proactive” refers to, for example, the case in which UE can send an unsolicited LPP ProvideCapabilities message to the LMF when the applicability change. “Reactive” refers to, for example, the case in which the UE can send an unsolicited LPP ProvideCapabilities message to the LMF if the applicability changes based on the configuration in LPP ProvideAssistanceData message.

[0081] The activated functionalities may be enabled based on, e.g., an LMF’s request for inferred location information using the LPP Request Location Information message.

[0082] FIG. 4 illustrates a flowchart of an example method 400, according to some implementations. For clarity of presentation, the description that follows generally describes method 400 in the context of the other figures in this description. For example, method 400 can be performed by UE 102 and / or base station 104 of FIG. 1. It will be understood that method 400 can be performed, for example, by any suitable system, environment, software, hardware, or a combination of systems, environments, software, and hardware, as appropriate. In some implementations, various steps of method 400 can be run in parallel, in combination, in loops, or in any order.

[0083] Operations of the method 400 include receiving a request for AI / ML-based positioning information (402). Such a request can be received, for example, by a UE and include an LPP Provide Location Information message requesting the AI / ML-based positioning information,Attorney Docket No. 56990-0073W01 / P70661WO1or by a BS and include an NR Positioning Protocol A (NRPPa) message requesting the AI / ML-based positioning information. An error associated with AI / ML-based positioning is detected (404). Detecting the error can include, for example, detecting that AI / ML-based positioning is a non-applicable functionality (or unsupported functionality or deactivated functionality), such as due to UE capabilities or conditions / configurations. At 406, non-AI / ML based positioning information is transmitted (e.g., automatically, or in response to a request for non-AI / ML based positioning information).

[0084] FIG. 5 illustrates an example UE 500. The UE 500 may be similar to and substantially interchangeable with UE 102 of FIG. 1.

[0085] The UE 500 may be any mobile or non-mobile computing device, such as, for example, a mobile phone, computer, tablet, industrial wireless sensors, video device (for example, cameras, video cameras, etc.), wearable devices (for example, a smart watch), relaxed-IoT devices, etc.

[0086] The UE 500 may include any / all of processor 502, RF interface circuitry 504, memory / storage 506, user interface 508, sensors 510, driver circuitry 512, power management integrated circuit (PMIC) 514, one or more antenna(s) 516, and battery 518. The components of the UE 500 may be implemented as integrated circuits (ICs), portions thereof, discrete electronic devices, or other modules, logic, hardware, software, firmware, or a combination thereof. The block diagram of FIG. 5 is intended to show a high-level view of some of the components of the UE 500. However, some of the components shown may be omitted, additional components may be present, and a different arrangement of the components shown may occur in other implementations.

[0087] The components of the UE 500 may be coupled with various other components over one or more interconnects 520, which may represent any type of interface, input / output, bus (local, system, or expansion), transmission line, trace, optical connection, etc., that allows various circuit components (on common or different chips or chipsets) to interact with one another.

[0088] The processor 502 may include one or more processors. For example, the processor 502 may include processor circuitry such as, for example, baseband processor circuitry (BB) 522A, central processor unit circuitry (CPU) 522B, and graphics processor unit circuitry (GPU) 522C. The processor 502 may include any type of circuitry or processor circuitry that executes or otherwise operates computer-executable instructions, such as program code, softwareAttorney Docket No. 56990-0073W01 / P70661WO1modules, or functional processes from memory / storage 506 to cause the UE 500 to perform operations as described herein.

[0089] In some implementations, the baseband processor circuitry 522A may access a communication protocol stack 524 in the memory / storage 506 to communicate over a 3GPP compatible network. In general, the baseband processor circuitry 522A may access the communication protocol stack to: perform user plane functions at a physical (PHY) layer, medium access control (MAC) layer, radio link control (RLC) layer, packet data convergence protocol (PDCP) layer, service data adaptation protocol (SDAP) layer, and PDU layer; and perform control plane functions at a PHY layer, MAC layer, RLC layer, PDCP layer, RRC layer, and a non-access stratum layer. In some implementations, the PHY layer operations may additionally / altematively be performed by the components of the RF interface circuitry 504. The baseband processor circuitry 522A may generate or process baseband signals or waveforms that carry information in 3 GPP-compatible networks. In some implementations, the waveforms for NR may be based cyclic prefix orthogonal frequency division multiplexing (OFDM) “CP-OFDM” in the uplink or downlink, and discrete Fourier transform spread OFDM “DFT-S-OFDM” in the uplink.

[0090] The memory / storage 506 may include one or more non-transitory, computer-readable media that includes instructions (for example, communication protocol stack 524) that may be executed by the processor 502 to cause the UE 500 to perform various operations described herein. For instance, the memory / storage 506 can include instructions that may be executed by the processor 502 to (or cause the UE 500 to) measure and / or process reference signals and perform positioning methods, including legacy and AI / ML-based positioning. In some examples, the memory / storage 506 can include instructions that may be executed by the processor 502 to perform data pairing to generate, for example, training data for AI / ML-based positioning models. The memory / storage 506 include any type of volatile or non-volatile memory that may be distributed throughout the UE 500. In some implementations, some of the memory / storage 506 may be located on the processor 502 itself (for example, LI and L2 cache), while other memory / storage 506 is external to the processor 502 but accessible thereto via a memory interface. The memory / storage 506 may include any suitable volatile or nonvolatile memory such as, but not limited to, dynamic random access memory (DRAM), static random access memory (SRAM), erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), Flash memory, solid-state memory, or any other type of memory device technology.Attorney Docket No. 56990-0073W01 / P70661WO1

[0091] The RF interface circuitry 504 may include transceiver circuitry and radio frequency front module (RFEM) that allows the UE 500 to communicate with other devices over a radio access network. The RF interface circuitry 504 may include various elements arranged in transmit or receive paths. These elements may include, for example, switches, mixers, amplifiers, filters, synthesizer circuitry, control circuitry, etc.

[0092] In the receive path, the RFEM may receive a radiated signal from an air interface via antenna(s) 516 and proceed to filter and amplify (with a low-noise amplifier) the signal. The signal may be provided to a receiver of the transceiver that downconverts the RF signal into a baseband signal that is provided to the baseband processor. In some examples, the receive path can be used to receive assistance data, requests for capability information, and / or requests for location information.

[0093] In the transmit path, the transmitter of the transceiver up-converts the baseband signal received from the baseband processor and provides the RF signal to the RFEM. The RFEM may amplify the RF signal through a power amplifier prior to the signal being radiated across the air interface via the antenna(s) 516. In various implementations, the RF interface circuitry 504 may be configured to transmit / receive signals in a manner compatible with NR access technologies. In some examples, the transmit path can be used to transmit capability information, applicable functionalities, and / or location information obtained via legacy and / or AI / ML-based methods. In some examples, the transmit path can be used to transmit reference signals (e.g., SRS) to one or more gNBs and / or TRPs.

[0094] The antenna(s) 516 may include one or more antenna elements to convert electrical signals into radio waves to travel through the air and to convert received radio waves over the air into electrical signals. In some implementations, the antenna elements may be arranged into one or more antenna panels. The antenna(s) 516 may have antenna panels that are omnidirectional, directional, or a combination thereof, to enable beamforming and multiple input, multiple output communications. The antenna(s) 516 may include any / all of microstrip antennas, printed antennas fabricated on the surface of one or more printed circuit boards, patch antennas, phased array antennas, etc. The antenna(s) 516 may have one or more panels designed for one or more specific frequency bands, such as bands in FR1 or FR2.

[0095] The user interface 508 includes various input / output (VO) devices designed to enable user interaction with the UE 500. The user interface 508 includes input device circuitry and output device circuitry. Input device circuitry includes any physical or virtual means forAttorney Docket No. 56990-0073W01 / P70661WO1accepting an input including, inter alia, one or more physical or virtual buttons (for example, a reset button), a physical keyboard, keypad, mouse, touchpad, touchscreen, microphones, scanner, headset, or the like. The output device circuitry includes any physical or virtual means for showing information or otherwise conveying information, such as sensor readings, actuator position(s), or other like information. Output device circuitry may include any number or combinations of audio or visual display, including, inter alia, one or more simple visual outputs / indicators (for example, binary status indicators such as light emitting diodes “LEDs” and multi -character visual outputs), or more complex outputs such as display devices or touchscreens (for example, liquid crystal displays “LCDs,” LED displays, quantum dot displays, projectors, etc.), with the output of characters, graphics, multimedia objects, and the like being generated or produced from the operation of the UE 500.

[0096] The sensors 510 may include devices, modules, or subsystems whose purpose is to detect events or changes in its environment and send the information (sensor data) about the detected events to some other device, module, subsystem, etc. Examples of such sensors include, inter alia, inertia measurement units including accelerometers, gyroscopes, or magnetometers; microelectromechanical systems or nanoelectromechanical systems including 3-axis accelerometers, 3-axis gyroscopes, or magnetometers; level sensors; temperature sensors (for example, thermistors); pressure sensors; image capture devices (for example, cameras or lensless apertures); light detection and ranging sensors; proximity sensors (for example, infrared radiation detector and the like); depth sensors; ambient light sensors; ultrasonic transceivers; microphones or other like audio capture devices; etc.

[0097] The driver circuitry 512 may include software and hardware elements that operate to control particular devices that are embedded in the UE 500, attached to the UE 500, or otherwise communicatively coupled with the UE 500. The driver circuitry 512 may include individual drivers allowing other components to interact with or control various input / output (I / O) devices that may be present within, or connected to, the UE 500. For example, driver circuitry 512 may include a display driver to control and allow access to a display device, a touchscreen driver to control and allow access to a touchscreen interface, sensor drivers to obtain sensor readings of sensors 510 and control and allow access to sensors 510, drivers to obtain actuator positions of electro-mechanic components or control and allow access to the electro-mechanic components, a camera driver to control and allow access to an embedded image capture device, audio drivers to control and allow access to one or more audio devices.Attorney Docket No. 56990-0073W01 / P70661WO1

[0098] The PMIC 514 may manage power provided to various components of the UE 500. In particular, with respect to the processor 502, the PMIC 514 may control power-source selection, voltage scaling, battery charging, or DC-to-DC conversion.

[0099] In some implementations, the PMIC 514 may control, or otherwise be part of, various power saving mechanisms of the UE 500. A battery 518 may power the UE 500, although in some examples the UE 500 may be mounted deployed in a fixed location, and may have a power supply coupled to an electrical grid. The battery 518 may be a lithium ion battery, a metal-air battery, such as a zinc-air battery, an aluminum-air battery, a lithium-air battery, and the like. In some implementations, such as in vehicle-based applications, the battery 518 may be a typical lead-acid automotive battery.

[0100] FIG. 6 illustrates an example access node 600 (e.g., a base station or gNB), according to some implementations. The access node 600 may be similar to and substantially interchangeable with base station 104. The access node 600 may include one or more of processor 602, RF interface circuitry 604, core network (CN) interface circuitry 606, memory / storage circuitry 608, and one or more antenna(s) 610. The processor 602 may include any type of circuitry or processor circuitry that executes or otherwise operates computerexecutable instructions, such as program code, software modules, or functional processes from memory / storage circuitry 608 to cause the access node 600 to perform operations as described herein.

[0101] The components of the access node 600 may be coupled with various other components over one or more interconnects 612. The processor 602, RF interface circuitry 604, memory / storage circuitry 608 (including communication protocol stack 614), antenna(s) 610, and interconnects 612 may be similar to like-named elements shown and described with respect to FIG. 5. For example, the processor 602 may include processor circuitry such as, for example, baseband processor circuitry (BB) 616A, central processor unit circuitry (CPU) 616B, and graphics processor unit circuitry (GPU) 616C.

[0102] In some examples, the memory / storage 608 may include one or more non-transitory, computer-readable media that includes instructions that may be executed by the processor 602 to cause the access node 600 to perform various operations described herein. For instance, the memory / storage 608 can include instructions that may be executed by the processor 602 to (or cause the access node 600 to) perform positioning methods and / or process positioning information, including legacy and AI / ML-based positioning information. In some examples,Attorney Docket No. 56990-0073W01 / P70661WO1the memory / storage 608 can include instructions that may be executed by the processor 602 to perform data pairing to generate, for example, training data for AI / ML-based positioning models.

[0103] The RF interface circuitry 604 may include transceiver circuitry and receive circuitry that allows the access node 600 to communicate with other devices over a radio access network In some examples, the transmit path can be used to transmit assistance data, requests for capability information, and / or requests for location information. In some examples, the receive path can be used to receive capability information, applicable functionalities, and / or location information obtained via legacy and / or AI / ML-based methods. In some examples, the receive path can be used to receive reference signals (e.g., SRS).The CN interface circuitry 606 may provide connectivity to a core network, for example, a 5th Generation Core network (5GC) using a 5GC-compatible network interface protocol such as carrier Ethernet protocols, or some other suitable protocol. Network connectivity may be provided to / from the access node 600 via a fiber optic or wireless backhaul. The CN interface circuitry 606 may include one or more dedicated processors or FPGAs to communicate using one or more of the aforementioned protocols. In some implementations, the CN interface circuitry 606 may include multiple controllers to provide connectivity to other networks using the same or different protocols.

[0104] As used herein, the terms “access node,” “access point,” or the like may describe equipment that provides the radio baseband functions for data and / or voice connectivity between a network and one or more users. These access nodes can be referred to as BS, gNBs, RAN nodes, eNBs, NodeBs, RSUs, TRxPs or TRPs, and so forth, and can include ground stations (e.g., terrestrial access points) or satellite stations providing coverage within a geographic area (e.g., a cell). As used herein, the term “NG RAN node” or the like may refer to an access node 600 that operates in an NR or 5G system (for example, a gNB), and the term “E-UTRAN node” or the like may refer to an access node 600 that operates in an LTE or 4G system (e.g., an eNB). According to various implementations, the access node 600 may be implemented as one or more of a dedicated physical device such as a macrocell base station, and / or a low power (LP) base station for providing femtocells, picocells or other like cells having smaller coverage areas, smaller user capacity, or higher bandwidth compared to macrocells.Attorney Docket No. 56990-0073W01 / P70661WO1

[0105] In some implementations, all or parts of the access node 600 may be implemented as one or more software entities running on server computers as part of a virtual network, which may be referred to as a CRAN and / or a virtual baseband unit pool (vBBUP).

[0106] Various components may be described as performing a task or tasks, for convenience in the description. Such descriptions should be interpreted as including the phrase “configured to.” Reciting a component that is configured to perform one or more tasks is expressly intended not to invoke 35 U.S.C. § 112(f) interpretation for that component.

[0107] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, or methods as set forth in the example section below. For example, the baseband circuitry as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth below. For another example, circuitry associated with a UE, base station, network element, etc., as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth below in the example section.

[0108] Any of the above-described examples may be combined with any other example (or combination of examples), unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.

[0109] Although the embodiments above have been described in considerable detail, numerous variations and modifications will become apparent to those skilled in the art once the above disclosure is fully appreciated. It is intended that the following claims be interpreted to embrace all such variations and modifications.

[0110] 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

Attorney Docket No. 56990-0073W01 / P70661WO1CLAIMSWe Claim:

1. A method comprising:receiving a request for artificial intelligence / machine learning (AI / ML) based positioning information;detecting an error associated with AI / ML based positioning; andcausing transmission of non-AI / ML based positioning information.

2. The method of claim 1, further comprising:causing transmission of an indication of the error associated with the AI / ML based positioning;after causing transmission of the indication of the error,causing transmission of capability information for non-AI / ML based positioning;receiving a request for non-AI / ML based positioning information; and responsive to the request for the non-AI / ML based positioning information, causing transmission of the non-AI / ML positioning information.

3. The method of claim 1, further comprising:before receiving the request for the AI / ML based positioning information, causing transmission of capability information for AI / ML based positioning; andcausing transmission of capability information for non-AI / ML based positioning.

4. The method of claim 3, wherein the capability information for AI / ML based positioning and the capability information for non-AI / ML based positioning are transmitted within the same message.

5. The method of claim 3, further comprising:receiving a request for positioning capabilities; andAttorney Docket No. 56990-0073W01 / P70661WO1in response to the request for positioning capabilities, transmitting both the capability information for AI / ML based positioning and the capability information for non-AI / ML based positioning.

6. The method of claim 1, wherein the request comprises an indication of a plurality of positioning methods including at least one AI / ML based positioning method and at least one non-AI / ML based positioning method.

7. The method of claim 6, further comprising:generating the non-AI / ML based positioning information based on the at least one non-AI / ML based positioning method.

8. The method of claim 1, further comprising:responsive to detecting the error associated with the AI / ML based positioning, causing transmission of the non-AI / ML based positioning information.

9. The method of claim 1, wherein detecting the error associated with AI / ML based positioning comprises detecting that an AI / ML based positioning method cannot be performed.

10. The method of claim 9, further comprising:causing transmission of an indication that the AI / ML based positioning method cannot be performed;responsive to the indication that AI / ML based positioning method cannot be performed, receiving a request for non-AI / ML based positioning information; and causing transmission of the non-AI / ML based positioning information.

11. The method of claim 1, further comprising:monitoring an outcome of AI / ML based positioning; andcausing transmission of an indication of the outcome, wherein the indication of the outcome comprises at least one of: an indication that a user equipment (UE)-based positioning with a UE-side model cannot be performed, an indication of a success, an indication of a failure, an indication of a change in AI / ML model, or an indication of a fallback to non-AI / ML positioning.Attorney Docket No. 56990-0073W01 / P70661WO112. A method, comprising:causing transmission of a request for artificial intelligence / machine learning (AI / ML) based positioning information;receiving an indication of an error associated with AI / ML based positioning; and receiving non-AI / ML based positioning information.

13. The method of claim 12, further comprising:after receiving the indication of the error,receiving capability information for non-AI / ML based positioning; causing transmission of a request for non-AI / ML based positioning information; andresponsive to the request for the non-AI / ML based positioning information, receiving the non-AI / ML positioning information.

14. The method of claim 12, further comprising:before causing transmission of the request for the AI / ML based positioning information,receiving capability information for AI / ML based positioning; and receiving capability information for non-AI / ML based positioning.

15. The method of claim 14, wherein the capability information for AI / ML based positioning and the capability information for non-AI / ML based positioning are received in the same message.

16. The method of claim 14, further comprising:transmitting a request for positioning capabilities; andin response to the request for positioning capabilities, receiving both the capability information for AI / ML based positioning and the capability information for non-AI / ML based positioning.

17. The method of claim 12, wherein the request comprises an indication of a plurality of positioning methods including at least one AI / ML based positioning method and at least one non-AI / ML based positioning method.Attorney Docket No. 56990-0073W01 / P70661WO118. The method of claim 17, wherein the non-AI / ML based positioning information is generated based on the at least one non-AI / ML based positioning method.

19. The method of claim 12, wherein the error comprises an indication that an AI / ML based positioning method cannot be performed, the method further comprising:receiving an indication that the AI / ML based positioning method cannot be performed;responsive to the indication that the AI / ML based positioning method cannot be performed, causing transmission of a request for non-AI / ML based positioning information; andreceiving the non-AI / ML based positioning information.

20. The method of claim 12, further comprising:receiving an indication of a monitoring outcome for AI / ML based positioning, wherein the indication of the monitoring outcome comprises at least one of: an indication that a user equipment (UE)-based positioning with a UE-side model cannot be performed, an indication of a success, an indication of a failure, an indication of a change in AI / ML model, or an indication of a fallback to non-AI / ML positioning.

21. One or more processors configured to, when executing instructions stored in memory, perform the method of any preceding claim.

22. A non-transitory computer storage medium encoded with instructions that, when executed by one or more processors, cause the one or more processors to perform the method of any of claims 1 to 20.

23. A system comprising one or more processors and one or more storage devices on which are stored instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform the method of any of claims 1 to 20.

24. An apparatus comprising one or more baseband processors configured to perform the method of any of claims 1 to 20.Attorney Docket No. 56990-0073W01 / P70661WO125. A base station comprising one or more processors configured to perform the method of any of any of claims 1 to 20.

Images