EP4643147A1

EP4643147A1 - Systems, methods, and devices for model validity for ai-based user equipment (ue) positioning

Info

Publication number: EP4643147A1
Application number: EP24710263.5A
Authority: EP
Inventors: Oghenekome Oteri; Dawei Zhang; Wei Zeng; Chunxuan Ye; Ankit Bhamri; Hong He
Original assignee: Apple Inc
Current assignee: Apple Inc
Priority date: 2023-02-03
Filing date: 2024-01-31
Publication date: 2025-11-05
Also published as: KR20250124231A; WO2024163544A1; CN120641783A

Abstract

One or more of the techniques described herein may include using neural network (NN) models to determine a location of a user equipment (UE). The output of the NN may be the location of the UE or be used in a subsequent procedure to determine the location of the UE. The techniques described herein may enable NN models to be configured, labeled, and validated for use in one or more conditions or scenarios. One or more of a UE, a base station, an artificial intelligence (AI) – management function (MF) (AI-MF) server, and a location management function (LMF) may be involved, and the procedures described herein may include a model configuration function, model selection function, and model inference function.

Description

SYSTEMS, METHODS, AND DEVICES FOR MODEL VALIDITY FOR AI-BASED USER EQUIPMENT (UE) POSITIONING

REFERENCE TO RELATED APPLICATIONS

[0001] This Application claims the benefit of U.S. Provisional Application No. 63/443,073, filed on February 3, 2023, the contents of which are hereby incorporated by reference in their entirety

FIELD

[0002] This disclosure relates to wireless communication networks and mobile device capabilities.

BACKGROUND

[0003] Wireless communication networks and wireless communication services are becoming increasingly dynamic, complex, and ubiquitous. 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. Such technology may include solutions for enabling user equipment (UE) and network devices, such as base stations, to communicate with one another. A feature of such networks and devices may include attempting to determine a geographic location of UEs.

BRIEF DESCRIPTION OF THE DRAWINGS

[0004] 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.

[0005] Fig. 1 is a diagram of an example overview of one or more of the techniques described herein. [0006] Fig. 2 is a diagram of an example network according to one or more implementations described herein.

[0007] Fig. 3 is a diagram of an example of user equipment (UE), base stations, core network, and artificial intelligence (Al) - management function (MF) (AI-MF) server according to one or more implementations described herein.

[0008] Fig. 4 is a diagram of an example of Al / machine learning (ML) (AI/ML) functionality and models according to one or more implementations described herein.

[0009] Fig. 5 is a diagram of an example of a neural network (NN) 500 according to one or more implementations described herein.

[0010] Fig. 6 is a diagram of an example of functions and corresponding entities and devices according to one or more implementations described herein.

[0011] Fig. 7 is a diagram of an example table of characteristics of Al-based UE positioning according to one or more implementations described herein.

[0012] Fig. 8 is a diagram of example process for obtaining a valid NN model based on model validity data according to one or more implementations described herein.

[0013] Fig. 9 is a diagram of an example process for determining a NN model based on assistance information and model validity labels according to one or more implementations described herein.

[0014] Fig. 10 is a diagram of an example table of validity labels for NN models according to one or more implementations described herein.

[0015] Fig. 11 is a diagram of an example process for selecting a NN model based on model validity testing according to one or more implementations described herein.

[0016] Fig. 12 is a diagram of an example of a process for model selection according to one or more implementations described herein.

[0017] Fig. 13 is a diagram of an example process for selecting a NN model based on model classes according to one or more implementations described herein.

[0018] Fig. 14 is a diagram of example data structures for NN model classes and validity labels according to one or more implementations described herein.

[0019] Fig. 15 is a diagram of example process for selecting a NN model based on validity data received for NN model classes according to one or more implementations described herein.

[0020] Fig. 16 is a diagram of example process for selecting multiple NN models based on validity data received for NN model classes according to one or more implementations described herein.

[0021] Fig. 17 is a diagram of an example process for model validation according to one or more implementations described herein.

[0022] Fig. 18 is a diagram of an example process for model validation according to one or more implementations described herein.

[0023] Fig. 19 is a diagram of an example of components of a device according to one or more implementations described herein.

[0024] Fig. 20 is a block diagram illustrating components, according to one or more implementations described herein, able to read instructions from a machine- readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and perform any one or more of the methodologies discussed herein.

DETAILED DESCRIPTION

[0025] 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.

[0026] Wireless communication networks may include user equipment (UE) capable of communicating with base stations and/or other network access nodes. The base stations may provide UE with access to a core network (CN) and additional external networks, such as the Internet. Wireless communication networks may implement various techniques and standards that enable services to be provided to UEs in a consistent and high-quality manner. An example of such services may include those relative a geographic location of UEs. The value of such services is often dependent on the level of accuracy with which the geographic location of UEs may be determined, and while currently available technologies may attempt to determine the geographic location of UEs, there remains room for improvement.

[0027] The techniques described herein enable the location of a UE to be determined with greater accuracy by applying artificial intelligence (Al), machine learning (ML), and neural networks (NN) to UE positioning procedures. These techniques may include labeling different neural network (NN) models for determining a location of a UE in different conditions or scenarios, validating and selecting a NN model given a current condition or scenario, and using a selected NN model to determine the position or location of a UE. These and many other processes, operations, and features are described below with reference to the figures.

[0028] Fig. 1 is a diagram of an example overview 100 of one or more of the implementations described herein. Example overview 100 may include UE 1 10 and/or base station 120, and LMF and/or AI-MF servers 130. One or more of the techniques described herein may include processes or operations performed by different devices. For example, in some implementations, certain operations may be performed by UE 1 10, while in other implementations, some or all of those operations may be performed by base station 120 or LMF and/or AI-MF servers 130. Detailed examples and explanations of these variations are described below with reference to the figures that follow. However, to streamline the explanation of example overview 100, “UE 110 and/or base station 120” may be referred to as “UE 110”, and “LMF and/or AI-MF servers 130” may be referred to as LMF 130

[0029] As shown, UE 1 10 and LMF 130 may communicate to configure NN model validity labels for NN models designed for locating UEs 1 10 (at 1 .1 ). A NN model validity label may be referred to herein as a “validity label,” a “label,” and so on). Different NN models may be configured and trained to operate under different conditions and in different circumstances. Labeling a NN model may include specifying appropriate conditions for using the NN model to determine the location of a UE. Such conditions may be defined using one or more of a wide variety of factors.

[0030] Examples of NN model labeling may include capabilities of the NN model, capabilities of a UE, base station, or other communication device, one or more dates, days, times, geographic areas, countries, networks, cells, or network access devices. Additional examples of NN model labeling may include associating a NN model with position accuracy quality (e.g., a degree of accuracy with which the NN model may determine, or help determine, the geographic position or location of a UE) and a model inference latency (e.g., an amount of time typically involved in using the NN model to determine the position or location of a UE). Further examples of NN model labeling may include a UE supporting one or more types of assistance signaling (e.g., location assistance signaling) or reference signal configurations. In some implementations, NN model labels may correspond to input layer information of the corresponding NN model.

[0031] UE 110 and LMF 130 may also operate to determine current condition for using a NN model to locate UE 110 (at 1 .2). For example, UE 110 or LMF 130 may initiate a UE location procedure that may involve determining a geographic location of UE 110. As part of such a procedure (and/or another type of procedure), UE 110 and/or LMF 130 may determine the current condition or circumstances of UE 110 and match the current condition or circumstances to the validity labels of the NN models. Doing so may enable UE 110 and/or LMF 130 to determine which of the NN models is valid (e.g., appropriate, effective, etc.) for determining the location of UE 110. Similar to the validity labels described above, the relevant condition or circumstances of UE 110 may be any number or combination of a wide variety of factors, such as capabilities of UE, capabilities of NN models, supported reference signal configurations, dates, days, times, etc.

[0032] When the current conditions satisfy the validity labels of a NN model, UE 110 and/or LMF 130 may select the NN model (from among NN models more suited for other conditions) (at 1 .3), and UE 110 and/or LMF 130 may precede to use the NN model to determine the geographic location or positioning of UE 110 (at 1 .4). Some NN models may be configured to determine the location of UE 110 directly, meaning the output of the NN model may be the geographic location of UE 110. Other NN models may be configured to output information configured to aid or assist in the location of UE 110 (e.g., by being applied to another NN model, a subsequent location algorithm, etc.). Accordingly, one or more of the techniques described herein may enable Al-based positioning for UEs by ensuring that different NN models are applied to appropriate conditions and scenarios.

[0033] In some implementations, the techniques described herein may include NN model selection based on validity testing data to verify whether a selected NN model matches the requirements or labels of the NN model. The NN model selecting entity (e.g., UE 110 or LMF 130) may receive validity testing data, which may include information regarding a current condition, capability, or scenario for which the NN model is to be used, and the selection entity many determine whether the validity testing data satisfy the NN model labels of one or more NN models. In some implementations, NN models may be organized into classes or groups, where each class corresponds to a different category of NN model and each NN model within a NN model class is associated with a different set of labels. In such scenarios, the NN model selecting entity may receive validity testing data, and a number of model classes, and the NN model selecting entity may use the validity testing data to validate one or more NN models from one or more of the model classes.

[0034] In other implementations, UE 110 may send LMF 130 information that describes NN models supported by UE 110 and assistance information if available (e.g., reference signal measurements, reference signal configuration supported, etc.). Based on the information, LMF 130 may provide UE 1 10 with a set of NN models and their corresponding validity labels. UE 1 10 may test the NN models based on current conditions and the validity labels, select a suitable NN model, and notify LMF 130 of the selection. LMF 130 may respond by providing UE 1 10 with model configuration information and supporting (e.g., assistance information) that UE 110 may use to apply the selected NN model during an Al-based positioning procedure. Additional examples of these and many other techniques, features, and implementations are described below with reference to the figures that follow.

[0035] Fig. 2 is an example network 200 according to one or more implementations described herein. Example network 200 may include UEs 210-1 , 210-2, etc. (referred to collectively as “UEs 210” and individually as “UE 210”), a radio access network (RAN) 220, a core network (CN) 230, application servers 240, and external networks 250.

[0036] The systems and devices of example network 200 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 200 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.

[0037] As shown, UEs 210 may include smartphones (e.g., handheld touchscreen mobile computing devices connectable to one or more wireless communication networks). Additionally, or alternatively, UEs 210 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, watches etc. In some implementations, UEs 210 may include internet of things (loT) devices (or loT UEs) that may comprise a network access layer designed for low-power loT applications utilizing short-lived UE connections. Additionally, or alternatively, an loT 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, loT networks, and more. Depending on the scenario, an M2M or MTC exchange of data may be a machine-initiated exchange, and an loT network may include interconnecting loT UEs (which may include uniquely identifiable embedded computing devices within an Internet infrastructure) with short-lived connections. In some scenarios, loT UEs may execute background applications (e.g., keep- alive messages, status updates, etc.) to facilitate the connections of the loT network.

[0038] UEs 210 may communicate and establish a connection with one or more other UEs 210 via one or more wireless channels 212, each of which may comprise a physical communications interface I layer. The connection may include an M2M connection, MTC connection, D2D connection, SL connection, etc. The connection may involve a PC5 interface. In some implementations, UEs 210 may be configured to discover one another, negotiate wireless resources between one another, and establish connections between one another, without intervention or communications involving RAN node 222 or another type of network node. In some implementations, discovery, authentication, resource negotiation, registration, etc., may involve communications with RAN node 222 or another type of network node.

[0039] UEs 210 may use one or more wireless channels 212 to communicate with one another. As described herein, UE 210-1 may communicate with RAN node 222 to request SL resources. RAN node 222 may respond to the request by providing UE 210 with a dynamic grant (DG) or configured grant (CG) regarding SL resources. A DG may involve a grant based on a grant request from UE 210. A CG may involve a resource grant without a grant request and may be based on a type of service being provided (e.g., services that have strict timing or latency requirements). UE 210 may perform a clear channel assessment (CCA) procedure based on the DG or CG, select SL resources based on the CCA procedure and the DG or CG; and communicate with another UE 210 based on the SL resources. The UE 210 may communicate with RAN node 222 using a licensed frequency band and communicate with the other UE 210 using an unlicensed frequency band.

[0040] UEs 210 may communicate and establish a connection with (e.g., be communicatively coupled) with RAN 220, which may involve one or more wireless channels 214-1 and 214-2, each of which may comprise a physical communications interface I 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., 222-1 and 222-2) 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 230. Additionally, at least one of the MN or the SN may be operated with shared spectrum channel access, and functions specified for UE 210 can be used for an integrated access and backhaul mobile termination (IAB-MT). Similar for UE 210, 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 222.

[0041] As described herein, UE 210 may receive and store one or more configurations, instructions, and/or other information for enabling SL-U communications with quality and priority standards. A PQI may be determined and used to indicate a QoS associated with an SL-U communication (e.g., a channel, data flow, etc.). Similarly, an L1 priority value may be determined and used to indicate a priority of an SL-U transmission, SL-U channel, SL-U data, etc. The PQI and/or L1 priority value may be mapped to a CAPC value, and the PQI, L1 priority, and/or CAPC may indicate SL channel occupancy time (COT) sharing, maximum (MCOT), timing gaps for COT sharing, LBT configuration, traffic and channel priorities, and more.

[0042] As shown, UE 210 may also, or alternatively, connect to access point (AP) 216 via connection interface 218, which may include an air interface enabling UE 210 to communicatively couple with AP 216. AP 216 may comprise a wireless local area network (WLAN), WLAN node, WLAN termination point, etc. The connection 218 may comprise a local wireless connection, such as a connection consistent with any IEEE 702.1 1 protocol, and AP 216 may comprise a wireless fidelity (Wi-Fi®) router or other AP. While not explicitly depicted in Fig. 2, AP 216 may be connected to another network (e.g., the Internet) without connecting to RAN 220 or CN 230. In some scenarios, UE 210, RAN 220, and AP 216 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 210 in RRC_CONNECTED being configured by RAN 220 to utilize radio resources of LTE and WLAN. LWIP may involve UE 210 using WLAN radio resources (e.g., connection interface 218) via IPsec protocol tunneling to authenticate and encrypt packets (e.g., Internet Protocol (IP) packets) communicated via connection interface 218. 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.

[0043] RAN 220 may include one or more RAN nodes 222-1 and 222-2 (referred to collectively as RAN nodes 222, and individually as RAN node 222) that enable channels 214-1 and 214-2 to be established between UEs 210 and RAN 220. RAN nodes 222 may include network access points configured to provide radio baseband functions for data and/or voice connectivity between users and the network based on one or more of the communication technologies described herein (e.g., 2G, 3G, 4G, 5G, WiFi, etc.). 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 222 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 222 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 the like having smaller coverage areas, smaller user capacity, or higher bandwidth compared to macrocells.

[0044] Some or all of RAN nodes 222, or portions thereof, 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 radio resource control (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 222; 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 222; 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 222. This virtualized framework may allow freed-up processor cores of RAN nodes 222 to perform or execute other virtualized applications.

[0045] In some implementations, an individual RAN node 222 may represent individual gNB-distributed units (DUs) connected to a gNB-control unit (CU) via individual F1 or other 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 220 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 222 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 210, and that may be connected to a 5G core network (5GC) 230 via an NG interface.

[0046] Any of the RAN nodes 222 may terminate an air interface protocol and may be the first point of contact for UEs 210. In some implementations, any of the RAN nodes 222 may fulfill various logical functions for the RAN 220 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 210 may be configured to communicate using orthogonal frequency-division multiplexing (OFDM) communication signals with each other or with any of the RAN nodes 222 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.

[0047] In some implementations, a downlink resource grid may be used for downlink transmissions from any of the RAN nodes 222 to UEs 210, 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.

[0048] Further, RAN nodes 222 may be configured to wirelessly communicate with UEs 210, and/or one another, over a licensed medium (also referred to as the “licensed spectrum” and/or the “licensed band”), an unlicensed shared medium (also referred to as the “unlicensed spectrum” and/or the “unlicensed band”), or combination thereof. In an example, a licensed spectrum may include channels that operate in the frequency range of approximately 400 MHz to approximately 3.8 GHz, whereas the unlicensed spectrum may include the 5 GHz band. A licensed spectrum may correspond to channels or frequency bands selected, reserved, regulated, etc., for certain types of wireless activity (e.g., wireless telecommunication network activity), whereas an unlicensed spectrum may correspond to one or more frequency bands that are not restricted for certain types of wireless activity. Whether a particular frequency band corresponds to a licensed medium or an unlicensed medium may depend on one or more factors, such as frequency allocations determined by a public-sector organization (e.g., a government agency, regulatory body, etc.) or frequency allocations determined by a private-sector organization involved in developing wireless communication standards and protocols, etc.

[0049] To operate in the unlicensed spectrum, UEs 210 and the RAN nodes 222 may operate using stand-alone unlicensed operation, licensed assisted access (LAA), eLAA, and/or feLAA mechanisms and/or NR-Unlicensed mechanisms. In these implementations, UEs 210 and the RAN nodes 222 may perform one or more known medium-sensing operations or carrier-sensing operations in order to determine whether one or more channels in the unlicensed spectrum is unavailable or otherwise occupied prior to transmitting in the unlicensed spectrum. The medium/carrier sensing operations may be performed according to a listen-before-talk (LBT) protocol.

[0050] The LAA mechanisms may be built upon carrier aggregation (CA) technologies of LTE-Advanced systems. In CA, each aggregated carrier is referred to as a component carrier (CC). In some cases, individual CCs may have a different bandwidth than other CCs. In time division duplex (TDD) systems, the number of CCs as well as the bandwidths of each CC may be the same for DL and UL. CA also comprises individual serving cells to provide individual CCs. The coverage of the serving cells may differ, for example, because CCs on different frequency bands will experience different pathloss. A primary service cell or PCell may provide a primary component carrier (PCC) for both UL and DL and may handle RRC and non-access stratum (NAS) related activities. The other serving cells are referred to as SCells, and each SCell may provide an individual secondary component carrier (SCC) for both UL and DL.

[0051]The PDSCH may carry user data and higher layer signaling to UEs 210. The physical downlink control channel (PDCCH) may carry information about the transport format and resource allocations related to the PDSCH channel, among other things. The PDCCH may also inform UEs 210 about the transport format, resource allocation, and hybrid automatic repeat request (HARQ) information related to the uplink shared channel. Typically, downlink scheduling (e.g., assigning control and shared channel resource blocks to UE 210-2 within a cell) may be performed at any of the RAN nodes 222 based on channel quality information fed back from any of UEs 210. The downlink resource assignment information may be sent on the PDCCH used for (e.g., assigned to) each of UEs 210.

[0052] The PDCCH uses control channel elements (CCEs) to convey the control information, wherein several CCEs (e.g., 6 or the like) may consists of a resource element groups (REGs), where a REG is defined as a physical resource block (PRB) in an OFDM symbol. Before being mapped to resource elements, the PDCCH complex-valued symbols may first be organized into quadruplets, which may then be permuted using a sub-block interleaver for rate matching, for example. Each PDCCH may be transmitted using one or more of these CCEs, where each CCE may correspond to nine sets of four physical resource elements known as REGs. Four quadrature phase shift keying (QPSK) symbols may be mapped to each REG. The PDCCH may be transmitted using one or more CCEs, depending on the size of the DCI and the channel condition. There may be four or more different PDCCH formats defined in LTE with different numbers of CCEs (e.g., aggregation level, L=1 , 2, 4, 8, or 26).

[0053] Some implementations may use concepts for resource allocation for control channel information that are an extension of the above-described concepts. For example, some implementations may utilize an extended (E)-PDCCH that uses PDSCH resources for control information transmission. The EPDCCH may be transmitted using one or more ECCEs. Similar to the above, each ECCE may correspond to nine sets of four physical resource elements known as an EREGs. An ECCE may have other numbers of EREGs in some situations.

[0054] The RAN nodes 222 may be configured to communicate with one another via interface 223. In implementations where the system is an LTE system, interface 223 may be an X2 interface. In NR systems, interface 223 may be an Xn interface. The X2 interface may be defined between two or more RAN nodes 222 (e.g., two or more eNBs I gNBs or a combination thereof) that connect to evolved packet core (EPC) or CN 230, 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 210 from an SeNB for user data; information of PDCP PDUs that were not delivered to a UE 210; 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.

[0055] As shown, RAN 220 may be connected (e.g., communicatively coupled) to CN 230. CN 230 may comprise a plurality of network elements 232, which are configured to offer various data and telecommunications services to customers/subscribers (e.g., users of UEs 210) who are connected to the CN 230 via the RAN 220. In some implementations, CN 230 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 230 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 abovedescribed 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 230 may be referred to as a network slice, and a logical instantiation of a portion of the CN 230 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.

[0056] As shown, CN 230, application servers 240, and external networks 250 may be connected to one another via interfaces 234, 236, and 238, which may include IP network interfaces. Application servers 240 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 230 (e.g., universal mobile telecommunications system packet services (UMTS PS) domain, LTE PS data services, etc.). Application servers 240 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 210 via the CN 230. Similarly, external networks 250 may include one or more of a variety of networks, including the Internet, thereby providing the mobile communication network and UEs 210 of the network access to a variety of additional services, information, interconnectivity, and other network features.

[0057] AI-MF servers 270 may include one or more servers, server devices, or network elements (e.g., VNFs) configured to send, receive, process, and/or store information. AI-MF servers 270 may communicate with CN 230 interface 272, which may comprise an IP interface. AI-MF servers 270 may support and provide functionality regarding model validity for Al-based UE positioning as described herein. For example, AI-MF servers 270 may enable NN models, for Al-based UE positioning, to be configured, labeled, and/or validated for use in one or more conditions or scenarios, and may include a model configuration function, a model selection function, and/or model inference function. In some implementations AI- MF servers 270 may also, or alternatively, perform one or more functions performed by a location management function (LMF) of CN 230.

[0058] Fig. 3 is a diagram of an example of UE 210, base stations 222, CN 230, and AI-MF servers 270 according to one or more implementations described herein. As shown, CN 230 may include access and mobility management function (AMF) 310, a location management function (LMF) 320, and/or one or more other types of functions or entities 330. Examples of such functions or entities may include a session management function (SMF), unified data management (UDM) function, a gateway mobile location center (GMLC), and more. AMF 310, LMF 320, etc., may be implemented by one or more servers in a centralized or distributed networking environment.

[0059] AMF 310 may communicate with base station 222 via an N2 interface and UE 210 via an N1 interface. AMF 310 may manage authentication, registration, and other functionalities relating to UEs 210 accessing a telecommunication mobile network. AMF 310 may also handle handovers, paging, and other functionality regarding the mobility and communications of UEs 210 with a telecommunication mobile network. AMF 310 may also provide security functionality for authenticating and authorizing UEs 210.

[0060] LMF 320 may provide positioning functionality to determine the geographic position of UE 210 based on downlink (DL) and uplink (UL) location measuring radio signals. LMF 320 may receive measurements and assistance information from base station 222 and UE 210 via AMF 310 and an NLs interface. LMF 320 may use the measurement and assistance information to compute the position of UE 210. A new NR positioning protocol A (NRPPa) protocol may be used to carry positioning information between base station 222 and LMF 320 over a next generation control plane interface (NG-C). LMF 320 may also configure UE 210 using LTE positioning protocol (LPP) via AMF 310, and base station 222 may configure UE 210 using RRC protocol over an LTE-Uu interface and/or an NR-Uu interface.

[0061] LMF 320 and/or AI-MF servers 270 may provide positioning assistance data to UE 210. Examples of such information may include information regarding signals to be measured (e.g., expected signal timing, signal coding, signal frequencies, signal Doppler, etc.), locations and identities of terrestrial transmitters (e.g., base stations 222, AP 216, etc.) and/or signal, timing and orbital information for non-terrestrial transmitters, such as satellites and satellite systems. Doing so may improve signal acquisition and measurement accuracy of UE 210 and, in some cases, enable UE 210 to better determine a current geographic location based on the location measurements. LMF 320 may implement a protocol to transfer Al ML information describe herein. The protocol may be part of a new NR positioning protocol A (NRPPa) protocol, another type of positioning protocol, or a newly developed positioning protocol.

[0062] LMF 320 and/or AI-MF servers 270 may provide UE 210 with information indicating locations and identities of terrestrial and/or non-terrestrial transmitters corresponding to a particular region and/or signaling information, such as transmission power, signal timing, etc. A UE 210 may obtain measurements of signal strengths (e.g., received signal strength indication (RSSI)) for signals received from such transceivers and/or may obtain a signal to noise ratio (S/N), a reference signal received power (RSRP), a reference signal received quality (RSRQ), a time of arrival (TOA), or a round trip signal propagation time (RTT) between UE 210 and one or more transceivers (e.g., base station 222, AP 216, etc.).

[0063] UE 210 may transfer these measurements to LMF 320 and/or AI-MF servers 270, to determine a location for UE 210, or in some implementations, may use these measurements together with assistance data (e.g., information indicating locations and identities of terrestrial and/or non-terrestrial transmitters) received from a location server (e.g., LMF 320 and/or AI-MF servers 270) or broadcast by base station 222 to determine a location for UE 210. UE 210 may measure a reference signal time difference (RSTD) between signals such as a position reference signal (PRS), cell specific reference signal (CRS), or tracking reference signal (TRS) transmitted by nearby pairs of transceivers. An RSTD measurement may provide the time of arrival difference between signals (e.g., TRS, CRS or PRS) received at UE 210 from two different transceivers. The UE 210 may return the measured RSTDs to LMF 320 and/or AI-MF servers 270, which may compute an estimated location for UE 210 based on known locations and known signal timing for the measured transceivers.

[0064] LMF 320 and/or AI-MF servers 270 may support and provide functionality regarding model validity for Al-based UE positioning. In some implementations, some or all of the functionality described herein as being performed by LMF 320 and/or AI-MF servers 270 may be performed by one or more other types of functions or entities, including base station 222, application servers 240, and/or another function or entity of CN 230.

[0065] Fig. 4 is a diagram of an example of AI/ML functionality and models 400 according to one or more implementations described herein. As shown, example 400 may include data collection function 410, model training function 420, model inference function 430, and actor 440. In some implementations, AI/ML functionality and models 400 may be implemented by one or more UEs 210, one or more base station 222, and/or one or more elements of CN 230, such as LMF 320. As described herein, AI/ML functionality and models 400 may be implemented to enhance throughput, robustness, accuracy, reliability, and positioning accuracy for different scenarios, such as those with heavy non-line- of-sight (NLOS) conditions.

[0066] Data collection function 410 may provide input data to model training function 420 and model inference function 430. AI/ML algorithm specific data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) may not be carried out by data collection function 410. Examples of input data may include measurements from UEs 210 or different network entities, feedback from actor 440, output from an AI/ML model. An AI/ML model may include a framework of features, vectors, and/or functions capable of evaluating input data and producing an output. In some implementations, an AI/ML model may include a trained neural network.

[0067] Training data may include input for the AI/ML model training function.

Inference data may include input for model inference function 430. Model training function 420 may perform AI/ML model training, validation, and testing which may generate model performance metrics as part of the model testing procedure. Model training function 420 may also be responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on training data delivered by a data collection function 410. A model deployment/update may be used to initially deploy a trained, validated, and tested AI/ML model to model inference function 430 or to deliver an updated model to model inference function 430.

[0068] Model inference function 430 may provide AI/ML model inference output (e.g., predictions or decisions). Model inference function 430 may provide model performance feedback to model training function 420 when applicable. Model inference function 430 is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on inference data delivered by data collection function 410. The inference output of the AI/ML model produced by model inference function 430. Details of inference output may be use case specific. Model performance feedback may be used for monitoring the performance of an AI/ML model, when available. Actor function 440 may receive output from the model inference function 430 and triggers or performs corresponding actions. Actor function 440 may trigger actions directed to other entities or to itself. The feedback information may be used to derive training data, inference data or to monitor the performance of the AI/ML model and its impact to the network through updating of performance indicators and performance counters.

[0069] Fig. 5 is a diagram of an example of a neural network (NN) 500 according to one or more implementations described herein. As shown, NN 500 may include nodes arranged in different layers, such as an input layer 510 of nodes, multiple hidden or intermediary layers 520 of nodes, and an output layer 530 of nodes. In some implementations, NN 500 may be an example of, or a portion of, model training function 420, an AI/ML model, model inference function 430, and/or actor function 440. For example, NN 500 may be trained on training data from data collection function 410, deployed by model training function 420 as an AI/ML model, and used by model inference function 430 to produce feedback for model training function 420 and an inference output for actor function 440.

[0070] Example NN 500 may include a number N of inputs introduced to four input nodes [N, 4] of input layer 510. This may include processing or encoding input data into a form, shape, vector, or data structure, that is receivable by the NN. The four input nodes may process the inputs to produce a first weight (Wi) that the four input nodes provide to the five nodes [4;5] of a first hidden layer. The five nodes of the first hidden layer may use a first function (fi) to process the inputs to produce a second weight (W2) that the five nodes of the first hidden layer may provide to the five nodes [5;5] of a second hidden layer. The five nodes of the second layer may use a second function (f2) to process the inputs to produce a third weight (W3) that the five nodes of the second hidden layer may provide to the three nodes [5;3] of output layer 530. The nodes of output layer 530 may each process the inputs received and produce an output. This may include converting or unencoding output data from a form, shape, vector, or data structure, that may be used by a subsequent algorithm, process, or procedure.

[0071] Artificial intelligence (Al) may involve the combination of computer science and datasets to enable problem-solving. Al may encompass machine learning (ML) and deep learning (DL), which are frequently mentioned in conjunction with Al. These disciplines are comprised of Al algorithms which seek to create expert systems which make predictions or classifications based on input data. ML, DL, and neural networks (NNs) are sub-fields of AL However, NNs are actually a subfield of ML, and DL is a sub-field of NNs. The way in which DL and ML differ is in how each algorithm learns. Deep ML may use labeled datasets (also known as supervised learning) to inform its algorithm, but it does not necessarily require a labeled dataset. DL may ingest unstructured data in its raw form (e.g., text or images), and it can automatically determine the set of features which distinguish different categories of data from one another. This may eliminate some of the human intervention required and enable use of larger data sets. DL may be viewed, in a sense, as scalable ML.

[0072] NNs, or artificial NNs (ANNs), may comprise logically interconnected nodes arranged in node layers. There may be an input layer, one or more hidden or intermediate layers, and an output layer. Each node, or artificial neuron, may connect to another and has an associated weight and threshold. If the output of any individual node is above the specified threshold value, that node is activated, sending data to the next layer of the network. Otherwise, no data may be passed along to the next layer of the network by that node. The “deep” in deep learning is just referring to the number of layers in a NN. A NN that consists of more than three layers — which would be inclusive of the input and the output — can be considered a deep learning algorithm or a deep NN. A neural network that only has three layers is just a basic NN.

[0073] Feedforward NNs, or multi-layer perceptrons (MLPs), may include an input layer, one or more a hidden layers, and an output layer. While these NNs are also referred to as MLPs, they may comprise sigmoid neurons, not perceptrons, as some real-world problems may nonlinear. Data is usually fed into these models to train them, and they may function as a foundation for computer vision, natural language processing, and other neural networks. Recurrent neural networks (RNNs) are identified by feedback loops.

[0074] Convolutional neural networks (CNNs) may be similar to feedforward NNs, but may be used for image recognition, pattern recognition, and/or computer vision. These NN may harness principles from linear algebra, particularly matrix multiplication, to identify patterns within an image. Linear regression analysis, for example, may be used to predict a value of a variable based on a value of another variable. This form of analysis may estimate coefficients of a linear equation, involving one or more independent variables that best predict the value of the dependent variable. Linear regression may fit a straight line or surface that minimizes discrepancies between a predicted value and an actual value. These learning algorithms may be leveraged when using time-series data to make predictions about future outcomes.

[0075] Fig. 6 is a diagram of an example 600 of functions and corresponding devices and entities according to one or more implementations described herein. As shown, example 600 includes model configuration function 610, model selection function 620, and model inference function 630 (referred to herein collectively as functions 610-630). Example 600 also includes UE 210, base station 222, LMF 320, and AI-MF server 270.

[0076] Example 600 provides an overview of the functions described herein and the devices, and combinations of devices, that may perform each function. That is, any of functions 610-630 may be performed by any combination of the depicted devices. For example, in some implementations, functions 610-630 may be performed by a combination of UE 210 and LMF 320. In another implementation, functions 610-630 may be performed by a combination of UE 210 and AI-MF server 270. In another implementation, functions 610-630 may be performed by base station 222 and LMF 320 and/or AI-MF servers 270. In yet another implementation, functions 610-630 may be performed by a combination of UE 210, base station 222, LMF 320, and AI-MF server 270.

[0077] Model configuration function 610 may include a process by which one or more models is created, configured, trained, and/or applied to a new scenario or condition. In some implementations, model configuration may include creating a NN model to be applied by UE 210, base station 222, under certain conditions, in a certain geographic location or area, etc. Model configuration may involve the application of training data to training model training function 420, updating an existing model based on model performance feedback, and/or specifying an existing model for application to a new environment, condition, or scenario. Model configuration may include associating a NN model with one or more labels, conditions, or characteristics for application of the NN model. Examples of such conditions or characteristics may include an estimated geographic location of UE 210, a cell ID, capabilities of the NN model itself, device capability information (e.g., UE capability information), assistance information, one or more reference signal configurations, a date, a day, a time, and so on. Associating a NN model with one or more labels may, in effect, identify the NN model as relevant to a current condition or scenario. Some or all of model configuration function 610 may be performed by UE 210, base station 222, LMF 320, AI-MF server 270, and/or any combination thereof.

[0078] Model selection function 620 may include a process by which a model is selected for use. Model selection may be based on one or more labels associated with the model. As described herein, a label may include a characteristic, condition, or scenario pertaining to UE 210. Examples of a label may include a capability of UE 210, a location of UE 210, a current cell of UE 210, a measured reference signal or signal strength, and/or one or more other conditions relating to UE 210. As model configuration function 610 may include associating a model with one or more labels, model selection function 620 may include a process by which a current condition is matched to the one or more labels of a particular model. Some or all of model selection function 620 may be performed by UE 210, base station 222, LMF 320, AI-MF server 270, and/or any combination thereof.

[0079] Model inference function 630 may include a process by which a selected NN model used to determine a location of UE 210. Input data to the selected NN model may include an estimated geographic location of UE 210, a cell ID where UE 210 is located, one or more signal strengths measured by UE 210, assistance information, and more. In some implementations, the location of UE 210 may be determined based solely on an outcome of the NN model. In other implementations, the output of the NN model may be part of a data set used determine the location of UE 210. That is, the output of the NN model may be used as an input to another location determination function that uses other information as inputs as well. Execution of model inference function 630 may result, or contributed to, in a more precise or accurate location of UE 210 that would be otherwise possible due to the NN model applied. As show, some or all of model inference function 630 may be performed by UE 210, base station 222, LMF 320, AI-MF server 270, and/or any combination thereof.

[0080] Fig. 7 is a diagram of an example table 700 of characteristics of Al-based UE positioning according to one or more implementations described herein. As shown, table 700 includes case 1 A, case 1 B, case 2A, case 2B, case 3A, and case 3B (collectively referred to herein as “cases 1 -3”). Cases 1 -3 include various examples devices and entities (e.g., UE 210, base station 222, LMF 320, etc.) that may use different NN models, inputs, outputs, and other types of information, to implement Al-based positioning in accordance with the techniques described herein. In some implementations, an AI-MF server 270 may be implemented, or involved, instead of one or more of UE 210, base station 222, or LMF 320. As such, not only are cases 1 -3 non-limiting examples of one or more of the techniques described herein, but cases 1-3 exemplify the broad scope and implementation variability of implementations of techniques described herein.

[0081] Table 700 includes columns entitled positioning type, assistance type, model, and AI/ML type. The positioning type may refer to a device or entity determining a location of UE 210. As shown, cases 1A and 1 B may be UE-based scenarios, in which UE 210 may determine the position or location of UE 210. By contrast, cases 2A, 2B, 3A, and 3B may be LMF-based scenarios, in which LMF 320 may determine the location of UE 210.

[0082] Assistance type may refer to devices or entities that may provide the positioning type device (e.g., UE 210 for UE-based scenarios and LMF 320 for LMF-based scenarios) with information to assist with determining the location of UE 210. An assistance type may not be applicable to cases 1 A and 1 B since UE 210 determines the location of UE 210 in cases 1A and 1 B. An assistance type of cases 2A, 2B, however, may include assistance information from UE 210 and an assistance type of cases 3A, and 3B, may include assistance information from NG-RAN/base-station 222. For example, UE 210 may provide location assistance information to assist LMF 320, and LMF 320 may use the information as an input to a NN model implemented by LMF 320 or as a parameter of another type of position procedure implemented by LMF 320. Model may refer to a device or entity implementing a NN model to enable the determination or inference the location of UE 210. As shown, UE 210 my implement a NN model in cases 1 A, 1 B, and 2A. LMF 320 may implement a NN model in cases 2B and 3B, and base station 222 may implement a NN model in case 3A. In some implementations, different entities may implement a NN model in different cases. [0083] AI/ML type may refer to whether the location of UE 210 is directly determined by the output of the NN model (AI/ML direct) or whether the output of the NN model is used to assist in determining the location of UE 210 (AI/ML assist). In an AI/ML assist scenario, the output of the NN may be used as an input or parameter of another positioning procedure. An example of such a procedure may include a location procedure designed to determine whether UE 210 is in a line-of-sight (LOS) or non-line-of-sight (NLOS) position. As shown, cases 1 A, 2B, and 3B may include implementations where the position or location of UE 210 is determined directly by the output of the NN model being used, while the output of the NN model being used in cases 1 B, 2A, and 3A may be used to assist in the determination of the position or location of UE 210 (e.g., by using the output in an additional algorithm, operation, process, etc.).

[0084] In some implementations, one or more of the techniques described herein may include an additional or alternative case than those shown in Fig. 7. For example, base station 222 may perform one or more functions of UE 210; AI-MF server 270 may perform one or more functions of LMF 320; and so on. Additionally, some implementations, such as in cases 1 A, 1 B, and/or 2A, NN model configuration and selection may be performed by LMF 320 and/or AI-MF server 270, and model inference may be performed by UE 210. In such implementations, LMF 320 and/or AI-MF server 270 may send a validity label to UE 210, and UE 210 may use the validity label to select an appropriate NN model. In other implementations of cases 1 A, 1 B, and/or 2A, UE 210 may be preconfigured with validity labels (e.g., have internal policies, rules, and parameters) such as area, zone, condition, time, etc., for selecting appropriate NN models.

[0085] In some implementations, such as in cases 2B and/or 3B, UE 210 and/or base station 222 may send assistance information (e.g., Doppler information) to LMF 320 and/or AI-MF server 270 to enable validation and/or selection of an appropriate model. In other implementations of cases 2B and/or 3B, LMF 320 and/or AI-MF server 270 may be preconfigured with internal algorithms, rules, and parameters for selection of appropriate models in a given scenario or set of conditions. In some implementations, such as in case 3A, LMF 320 and/or AI-MF server 270 may send validity labels to base station 222, and base station 222 may use the labels to select appropriate NN models. In other implementations of cases 3A, base station 222 may be preconfigured with internal algorithms, rules, and parameters for selection of appropriate models in a given scenario or set of conditions.

[0086] As any combination of functions 610, 620, and/or 630 may be performed by any combination of UE 210, base station 222, LMF 320, and AI-MF server 270, one or more of the examples described herein may refer to an “entity” that performs one or more of functions 610-610. Fig. 8, for example, refers to model configuration and selection entity 810 and model inference entity 820; Fig. 11 refers to model configuration entity 1 1 10 and model selection and inference entity 1120; and Fig. 13 refers to model configuration entity 1310 and model selection entity 1320. “Entity” may be interpreted as the device, or combination of devices” that performs the corresponding function(s) 610, 620, and/or 630 as described herein.

[0087] Fig. 8 is a diagram of example process 800 for obtaining a valid NN model based on model validity data according to one or more implementations described herein. Process 800 may be performed by model configuration and selection entity 810 and model inference entity 820. Model configuration and selection entity 810 may include a system or device that performs model configuration function 610 and model selection function 620 while model inference entity 820 may include a system or device that performs model inference function 630, as described above with reference to Fig. 6. As such, each of model configuration and selection entity 810 and model inference entity 820 may include one, or any combination of, UE 210, base station 222, AI-MF server 270, and/or LMF 320.

[0088] Additionally, example process 800 may include one or more fewer, additional, differently ordered and/or arranged operations than those shown in Fig. 8. In some implementations, some or all of the operations of example process 800 may be performed independently, successively, simultaneously, etc., of one or more of the other operations of example process 800. As such, techniques described herein are not limited to a number, sequence, arrangement, timing, etc., of the operations or process depicted in Fig. 8. Indeed, the techniques described herein may include additional and alternative versions of example process 800. [0089] As show, process 800 may include model configuration and selection entity 810 receiving assistance information from model inference entity 820 (at 830). For example, LMF 320 or AI-MF server 270 may receive assistance information from UE 210 and/or base station 222. Assistance information, as described herein, may include one or more types of information that may be relevant to using a NN model to determine or infer a position (e.g., of UE 210). Examples of such information may include reference signal information, reference signal measurement information, and other types of positioning information (e.g., an SRS, a PRS, a RSSI, a signal-to-noise ratio, an RSRP, an RSRQ, a signal TOA, a RTT, a CRS, a TRS, Doppler information, etc.). In some implementations, assistance information may include UE and/or base station capability information.

[0090] Model configuration and selection entity 810 may determine a NN model based on the assistance information and model validity labels (at 840). For example, LMF 320 may determine an appropriate NN model to use to determine a position of UE 210 based on the assistance information and model validity labels. For example, model configuration and selection entity 810 may include, store, or otherwise have access to one or more NN models for determining a position of UE 210.

[0091] The conditions and/or circumstances for using each NN model may be based on, or defined by, model validity labels associated with the NN model. Examples of a validity label may include a scenario label, a time interval label, a geographic location label, and/or a network zone label, and more. In some implementations, a validity label may include one or more types or combinations of assistance information, one or more values or value ranges of one or more types or combinations of assistance information, and more. Model configuration and selection entity 810 may determine which NN model is appropriate by comparing some or all of the assistance information to the model validity labels of the NN models. Upon determining that the assistance information satisfies, maps, or matches the model validity labels of a particular NN model, model configuration and selection entity 810 may select the NN model.

[0092] Model configuration and selection entity 810 may send a selected NN model to model inference entity 820 (at 850). For example, upon identifying or selecting an appropriate NN model for a given condition or scenario, LMF 320 may send the NN model to UE 210 and/or base station 222. In some implementations, model configuration and selection entity 810 may send the actual NN model that is selected. In other implementations, model configuration and selection entity 810 may send a NN identifier, and model inference entity 820 may select the NN model based on the NN identifier and may send appropriate configuration information for the selected model. For example, one option is if an inference entity selects a model, the inference entity may send information to the configuration entity about the selection, and the configuration entity may return model-specific configuration information to the inference entity.

[0093] Model inference entity 830 may receive the NN model and may use the NN model to generate position inference information based on the NN model (at 860). For example, UE 210 and/or base station 222 may receive a NN model from LMF 320 and may use the NN model to produce position inference information. As described herein, position inference information may include output information of a NN model. In some implementation, the position inference information may include the estimated or actual location of UE 210. In other implementations, the position inference information may be used in an additional, or subsequent, location determination algorithm or procedure along with one or more other types of information. For example, the position inference information may be used as part of a traditional positioning algorithm..

[0094] Fig. 9 is a diagram of an example process 900 for determining a NN model based on assistance information and model validity labels according to one or more implementations described herein. Example process 900 may be performed by model configuration and selection entity 810. As such, process 1200 may be performed by any one, or combination, of UE 210 base station 222, AI-MF server 270 and/or LMF 320. Additionally, example process 900 may include one or more fewer, additional, differently ordered and/or arranged operations or datasets than those shown in Fig. 9.

[0095] As shown, model configuration and selection entity 810 may receive assistance information (at 9.1 ). The assistance information may include characteristics (e.g., C_1 , C_2, . . ., C_N (where N is greater than or equal to 3). Model configuration and selection entity 810 may select and/or configure the NN model with one or more validity labels (at 9.2). The NN model and/or the validity labels may be determined based on the assistance information characteristics and one or more pre-configured network or device policies, rules, and/or parameters for enabling inference entities 820 to implement NN models. The NN model may include a NN identifier (e.g., NN_1 ) and one or more validity labels (e.g., VL_1 .1 , VL_2, . . ., VL_1 .N (where N is greater than or equal to 3), which may enable inference entity 820 to determine which NN model to apply under conditions described by the validity labels. Model configuration and selection entity 810 may send the NN model to inference entity 820 (at 9.3).

[0096] Fig. 10 is a diagram of an example table 1000 of validity labels for NN models according to one or more implementations described herein. Example table 1000 may include a data structure used by UE 210, base station 222, AI-MF server 270, and/or LMF 320, in one or more of the processes or techniques described herein. As shown, columns of example table 1000 may include NN identifiers NN_1 , NN_2, NN_3, . . ., NN_Q (where Q is greater than or equal to 4). Rows of example table 1000 may include validity labels (VLs) associated with an NN model identifier. For example, NN_1 may include, or be logically associated with, VL_1 .1 , VL_1 .2, . . ., VL_1 .N (where Q is greater than or equal to 3).

[0097] One validity label may include a particular characteristic or condition for using a corresponding NN model. Collectively, a set of validity labels may include the combined characteristics or conditions (e.g., the scenario) for using the corresponding NN model. In some implementations, a NN model may be validated by satisfying one validity label, a threshold number of validity labels (e.g., two or more), or all the validity labels of a particular NN model. The conditions for validating a NN model (e.g., how many validity labels are to be satisfied as a prerequisite for selection and use) may be the same for all NN models, specific to a NN class of the NN model, or specific to the NN model (e.g., regardless of NN class). In some implementations, a NN model may be validated and selected based on which the NN model is the most satisfied by assistance information.

[0098] Fig. 11 is a diagram of an example process 1 100 for selecting a NN model based on model validity testing according to one or more implementations described herein. Process 1 100 may be performed by model configuration entity 1 1 10 and model selection entity 1120. Each of, or both, model configuration entity 11 10 and model selection entity 1 120 may include any combination of UE 210, base station 222, AI-MF server 270, and/or LMF 320. Model configuration entity 11 10 may include a system or device that performs model configuration function 610 while model selection 1 120 may include a system or device that performs and model selection function 620 as described above with reference to Fig. 6. In some implementations, model configuration entity 1 1 10 or model selection entity 1 120 may also perform the operations of model inference function 630. In some implementations, the operations of model inference function 630 may be performed by a different entity.

[0099] Additionally, example process 1100 may include one or more fewer, additional, differently ordered and/or arranged operations than those shown in Fig. 11 . In some implementations, some or all of the operations of example process 1 100 may be performed independently, successively, simultaneously, etc., of one or more of the other operations of example process 1 100. As such, techniques described herein are not limited to a number, sequence, arrangement, timing, etc., of the operations or process depicted in Fig. 11 . Indeed, the techniques described herein may include additional and alternative versions of example process 1100.

[00100] As shown, model selection entity 1 120 may send model capability data of one or more NN models to model configuration entity 1110 (at 1130). For example, UE 210 may send model capability data to LMF 320. The model capability data may include information describing or indicating capabilities of a NN model that model selection entity 1 120 has selected or is otherwise to use for determining a location of UE 210.

[00101] Model configuration entity 1 110 may send model validity data to model selection entity 1 120 (at 1 140). For example, LMF 320 may send model validity data to UE 210. Model validity data, as described herein, may include information used to determine or verify whether one or more NN models is appropriate for a given scenario condition or scenario. Model validity data may include model input data, model performance requirements, model condition requirements, and/or one or more other types of information. Model validity data may also be referred to herein as model testing data, validity testing data, and the like. Model validity data may include model validity labels as described above with reference to previous Figures.

[00102] Model selection entity 1120 may determine model validity based on the model validity data (at 1150). For example, UE 210 may determine model validity based model validity data received from LMF 320. Model validity may mean that a NN model has been determined to be appropriate or valid for a given scenario or condition. In some implementations, model selection entity 1120 may determine model validity by applying input data to the NN model to generate output data and verifying whether the output data is consistent with the model performance requirements (e.g., within a threshold accuracy, latency, etc.) per the model validity data received. The model input data may be from the model validity data received from model configuration entity 1110 and/or based on information measured or stored by model selection entity 1120. Model selection entity 1120 may also, or alternatively, determine model validity by verifying that that one or more other types of conditions or requirements, specified by the model validity data, are satisfied. In some implementations, model selection entity 1120 may select a NN model for use when the model is determined to be valid (at 1160). In other implementations, model selection entity 1120 may mark or flag the NN model as valid for later use.

[00103] Model selection entity 1120 may provide model configuration entity 1110 with a model validity response (1170). For example, UE 210 may generate and communicate model validity response to LMF 320. A model validity response may include an indication of the results of determining or testing the NN model based on the model validity data, which may include an indication of the tested NN model(s) being valid or invalid. In some implementation, such as when model selection entity 1120 tests multiple NN models, model validity response information may include performance or validity metrics for each NN model, and model configuration entity 1 110 may select, based on the metrics, a NN model and indicate and configure the selected NN model for model selection entity 1120 for use (at 1180).

[00104] Fig. 12 is a diagram of an example of a process 1200 for model selection according to one or more implementations described herein. Example process 1200 may be performed by model selection entity 1110 (now shown). As such, process 1200 may be performed by any one, or combination, of UE 210 base station 222, AI-MF server 270 and/or LMF 320. Additionally, example process 1200 may include one or more fewer, additional, differently ordered and/or arranged operations or datasets than those shown in Fig. 12.

[00105] Model selection entity 1110 may receive validity data and test one or more NN models based on the validity data (at 12.1). As shown, model selection entity 1110 may receive validity data, represented as VD 2.1 , VD 2.2, VD 3.1 , VD_1 .S, VD 3.2, and VD 3.3. The validity data may include information for determining whether one or more NN models are appropriate for use. The validity data may include NN model inputs to be used for testing, acceptable NN model outputs, and/or other conditions or scenarios for using a NN model. In some implementations, model selection entity 1110 may test the validity of a NN model based solely on validity data received from model configuration entity 1110 (e.g., without the use of validity labels).

[00106] In other implementations, as validity labels may be used to indicate when a NN model may be used, a NN model may be valid when the conditions indicated by the validity labels of the NN model are satisfied. Example 12 includes NN models represented as NN_1 , NN_2, NN_3, . . ., NN-Q (where Q is greater than or equal to 1). Each NN model includes validity labels. For example, NN_1 includes VL_1 .1 , VL_1 .2, and VL_1 .3. Model selection entity 1110 may compare the validity data and/or the results of applying the validity test data to the validity labels of one or more NN models to determine which NN model is valid for use.

[00107] As shown, while the test data applies to some of the validity labels of some of the NN models, model selection entity 11 10 may select NN_3 (at 12.2) since NN_3 is the only NN model with conditions completely satisfied by the test data. In some implementations, a NN model may be validated and selected when all of the validity data corresponds the validity labels of a NN model. After selecting NN_3, model selection entity 1110 may send a notification or indication of the selection to model configuration entity 11 10 (at 12.3).

[00108] Fig. 13 is a diagram of an example process 1300 for selecting a NN model based on model classes according to one or more implementations described herein. Process 1300 may be performed by model configuration entity 1310 and model selection entity 1320. Each of, or both, model configuration entity 1310 and model selection entity 1320 may include any combination of UE 210, base station 222, AI-MF server 270, and/or LMF 320. Model configuration entity 1310 may include a system or device that performs model configuration function 610 while model selection 1320 may include a system or device that performs and model selection function 620 as described above with reference to Fig. 6. In some implementations, model configuration entity 1310 or model selection entity 1320 may also perform the operations of model inference function 630. In some implementations, the operations of model inference function 630 may be performed by a different entity.

[00109] Additionally, example process 1300 may include one or more fewer, additional, differently ordered and/or arranged operations than those shown in Fig. 13. In some implementations, some or all of the operations of example process 1300 may be performed independently, successively, simultaneously, etc., of one or more of the other operations of example process 1300. As such, techniques described herein are not limited to a number, sequence, arrangement, timing, etc., of the operations or process depicted in Fig. 13. Indeed, the techniques described herein may include additional and alternative versions of example process 1300.

[00110] As shown, model configuration entity 1310 may provide model selection entity 1320 model validity data for multiple NN model classes (at 1330). A NN model class, as described herein, may include a type or category of NN model. For example, LMF 320 may provide UE 210 an indication of a NN model class that LMF 320 may use for monitoring a location of UE 210 (at 1330). LMF 320 may also send UE 210 validity data (e.g., validity testing data) for each model of the NN class. NN models of a NN model class may be associated with one another in one or more ways, including a NN model class identifier, a NN model functionality, a NN model label, a NN model requirement, and/or a type of set of validity data.

[00111] Model selection entity 1320 may receive the validity data and select a NN model for each NN model class (at 1340). For example, UE 210 may receive the validity data, determine the number of validity data sets contained therein, determine a NN model class associated with each set of validity data, and map or determine one or more NN models for each set of validity data. The NN model classes and identified NN models may each correspond to a different type or scenario of Al-based positioning. In some implementations, model selection entity 1320 may determine or verify the validity of each NN model prior to selection. As described above, doing so may include applying an appropriate set of validity data to an appropriate type or class of NN model. Additionally, or alternatively, model selection entity 1320 may select NN models based on a one- to-many or a many-to-one mapping between the sets of model validity data and NN model classes.

[00112] Model selection entity 1320 may communicate the selected models to model configurate entity 1310 (at 1350). By doing so, model configuration entity 1310 (e.g., LMF 320) may be aware of the NN models that model selection entity 1320 (e.g., UE 210). As such, model configuration entity 1310 may periodically cause model selection entity 1310 or model inference entity (not shown) to switch between NN models. In some implementations, model selection entity 130 may indicate the selected NN models by providing a mapping of validity data sets or NN model classes to the NN models selected. In such implementations, the mapping may include a one-to-many or a many-to-one mapping between the sets of model validity data and NN model classes. The mapping may also include an indication of which NN models are to be ranked or prioritized over other NN models, which NN models are to be used under certain circumstances or conditions, etc. As such, model configuration entity 1310 may periodically cause model selection entity 1320 to switch from one of the selected NN models to another NN model (e.g., as time, conditions, or scenarios change) (at 1360).

[00113] Fig. 14 is a diagram of example data structures 1400 for NN model classes and validity labels according to one or more implementations described herein. As shown, example data structures 1400 may include data structure 1410, data structure 1420, and data structure 1430. Data structure 1410 may include NN models arranged by NN model class. For example, NN model class, corresponding to the NN model class identifier NN_CLASS_C1 , may include NN models corresponding to the NN model identifiers C1_NN_1 , C1_NN_2, . . ., C1 NN N (where N is greater than or equal to 2). The other NN model classes and corresponding NN models are represented similarly.

[00114] Data structure 1420 may include the validity labels of each NN model of NN model class NN_CLASS_C1 . For example, NN model of the NN model identifier C1_NN_1 may be associated with the validity labels VL_1 .1 , VL_1 .2, . . VL_1 .R (where R is greater than or equal to 3). The NN model identifiers C1_NN_2 and C1_NN_N are also represented with corresponding validity labels. Similarly, data structure 1430 may include the validity labels of each NN model of NN model class NN_CLASS_C2. For instance, NN model of the NN model identifier C2 NN 1 may be associated with the validity labels VL_1 .1 , VL_1 .2, . . ., VL_1 .U (where U is greater than or equal to 3). The NN models of identifiers C2 NN 2 and C2_NN_N are represented with validity labels similarly. Accordingly, the techniques described herein may include model configuration entity 1310, model selection entity 1320, and/or model inference entity 1320 organizing and maintaining NN models classes, NN models, and validity labels of NN models.

[00115] Fig. 15 is a diagram of example process 1500 for selecting a NN model based on validity data received for NN model classes according to one or more implementations described herein. As shown, example process 1500 may include validity data 1510 arranged according to NN model classes, represented by NN model identifiers NN_CLASS_C1 , NN_CLASS_C2, etc. Further, each NN model class of validity data 1510 may be associated with one or more types of validity data (VD), represented by VD_1 .1 , VD_1 .2, VD_1 .R, and so on.

[00116] Model selection entity 1320 (not shown) may receive validity data 1510 and select one or more NN models based on validity data 1510. For example, model selection entity 1320 may compare or map NN model classes of validity data 1510 to NN models of different NN model classes 1520 and 1530 (at 15.1 ). More particularly, model selection entity 1320 may compare or map types of validity data (VD) for a given NN model class to validity labels of NN models of each class. As shown, model selection entity 1320 may determine that the validity data received for NN_CLASS_C1 corresponds to the validity labels of NN_CLASS_C1 (at 15.2) and may therefore select the NN model of C1_NN_1 for Al-based positioning purposes (at 15.3). By contrast, model selection entity 1320 may determine that the validity data received for NN_CLASS_C2 does not corresponds to the validity labels of NN CLASS C2 (at 15.4) and therefore may not select the NN model of C1_NN_2 for Al-based positioning purposes.

[00117] Fig. 16 is a diagram of example process 1600 for selecting multiple NN models based on validity data received for NN model classes according to one or more implementations described herein. As shown, example process 1600 may include validity data 1610 arranged according to NN model classes, represented by NN model identifiers NN_CLASS_C1 , NN_CLASS_C2, etc. Further, each NN model class of validity data 1610 may be associated with one or more types of validity data (VD), represented by VD_1 .1 , VD_1 .2, VD_1 .R, and so on.

[00118] Model selection entity 1320 (not shown) may receive validity data 1610 and select one or more NN models based on validity data 1610. For example, model selection entity 1320 may compare or map NN model classes of validity data 1610 to NN models of different NN model classes 1620 (at 16.1). More particularly, model selection entity 1320 may compare or map types of validity data (VD) for a given NN model class to validity labels of NN models of each class. As shown, model selection entity 1320 may determine that the validity data received for NN_CLASS_C1 corresponds to the validity labels of NN_CLASS_C1 (at 16.2) and may therefore select the NN model of C1_NN_1 for Al-based positioning purposes (at 16.3).

[00119] Model selection entity 1320 may compare or map NN model classes of validity data 1610 to NN models of other NN model classes 1630 (at 16.4). As shown, model selection entity 1320 may determine that the validity data received for NN_CLASS_C2 corresponds to the validity labels of NN_CLASS_C2 (at 16.5) and may therefore select the NN model of C1_NN_2 for Al-based positioning purposes (at 16.6). Accordingly, validity data for multiple NN model classes may be mapped to multiple NN validity models and selected for use.

[00120] Fig. 17 is a diagram of an example process 1700 for model validation according to one or more implementations described herein. As shown, process 1700 is described below as being performed by UE 210 and LMF 320. However, one or more other devices may perform some or all of process 1700. For example, in some implementations, process 1700 may include base station 222 instead of UE 210, and additionally or alternatively, LMF 320 may be replaced by AI-MF server 270. Additionally, example process 1700 may include one or more fewer, additional, differently ordered and/or arranged operations than those shown in Fig. 17. In some implementations, some or all of the operations of example process 1700 may be performed independently, successively, simultaneously, etc., of one or more of the other operations of example process 1700.

[00121] As shown, process 1700 may include sending model capability data (block 1710). For example, UE 210 or base station 222 may send model capability data to LMF 320 and/or AI-MF server 270. Model capability data may include information describing a capability of an inference entity (e.g., UE 210 or base station 222) to use one or more types of NN models to determine a location of UE 210. Model capability data may include a number of NN models and information about the characteristics of each NN model, such a target accuracy, latency, complexity, size, etc. A target accuracy may refer to how accurate a NN model is in determining the location of UE 210 and may be represented as an error distribution or mean variance between the inferred location and the actual location of UE 210.

[00122] A latency may refer to a model inference latency, which may be an amount of time typically involved in using the NN model to determine the location of a UE 210. Model capability data may also include a signaling type, such as a reference signal type or configuration, for each NN model and an indication about the training of each NN model (e.g., whether each NN model is already trained, trained offline, trained online, etc.). Model capability data may also include a model type for each NN model. The model type may indicate one or more characteristics, such as input data to may be provided to a NN model, how resource-intensive a NN model may be, and the types and quantity of output data produced by a NN model.

[00123] Process 1700 may include sending model conditions and requirements data (block 1720). For example, UE 210 may send model conditions and requirements data to LMF 320. Model and requirements data may include conditions that UE 210 may support while operating NN models. Examples of model conditions data may include assistance signaling received by UE 210, reference signaling configurations supported by UE 210, and a type of training required by each NN model (e.g., whether the model is trained online versus offline). Additional examples of model and requirements data may include information, such as the type, quantity, quality, and frequency of NN model input data, one or more validity labels associated with each NN model, and an indication of whether each model is supervised, partially supervised, or unsupervised (e.g., by LMF 320). [00124] Process 1700 may include determining model configuration and validity data (block 1730). For example, LMF 320 may determine a model configuration and validity data for the NN models indicated by UE 210. LMF 320 may do so by matching the model capability data and the model conditions and requirements data to NN model data sets stored locally or otherwise available to LMF 320. In some implementations, LMF 320 may have a data repository that includes information about NN models configured to help determine the location of UE 210. Each NN model may be associated with configuration information indicating various characteristics about the NN model. Examples of such information may include a model identifier (ID), an index of the capabilities of each NN model, and reference signal configurations supported by each NN model. Additional examples of such information may include whether the NN model is trained online or offline, a schedule for updating the NN model with additional training data, and assistance data that may be used each NN model.

[00125] Process 1700 may include sending model configuration and validity data (block 1740). For example, LMF 320 may send model configuration and validity data to UE 210. The model configuration and validity data may indicate one or more NN models to be tested by UE 210, configurations parameters for configuring each NN model, and validity data for testing each NN model. The NN models, the configuration parameters, and validity data may be selected to enable UE 210 to run the NN models under test conditions to verify or validate that the NN models operate as expected. Thus, the NN models, the configuration parameters, and validity data may correspond to different conditions or scenarios in which the location of UE 210 may be determined (or facilitated) by an appropriate NN model.

[00126] Process 1700 may include testing the NN models based on configuration and testing data (at 1750). For example, UE 210 may test the NN models indicated by LMF 320 in accordance with the configuration and testing data provided by LMF 320. By evaluating whether the NN models operated as intended and produced acceptable outputs, UE 210 may determine whether each NN model is valid (i.e. , appropriate for the set of conditions for which the NN model was specified) and select the valid NN models. In some implementations, UE 210 may instead provide feedback information to LMF 320. Process 1700 may include sending feedback information to LMF 320 (block 1760). For example, UE 210 may report the results of the validity testing to LMF 320. In response, LMF 320 may determine which models were valid and select the valid NN models. Process 1700 may continue by LMF 320 providing UE 210 with an indication of the valid NN models (block 1770), which may cause UE 210 to select the indicated NN models for use.

[00127] Fig. 18 is a diagram of an example process 1800 for model validation according to one or more implementations described herein. As shown, process 1800 is described below as being performed by UE 210 and LMF 320. However, one or more other devices may perform some or all of process 1800. For example, in some implementations, process 1800 may include base station 222 instead of UE 210, and additionally or alternatively, LMF 320 may be replaced by AI-MF server 270. Additionally, example process 1800 may include one or more fewer, additional, differently ordered and/or arranged operations than those shown in Fig. 18. In some implementations, some or all of the operations of example process 1800 may be performed independently, successively, simultaneously, etc., of one or more of the other operations of example process 1800.

[00128] As show, process 1800 may include UE 210 providing LMF 320 assistance information and model capability information (at 1810). Assistance information and model capability data are described above. In some implementations, the assistance information may be current assistance information or assistance information indicative of a condition under which UE 210 is to use a NN model for determine a location of UE 210. Process 1800 may also include LMF 320 determining an NN model configuration and model labels based on the assistance information and model capability information (at 1820). For example, LMF 320 may determine conditions for UE 210 based on the assistance information and select an appropriate NN model abased on the current conditions and the model capability data. LMF 320 may also determine appropriate validity labels for UE 210 to use the NN model based on the assistance information, model capability data, and/or NN model selected. Process 1800 may include LMF 320 communicating the model configuration and validity labels to UE 210 (at 1830), and UE 210 may respond to LMF 320 with an acknowledgement message (at 1840). While not shown, UE 210 may monitor conditions for using the NN model and use the NN model when the monitored conditions are satisfied.

[00129] Fig. 19 is a diagram of an example of components of a device according to one or more implementations described herein. In some implementations, the device 1900 can include application circuitry 1902, baseband circuitry 1904, RF circuitry 1906, front-end module (FEM) circuitry 1908, one or more antennas 1910, and power management circuitry (PMC) 1912 coupled together at least as shown. The components of the illustrated device 1900 can be included in a UE or a RAN node. In some implementations, the device 1900 can include fewer elements (e.g., a RAN node may not utilize application circuitry 1902, and instead include a processor/controller to process IP data received from a CN or an Evolved Packet Core (EPC)). In some implementations, the device 1900 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 1900, 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).

[00130] The application circuitry 1902 can include one or more application processors. For example, the application circuitry 1902 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 1900. In some implementations, processors of application circuitry 1902 can process IP data packets received from an EPC.

[00131] The baseband circuitry 1904 can include circuitry such as, but not limited to, one or more single-core or multi-core processors. The baseband circuitry 1904 can include one or more baseband processors or control logic to process baseband signals received from a receive signal path of the RF circuitry 1906 and to generate baseband signals for a transmit signal path of the RF circuitry 1906. Baseband circuity 1904 can interface with the application circuitry 1902 for generation and processing of the baseband signals and for controlling operations of the RF circuitry 1906. For example, in some implementations, the baseband circuitry 1904 can include a 3G baseband processor 1904A, a 4G baseband processor 1904B, a 5G baseband processor 1904C, or other baseband processor(s) 1904D for other existing generations, generations in development or to be developed in the future (e.g., 5G, 6G, etc.).

[00132] The baseband circuitry 1904 (e.g., one or more of baseband processors 1904A-D) can handle various radio control functions that enable communication with one or more radio networks via the RF circuitry 1906. In other implementations, some or all of the functionality of baseband processors 1904A- D can be included in modules stored in the memory 1904G and executed via a Central Processing Unit (CPU) 1904E. The radio control functions can include, but are not limited to, signal modulation/demodulation, encoding/decoding, radio frequency shifting, etc. In some implementations, modulation/demodulation circuitry of the baseband circuitry 1904 can include Fast-Fourier Transform (FFT), precoding, or constellation mapping/de-mapping functionality. In some implementations, encoding/decoding circuitry of the baseband circuitry 1904 can include convolution, tail-biting convolution, turbo, Viterbi, or Low-Density Parity Check (LDPC) encoder/decoder functionality. Implementations of modulation/demodulation and encoder/decoder functionality are not limited to these examples and can include other suitable functionality in other implementations.

[00133] In some implementations, memory 1904G may receive and/or store information and instructions for using NN models to determine a location of UE 210. The output of the NN may be the location of the UE 210 or be used in a subsequent procedure to determine the location of the UE. The information and instructions may enable NN models to be configured, labeled, and validated for use in one or more scenarios. One or more of UE 210, base station 222, AI-MF server 270, and LMF 320 may be involved, and the procedures described herein may include a model configuration function, model selection function, and model inference function.

[00134] In some implementations, the baseband circuitry 1904 can include one or more audio digital signal processor(s) (DSP) 1904F. The audio DSPs 1904F 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 1904 and the application circuitry 1902 can be implemented together such as, for example, on a system on a chip (SOC).

[00135] In some implementations, the baseband circuitry 1904 can provide for communication compatible with one or more radio technologies. For example, in some implementations, the baseband circuitry 1904 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 1904 is configured to support radio communications of more than one wireless protocol can be referred to as multi-mode baseband circuitry.

[00136] RF circuitry 1906 can enable communication with wireless networks using modulated electromagnetic radiation through a non-solid medium. In various implementations, the RF circuitry 1906 can include switches, filters, amplifiers, etc. to facilitate the communication with the wireless network. RF circuitry 1906 can include a receive signal path which can include circuitry to down-convert RF signals received from the FEM circuitry 1908 and provide baseband signals to the baseband circuitry 1904. RF circuitry 1906 can also include a transmit signal path which can include circuitry to up-convert baseband signals provided by the baseband circuitry 1904 and provide RF output signals to the FEM circuitry 1908 for transmission.

[00137] In some implementations, the receive signal path of the RF circuitry 1906 can include mixer circuitry 1906A, amplifier circuitry 1906B and filter circuitry 1906C. In some implementations, the transmit signal path of the RF circuitry 1906 can include filter circuitry 1906C and mixer circuitry 1906A. RF circuitry 1906 can also include synthesizer circuitry 1906D for synthesizing a frequency for use by the mixer circuitry 1906A of the receive signal path and the transmit signal path. In some implementations, the mixer circuitry 1906A of the receive signal path can be configured to down-convert RF signals received from the FEM circuitry 1908 based on the synthesized frequency provided by synthesizer circuitry 1906D. The amplifier circuitry 1906B can be configured to amplify the down-converted signals and the filter circuitry 1906C 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 1904 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 1906A of the receive signal path can comprise passive mixers, although the scope of the implementations is not limited in this respect.

[00138] In some implementations, the mixer circuitry 1906A of the transmit signal path can be configured to up-convert input baseband signals based on the synthesized frequency provided by the synthesizer circuitry 1906D to generate RF output signals for the FEM circuitry 1908. The baseband signals can be provided by the baseband circuitry 1904 and can be filtered by filter circuitry 1906C.

[00139] In some implementations, the mixer circuitry 1906A of the receive signal path and the mixer circuitry 1906A 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 1906A of the receive signal path and the mixer circuitry 1906A 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 1906A 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 1906A of the receive signal path and the mixer circuitry 1906A of the transmit signal path can be configured for superheterodyne operation.

[00140] 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 1906 can include analog-to-digital converter (ADC) and digital-to-analog converter (DAC) circuitry and the baseband circuitry 1904 can include a digital baseband interface to communicate with the RF circuitry 1906.

[00141] 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.

[00142] In some implementations, the synthesizer circuitry 1906D can be a fractional-N synthesizer or a fractional N/N+1 synthesizer, although the scope of the implementations is not limited in this respect as other types of frequency synthesizers can be suitable. For example, synthesizer circuitry 1906D can be a delta-sigma synthesizer, a frequency multiplier, or a synthesizer comprising a phase-locked loop with a frequency divider.

[00143] The synthesizer circuitry 1906D can be configured to synthesize an output frequency for use by the mixer circuitry 1906A of the RF circuitry 1906 based on a frequency input and a divider control input. In some implementations, the synthesizer circuitry 1906D can be a fractional N/N+1 synthesizer.

[00144] 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 1904 or the applications circuitry 1902 depending on the desired output frequency. In some implementations, a divider control input (e.g., N) can be determined from a lookup table based on a channel indicated by the applications circuitry 1902.

[00145] Synthesizer circuitry 1906D of the RF circuitry 1906 can include a divider, a delay-locked loop (DLL), a multiplexer and a phase accumulator. In some implementations, the divider can be a dual modulus divider (DMD) and the phase accumulator can be a digital phase accumulator (DPA). In some implementations, the DMD can be configured to divide the input signal by either N or N+1 (e.g., based on a carry out) to provide a fractional division ratio. In some example implementations, the DLL can include a set of cascaded, tunable, delay elements, a phase detector, a charge pump and a D-type flip-flop. In these implementations, the delay elements can be configured to break a VCO period up into Nd equal packets of phase, where Nd is the number of delay elements in the delay line. In this way, the DLL provides negative feedback to help ensure that the total delay through the delay line is one VCO cycle.

[00146] In some implementations, synthesizer circuitry 1906D can be configured to generate a carrier frequency as the output frequency, while in other implementations, the output frequency can be a multiple of the carrier frequency (e.g., twice the carrier frequency, four times the carrier frequency) and used in conjunction with quadrature generator and divider circuitry to generate multiple signals at the carrier frequency with multiple different phases with respect to each other. In some implementations, the output frequency can be a LO frequency (fLO). In some implementations, the RF circuitry 1906 can include an IQ/polar converter.

[00147] FEM circuitry 1908 can include a receive signal path which can include circuitry configured to operate on RF signals received from one or more antennas 1910, amplify the received signals and provide the amplified versions of the received signals to the RF circuitry 1906 for further processing. FEM circuitry 1908 can also include a transmit signal path which can include circuitry configured to amplify signals for transmission provided by the RF circuitry 1906 for transmission by one or more of the one or more antennas 1910. In various implementations, the amplification through the transmit or receive signal paths can be done solely in the RF circuitry 1906, solely in the FEM circuitry 1908, or in both the RF circuitry 1906 and the FEM circuitry 1908.

[00148] In some implementations, the FEM circuitry 1908 can include a TX/RX switch to switch between transmit mode and receive mode operation. The FEM circuitry can include a receive signal path and a transmit signal path. The receive signal path of the FEM circuitry can include an LNA to amplify received RF signals and provide the amplified received RF signals as an output (e.g., to the RF circuitry 1906). The transmit signal path of the FEM circuitry 1908 can include a power amplifier (PA) to amplify input RF signals (e.g., provided by RF circuitry 1906), and one or more filters to generate RF signals for subsequent transmission (e.g., by one or more of the one or more antennas 1910). [00149] In some implementations, the PMC 1912 can manage power provided to the baseband circuitry 1904. In particular, the PMC 1912 can control powersource selection, voltage scaling, battery charging, or DC-to-DC conversion. The PMC 1912 can often be included when the device 1900 is capable of being powered by a battery, for example, when the device is included in a UE. The PMC 1912 can increase the power conversion efficiency while providing desirable implementation size and heat dissipation characteristics.

[00150] While Fig. 19 shows the PMC 1912 coupled only with the baseband circuitry 1904. However, in other implementations, the PMC 1912 may be additionally or alternatively coupled with, and perform similar power management operations for, other components such as, but not limited to, application circuitry 1902, RF circuitry 1906, or FEM circuitry 1908.

[00151] In some implementations, the PMC 1912 can control, or otherwise be part of, various power saving mechanisms of the device 1900. For example, if the device 1900 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 1900 can power down for brief intervals of time and thus save power.

[00152] If there is no data traffic activity for an extended period of time, then the device 1900 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 1900 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 1900 may not receive data in this state; in order to receive data, it can transition back to RRC_Connected state.

[00153] 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 unreachable to the network and can power down completely. Any data sent during this time incurs a large delay and it is assumed the delay is acceptable.

[00154] Processors of the application circuitry 1902 and processors of the baseband circuitry 1904 can be used to execute elements of one or more instances of a protocol stack. For example, processors of the baseband circuitry 1904, alone or in combination, can be used execute Layer 3, Layer 2, or Layer 1 functionality, while processors of the baseband circuitry 1904 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.

[00155] Fig. 20 is a block diagram illustrating components, according to some example implementations, able to read instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and perform any one or more of the methodologies discussed herein. Specifically, Fig. 20 shows a diagrammatic representation of hardware resources 2000 including one or more processors (or processor cores) 2010, one or more memory/storage devices 2020, and one or more communication resources 2030, each of which may be communicatively coupled via a bus 2040. For implementations where node virtualization (e.g., NFV) is utilized, a hypervisor 2002 may be executed to provide an execution environment for one or more network slices/sub-slices to utilize the hardware resources 2000.

[00156] The processors 2010 (e.g., a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a digital signal processor (DSP) such as a baseband processor, an application specific integrated circuit (ASIC), a radio-frequency integrated circuit (RFIC), another processor, or any suitable combination thereof) may include, for example, a processor 2012 and a processor 2014.

[00157] The memory/storage devices 2020 may include main memory, disk storage, or any suitable combination thereof. The memory/storage devices 2020 may include, but are not limited to any type of volatile or non-volatile memory such as 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 storage, etc.

[00158] In some implementations, memory /storage devices 2020 receive and/or store information and instructions 2055 for using NN models to determine a location of UE 210. The output of the NN may be the location of the UE 210 or be used in a subsequent procedure to determine the location of the UE. The information and instructions 2055 may enable NN models to be configured, labeled, and validated for use in one or more scenarios. One or more of UE 210, base station 222, AI-MF server 270, and LMF 320 may be involved, and the procedures described herein may include a model configuration function, model selection function, and model inference function.

[00159] The communication resources 2030 may include interconnection or network interface components or other suitable devices to communicate with one or more peripheral devices 2004 or one or more databases 2006 via a network 2008. For example, the communication resources 2030 may include wired communication components (e.g., for coupling via a Universal Serial Bus (USB)), cellular communication components, NFC components, Bluetooth® components (e.g., Bluetooth® Low Energy), Wi-Fi® components, and other communication components.

[00160] Instructions 2050 may comprise software, a program, an application, an applet, an app, or other executable code for causing at least any of the processors 2010 to perform any one or more of the methodologies discussed herein. The instructions 2050 may reside, completely or partially, within at least one of the processors 2010 (e.g., within the processor’s cache memory), the memory/storage devices 2020, or any suitable combination thereof. Furthermore, any portion of the instructions 2050 may be transferred to the hardware resources 2000 from any combination of the peripheral devices 2004 or the databases 2006. Accordingly, the memory of processors 2010, the memory/storage devices 2020, the peripheral devices 2004, and the databases 2006 are examples of computer-readable and machine-readable media.

[00161] 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.

[00162] In example 1 , which may also include one or more of the examples described herein, a device, comprises: a memory; and a processor configured to, when executing instructions stored in the memory, cause the device to: obtain a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); obtain assistance information corresponding to a condition of the UE; select the NN model by matching the assistance information to the validity labels; and use the NN model to determine the location of the UE.

[00163] In example 2, which may also include one or more of the examples described herein, the device is the UE. In example 3, which may also include one or more of the examples described herein, the device is a base station. In example 4, which may also include one or more of the examples described herein, the device receives the NN model with the one or more validity labels from a server device.

[00164] In example 5, which may also include one or more of the examples described herein, the device obtains the NN model with the one or more validity labels by creating the NN model with the one or more validity labels. In example 6, which may also include one or more of the examples described herein, the device obtains the NN model with the one or more validity labels during a NN model setup procedure.

[00165] In example 7, which may also include one or more of the examples described herein, a server device, comprising: a memory; and a processor configured to, when executing instructions stored in the memory, cause the server device to: receive assistance information; determine, based on the assistance information, a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); and communicate the NN model to a device to enable the location of the UE or use the NN model to determine the location of the UE.

[00166] In example 8, which may also include one or more of the examples described herein, the server device comprises a location management function of a core network. In example 9, which may also include one or more of the examples described herein, the server device comprises an artificial intelligence (Al) - management function(MF) (AI-MF) server. In example 10, which may also include one or more of the examples described herein, the device is the UE and the assistance information is received from the UE. In example 1 1 , which may also include one or more of the examples described herein, the device is a base station and the assistance information is received from the base station.

[00167] In example 12, which may also include one or more of the examples described herein, one or more devices may comprise a memory; and a processor configured to, when executing instructions stored in the memory, cause the one or more device to: obtain validity testing data based on model capability data; and determine a validity of a neural network (NN) model based on the validity testing data, wherein: the NN model is configured to enable determination of a location of a user equipment (UE), and when the NN model is valid, the NN is used to determine the location of the UE.

[00168] In example 13, which may also include one or more of the examples described herein, the one or more devices comprises at least one of: the UE, a base station, a location management function (LMF), or an artificial intelligence (Al) - management function(MF) (AI-MF) server. In example 14, which may also include one or more of the examples described herein, testing the validity of the NN model comprises determining whether the NN model perform appropriately for a current condition of the UE. In example 15, which may also include one or more of the examples described herein, the model capability data is received from the UE or a base station; and the NN model is used by the UE or the base station.

[00169] In example 16, which may also include one or more of the examples described herein, the model capability data is received from the UE or a base station; and the NN model is used by one of the UE, the base station, a location management function (LMF), or an artificial intelligence (Al) - management function(MF) (AI-MF) server.

[00170] In example 17, which may also include one or more of the examples described herein, when the NN model is invalid, a message is generated that indicates that the NN model is invalid. In example 18, which may also include one or more of the examples described herein, the model capability data corresponds to multiple NN models, the validity testing data corresponds to multiple NN models, and a validity of the multiple NN models is determined. In example 19, which may also include one or more of the examples described herein, the multiple NN models correspond to different NN model classes.

[00171] In example 20, which may also include one or more of the examples described herein, multiple NN models may correspond to one or more NN model class. In example 21 , which may also include one or more of the examples described herein, when more than one NN models are valid for a set of validity testing data, a selection criteria may be applied to select a best NN model among the more than one NN models. In example 22, which may also include one or more of the examples described herein, a device, comprising: a memory; and a processor configured to, when executing instructions stored in the memory, cause the device to: communicate mobility capability data to a location management function (LMF); communicate neural network (NN) conditions and requirements data to the LMF; receive model configuration and validity data from the LMF; and determine whether one or more NN models is valid based on the model configuration and validity data.

[00172] In example 23, which may also include one or more of the examples described herein, the device comprises a user equipment (UE). In example 24, which may also include one or more of the examples described herein, the device comprises a base station. In example 25, which may also include one or more of the examples described herein, capability data comprises an accuracy quality, a latency, a reference signal configuration, and a model type corresponding to a NN model. In example 26, which may also include one or more of the examples described herein, the model configuration and validity data comprise a model identifier (ID), a reference signal configuration, a feedback configuration, and assistance data.

[00173] In example 27, which may also include one or more of the examples described herein, the device is further configured to provide the LMF with feedback data regarding a validity of the one or more NN models. In example 28, which may also include one or more of the examples described herein, the device is further configured to receive, in response to sending the feedback data, a model indication of whether to use the one or more NN models.

[00174] In example 29, which may also include one or more of the examples described herein, a server device may comprise a memory; and a processor configured to, when executing instructions stored in the memory, cause the device to: receive model capability data and assistance data from a device; determine, based on the model capability data and assistance data, a neural network (NN) model configuration and validity labels; communicate the model configuration and validity data to the device; and receive, from the device, and validity acknowledgement for the model configuration and validity data.

[00175] In example 30, which may also include one or more of the examples described herein, the server device comprises a location management function of a core network. In example 31 , which may also include one or more of the examples described herein, the server device comprises an artificial intelligence (Al) - management function(MF) (AI-MF) server. In example 32, which may also include one or more of the examples described herein, the model capability data comprises a reference signal configuration supported by the device.

[00176] In example 33, which may also include one or more of the examples described herein, a method, performed by a device, the method comprising: obtaining a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); obtaining assistance information corresponding to a condition of the UE; selecting the NN model by matching the assistance information to the validity labels; and using the NN model to determine the location of the UE.

[00177] In example 34, which may also include one or more of the examples described herein, the device receives the NN model with the one or more validity labels from a server device. In example 35, which may also include one or more of the examples described herein, the device obtains the NN model with the one or more validity labels by creating the NN model with the one or more validity labels. In example 36, which may also include one or more of the examples described herein, the device obtains the NN model with the one or more validity labels during a NN model setup procedure.

[00178] In example 37, which may also include one or more of the examples described herein, a method, performed by a server device, the method comprising: receiving assistance information; determining, based on the assistance information, a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); and communicating the NN model to a device to enable the location of the UE or use the NN model to determine the location of the UE.

[00179] In example 38, which may also include one or more of the examples described herein, the server device comprises a location management function of a core network. In example 39, which may also include one or more of the examples described herein, the server device comprises an artificial intelligence (Al) - management function (MF) (AI-MF) server. In example 40, which may also include one or more of the examples described herein, the device is the UE and the assistance information is received from the UE.

[00180] In example 41 , which may also include one or more of the examples described herein, a computer-readable medium comprising instructions that when performed by one or more processors causes the one or more processors to: obtain a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); obtain assistance information corresponding to a condition of the UE; select the NN model by matching the assistance information to the validity labels; and use the NN model to determine the location of the UE.

[00181] In example 42, which may also include one or more of the examples described herein, a computer-readable medium comprising instructions that when performed by one or more processors causes the one or more processors to: receive assistance information; determine, based on the assistance information, a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); and communicate the NN model to a device to enable the location of the UE or use the NN model to determine the location of the UE.

[00182] 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.

[00183] 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.

[00184] 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 application.

[00185] 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 or 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.

[00186] 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 to minimize risks of unintentional or unauthorized access or use, and the nature of authorized use should be clearly indicated to users.

Claims

CLAIMS What is claimed is:

1 . A device, comprising: a memory; and a processor configured to, when executing instructions stored in the memory, cause the device to: obtain a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); obtain assistance information corresponding to a condition of the UE; select the NN model by matching the assistance information to the validity labels; and use the NN model to determine the location of the UE.

2. The device of claim 1 , wherein the device is the UE.

3. The device of claim 1 , wherein the device is a base station.

4. The device of claim 1 , wherein the device receives the NN model with the one or more validity labels from a server device.

5. The device of claim 1 , wherein the device obtains the NN model with the one or more validity labels by creating the NN model with the one or more validity labels.

6. The device of claim 1 , wherein the device obtains the NN model with the one or more validity labels during a NN model setup procedure.

7. A server device, comprising: a memory; and a processor configured to, when executing instructions stored in the memory, cause the server device to: receive assistance information; determine, based on the assistance information, a neural network (NN) model with one or more validity labels corresponding to a condition for using the NN model to determine a location of a user equipment (UE); and communicate the NN model to a device to enable the location of the UE or use the NN model to determine the location of the UE.

8. The server device of claim 7, wherein the server device comprises a location management function of a core network.

9. The server device of claim 7, wherein the server device comprises an artificial intelligence (Al) - management function(MF) (AI-MF) server.

10. The server device of claim 7, wherein the device is the UE and the assistance information is received from the UE.

11 .The server device of claim 7, wherein the device is a base station and the assistance information is received from the base station.

12. One or more devices, comprising: a memory; and a processor configured to, when executing instructions stored in the memory, cause the one or more device to: obtain validity testing data based on model capability data; and determine a validity of a neural network (NN) model based on the validity testing data, wherein: the NN model is configured to enable determination of a location of a user equipment (UE), and when the NN model is valid, the NN is used to determine the location of the UE.

13. The one or more devices of claim 12, wherein the one or more devices comprises at least one of: the UE, a base station, a location management function (LMF), or an artificial intelligence (Al) - management function(MF) (AI-MF) server.

14. The one or more devices of claim 12, wherein testing the validity of the NN model comprises determining whether the NN model perform appropriately for a current condition of the UE.

15. The one or more devices of claim 12, wherein: the model capability data is received from the UE or a base station; and the NN model is used by one of the UE, the base station, a location management function (LMF), or an artificial intelligence (Al) - management function(MF) (AI-MF) server.

16. The one or more devices of claim 12, wherein, when the NN model is invalid, a message is generated that indicates that the NN model is invalid.

17. The one or more devices of claim 12, wherein the model capability data corresponds to multiple NN models, the validity testing data corresponds to multiple NN models, and a validity of the multiple NN models is determined.

18. The one or more devices of claim 17, wherein the multiple NN models correspond to different NN model classes.

19. The one or more devices of claim 17, where multiple NN models may correspond to one or more NN model class.

20. The one or more devices of claim 17, wherein, when more than one NN models are valid for a set of validity testing data, a selection criteria may be applied to select a best NN model among the more than one NN models.