Training and inference consistency in ai / ML positioning

Abstract

Apparatus and methods for training and inference consistency in Al / ML positioning. One method (400) may include a user equipment receiving (402), from a network entity, a first configuration associated with positioning reference signal (PRS) configuration, wherein the first configuration comprises one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning; and transmitting (404), to the network entity, a request for PRS configuration.

Description

TITLETRAINING AND INFERENCE CONSISTENCY IN AI / ML POSITIONINGCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of US Provisional Application No. 63 / 718180, filed November 8, 2024. The entire content of the above-referenced application is hereby incorporated by reference.TECHNICAL FIELD

[0002] Some example embodiments may generally relate to mobile or wireless telecommunication systems, such as 3rdGeneration Partnership Project (3GPP) Long Term Evolution (LTE), 511generation (5G) radio access technology (RAT), new radio (NR) access technology, 6thgeneration (6G), and / or other communications systems. For example, certain example embodiments may relate to systems and / or methods for training and inference consistency in artificial intelligence (Al)Zmachine learning (ML) positioning.BACKGROUND

[0003] Examples of mobile or wireless telecommunication systems may include radio frequency (RF) 5G RAT, the Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), LTE Evolved UTRAN (E-UTRAN), LTE-Advanced (LTE-A), LTE-A Pro, NR access technology, and / or MulteFire Alliance. 5G wireless systems refer to the next generation (NG) of radio systems and network architecture. A 5G system is typically built on a 5G NR, but a 5G (or NG) network may also be built on E-UTRA radio. It is expected that NR can support service categories such as enhanced mobile broadband (eMBB), ultra-reliable low-latency-communication (URLLC), and massive machine-type communication (mMTC). NR is expected to deliver extreme broadband, ultra-robust, low-latency connectivity, and massive networking to support the Internet of Things (loT). The next generation radio access network (NG-RAN) represents the radio access network (RAN) for 5G, which may provide radio access for NR, LTE, and LTE- A. It is noted that the nodes in 5G providing radio access functionality to a user equipment (e.g., similar to the Node B in UTRAN or the Evolved Node B (eNB) in LTE) may be referred to as next-generation Node B (gNB) when built on NR radio, and may be referred to as next-generation eNB (NG-eNB) when built on E- UTRA radio.SUMMARY

[0004] In accordance with some example embodiments, a method may include receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The method may further include transmitting, to the network entity, a request for PRS configuration.

[0005] In accordance with certain example embodiments, an apparatus may include means for receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The apparatus may further include means for transmitting, to the network entity, a request for PRS configuration.

[0006] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more networkside additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The method may further include transmitting, to the network entity, a request for PRS configuration.

[0007] In accordance with some example embodiments, a computer program product may perform a method. The method may include receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more networkside additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The method may further include transmitting, to the network entity, a request for PRS configuration.

[0008] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to receive, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit, to the network entity, a request for PRS configuration.

[0009] In accordance with various example embodiments, an apparatus may include receiving circuitry configured to perform receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The apparatus may further include transmitting circuitry configured to perform transmitting, to the network entity, a request for PRS configuration.

[0010] In accordance with some example embodiments, a method may include transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The method may further include receiving, from the user equipment, a request for PRS configuration.

[0011] In accordance with certain example embodiments, an apparatus may include means for transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The apparatus may further include means for receiving, from the user equipment, a request for PRS configuration.

[0012] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more networkside additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The method may further include receiving, from the user equipment, a request for PRS configuration.

[0013] In accordance with some example embodiments, a computer program product may perform a method. The method may include transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more networkside additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The method may further include receiving, from the user equipment, a request for PRS configuration.

[0014] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to transmit, to a user equipment, a first configuration associated with positioningreference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to receive, from the user equipment, a request for PRS configuration.

[0015] In accordance with various example embodiments, an apparatus may include transmitting circuitry configured to perform transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The apparatus may further include receiving circuitry configured to perform receiving, from the user equipment, a request for PRS configuration.

[0016] In accordance with some example embodiments, a method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The method may further include receiving, from the network entity, a configuration associated with PRS configuration.

[0017] In accordance with certain example embodiments, an apparatus may include means for transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The apparatus may further include means for receiving, from the network entity, a configuration associated with PRS configuration.

[0018] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The method may further include receiving, from the network entity, a configuration associated with PRS configuration.

[0019] In accordance with some example embodiments, a computer program product may perform a method. The method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration forconfiguring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include receiving, from the network entity, a configuration associated with PRS configuration.

[0020] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to transmit, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)- enabled positioning. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to receive, from the network entity, a configuration associated with PRS configuration.

[0021] In accordance with various example embodiments, an apparatus may include transmitting circuitry configured to perform transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)- enabled positioning. The apparatus may further include receiving circuitry configured to perform receiving, from the network entity, a configuration associated with PRS configuration.

[0022] In accordance with some example embodiments, a method may include receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include transmitting, to the user equipment, a configuration associated with PRS configuration.

[0023] In accordance with certain example embodiments, an apparatus may include means for receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The apparatus may further include means for transmitting, to the user equipment, a configuration associated with PRS configuration.

[0024] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configurationfor configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include transmitting, to the user equipment, a configuration associated with PRS configuration.

[0025] In accordance with some example embodiments, a computer program product may perform a method. The method may include receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include transmitting, to the user equipment, a configuration associated with PRS configuration.

[0026] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to receive, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)- enabled positioning. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit, to the user equipment, a configuration associated with PRS configuration.

[0027] In accordance with various example embodiments, an apparatus may include receiving circuitry configured to perform receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)- enabled positioning. The apparatus may further include transmitting circuitry configured to perform transmitting, to the user equipment, a configuration associated with PRS configuration.

[0028] In accordance with some example embodiments, a method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include transmitting, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the UE. The method may further include receiving, from the network entity, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0029] In accordance with certain example embodiments, an apparatus may include means for transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The apparatus may further include means for transmitting, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the UE. The apparatus may further include means for receiving, from the network entity, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0030] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include transmitting, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the UE. The method may further include receiving, from the network entity, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0031] In accordance with some example embodiments, a computer program product may perform a method. The method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. The method may further include transmitting, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the UE. The method may further include receiving, from the network entity, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0032] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to transmit, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)- enabled positioning. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit, to the network entity, a first indication of detectedperformance degradation associated with the UE-side AI / ML-enabled positioning at the UE. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to receive, from the network entity, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0033] In accordance with various example embodiments, an apparatus may include transmitting circuitry configured to perform transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)- enabled positioning. The apparatus may further include transmitting circuitry configured to perform transmitting, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the UE. The apparatus may further include receiving circuitry configured to perform receiving, from the network entity, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0034] In accordance with some example embodiments, a method may include receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include receiving, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment. The method may further include transmitting, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0035] In accordance with certain example embodiments, an apparatus may include means for receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The apparatus may further include means for receiving, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment. The apparatus may further include means for transmitting, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0036] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include receiving, from a user equipment, a request for positioning referencesignal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include receiving, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment. The method may further include transmitting, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one networkside additional condition.

[0037] In accordance with some example embodiments, a computer program product may perform a method. The method may include receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The method may further include receiving, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment. The method may further include transmitting, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one networkside additional condition.

[0038] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to receive, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)- enabled positioning. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to receive, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.

[0039] In accordance with various example embodiments, an apparatus may include receiving circuitry configured to perform receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)- enabled positioning. The apparatus may further include receiving circuitry configured to perform receiving,from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment. The apparatus may further include transmitting circuitry configured to perform transmitting, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition.BRIEF DESCRIPTION OF THE DRAWINGS

[0040] For a proper understanding of example embodiments, reference should be made to the accompanying drawings, wherein:

[0041] FIG. 1 illustrates an example of a downlink (DL) positioning reference signal (PRS) configuration structure;

[0042] FIG. 2 illustrates an example of resource ID (beam ID) assignment;

[0043] FIG. 3 illustrates an example of a signaling diagram according to certain example embodiments;

[0044] FIG. 4 illustrates an example of a flow diagram of a method according to various example embodiments;

[0045] FIG. 5 illustrates an example of a flow diagram of a method accordingvarious example embodiments;

[0046] FIG. 6 illustrates an example of a flow diagram of a method accordingvarious example embodiments;

[0047] FIG. 7 illustrates an example of a flow diagram of a method according to various example embodiments;

[0048] FIG. 8 illustrates an example of a flow diagram of a method according to various example embodiments;

[0049] FIG. 9 illustrates an example of a flow diagram of a method according to various example embodiments;

[0050] FIG. 10 illustrates an example of various network devices according to some example embodiments; and

[0051] FIG. 11 illustrates an example of a 5G network and system architecture according to certain example embodiments.DETAILED DESCRIPTION

[0052] It will be readily understood that the components of certain example embodiments, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of differentconfigurations. Thus, the following detailed description of some example embodiments of systems, methods, apparatuses, and computer program products for training and inference consistency in AI / ML positioning is not intended to limit the scope of certain example embodiments, but is instead representative of selected example embodiments.

[0053] Consistency between training and inference conditions may improve the performance of AI / ML solutions. For example, if an AI / ML model is trained under certain conditions, the performance of the model may be improved when similar conditions hold during inference. For example, in mobile networks, some of the training / inference conditions may be only known to the network (NW) (e.g., gNB or CN, depending on the scenario). To establish consistency between training and inference of UE side models, it may be helpful for the UE to receive some information about such training / inference conditions, which may be referred to as NW-side additional conditions or NW-side conditions. The life cycle of an AI / ML functionality (or AI / ML-enabled feature / feature group (FG)) may be managed (also referred to as life cycle management (LCM)) at a functionality-level. For example, activation and / or deactivation of an AI / ML functionality (or AI / ML-enabled feature / feature group) may be under the control of the NW. The model selection may be performed by the UE. In such a manner, UE proprietary information is not shared with the NW.

[0054] For an AI / ML-enabled feature / FG, additional conditions may refer to aspects that are assumed for the training of the model but are not a part of UE capability. The additional conditions may not be specified. Additional conditions can be divided into two categories: NW-side additional conditions and UE-side additional conditions.

[0055] For inference for UE-side models, consistency between training and inference regarding NW- side additional conditions (if identified) may be achieved using at least one of the following approaches (e.g., when feasible and necessary):

[0056] Model identification to achieve alignment on the NW-side additional condition between NW-side and UE-side; or

[0057] Information and / or indication on NW-side additional conditions is provided to UE.

[0058] In the context of UE positioning feature that is based on UE sided AI / ML model, maintaining training and inference consistency (e.g., by using additional conditions) may be applicable for at least two positioning use cases.

[0059] In a first case (herein referred to as "UE positioning case 1”), UE-based positioning may be implemented using UE-side model(s), direct AI / ML or AI / ML assisted positioning. In such a case, UE may use radio measurements to estimate (e.g., directly) its position using AI / ML model(s).

[0060] In a second case (herein referred to as "UE positioning case 2”), UE-assisted / LMF-based positioning may be implemented with UE-side model(s), AI / ML assisted positioning. In such a case, UE may use radio measurements to extract assistance information using AI / ML model(s). For example, an AI / ML model at the UE may use the radio measurements and may identify if the measurements may be related to a LOS or NLOS situation. Such extracted assistance information may be transferred to the NW to assist the NW in estimating the UE position.

[0061] In case 1 or case 2 above, the NW-side conditions may be used at the UE. As an example, a UE may have more than one AI / ML model for direct AI / ML-based positioning and may have one for the case when condition X holds and one for the case when condition set Y holds. If X and Y are only known at the network, the NW-side additional conditions may be communicated from the NW to the UE to enable a proper model selection at the UE. This approach may apply for many model control operations, such as deactivation, activation, switching and fallback.

[0062] The following are examples of NW-side additional conditions for positioning that may improve the consistency between training data collection, training and inference.

[0063] Validity area

[0064] TRP / ARP location information

[0065] PRS beam angle information

[0066] PRS TX power information

[0067] PRS and TRP / ARP mapping information

[0068] TRP relative time difference information

[0069] TRP transmitter timing error information

[0070] TRP LOS / NLOS state information

[0071] The UE positioning cases 1 and 2 may be implemented for on-demand PRS (ODPRS) transmission procedures with UE side AI / ML model(s). For example, to train the AI / ML models deployed at the UE side for the UE positioning cases, UE may receive reference signals from a base station (e.g., a gNB) to perform its radio measurements and use such measurements as AI / ML input attributes toestimate (e.g., directly) the position (in UE positioning case 1) and / or decide on assistance information (in UE positioning case 2). The fact that ODPRS allows for a UE-initiated procedure may enable training and inference data collection / delivery for UE positioning cases 1 and 2. For example, in UE-initiated On- Demand PRS, the UE may send an On-Demand PRS request to the LMF via LPP Request Assistance Data (RAD) message. The On-Demand PRS request may be a request for a pre-defined PRS configuration indicated with pre-defined PRS configuration ID or explicit parameter for PRS configuration and may be a request for PRS transmission or change to the PRS transmission characteristics for positioning measurements. In response, the network implementation (e.g., a network entity such as LMF) may accept, reject, or ignore the received UE-initiated On-Demand PRS request. For example, the LMF may provide the PRS configuration used for PRS transmission or error cause via LPP Provide Assistance Data (PAD) message to the UE. The information in the Provide Assistance Data message may be used at the UE side to improve consistency between training and inference. Table 1 below shows examples of the information that may be transferred from LMF to the UE for DL-TDOA Positioning.

[0072] Table 1

[0073] In the Provide Assistance Data from the LPP message body (e.g., in 5G NR), a UE may receive information about a configuration associated to PRS transmission characteristics, e.g., such as repetition and periodicity, resource set and resource from NG-RAN. The information about the configuration may be used as NW-side additional conditions to maintain training and inference consistency.

[0074] There are different supported positioning reference signals (e.g., in 5G), which includes downlinkPRS (DL PRS) and uplink SRS (UL SRS). In the UE positioning cases 1 and 2, DL PRS may be relevant. DL PRS (e.g., NR DL PRS) may be configured within one slot or over multiple slots. In the case of a single slot, the starting resource element in time and frequency from a TRP may be determined in the configuration. For multiple slots, aspects such as gaps among PRS slots and periodicity may be additionally configured. As illustrated in figure 1, the DL PRS configuration can be represented as a hierarchical structure. As seen in figure 1 , there are at most four frequency layers shown as positioning frequency layers (PFL). Each PFL can be employed by a maximum of 64 TRPs. Each TRP per frequency layer can have up to two resource sets, e.g., for wide and narrow beams. Each resource set can have up to 64 resources. A PRS resource represents a PRS beam, and a resource set refers to a set of PRS beams belonging to a specific TRP over the same PFL.

[0075] The DL PRS configuration may indicate the PFL and TRP to the UE. For example, as shown in figure 1, the corresponding IDs for PFL and TRP are interpretable by UE, e.g., PFL1 refers to a single frequency layer. The same is the case for TRPs. This interpretability does not apply to resource set ID and / or resource ID. Resource set ID and / or resource ID cannot be used for establishing training and inference consistency, e.g., due to such lack of interpretability. For example, as shown on the left side of figure 2, one TRPX (e.g., a base station, such as gNB) may have a set of very narrow beams at one time, and it may decide to transmit PRS over beam 1 to the UE. In this case, Resource ID1 along with PFL ID (and other information) may be indicated to the UE in DL PRS configuration. As seen, on the left side of figure 2, Resource ID1 refers to a narrow beam (beam 1) in a specific direction. At a different time, as shown on the right side of figure 2, the TRPX may decide to use a set of two wider beams. In this case, the TRPX may decide to use the beam 2 for PRS transmission and may assign Resource ID1 to beam 2. Similar to the left side of the figure 2, Resource ID1 along with PFL ID (and other information) may be indicated to the UE in DL PRS configuration. In these two different scenarios, the beams 1 and 2 are employed for PRS transmission and these two beams have different physical characteristics. However, the UE gets the same ID, i.e. , Resource ID1 . When AI / ML-enabled positioning is used at the UE, UE may use more information, e.g., about the physical characteristics of the beams. For example, in the case that a UE has two trained AI / ML models, one for the case with very narrow beams and the other for wide beams. In such a case, information about the physical characteristics of the beams other than the beam ID(s) may enable the UE to select the best model to perform inferences.

[0076] The performance of UE-side AI / ML models may be improved when a UE performs measurements on reference symbols during inference that match the characteristics of the reference symbols captured during the AI / ML model training and data collection phases. For example, data collected during the data collection phase may include measurements such as channel impulse response (CIR), power delay profile (PDP) and power delay (PD) as inputs to positioning AI / ML models. Such collected measurements may not include detailed beam information. Accordingly, the performance of UE-side AI / ML models may be improved if the UE is able to determine and ensure that the NW transmissions (e.g., PRS transmissions) during inference are similar to the NW transmissions that were collected during the data collection phase (and used during the training phase). NW-side additional information described here may help the UE determine during inference whether a beam transmitted by a TRP has similar physical characteristics as compared to the beam that was measured during training phase.

[0077] Although the physical setup (e.g., physical beam pattern) of a TRP may not change very frequently, training data collection (or training) and inference phases for UE-side models may occur in very different time frames. The chance of physical setup of a TRP being different between the training data collection and inference phases may not be negligible. For example, NR-DL-PRS-ResourcelD (e.g., the resources at the bottom layer of the hierarchy illustrated in figure 2) and ResourceSetID (e.g., the resource sets in second-to-bottom layer of the hierarchy illustrated in figure 2) from ProvideAssistanceData in ODPRS may refer to logical beam information and may allow the UE to track the measurements from specific beams only while sweeping. As discussed above, during inference, the same Resource ID may refer to a narrow beam at one time and to a wider at a different time. In other words, the mapping between the physical beams and the logical beams may change over time. This may affect data collection, inference, and / or training consistency. In such cases, while the UE knows the IDs, but the IDs may provide no information about the physical world, e.g., if a ResourcelD refers to a narrow or wide beam. The knowledge about the physical anchors (e.g., physical characteristics of the beams) may improve the performance of AI / ML models (e.g., by establishing the consistency between inference and training) for UE positioning cases 1 and 2 described here.

[0078] In some embodiments, in ODPRS, network-side additional conditions may be transferred from the network to the UE and may provide information (e.g., sufficient information) about the physical anchors of the PRS configuration to enable AI / ML-based / assisted positioning (also herein referred to as AI / ML-enabled positioning) at the UE. Table 2 below illustrates examples of information related to network-side additional conditions.

[0079] Table 2

[0080] The information related to network-side additional conditions is designed to give a UE information for maintaining the consistency between training and inference. Such information is designed in such a manner that it does not reveal proprietary information of the network vendor to the UE. For example, instead of sharing exact values, ranges of values, binary values, high / medium / low levels are used.

[0081] The mandatory part of the NW-side additional conditions in Table 2 may be transferred (e.g., transmitted) from the network to the UE for AI / ML positioning (also herein referred to as AI / ML-enabled positioning) at the UE (e.g., based on an indication as described herein). Based on the mandatory NW- side additional condition(s) received from the network, the UE may determine whether one of its AI / ML models was trained for the conditions similar to the ones indicated by the NW-side additional conditions. Without being given such mandatory NW-side additional condition(s), the UE may not be able to determine and / or report that it has a model capable of supporting configuration(s) for AI / ML-enabled positioning. If the UE determines that it does not have an appropriate AI / ML model for the received NW- side additional conditions, the NW may need to configure a non-AI / ML method (e.g., for UE positioning). AI / ML functionality operations such as activating, deactivating, switching may use the mandatory part of NW-side additional conditions.

[0082] The optional part of the NW-side additional conditions in Table 2 may or may not be transferred (e.g., transmitted) to the UE. For instance, in case of performance (e.g., key performance indicator (KPI)) degradation, the network (e.g., LMF) may decide to provide such optional information to the UE. In at least one embodiment, such optional information may be presented in terms of an ID, e.g., associated ID.

[0083] In some embodiments, in the UE-initiated ODPRS, the NW-side additional condition information may be included in Provide Assistance Data that may be transmitted from the network (e.g., a network entity such as LMF) to the UE. The LMF cannot reject a request from the UE for sharing the mandatory part of NW-side additional information. The LMF may not share the optional part of the NW-side additional conditions (e.g., the LMF may decide to not share it) in response to a request from the UE for such information. In some embodiments, the LMF may provide a list of pre-defined ODPR PRS configurations (e.g., for the propose of data collection (DC)) to the UE. The UE may be allowed to request ODPR parameter(s), e.g., based on the pre-defined PRS training / inference configuration ID (which is index-based request corresponding to the network conditions represented by associated ID). The UE may explicitly request configuration(s) that are within the scope of the received pre-defined DC configuration(s). Such pre-defined configuration(s) provide more NW-centric control for the data collection procedure used for the training / inference propose.

[0084] In some embodiments, in the UE-initiated ODPRS, an indication may be transmitted (e.g., as a separate signaling message) from the UE to the network (e.g., a network entity such as LMF). The indication may indicate to the LMF the ODPRS request is for the purpose of AI / ML-enabled positioning. The indication may indicate (e.g., imply) that the UE may request some NW-side additional condition(s) for AI / ML-enabled positioning. In response, the LMF may provide a set of mandatory NW-side additional conditions to the UE. If the indication is not used in the UE-initiated ODPRS, the LMF may not provide any NW-side additional conditions (mandatory or optional) to the UE. In some embodiments, such indication may be indicated implicitly (e.g., not transmitted in a separate signaling message). In such cases, the LMF can determine such an implicit indication based on the message structure.

[0085] In some embodiments, in the UE-initiated ODPRS, the LPP Request Assistance Data may include an indication of UE preference(s) regarding part of the NW-side additional conditions that are controllable by the network (e.g., the LMF). For example, if a UE has one or more AI / ML models trained for the situations with low interference on PRS, the UE may indicate to the LMF that it prefers to receive PRS from TRPs with low cell loads. In response, when selecting the TRPs, the LMF may take such an indication of UE preference(s) into account, e.g., because the relevant NW-side additional conditions are controllable by the network. The same exchange between the UE and LMF may apply when the training data collection is performed.

[0086] In other cases, some NW-side additional conditions are not controllable by the network, e.g., the load level in the serving cell of the UE. In such cases, the UE may not be able to provide any preference for such NW-side additional conditions.

[0087] Based on the indication from the UE that the ODPRS request is for the purpose of AI / ML-enabled positioning, in some embodiments, the LMF can prioritize responding to the LPP Request Assistance Data from a UE that has indicated to perform AI / ML-enabled positioning over requests from other UEs (e.g., the UEs that use non-AI / ML positioning).

[0088] In some embodiments, the NRPPa TRP information exchange procedure in ODPRS may include information regarding the support of a base station / TRP (e.g., a gNB / TRP) for different NW-side additional conditions. Similarly, in some embodiment, the NRPPa PRS configuration request from theLMF to a base station / TRP (e.g., a gNB / TRP) may include information regarding the support of for different NW-side additional conditions.

[0089] Certain example embodiments described herein may have various benefits and / or advantages to overcome the disadvantages described above. For example, certain example embodiments may improve training and inference consistency in UE-side AI / ML-enabled positioning that depend on network-side additional conditions. Thus, certain example embodiments discussed below are directed to improvements in computer-related technology.

[0090] FIG. 3 illustrates an example of a signaling diagram 300 depicting example operations of an OPDRS procedure using NW-side additional condition(s), according to certain example embodiments. Serving Base Station / TRP 304, neighbor base station(s) / TRP(s) 306, and NE 308 may be similar to NE 1010, as illustrated in FIG. 10, according to certain example embodiments. UE 302 may be similar to UE 1020, as illustrated in FIG. 10, according to certain example embodiments. NE 308 may also be similar to the network functions (as illustrated in FIG. 10), according to certain example embodiments.

[0091] At operation 310, information exchange may be performed between NE 308 (e.g., LMF), and serving base station / TRP 304 (e.g., a gNB) and neighbor base station (s) / TRP 306 (e.g., a gNB). The information exchange may be implemented using a NRPPa TRP information exchange procedure in ODPRS. The exchanged information may include the ODPRS configuration (s) that the serving base station / TRP 304 and / or neighbor base station(s) / TRP(s) 306 can support, such as the NW-side additional condition(s) (as illustrated in Table 2).

[0092] During operations 312, 314, 316, and 318, a UE-initiated on-demand PRS procedure may be performed. At operation 312, UE 302 may indicate to NE 308 the request (e.g., the ODPRS request in operation 316) is related to AI / ML-enabled positioning. In one embodiment, UE 302 may signal the indication to the NE 308 before receiving PRS configurations in operation 314. Signaling the indication before operation 314 may allow UE 302 to obtain appropriate pre-defined PRS configurations from NE 308 during operation 314. The indication may be configured to instruct NE 308 to provide the mandatory NW-side additional conditions to UE 302.

[0093] In another embodiment, the indication may be part of the LPP Request Assistance Data in operation 316. In such a case, the indication may also be configured to instruct NE 308 to provide the mandatory NW-side additional conditions to UE 302, e.g., over LPP Provide Assistance Data in operation 326.

[0094] In yet another embodiment, the indication may be signaled implicitly. For example, a field in the ODPRS request to NE 308 via LPP Request Assistance Data message (e.g., in operation 316) may include information about UE preference regarding NW-side additional conditions. The presence of such a field may implicitly indicate to NE 308 that the ODPRS request is related to AI / ML-enabled positioning.

[0095] In any of the above embodiments, based on receiving the indication, NE 308 may be able to prioritize responding to the ODPRS request over other ODPRS requests to enable AI / ML-enabled positioning at UE 302, e.g., by selecting the base station(s) / TRP(s) that satisfy the requested NW-side additional condition(s) (discussed in more detail in operation 320). Prioritizing ODPRS requests related to AI / ML-enabled positioning over other ODPRS requests provide advantage(s). For example, if a ODPRS request related to AI / ML enabled positioning is not responded to according to the request, UE 302 may not be able to deploy any of its UE-side AI / ML models and may fall back to other non-AI / ML positioning methods, which may reduce the accuracy of positioning-related decisions at UE 302.

[0096] Because positioning information is needed in many different use cases, falling back to non-AI / ML positioning methods may affect positioning accuracy and performance of other use cases that use positioning estimation. For example, the positioning-related decision may be the position estimation in the UE positioning case 1 described herein. As another example, a decision on assistance data (e.g., LOS / NLOS) may need to be transmitted to NE 308 (e.g., LMF).

[0097] Based on receiving the indication, NE 308 may be configured to transmit (e.g., transfer) the mandatory part of the NW-side additional conditions to the UE 302 for AI / ML-enabled positioning at the UE 302. In response to mandatory part of the NW-side additional conditions, UE 302 may be able to make an informed decision, e.g., AI / ML model selection.

[0098] In some embodiments, based on receiving the indication, the NE 308 (e.g., LMF) may determine to provide more information to UE 302, e.g., information as described in Table 1 and / or optional NW-side additional conditions as described in Table 2. In some embodiments, NE 308 (e.g., LMF) may notice or receive any report from UE 302 about performance degradation on positioning accuracy and may determine to provide more optional information to the UE 302, e.g., until the performance accuracy degradation problem is resolved (see more details in operation 318).

[0099] At operation 314, NE 308 (e.g., LMF) may provide (e.g., indicate) pre-defined PRS configurations to UE 302. The indicated pre-defined PRS configurations may at least include mandatory part of the NW- side additional conditions (also herein referred to as mandatory features of the NW-side data collection).

[0100] For example, based on operation 310, NE 308 (e.g., LMF) may determine that it can provide PRS transmission for cases where the range of the number of supported beams for a given Resource Set can be X1 to X2 or X3 to X4. In such a case, the NE 308 may provide two or more pre-defined PRS configurations to the UE 302. Some of the pre-defined PRS configurations may include the information that indicates the supported number of beams are between X1 and X2 while some other pre-defined PRS configurations may include that indicates the supported number of beams are between X3 and X4.

[0101] If the NE 308 does not receive the indication during operation 312 that the ODPRS request is related to AI / ML-enabled positioning, NE 308 may perform operation 314 without providing any information regarding the NW-side additional conditions. The predefined PRS configurations may be provided (e.g., indicated) via LPP Provide Assistance Data message or via positioning system information (posSI).

[0102] At operation 316, UE 302 may send an ODPRS request to the NE 308 (e.g., LMF), e.g., via LPP Request Assistance Data message. The ODPRS request may be a request for a predefined PRS configuration (e.g., indicated with pre-defined PRS configuration ID or explicit parameter for PRS configuration), and / or may be a request for PRS transmission or a change to the PRS transmission characteristics for positioning measurements. The ODPRS request may include information about UE preference (also herein referred to as UE-preferred PRS configuration(s) or UE-preferred configuration(s)) for the NW-side additional conditions.

[0103] Based on the above-described ODPRS request, NE 308 may or may not provide the PRS configuration according to the UE preference (i.e., it is optional for NE 308 to provide the configuration according to UE's preference). While the NE 308 (e.g., LMF) may decide to provide the mandatory assistance data (e.g., based on the received indication during operation 312), the NE 308 may not respond to the Request Assistance Data related to the UE preference (e.g., from operation 316). For example, if UE requests to receive PRS from beams with beam width between Y1 and Y2 (e.g., as its reference), the NE 308 (e.g. LMF) may decide to not accept or respond to the UE preference (e.g., NE 308 may select some base stations / TRPs that employ beams in the range of Y3 and Y4 instead). In such a case, the NE 308 may inform the UE 302 about the selected NW-side additional condition(s) (which are different from the UE preference). In other words, while UE 302 may be able to request UE preferred configuration(s) for NW-side additional condition(s), UE 302 do not have control over the configuration(s). The NE 308 remains in control of deciding whether or not to accept or reject the request. Regardless of whether NE 308 accepts or rejects the request, the NE 308 may inform the UE 302 about the NW-sideadditional conditions for the ODPRS (e.g., the NW-side additional conditions selected by NE 308). Based on the NW-side additional conditions from NE 308, the UE 302 may determine whether to use the PRS transmission configured according to the received NW-side additional conditions or not and may determine to perform a ODPRS request (e.g., if the UE 302 determines not to use the PRS transmission configured as such).

[0104] In such a manner, while UE 302 may not control the UE-side training and / or inference data collection for AI / ML-enabled positioning, UE 302 may influence such data collection by being allowed to present its preferences for the PRS configuration (s)Zparameter(s) of the NW-side additional conditions.

[0105] For example, based on internal analysis at UE 302 (which may be implementation specific), UE 302 may determine that its AI / ML model(s) are / have been trained using a biased dataset. In one example, the dataset may mostly include radio measurements from PRS transmission over very narrow beams. To improve its AI / ML model(s) or to train a new AI / ML model for cases where PRS is transmitted over wider beams, UE 302 may determine to collect such data (e.g., radio measurements from PRS transmission over wider beams). In some embodiments, a request for collecting such data may be indicated by indicating values (e.g., configuration / parameter values) for the relevant NW-side additional conditions (e.g., relevant feature of the NW-side additional conditions) that refer to wider beams.

[0106] At operation 318, UE 302 may optionally provide some feedback about performance of the AI / ML positioning at the UE to NE 308. In case of degradation in positioning related accuracy, the UE 302 may provide recommendation(s) on how to overcome such degradation.

[0107] As discussed herein, the NE 308 (e.g., LMF) may not accept or respond to ODPRS parameters and configurations requested by UE 302 (e.g., as UE preference(s)), for example, in Request Assistance Data. In one example, UE 302 may receive PRS with undesired characteristics (e.g., physical characteristics). UE 302 may detect performance degradation (e.g., degradation that does not exceed an acceptable threshold such that fallback to the non-AI / ML-enabled methods is desirable). In such cases, the UE 302 may indicate detected performance degradation to the NE 308. Based on the indicated performance degradation, the NE 308 may take the degradation into account and may provide the PRS configuration that is more similar to the UE-preferred PRS configuration requested by the UE 302 (e.g., by selecting a different base station / TRP).

[0108] In some embodiments, UE 302 may detect performance degradation by requesting location / positioning information estimated using other method(s) (e.g., using NW-side AI / ML model(s)). UE 302 may request such information periodically (e.g., once in a while). UE 302 may determine there isperformance degradation if a difference between the UE-side estimation and the NW-side estimation exceeds (e.g., constantly) an acceptable threshold (e.g., non-negligible). Indication of performance degradation may be implemented in various ways. In some embodiments, the indication may be in a binary format, e.g., indication of "1” indicates degradation. In some embodiments, the indication may be indicated using low / medium / high values.

[0109] In addition to performance degradation feedback, UE 302 may provide recommend ation(s) to the NE 308 (e.g., LMF) for resolving the performance degradation. For example, the UE 302 may indicate to the NE 308 a request for PRS transmission at least from 5 base stations / TRPs with beam width between Y1 and Y2 and the average distance of base stations / TRPs between D1 to D2.

[0110] The feedback for performance degradation and / or recommendation described herein that are provided by the UE 302 may be processed by the NE 308 as described in operation 320.

[0111] The performance degradation indication and / or the recommendations may be transmitted to the NE 308 at any time (e.g., other than an operation that immediately follows operation 316). It should be understood that operation 318 may be performed only for AI / ML-enabled positioning (e.g., it is not applicable for non-AI / ML-enabled positioning).

[0112] At operation 320, the NE 308 (e.g., LMF) may determine the need for PRS transmission or update of PRS configuration, e.g., based on the information received during operation 312, 316, and / or 318. For example, if a ODPRS request is indicated to be related to AI / ML-enabled positioning (e.g., during operation 312), the NE 308 may accept the parameter(s) indicated in the ODPRS request (e.g., during operation 316), e.g., before selecting the base station (s) / TRP(s) and / or initiating PRS transmission.

[0113] As another example, if the NE 308 receives information from the UE 302 on performance degradation and / or recommendation (s) for performance enhancement (e.g., during operation 318), the NE 308 may consider such information and may update the PRS configuration and selection of base station(s) / TRP(s).

[0114] At operation 322, NE 308 (e.g. LMF) may request from the serving base station / TRP 304 and / or non-serving (e.g., neighbor) base stations / TRPs 306 PRS transmission with NE's 308 desired PRS configuration or information on the PRS configuration that can be provided by the serving base station / TRP 304 and / or non-serving base stations / TRPs 306, e.g., via NRPPa PRS CONFIGURATION REQUEST message. The PRS configuration may include one or more NW-side additional conditions that NE 308 determines to enforce, e.g., based on the ODPRS request received from UE 302 in operation 316.

[0115] If the NE 308 does not indicate any explicit configuration (s)Zparameter(s) for the NW-side additional condition (s), the serving base station / TRP 304 and / or neighbor base stations / TRPs 306 may determine to set PRS configuration based on their internal logic (which may be implementation specific).

[0116] At operation 324A, the serving base station / TRP 304 and / or neighbor base stations / TRPs 306 may provide the successfully configured or updated PRS transmission based on the request in operation 322, e.g., in a NRPPa PRS CONFIGURATION RESPONSE message. The successfully configured transmission may be configured with the PRS configuration available at the serving base station / TRP 304 and / or neighbor base stations / TRPs 306 (which may be different from the requested PRS configuration in operation 322.)

[0117] Alternatively, at operation 324B, the successfully configured or updated PRS transmission may be provided in an NRPPa message separate from a NRPPa PRS CONFIGURATION RESPONSE message (e.g., an NRPPa message reserved for transmitting PRS configuration related to the NW-side additional additions).

[0118] In either operation 324A or 324B, for the configuration(s) / parameter(s) that are determined and set based on internal base station / TRP (e.g., gNB) logic and that are related to the mandatory features of the NW-side additional conditions, the serving base station / TRP 304 and / or neighbor base stations / TRPs 306 may be configured to provide the values of the configuration(s) / parameter(s) (e.g., the correct / corresponding range or level according to Table 2) to the NE 308 (e.g., LMF).

[0119] In either operation 324A or 324B, for the configuration(s) / parameter(s) that are determined and set based on internal base station / TRP (e.g., gNB) logic and that are related to the optional features of the NW-side additional conditions, the serving base station / TRP 304 and / or neighbor base stations / TRPs 306 may or may not provide the values of the configuration(s) / parameter(s) (e.g., the correct / corresponding range or level according to Table 2) to NE 308 (e.g., LMF).

[0120] In either operation 324A or 324B, for the configuration(s) / parameter(s) that are determined and set based on base station / TRP (e.g., gNB) logic and that are not controllable by the NE 308 (e.g., LMF) (such as feature(s) related to the serving or neighbor cell load), the serving base station / TRP 304 and / or neighbor base stations / TRPs 306 may inform the NE 308 of that NW-side additional condition, e.g., if that NW-side additional condition is mandatory. If that NW-side additional condition is optional, the serving base station / TRP 304 and / or neighbor base stations / TRPs 306 may or may not inform the NE 308 of that NW-side additional condition.

[0121] At operation 326, the NE 308 (e.g., LMF) may provide a response to the ODPRS request received during operation 316, e.g., via a LPP Provide Assistance Data message. The response may include a minimum set of NW-side additional condition information. For example, if it has been indicated from UE 302 to the NE 308 that the PRS is requested for AI / ML-enabled positioning at the UE side (e.g., during operation 312), the NE 308 may provide the Provide Assistance Data that include at least the mandatory features of the NW-side additional conditions.

[0122] Regarding the optional features of the NW-side additional conditions (e.g., the NW-side additional conditions that may or may not be controllable by the network) with values / ranges / levels known to the NE 308, NE 308 may determine whether to send / transmit / transfer the information to the UE 302 based on the information received in Request Assistance Data during operation 316 as described herein and / or the feedback and / or recommendation related to accuracy performance at UE 302 during operation 318 as described herein.

[0123] FIG. 4 illustrates an example of a flow diagram of a method 400 that may be performed by a UE, such as UE 302 in FIG. 3 and / or UE 1020 in FIG. 10, according to various example embodiments.

[0124] At step 402, the method may include receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0125] In some embodiments, the one or more network-side additional conditions may include at least one of the following: at least one mandatory network-side additional condition, or at least one optional network-side additional condition. In some embodiments, the one or more network-side additional conditions may relate to a physical characteristic of PRS. In some embodiments, the first configuration may include a range of values, a binary value, or one of a high, medium, or low level. In some embodiments, the UE-side AI / ML-enabled positioning may be implemented using one or more UE-side AI / ML models. In some embodiments, the first configuration may further include at least one of the following: a list of parameters for data collection of the UE-side AI / ML-enabled positioning; a list of features for data collection of the UE-side AI / ML-enabled positioning; a list of parameters for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning; or a list of features for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning.

[0126] At step 404, the method may further include transmitting, to the network entity, a request for PRS configuration. In some embodiments, the request for PRS configuration may include at least one of the following: PRS identifier (ID) of candidate TRP, resource set, or periodicity.

[0127] In some embodiments, the method may further include transmitting, to the network entity, a first indication associated with the request for PRS configuration. The first indication may indicate the requested PRS configuration to be used for UE-side AI / ML-enabled positioning. In such embodiments, the first indication may be transmitted along with the request for PRS configuration or separately from the request for PRS configuration.

[0128] In some embodiments, the request for PRS configuration may indicate at least one of the following: a UE-preferred PRS configuration for configuring the one or more network-side additional conditions; a selection of the first configuration; or at least one parameter of the one or more network-side additional conditions. In some ones of such embodiments, the method may further include receiving, from the network entity, a second configuration associated with PRS configuration, where the second configuration may be the same as the UE-preferred PRS configuration. In other ones of such embodiments, the method may further include receiving, from the network entity, a second configuration associated with PRS configuration, where the second configuration may be the same as the selection of the first configuration. In yet other ones of such embodiments, the method may further include receiving, from the network entity, a second configuration associated with PRS configuration, where the second configuration comprises at least one network-side additional condition that may be different from the one or more network-side additional conditions of the UE-preferred PRS configuration.

[0129] FIG. 5 illustrates an example of a flow diagram of a method 500 that may be performed by a NE, such as NE 308 illustrated in FIG. 3 and / or NE 1010 illustrated in FIG. 10 and / or a network function similar to network functions illustrated in FIG. 10, according to various example embodiments.

[0130] At step 502, the method may include transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0131] In some embodiments, the one or more network-side additional conditions may include at least one of the following: at least one mandatory network-side additional condition, or at least one optional network-side additional condition. In some embodiments, the one or more network-side additional conditions may relate to a physical characteristic of PRS. In some embodiments, the first configurationmay include a range of values, a binary value, or one of a high, medium, or low level. In some embodiments, the first configuration may further include at least one of the following: a list of parameters for data collection of the UE-side AI / ML-enabled positioning; a list of features for data collection of the UE-side AI / ML-enabled positioning; a list of parameters for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning; or a list of features for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning.

[0132] At step 504, the method may include receiving, from the user equipment, a request for PRS configuration. In some embodiments, the request for PRS configuration may indicate at least one of the following: a UE-preferred PRS configuration for configuring the one or more network-side additional conditions; a selection of the first configuration; at least one parameter of the one or more network-side additional conditions; PRS identifier (ID) of candidate TRP; resource set; or periodicity. In such embodiments, the method may further include transmitting, to the user equipment, a second configuration associated with PRS configuration. The second configuration may be the same as the UE-preferred PRS configuration; may be the same as the selection of the first configuration; or may include at least one network-side additional condition that is different from the one or more network-side additional conditions of the UE-preferred PRS configuration.

[0133] In some embodiments, the method may further include receiving, from the user equipment, a first indication associated with the request for PRS configuration. The first indication may indicate the requested PRS configuration to be used for UE-side AI / ML-enabled positioning. In such embodiments, the first indication may be received along with the request for PRS configuration or separately from the request for PRS configuration.

[0134] In some embodiments, the method may further include determining to transmit a second request for positioning reference signal (PRS) configuration based at least on receiving the request for PRS configuration. The method may further include transmitting, to one or more base stations, the second request for PRS configuration. The second request may request that the one or more network-side additional conditions be configured according to the UE-preferred PRS configuration. The method may further include receiving, from the one or more base stations, a response that indicates whether networkside additional condition is to be configured according to the UE-preferred PRS configuration or not.

[0135] FIG. 6 illustrates an example of a flow diagram of a method 600 that may be performed by a UE, such as UE 302 in FIG. 3 and / or UE 1020 in FIG. 10, according to various example embodiments.

[0136] At step 602, the method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. In some embodiments, the one or more network-side additional conditions may relate to a physical characteristic of PRS. In some embodiments, the UE-side AI / ML-enabled positioning may be implemented using at least one or more UE-side AI / ML models.

[0137] At step 604, the method may further include receiving, from the network entity, a configuration associated with PRS configuration. In some embodiments, the configuration associated with PRS configuration may include a range of values, a binary value, or one of a high, medium, or low level. In some embodiments, the configuration associated with PRS configuration may be different from the UE- preferred configuration.

[0138] FIG. 7 illustrates an example of a flow diagram of a method 700 that may be performed by a NE, such as NE 308 illustrated in FIG. 3 and / or NE 1010 illustrated in FIG. 10 and / or a network function similar to network functions illustrated in FIG. 10, according to various example embodiments.

[0139] At step 702, the method may include receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. In some embodiments, the one or more network-side additional conditions may relate to a physical characteristic of PRS.

[0140] At step 704, the method may further include transmitting, to the user equipment, a configuration associated with PRS configuration. In some embodiments, the configuration associated with PRS configuration may include a range of values, a binary value, or one of a high, medium, or low level. In some embodiments, the configuration associated with PRS configuration may be different from the UE- preferred configuration.

[0141] FIG. 8 illustrates an example of a flow diagram of a method 800 that may be performed by a UE, such as UE 302 in FIG. 3 and / or UE 1020 in FIG. 10, according to various example embodiments.

[0142] At step 802, the method may include transmitting, to a network entity, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning. In some embodiments, the one or more network-sideadditional conditions may relate to a physical characteristic of PRS. In some embodiments, the UE-side AI / ML-enabled positioning may be implemented using at least one or more UE-side AI / ML models.

[0143] At step 804, the method may further include transmitting, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the UE.

[0144] At step 806, the method may further include receiving, from the network entity, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition. In some embodiments, the first configuration may include the UE-preferred configuration, a configuration similar to the UE-preferred configuration, or a configuration different from the UE-preferred configuration.

[0145] In some embodiments, the method may further include transmitting, to the network entity, a second indication for the request for PRS configuration. The second indication may indicate the requested PRS configuration to be used for the UE-side Al / ML-enabled positioning.

[0146] FIG. 9 illustrates an example of a flow diagram of a method 900 that may be performed by a NE, such as NE 308 illustrated in FIG. 3 and / or NE 1010 illustrated in FIG. 10 and / or a network function similar to network functions illustrated in FIG. 10, according to various example embodiments.

[0147] At step 902, the method may include receiving, from a user equipment, a request for positioning reference signal (PRS) configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. In some embodiments, the one or more network-side additional conditions may relate to a physical characteristic of PRS.

[0148] At step 904, the method may further include receiving, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment.

[0149] At step 906, the method may further include transmitting, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition. In some embodiments, the first configuration may include the UE-preferred configuration, a configuration similar to the UE-preferred configuration, or a configuration different from the UE-preferred configuration.

[0150] In some embodiments, the method may further include receiving, from the user equipment, a second indication for the request for PRS configuration. The second indication may indicate the requested PRS configuration to be used for the UE-side Al / ML-enabled positioning.

[0151] FIG. 10 illustrates an example of a system according to certain example embodiments. In one example embodiment, a system may include multiple devices, such as, for example, NE 1010 and / or UE1020.

[0152] NE 1010 may be one or more of a base station (e.g, 3G UMTS NodeB, 4G LTE Evolved NodeB, or 5G NR Next Generation NodeB), a serving gateway, a server, and / or any other access node or combination thereof.

[0153] NE 1010 may further include at least one gNB-centralized unit (CU), which may be associated with at least one gNB-distributed unit (DU). The at least one gNB-CU and the at least one gNB-DU may be in communication via at least one F1 interface, at least one Xn-C interface, and / or at least one NG interface via a 5thgeneration core (5GC).

[0154] UE 1020 may include one or more of a mobile device, such as a mobile phone, smart phone, personal digital assistant (PDA), tablet, or portable media player, digital camera, pocket video camera, video game console, navigation unit, such as a global positioning system (GPS) device, desktop or laptop computer, single-location device, such as a sensor or smart meter, or any combination thereof. Furthermore, NE 1010 and / or UE 1020 may be one or more of a citizens broadband radio service device (CBSD).

[0155] NE 1010 and / or UE 1020 may include at least one processor, respectively indicated as 1011 and1021. Processors 1011 and 1021 may be embodied by any computational or data processing device, such as a central processing unit (CPU), application specific integrated circuit (ASIC), or comparable device. The processors may be implemented as a single controller, or a plurality of controllers or processors.

[0156] At least one memory may be provided in one or more of the devices, as indicated at 1012 and 1022. The memory may be fixed or removable. The memory may include computer program instructions or computer code contained therein. Memories 1012 and 1022 may independently be any suitable storage device, such as a non-transitory computer-readable medium. The term "non-transitory,” as used herein, may correspond to a limitation of the medium itself ( / .a, tangible, not a signal) as opposed to a limitation on data storage persistency {e.g., random access memory (RAM) vs. read-only memory (ROM)). A hard disk drive (HDD), random access memory (RAM), flash memory, or other suitable memory may be used. The memories may be combined on a single integrated circuit as the processor, or may be separate from the one or more processors. Furthermore, the computer program instructions stored in the memory, andwhich may be processed by the processors, may be any suitable form of computer program code, for example, a compiled or interpreted computer program written in any suitable programming language.

[0157] Processors 1011 and 1021 , memories 1012 and 1022, and any subset thereof, may be configured to provide means corresponding to the various blocks of FIGs. 3-9. Although not shown, the devices may also include positioning hardware, such as GPS or micro electrical mechanical system (MEMS) hardware, which may be used to determine a location of the device. Other sensors are also permitted, and may be configured to determine location, elevation, velocity, orientation, and so forth, such as barometers, compasses, and the like.

[0158] As shown in FIG. 10, transceivers 1013 and 1023 may be provided, and one or more devices may also include at least one antenna, respectively illustrated as 1014 and 1024. The device may have many antennas, such as an array of antennas configured for multiple input multiple output (Ml MO) communications, or multiple antennas for multiple RATs. Other configurations of these devices, for example, may be provided. Transceivers 1013 and 1023 may be a transmitter, a receiver, both a transmitter and a receiver, or a unit or device that may be configured both for transmission and reception.

[0159] The memory and the computer program instructions may be configured, with the processor for the particular device, to cause a hardware apparatus, such as UE, to perform any of the processes described above ( / .e., FIGs. 3-9). Therefore, in certain example embodiments, a non-transitory computer- readable medium may be encoded with computer instructions that, when executed in hardware, perform a process such as one of the processes described herein. Alternatively, certain example embodiments may be performed entirely in hardware.

[0160] In certain example embodiments, an apparatus may include circuitry configured to perform any of the processes or functions illustrated in FIGs. 3-9. As used in this application, the term "circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry), (b) combinations of hardware circuits and software, such as (as applicable): (I) a combination of analog and / or digital hardware circuit(s) with software / firmware and (II) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions), and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation. This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuitor processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0161] FIG. 11 illustrates an example of a 5G network and system architecture according to certain example embodiments. Shown are multiple network functions that may be implemented as software operating as part of a network device or dedicated hardware, as a network device itself or dedicated hardware, or as a virtual function operating as a network device or dedicated hardware. The NE and UE illustrated in FIG. 11 may be similar to NE 1010 and UE 1020, respectively. The user plane function (UPF) may provide services such as intra-RAT and inter-RAT mobility, routing and forwarding of data packets, inspection of packets, user plane quality of service (QoS) processing, buffering of downlink packets, and / or triggering of downlink data notifications. The application function (AF) may primarily interface with the core network to facilitate application usage of traffic routing and interact with the policy framework.

[0162] According to certain example embodiments, processors 1011 and 1021 , and memories 1012 and 1022, may be included in or may form a part of processing circuitry or control circuitry. In addition, in some example embodiments, transceivers 1013 and 1023 may be included in or may form a part of transceiving circuitry.

[0163] In some example embodiments, an apparatus (e.g., NE 1010 and / or UE 1020) may include means for performing a method, a process, or any of the variants discussed herein. Examples of the means may include one or more processors, memory, controllers, transmitters, receivers, and / or computer program code for causing the performance of the operations.

[0164] In various example embodiments, apparatus 1020 may be controlled by memory 1022 and processor 1021 to receive, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration; and transmit, to the network entity, a request for PRS configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al)Zmachine learning (ML)-enabled positioning.

[0165] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration; and transmitting, to the network entity, a request for PRS configuration. The first configuration may includeone or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0166] In various example embodiments, apparatus 1010 may be controlled by memory 1012 and processor 1011 to transmit, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration; and receive, from the user equipment, a request for PRS configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)- side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0167] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration; and means for receiving, from the user equipment, a request for PRS configuration. The first configuration may include one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0168] In various example embodiments, apparatus 1020 may be controlled by memory 1022 and processor 1021 to transmit, to a network entity, a request for positioning reference signal (PRS) configuration; and receive, from the network entity, a configuration associated with PRS configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0169] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for transmitting, to a network entity, a request for positioning reference signal (PRS) configuration; and means for receiving, from the network entity, a configuration associated with PRS configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0170] In various example embodiments, apparatus 1010 may be controlled by memory 1012 and processor 1011 to receive, from a user equipment, a request for positioning reference signal (PRS) configuration; and transmit, to the user equipment, a configuration associated with PRS configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0171] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for receiving, from a user equipment, a request for positioning reference signal (PRS) configuration; and means for transmitting, to the user equipment, a configuration associated with PRS configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0172] In various example embodiments, apparatus 1020 may be controlled by memory 1022 and processor 1021 to transmit, to a network entity, a request for positioning reference signal (PRS) configuration; transmit, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the UE; and receive, from the network entity, a first configuration associated with PRS configuration. The request may indicate a user equipment (UE)- preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The first configuration may include at least one network-side additional condition.

[0173] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for transmitting, to a network entity, a request for positioning reference signal (PRS) configuration; means for transmitting, to the network entity, a first indication of detected performance degradation associated with the UE-side AI / ML- enabled positioning at the UE; and means for receiving, from the network entity, a first configuration associated with PRS configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The first configuration may include at least one networkside additional condition.

[0174] In various example embodiments, apparatus 1010 may be controlled by memory 1012 and processor 1011 to receive, from a user equipment, a request for positioning reference signal (PRS) configuration; receive, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment; and transmit, to the user equipment, a first configuration associated with PRS configuration. The first configuration may include at least one network-side additional condition. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning.

[0175] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for receiving, from a user equipment, a request for positioning reference signal (PRS) configuration; means for receiving, from the user equipment, a first indication of detected performance degradation associated with the UE-side AI / ML-enabled positioning at the user equipment; and means for transmitting, to the user equipment, a first configuration associated with PRS configuration. The request may indicate a user equipment (UE)-preferred PRS configuration for configuring one or more network-side additional conditions for UE-side artificial intelligence (Al) / machine learning (ML)-enabled positioning. The first configuration may include at least one networkside additional condition

[0176] The features, structures, or characteristics of example embodiments described throughout this specification may be combined in any suitable manner in one or more example embodiments. For example, the usage of the phrases "various embodiments,” "certain embodiments,” "some embodiments,” or other similar language throughout this specification refers to the fact that a particular feature, structure, or characteristic described in connection with an example embodiment may be included in at least one example embodiment. Thus, appearances of the phrases "in various embodiments,” "in certain embodiments,” "in some embodiments,” or other similar language throughout this specification does not necessarily all refer to the same group of example embodiments, and the described features, structures, or characteristics may be combined in any suitable manner in one or more example embodiments.

[0177] As used herein, "at least one of the following: ” and "at least one of ” and similar wording, where the list of two or more elements are joined by "and” or "or,” mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0178] Additionally, if desired, the different functions or procedures discussed above may be performed in a different order and / or concurrently with each other. Furthermore, if desired, one or more of the described functions or procedures may be optional or may be combined. As such, the description above should be considered as illustrative of the principles and teachings of certain example embodiments, and not in limitation thereof.

[0179] One having ordinary skill in the art will readily understand that the example embodiments discussed above may be practiced with procedures in a different order, and / or with hardware elements in configurations which are different than those which are disclosed. Therefore, although some embodiments have been described based upon these example embodiments, it would be apparent to those of skill in the art thatcertain modifications, variations, and alternative constructions would be apparent, while remaining within the spirit and scope of the example embodiments.

[0180] Partial Glossary

[0181] TRP Transmission Reception Point

[0182] PRS Positioning Reference Signal

[0183] ODPRS On-demand PRS

[0184] SRS Sounding Reference Signal

[0185] LOS Line-of-Sight

[0186] NLOS Non-Line-of-Sight

[0187] NW Network

[0188] AI / ML Artificial Intelligence I Machine Learning

[0189] LMF Location Management Function

[0190] ID Identifier

[0191] LCM Life Cycle Management

[0192] DC Data collection

[0193] ARP Antenna Reference Point

[0194] LPP LTE Positioning Protocol

[0195] DL-TDOA Downlink-Time Difference of Arrival

[0196] NRPPa NR Positioning Protocol A

[0197] posSI positioning System Information

[0198] 3GPP 3rdGeneration Partnership Project

[0199] 5G 5thGeneration

[0200] 5GC 5thGeneration Core

[0201] 6G 6thGeneration

[0202] ASIC Application Specific Integrated Circuit

[0203] CBSD Citizens Broadband Radio Service Device

[0204] CN Core Network

[0205] CPU Central Processing Unit

[0206] CU Centralized Unit

[0207] DL Downlink

[0208] DU Distributed Unit

[0209] eMBB Enhanced Mobile Broadband

[0210] eNB Evolved Node B

[0211] gNB Next Generation Node B

[0212] GPS Global Positioning System

[0213] HDD Hard Disk Drive

[0214] loT Internet of Things

[0215] LTE Long-Term Evolution

[0216] LTE-A Long-Term Evolution Advanced

[0217] MEMS Micro Electrical Mechanical System

[0218] MIMO Multiple Input Multiple Output

[0219] mMTC Massive Machine Type Communication

[0220] NE Network Entity

[0221] NG Next Generation

[0222] NG-eNB Next Generation Evolved Node B

[0223] NG-RAN Next Generation Radio Access Network

[0224] NR New Radio

[0225] PDA Personal Digital Assistance

[0226] QoS Quality of Service

[0227] RAM Random Access Memory

[0228] RAN Radio Access Network

[0229] RAT Radio Access Technology

[0230] RF Radio Frequency

[0231] ROM Read-Only Memory

[0232] UE User Equipment

[0233] UL Uplink

[0234] UMTS Universal Mobile Telecommunications System

[0235] UPF User Plane Function

[0236] URLLC Ultra-Reliable and Low-Latency Communication

[0237] UTRAN Universal Mobile Telecommunications System Terrestrial Radio AccessNetwork

Claims

WE CLAIM:1 . An apparatus, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration, wherein the first configuration comprises one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning; and transmit, to the network entity, a request for PRS configuration.

2. The apparatus according to claim 1 , wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: transmit, to the network entity, a first indication associated with the request for PRS configuration, wherein the first indication indicates the requested PRS configuration to be used for UE-side AI / ML- enabled positioning.

3. The apparatus according to claim 2, wherein the first indication is transmitted along with the request for PRS configuration or separately from the request for PRS configuration.

4. The apparatus according to claim 1, wherein the one or more network-side additional conditions comprise at least one of the following: at least one mandatory network-side additional condition, or at least one optional network-side additional condition.

5. The apparatus according to claim 1 , wherein the request for PRS configuration indicates at least one of the following: a UE-preferred PRS configuration for configuring the one or more network-side additional conditions; a selection of the first configuration; or at least one parameter of the one or more network-side additional conditions.

6. The apparatus according to claim 5, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive, from the network entity, a second configuration associated with PRS configuration, wherein the second configuration is the same as the UE-preferred PRS configuration.

7. The apparatus according to claim 5, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive, from the network entity, a second configuration associated with PRS configuration, wherein the second configuration is the same as the selection of the first configuration.

8. The apparatus according to claim 5, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive, from the network entity, a second configuration associated with PRS configuration, wherein the second configuration comprises at least one network-side additional condition that is different from the one or more network-side additional conditions of the UE-preferred PRS configuration.

9. The apparatus according to any of claims 1-8, wherein the one or more network-side additional conditions relate to a physical characteristic of PRS.

10. The apparatus according to any of claims 1-9, wherein the first configuration comprises a range of values, a binary value, or one of a high, medium, or low level.11 . The apparatus according to any of claims 1-10, wherein the UE-side AI / ML-enabled positioning is implemented using one or more UE-side AI / ML models.

12. The apparatus according to any of claims 1-11 , wherein the request for PRS configuration comprises at least one of the following: PRS identifier (ID) of candidate TRP, resource set, or periodicity.

13. The apparatus according to any of claims 1-12, wherein the first configuration further comprises at least one of the following: a list of parameters for data collection of the UE-side AI / ML-enabled positioning; a list of features for data collection of the UE-side AI / ML-enabled positioning;a list of parameters for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning; or a list of features for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning.

14. An apparatus, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration, wherein the first configuration comprises one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning; and receive, from the user equipment, a request for PRS configuration.

15. The apparatus according to claim 14, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive, from the user equipment, a first indication associated with the request for PRS configuration, wherein the first indication indicates the requested PRS configuration to be used for UE- side AI / ML-enabled positioning.

16. The apparatus according to claim 15, wherein the first indication is received along with the request for PRS configuration or separately from the request for PRS configuration.

17. The apparatus according to claim 14, wherein the one or more network-side additional conditions comprise at least one of the following: at least one mandatory network-side additional condition, or at least one optional network-side additional condition.

18. The apparatus according to claim 14, wherein the request for PRS configuration indicates at least one of the following: a UE-preferred PRS configuration for configuring the one or more network-side additional conditions;a selection of the first configuration; at least one parameter of the one or more network-side additional conditions;PRS identifier (ID) of candidate TRP; resource set; or periodicity.

19. The apparatus according to claim 18, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: transmit, to the user equipment, a second configuration associated with PRS configuration, wherein the second configuration is the same as the UE-preferred PRS configuration; or the second configuration is the same as the selection of the first configuration; or the second configuration comprises at least one network-side additional condition that is different from the one or more network-side additional conditions of the UE-preferred PRS configuration.

20. The apparatus according to claim 18, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: determine to transmit a second request for positioning reference signal (PRS) configuration based at least on receiving the request for PRS configuration; transmit, to one or more base stations, the second request for PRS configuration, wherein the second request requests that the one or more network-side additional conditions be configured according to the UE-preferred PRS configuration; and receive, from the one or more base stations, a response that indicates whether network-side additional condition is to be configured according to the UE-preferred PRS configuration or not.

21. The apparatus according to any of claims 14-20, wherein the one or more network-side additional conditions relate to a physical characteristic of PRS.

22. The apparatus according to any of claims 14-21 , wherein the first configuration comprises a range of values, a binary value, or one of a high, medium, or low level.

23. The apparatus according to any of claims 14-22, wherein the first configuration further comprises at least one of the following:a list of parameters for data collection of the UE-side AI / ML-enabled positioning; a list of features for data collection of the UE-side AI / ML-enabled positioning; a list of parameters for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning; or a list of features for maintaining consistency between training and inference of the UE-side AI / ML-enabled positioning.

24. A method, comprising: receiving, from a network entity, a first configuration associated with positioning reference signal (PRS) configuration, wherein the first configuration comprises one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning; and transmitting, to the network entity, a request for PRS configuration.

25. A method, comprising: transmitting, to a user equipment, a first configuration associated with positioning reference signal (PRS) configuration, wherein the first configuration comprises one or more network-side additional conditions for user equipment (UE)-side artificial intelligence (Al) / machine learning (ML)-enabled positioning; and receiving, from the user equipment, a request for PRS configuration.

Images