Broadcast of assistance data for artificial intelligence (AI) / machine learning (ML) model of positioning functionality
The solution addresses the lack of assistance data broadcasting for AI/ML positioning by enabling UE to validate and activate AI/ML models based on environmental conditions, ensuring effective AI/ML-based positioning in wireless communication systems.
Patent Information
- Application Number
- PCT/SE2024/050478
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-18
- Filing Date
- 2024-05-17
- Publication Date
- 2024-11-21
AI Technical Summary
Existing wireless communication systems lack configurations for supporting the broadcasting of assistance data for artificial intelligence (AI)/machine learning (ML) positioning functionality, which is essential for ensuring the validity and effectiveness of AI/ML models in UE-side and network-side positioning applications.
The proposed solution involves a method and apparatus for broadcasting assistance information in Positioning System Information Blocks (PosSIBs) to user equipment (UE), allowing the UE to determine the validity of its AI/ML model based on conditions such as TRP synchronization error, TRP location information, TRP antenna beam information, and DL reference signal transmit power, and enabling the activation of valid AI/ML models for location prediction.
This solution effectively manages AI/ML-based positioning by ensuring that AI/ML models are valid and operational in changing environments, enhancing positioning accuracy and reliability in both RRC IDLE and RRC CONNECTED states, and facilitating model updates when conditions are not met.
Smart Images

Figure SE2024050478_21112024_PF_FP_ABST
Abstract
Description
[0001] BROADCAST OF ASSISTANCE DATA FOR ARTIFICIAL INTELLIGENCE (AI) / MACHINE LEARNING (ML) MODEL OF POSITIONING FUNCTIONALITY
[0002] TECHNICAL FIELD
[0003] The present disclosure relates to wireless communications, and in particular, to configurations for supporting broadcasting of assistance data for artificial intelligence (AI) / machine learning (ML) positioning functionality.
[0004] BACKGROUND
[0005] The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile user equipments (UE), as well as communication between network nodes and between UEs. The 3GPP is also developing standards for Sixth Generation (6G) wireless communication networks.
[0006] Artificial Intelligence (Al), Machine Learning (ML) models and the need for retraining or retuning for operating environment changes
[0007] Artificial Intelligence (Al) and Machine Learning (ML) have been investigated as promising tools to optimize the design of the air-interface in wireless communication networks by both academia and industry. Example use cases include using autoencoders for CSI compression to reduce the feedback overhead and improve channel prediction accuracy, using deep neural networks for classifying LOS and NLOS conditions to enhance the positioning accuracy, using reinforcement learning for beam selection at the network side and / or the UE side to reduce the signaling overhead and beam alignment latency, and using deep reinforcement learning to leam an optimal precoding policy for complex MIMO precoding problems.
[0008] In 3GPP NR standardization work, there will be a new release 18 study item (SI) on AI / ML for NR air interface starting in May 2022. This study item will explore the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. Through studying a few selected use cases (e.g., CSI feedback, beam management and positioning), this SI aims at laying the foundation for future air-interface use cases leveraging AI / ML techniques. Building an AI / ML model includes several development steps where the actual training of the Al model is just one step in a training pipeline. One aspect of AI / ML development is AI / ML model lifecycle management. An example AI / ML model lifecycle management is illustrated in the diagram of FIG. 1, including a training pipeline 1 and an inference pipeline 2. The Al model lifecycle management typically includes:
[0009] • A training (re-training) pipeline 1, including one or more of: o Data ingestion (Step S2), which may include gathering raw (training) data from a data storage. After data ingestion, there may also be a step that controls the validity of the gathered data. o Data pre-processing (Step S4), which may include some feature engineering applied to the gathered data, e.g., it may include data normalization and possibly a data transformation required for the input data to the AI / ML model. o Perform the model training steps (Step S6). o Model evaluation (Step S8), which may include benchmarking the performance to some baseline. The iterative steps of model training and model evaluation continues until the acceptable level of performance is achieved. o Model registration (Step S10), which may include registering the AI / ML model, including any corresponding AI / ML-meta data that provides information on how the AI / ML model was developed, and possibly AI / ML model evaluations and performance outcomes.
[0010] • A deployment stage (SI 1) to make the trained (or re-trained) AI / ML model part of the inference pipeline 2.
[0011] • An inference pipeline 2, including one or more of: o Data ingestion (Step SI 2), which may include gathering raw (inference) data from a data storage. o Data pre-processing stage (Step SI 4), which may be typically identical or similar to corresponding processing that occurs in the training pipeline. o Model operational (Step SI 6), which may refer to using the trained and deployed model in an operational mode. o Data & model monitoring (Step SI 8), which may refer to validating that the inference data are from a distribution that aligns well with the training data, as well as monitoring model outputs for detecting any performance, or operational, drifts.
[0012] A drift detection stage (Step S20) that informs other entities or processes (e.g., the training pipeline 1) about any drifts in the model operations.
[0013] In a first scenario, it may be assumed that AI / ML models operating with the existing standard air-interface are placed at the UE side. A UE may be configured to use the AI / ML model(s) to generate output(s) that are reported (e.g., via a network node and / or transmit / receive points (TRPs)) to a centralized node (e.g., a management node) in the network for positioning the UE location.
[0014] In a second scenario, it may be assumed that AI / ML models operating with the existing standard air-interface are placed at different network nodes (and / or Transmit / Receive Points (TRPs)). A network node and / or TRP may be configured to use the AI / ML model(s) to generate output(s) that are reported to a centralized node (e.g., a management node) in the network for positioning the UE location.
[0015] Broadcast of assistance data for positioning
[0016] For NR positioning, assistance data may need to be provided by the location server (e.g., a location management function, LMF, which may be implemented, e.g., in a host computer, management node, network node, core node, etc.) to the target UE.
[0017] Positioning assistance data may be included in positioning System Information Blocks (posSIBs). The posSIBs may be carried in RRC System Information (SI) messages. The mapping of posSIBs (assistance data) to SI messages is flexibly configurable and provided to the UE in SIB1 for NG-RAN node.
[0018] The UE may request posSI by means of on-demand SI request in Radio Resource Control (RRC)_IDLE / RRC_INACTIVE and also request posSIBs by means of on- demand SI request in RRC CONNECTED.
[0019] For each assistance data element, a separate posSIB-type is defined. Each posSIB may be ciphered by the LMF using the 128-bit Advanced Encryption Standard (AES) algorithm (with counter mode), either with the same or different ciphering key. The posSIBs which exceed the maximum size limit may be segmented by the LMF.
[0020] In some existing systems, AI / ML based positioning using a UE-side model, additional assistance information may be needed, e.g., so that the UE may be able to check the AI / ML model validity. Thus, existing systems lack configurations for supporting broadcasting of assistance data for artificial intelligence (AI) / machine learning (ML) positioning functionality.
[0021] SUMMARY
[0022] Some embodiments advantageously provide methods, systems, and apparatuses for supporting broadcasting of assistance data for artificial intelligence (AI) / machine learning (ML) positioning functionality.
[0023] According to one aspect of the present disclosure, a method implemented in a UE is provided. The method includes receiving assistance information in at least one PosSIB for UE-side ML-based location prediction from a network node, the assistance information corresponding to at least one UE-side ML model validity condition. The method includes determining a validity of at least one UE-side ML model based on the received assistance information.
[0024] According to one or more embodiments of this aspect, the method further includes determining that the UE has entered a new cell; comparing at least one parameter of the assistance information associated with the at least one posSIB to a posSIB of another type associated with the new cell; and determining the validity of the at least one UE-side ML model based on whether the at least one parameter of the assistance information matches the posSIB of the other type within a predefined threshold.
[0025] According to one or more embodiments of this aspect, the UE-side ML model validity condition corresponds to at least one of: a TRP synchronization error; TRP location information; TRP antenna beam information; a DL reference signal transmit power; and at least one valid coverage area.
[0026] According to one or more embodiments of this aspect, the method further includes transmitting a first indication to the network node indicating that at least one UE-side ML model is valid; and upon receiving a second indication from the network node, activating the at least one valid UE-side ML model for location prediction.
[0027] According to one or more embodiments of this aspect, the method further includes receiving an indication of the at least one UE-side ML model being one of area specific and cell specific.
[0028] According to another aspect of the present disclosure, a UE is provided. UE is configured to receive assistance information in at least one PosSIB for UE-side ML-based location prediction from a network node , the assistance information corresponding to at least one UE-side ML model validity condition. UE is configured to determine a validity of at least one UE-side ML model based on the received assistance information.
[0029] According to one or more embodiments of this aspect, UE is further configured to: determine that the UE has entered a new cell; compare at least one parameter of the assistance information associated with the at least one posSIB to a posSIB of another type associated with the new cell; and determine the validity of the at least one UE-side ML model based on whether the at least one parameter of the assistance information matches the posSIB of the other type within a predefined threshold.
[0030] According to one or more embodiments of this aspect, the UE-side ML model validity condition corresponds to at least one of: a TRP synchronization error; TRP location information; TRP antenna beam information; a DL reference signal transmit power; and at least one valid coverage area.
[0031] According to one or more embodiments of this aspect, UE is further configured to: transmit a first indication to the network node indicating that at least one UE-side ML model is valid; and upon receiving a second indication from the network node , activate the at least one valid UE-side ML model for location prediction.
[0032] According to one or more embodiments of this aspect, UE is further configured to receive an indication of the at least one UE-side ML model being one of area specific and cell specific.
[0033] According to another aspect of the present disclosure, a method implemented in a network node is provided. The method includes: determining assistance information in at least one PosSIB for user equipment, UE, -side ML-based location prediction, the assistance information corresponding to at least one UE-side ML model validity condition; and transmitting the assistance information to a UE to enable the UE to determine a validity of at least one UE-side ML model.
[0034] According to one or more embodiments of this aspect, the method further includes: identifying a plurality of cells that share similar conditions within a predefined margin; and including in the assistance information an identification of the plurality of cells.
[0035] According to one or more embodiments of this aspect, the UE-side ML model validity condition corresponds to at least one of: a TRP synchronization error; TRP location information; TRP antenna beam information; a DL reference signal transmit power; and at least one valid coverage area.
[0036] According to one or more embodiments of this aspect, the method further includes receiving a first indication from the UE indicating that at least one UE-side ML model is valid; and in response to the first indication, transmitting a second indication to the UE to enable the UE to activate the at least one valid UE-side ML model.
[0037] According to one or more embodiments of this aspect, the method further includes indicating the at least one UE-side ML model being one of area specific and cell specific.
[0038] According to another aspect of the present disclosure, a network node is provided. Network node is configured to determine assistance information in at least one PosSIB for user equipment, UE, -side ML-based location prediction, the assistance information corresponding to at least one UE-side ML model validity condition, network node is configured to transmit the assistance information to a UE to enable the UE to determine a validity of at least one UE-side ML model.
[0039] According to one or more embodiments of this aspect, network node is further configured to: identify a plurality of cells that share similar conditions within a predefined margin; and include in the assistance information an identification of the plurality of cells.
[0040] According to one or more embodiments of this aspect, the UE-side ML model validity condition corresponds to at least one of: a TRP synchronization error; TRP location information; TRP antenna beam information; a DL reference signal transmit power; and at least one valid coverage area.
[0041] According to one or more embodiments of this aspect, network node is further configured to: receive a first indication from the UE indicating that at least one UE-side ML model is valid; and in response to the first indication, transmit a second indication to the UE to enable the UE to activate the at least one valid UE-side ML model.
[0042] According to one or more embodiments of this aspect, network node is further configured to indicate the at least one UE-side ML model being one of area specific and cell specific.
[0043] BRIEF DESCRIPTION OF THE DRAWINGS
[0044] A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:
[0045] FIG. 1 is a flowchart illustrating an example AI / ML model lifecycle management, including a training pipeline and an inference pipeline;
[0046] FIG. 2 is a schematic diagram of an example network architecture illustrating a communication system according to the principles in the present disclosure; FIG. 3 is a block diagram of a network node in communication with a UE over an at least partially wireless connection according to some embodiments of the present disclosure;
[0047] FIG. 4 is a flowchart of an example process in a network node for supporting broadcasting of assistance data for AI / ML positioning functionality according to some embodiments of the present disclosure;
[0048] FIG. 5 is a flowchart of an example process in a UE for supporting broadcasting of assistance data for AI / ML positioning functionality according to some embodiments of the present disclosure;
[0049] FIG. 6 is a flowchart of an example process in a network node according to some embodiments of the present disclosure; and
[0050] FIG. 7 is a flowchart of an example process in a UE according to some embodiments of the present disclosure.
[0051] DETAILED DESCRIPTION
[0052] Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to supporting broadcasting of assistance data for AI / ML positioning functionality. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein. Like numbers refer to like elements throughout the description.
[0053] As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.
[0054] In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate and modifications and variations are possible of achieving the electrical and data communication.
[0055] In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and / or wireless connections.
[0056] The term “network node” used herein can be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multistandard radio (MSR) radio node such as MSR BS, multi-cell / multicast coordination entity (MCE), integrated access and backhaul (IAB) node, relay node, donor node controlling relay, radio access point (AP), TRP, transmission points, transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a user equipment (UE) such as a wireless device (WD) or a radio network node.
[0057] The term transmission / reception point (TRP) (also referred to as a transmit and receive point) used herein may refer to one or more of a base station, a network node, a gNB, eNB, etc., which may be configured as and / or which may comprise one or more TRPs. In some embodiments, a TRP may be an entity or a set of entities responsible for the transmission and reception of signals and data between the network and the UE. The TRP may be a physical or virtual instance of a base station or a network node, including next-generation Node B (gNB) or evolved Node B (eNB), radio head, etc., each of which can be configured as and / or may comprise one or more TRPs. A TRP may consist of one or more transmission / reception (Tx / Rx) elements, such as antennas, antenna ports, etc., which may be deployed in a variety of configurations based on the particular system.
[0058] In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The UE herein can be any type of wireless device capable of communicating with a network node or another UE over radio signals, such as UE. The UE may also be a radio communication device, target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine communication (M2M), low-cost and / or low-complexity UE, a sensor equipped with UE, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device, etc.
[0059] Also, in some embodiments the generic term “radio network node” is used. It can be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi-cell / multicast Coordination Entity (MCE), IAB node, relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH).
[0060] Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and / or New Radio (NR), may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.
[0061] Note further, that functions described herein as being performed by a UE or a network node may be distributed over a plurality of UEs and / or network nodes. In other words, it is contemplated that the functions of the network node and UE described herein are not limited to performance by a single physical device and, in fact, can be distributed among several physical devices.
[0062] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
[0063] Some embodiments provide configurations for supporting broadcasting of assistance data for AI / ML positioning functionality.
[0064] Referring again to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 2 a schematic diagram of a communication system 10, according to an embodiment, such as a 3 GPP-type cellular network that may support standards such as LTE and / or NR (5G), which comprises an access network 12, such as a radio access network, and a core network 14. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). A coverage area 18 may also refer to and / or correspond to a cell. Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first UE 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second UE 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of UEs 22a, 22b (collectively referred to as UEs 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding network node 16. Note that although only two UEs 22 and three network nodes 16 are shown for convenience, the communication system may include many more UEs 22 and network nodes 16.
[0065] Also, it is contemplated that a UE 22 can be in simultaneous communication and / or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a UE 22 can have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, UE 22 can be in communication with an eNB for LTE / E-UTRAN and a gNB for NR / NG-RAN.
[0066] A network node 16 is configured to include a network (NW) location management function (LMF) unit 32 which is configured for supporting broadcasting of assistance data for AI / ML positioning functionality. A UE 22 is configured to include a UE AI / ML unit 34 which is configured for supporting broadcasting of assistance data for AI / ML positioning functionality. Example implementations, in accordance with an embodiment, of the UE 22 and network node 16 will now be described with reference to FIG. 3.
[0067] The communication system 10 includes a network node 16 provided in a communication system 10 and including hardware 58 enabling it to communicate with the with the UE 22. The hardware 58 may include a communication interface 60 for setting up and maintaining a wired or wireless connection with an interface of a different communication device of the communication system 10, as well as a radio interface 62 for setting up and maintaining at least a wireless connection 64 with a UE 22 located in a coverage area 18 served by the network node 16. The radio interface 62 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers.
[0068] In the embodiment shown, the hardware 58 of the network node 16 further includes processing circuitry 68. The processing circuitry 68 may include a processor 70 and a memory 72. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 68 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 70 may be configured to access (e.g., write to and / or read from) the memory 72, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).
[0069] Thus, the network node 16 further has software 74 stored internally in, for example, memory 72, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 74 may be executable by the processing circuitry 68. The processing circuitry 68 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by network node 16. Processor 70 corresponds to one or more processors 70 for performing network node 16 functions described herein. The memory 72 is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 74 may include instructions that, when executed by the processor 70 and / or processing circuitry 68, causes the processor 70 and / or processing circuitry 68 to perform the processes described herein with respect to network node 16. For example, processing circuitry 68 of the network node 16 may include NW LMF unit 32 configured for supporting broadcasting of assistance data for AI / ML positioning functionality.
[0070] The communication system 10 further includes the UE 22 already referred to. The UE 22 may have hardware 80 that may include a radio interface 82 configured to set up and maintain a wireless connection 64 with a network node 16 serving a coverage area 18 in which the UE 22 is currently located. The radio interface 82 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers.
[0071] The hardware 80 of the UE 22 further includes processing circuitry 84. The processing circuitry 84 may include a processor 86 and memory 88. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 84 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 86 may be configured to access (e.g., write to and / or read from) memory 88, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).
[0072] Thus, the UE 22 may further include software 90, which is stored in, for example, memory 88 at the UE 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the UE 22. The software 90 may be executable by the processing circuitry 84. The software 90 may include a client application 92. The client application 92 may be operable to provide a service to a human or non-human user via the UE 22. The client application 92 may interact with the user to generate the user data that it provides.
[0073] The processing circuitry 84 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by UE 22. The processor 86 corresponds to one or more processors 86 for performing UE 22 functions described herein. The UE 22 includes memory 88 that is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 90 and / or the client application 92 may include instructions that, when executed by the processor 86 and / or processing circuitry 84, causes the processor 86 and / or processing circuitry 84 to perform the processes described herein with respect to UE 22. For example, the processing circuitry 84 of the UE 22 may include a UE AI / ML unit 34 configured for supporting broadcasting of assistance data for AI / ML positioning functionality.
[0074] In some embodiments, the inner workings of the network node 16 and UE 22 may be as shown in FIG. 3 and independently, the surrounding network topology may be that of FIG. 2.
[0075] In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.
[0076] Although FIGS. 2 and 3 show various “units” such as NW LMF unit 32, cloud and UE AI / ML unit 34 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.
[0077] FIG. 4 is a flowchart of an example process in a network node 16 for supporting broadcasting of assistance data for AI / ML positioning functionality. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 68 (including the NW LMF unit 32), processor 70, radio interface 62 and / or communication interface 60. Network node 16 is configured to determine (Block SI 00) assistance information for user UE-side (also referred to as “UE- side” in the context of UEs 22) artificial intelligence / machine learning (AI / ML) based location prediction, the assistance information corresponding to at least one UE-side AI / ML model validity condition. Network node 16 is configured to cause transmission (Block SI 02) of the assistance information to a UE 22 for enabling the UE 22 to determine a validity of at least one UE-side AI / ML model.
[0078] In some embodiments, the network node 16 is further configured to identify a plurality of cells which share similar conditions within a predefined margin, where the assistance information identifies the plurality of cells.
[0079] In some embodiments, the model validity condition corresponds to at least one of a transmission / reception point (TRP) synchronization error, TRP location information, TRP antenna beam information, a downlink (DL) reference signal transmit power, and at least one valid coverage area.
[0080] In some embodiments, network node 16 is further configured to receive a first indication from the UE 22 indicating that at least one UE-side AI / ML model valid, and responsive to the first indication, cause transmission of a second indication to the UE 22 enabling the UE 22 to activate the at least one UE-side AI / ML model which is valid.
[0081] FIG. 5 is a flowchart of an example process in a UE 22 according to some embodiments of the present disclosure for supporting broadcasting of assistance data for AI / ML positioning functionality. One or more blocks described herein may be performed by one or more elements of UE 22 such as by one or more of processing circuitry 84 (including the UE AI / ML unit 34), processor 86, radio interface 82 and / or communication interface 60. UE 22 is configured to receive (Block SI 04) assistance information for UE- side (also referred to as UE-side in the context of UEs 22 which are UEs) artificial intelligence / machine learning (AI / ML) based location prediction from a network node 16, the assistance information corresponding to at least one UE-side AI / ML model validity condition. UE 22 is configured to determine (Block SI 06) the validity of at least one UE- side AI / ML model based on the received assistance information and a current state of the UE 22.
[0082] In some embodiments, the UE 22 is further configured to determine that the UE 22 has entered a new cell (e.g., coverage area 18), compare at least one parameter of the assistance information with at least one condition associated with the new cell, and determine the validity of the at least one UE-side AI / ML model based on whether the at least one parameter of the assistance information matches the at least one condition associated with the new cell within a predefined threshold.
[0083] In some embodiments, the model validity condition corresponds to at least one of a transmission / reception point (TRP) synchronization error, TRP location information, TRP antenna beam information, a downlink (DL) reference signal transmit power, and at least one valid coverage area.
[0084] In some embodiments, the UE 22 is further configured to transmit a first indication to the network node indicating that at least one UE-side AI / ML model is valid, and, responsive to receiving a second indication from the network node, activate the at least one valid UE-side AI / ML model for location prediction.
[0085] FIG. 6 is a flowchart of another example process in a network node 16 for supporting broadcasting of assistance data for AI / ML positioning functionality. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 68 (including the NW LMF unit 32), processor 70, radio interface 62 and / or communication interface 60. Network node 16 is configured to determine (Block SI 08) assistance information in at least one Positioning System Information Block, posSIB, for user equipment, UE, -side machine learning, ML, - based location prediction, the assistance information corresponding to at least one UE-side ML model validity condition, network node 16 is configured to transmit (Block SI 10) the assistance information to a UE 22 to enable the UE 22 to determine a validity of at least one UE-side ML model.
[0086] In some embodiments, network node 16 is further configured to: identify a plurality of cells that share similar conditions within a predefined margin; and include in the assistance information an identification of the plurality of cells.
[0087] In some embodiments, the UE-side ML model validity condition corresponds to at least one of: a transmission / reception point, TRP, synchronization error; TRP location information; TRP antenna beam information; a downlink, DL, reference signal transmit power; and at least one valid coverage area.
[0088] In some embodiments, network node 16 is further configured to: receive a first indication from the UE 22 indicating that at least one UE-side ML model is valid; and in response to the first indication, transmit a second indication to the UE 22 to enable the UE 22 to activate the at least one valid UE-side ML model.
[0089] In some embodiments, network node 16 is further configured to indicate the at least one UE-side ML model being one of area specific and cell specific.
[0090] FIG. 7 is another flowchart of an example process in a UE 22 according to some embodiments of the present disclosure for supporting broadcasting of assistance data for AI / ML positioning functionality. One or more blocks described herein may be performed by one or more elements of UE 22 such as by one or more of processing circuitry 84 (including the WD AI / ML unit 34), processor 86, radio interface 82 and / or communication interface 60. UE 22 is configured to receive (Block SI 12) assistance information in at least one Positioning System Information Block, posSIB, for UE-side machine learning, ML, -based location prediction from a network node 16, the assistance information corresponding to at least one UE-side ML model validity condition. UE 22 is configured to determine (Block S 114) a validity of at least one UE-side ML model based on the received assistance information.
[0091] In some embodiments, UE 22 is further configured to: determine that the UE 22 has entered a new cell; compare at least one parameter of the assistance information associated with the at least one posSIB to a posSIB of another type associated with the new cell; and determine the validity of the at least one UE-side ML model based on whether the at least one parameter of the assistance information matches the posSIB of the other type within a predefined threshold.
[0092] In some embodiments, the UE-side ML model validity condition corresponds to at least one of: a transmission / reception point, TRP, synchronization error; TRP location information; TRP antenna beam information; a downlink, DL, reference signal transmit power; and at least one valid coverage area.
[0093] In some embodiments, UE 22 is further configured to: transmit a first indication to the network node 16 indicating that at least one UE-side ML model is valid; and upon receiving a second indication from the network node 16, activate the at least one valid UE- side ML model for location prediction.
[0094] In some embodiments, UE 22 is further configured to receive an indication of the at least one UE-side ML model being one of area specific and cell specific.
[0095] Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for supporting broadcasting of assistance data for AI / ML positioning functionality.
[0096] With the broadcast of assistance data for UE-side model configurations, in some embodiments, AI / ML based positioning may be properly managed by UEs 22 in RRC IDLE and RRC INACTIVE state, for example. The UE 22 may be configured to request on-demand SIB for the positioning assistance data, as described herein.
[0097] Embodiments of the present disclosure provide apparatuses and methods for supporting various types of AI / ML based positioning, where an AI / ML model is located in the UE 22 (i.e., “UE-side”, “UE-based”, “UE-assisted”, etc.), which may also be referred to as “UE-side”, “UE-based”, “UE-assisted”, etc., in the context of UEs 22 which are UEs, for example.
[0098] Model validity conditions
[0099] In some embodiments, for the UE-side model for positioning, several conditions may be checked (e.g., by one or more of UE 22, network node 16, etc.) to determine if the trained AI / ML model is expected to function well (e.g., with satisfactory accuracy, speed, power, or other performance metrics). The positioning method may be UE 22-based or UE-22 assisted, including, for example:
[0100] • Case 1 : UE positioning with UE-side model, direct AI / ML or AI / ML assisted positioning; • Case 2a: UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning; and
[0101] • Case 2b: UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning.
[0102] The model validity conditions may include one or more of the following:
[0103] • TRP synchronization error;
[0104] • TRP location information;
[0105] • TRP antenna beam information. The beam information may include beam pattern information and / or beam power information. The beam pattern information may be expressed by azimuth and elevation.
[0106] • DL reference signal transmit power. For positioning, typically the DL reference signal is DL PRS.
[0107] • An area (e.g., coverage area 18) where an AI / ML model should be valid. The area may be identified by an area ID. In a preferred example, the area is composed of one or more cells (e.g., coverage areas 18), and each cell may be identified by a cell ID.
[0108] The NW LMF unit 32 (and / or network node 16, etc.) may be configured to send the above information of the deployment to the target UE 22 via broadcast message(s), e.g., via a network node 16, TRP 63, etc. This allows the target UE 22 to check whether the trained AI / ML model of the target UE 22 (e.g., implemented in or by UE AI / ML unit 34) is compatible with the deployment environment.
[0109] • In some embodiments, if the target UE 22 verifies that all the model validity conditions of the deployment environment are compatible with the AI / ML model, then the model may be eligible for operation. The UE 22 may be configured to determine / decide to activate the AI / ML model by itself (e.g., without requiring or waiting for additional signaling or control information from another entity such as a network node 16). Alternatively, the UE 22 may be configured to notify the network node 16 (e.g., a location server, NW LMF unit 32) that the UE 22's model is available, so that the network node 16 may decide whether and when to activate UE 22's model, and signals the decision to the UE 22 (e.g., via network node 16, TRP 63, etc ).
[0110] • In some embodiments, if any of the model validity conditions of the deployment environment are not compatible with the AI / ML model, then the UE 22's model may not be eligible for operation in this deployment. The UE 22 may be configured to signal to the network node 16 that UE 22 cannot support the positioning functionality with its AI / ML model. The UE 22 may also be configured to take action to update its model. For example, a procedure may be triggered to collect training data for the current deployment (e.g., from UE 22, from other UEs 22, from network nodes 16, etc.), re-train and / or fine-tune the model, so that an updated model may be eligible for operation in the current deployment. In another example, the UE 22 may be configured to receive a new model (e.g., from network node 16, and / or via model transfer or model delivery from a server) for the current deployment.
[0111] In the discussion above, for simplicity, it may be in some cases assumed that the UE 22 is configured with one AI / ML model for the desired positioning functionality. In some embodiments, the UE 22 may be configured with multiple AI / ML models for such functionality. In this case, the checking of the model validity conditions (e.g., by UE 22) may be performed on all (or at least a plurality ol) the candidate AI / ML models. As long as one of the candidate AI / ML model(s) is compatible with the deployment environment, the positioning functionality may be supported by the UE 22 with the AI / ML model, and the compatible model may be identified and selected for operation (e.g., by UE 22). On the other hand, if none of the candidate AI / ML models is compatible with the deployment environment, then in some embodiments, it may be determined (e.g., by UE 22) that the positioning functionality cannot be supported by the UE 22 with any of the AI / ML models which are available and / or configured and / or configurable.
[0112] In some embodiments, a UE 22 with AI / ML positioning capability may be configured to request posSI by means of on-demand SI request in RRC IDLE / RRC INACTIVE and also to request posSIBs by means of on-demand SI request in RRC CONNECTED. The posSI may provide model validity information to the UE 22 to support the operation of UE-side AI / ML model for positioning, including Cases 1, 2a, 2b, described above. Such requests may, e.g., be transmitted / sent by UE 22 to one or more of a network node 16, etc.
[0113] In the following, some examples of model validity conditions are discussed in further detail to illustrate the methodology of some embodiments of the present disclosure.
[0114] TRP synchronization error as model validity condition
[0115] In one embodiment, TRP synchronization error is checked as a model validity condition. When a UE 22 receives the TRP synchronization error information from the network (e.g., via one or more of NW LMF unit 32, network node 16, etc.), then the UE 22 may be configured to compare such received information of the deployment scenario with the stored information of the UE 22's AI / ML model. For this case, the stored information is a type of meta data which indicates the acceptable range of network synchronization error of the trained AI / ML model.
[0116] • In some embodiments, if the TRP synchronization error (e.g., up to 50ns error) of current deployment is larger than the acceptable range (e.g., 0 - 20ns) of the AI / ML model, then the AI / ML model may not be expected to work well, and the AI / ML model should not be activated (e.g., by UE 22). The UE 22 may be configured to perform positioning using conventional (non- AI / ML) positioning methods, for example, as a backup / fallback mechanism. The UE 22 may also / altematively be configured to attempt to update its AI / ML model so that it is adapted to the current deployment scenario.
[0117] • On the other hand, in some embodiments, if the TRP synchronization error (e.g., up to 20ns error) of current deployment is within the acceptable range (0 - 30ns) of the AI / ML model, then the AI / ML model may be considered for activation (e.g., by UE 22).
[0118] In terms of signaling, the TRP synchronization error may be provided, for example, by parameter subframeOffset in NR-RTD-Info, as illustrated below.
[0119] NR-RTD-Info
[0120] The IE NR-RTD-Info is used by the location server to provide time synchronization information between a reference TRP and a list of neighbour TRPs.
[0121] - ASN1 START
[0122] NR-RTD-Info-rl6 ::= SEQUENCE { referenceTRP-RTD-Info-rl6 ReferenceTRP-RTD-Info-rl6, rtd-InfoList-r 16 RTD-InfoList-r 16,
[0123] ReferenceTRP-RTD-Info-rl 6 ::= SEQUENCE { dl-PRS-ID-Ref-r!6 INTEGER (0..255), nr-PhysCellID-Ref-r!6 NR-PhysCellID-rl6 OPTIONAL, - Need
[0124] ON nr-CellGlobalID-Ref-rl6 NCGI-rl5 OPTIONAL, - Need
[0125] ON nr-ARFCN-Ref-r!6 ARFCN-ValueNR-rl 5 OPTIONAL, - Need
[0126] ON refTime-rl6 CHOICE { systemFrameNumber-r!6 BIT STRING (SIZE (10)), utc-r!6 UTCTime, rtd-RefQuality-r!6 NR-TimingQuality-rl 6 OPTIONAL, — Need ON
[0127] RTD-InfoList-rl 6 ::= SEQUENCE (SIZE (L.nrMaxFreqLayers-rl6)) OF RTD-
[0128] InfoListPerF reqLay er-r 16
[0129] RTD-InfoListPerFreqLayer-rl6 ::= SEQUENCE (SIZE(l..nrMaxTRPsPerFreq-rl6)) OF
[0130] RTD-InfoElement-r 16
[0131] RTD-InfoElement-rl6 ::= SEQUENCE { dl-PRS-ID-r!6 INTEGER (0..255), nr-PhysCellID-rl6 NR-PhysCellID-rl6 OPTIONAL, - Need
[0132] ON nr-CellGlobalID-rl6 NCGI-rl5 OPTIONAL, - Need
[0133] ON nr-ARFCN-r!6 ARFCN-ValueNR-rl 5 OPTIONAL, - Need
[0134] ON subframeOffset-rl6 INTEGER (0..1966079), rtd-Quality-r!6 NR-TimingQuality-rl 6,
[0135] - ASN1STOP subfiameOffset
[0136] This field specifies the subframe boundary offset at the TRP antenna location between the reference TRP and this neighbour TRP in time units Tc= l / AffmaxQ) where A / max= 480 ■ 103Hz and Nf= 4096 (TS 38.211
[0041] ).
[0137] The offset is counted from the beginning of a subframe #0 of the reference TRP to the beginning of the closest subsequent subframe of this neighbour TRP.
[0138] Scale factor 1 Tc.
[0139] DL reference signal transmit power
[0140] In one embodiment, a DL reference signal (i. e. , DL PRS) transmit power is checked as a model validity condition, e.g., by UE 22 and / or UE AI / ML unit 34. When a UE 22 receives the DL PRS transmit power information from the network (e.g., via one or more of NW LMF unit 32, network node 16, etc.), the UE 22 may compare such received information of the deployment scenario with the stored information of the UE 22's AI / ML model. For this case, the stored information may be, for example, a type of meta data which indicates the acceptable range of DL PRS transmit power of the trained AI / ML model.
[0141] • In some embodiments, if the DL PRS transmit power (e.g., 10 dBm) of a current deployment is outside the acceptable range (e.g., 15 to 30 dBm) of the AI / ML model, then the AI / ML model may not be expected to work well, and the AI / ML model should not be activated. The UE 22 may perform positioning using conventional (non- AI / ML) positioning methods. The UE 22 may also be configured to attempt to update its AI / ML model so that it is adapted to the current deployment scenario.
[0142] • On the other hand, in some embodiments, if the DL PRS transmit power (e.g., 23 dBm) of current deployment is within the acceptable range (e.g., 15 to 30 dBm) of the AI / ML model, then the AI / ML model may be considered (e.g., by UE 22 )for activation.
[0143] In terms of signalling, the DL PRS transmit power may, for example, be provided by parameter dl -PRS -ResourcePower in NR-DL-PRS-ResourceSet, as illustrated below. NR-DL-PRS-ResourceSet is carried as a component of NR-DL-PRS-AssistanceData. Thus, for example, the network, such as via one or more of NW LMF unit 32, network node 16, etc., may signal NR-DL-PRS-AssistanceData to the UE 22, which is broadcast in the cell (e.g., a coverage area 18) via posSibType6-l.
[0144] NR-DL-PRS-ResourceSet-rl6 ::= SEQUENCE { nr-DL-PRS-ResourceSetID-r!6 NR-DL-PRS-ResourceSetID-rl6, dl-PRS-Periodicity-and-ResourceSetSlotOffset-r!6
[0145] NR-DL-PRS-Periodicity-and-
[0146] ResourceSetSlotOffset-r 16, dl-PRS-ResourceRepetitionFactor-r!6 ENUMERATED {n2, n4, n6, n8, n!6, n32,
[0147] OPTIONAL,
[0148] - Need OP dl-PRS-ResourceTimeGap-r 16 ENUMERATED {si, s2, s4, s8, s!6, s32, ...} OPTIONAL,
[0149] - Cond Rep dl-PRS-NumSymbols-rl6 ENUMERATED {n2, n4, n6, n!2, ...}, dl-PRS-MutingOptionl -r 16 DL-PRS -MutingOption 1 -r 16 OPTIONAL, - Need OP dl-PRS-MutingOption2-r 16 DL-PRS -MutingOption2-r 16 OPTIONAL, - Need OP dl-PRS-ResourcePower-rl6 INTEGER (-60..50), dl-PRS-ResourceList-r!6 SEQUENCE (SIZE
[0150] (L.nrMaxResourcesPerSet-rl6)) OF
[0151] NR-DL-PRS-
[0152] Resource-rl6, dl-PRS-ResourcePower
[0153] This field specifies the average EPRE of the resources elements that carry the
[0154] PRS in dBm that is used for PRS transmission. The UE assumes constant EPRE is used for all REs of a given DL-PRS resource.
[0155] Area ID as model validity condition
[0156] In one embodiment, the area ID may be checked (e.g., by UE 22, by network node 16, etc.) as a model validity condition. When a UE 22 receives the area ID from the network (e.g., via one or more of NW LMF unit 32, network node 16, etc.), then the UE 22 may be configured to compare the area ID of the deployment scenario with the stored information of the UE 22's AI / ML model. Here, the area(s) (e.g., coverage areas 18, or some other defined area) that the model has been trained for are stored (e.g., in memory 88) as part of the metadata of the model.
[0157] • In some embodiments, if the AI / ML model has not been trained for the current area (e.g., a coverage area 18, or some other defined area), then the AI / ML model may not be expected to work well, and the AI / ML model should not be activated (e.g., by UE 22). The UE 22 may, as an alternative, perform positioning using conventional (non- AI / ML) positioning methods. The UE 22 may also be configured to try to update its AI / ML model so that it is adapted to the current deployment scenario.
[0158] • On the other hand, in some embodiments, if the AI / ML model has been trained for the current area, then the AI / ML model may be considered for activation.
[0159] In terms of signalling, the area ID can be represented, for example, by the ArealD- CellList information element as shown below, which may be provided by the network (e.g., via one or more of NW LMF unit 32, network node 16, etc.) to the UE 22, or vice- versa.
[0160] - ArealD-CellList
[0161] The IE ArealD-CellList provides the NR Cell-IDs of the TRPs belonging to a particular network area. It can be used to indicate the validity area of an AI / ML model.
[0162] - ASN1 START
[0163] AreaID-CellList-rl7 ::= SEQUENCE (SIZE(l..maxCellIDsPerArea-rl7)) OF NR-Cell-
[0164] IDs-rl7
[0165] NR-Cell-IDs-rl7 ::= SEQUENCE { nr-CellGlobalID-r!7 NCGI-rl5 OPTIONAL, -
[0166] Need ON nr-Phy sCelllD-r 17 NR-PhysCellID-rl6 OPTIONAL, -
[0167] Need ON nr-ARFCN-r!7 ARFCN-ValueNR-rl5 OPTIONAL, -
[0168] Need ON - ASN1ST0P
[0169] Assistance data for the model validity condition
[0170] In an embodiment, an example posSIB type (e.g., posSibType7-l) is defined for carrying assistance data for UE-side model for positioning (e.g., aNR-AIML- AssistanceData IE), which may be signaled by the network (e.g., via one or more of NW LMF unit 32, network node 16, etc.) to the UE 22, or vice-versa.
[0171] In the following, the NR-AIML-AssistanceData IE is illustrated below, which includes the TRP synchronization error, and area ID. It is understood that other information elements for AI / ML model operating condition may be included in a similar manner.
[0172] NR-AIML-AssistanceData ::= SEQUENCE {
[0173] NR-TRP-Sync-Info NR-RTD-Info OPTIONAL -
[0174] Need ON
[0175] AIMLModel Validity Area ArealD-CellList OPTIONAL
[0176] Need ON
[0177] In some embodiments, broadcast of positioning assistance data (e.g., by the network, such as via one or more of NW LMF unit 32, network node 16, etc.) may be supported via Positioning System Information Blocks (posSIBs). The posSIBs may be carried in RRC System Information (SI) messages. For example, for NR RRC System Information (SI), a single SIBpos IE may be defined, which may be carried in IE PosSystemInformation-rl6-IEs. An example mapping of posSibType to assistance data element is shown in Table 1 below:
[0178] Table 1: Mapping of posSibType to assistanceDataElement In an alternative embodiment, multiple new posSIB types (e.g., posSibType7-l, posSibType7-2) may be defined for carrying assistance data for UE-side model for positioning (e.g., transmitted by the network, such as via one or more of NW LMF unit 32, network node 16, etc., to the UE 22).
[0179] This is illustrated with the example below, where posSibType7-l provides the TRP synchronization information, and posSibType7-2 provides the area ID where the AI / ML model is expected to function.
[0180] Table 2: Mapping of two new posSibType to assistanceDataElement
[0181] RRC signalling
[0182] An example assistance data element for assisting with positioning is shown below. This example may also support the broadcast data for providing UE-side AI / ML model validity conditions (e.g., by the network, such as via one or more of NW LMF unit 32, network node 16, etc., to UE 22). For example, if following Table 1 for the mapping, then: if the posSibType in IE PosSIB-Type indicates 'posSibType7-l', the assistanceDataElement OCTET STRING includes the LPP IE NR-AIML-AssistanceData.
[0183] AssistanceDataSIBelement
[0184] In some embodiments, the IE AssistanceDataSIBelement may be used in the IE SystemlnformationBlockPos as specified in TS 36.331 and IE SIBpos as specified in TS 38.331, for example:
[0185] AssistanceDataSIBelement-rl5 ::= SEQUENCE { valueTag-r!5 INTEGER (0..63)
[0186] OPTIONAL, - Need OP expirationTime-rl 5 UTCTime
[0187] OPTIONAL, - Need OP cipheringKeyData-r 15 CipheringKeyData-r 15 OPTIONAL, -
[0188] Need OP segmentationlnfo-r 15 Segmentationlnfo-rl 5 OPTIONAL, -
[0189] Need OP assistanceDataElement-rl 5 OCTET STRING, Using Table 1 as an example for the posSibType to assistanceDataElement mapping, some RRC signalling may be updated as shown below, so that posSibType7-l is supported to provide NR-AIML-AssistanceData. The new broadcast message facilitates the signalling of assistance data for UE-side AI / ML model for the positioning functionality (e.g., by the network, such as via one or more of NW LMF unit 32, network node 16, to UE 22).
[0190] DedicatedSIBRequest
[0191] An example DedicatedSIBRequest message according to some embodiments of the present disclosure is provided below.
[0192] The DedicatedSIBRequest message is used to request SIB(s) required by the UE in
[0193] RRC CONNECTED as specified in clause 5.2.2.3.5.
[0194] Signalling radio bearer: SRB1
[0195] RLC-SAP: AM
[0196] Logical channel: DCCH
[0197] Direction: UE to Network
[0198] DedicatedSIBRequest message
[0199] DedicatedSIBRequest-rl 6 ::= SEQUENCE { criticalExtensions CHOICE { dedicatedSIBRequest-r!6 DedicatedSIBRequest-rl6-IEs, criticalExtensionsFuture SEQUENCE {}
[0200] PosSIB-ReqInfo-rl6 ::= SEQUENCE { gnss-id-r!6 GNSS-ID-rl6 OPTIONAL, sbas-id-r!6 SBAS-ID-H6 OPTIONAL, posSibType-r!6 ENUMERATED { posSibTypel-1, posSibTypel-2, posSibTypel-3, posSibTypel-4, posSibTypel-5, posSibTypel-6, posSibTypel-7, posSibTypel-8, posSibType2-l, posSibType2-2, posSibType2-3, posSibType2-4, posSibType2-5, posSibType2-6, posSibType2-7, posSibType2-8, posSibType2-9, posSibType2-10, posSibType2-l l, posSibType2-12, posSibType2-13, posSibType2-14, posSibType2-15, posSibType2-16, posSibType2-17, posSibType2-18, posSibType2-19, posSibType2-20, posSibType2-21, posSibType2-22, posSibType2-23, posSibType3-l, posSibType4-l, posSibType5-l, posSibType6-l, posSibType6-2, posSibType6-3,..., posSibTypel-9-vl710, posSibTy pe 1-10-v 1710, posSibType2-24-v 1710, posSibType2-25-v 1710, posSibTy pe6-4-v 1710, posSibTy pe6-5 -v 1710, posSibType6-6-vl710, posSibType7-l }
[0201] PosSystemInformation-rl6-IEs ::= SEQUENCE { posSIB-TypeAndlnfo-r 16 SEQUENCE (SIZE (L .maxSIB)) OF CHOICE { posSibl-l-rl6 SIBpos-rl6, posSibl-2-rl6 SIBpos-rl6, posSib6-6-vl700 SIBpos-rl6 posSib7-l SIBpos-rl6 lateNonCriticalExtension OCTET STRING OPTIONAL, nonCriticalExtension SEQUENCE {} OPTIONAL
[0202] - PosSI-Schedulinglnfo
[0203] PosSI-SchedulingInfo-rl6 ::= SEQUENCE { posSchedulinglnfoList-rl 6 SEQUENCE (SIZE (L.maxSI-Message)) OF
[0204] PosSchedulingInfo-rl6, posSI-RequestConfig-rl6 SI-RequestConfig
[0205] OPTIONAL, - Cond MSG-1 posSI-RequestConfigSUL-rl 6 S I-RequestC onfig
[0206] OPTIONAL, - Cond SUL-MSG- 1 [[ posSI-RequestConfigRedCap-rl 7 SI-RequestConfig
[0207] OPTIONAL - Cond REDCAP-MSG-1
[0208] ]]
[0209] PosSchedulingInfo-rl6 ::= SEQUENCE { offsetToSI-Used-r!6 ENUMERATED {true}
[0210] OPTIONAL, - Need R posSI-Periodicity-r!6 ENUMERATED {rf8, rf!6, rf32, rf64, rf!28, rf256, rf512}, posSI-BroadcastStatus-r!6 ENUMERATED {broadcasting, notBroadcasting}, posSIB-Mapping!nfo-rl6 PosSIB-MappingInfo-rl6,
[0211] PosSIB-MappingInfo-rl6 ::= SEQUENCE (SIZE (L.maxSIB)) OF PosSIB-Type-rl6
[0212] PosSIB-Type-rl6 ::= SEQUENCE { encrypted-r!6 ENUMERATED { true }
[0213] OPTIONAL, - Need R gnss-id-r!6 GNSS-ID-rl6 OPTIONAL, -
[0214] Need R sbas-id-r!6 SBAS-ID-rl6 OPTIONAL, -
[0215] Need R posSibType-r!6 ENUMERATED { posSibTypel-1, posSibTypel-2, posSibTypel-3, posSibTypel-4, posSibTypel-5, posSibTypel-6, posSibTypel-7, posSibTypel-8, posSibType2-l, posSibType2-2, posSibType2-3, posSibType2-4, posSibType2-5, posSibType2-6, posSibType2-7, posSibType2-8, posSibType2-9, posSibType2-10, posSibType2-l l, posSibType2-12, posSibType2-13, posSibType2-14, posSibType2-15, posSibType2-16, posSibType2-17, posSibType2-18, posSibType2-19, posSibType2-20, posSibType2-21, posSibType2-22, posSibType2-23, posSibType3-l, posSibType4-l, posSibType5-l,posSibType6-l, posSibType6-2, posSibType6-3, posSib7-l,... }, areaScope-rl6 ENUMERATED {true}
[0216] OPTIONAL - Need S
[0217] SIBpos
[0218] SIBpos-rl6 ::= SEQUENCE { assistanceDataSIB-Element-r!6 OCTET STRING, lateNonCriticalExtension OCTET STRING OPTIONAL,
[0219] SIBpos field descriptions assistanceDataSIB-Element
[0220] Parameter AssistanceDataSIBelement defined in TS 37.355
[0049] , The first / lefimost bit of the first octet contains the most significant bit.
[0221] Procedures for a UE 22 to check its AI / ML model validity using the newly defined posSIB type
[0222] Using Table 1 as an example for the posSibType to assistanceDataElement mapping, the overall steps for some embodiments of the present disclosure, from a network perspective (e.g., from the perspective of one or more of NW LMF unit 32, network node 16, etc.) is as follows. Note that in some embodiments, the order among steps 1000 - 1030 may be changed, and further, that in some embodiments, only a subset of the steps are used. Step SI 000: The network node 16 is configured to identify cells (e.g., coverage areas 18) sharing the same (or closely similar within a predefined margin) conditions for UE-sided AI / ML-based prediction.
[0223] Step S1010: The network node 16 is configured to configure the assistance data in the NR-AIML-AssistanceData IE, and set this IE in the AssistanceDataSIBelement IE contained in the posSIB which is configured to be the posSIB7-l type. Step S1020: The network node 16 is configured to set the valueTag for the posSIB message in SIB1 to be the version of the assistance data. The valueTag is incremented every time the assistance data is changed.
[0224] Step S1030: The network node 16 is configured to set the areaScope for the posSIB message in SIB1. The areaScope is set to true to indicate that the posSIB is area specific. If the field is absent, the posSIB is cell specific.
[0225] Step SI 040: The network node 16 is configured to broadcast (or to cause a broadcast ol) SIB1 and the posSIB, e.g., to the UE 22.
[0226] Accordingly, from a UE 22 perspective, a UE 22, e.g., using processing circuitry 84, AI / ML unit 34, etc., may be configured to perform one or more of the following:
[0227] Step S2000: UE 22 acquires SIB1 and the posSIB with posSIB7-l type from a cell (coverage area 18), and stores the posSIB together with the associated data (e.g., SystemlnformationArealD, NR-AIML-AssistanceData, expirationTime, valueTag, and areaScope)
[0228] A UE 22, e.g., using processing circuitry 84, AI / ML unit 34, etc., may perform this step multiple times in the same cell, or / and perform this steps multiple times for different cells, hence, the UE 22 may store multiple posSIBs with the posSIB7-l type.
[0229] Step S2010: UE 22 enters a new cell or reconnects to the same cell.
[0230] Step S2020: UE 22 acquires SIB1 from the serving cell.
[0231] Step S2030: UE 22 compares the associated information for each stored posSIBs with the posSIB7-l type (e.g., SystemlnformationArealD, NR-AIML-AssistanceData, expirationTime, valueTag, and areaScope) with the information received from SIB1: a) If the information matches for a stored posSIBs with the posSIB7-l type, UE 22 considers the stored posSIB as valid for the serving cell. An optional UE 22 action can be that the is configured to UE 22 select the AI / ML-based positoning model trained for the condition indicated by the valid posSIB. b) If none of the stored posSIBs with the posSIB7-l type match to the information acquired from SIB1, then no stored posSIBs with the posSIB7-l type is valid. Optional UE 22 actions may include the UE 22 being configured to request fallback to a non-ML positioning algorithm, or / and the UE 22 being configured to acquire posSIB with the posSIB7-l type from the serving cell, or / and the UE 22 request data collection for the current condition in the serving cell.
[0232] Area ID in various life cycle management stages of the AI / ML model In addition to model inference for AI / ML model deployment, the area ID may be used (e.g., by one or more of UE 22, network node 16, etc.) in other life cycle management stages of the AI / ML model.
[0233] Model training
[0234] For training data collection and model training, all the cells in a given area (e.g., associated with a given area ID) may need to be covered. Adequate training data should be collected from all the cells (e.g., by one or more of UE 22, network node 16, etc.).
[0235] In some embodiments, when performing model training, data from all the cells in a given area may be ingested (e.g., by one or more of UE 22, network node 16, etc.), so that the trained model may be expected to work well (e.g., when deployed in a UE 22) in any of the cells in the given area.
[0236] Model monitoring
[0237] For model monitoring, data may be collected (e.g., by one or more of UE 22, network node 16, etc.) when the target UE 22 is any of the cells in a given area. If the model is detected to have unsatisfactory performance in any of the cells, then an alarm may be configured (e.g., by one or more of UE 22, network node 16, etc.) to be triggered. Subsequent action may be taken (e.g., by one or more of UE 22, network node 16, etc.), to either deactivate the model, or to switch to a different model, or to update the model.
[0238] Model update / model switching / model fine-tuning / model re-training
[0239] In some embodiments, when the UE 22 decides to change the model to a new one, the UE 22 may need to be configured to ensure that the new model is expected to work well in all the cells in a given area (e.g., associated with a given area ID). The UE 22 may be configured to change the model by any of the following: model update, model switching, model fine-tuning, and / or model re-training.
[0240] Example Embodiments:
[0241] Example Al . A network node 16 comprising processing circuitry configured to: determine assistance information for user equipment-side (UE-side) artificial intelligence / machine learning (AI / ML) based location prediction, the assistance information corresponding to at least one UE-side AI / ML model validity condition; and cause transmission of the assistance information to a UE 22 for enabling the UE 22 to determine a validity of at least one UE-side AI / ML model.
[0242] Example A2. The network node 16 of Example Al, wherein the method further comprises: identifying a plurality of cells which share similar conditions within a predefined margin; and the assistance information identifying the plurality of cells. Example A3. The network node 16 of any one of Examples Al and A2, wherein the model validity condition corresponds to at least one of: a transmission / reception point (TRP) synchronization error; TRP location information; TRP antenna beam information; a downlink (DL) reference signal transmit power; and at least one valid coverage area.
[0243] Example A4. The network node 16 of any one of Examples Al -A3, wherein the processing circuitry is further configured to: receive a first indication from the UE 22 indicating that at least one UE-side AI / ML model valid; and responsive to the first indication, cause transmission of a second indication to the UE 22 enabling the UE 22 to active the at least one UE-side AI / ML model which is valid.
[0244] Example Bl. A method implemented in a network node 16, the method comprising: determining assistance information for user equipment-side (UE-side) artificial intelligence / machine learning (AI / ML) based location prediction, the assistance information corresponding to at least one UE-side AI / ML model validity condition; and transmitting the assistance information to the UE 22 for enabling a UE 22 to determine a validity of at least one UE-side AI / ML model.
[0245] Example B2. The method of Example Bl, further comprising: identifying a plurality of cells which share similar conditions within a predefined margin; and including in the assistance information an identification of the plurality of cells.
[0246] Example B3. The method of any one of Examples Bl and B2, wherein the model validity condition corresponds to at least one of: a transmission / reception point (TRP) synchronization error; TRP location information; TRP antenna beam information; a downlink (DL) reference signal transmit power; and at least one valid coverage area.
[0247] Example B4. The method of any one of Examples B1-B3, further comprising: receiving a first indication from the UE indicating that at least one UE-side AI / ML model is valid; and in response to the first indication, transmitting a second indication to the UE 22 to enable the UE 22 to activate the at least one valid UE-side AI / ML model.
[0248] Example CL A user equipment (UE) 22 comprising processing circuitry configured to: receive assistance information for UE-side artificial intelligence / machine learning (AI / ML) based location prediction from a network node, the assistance information corresponding to at least one UE-side AI / ML model validity condition; and determine the validity of at least one UE-side AI / ML model based on the received assistance information and a current state of the UE 22.
[0249] Example C2. The UE 22 of Example Cl, wherein the processing circuitry is further configured to: determine that the UE 22 has entered a new cell; compare at least one parameter of the assistance information with at least one condition associated with the new cell; and determine the validity of the at least one UE-side AI / ML model based on whether the at least one parameter of the assistance information matches the at least one condition associated with the new cell within a predefined threshold.
[0250] Example C3. The UE 22 of any one of Examples Cl and C2, wherein the model validity condition corresponds to at least one of: a transmission / reception point (TRP) synchronization error; TRP location information; TRP antenna beam information; a downlink (DL) reference signal transmit power; and at least one valid coverage area.
[0251] Example C4. The UE 22 of any one of Examples C1-C3, wherein the processing circuitry is further configured to: transmit a first indication to the network node 16 indicating that at least one UE-side AI / ML model is valid; and responsive to receiving a second indication from the network node 16, activate the at least one valid UE-side AI / ML model for location prediction.
[0252] Example DI . A method implemented in a user equipment (UE) 22, the method comprising: receiving assistance information for UE-side artificial intelligence / machine learning (AI / ML) based location prediction from a network node, the assistance information corresponding to at least one UE-side AI / ML model validity condition; and determining the validity of at least one UE-side AI / ML model based on the received assistance information and a current state of the UE 22.
[0253] Example D2. The method of Example DI, further comprising: determining that the UE 22 has entered a new cell; comparing at least one parameter of the assistance information with at least one condition associated with the new cell; and determining the validity of the at least one UE-side AI / ML model based on whether the at least one parameter of the assistance information matches the at least one condition associated with the new cell within a predefined threshold.
[0254] Example D3. The method of any one of Examples DI and D2, wherein the model validity condition corresponds to at least one of: a transmission / reception point (TRP) synchronization error; TRP location information; TRP antenna beam information; a downlink (DL) reference signal transmit power; and at least one valid coverage area.
[0255] Example D4. The method of any one of Examples D1-D3, further comprising: transmitting a first indication to the network node indicating that at least one UE- side AI / ML model is valid; and upon receiving a second indication from the network node, activating the at least one valid UE-side AI / ML model for location prediction. As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and / or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and / or functionality described herein may be performed by, and / or associated to, a corresponding module, which may be implemented in software and / or firmware and / or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that can be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.
[0256] Some embodiments are described herein with reference to flowchart illustrations and / or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.
[0257] These computer program instructions may also be stored in a computer readable memory or storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function / act specified in the flowchart and / or block diagram block or blocks.
[0258] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.
[0259] It is to be understood that the functions / acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality / acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.
[0260] Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
[0261] Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments can be combined in any way and / or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.
[0262] It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings without departing from the scope of the following claims.
Claims
What is claimed is:
1. A method implemented in a user equipment, UE, (22) the method comprising: receiving (SI 12) assistance information in at least one Positioning System Information Block, posSIB, for UE-side machine learning, ML, -based location prediction from a network node (16), the assistance information corresponding to at least one UE- side ML model validity condition; and determining (SI 14) a validity of at least one UE-side ML model based on the received assistance information.
2. The method of Claim 1, further comprising: determining that the UE (22) has entered a new cell; comparing at least one parameter of the assistance information associated with the at least one posSIB to a posSIB of another type associated with the new cell; and determining the validity of the at least one UE-side ML model based on whether the at least one parameter of the assistance information matches the posSIB of the other type within a predefined threshold.
3. The method of any one of Claims 1-2, wherein the UE-side ML model validity condition corresponds to at least one of: a transmission / reception point, TRP, synchronization error;TRP location information;TRP antenna beam information; a downlink, DL, reference signal transmit power; and at least one valid coverage area.
4. The method of any one of Claims 1-3, further comprising: transmitting a first indication to the network node (16) indicating that at least one UE-side ML model is valid; and upon receiving a second indication from the network node (16), activating the at least one valid UE-side ML model for location prediction.
5. The method of any one of Claims 1-4, further comprising receiving an indication of the at least one UE-side ML model being one of area specific and cell specific.
6. A user equipment, UE, 22 comprising processing circuitry (84) configured to: receive assistance information in at least one Positioning System Information Block, posSIB, for UE-side machine learning, ML, -based location prediction from a network node (16), the assistance information corresponding to at least one UE-side ML model validity condition; and determine a validity of at least one UE-side ML model based on the received assistance information.
7. The UE (22) of Claim 6, wherein the processing circuitry (84) is further configured to: determine that the UE (22) has entered a new cell; compare at least one parameter of the assistance information associated with the at least one posSIB to a posSIB of another type associated with the new cell; and determine the validity of the at least one UE-side ML model based on whether the at least one parameter of the assistance information matches the posSIB of the other type within a predefined threshold.
8. The UE of any one of Claims 6-7, wherein the UE-side ML model validity condition corresponds to at least one of: a transmission / reception point, TRP, synchronization error;TRP location information;TRP antenna beam information; a downlink, DL, reference signal transmit power; and at least one valid coverage area.
9. The UE (22) of any one of Claims 6-8, wherein the processing circuitry (84) is further configured to: transmit a first indication to the network node (16) indicating that at least one UE- side ML model is valid; andupon receiving a second indication from the network node (16), activate the at least one valid UE-side ML model for location prediction.
10. The UE (22) of any one of Claims 6-9, wherein the processing circuitry (84) (84) is further configured to receive an indication of the at least one UE-side ML model being one of area specific and cell specific.
11. A method implemented in a network node (16), the method comprising: determining (SI 08) assistance information in at least one Positioning SystemInformation Block, posSIB, for user equipment, UE, -side machine learning, ML, -based location prediction, the assistance information corresponding to at least one UE-side ML model validity condition; and transmitting (SI 10) the assistance information to a UE (22) to enable the UE (22) to determine a validity of at least one UE-side ML model.
12. The method of Claim 11, further comprising: identifying a plurality of cells that share similar conditions within a predefined margin; and including in the assistance information an identification of the plurality of cells.
13. The method of any one of Claims 11-12, wherein the UE-side ML model validity condition corresponds to at least one of: a transmission / reception point, TRP, synchronization error;TRP location information;TRP antenna beam information; a downlink, DL, reference signal transmit power; and at least one valid coverage area.
14. The method of any one of Claims 11-13, further comprising: receiving a first indication from the UE (22) indicating that at least one UE-side ML model is valid; and in response to the first indication, transmitting a second indication to the UE (22) to enable the UE (22) to activate the at least one valid UE-side ML model.
15. The method of any one of Claims 11-14, further comprising indicating the at least one UE-side ML model being one of area specific and cell specific.
16. A network node (16) comprising processing circuitry (68) configured to: determine assistance information in at least one Positioning System InformationBlock, posSIB, for user equipment, UE, -side machine learning, ML, -based location prediction, the assistance information corresponding to at least one UE-side ML model validity condition; and transmit the assistance information to a UE (22) to enable the UE (22) to determine a validity of at least one UE-side ML model.
17. The network node (16) of Claim 16, wherein the processing circuitry (68) is further configured to: identify a plurality of cells that share similar conditions within a predefined margin; and include in the assistance information an identification of the plurality of cells.
18. The network node (16) of any one of Claims 16-17, wherein the UE-side ML model validity condition corresponds to at least one of: a transmission / reception point, TRP, synchronization error;TRP location information;TRP antenna beam information; a downlink, DL, reference signal transmit power; and at least one valid coverage area.
19. The network node (16) of any one of Claims 16-18, wherein the processing circuitry (68) is further configured to: receive a first indication from the UE (22) indicating that at least one UE-side ML model is valid; and in response to the first indication, transmit a second indication to the UE (22) to enable the UE (22) to activate the at least one valid UE-side ML model.
20. The network node (16) of any one of Claims 16-19, wherein the processing circuitry (68) is further configured to indicate the at least one UE-side ML model being one of area specific and cell specific.
Citation Information
Patent Citations
Network verified user device position in a wireless communication network
WO2023001520A1
