Method and apparatus for artificial intelligence or machine learning (ai / ML)-based positioning

Abstract

Methods and apparatuses for Artificial Intelligence or Machine Learning (AI / ML)-based positioning are provided. The method includes receiving, from a network entity, Non-Access Stratum (NAS) signaling including at least one association identifier and a Positioning Reference Signal (PRS) configuration, performing, based on the PRS configuration, measurements to obtain at least one measurement result, labeling the at least one measurement result with the at least one association identifier, training an AI / ML model based on the at least one measurement result labeled with the at least one association identifier, and labeling the AI / ML model with the at least one association identifier.

Description

METHOD AND APPARATUS FOR ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING (AI / ML)-BASED POSITIONING

[0001] The present disclosure is related to wireless communication and, more specifically, to methods and apparatuses for Artificial Intelligence or Machine Learning (AI / ML)-based positioning.

[0002] Various efforts have been made to improve different aspects of wireless communication for the cellular wireless communication systems, such as the 5thGeneration (5G) New Radio (NR) system, by improving data rate, latency, reliability, and mobility. The 5G NR system is designed to provide flexibility and configurability to optimize network services and types, accommodating various use cases, such as enhanced Mobile Broadband (eMBB), massive Machine-Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC). As the demand for radio access continues to increase, however, there exists a need for further improvements in the art.Summery of Invention

[0003] The present disclosure is related to methods and apparatuses for Artificial Intelligence or Machine Learning (AI / ML)-based positioning.

[0004] According to a first aspect of the present disclosure, a User Equipment (UE) is provided including at least one processor and at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the UE to receive, from a network entity, first Non-Access Stratum (NAS) signaling including at least one association identifier and a Positioning Reference Signal (PRS) configuration, perform, based on the PRS configuration, measurements to obtain at least one measurement result, label the at least one measurement result with the at least one association identifier, train an Artificial Intelligence or Machine Learning (AI / ML) model based on the at least one measurement result labeled with the at least one association identifier, and label the AI / ML model with the at least one association identifier.

[0005] In some implementations of the first aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to receive, from the network entity, second NAS signaling including a list of network-side additional conditions and a functionality mapping request indication.

[0006] In some implementations of the first aspect of the present disclosure, the list of network-side additional conditions includes one or more network-side additional condition identifiers, each of the one or more network-side additional condition identifiers indicating a predefined environmental or deployment condition used by the network entity.

[0007] In some implementations of the first aspect of the present disclosure, the functionality mapping request indication is configured to request the UE to report mapping information between one or more supported functionalities of the UE and the list of network-side additional conditions.

[0008] In some implementations of the first aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to transmit, to the network entity, third NAS signaling in response to the functionality mapping request indication, the third NAS signaling including the mapping information.

[0009] In some implementations of the first aspect of the present disclosure, the network entity includes a Location Management Function (LMF).

[0010] In some implementations of the first aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to receive, from the network entity, an indication to deactivate the AI / ML model.

[0011] According to a second aspect of the present disclosure, a method performed by a User Equipment (UE) for Artificial Intelligence or Machine Learning (AI / ML)-based positioning is provided, the method including receiving, from a network entity, Non-Access Stratum (NAS) signaling including at least one association identifier and a Positioning Reference Signal (PRS) configuration, performing, based on the PRS configuration, measurements to obtain at least one measurement result, labeling the at least one measurement result with the at least one association identifier, training an AI / ML model based on the at least one measurement result labeled with the at least one association identifier, and labeling the AI / ML model with the at least one association identifier.

[0012] According to a third aspect of the present disclosure, a network entity is provided including at least one processor and at least one non-transitory computer-readable medium coupled to the at least one processor and storing computer-executable instructions that, when executed by the at least one processor, cause the network entity to transmit, to a User Equipment (UE), first Non-Access Stratum (NAS) signaling including at least one association identifier and a Positioning Reference Signal (PRS) configuration, enabling the UE to perform, based on the PRS configuration, measurements to obtain at least one measurement result and to label the at least one measurement result with the at least one association identifier.

[0013] In some implementations of the third aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the network entity to transmit, to the UE, second NAS signaling including a list of network-side additional conditions and a functionality mapping request indication.

[0014] In some implementations of the third aspect of the present disclosure, the list of network-side additional conditions includes one or more network-side additional condition identifiers, each of the one or more network-side additional condition identifiers indicating a predefined environmental or deployment condition used by the network entity.

[0015] In some implementations of the third aspect of the present disclosure, the functionality mapping request indication is configured to request the UE to report mapping information between one or more supported functionalities of the UE and the list of network-side additional conditions.

[0016] In some implementations of the third aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the network entity to receive, after transmitting the second NAS signaling to the UE, third NAS signaling including the mapping information from the UE.

[0017] In some implementations of the third aspect of the present disclosure, the network entity includes a Location Management Function (LMF).

[0018] In some implementations of the third aspect of the present disclosure, the one or more computer-executable instructions, when executed by the at least one processor, further cause the network entity to transmit, to the UE, an indication to deactivate an Artificial Intelligence or Machine Learning (AI / ML) model trained by the at least one measurement result.

[0019] Aspects of the present disclosure are best understood from the following detailed disclosure when read with the accompanying drawings. Various features are not drawn to scale. Dimensions of various features may be arbitrarily increased or reduced for clarity of discussion.

[0020] FIG. 1 is a flowchart illustrating a method / process for AI / ML-based positioning in a wireless communication system, according to an example implementation of the present disclosure.

[0021] FIG. 2 is a block diagram illustrating node for wireless communications, in accordance with various aspects of the present disclosure.

[0022] The following contains specific information related to implementations of the present disclosure. The drawings and their accompanying detailed disclosure are merely directed to implementations. However, the present disclosure is not limited to these implementations. Other variations and implementations of the present disclosure will be obvious to those skilled in the art.

[0023] Unless noted otherwise, like or corresponding elements among the drawings may be indicated by like or corresponding reference numerals. Moreover, the drawings and illustrations in the present disclosure are generally not to scale and are not intended to correspond to actual relative dimensions.

[0024] For consistency and ease of understanding, like features may be identified (although, in some examples, not illustrated) by the same numerals in the drawings. However, the features in different implementations may be different in other respects and shall not be narrowly confined to what is illustrated in the drawings.

[0025] References to “one implementation,” “an implementation,” “example implementation,” “various implementations,” “some implementations,” “implementations of the present application,” etc., may indicate that the implementation(s) of the present application so described may include a particular feature, structure, or characteristic, but not every possible implementation of the present application necessarily includes the particular feature, structure, or characteristic. Further, repeated use of the phrase “in one implementation,” or “in an example implementation,” “an implementation,” do not necessarily refer to the same implementation, although they may. Moreover, any use of phrases like “implementations” in connection with “the present application” are never meant to characterize that all implementations of the present application must include the particular feature, structure, or characteristic, and should instead be understood to mean “at least some implementations of the present application” includes the stated particular feature, structure, or characteristic.

[0026] The term “coupled” is defined as connected, whether directly or indirectly through intervening components, and is not necessarily limited to physical connections. The term “comprising,” when utilized, means “including, but not necessarily limited to”; it specifically indicates open-ended inclusion or membership in the so-described combination, group, series, and the equivalent.

[0027] The expression “at least one of A, B and C” or “at least one of the following: A, B and C” means “only A, or only B, or only C, or any combination of A, B and C.” The terms “system” and “network” may be used interchangeably. The term “and / or” is only an association relationship for describing associated objects and represents that three relationships may exist such that A and / or B may indicate that A exists alone, A and B exist at the same time, or B exists alone. The character “ / ” generally represents that the associated objects are in an “or” relationship.

[0028] For the purposes of explanation and non-limitation, specific details, such as functional entities, techniques, protocols, and standards, are set forth for providing an understanding of the disclosed technology. In other examples, detailed disclosure of well-known methods, technologies, systems, and architectures are omitted so as not to obscure the present disclosure with unnecessary details.

[0029] Persons skilled in the art will immediately recognize that any network function(s) or algorithm(s) disclosed may be implemented by hardware, software, or a combination of software and hardware. Disclosed functions may correspond to modules which may be software, hardware, firmware, or any combination thereof.

[0030] A software implementation may include computer executable instructions stored on a computer-readable medium, such as memory or other type of storage devices. One or more microprocessors or general-purpose computers with communication processing capability may be programmed with corresponding executable instructions and perform the disclosed network function(s) or algorithm(s).

[0031] The microprocessors or general-purpose computers may include Application-Specific Integrated Circuits (ASICs), programmable logic arrays, and / or one or more Digital Signal Processor (DSPs). Although some of the disclosed implementations are oriented to software installed and executing on computer hardware, alternative implementations implemented as firmware, as hardware, or as a combination of hardware and software are well within the scope of the present disclosure. The computer-readable medium includes but is not limited to Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory, Compact Disc Read-Only Memory (CD-ROM), magnetic cassettes, magnetic tape, magnetic disk storage, or any other equivalent medium capable of storing computer-readable instructions.

[0032] A radio communication network architecture such as a Long-Term Evolution (LTE) system, an LTE-Advanced (LTE-A) system, an LTE-Advanced Pro system, or a 5G NR Radio Access Network (RAN) typically includes at least one base station (BS), at least one UE, and one or more optional network elements that provide connection within a network. The UE communicates with the network such as a Core Network (CN), an Evolved Packet Core (EPC) network, an Evolved Universal Terrestrial RAN (E-UTRAN), a 5G Core (5GC), or an internet via a RAN established by one or more BSs.

[0033] A UE may include, but is not limited to, a mobile station, a mobile terminal or device, or a user communication radio terminal. The UE may be a portable radio equipment that includes, but is not limited to, a mobile phone, a tablet, a wearable device, a sensor, a vehicle, or a Personal Digital Assistant (PDA) with wireless communication capability. The UE is configured to receive and transmit signals over an air interface to one or more cells in a RAN. A UE may be referred to as a PHY / MAC / RLC / PDCP / SDAP entity. The PHY / MAC / RLC / PDCP / SDAP entity may be referred to as the UE.

[0034] The BS may be configured to provide communication services according to at least a Radio Access Technology (RAT) such as Worldwide Interoperability for Microwave Access (WiMAX), Global System for Mobile communications (GSM) that is often referred to as 2G, GSM Enhanced Data rates for GSM Evolution (EDGE) RAN (GERAN), General Packet Radio Service (GPRS), Universal Mobile Telecommunication System (UMTS) that is often referred to as 3G based on basic wideband-code division multiple access (W-CDMA), high-speed packet access (HSPA), LTE, LTE-A, evolved LTE (eLTE) that is LTE connected to 5GC, NR (often referred to as 5G), and / or LTE-A Pro. However, the scope of the present disclosure is not limited to these protocols.

[0035] The BS may include, but is not limited to, a node B (NB) in the UMTS, an evolved node B (eNB) in LTE or LTE-A, a radio network controller (RNC) in UMTS, a BS controller (BSC) in the GSM / GERAN, an ng-eNB in an Evolved Universal Terrestrial Radio Access (E-UTRA) BS in connection with 5GC, a next generation Node B (gNB) in the 5G-RAN, or any other apparatus capable of controlling radio communication and managing radio resources within a cell. The BS may serve one or more UEs via a radio interface.

[0036] The BS may be operable to provide radio coverage to a specific geographical area using multiple cells forming the RAN. The BS may support the operations of the cells. Each cell may be operable to provide services to at least one UE within its radio coverage.

[0037] Each cell (often referred to as a serving cell) may provide services to serve one or more UEs within its radio coverage, such that each cell schedules the DL (and optionally UL resources) to at least one UE within its radio coverage for DL (and optionally UL packet transmissions from the UE). The BS may communicate with one or more UEs in the radio communication system via the plurality of cells.

[0038] A cell may allocate sidelink (SL) resources for supporting the Proximity Service (ProSe) or Vehicle to Everything (V2X) service. Each cell may have overlapped coverage areas with other cells.

[0039] In Multi-RAT Dual Connectivity (MR-DC) cases, the primary cell of a Master Cell Group (MCG) or a Secondary Cell Group (SCG) may be referred to as a Special Cell (SpCell). A Primary Cell (PCell) may include the SpCell of an MCG. A Primary SCG Cell (PSCell) may include the SpCell of an SCG. MCG may include a group of serving cells associated with the Master Node (MN), including the SpCell and optionally one or more Secondary Cells (SCells). An SCG may include a group of serving cells associated with the Secondary Node (SN), including the SpCell and optionally one or more SCells.

[0040] As described above, the frame structure for NR supports flexible configurations for accommodating various next generation (e.g., 5G) communication requirements, such as Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC), while fulfilling high reliability, high data rate, and low latency requirements. The Orthogonal Frequency-Division Multiplexing (OFDM) technology in the 3GPP may serve as a baseline for an NR waveform. The scalable OFDM numerology, such as adaptive sub-carrier spacing, channel bandwidth, and Cyclic Prefix (CP), may also be used.

[0041] Two coding schemes may be considered for NR, specifically Low-Density Parity-Check (LDPC) code and Polar Code. The coding scheme adaption may be configured based on channel conditions and / or service applications.

[0042] At least the DL transmission data, a guard period, and UL transmission data should be included in a transmission time interval (TTI) of a single NR frame. The respective portions of the DL transmission data, the guard period, and the UL transmission data should also be configurable based on, for example, the network dynamics of NR. SL resources may also be provided in an NR frame to support ProSe services or V2X services.

[0043] Any two or more of the following paragraphs, (sub)-bullets, points, actions, behaviors, terms, or claims described in the present disclosure may be combined logically, reasonably, and properly to form a specific method.

[0044] Any sentence, paragraph, (sub)-bullet, point, action, behaviors, terms, or claims described in the present disclosure may be implemented independently and separately to form a specific method.

[0045] Dependency, e.g., “based on”, “more specifically”, “preferably”, “in one embodiment”, “in some implementations”, etc., in the present disclosure is just one possible example which would not restrict the specific method.

[0046] “A and / or B” in the present disclosure may refer to either A or B, both A and B, or at least one of A and B.

[0047] In this disclosure, “X / Y” may encompass the meanings of “X or Y,” “X and Y,” and “X and / or Y,” as indicated by two or more of the sentences, paragraphs, sub-bullets, points, actions, behaviors, terms, alternatives, aspects, examples, embodiments, or claims described in the following invention(s).

[0048] One aspect of the present disclosure may be applied in various contexts, including communications, communication equipment (such as mobile telephone apparatus, base station apparatus, wireless LAN apparatus, and / or sensor devices), integrated circuits (such as communication chips), and software programs, among others.

[0049] The terms “an antenna port” and “antenna ports,” as discussed in the present disclosure, may refer to “an antenna port used for transmission of PUSCH(s) / PUCCH(s)” and “antenna ports used for transmission of PUSCH(s) / PUCCH(s),” respectively.

[0050] Some of the terms, definitions, and / or abbreviations included in the present disclosure may either be sourced from existing documents (such as those from ETSI, ITU, or other sources) or may be newly created by experts from the 3GPP whenever there was a need for a precise vocabulary.

[0051] Examples of some selected terms in the present disclosure are provided as follows.

[0052] Antenna Panel: A conceptual term for a UE antenna implementation. It may be assumed that a panel may be an operational unit for controlling a transmit spatial filter (beam). A panel may typically include multiple antenna elements. In some implementations, a beam may be formed by a panel, and in order to form two beams simultaneously, two panels may be needed. Such simultaneous beamforming by multiple panels may be subject to the UE capability. A similar definition for “panel” may be applicable by applying spatial receiving filtering characteristics.

[0053] Beam: A beam may include a spatial (domain) filtering. In one example, the spatial filtering may be applied in the analog domain by adjusting a phase and / or amplitude of the signal before being transmitted by a corresponding antenna element. In another example, the spatial filtering may be applied in the digital domain by the Multi-Input Multi-Output (MIMO) technique in the wireless communication system. For example, “a UE made a PUSCH transmission by using a specific beam” may mean that the UE made the PUSCH transmission by using the specific spatial / digital domain filter. The “beam” may also be, but is not limited to be, represented as an antenna, an antenna port, an antenna element, a group of antennas, a group of antenna ports, or a group of antenna elements. The beam may also be formed by a certain reference signal resource. In short, the beam may be equivalent to a spatial domain filter through which the EM wave is radiated. Beam information may include details about the selected or utilized beam or spatial filter. In some implementations, the individual beams (e.g., spatial filters) may be used to transmit individual reference signals. Consequently, a beam or beam information may be represented by one or more reference signal resource indices.

[0054] In the present disclosure, although the term “gNB” may have been used throughout the document, it should be understood that the term “gNB” may be replaced by any other type of BS (e.g., an eNB). Additionally, unless specifically noted otherwise, the terms “SSB” and “OD-SSB” may be used interchangeably in the present disclosure.

[0055] In the present disclosure, the term “network (NW)”, “cell,” “camped cell,” “serving cell,” “base station,” “gNB,” “eNB” and “ng-eNB” may be used interchangeably. In some implementations, some of these items may refer to the same network entity.

[0056] In the wireless cellular network, applications such as navigation and localized services may need to have the information of the location of a mobile device (e.g., a UE). As such, the positioning method may play an essential role in these applications and services.

[0057] Currently, the positioning mechanisms may be classified into cellular-based positioning methods and non-cellular-based positioning methods. The cellular-based positioning methods may be based on the system supported by LTE and / or NR. The non-cellular-based positioning methods may be based on the system supported by satellites such as the Global Navigation Satellite System (GNSS), WiFi, and / or bluetooth. For the cellular-based positioning methods, Time Difference of Arrival (TDoA), Angle of Arrival (AoA), and multiple-Round Trip Time (multi-RTT) may be designed by leveraging the positioning reference signal (PRS). However, these positioning methods may require a Line-of-Sight (LoS) measurement environment. In some implementations, the accuracy of the positioning methods may degrade when there is no LoS path measured by the UE or the gNB.

[0058] As such, AI / ML may facilitate the enhancement on positioning accuracy. With the collection of an adequate amount of data, the AI / ML may provide accurate location information.

[0059] Currently, a PRS resource may be associated with a PRS resource set which may be further associated with a frequency layer, and the positioning measurement object may be configured by the Location Management Function (LMF) to the UE via a Non-Access Stratum (NAS) signaling (e.g., the ProvideAssistanceData message defined in the LTE Positioning Protocol (LPP)). The positioning measurement object may include one or more PRS resources, one or more PRS resource sets, or one or more frequency layers. To leverage the data collection for AI / ML-based positioning, a UE may benefit from having the knowledge of the AI / ML-related information, such as the awareness of AI / ML, the related AI / ML model, the related AI / ML functionality, and so on. Furthermore, to facilitate the network to manage the AI / ML models and / or functionalities, in this disclosure, the AI / ML-related information may be associated with the positioning measurement objects.

[0060] In the present disclosure, the following scenarios may be considered. A network may include one or more RAN nodes (e.g., an eNB and / or a gNB). Each RAN node may include one or more cells. Each cell may be associated with one or more Transmission and Reception Points (TRP) and / or Transmission Points (TP). A UE may be capable of receiving the PRS from one or more TRPs and / or TPs in the same cell or different cells. An LMF may reside in the core network. The communication between the UE and the LMF may be facilitated via the RAN nodes. In some implementations, the communication between the UE and the LMF may be transparent to the RAN nodes.

[0061] For AI / ML, a dataset may be collected with different Additional Conditions (ACs). The ACs may be further classified to network-side (NW-side) ACs and UE-side ACs. A NW-side AC may be known to the network. In some implementations, a NW-side AC may be implicitly known to the UE or unknown to the UE. A UE-side AC may be known to the UE. In some implementations, a UE-side AC may be implicitly known to the network or unknown to the network.

[0062] The UE may be capable of supporting one or more AI / ML models and / or functionalities. The supporting one or more AI / ML models and / or functionalities may include collecting data, training, inferencing, and / or managing the AI / ML models and / or functionalities. At least one of the functionalities may be associated with one or more NW-side ACs and / or one or more UE-side ACs. In some implementations, at least one of the functionalities may be associated with one or more models.

[0063] FIG. 1 is a flowchart illustrating method / process 100 for AI / ML-based positioning in a wireless communication system, according to an example implementation of the present disclosure. Although actions 102, 104, 106, 108, and 110 are illustrated, as separate actions, represented as independent blocks in FIG. 1, these separately illustrated actions should not be construed as to be necessarily order-dependent. The order in which the actions are performed in FIG. 1 is not intended to be construed as a limitation, and any number of the disclosed blocks may be combined in any order to implement the method, or an alternative method. Each of actions 102, 104, 106, 108, and 110 may be performed independent of the other actions, and may be omitted in some implementations of the present disclosure. Moreover, method / process 100 may be combined with other procedures / methods described in the present disclosure. Process 100 may be performed by a UE, with each action of process 100 corresponding to an operation executed by the UE.

[0064] In action 102, the UE may receive, from a network entity, first NAS signaling including at least one association identifier and a PRS configuration. The network entity may include (or may be) an LMF.

[0065] In action 104, the UE may perform, based on the PRS configuration, measurements to obtain at least one measurement result.

[0066] In action 106, the UE may label the at least one measurement result with the at least one association identifier.

[0067] In action 108, the UE may train an AI / ML model based on the at least one measurement result labeled with the at least one association identifier.

[0068] In action 110, the UE may label the AI / ML model with the at least one association identifier.

[0069] Additionally or alternatively, in process 100, the UE may further receive, from the network entity, second NAS signaling including a list of network-side additional conditions and a functionality mapping request indication. The list of network-side additional conditions may include one or more network-side additional condition identifiers. Each of the one or more network-side additional condition identifiers may indicate a predefined environmental or deployment condition used by the network entity. The functionality mapping request indication may be configured to request the UE to report mapping information between one or more supported functionalities of the UE and the list of network-side additional conditions.

[0070] Additionally or alternatively, in process 100, the UE may further transmit, to the network entity, third NAS signaling in response to the functionality mapping request indication. The third NAS signaling may include the mapping information.

[0071] Additionally or alternatively, in process 100, the UE may further receive, from the network entity, an indication to deactivate the AI / ML model.

[0072] Process 100 may provide a comprehensive framework for AI / ML-based positioning that significantly enhances positioning accuracy and system efficiency in wireless communication networks. By introducing association identifiers to label both measurement results and trained AI / ML models, process 100 may enable precise model management where the network entity (e.g., the LMF) can select and activate the most suitable models for specific environmental conditions such as dense urban areas or indoor environments. The functionality mapping mechanism may establish transparency between the UE and the network regarding AI / ML capabilities, allowing the network to make informed decisions about positioning methods based on current conditions and UE capabilities.

[0073] It should also be noted that the network device, such as the entities in located in the CN, may perform methods / actions corresponding to those performed by the UE. For example, the receiving actions performed by the UE may correspond to the transmitting / configuring actions of the network device; the transmitting actions performed by the UE may correspond to the receiving actions of the network device. That is, the network device and the UE may have reciprocally aligned roles in transmission and reception. For example, the network device may transmit, to the UE, first NAS signaling including at least one association identifier and a PRS configuration, enabling the UE to perform, based on the PRS configuration, measurements to obtain at least one measurement result and to label the at least one measurement result with the at least one association identifier.

[0074] The following sections of the present disclosure may provide detailed implementation examples for various aspects of Process 100, as well as additional embodiments that may be combined with process 100 to enhance the AI / ML-based positioning functionality. These implementations may cover specific signaling procedures, information element definitions, model association mechanisms, measurement collection methods, and lifecycle management operations. While these implementations are described in the context of process 100 to illustrate their integration and synergies with the overall framework, each implementation may also be realized independently unless specifically indicated otherwise.

[0075] Pre-coordination for Model and / or Functionality

[0076] This section may describe the pre-coordination procedures between the network entity and the UE for AI / ML-based positioning. These procedures may enable the network entity to discover which AI / ML models and functionalities are available at the UE, and how these capabilities relate to different network conditions. The functionality mapping mechanisms described here may provide the foundation for the association identifier framework used in process 100. While these pre-coordination procedures may work together with process 100 to enable comprehensive AI / ML positioning, the procedures may also be implemented independently in systems that require capability discovery and coordination between network and UE for AI / ML operations.

[0077] In some implementations, the network entity (e.g., the LMF) may initiate a pre-coordination procedure to acquire the information of the availability of the UE-side model by sending first NAS signaling, which may be an LPP message, to the UE. The “first NAS signaling” referenced in this section and subsequent sections may correspond to the “second NAS signaling” mentioned in process 100.

[0078] In some implementations, the first NAS signaling may include a list of NW-side AC Information Elements (IEs) (e.g., the list of network-side additional conditions as specified in process 100), and / or a list of known UE-side AC IEs, and / or a functionality mapping request IE (e.g., the functionality mapping request indication as specified in process 100), and / or a model mapping request IE, and / or a functionality-model association request IE. In some implementations, the LMF may be implemented to know a certain set of UE-side ACs, and the LMF may use the UE-side AC IEs to indicate to the UE which UE-side ACs are known to the LMF to facilitate the pre-coordination procedure.

[0079] In some implementations, an IE (e.g., a NW-side AC IE) may be used to indicate the known NW-side AC by the network (e.g., the LMF). In some implementations, the LMF may be implemented to know a certain set of NW-side ACs, and the LMF may use the NW-side AC IEs to indicate to the UE which NW-side ACs are known to the LMF.

[0080] In some implementations, a UE may be implemented to know a certain set of NW-side ACs, and the UE may be indicated the information regarding the NW-side ACs associated with the LMF. The information may include the mapping between the NW-side ACs and the identities of the NW-side ACs, the currently applicable NW-side ACs, and other related information.

[0081] In some implementations, a NW-side AC IE may take an ENUMERATED format, and the UE may comprehend that the corresponding NW-side AC is known to the LMF. For example, if the NW-side AC IE takes the value ‘dense-clutter,’ the UE may comprehend that the LMF knows the NW-side AC of topology layout with dense clutters.

[0082] In some implementations, a NW-side AC IE may take an integer value, and the UE may comprehend that the NW-side AC which corresponds to the integer value in a predefined table is known to the LMF. The predefined table may show that each NW-side AC is associated with which integer value. For example, if the NW-side AC IE takes the value ‘1,’ the UE may comprehend that the LMF knows the NW-side AC corresponding to the first entry in the predefined table. If the NW-side AC IE takes the value ‘0,’ the UE may comprehend that the LMF does not know the NW-side AC corresponding to the first entry in the predefined table.

[0083] In some implementations, a NW-side AC IE may be a sequence including an integer value and an ENUMERATED value, and the UE may comprehend that the LMF knows the NW-side AC which corresponds to the ENUMERATED value and associates the NW-side AC with the integer value. For example, if a UE receives a NW-side AC IE with an ENUMERATED value 'dense-clutter' and an integer value '1', the UE may comprehend that the LMF knows the NW-side AC of topology layout with dense clutters and the LMF associates the NW-side AC with an integer value ‘1.’

[0084] In some implementations, a UE may not know a certain NW-side AC, and the UE may ignore the unknown NW-side AC indicated by the NW-side AC IE.

[0085] In some implementations, a NW-side AC IE may be associated with one or multiple cells and / or TRPs and may vary in time. In some implementations, a NW-side AC IE may include an NW-side AC identity / identifier (ID) and a list of cell IDs (e.g., Physical Cell IDs (PCIs) and / or other cell IDs determined by the additionalPCI IE). In some implementations, the UE may comprehend that the NW-side AC ID is associated with the cells whose cell IDs are in the list.

[0086] In some implementations, an IE (e.g., a known UE-side AC IE) may be used to indicate the UE-side AC known to the network (e.g., the LMF). In some implementations, the LMF may be implemented to know a certain set of UE-side ACs, and the LMF may use the UE-side AC IEs to indicate to the UE which UE-side ACs are known to the LMF.

[0087] In some implementations, a UE may be implemented to know a certain set of UE-side ACs, and the UE may be indicated the information regarding the UE-side ACs associated with the LMF. The information may include the mapping between the UE-side ACs and the identities of the UE-side ACs, and other related information.

[0088] In some implementations, a known UE-side AC IE may take an ENUMERATED format, and the UE may comprehend that the corresponding UE-side AC is known to the LMF. For example, if the UE-side AC IE takes the value ‘low-mobility,’ the UE may comprehend that the LMF knows the UE-side AC of low UE mobility.

[0089] In some implementations, a known UE-side AC IE may take an integer value, and the UE may comprehend that the UE-side AC which corresponds to the value in a predefined table is known to the LMF. For example, if the UE-side AC IE takes the value ‘1,’ the UE may comprehend that the LMF knows the UE-side AC corresponding to the first entry in the predefined table. If the UE-side AC IE takes the value ‘0,’ the UE may comprehend that the LMF does not know the UE-side AC corresponding to the first entry in the predefined table.

[0090] In some implementations, a known UE-side AC IE may be a sequence including an integer value and an ENUMERATED value, and the UE may comprehend that the LMF knows the UE-side AC which corresponds to the ENUMERATED value and associates the UE-side AC with the integer value. For example, if a UE receives a UE-side AC IE with an ENUMERATED value 'low-mobility' and an integer value ‘1,’ the UE may comprehend that the LMF knows the UE-side AC of low UE mobility and the LMF associates the UE-side AC with an integer value ‘1.’

[0091] In some implementations, a UE may not know a certain UE-side AC, which may be indicated by the LMF, and the UE may ignore the unknown UE-side AC indicated by the UE-side AC IE.

[0092] In some implementations, an IE (e.g., a functionality mapping request IE) may be used to indicate that the LMF requests the mapping relation between the functionality of the UE and the corresponding NW-side AC. In some implementations, a functionality mapping request IE may take an ENUMERATED format, and the UE may comprehend the mapping relation between the functionality of the UE and the corresponding NW-side AC is requested if the functionality mapping request IE is present with value ‘true.’ The UE may comprehend the mapping relation between the functionality of the UE and the corresponding NW-side AC is not requested if the functionality mapping request IE is absent or present with value ‘false.’

[0093] In some implementations, upon transmitting the first NAS message including the functionality mapping request IE with value ‘true,’ the LMF may start a timer. Upon the expiry of the timer, the LMF may assume that the UE has the same understanding on the NW-side and UE-side ACs. The same understanding may include the same definition and / or the same mapping method for the association of NW-side / UE-side AC with the NW-side / UE-side AC ID.

[0094] In some implementations, upon transmitting the first NAS message including the functionality mapping request IE with value ‘true,’ the LMF may immediately assume the UE has the same understanding on the NW-side and UE-side ACs. The same understanding may include the same definition and / or the same mapping method for the association of NW-side / UE-side AC with the NW-side / UE-side AC ID.

[0095] In some implementations, upon transmitting the first NAS message including the functionality mapping request IE with value ‘true,’ the LMF may wait for second NAS signaling from the UE. Upon receiving the second NAS signaling from the UE, the LMF may assume the UE has the same understanding on the NW-side and UE-side ACs. The same understanding may include the same definition and / or the same mapping method for the association of NW-side / UE-side AC with the NW-side / UE-side AC ID. The “second NAS signaling” referenced in this section and subsequent sections may correspond to the “third NAS signaling” mentioned in process 100.

[0096] In some implementations, an IE (e.g., a model mapping request IE) may be used to indicate that the LMF requests the mapping relation between the model of the UE and the corresponding NW-side AC and / or UE-side AC. In some implementations, a model mapping request IE may take an ENUMERATED format, and the UE may comprehend the mapping relation between the model of the UE and the corresponding NW-side AC and / or UE-side AC is requested if the model mapping request IE is present with value 'true'. The UE may comprehend the mapping relation between the model of the UE and the corresponding NW-side AC and / or UE-side AC is not requested if the model mapping request IE is absent or present with value ‘false.’

[0097] In some implementations, an IE (e.g., a functionality-model association request IE) may be used to indicate that the LMF requests the association between the model of the UE and the functionality. In some implementations, a functionality-model association request IE may take an ENUMERATED format, and the UE may comprehend that the network (e.g., the LMF) is requesting the association between the models of the UE and functionalities if the functionality-model association request IE is present with value 'true'. The UE may comprehend that the network (e.g., the LMF) is not requesting the association between the models of the UE and functionalities if the functionality-model association request IE is absent or is present with value ‘false.’

[0098] In some implementations, the UE may transmit the second NAS signaling (e.g., an LPP message) to the LMF to inform the mapping relation (e.g., the mapping information as specified in process 100).

[0099] In some implementations, the UE may transmit the second NAS signaling proactively without any indication from the network. In some implementations, the indication may be the first NAS signaling.

[0100] In some implementations, the UE may transmit the second NAS signaling upon receiving the first NAS signaling from the LMF.

[0101] In some implementations, the second NAS signaling may include a functionality mapping IE, and / or a model mapping IE, and / or a functionality-model association IE.

[0102] In some implementations, the functionality mapping IE may be used to indicate the number of available functionalities at the UE and / or the mapping relation between the NW-side ACs and the available functionalities. An “available functionality” may represent a functionality which is allocated with a specific memory for data collection and training, or a functionality with models which are ready for training, or a functionality with models which have already been trained.

[0103] In some implementations, the UE may include the functionality mapping IE in the second NAS signaling if the UE receives the first NAS signaling containing the functionality mapping request IE with value ‘true.’

[0104] In some implementations, the functionality mapping IE may take an integer value, and the LMF may comprehend the value to be the number of available functionalities at the UE side.

[0105] In some implementations, the functionality mapping IE may be a list of sequences, and the LMF may comprehend that the number of sequences in the list is the number of functionalities available at the UE. The LMF may comprehend a sequence as a functionality.

[0106] In some implementations, a sequence may include a list of ENUMERATED values, and the LMF may comprehend that the NW-side ACs corresponding to the ENUMERATED values in the sequence are supported by the same functionality, and that the NW-side ACs corresponding to the ENUMERATED values in different sequences are supported by different functionalities. The number of the ENUMERATED values may be equal to or less than the number of NW-side AC IEs included in the first NAS signaling.

[0107] In some implementations, a sequence may include a list of integer values, and the LMF may comprehend that the NW-side ACs, associated with the value in the NW-side AC IE of the first NAS signaling, corresponding to the integer values in the sequence are supported by the same functionality, and that the NW-side ACs, associated with the value in the NW-side AC IE of the first NAS signaling, corresponding to the integer values in different sequences are supported by different functionalities. The number of the integer values may be equal to or less than the number of NW-side AC IEs included in the first NAS signaling.

[0108] In some implementations, a sequence may include a list of integer values, and the LMF may comprehend that the NW-side ACs, associated with the value in a predefined table, corresponding to the integer values in the sequence are supported by the same functionality, and that the NW-side ACs, associated with the value in a predefined table, corresponding to the integer values in different sequences are supported by different functionality. The predefined table may be given when the UE is implemented.

[0109] In some implementations, a sequence may be a bitmap, and the number of bits may equal the number of NW-side AC IEs in the first NAS signaling. The N-th bit may represent the NW-side AC IE associated with the integer value N, and the content of the bit may represent whether the NW-side AC IE is mapped to the functionality. The content may be ‘0’ or ‘1.’ For example, the LMF may interpret a sequence with value '1001' that the NW-side ACs associated with integer 1 and 4 are associated with the functionality and the NW-side ACs associated with integer 2 and 3 are not associated with the functionality.

[0110] In some implementations, a sequence may further contain a functionality ID IE, with an integer value, to identify the functionality corresponding to the sequence including the list of associated NW-side ACs.

[0111] In some implementations, the model mapping IE may be used to indicate the number of available models at the UE and / or the mapping relation between the NW-side ACs and / or UE-side ACs and the available models.

[0112] In some implementations, the UE may include the model mapping IE in the second NAS signaling if the UE receives the first NAS signaling containing the model mapping request IE with value ‘true.’

[0113] In some implementations, the model mapping IE may take an integer value, and the LMF may comprehend the value to be the number of available models at the UE side.

[0114] In some implementations, the model mapping IE may be a list of sequences, and the LMF may comprehend that the number of sequences in the list is the number of models available at the UE. The LMF may associate a sequence to a model at the UE-side.

[0115] In some implementations, a sequence may include a list of ENUMERATED values, and the LMF may comprehend that the NW-side ACs corresponding to the ENUMERATED values in the sequence are supported by the same model, and that the NW-side ACs corresponding to the ENUMERATED values in different sequences are supported by different models. The number of the ENUMERATED values may be equal to or less than the number of NW-side AC IEs included in the first NAS signaling.

[0116] In some implementations, a sequence may include a list of integer values, and the LMF may comprehend that the NW-side ACs, associated with the value in the NW-side AC IE of the first NAS signaling, corresponding to the integer values in the sequence are supported by the same model, and that the NW-side ACs, associated with the value in the NW-side AC IE of the first NAS signaling, corresponding to the integer values in different sequences are supported by different models. The number of the integer values may be equal to or less than the number of NW-side AC IEs included in the first NAS signaling.

[0117] In some implementations, a sequence may include a list of integer values, and the LMF may comprehend that the NW-side ACs, associated with the value in a predefined table, corresponding to the integer values in the sequence are supported by the same model, and that the NW-side ACs, associated with the value in a predefined table, corresponding to the integer values in different sequences are supported by different models. The predefined table may be given when the UE is implemented.

[0118] In some implementations, a sequence may further contain a list of ENUMERATED values, and the LMF may comprehend that the UE-side ACs corresponding to the ENUMERATED values in the sequence are supported by the same model, and that the UE-side ACs corresponding to the ENUMERATED values in different sequences are supported by different models.

[0119] In some implementations, a sequence may include a list of integer values, and the LMF may comprehend that the UE-side ACs, associated with the value in the UE-side AC IE of the first NAS signaling, corresponding to the integer values in the sequence are supported by the same model, and that the UE-side ACs, associated with the value in the UE-side AC IE of the first NAS signaling, corresponding to the integer values in different sequences are supported by different models.

[0120] In some implementations, a sequence may include a list of integer values, and the LMF may comprehend that the UE-side ACs, associated with the value in a predefined table, corresponding to the integer values in the sequence are supported by the same model, and that the UE-side ACs, associated with the value in a predefined table, corresponding to the integer values in different sequences are supported by different models.

[0121] In some implementations, a sequence may be a bitmap, and the number of bits may equal the number of UE-side AC IEs in the first NAS signaling. The N-th bit may represent the UE-side AC IE associated with the integer value N, and the content of the bit may represent whether the UE-side AC IE is mapped to the functionality. The content may be ‘0’ or ‘1.’ For example, the LMF may interpret a sequence with value '1001' that the UE-side ACs associated with integer 1 and 4 are associated with the functionality and the UE-side ACs associated with integer 2 and 3 are not associated with the functionality.

[0122] In some implementations, a sequence may further contain a model ID IE, with an integer value, to identify the ID of the associated NW-side ACs and the UE-side ACs.

[0123] In some implementations, a functionality-model association IE may be used to indicate the association between available functionalities and available models. In some implementations, a functionality-model association IE may be a list of sequences.

[0124] In some implementations, a sequence may include a functionality ID IE and a model ID IE, and the LMF may comprehend that the functionality identified by the functionality ID IE is associated with the model identified by the model ID IE, in the same sequence.

[0125] In some implementations, a sequence may include a functionality ID IE and a list of model ID IEs, and the LMF may comprehend that the functionality identified by the functionality ID IE is associated with the models identified by the list of model ID IEs, in the same sequence.

[0126] In some implementations, a sequence may include a model ID IE and a list of functionality ID IEs, and the LMF may comprehend that the model identified by the model ID IE is associated with the functionalities identified by the list of functionality ID IEs.

[0127] PRS Measurement Object Configuration

[0128] This section may describe the detailed procedures and information elements for configuring PRS measurement objects specifically designed for AI / ML-based positioning. The configuration mechanisms presented herein may enable the network entity to provide the UE with comprehensive PRS configurations along with AI / ML-specific parameters through NAS signaling. The AIML-ModelAssociationId and AIML-FunctionalityAssociationId IEs introduced in this section may serve as association identifiers that enable systematic management of AI / ML models and their corresponding measurement configurations. While these procedures may be integrated with process 100 to implement a complete AI / ML-based positioning solution, the configuration mechanisms and information elements described herein may also be utilized independently in various AI / ML positioning implementations where association-based model management is beneficial.

[0129] In some implementations, the network entity, such as the LMF, may configure PRS measurement objects to a UE via third NAS signaling (e.g., the ProvideAssistanceData message defined in the LPP). The PRS measurement objects may include frequency layers, PRS resource sets, and PRS resources. In some implementations, the NAS signaling may include one or more assistance data IEs for positioning methods (e.g., the NR-Multi-RTT-ProvideAssistanceData IE, and / or the NR-DL-AoD-ProvideAssistanceData IE, and / or the NR-DL-TDOA-ProvideAssistanceData IE). The “third NAS signaling” referenced in this section and subsequent sections may correspond to the “first NAS signaling” mentioned in process 100.

[0130] In some implementations, an assistance data IE may include a PRS configuration IE (e.g., the NR-DL-PRS-AssistanceData IE) including a sequence including a frequency layer IE (e.g., the NR-DL-PRS-PositioningFrequencyLayer IE) which is associated with the frequency layer and a list of TRP assistance data IEs (e.g., the NR-DL-PRS-AssistanceDataPerTRP IE), each of which is associated with a TRP.

[0131] In some implementations, the frequency layer IE may indicate the information associated with the frequency layer and may include the information of PRS sub-carrier spacing, the resource bandwidth, the starting PRB, the point A, the combination size, and the cyclic prefix. In some implementations, the TRP assistance data IEs may indicate the information associated with a TRP transmitting downlink PRS, and the TRP-associated information may include a cell ID, an ID indicating the absolute frequency where the PRS may be transmitted, and an IE (e.g., the NR-DL-PRS-Info IE) related to PRS configured for the TRP. In some implementations, the IE related to PRS configured for a TRP may include a list of PRS resource set IEs (e.g., the NR-DL-PRS-ResourceSet IE).

[0132] In some implementations, a PRS resource set IE may indicate a set of PRS resources with some common properties, and a PRS resource set IE may include a PRS resource set ID, a parameter indicating the periodicity and the offset of the PRS resources associated with the PRS resource set, the length of time gap of the PRS resources associated with the PRS resource set, the repetition factor, the number of symbols for the PRS resources associated with the PRS resource set, the power of the PRS resources associated with the PRS resource set, and a list of PRS resource IEs. In some implementations, a PRS resource IE may indicate a specific PRS resource in a PRS resource set, and a PRS resource IE may include a PRS resource ID, a PRS sequence ID, a pattern of the symbols where PRS is transmitted, a slot offset and a symbol offset referred to the offset of the associated PRS resource set, and a Quasi-CoLocation (QCL) IE indicating the beam of the PRS.

[0133] In some implementations, the LMF may additionally include an AI / ML assistance data IE (e.g., NR-DL-AIML-ProvideAssistanceData IE) which is specifically for AI / ML-based positioning in the NAS signaling (e.g., ProvideAssistanceData message). In some implementations, upon receiving the AI / ML assistance data IE from the LMF, the UE may comprehend that the parameters, information, and / or configurations included in the AI / ML assistance data IE are specifically configured for AI / ML-based positioning. In some implementations, the AI / ML assistance data IE may include a PRS configuration IE, and / or a list of AIML-ModelAssociationToAddMod IEs, and / or a list of AIML-ModelAssociationId IEs, and / or a list of AIML-FunctionalityAssociationToAddMod IEs, and / or a list of AIML-FunctionalityAssociationId IEs.

[0134] In some implementations, the PRS configuration IE (e.g., NR-DL-PRS-AssistanceData) may be used to indicate the PRS configuration associated with the AI / ML-based positioning and an AI / ML model ID for the UE to identify. In some implementations, a UE receiving such AI / ML assistance data IE may comprehend that all of the PRS resources, PRS resource sets, and frequency layers configured in the assistance data IE are associated with an AI / ML model. The AI / ML model may be trained, stored, re-trained, monitored, activated, and / or deactivated and may be identified by the AI / ML model ID.

[0135] In some implementations, the list of particular IEs (e.g., the AIML-ModelAssociationToAddMod IEs) may be used to add or modify the information and / or configuration related to the AI / ML models for positioning which are stored at the UE. In some implementations, an AIML-ModelAssociationToAddMod IE may include an AIML-ModelAssociationId IE, and / or an AIML-Output IE, and / or an AIML-ModelInput IE, and / or a list of prs-MeasObject IEs.

[0136] In some implementations, an AIML-ModelAssociationId IE may be used to identify an AI / ML configuration and the associated PRS measurement objects. In some implementations, an AIML-ModelAssociationId IE may take an integer value, and the UE may comprehend the value to be the identifier for the AI / ML configuration and the associated PRS measurement objects which are present in the same AIML-ModelAssociationToAddMod IE.

[0137] In some implementations, an AIML-Output IE may be used to indicate the output metric of the AI / ML model. In some implementations, an AIML-Output IE may take an ENUMERATED format, and the UE may comprehend that the model output is the UE location if the value of the AIML-Output IE is ‘location.’ The UE may comprehend that the model output is a hard indication of LoS if the value of the AIML-Output IE is 'hard-los'. The UE may comprehend that the model output is a soft indication of LoS if the value of the AIML-Output IE is ‘soft-los.’ In some implementations, a UE may comprehend that the output of the AI / ML model is up to the implementation of the UE if the AIML-Output IE is absent or is present with value ‘null.’

[0138] In some implementations, an AIML-Input IE may be used to indicate the input metric of the AI / ML model. In some implementations, an AIML-Input IE may take an ENUMERATED format, and the UE may comprehend that the model input is the Channel Impulse Response (CIR) if the value of the AIML-Input IE is ‘cir.’ The UE may comprehend that the model input is the delay profile (DP) if the value of the AIML-Input IE is ‘dp.’ The UE may comprehend that the model input is the power delay profile if the value of the AIML-Input IE is ‘pdp.’ In some implementations, a UE may comprehend that the input of the AI / ML model is up to the implementation of the UE if the AIML-Input IE is absent or is present with value ‘null.’

[0139] In some implementations, the prs-MeasObject IE may be used to indicate a PRS measurement object specific for the model.

[0140] In some implementations, the prs-MeasObject IE may be a frequencyLayer object with a dl-PRS-ID IE, and the UE may comprehend the PRS measurement object is all the PRS resources associated with the frequency layer whose dl-PRS-ID equals the dl-PRS-ID in the prs-MeasObject.

[0141] In some implementations, the prs-MeasObject IE may be a prs-ResourceSet object with a dl-PRS-ID IE and an nr-DL-PRS-ResourceSetID IE, and the UE may comprehend the PRS measurement object is all the PRS resources associated with the PRS resource set whose nr-DL-PRS-ResourceSetID equals the nr-DL-PRS-ResourceSetID in the prs-MeasObject and which is associated with the frequency layer whose dl-PRS-ID equals the dl-PRS-ID in the prs-MeasObject.

[0142] In some implementations, the prs-MeasObject IE may be a prs-Resource object with a dl-PRS-ID IE, an nr-DL-PRS-ResourceSetID IE, and an nr-DL-PRS-ResourceID, and the UE may comprehend the PRS measurement object is the PRS resource whose nr-DL-PRS-ResourceID equals the nr-DL-PRS-ResourceID in the prs-MeasObject and which is associated with the PRS resource set whose nr-DL-PRS-ResourceSetID equals the nr-DL-PRS-ResourceSetID in the prs-MeasObject and which is associated with the frequency layer whose dl-PRS-ID equals the dl-PRS-ID in the prs-MeasObject.

[0143] In some implementations, the list of AIML-ModelAssociationId IEs may be used to release the information and / or configuration related to the AI / ML models for positioning which are stored at the UE. The list of AIML-ModelAssociationId IEs may be included in an AIML-ModelAssociationIDToRelease IE. In some implementations, a UE may comprehend that the stored AIML-ModelAssociationToAddMod IEs whose AIML-ModelAssociationId IE values are in the list are to be released.

[0144] In some implementations, the list of AIML-FunctionalityAssociationToAddMod IEs may be used to add or modify the information and / or configuration related to the AI / ML functionalities for positioning which are stored at the UE. In some implementations, an AIML-FunctionalityAssociationToAddMod IE may include an AIML-FunctionalityAssociationId IE, and / or a list of prs-MeasObject IEs.

[0145] In some implementations, an AIML-FunctionalityAssociationId IE may be used to identify an AI / ML configuration and the associated PRS measurement objects. In some implementations, an AIML-FunctionalityAssociationId IE may take an integer value, and the UE may comprehend the value to be the identifier for the AI / ML configuration and the associated PRS measurement objects which are present in the same AIML-FunctionalityAssociationToAddMod IE.

[0146] In some implementations, the prs-MeasObject IE may be used to indicate a PRS measurement object specific for the model.

[0147] In some implementations, the prs-MeasObject IE may be a frequencyLayer object with a dl-PRS-ID IE, and the UE may comprehend the PRS measurement object is all the PRS resources associated with the frequency layer whose dl-PRS-ID equals the dl-PRS-ID in the prs-MeasObject.

[0148] In some implementations, the prs-MeasObject IE may be a prs-ResourceSet object with a dl-PRS-ID IE and an nr-DL-PRS-ResourceSetID IE, and the UE may comprehend the PRS measurement object is all the PRS resources associated with the PRS resource set whose nr-DL-PRS-ResourceSetID equals the nr-DL-PRS-ResourceSetID in the prs-MeasObject and which is associated with the frequency layer whose dl-PRS-ID equals the dl-PRS-ID in the prs-MeasObject.

[0149] In some implementations, the prs-MeasObject IE may be a prs-Resource object with a dl-PRS-ID IE, an nr-DL-PRS-ResourceSetID IE, and an nr-DL-PRS-ResourceID, and the UE may comprehend the PRS measurement object is the PRS resource whose nr-DL-PRS-ResourceID equals the nr-DL-PRS-ResourceID in the prs-MeasObject and which is associated with the PRS resource set whose nr-DL-PRS-ResourceSetID equals the nr-DL-PRS-ResourceSetID in the prs-MeasObject and which is associated with the frequency layer whose dl-PRS-ID equals the dl-PRS-ID in the prs-MeasObject.

[0150] In some implementations, the list of AIML-FunctionalityAssociationId IEs may be used to release the information and / or configuration related to the AI / ML functionalities for positioning which are stored at the UE. In some implementations, a UE may comprehend that the stored AIML-FunctionalityAssociationToAddMod IEs whose AIML-FunctionalityAssociationId IE values are in the list are to be released.

[0151] In some implementations, the LMF may include additional AI / ML assistance IEs in ProvideAssistanceData IEs (e.g., the NR-DL-TDOA-ProvideAssistanceData IE, the NR-DL-AOD-ProvideAssistanceData IE, and the NR-Multi-RTT-ProvideAssistanceData IE), where the additional AI / ML assistance IEs may be the above-mentioned list of AIML-ModelAssociationToAddMod IEs, and / or the list of AIML-ModelAssociationId IEs, and / or the list of AIML-FunctionalityAssociationToAddMod IEs, and / or the list of AIML-FunctionalityAssociationId IEs.

[0152] In some implementations, upon receiving the third NAS signaling, the UE may apply the configuration included in the third NAS signaling.

[0153] In some implementations, the UE may stop inferencing the current models and / or functionalities upon receiving the third NAS signaling.

[0154] In some implementations, the UE may deactivate all the activated models and / or functionalities upon receiving the third NAS signaling.

[0155] In some implementations, the UE may store the PRS configuration IE in the third NAS signaling. In some implementations, if the UE has stored a PRS configuration IE associated with the AI / ML positioning method, the UE may release the stored PRS configuration IE associated with the AI / ML positioning method and then store the PRS configuration IE in the third NAS signaling as the PRS configuration IE associated with the AI / ML positioning method.

[0156] In some implementations, the UE may check the list of AIML-ModelAssociationToAddMod IEs in the received third NAS signaling with the stored AIML-ModelAssociationToAddMod IEs.

[0157] In some implementations, for an AIML-ModelAssociationToAddMod IE in the received third NAS signaling, if there is an existing stored AIML-ModelAssociationToAddMod IE with the same AIML-ModelAssociationId IE value, the UE may release the corresponding stored AIML-ModelAssociationToAddMod IE and store the received AIML-ModelAssociationToAddMod IE.

[0158] In some implementations, for an AIML-ModelAssociationToAddMod IE in the received third NAS signaling, if there is no existing stored AIML-ModelAssociationToAddMod IE with the same AIML-ModelAssociationId IE value, the UE may store the received AIML-ModelAssociationToAddMod IE.

[0159] In some implementations, the UE may check the list of AIML-ModelAssociationId IEs in the received third NAS signaling. In some implementations, the UE may release the stored AIML-ModelAssociationToAddMod IEs whose AIML-ModelAssociationId IE values are in the list.

[0160] In some implementations, the UE may check the list of AIML-FunctionalityAssociationToAddMod IEs in the received third NAS signaling with the stored AIML-FunctionalityAssociationToAddMod IEs.

[0161] In some implementations, for an AIML-FunctionalityAssociationToAddMod IE in the received third NAS signaling, if there is an existing stored AIML-FunctionalityAssociationToAddMod IE with the same AIML-FunctionalityAssociationId IE value, the UE may release the corresponding stored AIML-FunctionalityAssociationToAddMod IE and store the received AIML-FunctionalityAssociationToAddMod IE.

[0162] In some implementations, for an AIML-FunctionalityAssociationToAddMod IE in the received third NAS signaling, if there is no existing stored AIML-FunctionalityAssociationToAddMod IE with the same AIML-FunctionalityAssociationId IE value, the UE may store the received AIML-FunctionalityAssociationToAddMod IE.

[0163] In some implementations, the UE may check the list of AIML-FunctionalityAssociationId IEs in the received third NAS signaling. In some implementations, the UE may release the stored AIML-FunctionalityAssociationToAddMod IEs whose AIML-FunctionalityAssociationId IE values are in the list.

[0164] Measurement Data Collection and Model / Functionality Association

[0165] This section may describe the procedures for collecting measurement data, training AI / ML models, and managing dynamic associations between models and network conditions. The mechanisms presented herein may detail how the UE organizes PRS measurements into labeled datasets, trains AI / ML models using these datasets, and validates model performance through cross-set validation. These procedures may directly implement actions 104 through 110 of process 100 by providing specific mechanisms for measurement collection, result labeling, and model training with association identifiers. Additionally, this section may introduce temporary association mechanisms that allow dynamic updates to model-condition mappings based on validation results. While these data collection and model training procedures may complement Process 100 for comprehensive AI / ML positioning, the mechanisms may also be implemented independently in systems requiring structured measurement management and adaptive model association for positioning applications.

[0166] In some implementations, the UE may perform a PRS measurement according to the stored PRS measurement object associated with the AI / ML positioning method. In some implementations, the UE may collect the measured results and store the measured results in a memory space labeled by the FunctionalityAssociationId and / or the ModelAssociationId associated with the PRS measurement object on which the measurement is performed. In the present disclosure, a “dataset” may represent a collection of measurement results stored in a memory space labeled by a specific IE such as the FunctionalityAssociationId IE or the ModelAssociationId IE.

[0167] In some implementations, the UE may determine the measured result according to the AIML-Input IE included in the stored AIML-ModelAssociationToAddMod IE whose ModelAssociationId labels the dataset.

[0168] In some implementations, the UE may determine the channel impulse response as the measured result if the value of the AIML-Input IE is ‘cir.’

[0169] In some implementations, the UE may determine the delay profile as the measured result if the value of the AIML-Input IE is ‘dp.’

[0170] In some implementations, the UE may determine the power delay profile as the measured result if the value of the AIML-Input IE is ‘pdp.’

[0171] In some implementations, the UE may determine the Reference Signal Received Power (RSRP) as the measured result if the value of the AIML-Input IE is ‘rsrp.’

[0172] In some implementations, the UE may determine the Signal to Interference and Noise Ratio (SINR) as the measured result if the value of the AIML-Input IE is ‘sinr.’

[0173] In some implementations, the UE may determine the Received Signal Strength Indicator (RSSI) as the measured result if the value of the AIML-Input IE is 'rssi'.

[0174] In some implementations, the UE may consider that the determination of the measured result is up to the implementation of the UE if the value of the AIML-Input IE is 'null' or if the AIML-Input IE is absent from the stored AIML-ModelAssociationToAddMod IE.

[0175] In some implementations, the measured result may additionally include the ground truth label associated with the measurement result.

[0176] In some implementations, the ground truth label may include but may not be limited to the location of the UE, and / or the LoS probability, and / or the quality of the ground truth label. In some implementations, the UE may determine the ground truth label according to the AIML-Output IE included in the stored AIML-ModelAssociationToAddMod IE whose ModelAssociationId labels the dataset.

[0177] In some implementations, the UE may determine the location of the UE as the ground truth label if the value of the AIML-Output IE is ‘location.’

[0178] In some implementations, the UE may determine the soft indication of LoS probability as the ground truth label if the value of the AIML-Output IE is ‘soft-los.’ The soft indication of LoS probability may refer to a predefined value indicating the LoS probability. In some implementations, the soft indication may take an ENUMERATED value. For example, a soft indication of LoS probability with value '.3' may be interpreted as the probability of LoS is 0.3.

[0179] In some implementations, the UE may determine the hard indication of LoS probability as the ground truth label if the value of the AIML-Output IE is ‘hard-los.’ The hard indication of LoS probability may refer to a binary value indicating the LoS probability and may take ENUMERATED values in {‘los’, ‘nlos’} or a Boolean value. The binary value may include one value indicating the LoS probability as 0 and the other value indicating the LoS probability as 1, or one value indicating the LoS probability as greater than 0.5 and the other value indicating the LoS probability as less than 0.5. For example, a hard indication of LoS probability with value 'true' or with value ‘nlos’ may be interpreted that the channel status is LoS.

[0180] In some implementations, the UE may consider that the determination of the ground truth label is up to the implementation of the UE if the value of the AIML-Output IE is ‘null’ or if the AIML-Output IE is absent from the stored AIML-ModelAssociationToAddMod IE.

[0181] In some implementations, a ground truth label is associated with a measurement result if the ground truth label and the measurement result are obtained within a period. In some implementations, the period may be preconfigured by the network. The period may be configured as a multiple of the PRS period, as a multiple of the monitoring period, or as a multiple of the inference period. In some implementations, the period may be set up to the implementation of the UE. In some implementations, a UE may consider a ground truth label is not associated with a measurement result and / or a measurement result is not associated with a ground truth label if the ground truth label and the measurement result are not obtained within a period. In some implementations, if a ground truth label is not associated with any measurement result, the UE may release the ground truth label. If a measurement result is not associated with any ground truth label, the UE may release the measurement result.

[0182] In some implementations, the UE may store the measured result in the dataset labeled by a specific ID (e.g., the FunctionalityAssociationId IE and / or the ModelAssociationId IE) associated with the PRS measurement object on which the measurement is performed.

[0183] In some implementations, if a PRS measurement object is associated with more than one FunctionalityAssociationId and / or ModelAssociationId, the UE may separately store the measured result obtained from the PRS measurement object in more than one dataset labeled by the more than one FunctionalityAssociationId and / or ModelAssociationId which the PRS measurement object is associated with.

[0184] In some implementations, the UE may train the AI / ML model with one or more of the stored datasets. In some implementations, after training the AI / ML model, the UE may associate the obtained AI / ML model with the FunctionalityAssociationId and / or the ModelAssociationId corresponding to the one or more datasets used for the training the AI / ML model.

[0185] In some implementations, the UE may perform cross-set validation by validating an AI / ML model with stored datasets labeled by the FunctionalityAssociationId and / or the ModelAssociationId which are not associated with the AI / ML model.

[0186] In some implementations, if the AI / ML model passes the cross-set validation, the UE may temporarily associate the AI / ML model with the FunctionalityAssociationId and / or the ModelAssociationId labeling the datasets for cross-set validation. In some implementations, the UE may generate a temporary association of model and NW-side AC, and / or an association of functionality and NW-side AC, and / or an association of functionality and model. In some implementations, the generated temporary associations may be separate from the stored associations, and the generated temporary associations may be released or updated dynamically.

[0187] In some implementations, if the AI / ML model passes the cross-set validation, the UE may transmit fourth NAS signaling toward the network (e.g., the LMF). In some implementations, the fourth NAS signaling may include a temporary model-AC association IE, and / or a temporary model-functionality association IE, and / or a temporary functionality-AC association IE, and / or a temporary association validity timer IE, and / or a temporary association validity counter IE. In some implementations, upon receiving the fourth NAS signaling from the UE, the LMF may apply the temporary associations indicated in the fourth NAS signaling.

[0188] In some implementations, a temporary model-AC association IE may be used to indicate the temporary association between the model and the NW-side ACs. In some implementations, the temporary model-AC association IE may be a list of sequences, each of which includes one or more AIML-ModelAssociationId IEs and one or more NW-side AC indication IEs, and the LMF may comprehend that the models with AIML-ModelAssociationId IEs may be temporarily associated with the NW-side ACs indicated by the NW-side AC indication IEs in the same sequence. In some implementations, upon receiving the fourth NAS signaling from the UE, if the temporary model-AC association IE is present, the LMF may store the temporary model-AC association IE.

[0189] In some implementations, a temporary functionality-AC association IE may be used to indicate the temporary association between the functionality and the NW-side ACs. In some implementations, the temporary functionality-AC association IE may be a list of sequences, each of which includes one or more AIML-FunctionalityAssociationId IEs and one or more NW-side AC indication IEs, and the LMF may comprehend that the functionalities with AIML-FunctionalityAssociationId IEs may be temporarily associated with the NW-side ACs indicated by the NW-side AC indication IEs in the same sequence. In some implementations, upon receiving the fourth NAS signaling from the UE, if the temporary functionality-AC association IE is present, the LMF may store the temporary functionality-AC association IE.

[0190] In some implementations, the temporary model-functionality association IE may be used to indicate the temporary association between the functionality and the model. In some implementations, the temporary model-functionality association IE may be a list of sequences, each of which includes one or more AIML-FunctionalityAssociationId IEs and one or more AIML-ModelAssociationId IEs, and the LMF may comprehend that the functionalities with AIML-FunctionalityAssociationId IEs may be temporarily associated with the models with AIML-ModelAssociationId IEs in the same sequence. In some implementations, upon receiving the fourth NAS signaling from the UE, if the temporary model-functionality association IE is present, the LMF may store the temporary model-functionality association IE.

[0191] In some implementations, the temporary association validity timer IE may be used to indicate the duration that the temporary association is valid. In some implementations, the temporary association validity timer IE may take an ENUMERATED value, and the LMF may comprehend the corresponding duration to be the duration that the temporary association is valid. In some implementations, upon receiving the fourth NAS signaling from the UE, if the temporary association validity timer IE is present, the LMF may store the temporary association validity timer IE and start a first timer. In some implementations, if the first timer expires when the value of the first timer exceeds the value indicated by the temporary association validity timer IE, the LMF may perform a temporary association release procedure. In some implementations, if the first timer is running, when the LMF receives another fourth NAS signaling from the UE, the LMF may stop the first timer.

[0192] In some implementations, the association validity counter IE may be used to indicate the number of consecutive events before the temporary association is invalid. In some implementations, the association validity counter IE may take an integer value (e.g., N), and the LMF may comprehend that the temporary association is invalid upon the N-th consecutive event. In some implementations, upon receiving the fourth NAS signaling from the UE, if the temporary association validity counter IE is present, the LMF may store the temporary association validity counter IE and start a first counter. The LMF may initialize the first counter to 1. In some implementations, upon an event occurrence, the LMF may increase the first counter. In some implementations, if the first counter equals the value indicated by the temporary association validity counter IE, the LMF may perform a temporary association release procedure. In some implementations, an event may be an inference instance, and / or a monitoring instance, and / or a preconfigured periodicity. The consecutive events may be the same events. For example, the LMF may consider the temporary association is invalid upon the N-th consecutive inference instance.

[0193] In some implementations, a NW-side AC indication IE may take an integer value and may indicate a NW-side AC according to the association in the first NAS signaling.

[0194] In some implementations, a NW-side AC indication IE may take an integer value and may indicate a NW-side AC according to a predefined table stored by the UE.

[0195] In some implementations, a NW-side AC indication IE may take an ENUMERATED value and may indicate a corresponding NW-side AC.

[0196] In some implementations, if a monitoring event occurs when the accuracy of the AI / ML functionality falls below a threshold for a consecutive number of monitoring instances, the LMF may perform a temporary association release procedure.

[0197] In some implementations, if the LMF receives a new fourth NAS signaling from the UE, the LMF may perform a temporary association release procedure and apply the temporary association in the new fourth NAS signaling.

[0198] In some implementations, in a temporary association release procedure, the LMF may release all of, or a part of, the temporary model-AC association IE, and / or the temporary model-functionality association IE, and / or the temporary functionality-AC association IE, and / or the temporary association validity timer IE, and / or the temporary association validity counter IE.

[0199] In some implementations, after performing a temporary association release procedure, the LMF may send a NAS signaling to the UE to indicate the release of the temporary associations.

[0200] NW-side Life Cycle Management (LCM) for UE-side model with Association ID

[0201] This section may describe the LCM procedures for controlling UE-side AI / ML models through association identifiers. The mechanisms presented herein may enable the network entity to dynamically manage AI / ML models and functionalities at the UE by sending management commands via NAS signaling. The LCM procedures may extend the framework established in process 100 by providing operational control over the AI / ML models that have been trained and labeled with association identifiers. The activation, deactivation, training, and selection mechanisms described in this section may demonstrate how the association identifier system introduced in process 100 enables efficient model management throughout the positioning service lifecycle. While these LCM procedures may build upon process 100 to provide comprehensive model control, the mechanisms may also be implemented independently in systems requiring network-controlled management of AI / ML resources for positioning applications.

[0202] In some implementations, the LMF may perform LCM via one or more association IDs such as the AIML-ModelAssociationId IE and / or the AIML-FunctionalityAssociationId IE.

[0203] In some implementations, the LMF may tranmit fifth NAS signaling to instruct the UE to perform activation, deactivation, train, and / or (re)selection on the UE-side models and / or functionalities. In some implementations, the fifth NAS signaling may include a management IE, and / or a list of AIML-ModelAssociationId IEs, and / or a list of AIML-FunctionalityAssociationId IEs. In some implementations, the management IE may be used to indicate the action instructed to the UE and may take an ENUMERATED value.

[0204] In some implementations, if the management IE is set to ‘activation,’ the UE may comprehend to activate the models associated with the value in the list of the AIML-ModelAssociationId IEs, and / or the functionalities associated with the value in the list of the AIML-FunctionalityAssociationId IEs.

[0205] In some implementations, if the management IE is set to ‘deactivation,’ the UE may comprehend to deactivate the models associated with the value in the list of the AIML-ModelAssociationId IEs, and / or the functionalities associated with the value in the list of the AIML-FunctionalityAssociationId IEs.

[0206] In some implementations, if the management IE is set to ‘train,’ the UE may comprehend to train and / or retrain the models associated with the value in the list of the AIML-ModelAssociationId IEs, and / or the functionalities associated with the value in the list of the AIML-FunctionalityAssociationId IEs. In some implementations, after the UE trains and / or retrains the models, the UE may immediately activate the models.

[0207] In some implementations, if the management IE is set to ‘train,’ and the UE is using a model which is associated with the value in the list of the AIML-ModelAssociationId IEs, the UE may stop using the model and may deactivate the model. If the management IE is ‘train,’ and the UE is using a functionality which is associated with the value in the list of the AIML-FunctionalityAssociationId IEs, the UE may stop using the functionality and may deactivate the functionality. In some implementations, if the management IE is set to ‘selection,’ the UE may comprehend to use the models associated with the value in the list of the AIML-ModelAssociationId IEs, and / or the functionalities associated with the value in the list of the AIML-FunctionalityAssociationId IEs for the inference.

[0208] In some implementations, if the management IE is set to ‘reselection,’ the UE may comprehend to stop using the currently used model and / or functionality and use the models associated with the value in the list of the AIML-ModelAssociationId IEs, and / or the functionalities associated with the value in the list of the AIML-FunctionalityAssociationId IEs for the inference.

[0209] Alternatively or additionally, the LMF may send sixth NAS signaling to instruct the UE to perform activation, deactivation, train, and / or (re)selection on the UE-side models and / or functionalities. In some implementations, the sixth NAS signaling may include an activationModelList IE, and / or an activationFunctionalityList IE, and / or a deactivationModelList IE, and / or a deactivationFunctionalityList IE, and / or a trainModelList IE, and / or a trainFunctionalityList IE, and / or a selectionModelList IE, and / or a selectionFunctionalityList IE.

[0210] In some implementations, an activationModelList IE may be used to indicate the models to be activated and may be a list of AIML-ModelAssociationId IEs. In some implementations, the UE may interpret the activationModelList IE to activate the models associated with the AIML-ModelAssociationId IE values in the activationModelList.

[0211] In some implementations, an activationFunctionalityList IE may be used to indicate the functionalities to be activated and may be a list of AIML-FunctionalityAssociationId IEs. In some implementations, the UE may interpret the activationFunctionalityList IE to activate the functionalities associated with the AIML-FunctionalityAssociationId IE values in the list (e.g., determined by the activationFunctionalityList IE).

[0212] In some implementations, a deactivationModelList IE may be used to indicate the models to be deactivated and may be a list of AIML-ModelAssociationId IEs. In some implementations, the UE may interpret the deactivationModelList IE to deactivate the models associated with the AIML-ModelAssociationId IE values in the list (e.g., determined by the deactivationModelList IE).

[0213] In some implementations, a deactivationFunctionalityList IE may be used to indicate the functionalities to be deactivated and may be a list of AIML-FunctionalityAssociationId IEs. In some implementations, the UE may interpret the deactivationFunctionalityList IE to deactivate the functionalities associated with the AIML-FunctionalityAssociationId IE values in the list (e.g., determined by the deactivationFunctionalityList IE).

[0214] In some implementations, a trainModelList IE may be used to indicate the models to be trained and / or retrained and may be a list of AIML-ModelAssociationId IEs. In some implementations, the UE may interpret the trainModelList IE to train and / or retrain the models associated with the AIML-ModelAssociationId IE values in the trainModelList.

[0215] In some implementations, a trainFunctionalityList IE may be used to indicate the functionalities to be trained and / or retrained and may be a list of AIML-FunctionalityAssociationId IEs. In some implementations, the UE may interpret the trainFunctionalityList IE to train and / or retrain the functionalities associated with the AIML-FunctionalityAssociationId IE values in list determined by the trainFunctionalityList IE.

[0216] In some implementations, a selectionModelList IE may be used to indicate the models to be inferenced and may be a list of AIML-ModelAssociationId IEs. In some implementations, a reselectionModelList IE may be used to indicate the models to be reselected for inference and may be a list of AIML-ModelAssociationId IEs. In some implementations, the UE may interpret to inference the models associated with the AIML-ModelAssociationId IE values in the selectionModelList. In some implementations, the UE may interpret to stop inferencing the current models and start inferencing the models associated with the AIML-ModelAssociationId IE values in the list determined by the reselectionModelList IE.

[0217] In some implementations, a selectionFunctionalityList IE may be used to indicate the functionalities to be inferenced and may be a list of AIML-FunctionalityAssociationId IEs. In some implementations, a reselectionFunctionalityList IE may be used to indicate the functionalities to be reselected for inference and may be a list of AIML-FunctionalityAssociationId IEs. In some implementations, the UE may interpret to inference the functionalities associated with the AIML-FunctionalityAssociationId IE values in the list determined by the selectionFunctionalityList IE. In some implementations, the UE may interpret to stop inferencing the current functionalities and start inferencing the functionalities associated with the AIML-FunctionalityAssociationId IE values in the list determined by the reselectionFunctionalityList IE.

[0218] In the present disclosure, the RAT may include but may not be limited to the NR, the LTE, the E-UTRA connected to the 5GC, the LTE connected to the 5GC, the E-UTRA connected to the EPC, and LTE connected to the EPC. The mechanisms proposed in the present disclosure may be applied for UEs in public networks, or in a private network such as a Non-Public Network (NPN), a Standalone NPN (SNPN), or a Public Network Integrated-NPN (PNI-NPN).

[0219] The mechanisms proposed in the present disclosure may be used for a licensed frequency and / or an unlicensed frequency. In addition, the proposed mechanism of conditional configuration selection may be applied for the cases where a UE may experience a radio link failure when configured with conditional configurations.

[0220] The system information (SI) may refer to the Master Information Block (MIB), the System Information Block Type 1 (SIB1), and other SI. The minimum SI may include the MIB and the SIB1. Other SI may refer to the SIB3, the SIB4, the SIB5, and other SIB(s).

[0221] The dedicated signaling may refer to but may not be limited to Radio Resource Control (RRC) message(s). For example, the dedicated signaling may include the RRC (Connection) Setup Request message, the RRC (Connection) Setup message, the RRC (Connection) Setup Complete message, the RRC (Connection) Reconfiguration message, the RRC Connection Reconfiguration message including the mobility control information, the RRC Connection Reconfiguration message without the mobility control information inside, the RRC Reconfiguration message including the configuration with sync, the RRC Reconfiguration message without the configuration with sync inside, the RRC (Connection) Reconfiguration Complete message, the RRC (Connection) Resume Request message, the RRC (Connection) Resume message, the RRC (Connection) Resume Complete message, the RRC (Connection) Reestablishment Request message, the RRC (Connection) Reestablishment message, the RRC (Connection) Reestablishment Complete message, the RRC (Connection) Reject message, the RRC (Connection) Release message, the RRC System Information Request message, the UE Assistance Information message, the UE Capability Enquiry message, and the UE Capability Information message.

[0222] The UE in the RRC_CONNECTED state, the UE in the RRC_INACTIVE state, and the UE in the RRC_IDLE state may apply the proposed mechanisms.

[0223] The NAS signaling in the present disclosure may refer to but may not be limited to the LPP message.

[0224] FIG. 2 is a block diagram illustrating node 200 for wireless communications, in accordance with various aspects of the present disclosure. As illustrated in FIG. 2, node 200 may include transceiver 220, processor 228, memory 234, one or more presentation components 238, and at least one antenna 236. Node 200 may also include a radio frequency (RF) spectrum band module, a BS communications module, a network communications module, and a system communications management module, Input / Output (I / O) ports, I / O components, and a power supply (not illustrated in FIG. 2).

[0225] Each of the components may directly or indirectly communicate with each other over one or more buses 240. Node 200 may be a UE or a BS that performs various functions disclosed with reference to FIG. 1.

[0226] Transceiver 220 has transmitter 222 (e.g., transmitting / transmission circuitry) and receiver 224 (e.g., receiving / reception circuitry) and may be configured to transmit and / or receive time and / or frequency resource partitioning information. Transceiver 220 may be configured to transmit in different types of subframes and slots including, but not limited to, usable, non-usable, and flexibly usable subframes and slot formats. Transceiver 220 may be configured to receive data and control channels.

[0227] Node 200 may include a variety of computer-readable media. Computer-readable media may be any available media that may be accessed by node 200 and include volatile (and / or non-volatile) media and removable (and / or non-removable) media.

[0228] The computer-readable media may include computer-storage media and communication media. Computer-storage media may include both volatile (and / or non-volatile media), and removable (and / or non-removable) media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or data.

[0229] Computer-storage media may include RAM, ROM, EPROM, EEPROM, flash memory (or other memory technology), CD-ROM, Digital Versatile Disks (DVD) (or other optical disk storage), magnetic cassettes, magnetic tape, magnetic disk storage (or other magnetic storage devices), etc. Computer-storage media may not include a propagated data signal. Communication media may typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanisms and include any information delivery media.

[0230] The term “modulated data signal” may mean a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. Communication media may include wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, and other wireless media. Combinations of any of the aforementioned listed components should also be included within the scope of computer-readable media.

[0231] Memory 234 may include computer-storage media in the form of volatile and / or non-volatile memory. Memory 234 may be removable, non-removable, or a combination thereof. Example memory may include solid-state memory, hard drives, optical-disc drives, etc. As illustrated in FIG. 2, memory 234 may store a computer-readable and / or computer-executable instructions 232 (e.g., software codes) that are configured to, when executed, cause processor 228 to perform various functions disclosed herein, for example, with reference to FIG. 1. Alternatively, instructions 232 may not be directly executable by processor 228 but may be configured to cause node 200 (e.g., when compiled and executed) to perform various functions disclosed herein.

[0232] Processor 228 (e.g., having processing circuitry) may include an intelligent hardware device, e.g., a Central Processing Unit (CPU), a microcontroller, an ASIC, etc. Processor 228 may include memory. Processor 228 may process data 230 and instructions 232 received from memory 234, and information transmitted and received via transceiver 220, the baseband communications module, and / or the network communications module. Processor 228 may also process information to send to transceiver 220 for transmission via antenna 236 to the network communications module for transmission to a CN.

[0233] One or more presentation components 238 may present data indications to a person or another device. Examples of presentation components 238 may include a display device, a speaker, a printing component, a vibrating component, etc.

[0234] In view of the present disclosure, it is obvious that various techniques may be used for implementing the disclosed concepts without departing from the scope of those concepts. Moreover, while the concepts have been disclosed with specific reference to certain implementations, a person of ordinary skill in the art may recognize that changes may be made in form and detail without departing from the scope of those concepts. As such, the disclosed implementations are to be considered in all respects as illustrative and not restrictive. It should also be understood that the present disclosure is not limited to the particular implementations disclosed and many rearrangements, modifications, and substitutions are possible without departing from the scope of the present disclosure.

Claims

1. A User Equipment (UE) comprising: 　　　　at least one processor; and 　　　　at least one non-transitory computer-readable medium coupled to the at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the UE to: 　　　　receive, from a network entity, first Non-Access Stratum (NAS) signaling comprising at least one association identifier and a Positioning Reference Signal (PRS) configuration; 　　　　perform, based on the PRS configuration, measurements to obtain at least one measurement result; 　　　　label the at least one measurement result with the at least one association identifier; 　　　　train an Artificial Intelligence or Machine Learning (AI / ML) model based on the at least one measurement result labeled with the at least one association identifier; and 　　　　label the AI / ML model with the at least one association identifier.

2. The UE of claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　receive, from the network entity, second NAS signaling comprising a list of network-side additional conditions and a functionality mapping request indication.

3. The UE of claim 2, wherein the list of network-side additional conditions comprises one or more network-side additional condition identifiers, each of the one or more network-side additional condition identifiers indicating a predefined environmental or deployment condition used by the network entity.

4. The UE of claim 2, wherein the functionality mapping request indication is configured to request the UE to report mapping information between one or more supported functionalities of the UE and the list of network-side additional conditions.

5. The UE of claim 4, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　transmit, to the network entity, third NAS signaling in response to the functionality mapping request indication, the third NAS signaling comprising the mapping information.

6. The UE of claim 1, wherein the network entity comprises a Location Management Function (LMF).

7. The UE of claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　receive, from the network entity, an indication to deactivate the AI / ML model.

8. A method performed by a User Equipment (UE) for Artificial Intelligence or Machine Learning (AI / ML)-based positioning, the method comprising: 　　　　receiving, from a network entity, Non-Access Stratum (NAS) signaling comprising at least one association identifier and a Positioning Reference Signal (PRS) configuration; 　　　　performing, based on the PRS configuration, measurements to obtain at least one measurement result; 　　　　labeling the at least one measurement result with the at least one association identifier; 　　　　training an AI / ML model based on the at least one measurement result labeled with the at least one association identifier; and 　　　　labeling the AI / ML model with the at least one association identifier.

9. A network entity comprising: 　　　　at least one processor; and 　　　　at least one non-transitory computer-readable medium coupled to the at least one processor and storing computer-executable instructions that, when executed by the at least one processor, cause the network entity to: 　　　　transmit, to a User Equipment (UE), first Non-Access Stratum (NAS) signaling comprising at least one association identifier and a Positioning Reference Signal (PRS) configuration, enabling the UE to perform, based on the PRS configuration, measurements to obtain at least one measurement result and to label the at least one measurement result with the at least one association identifier.

10. The network entity of claim 9, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the network entity to: 　　　　transmit, to the UE, second NAS signaling comprising a list of network-side additional conditions and a functionality mapping request indication.

11. The network entity of claim 10, wherein the list of network-side additional conditions comprises one or more network-side additional condition identifiers, each of the one or more network-side additional condition identifiers indicating a predefined environmental or deployment condition used by the network entity.

12. The network entity of claim 10, wherein the functionality mapping request indication is configured to request the UE to report mapping information between one or more supported functionalities of the UE and the list of network-side additional conditions.

13. The network entity of claim 10, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the network entity to: 　　　　receive, after transmitting the second NAS signaling to the UE, third NAS signaling comprising the mapping information from the UE.

14. The network entity of claim 9, wherein the network entity comprises a Location Management Function (LMF).

15. The network entity of claim 9, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the network entity to: 　　　　transmit, to the UE, an indication to deactivate an Artificial Intelligence or Machine Learning (AI / ML) model trained by the at least one measurement result.

Images