Device and method for data collection in wireless communication networks
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-07
- Publication Date
- 2026-08-13
Smart Images

Figure CN2025076306_13082026_PF_FP_ABST
Abstract
Description
DEVICE AND METHOD FOR DATA COLLECTION IN WIRELESS COMMUNICATION NETWORKSTECHNICAL FIELD
[0001] The present disclosure relates to wireless communication systems, particularly in the context of new radio (NR) technologies. Specifically, it pertains to the application of artificial intelligence (AI) and machine learning (ML) techniques for enhancing the positioning accuracy of user equipment (UE) , particularly in scenarios involving non-line-of-sight (NLOS) conditions between transmission and reception points (TRPs) and the UE.BACKGROUND
[0002] Positioning of UE is crucial in modern wireless networks, particularly for applications that require high precision, such as navigation, autonomous systems, and location-based services. Traditional positioning techniques rely on line-of-sight (LOS) conditions for accurate position estimation. However, in many practical scenarios, non-line-of-sight (NLOS) conditions are prevalent due to obstacles such as buildings, walls, or other environmental obstructions, degrading traditional positioning techniques' accuracy.
[0003] To address this challenge, the 3rd Generation Partnership Project (3GPP) has investigated using AI / ML techniques to enhance positioning in 5G NR systems. By leveraging channel measurements obtained from uplink (UL) and downlink (DL) transmissions, AI / ML-based methods enable enhanced positioning accuracy even under NLOS conditions. These channel measurements can be used in two principal approaches: (i) direct AI / ML positioning, where the position of a UE is directly estimated from channel measurements, and (ii) AI / ML-assisted positioning, where channel parameters, such as time of arrival (TOA) or LOS / NLOS indicators, are estimated from channel measurements and subsequently used for position calculation.
[0004] In both approaches, AI / ML models are trained using channel measurements and corresponding labels (e.g., known positions or channel parameter values) . Once trained, these models can infer the UE's position or channel parameters. Depending on the system configuration, the AI / ML model can be deployed at different network nodes, including the UE, the gNodeB (gNB) , or the location management function (LMF) . The network node at which the channel measurements are collected and the location where the positioning process is executed can vary, leading to several use-case scenarios.
[0005] The models may leverage channel measurements derived from different types of reference signals. Positioning Reference Signals (PRS) transmitted from the gNB are used for downlink measurements. Sounding Reference Signals (SRS) transmitted by the UE or positioning reference units (PRUs) are utilized for uplink measurements. The PRUs are special devices with a known position, often used to create labeled datasets for model training.
[0006] Several use cases and scenarios have been identified for positioning in the study of AI / ML for NR air interface under 3GPP Release 18, classified according to the model's location, the measurements' collection point, and the node where the positioning takes place. For example, the model may be located at the UE, the gNB, or the LMF, while the channel measurements may be collected at the UE, the gNB, or the PRU. This diversity in system configurations enables different architectures for the implementation of AI / ML-based positioning.
[0007] A critical aspect of the disclosure is the reporting and interpreting of channel measurements and calculated results. Traditionally, network nodes (e.g., gNBs, PRUs, and UEs) report measured results (i.e., channel measurements) to the LMF, which processes the information to compute the position of the UE. However, in AI / ML-assisted positioning, network nodes report calculated results, such as model-derived timing information (e.g., time of flight (TOF) or relative time of arrival (RTOA) ) and LOS / NLOS indicators, to the LMF. This information enables the LMF to make more accurate decisions regarding the UE's position, even in NLOS conditions.
[0008] While these techniques offer potential advantages, practical challenges exist, especially in the context of data collection. For example, accurate pairing of channel measurements and corresponding labels (e.g., ground-truth UE locations) is often required. Pairing can be performed based on timestamp proximity. If the time difference between a measurement and its label is too large, pairing errors may occur, leading to reduced accuracy. In some cases, labels (e.g., location information) are generated at a centralized LMF that may not be generated simultaneously when the channel measurements are collected at a UE or gNB.
[0009] These limitations highlight the complexity of achieving high positioning accuracy, especially in dynamic and obstructed environments, and underscore the importance of further developments in this area.SUMMARY
[0010] Given the above challenges, this disclosure aims to introduce a novel system, method, and apparatus for enhancing the accuracy, efficiency, and reliability of positioning in wireless communication systems, particularly in the context of 5G NR and beyond. One objective of this disclosure is to improve the accuracy of machine learning models or fingerprinting-based schemes used in wireless communication systems. Another objective is to provide a solution that can be flexibly implemented in multiple deployment scenarios.
[0011] These and other objectives are achieved by the solution of the present disclosure as provided in the independent claims. Advantageous implementations are further defined in the dependent claims.
[0012] A first aspect of the disclosure provides an entity for a wireless communication system, the entity being configured to receive a label from a network entity, wherein the label is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps; and associate the label with a measurement obtained at the entity.
[0013] This disclosure proposes an entity or device that ensures that labels and measurements are correctly paired in time, thereby reducing mismatches and improving accuracy in training models. This approach ensures that the entity can correctly pair a received label with a measurement taken at a corresponding time. By using a defined set of time stamps, the risk of pairing mismatched labels and measurements is minimized, which is crucial for accurate data processing in wireless networks. This improves the reliability of location estimation, timing measurements, and model training.
[0014] In an implementation form of the first aspect, the entity is configured to associate the label with the measurement based on a comparison of the time stamp associated with the label and a time stamp associated with the measurement.
[0015] By comparing the time stamp of the label and the time stamp of the measurement, the entity can determine the best possible match, ensuring that the data used for analysis or model training are close in time. This prevents pairing with outdated or premature labels or with outdated measurement, thereby reducing errors in position estimation or other analytical processes.
[0016] In an implementation form of the first aspect, the defined set of one or more time stamps comprises one or more time stamps within a timing offset of a time when the entity makes a measurement.
[0017] Allowing a timing offset provides flexibility in pairing measurements and labels, accommodating uncertainties in network delays or processing time variations. This improves the robustness of the method in real-world conditions where perfect time alignment may not always be feasible.
[0018] In an implementation form of the first aspect, the entity is further configured to receive the defined set of one or more time stamps.
[0019] This feature ensures that the entity gains awareness of the timing of the labels that can be delivered. This enables the entity to optimize its measurement process, reducing unnecessary data collection and improving system efficiency.
[0020] In an implementation form of the first aspect, the defined set of one or more time stamps is determined by the network entity.
[0021] This allows a centralized network function, such as an LMF, to coordinate the timing of labels and measurements across multiple entities. A network-determined time stamp set ensures consistency and reduces the likelihood of conflicts between different network components.
[0022] In an implementation form of the first aspect, the defined set of one or more time stamps is determined by the network entity based on a set of one or more time stamps indicated by the entity.
[0023] This introduces a level of adaptability, where the network can adjust the time stamp set according to the entity’s operational needs. This is particularly useful when the measurement entity has knowledge of its own timing requirements, leading to better pairing at the measurement entity.
[0024] In an implementation form of the first aspect, the entity is further configured to receive an indication of the provision of a label associated with a time stamp out of the defined set of one or more time stamps.
[0025] Receiving an explicit indication about label availability allows the entity to prepare for pairing the label with the correct measurement. This prevents unnecessary delays and improves real-time processing capabilities in dynamic network environments.
[0026] In an implementation form of the first aspect, the entity is further configured to determine the defined set of one or more time stamps; and request the network entity to provide a label associated with a time stamp from the defined set of one or more time stamps.
[0027] By allowing the entity to request a label for a specific time frame, this mechanism enables proactive data collection. This ensures that the entity only receives relevant labels, reducing network overhead and unnecessary processing.
[0028] In an implementation form of the first aspect, the entity is further configured to receive a measurement request from the network entity, wherein the measurement request is indicative of the defined set of one or more time stamps.
[0029] This ensures that the entity aligns its measurements with expected label availability. By having prior knowledge of which time stamps will be used for label generation, the entity can optimize its data collection strategy.
[0030] In an implementation form of the first aspect, the one or more time stamps in the defined set are associated with a TRP identifier and / or a reference signal, and the entity is configured to obtain a measurement associated with the reference signal, and / or associated with a TRP corresponding to the TRP identifier.
[0031] By linking time stamps with specific TRPs or reference signals, the method ensures that measurements are accurately attributed to the correct transmission point. This is particularly beneficial for positioning and signal quality assessments, leading to more precise location and connectivity estimations.
[0032] In an implementation form of the first aspect, the label comprises at least one of the following: location information of a UE, an LOS indicator, a timing parameter indicative of a direct path between a UE and a TRP, said timing parameter comprising at least one of a reference signal time difference (RSTD) , a RTOA, a propagation delay, or a TOF.
[0033] This enhances the value of the labels by including key parameters necessary for network optimization and location estimation. Using precise timing parameters such as TOF or RSTD helps in refining time-based positioning calculations.
[0034] In an implementation form of the first aspect, the defined set of one or more time stamps comprises a plurality of discrete time stamps, or a continuous or semi-continuous range of time values between a minimum and maximum time value.
[0035] By supporting both discrete time stamps and continuous / semi-continuous ranges, the disclosure provides flexibility to accommodate different use cases and different pairing possibilities based on the time stamp. For example, the entity may request a label with a given time stamp but the network entity provides a label with the given time stamp plus a timing offset, such that the set of one or more time stamps comprises a range of time stamps around the given time stamp. This allows for a flexibility in the provision of the label with a time stamp.
[0036] In an implementation form of the first aspect, the entity is further configured to train a model based on a measurement and a label that are paired using one or more time stamps of the defined set of one or more time stamps, wherein the model is configured to infer at least one of: a location of a UE, an LOS indicator, or a timing parameter associated with a direct path between the UE and a TRP.
[0037] Ensuring accurate time-aligned pairing between measurements and labels leads to improved model training outcomes. This is essential for applications such as UE positioning, network optimization, and mobility prediction, where accurate pairing of measurements and labels is crucial.
[0038] In an implementation form of the first aspect, the entity is one of the following: a base station, a TRP, a gNB, a PRU, or a UE.
[0039] Possibly, the proposed entity may be implemented in a gNB, a TRP, a PRU, or a UE, which have the capability of receiving reference signals as part of their implementation of the relevant specification. Notably, this disclosure is applicable to various types of network devices, increasing its flexibility and utility in different wireless communication environments.
[0040] A second aspect of the disclosure provides a network entity in a wireless communication system, configured to provide a label to an entity, wherein the label is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps.
[0041] This disclosure further proposes a network entity that generates and provides the labels to the entity. This approach ensures that labels are generated using a predefined time stamp set helps in maintaining consistency across different network entities. This improves interoperability and reduces errors due to mismatched timing.
[0042] In an implementation form of the second aspect, the defined set of one or more time stamps is determined by the network entity.
[0043] Having the network manage the time stamp set ensures centralized control, which is beneficial in scenarios where multiple measurement entities are involved. This improves the pairing of measurements and label across different entities.
[0044] In an implementation form of the first aspect, the network entity is configured to send to the entity an indication of the provision of a label with a time stamp from the defined set of one or more time stamps.
[0045] By notifying measurement entities about the timing of the labels that can be provided, ensures efficient data utilization and prevents unnecessary processing delays.
[0046] In an implementation form of the first aspect, the network entity is further configured to receive a request to provide a label associated with a time stamp from the defined set of one or more time stamps.
[0047] This feature allows measurement entities to request labels on demand, thereby ensuring that only relevant labels are generated, optimizing resource usage.
[0048] In an implementation form of the second aspect, the network entity is further configured to send a measurement request to the entity, wherein the measurement request is indicative of the defined set of one or more time stamps.
[0049] This facilitates better planning and alignment between measurement and label generation, ensuring consistency in data collection.
[0050] In an implementation form of the second aspect, the defined set of one or more time stamps is determined by the network entity based on a set of one or more time stamps indicated by the entity.
[0051] By incorporating requirements from measurement entities, the network can fine-tune the time stamp selection process, improving alignment with measurement conditions.
[0052] In an implementation form of the second aspect, the one or more time stamps in the defined set are associated with a TRP identifier and / or a reference signal.
[0053] This ensures that labels correspond to the correct transmission sources, enhancing accuracy in positioning and network performance monitoring.
[0054] In an implementation form of the second aspect, the label comprises at least one of the following: location information of a UE, an LOS indicator, a timing parameter indicative of a direct path between a UE and a TRP, said timing parameter comprising at least one of a RSTD, a RTOA, a propagation delay, or a TOF.
[0055] This enhances the value of the labels by including key parameters necessary for network optimization and location estimation. Using precise timing parameters such as TOF or RSTD helps in refining time-based positioning calculations.
[0056] In an implementation form of the second aspect, the defined set of one or more time stamps comprises a plurality of discrete time stamps, or a continuous or semi-continuous range of time values between a minimum and maximum time value.
[0057] By supporting both discrete time stamps and continuous / semi-continuous ranges, the disclosure provides flexibility to accommodate different use cases and different pairing possibilities based on the time stamp. For example, the entity may request a label with a given time stamp but the network entity provides a label with the given time stamp plus a timing offset, such that the set of one or more time stamps comprises a range of time stamps around the given time stamp. This allows for a flexibility in the provision of the label with a time stamp.
[0058] In an implementation form of the second aspect, the network entity is an LMF.
[0059] This identifies the network entity as an LMF, which is responsible for managing positioning services in the system. By specifying the LMF, it allows for optimized coordination of time-stamped label provisioning across the network. This enhances the applicability of the system for positioning and location-based services, ensuring precise signal measurements for location determination in a wireless network.
[0060] A third aspect of the disclosure provides a method performed by an entity for a wireless communication system, wherein the method comprises: receiving a label from the network entity, wherein the label is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps; and associating the label with a measurement obtained at the entity.
[0061] Implementation forms of the method of the third aspect may correspond to the implementation forms of the entity of the first aspect described above. The method of the third aspect and its implementation forms achieve the same advantages and effects as described above for the entity of the first aspect and its implementation forms.
[0062] A fourth aspect of the disclosure provides a method performed by a network entity, wherein the method comprises providing a label to an entity, wherein the label is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps.
[0063] Implementation forms of the method of the fourth aspect may correspond to the implementation forms of the network entity of the second aspect described above. The method of the fourth aspect and its implementation forms achieve the same advantages and effects as described above for the network entity of the second aspect and its implementation forms.
[0064] A fifth aspect of the disclosure provides a computer program or computer program product comprising a program code for carrying out, when implemented on a processor, the method according to the third aspect and any implementation forms of the third aspect, or the fourth aspect and any implementation forms of the fourth aspect.
[0065] It has to be noted that all devices, elements, units and means described in the present application could be implemented in software or hardware elements or any kind of combination thereof. All steps that are performed by the various entities described in the present application as well as the functionalities described to be performed by the various entities are intended to mean that the respective entity is adapted to or configured to perform the respective steps and functionalities. Even if, in the following description of specific embodiments, a specific functionality or step to be performed by external entities is not reflected in the description of a specific detailed element of that entity that performs that specific step or functionality, it should be clear for a skilled person that these methods and functionalities can be implemented in respective software or hardware elements or any kind of combination thereof.BRIEF DESCRIPTION OF DRAWINGS
[0066] The above-described aspects and implementation forms of the present disclosure will be explained in the following description of specific embodiments in relation to the enclosed drawings, in which:
[0067] FIG. 1 shows an entity according to an embodiment of the disclosure;
[0068] FIG. 2 shows a network entity according to an embodiment of the disclosure;
[0069] FIG. 3 shows a result determination procedure according to an embodiment of the disclosure;
[0070] FIG. 4 shows signaling exchanges among entities according to an embodiment of the disclosure;
[0071] FIG. 5 shows signaling exchanges among entities according to an embodiment of the disclosure;
[0072] FIG. 6 shows signaling exchanges among entities according to an embodiment of the disclosure;
[0073] FIG. 7 shows signaling exchanges among entities according to an embodiment of the disclosure;
[0074] FIG. 8 shows a method according to an embodiment of the disclosure; and
[0075] FIG. 9 shows a method according to an embodiment of the disclosure.DETAILED DESCRIPTION OF EMBODIMENTS
[0076] The present disclosure describes an entity and a network entity in a wireless communication system, as well as various methods and embodiments related to determining and reporting timing information and channel parameters for positioning. The embodiments introduce improved mechanisms for efficient and accurate positioning of the UE, thereby supporting advanced use cases for location-based services in future wireless communication networks.
[0077] Illustrative embodiments of the entity, the network entity, and corresponding methods, are described with reference to the figures. Although this description provides a detailed example of possible implementations, it should be noted that the details are intended to be exemplary and in no way limit the scope of the application.
[0078] Moreover, an embodiment or example may refer to other embodiments or examples. For example, any description including but not limited to terminology, element, process, explanation, and / or technical advantage mentioned in one embodiment / example is applicable to the other embodiments or examples.
[0079] FIG. 1 shows an entity 100 in a wireless communication system according to an embodiment of this disclosure.
[0080] The entity 100 may comprise processing circuitry (not shown) configured to perform, conduct, or initiate the various operations of the entity 100 described herein. The processing circuitry may comprise hardware and software. The hardware may comprise analog circuitry digital circuitry, or both analog and digital circuitry. The digital circuitry may comprise components such as application-specific integrated circuits (ASICs) , field-programmable arrays (FPGAs) , digital signal processors (DSPs) , or multi-purpose processors. The entity 100 may further comprise memory circuitry, which stores one or more instruction (s) that can be executed by the processor or by the processing circuitry, in particular under the control of the software. For instance, the memory circuitry may comprise a non-transitory storage medium storing executable software code which, when executed by the processor or the processing circuitry, causes the various operations of the entity 100 to be performed. In one embodiment, the processing circuitry comprises one or more processors and a non-transitory memory connected to the one or more processors. The non-transitory memory may carry executable program code which, when executed by the one or more processors, causes entity 100 to perform, conduct or initiate the operations or methods described herein.
[0081] The entity 100 is configured to receive a label 101 from a network entity 200, wherein the label 101 is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps. Possibly, the label 101 may be received together with the time stamp.
[0082] The entity 100 is further configured to associate the label 101 with a measurement 102 obtained at the entity 100. The measurement 102 may be associated with a reference signal transmitted by one or more network nodes in the wireless communication system. The entity 100 may be considered as a measurement entity. Possibly, the proposed entity 100 may be implemented in a gNB, a TRP, a PRU, or a UE, which have the capability of receiving reference signals as part of their implementation of the relevant specification. For instance, the reference signal may include an SRS sent by a PRU or UE. In another instance, the reference signal may include a PRS sent by a gNB or TRP. Notably, this disclosure is applicable to various types of network devices, increasing its flexibility and utility in different wireless communication environments.
[0083] Possibly, the defined set of one or more time stamps comprises one or more time stamps within a timing offset of a time when the entity makes a measurement.
[0084] In one implementation, the entity 100 is further configured to associate the label 101 with the measurement 102 based on a comparison of the time stamp associated with the label 101 and a time stamp associated with the measurement 102. Notably, the time stamp associated with the measurement 102 may refer to the time when the measurement 102 is made. The association of the label 101 with the measurement 102 may include pairing the measurement 102 with the label 101, based on a comparison of the measurement time stamp and the label time stamp.
[0085] In some implementations, after the association or the pairing is completed, the entity 100 is further configured to train a model using the paired measurement and label. This model may be, for instance, a machine-learning algorithm or another form of statistical estimator that predicts one or more parameters such as: UE location, LOS condition, or timing information related to the direct path between a UE and a TRP (e.g., RSTD or TOF) .
[0086] Because both the measurement and the label are aligned in time, i.e., the time stamp of the measurement is close to the time stamp of the label, the entity 100 can avoid errors arising from mismatched or outdated label-measurement associations. By improving the accuracy of data-label pairing, this disclosure enhances machine learning model training in wireless networks, particularly for location inference, LOS detection, and timing parameter estimation.
[0087] Possibly, the defined set of time stamps may consist of one or more discrete time stamps or a range of values, allowing for flexibility in how time stamps are selected. The range of values may be a continuous or semi-continuous range of time values between a minimum and maximum time value.
[0088] The label 101 may contains UE location, LOS indicator, or a timing parameter of the direct path between a UE and a TRP. This enhances the value of the labels by including key parameters necessary for network optimization and location estimation. For instance, using precise timing parameters such as TOF or RSTD helps in refining time-based positioning calculations.
[0089] The disclosure introduces two methods for determining this set of time stamps:
[0090] 1. Label Request with Desired Time Stamp:
[0091] The entity 100, i.e., the measurement entity, determines when a label is needed and communicates the required set of time stamps to the network entity 200 such as the LMF.
[0092] 2. Anticipated Label Provision with Given Time Stamp:
[0093] The network entity 200 determines when a label can be generated and communicates the set of time stamps to the measurement entity, enabling it to align measurements accordingly.
[0094] Furthermore, the defined set of time stamps can be linked to reference signals or a TRP identifier, ensuring correct association between measurements and labels. This enhances accuracy in positioning, LOS detection, and timing-based measurements such as RSTD or TOF. The disclosure allows different entities (e.g., gNB, UE, or a PRU) to perform pairing at various stages, and it supports joint execution of the two proposed methods.
[0095] Accordingly, FIG. 2 shows a network entity 200 according to an embodiment of the disclosure. The network entity 200 may comprise processing circuitry (not shown) configured to perform, conduct, or initiate the various operations of the network entity 200 described herein. The processing circuitry may comprise hardware and software. The hardware may comprise analog circuitry digital circuitry, or both analog and digital circuitry. The digital circuitry may comprise components such as ASICs, FPGAs, DSPs, or multi-purpose processors. The network entity 200 may further comprise memory circuitry, which stores one or more instruction (s) that can be executed by the processor or by the processing circuitry, in particular under the control of the software. For instance, the memory circuitry may comprise a non-transitory storage medium storing executable software code which, when executed by the processor or the processing circuitry, causes the various operations of the network entity 200 to be performed. In one embodiment, the processing circuitry comprises one or more processors and a non-transitory memory connected to the one or more processors. The non-transitory memory may carry executable program code which, when executed by the one or more processors, causes the network entity 200 to perform, conduct or initiate the operations or methods described herein.
[0096] The network entity 200 illustrated in FIG. 2 may be adapted to coordinate label provision and / or measurement requests in the wireless communication system. Examples of such a network entity include an LMF, a core-network-based positioning server, or any operations / maintenance server capable of supplying ground-truth-like labels.
[0097] The network entity 200 is configured to provide a label 101 to an entity 100, wherein the label is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps. Possibly, the entity 100 may be the entity 100 shown in FIG. 1.
[0098] This architecture ensures that both sides (the measurement entity and the label-providing network entity) operate with a consistent set of aligned time stamps, reducing the risk of temporal mismatch.
[0099] The following embodiments describe detailed scenarios where the entity 100 as shown in FIG. 1 interacts with a network entity 200 as shown in FIG. 2 for ensuring accurate alignment between measurements and labels for positioning purposes.
[0100] FIG. 3 illustrates an embodiment in which the network entity 200 (e.g., an LMF) announces to the entity 100 (e.g., a UE) that a label 101 will be provided at a specified time stamp (or with a time stamp out of a range or set of time stamps) . The time stamp corresponds to a time when the network entity 200 can generate or obtain an accurate label (for instance, a UE position or LOS indicator) .
[0101] The LMF signals the UE, i.e., sends an announcement or indication 103 indicating e.g., that a label 101 will be provided with a time stamp T_label or with a time stamp within a range of time stamps. The UE performs measurements of a PRS transmitted by a gNB or TRP at times near T_label or within the range of time stamps. The LMF creates the label 101 that is valid at T_label (e.g., actual UE location) . The LMF sends the label to the UE, with the time stamp T_label. The UE pairs the measurement and label by matching T_label or with a time stamp of a measurement close to T_label or within the indicated range of time stamps.
[0102] This approach prevents outdated label-measurement pairing and can be used to train a model on the UE side, which infers the UE location or channel parameters like timing information of the direct path or LOS / NLOS information.
[0103] FIG. 4 shows signaling exchanges between entities according to an embodiment of this disclosure. In this embodiment, the network entity 200, e.g., the LMF, announces label provision to a gNB (entity 100) rather than a UE.
[0104] In this scenario, the gNB (as the measurement entity 100) receives from the LMF a message, i.e., an announcement or indication 103 indicating e.g., a label 101 will be provided with a time stamp T_label or with a time stamp within a range of time stamps. The given time stamp may correspond to the time when the LMF can generate a label, which can be close in time with when the gNB will make a measurement at a TRP belonging to the gNB.
[0105] Optionally, the LMF can also indicate that the label 101 is associated with a certain SRS or measurement identifier, e.g., it may indicate that a label 101 will be provided with a time stamp T_label for TRP X. This enables the gNB to know with which TRP and measurements to associate the label, when the label is provided. The gNB makes measurements of an SRS sent by a UE (or PRU) , storing measurements with time stamp close to T_label or with a time stamp within the range of time stamps. The network entity 200 provides the label (for example, a timing information or LOS indicator between the UE and TRP X) .
[0106] The gNB aligns the measurement time stamp with T_label and pairs the measurement with the label, i.e., based on a time stamp of a measurement close to T_label or within the indicated range of time stamps. The gNB may use these pairings to train or refine a model used for timing determination or LOS classification.
[0107] Another embodiment of this disclosure may include sending the announcement of a label provision with a given time stamp in the request of location information sent from the LMF to a UE. This request of location information may trigger the UE to make measurements. The announcement of a label provision with a given time stamp can be sent in the information element RequestLocationInformation or in information elements carried within RequestLocationInformation, e.g., in CommonIEsRequestLocationInformation or nr-DL-TDOA-RequestLocationInformation.
[0108] The indication can include the type of label that will be provided, a set of one or more time stamps for which a label may be provided, or an identifier of the PRS, TRP and / or measurement which is associated with the label. The set of one or more time stamps can consist of a set of timing values or one or more ranges of time stamps between a minimum and a maximum timing value.
[0109] Yet another embodiment of this disclosure proposes sending the announcement of a label provision with given time stamp in the request of measurements sent from the LMF to a gNB. This can be sent in the information element Measurement Request as shown in Table 1 below. Table 1
[0110] Table 1 shows a new information element, i.e., Label Delivery Announcement. The announcement of a label provision with given time stamp can be sent for one TRP within the corresponding TRP Measurement Request Item, allowing the indication to associate the label with the corresponding TRP. The indication can include the type of label that will be provided, a set of one or more time stamps for which a label may be provided, or an identifier of the SRS or measurement which is associated with the label. The set of one or more time stamps can consist of a set of timing values or one or more ranges of time stamps between a minimum and a maximum timing value. The indication of a label provision with given time stamp can also be sent within TRP Measurement Quantities Item carried in the Measurement Request IE, allowing the gNB to associate the label with the corresponding SRS configuration as well as with the type of label that will be provided, i.e., based on the requested TRP Measurement Type.
[0111] FIG. 5 shows signaling exchanges between entities according to an embodiment of this disclosure. In the embodiment, the entity 100, e.g., the UE, specifically requests a label for a “desired time stamp” for instance T_desired.
[0112] This might occur if the UE knows it will be making a measurement (e.g., a PRS measurement) at time T_desired and wishes to receive a label aligned with that measurement.
[0113] The UE informs the network entity 200 in a request 104 about the request for a label 101 with time stamp T_desired. The network entity 200, i.e., the LMF, may acknowledge or propose an alternative time (if T_desired is not feasible) . The UE proceeds with its measurement, e.g., at T_desired, saving the measurement data. If the LMF can provide the label, it sends the label with the time stamp T_desired (or references T_desired in the label) . The LMF can also provide the label generated with another time stamp close to T_desired, i.e., in case the LMF may not be able to generate the label at time T_desired. The UE pairs the measurement with the label and optionally trains a model (e.g., for location estimation) .
[0114] Possibly, if the LMF has confirmed that it can provide the requested label 101 with the desired time stamp, the LMF may not need to send the time stamp when sending the label 101. The UE can make the pairing of the measurements and the provided label based on the aligned time stamp.
[0115] It should be noted that an aligned time stamp may not necessarily mean a time stamp equal exactly to another value, but rather that the time stamp may be close in time to another value.
[0116] In a variant of this embodiment, after the LMF receives the request of the label with a desired time stamp, the LMF can indicate that it cannot provide a label with a requested time stamp but instead that it can provide a label with another given time stamp, e.g., a nearby time stamp to the requested one.
[0117] In another variant of this embodiment, the UE may request a label with a time stamp out of a range of time stamps, allowing the LMF to have flexibility in the generation of the label within that range of time stamps.
[0118] FIG. 6 shows an embodiment similar to the embodiment shown in FIG. 5, except that a gNB (entity 100) requests a label for a desired time stamp T_desired. For example, the gNB might have knowledge of when a UE’s SRS is scheduled, so it can proactively ask the LMF for a label specifically matching that measurement time. The procedure is analogous to FIG. 5.
[0119] The gNB requests the LMF to provide a label with a time stamp T_desired, potentially indicating a certain TRP or measurement ID. The LMF can optionally confirm T_desired or offers a nearby time stamp, i.e., in case it cannot generate a label at time T_desired. The gNB measures SRS from the UE at T_desired. The LMF provides a label referencing T_desired. The gNB pairs and trains a model (e.g., to determine LOS / NLOS information or estimate time of flight) .
[0120] Optionally, the request 104 for a label with a desired time stamp may be carried in the request of assistance data sent to the LMF for UE-based positioning. This can be sent in the information element nr-PosCalcAssistanceRequest or NR-DL-TDOA-RequestAssistanceData. The request can include the type of label that is required, a set of one or more time stamps for which a label may be needed, or an identifier of the PRS, TRP and / or measurement which is associated with the label.
[0121] In a variant of this embodiment, the gNB may request a label with a time stamp out of a range of time stamps, allowing the LMF to have flexibility in the generation of the label within that range of time stamps.
[0122] FIG. 7 shows another embodiment covering a scenario in which multiple time stamps are requested by the measurement entity 100, and the network entity 200 partially refines or confirms them:
[0123] The entity 100 may indicate a set of desired time stamps {T1, T2, T3, …} to the network entity 200, e.g., in a request 104 for one or more labels associated with the set of desired time stamps. The network entity 200 may accept all or only a subset {T1, T3, …} , responding with a refined set of “aligned time stamps” it can support, in an indication 103, e.g., an announcement of label provision of one or more labels with one or more given / refined time stamps.
[0124] The entity 100 acquires measurements at or near the accepted time stamps. The network entity 200 provides corresponding labels (each with a time stamp that is within a predefined threshold of an accepted time) . The entity 100 associates each measurement with the correct label and can use these pairs to train a model or enhance a location / timing algorithm.
[0125] Across all these embodiments, the key aspect is ensuring that measurement time stamps and label time stamps are aligned (or at least within a small threshold) , thereby improving pairing accuracy and avoiding mismatched training data.
[0126] This approach is flexible in the direction of control: for instance, either the network entity 200 announces time stamps, or the measuring entity 100 requests them, or both refine them iteratively. This approach is also flexible in the label content: the label may include a variety of positioning or radio-propagation information, such as the UE’s actual coordinates, a LOS / NLOS indicator, or timing parameters of the direct path between a UE and a TRP.
[0127] Because each measurement now has a correctly matched label, the training phase of any predictive or analytical model yields more accurate parameters. This can drastically improve location tracking, channel state predictions, or link quality estimation.
[0128] FIG. 8 shows a method 800 according to an embodiment of the disclosure. In a particular embodiment, the method 800 is performed by an entity 100 shown in one of FIG. 1 to FIG. 7. The method 800 comprises a step 801 of receiving a label 101 from a network entity 200, wherein the label 101 is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps. Possibly, the network entity 200 may be the network entity 200 shown in one of FIG. 1 to FIG. 7. The method 900 further comprises a step 902 of associating the label 101 with a measurement 102 obtained at the entity 100.
[0129] FIG. 9 shows a method 900 according to an embodiment of the disclosure. In a particular embodiment, the method 900 is performed by a network entity 200 shown in one of FIG. 1 to FIG. 7. The method 900 comprises a step 901 of providing a label 101 to an entity 100, wherein the label is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps. Possibly, the entity 100 may be the entity 100 shown in one of FIG. 1 to FIG. 7.
[0130] To summarize, by ensuring accurate alignment between measurements and labels, embodiments of this disclosure significantly improve the accuracy of machine learning models used in wireless communication systems. It reduces errors due to outdated or mismatched data, enhances positioning accuracy, and optimizes network performance. The flexibility in determining time stamp sets allows it to adapt to different network conditions and measurement scenarios, making it a highly practical solution for next-generation wireless networks.
[0131] The described methods and systems are applicable to various network nodes, including gNBs, TRPs, PRUs, and UEs, thereby providing a unified and adaptable approach to positioning in 5G and beyond wireless communication networks. The proposed system supports both uplink (SRS) and downlink (PRS) positioning and can be flexibly implemented in multiple deployment scenarios.
[0132] The present disclosure has been described in conjunction with various embodiments as examples as well as implementations. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed embodiments of the disclosure, from the studies of the drawings, this disclosure, and the independent claims. In the claims as well as in the description the word “comprising” does not exclude other elements or steps and the indefinite article “a” or “an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutually different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation.
[0133] Furthermore, any method according to embodiments of the disclosure may be implemented in a computer program, having code means, which when run by processing means causes the processing means to execute the steps of the method. The computer program is included in a computer-readable medium of a computer program product. The computer-readable medium may comprise essentially any memory, such as a ROM (Read-Only Memory) , a PROM (Programmable Read-Only Memory) , an EPROM (Erasable PROM) , a Flash memory, an EEPROM (Electrically Erasable PROM) , or a hard disk drive.
[0134] Moreover, it is realized by the skilled person that embodiments of the entity 100 or the network entity 200, comprise the necessary communication capabilities in the form of e.g., functions, means, units, elements, etc., for performing the solution. Examples of other such means, units, elements, and functions are processors, memory, buffers, control logic, encoders, decoders, rate matchers, de-rate matchers, mapping units, multipliers, decision units, selecting units, switches, interleavers, de-interleavers, modulators, demodulators, inputs, outputs, antennas, amplifiers, receiver units, transmitter units, DSPs, trellis-coded modulation (TCM) encoder, TCM decoder, power supply units, power feeders, communication interfaces, communication protocols, etc. which are suitably arranged together for performing the solution.
[0135] Especially, the processor (s) of the entity 100 or the network entity 200 may comprise, e.g., one or more instances of a CPU, a processing unit, a processing circuit, a processor, an ASIC, a microprocessor, or other processing logic that may interpret and execute instructions. The expression “processor” may thus represent a processing circuitry comprising a plurality of processing circuits, such as, e.g., any, some, or all of the ones mentioned above. The processing circuitry may further perform data processing functions for inputting, outputting, and processing of data comprising data buffering and device control functions, such as call processing control, user interface control, or the like.
Claims
1.An entity (100) for a wireless communication system, the entity (100) being configured to:receive a label (101) from a network entity (200) , wherein the label (101) is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps; andassociate the label (101) with a measurement (102) obtained at the entity (100) .2.The entity (100) according to claim 1, configured to:associate the label (101) with the measurement (102) based on a comparison of the time stamp associated with the label (101) and a time stamp associated with the measurement (102) .3.The entity (100) according to claim 1 or 2, wherein the defined set of one or more time stamps comprises one or more time stamps within a timing offset of a time when the entity makes a measurement.4.The entity (100) according to any of the preceding claims, configured to:receive the defined set of one or more time stamps.5.The entity (100) according to any of the preceding claims, wherein the defined set of one or more time stamps is determined by the network entity (200) .6.The entity (100) according to claim 5, wherein the defined set of one or more time stamps is determined by the network entity (200) based on a set of one or more time stamps indicated by the entity (100) .7.The entity (100) according to any of the preceding claims, configured to:receive an indication (103) of the provision of a label (101) associated with a time stamp out of the defined set of one or more time stamps.8.The entity (100) according to any of the preceding claims, configured to:determine the defined set of one or more time stamps; andrequest the network entity (200) to provide a label (101) associated with a time stamp from the defined set of one or more time stamps.9.The entity (100) according to any of the preceding claims, configured to:receive a measurement request from the network entity (200) , wherein the measurement request is indicative of the defined set of one or more time stamps.10.The entity (100) according to any of the preceding claims, wherein the one or more time stamps in the defined set are associated with a transmit receive point, TRP, identifier and / or a reference signal, and the entity (100) is configured toobtain a measurement associated with the reference signal, and / or associated with a TRP corresponding to the TRP identifier.11.The entity (100) according to any of the preceding claims, wherein the label (101) comprises at least one of the following:location information of a user equipment, UE,a line-of-sight, LOS, indicator,a timing parameter indicative of a direct path between a UE and a TRP, said timing parameter comprising at least one of a reference signal time difference, a relative time of arrival, a propagation delay, or a time of flight.12.The entity (100) according to any of the preceding claims, wherein the defined set of one or more time stamps comprises a plurality of discrete time stamps, or a continuous or semi-continuous range of time values between a minimum and maximum time value.13.The entity (100) according to any of the preceding claims, configured to:train a model based on a measurement and a label that are paired using one or more time stamps of the defined set of one or more time stamps,wherein the model is configured to infer at least one of: a location of a UE, a LOS indicator, or a timing parameter associated with a direct path between the UE and a TRP.14.The entity (100) according to any of the preceding claims, wherein the entity (100) is one of the following: a base station, a TRP, a gNB, a position reference unit, or a user equipment.15.A network entity (200) in a wireless communication system, the network entity (200) being configured to:provide a label (101) to an entity (100) , wherein the label (101) is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps.16.The network entity (200) according to claim 15, wherein the defined set of one or more time stamps is determined by the network entity (200) .17.The network entity (200) according to claim 15 or 16, configured to:send to the entity (100) an indication (103) of the provision of a label with a time stamp from the defined set of one or more time stamps.18.The network entity (200) according to any of claims 15 to 17, configured to:receive a request (104) to provide a label associated with a time stamp from the defined set of one or more time stamps.19.The network entity (200) according to any of claims 15 to 18, configured to:send a measurement request to the entity (100) , wherein the measurement request is indicative of the defined set of one or more time stamps.20.The network entity (200) according to claim 19, wherein the defined set of one or more time stamps is determined by the network entity (200) based on a set of one or more time stamps indicated by the entity.21.The network entity (200) according to any of claims 15 to 20, wherein the one or more time stamps in the defined set are associated with a transmit receive point, TRP, identifier and / or a reference signal.22.The network entity (200) according to any of claims 15 to 21, wherein the label (101) comprises at least one of the following:location information of a user equipment, UE,a line-of-sight, LOS, indicator,a timing parameter indicative of a direct path between a UE and a TRP, said timing parameter comprising at least one of a reference signal time difference, a relative time of arrival, a propagation delay, or a time of flight.23.The network entity (200) according to any of claims 15 to 22, wherein the defined set of one or more defined time stamps comprises a plurality of discrete time stamps, or a continuous or semi-continuous range of time values between a minimum and maximum time value.24.The network entity (200) according to any of claims 15 to 23, wherein the network entity (200) is a location management function.25.A method (800) performed by an entity (100) for a wireless communication system, the method (800) comprising:receiving (801) a label (101) from the network entity (200) , wherein the label (101) is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps; andassociating (802) the label (101) with a measurement (102) obtained at the entity (100) .26.A method (900) performed by a network entity (200) , the method (900) comprising:providing (901) a label (101) to an entity (100) , wherein the label (101) is associated with a time stamp, wherein the time stamp is from a defined set of one or more time stamps.27.A computer program product comprising computer readable code instructions which, when run in a computer will cause the computer to perform the method (800, 900) according to claim 25 or 26.