Training sample evaluation in localization

Abstract

Example embodiments of the present disclosure relate to positioning enhancements. A first device receives, from a second device, first information indicating a target accuracy for positioning and a set of parameters for label quality assessment of training samples. The training sample includes radio measurements, and tag information associated with the radio measurements. And the first device determines a quality parameter of the training sample based on the parameter set and the label information. The first device then sends a report to the second device, the report including at least the quality parameter. In this manner, a model for positioning can be well trained with the evaluated training samples, and thus positioning accuracy is improved.

Description

Technical Field

[0001] Various exemplary embodiments of the present disclosure generally relate to the field of telecommunications, and particularly to methods, devices, apparatuses, and computer-readable storage media for training sample evaluation in positioning. Background Art

[0002] In the telecommunications industry, artificial intelligence / machine learning (AI / ML) models have been adopted in telecommunications systems to improve the performance of telecommunications systems. For example, AI / ML models have been adopted for the positioning of devices in communication networks. A large dataset of training samples will be used to train the AI / ML model to improve positioning accuracy. Therefore, it is worth studying the evaluation of training samples for machine learning training in positioning. Summary of the Invention

[0003] In a first aspect of the present disclosure, a first device is provided. The first device includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first device to at least perform: receiving first information from a second device, the first information indicating a target accuracy for positioning and a set of parameters for label quality evaluation of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; determining a quality parameter of the training samples based on the set of parameters, the label information, and the target accuracy; and sending a report to the second device, the report including at least the quality parameter.

[0004] In a second aspect of the present disclosure, a second device is provided. The second device includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second device to at least perform: sending first information to a first device, the first information indicating a target accuracy for positioning and a set of parameters for label quality evaluation of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; and receiving a report from the first device, the report including at least the quality parameter, the quality parameter being determined based on the set of parameters, the label information, and the target accuracy.

[0005] In a third aspect of the present disclosure, a method is provided. The method includes: receiving, at a first device, first information from a second device, the first information indicating a target accuracy for positioning and a set of parameters for label quality evaluation of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; determining a quality parameter of the training samples based on the set of parameters, the label information, and the target accuracy; and sending a report to the second device, the report including at least the quality parameter.

[0006] In a fourth aspect of the present disclosure, a method is provided. The method includes: sending, at a second device, first information to a first device, the first information indicating a target accuracy for positioning and a set of parameters for label quality assessment of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; and receiving, from the first device, a report that includes at least a quality parameter, the quality parameter being determined based on the set of parameters, the label information, and the target accuracy.

[0007] In a fifth aspect of the present disclosure, a first device is provided. The first device includes: means for receiving first information from a second device, the first information indicating a target accuracy for positioning and a set of parameters for label quality assessment of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; means for determining a quality parameter of the training samples based on the set of parameters, the label information, and the target accuracy; and means for sending a report to the second device, the report including at least the quality parameter.

[0008] In a sixth aspect of the present disclosure, a second device is provided. The second device includes: means for sending first information to a first device, the first information indicating a target accuracy for positioning and a set of parameters for label quality assessment of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; and means for receiving a report from the first device, the report including at least a quality parameter, the quality parameter being determined based on the set of parameters, the label information, and the target accuracy.

[0009] In a seventh aspect of the present disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to at least execute the method according to the third aspect.

[0010] In an eighth aspect of the present disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to at least execute the method according to the fourth aspect.

[0011] It should be understood that the Summary section is not intended to identify key features or essential features of the embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become readily appreciated through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0013] Figure 1 illustrates an example communication environment in which example embodiments of the present disclosure may be implemented;

[0014] Figure 2 Illustrates a signaling diagram for communication according to some example embodiments of the present disclosure;

[0015] Figures 3A to 3C Illustrates an example location distribution of a noise sample source according to some example embodiments of the present disclosure;

[0016] Figure 4 Illustrates a flowchart of a method implemented at a first device according to some example embodiments of the present disclosure;

[0017] Figure 5 Illustrates a flowchart of a method implemented at a second device according to some example embodiments of the present disclosure;

[0018] Figure 6 Illustrates a simplified block diagram of a device suitable for implementing example embodiments of the present disclosure; and

[0019] Figure 7 Illustrates a block diagram of an example computer-readable medium according to some example embodiments of the present disclosure.

[0020] Throughout the drawings, the same or similar reference numerals denote the same or similar elements. Detailed Description

[0021] The principles of the present disclosure will now be described with reference to some example embodiments. It should be understood that these embodiments are described for illustrative purposes only and help those skilled in the art understand and implement the present disclosure without imposing any limitation on the scope of the present disclosure. The present disclosure described herein can be implemented in various ways other than those described below.

[0022] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0023] References in the present disclosure to "one embodiment", "an embodiment", "example embodiment", etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but each embodiment does not necessarily include that particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an example embodiment, whether explicitly described or not, it is contemplated within the knowledge of those skilled in the art to combine such feature, structure or characteristic with other embodiments.

[0024] It should be understood that although terms such as "first" and "second" may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish the functionality of various elements. As used herein, the term "and / or" includes any combination and all combinations of one or more of the listed items.

[0025] The terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the example embodiments. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that when used herein, the terms "comprises", "comprising", "has", "having", "includes" and / or "including" specify the presence of the stated features, elements, and / or components, etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0026] As used herein, "at least one of the following: <list of two or more elements>" and "at least one of <list of two or more elements>" and similar phrases (where the list of two or more elements is joined by "and" or "or") mean at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0027] As used herein, unless explicitly stated, performing a step "in response to A" does not indicate that the step is performed immediately after A occurs, and one or more intermediate steps may be included.

[0028] The terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the example embodiments. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that when used herein, the terms "comprises", "comprising", "has", "having", "includes" and / or "including" specify the presence of the stated features, elements, and / or components, etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0029] As used in this application, the term "circuitry" may refer to one or more or all of the following:

[0030] (a) Implementations solely in hardware circuitry (such as implementations solely in analog circuitry and / or digital circuitry); and

[0031] (b) Combinations of hardware circuitry and software, such as (if applicable):

[0032] (i) Combinations of (one or more) analog hardware circuitry and / or digital hardware circuitry with software / firmware, and

[0033] (ii) (One or more) hardware processors (including (one or more) digital signal processors) with software, and any part of (one or more) memories, which work together to enable a device such as a mobile phone or a server to perform various functions) and

[0034] (c) (One or more) hardware circuitry and / or (one or more) processors that require software (e.g., firmware) for operation, such as (one or more) microprocessors or a part of (one or more) microprocessors, but the software may not be present when not required for operation.

[0035] This definition of circuitry applies to all uses of the term in this application, including in any claims. As another example, as used in this application, the term circuitry also covers implementations of only hardware circuitry or a processor (or processors) or a part of hardware circuitry or a processor and its (or their) accompanying software and / or firmware. For example and if applicable to a particular claim element, the term circuitry also covers baseband integrated circuits or processor integrated circuits for mobile devices or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0036] As used herein, the term "communication network" refers to a network that follows any suitable communication standard, such as a fifth-generation (5G) system, Long-Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), NarrowBand Internet of Things (NB-IoT), etc. In addition, the communication between a terminal device and a network device in a communication network can be performed according to any suitable generation of communication protocols, which include but are not limited to first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G) New Radio (NR) communication protocols, and / or any other protocols known currently or to be developed in the future. Embodiments of the present disclosure can be applied in various communication systems. Considering the rapid development in communications, there will of course also be future types of communication technologies and systems that can be utilized to embody the present disclosure. The scope of the present disclosure should not be regarded as limited to the above systems.

[0037] As used herein, the term "network device" refers to a node in a communication network through which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), e.g., Node B (NodeB or NB), evolved Node B (eNodeB or eNB), next-generation Node B (NR NB), remote radio unit (RRU), radio header (RH), remote radio head (RRH), integrated access and backhaul (IAB) node, relay, low-power node (such as femto, pico), etc., depending on the terminology and technology applied. It is allowed to define the network device as part of a gNB, such as, for example, in the CU / DU split, in which case the network device is defined as gNB-CU or gNB-DU.

[0038] The term "terminal device" refers to any end device that may be capable of wireless communication. By way of example and not limitation, the terminal device may also be referred to as a communication device, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). The terminal device may include, but is not limited to, mobile phones, cellular phones, smart phones, IP voice (VoIP) phones, wireless local loop phones, tablet computers, wearable terminal devices, personal digital assistants (PDA), portable computers, desktop computers, image capture terminal devices (such as digital cameras), game terminal devices, music storage and playback devices, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded equipment (LEE), laptop mounted equipment (LME), USB dongles, smart devices, wireless customer premise equipment (CPE), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMD), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of an industrial and / or automation processing chain), consumer electronic devices, devices operating on commercial wireless networks and / or industrial wireless networks, etc. The terminal device may also correspond to the mobile termination (MT) part of an integrated access and backhaul (IAB) node (also known as a relay node). In the following description, the terms "terminal device", "communication device", "terminal", "user equipment", and "UE" may be used interchangeably.

[0039] Although in various example embodiments, the functionality described herein may be performed in fixed and / or wireless network nodes, in other example embodiments, the functionality may be implemented in a user equipment device (such as a mobile phone or a tablet computer or a laptop computer or a desktop computer or a mobile IoT device or a fixed IoT device). In appropriate cases, the user equipment device may be equipped, for example, with the corresponding capabilities described in connection with (one or more) fixed and / or wireless network nodes. The user equipment device may be a user equipment and / or a control device, such as a chipset or a processor, which is configured to control the user equipment when installed in the user equipment. Examples of such functionality include a bootstrapping server function and / or a home subscriber server, which may be implemented in the user equipment device by providing software to the user equipment device, the software being configured to cause the user equipment device to perform from the perspective of these functions / nodes.

[0040] Example environment

[0041] Figure 1 FIG. 100 illustrates an example communication environment 100 in which example embodiments of the present disclosure may be implemented. The communication environment 100 includes devices 110-1, 110-2, 110-3, …, and 110-N, which may be collectively referred to as “(one or more) devices 110”. The communication environment also includes devices 120 and 130. The (one or more) devices 110, device 120, and device 130 may communicate with each other.

[0042] In Figure 1 an example, device 110 may include a terminal device, and device 130 may include a network device serving the terminal device. Device 120 may include a core network device. For example, device 120 may include a device on which a location management function (LMF) may be implemented.

[0043] In some example embodiments, a central ML unit (also referred to as a “central unit”) may be located within the communication environment 100. For example, the central ML unit may be part of the LMF implemented on device 120. The central ML unit trains an AI / ML model for positioning by using training samples. The central ML unit may be any suitable unit for data analysis, including but not limited to a 5G network data analytics function (NWDAF).

[0044] In some example embodiments, the central ML unit may collect training samples from a set of data collection devices deployed at certain locations. The data collection devices may include positioning reference units (PRUs) or any other suitable data collection devices. A PRU is a reference unit, such as a device or network node at a known location (i.e., having tag information). The PRU may take measurements to generate calibration data for refining the positions of other target devices in the area.

[0045] In some example embodiments, devices 110, 120, and / or 130 may operate as data collection devices. For example, in addition to providing (their) own positions via a radio access network (RAN) or non-RAN, devices 110, 120, and / or 130 may also provide positioning measurements or estimates. The positioning information provided by devices 110, 120, and / or 130 is collected in the communication environment 100 and can thus be used to analyze the propagation properties of the communication environment 100.

[0046] The central ML unit may combine positioning measurements from different PRUs to train the positioning ML framework. The trained ML framework may be deployed on network entities that run ML processes and / or algorithms. Such entities may be referred to as host types. The host types that execute the ML processes may be target devices to be positioned, PRUs, and potentially radio access networks (e.g., network devices and / or LMFs) to enhance positioning accuracy.

[0047] It should be understood that Figure 1 the number of devices shown and the connections of the devices are for illustrative purposes only and do not impose any limitations. The communication environment 100 may include any suitable number of devices configured to implement the example embodiments of the present disclosure. Although not shown, it should be understood that one or more additional devices may be located in the cell of device 130, and one or more additional cells may be deployed in the communication environment 100. It should be noted that although illustrated as a network device, device 130 may be other devices than network devices. Although illustrated as a terminal device, device 110 may be other devices than terminal devices.

[0048] Hereinafter, for illustrative purposes, some example embodiments are described in which device 110 operates as a terminal device and device 130 operates as a network device. However, in some example embodiments, the operations described in connection with the terminal device may be implemented at a network device or other device, and the operations described in connection with the network device may be implemented at a terminal device or other device.

[0049] In some example embodiments, if device 110 is a terminal device and device 130 is a network device, the link from device 130 to device 110 is referred to as a downlink (DL), and the link from device 110 to device 130 is referred to as an uplink (UL). In the DL, device 130 is a transmitting (TX) device (or transmitter), and device 110 is a receiving (RX) device (or receiver). In the UL, device 110 is a TX device (or transmitter), and device 130 is an RX device (or receiver).

[0050] Communication in communication environment 100 can be implemented according to any suitable communication protocol(s), which include but are not limited to cellular communication protocols of the first generation (1G), second generation (2G), third generation (3G), fourth generation (4G), fifth generation (5G), sixth generation (6G), etc., wireless local area network communication protocols (such as those of the Institute of Electrical and Electronics Engineers (IEEE) 802.11, etc.), and / or any other protocol known currently or to be developed in the future. Moreover, the communication can utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplexing (FDD), Time Division Duplexing (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiplexing (OFDM), Discrete Fourier Transform Spread OFDM (DFT-s-OFDM), and / or any other technology known currently or to be developed in the future.

[0051] As mentioned above, AI / ML can be adopted in a communication system to improve positioning accuracy. The AI / ML model can be trained using a dataset of training samples. To better train the AI / ML model, a large dataset with accurate ground truth or labels is required. However, in many applications, it is difficult to obtain accurate labels (also known as gold labels) for the training samples. For example, a noisy label refers to an inaccurate value for a target parameter, rather than the true or actual value at the measurement time. Therefore, it is worth studying training the model using training samples with noisy labels.

[0052] In one scheme, multiple schemes for training an AI / ML model using noisy labels are proposed. For example, it is proposed to update the loss function using proximity consistency regularization. In another scheme, it is proposed to average multiple noisy labels to reduce the impact of noisy labels in model training.

[0053] With the large-scale deployment of communication infrastructure, devices in the communication environment can provide positioning measurements and their own location (which can be used as a tag for positioning measurements). A promising approach for training models in positioning is to use the measurements and locations (tags) provided by devices in the communication system as training samples. However, since the obtained locations as tags are inaccurate, these locations may be noisy tags. That is, these training samples contain noisy tags. The evaluation of training samples with noisy tags needs to be improved to enhance model training in positioning.

[0054] Principle of operation for communication and example signaling

[0055] As discussed above, evaluating training samples for training AI / ML models in positioning is challenging. According to some example embodiments of the present disclosure, a solution for evaluating training samples in positioning is provided. In this solution, a first device receives first information from a second device, the first information indicating a target accuracy for positioning and a set of parameters for evaluating the quality of tags for training samples. The training samples include: radio measurements and tag information associated with the radio measurements. The first device determines a quality parameter of the training sample based on the set of parameters, the tag information, and the target accuracy. The first device then sends a report to the second device, the report including at least the quality parameter.

[0056] In this way, the first device can evaluate the quality of tags of the training sample before sending the training sample to the second device. In addition, the first device can report the quality of the training sample to the second device, so that the AI / ML model training performed by the second device can be improved.

[0057] Example embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings.

[0058] Now refer to Figure 2 , Figure 2 FIG. 200 is a signaling diagram for communication according to some example embodiments of the present disclosure. As Figure 2 shown in, signaling diagram 200 involves a first device 201 and a second device 202. For the purpose of discussion, the signaling flow 200 is described with reference to Figure 1 .

[0059] In some example embodiments, the first device 201 may refer to or include Figure 1 the device 110 or the device 130 shown in. The second device 202 may refer to or include Figure 1The device 120 shown in . It should be understood that the first device 201 and the second device 202 may refer to or include any suitable devices, including but not limited to, a UE, a PRU, a transmit / receive point (TRP), a gNB, a next-generation (NG) radio access network (RAN) (NG-RAN) node, or a network element such as an LMF. The scope of the present disclosure is not limited in this regard.

[0060] Although Figure 2 illustrates a first device 201 and a second device 202, it should be understood that there may be multiple devices performing similar operations as described below with respect to the first device 201 or the second device 202.

[0061] In some example embodiments, the first device 201 includes a device 110, such as a terminal device. In such a case, the first device 201 may send information or a signal to the second device 202 via an LTE positioning protocol (LPP) information element (IE), such as an IE in LPPProvideLocationInformation. Alternatively or in addition, in some example embodiments, the first device 201 includes a device 130, such as a network device. In such a case, the first device 201 may send information or a signal to the second device 202 via an NR positioning protocol annex (NRPPa) IE, such as an IE in NRPPa MeasurementReport. It should be understood that the IEs described below are for illustrative purposes only and do not impose any limitations. The device may use any suitable IE or other information format to send information. The scope of the present disclosure is not limited in this regard.

[0062] In operation, the second device 202 sends (240) first information to the first device 201. The first information indicates a target accuracy (TA) for positioning and a set of parameters for label quality assessment of training samples. For example, the first information may be in an LPP IE. The label quality assessment of training samples represents a process of evaluating the quality of training samples or the quality of the labels of training samples. As used herein, the term "label quality assessment" may also be referred to as "training sample assessment".

[0063] In some example embodiments, the TA for positioning may be predetermined. For example, the TA may be determined based on network requirements.

[0064] In some example embodiments, the set of parameters may include: a set of coefficients needed to determine quality parameters. For example, the set of coefficients may include a set of exponential coefficients. Alternatively or in addition, the set of coefficients may include a set of attenuation rates. Examples of the parameters will be described below.

[0065] The training samples include: radio measurements and label information associated with the radio measurements. The radio measurements and the label information associated with the radio measurements can be obtained by the first device 201 and / or the second device 202. For example, the radio measurements can include positioning measurements, such as measurements of in-field NR signals collected by the first device 201 and / or the second device 202. The positioning measurements can include any combination of time, angle of arrival, channel impulse response (CIR), etc. The positioning measurements can be obtained after receiving a positioning signal. Examples of the positioning signal can include, but are not limited to, a downlink positioning reference signal (PRS), an uplink sounding reference signal (SRS), or a sidelink (SL) positioning reference signal (SL-PRS).

[0066] In some example embodiments, the first device 201 uses the positioning measurements to estimate its position. The estimation results are the position mean μ and the position variance Σ. If there are multiple positioning sources, the NR element calculates and stores the mean and variance for each labeling source.

[0067] In some example embodiments, the label information associated with the radio measurements can include any suitable label information, including but not limited to the position estimate of the first device 201 estimated at the time of measurement, a non-line-of-sight (NLOS) indication, time / angle, or power measurements, etc. The scope of the present disclosure is not limited in this regard.

[0068] In some example embodiments, the label information (such as the position estimate) can be obtained from at least one positioning source (also referred to as a labeling source), which includes but is not limited to a global navigation satellite system (GNSS), a radio access technology (RAT), LIDAR, Wi-Fi-based positioning, ML-based positioning, etc. The training samples with noisy labels having one or more positioning sources can be represented as pairs (positioning measurements, label 1, label 2, …, label M), where label M represents the 2D or 3D position estimate provided by the positioning source M.

[0069] In some example embodiments, if the training sample has one labeling source, the training sample evaluation depends on the variance of the position estimate with respect to TA. In such a case, the first device 201 can perform the label quality evaluation of the training sample based on TA and the mean and variance of the position estimate obtained for the positioning source associated with the radio measurements.

[0070] In some example embodiments, the training sample has more than one label source, and the first device 201 may perform label quality assessment of the training sample based on the TA and the mean and variance of the position estimate obtained for the positioning source associated with the radio measurement. Alternatively or in addition, in some example embodiments, to perform label quality assessment, the first device 201 determines (255) the label quality of the training sample. The determination of the label quality will be described below.

[0071] As discussed above, the second device sends (240) the first information to the first device 201. In some example embodiments, if the training sample evaluation is enabled, the second device 202 may send (240) the first information.

[0072] To enable the training sample evaluation, the second device 202 may send (215) the second information to the first device 201. The second information indicates: the required type of radio measurement and position estimate. The required type of radio measurement may need to be recorded. The format for reporting the estimated position or position estimate may include the mean and variance of the estimate.

[0073] The second information also indicates whether the training sample evaluation is enabled. For example, the second information may include the LPPProvideAssistanceData IE "Label Consistency Score (LCS) = 1 / 0". This IE is used to enable or disable the training sample evaluation at the first device 201. If the LCS is equal to 1, the training sample evaluation is enabled. As discussed above, in some example embodiments, if the training sample evaluation is enabled, the second device 202 sends (240) the first information to the first device 201. Otherwise, if the LCS is equal to 0, the training sample evaluation is disabled. If the training sample evaluation is disabled, the first device 201 sends the radio measurement and the label without cleaning or comparing with the TA.

[0074] In some example embodiments, the first device 201 receives (220) the second information. The first device 201 may determine (225) whether the first device 201 is capable of providing the required type of radio measurement based on the capability information of the first device 201. By way of example, if the required type of radio measurement includes GNSS measurements and LIDAR measurements (i.e., the second device 202 requests GNSS reports and LIDAR reports), the first device 201 may determine whether the GNSS source and the LIDAR source are available. If the GNSS positioning source and the LIDAR positioning source become available, the first device 201 is capable of providing GNSS measurements and LIDAR measurements.

[0075] If the first device 201 is capable of providing radio measurements of the required type, the first device 201 sends (230) third information to the second device 202. The third information indicates that the first device 201 is capable of providing radio measurements of the required type. For example, the third information may include an acknowledgement (ACK), such as an LPP ProvideLocationInformation IE.

[0076] In some example embodiments, the second device 202 receives (235) the third information. Based on receiving (235) the third information, the second device 202 sends (240) the first information. Additionally, in some example embodiments, based on receiving (235) the third information, the second device 202 may request that a network device serving the device 201 allocate resources for a subsequent positioning measurement report.

[0077] The first device 201 receives (245) the first information. Using the first information, the first device 201 determines (255) a quality parameter of a training sample based on a set of parameters, tag information, and target accuracy. For example, the quality parameter may include an LCS or any suitable quality parameter. If the (multiple) positioning measurements or (multiple) estimates have higher accuracy, the LCS value is higher. Otherwise, if the (multiple) measurements or (multiple) estimates have lower accuracy, the LCS value is lower. In some example embodiments, in the case where the estimated positions from various sources are consistent, the LCS value will increase proportionally to the number of positioning sources.

[0078] In some example embodiments, the LCS may be determined by using a suitable LCS metric. Consider that M tag sources are available for the k-dimensional position estimation of a measurement sample. and are the mean and variance of the estimate reported by the i-th source, respectively. The estimated position of the i-th source is Gaussian distributed as An example LCS metric is as follows:

[0079]

[0080] where S i represents the score of the i-th source based on two factors: a) its positioning accuracy compared to the TA, and b) the consistency of this position estimate with other tag sources.

[0081] In some example embodiments, S i can be defined as follows:

[0082]

[0083] where α i > 0 is the exponential decay rate for the i-th source. C ≥ 0 is a control to obtain Ai Range of ≥ 1 (σ i Bias coefficient of <c). Also, T A > 0 is the target accuracy for the positioning task. β i，j > 0, γ i，j ≥ 0, and D KL (P i ||P j ) ≥ 0 respectively represent the exponential decay rate, weighting coefficient, and Kullback-Leibler (KL) divergence of the two position distributions of sources i and j. For two Gaussian distributions and The KL divergence is as follows.

[0084]

[0085] As described above, the set of parameters included in the first information includes a set of coefficients. The set of coefficients may include, but is not limited to, the exponential decay rate α i , bias coefficient C, exponential decay rate β i，j , weighting coefficient γ i，j , or any other suitable parameters. It should be understood that the example parameters or coefficients are for illustrative purposes only and do not impose any limitations. Below will be described with respect to Figures 3A to 3C Examples of multiple distributions of samples from multiple positioning sources, and the corresponding LCS.

[0086] The first device 201 sends (265) a report to the second device 202, and the report includes at least quality parameters. For example, the first device 201 may send (265) the LCS to the second device 202.

[0087] In some example embodiments, the report sent (265) by the first device 201 may include additional information. For example, the report may further include radio measurements, the position estimate of the first device 201, and quality parameters.

[0088] In some example embodiments, the first device 201 may determine (260) to send (265) different reports to the second device 202. The determination (260) may be performed by comparing the quality parameter with a tag quality threshold. In some example embodiments, the tag quality threshold may be predefined.

[0089] Alternatively or in addition, in some example embodiments, the label quality threshold may be determined (210) by the second device 202. By way of example, the label quality threshold may include a threshold for the LCS. The threshold for the LCS is also referred to as TH_LCS. In some example embodiments, the second device 202 determines (210) the label quality threshold based on network requirements or other parameters related to model training. For example, the second device 202 may determine (210) the label quality threshold based on the TA and the size of the training data set for positioning. The label quality threshold may be sent by the second device 202 to the first device 201. For example, the label quality threshold may be indicated by the first information sent (240) by the second device 202. Alternatively, in some example embodiments, the second device 202 may send the label quality threshold separately from the first information.

[0090] In some example embodiments, if the first device 201 determines (260) that the quality parameter is less than the label quality threshold, the first device 201 sends (265) a report including the quality parameter to the second device 202. That is, the radio measurements and the position estimate may not be sent to the second device 202. In this way, the first device 201 can reject or discard training samples with a low LCS. Such evaluation or pre-evaluation of training samples helps to be more efficient in data collection and accept / reject samples based on label quality or label accuracy.

[0091] Alternatively or in addition, in some example embodiments, if the first device 201 determines (260) that the quality parameter is equal to or greater than the label quality threshold, the first device 201 sends (265) a report including the quality parameter, the position estimate of the first device 201, and the radio measurements to the second device 202. In this way, training samples with noisy labels from one or more sources are pre-evaluated before being sent to the second device 202. The second device 202 may receive (270) training samples with a higher LCS and collect the received (270) training samples as new training data for training the AI / ML model.

[0092] In some example embodiments, the first device 201 includes the device 110, such as a terminal device. In such a case, the first device 201 may send (265) the report via the IE in LPP ProvideLocationInformation. Alternatively or in addition, in some example embodiments, the first device 201 includes the device 130, such as a network device. In such a case, the first device 201 may send (265) the report via the IE called "LCS-info" in the NR Positioning Protocol Annex (NRPPa) MeasurementReport.

[0093] The second device 202 receives (270) the report from the first device 201.

[0094] In some example embodiments, the second device 202 determines whether another positioning source is available at the second device 202. If the second device 202 determines that another positioning source is available, the second device 202 determines (275) another tag quality parameter based on the position estimate from the first device 201 and another position estimate from another positioning source at the second device 202. By way of example, the second device 202 calculates the LCS by combining the (multiple) position estimates reported by the first device 201 with the (multiple) possible position estimates from other tag sources.

[0095] Additionally or alternatively, in some example embodiments, the second device 202 stores (280) the radio measurements and the position estimate together with another quality parameter. By way of example only, the second device 202 adds the radio measurements, the estimated (multiple) position mean and (multiple) position variance, and the calculated LCS to the training data set.

[0096] In some example embodiments, in the case where the second device 202 collects training samples with multiple noisy tags, the second device 202 may select one tag from the reported tags or combine the reported tags.

[0097] Three example LCSs are calculated to illustrate the evaluation process of training samples with multiple noisy tags for 2D positioning. In the following example with two noisy positioning sources (M = 2), the parameter set includes α i = 1, β i，j = 1, γ i，j = 3, …, M, j = 1, …, M. The target accuracy of the positioning is set to T A = 1. In these examples, the aim is to have the position accuracy within 99% confidence. Thus, since 99% of the 2D positions will lie within the range , the coefficient C = T A / 3. For the source, such a coefficient C results in A i ≥ 1, since tags within the acceptable accuracy range are provided 99% of the time.

[0098] The present disclosure provides a framework for evaluating and cleaning training samples having different numbers of tag sources, which may be collected from different devices. The framework includes data cleaning, tag combination, and cooperation and reporting between a first device and a second device. By evaluating the tag quality of training samples, the training samples can be cleaned based on the localization target accuracy and the accuracy of the position estimation. Such a scheme provides an efficient way to compare the usefulness of samples having different numbers of noisy tags and different estimation accuracies for training an AI / ML model. Additionally, by using the signaling diagram 200, the transmission overhead can be reduced by pre-evaluating the training samples at the first device and transmitting only the samples with sufficient accuracy to the second device.

[0099] Example embodiments according to the present disclosure explore the benefits of enhancing the air interface by leveraging features enabling AI / ML-based algorithms for enhanced performance and / or reduced complexity / overhead. For example, the solution can enhance CSI (e.g., reduced overhead, improved accuracy, prediction), beam management (e.g., beam prediction in time and / or spatial domains for reduced overhead and latency, improved beam selection accuracy), and enhanced positioning accuracy.

[0100] Figure 3A Illustrated are an example location distribution 310 and an example location distribution 320 of noise sources for samples from two sources. In Figure 3A the example, the two sources provide noisy tags having the following means and variances: Table 1 below shows the parameters calculated using the above (1) to (4). In this example, due to the overlap of the location distributions from the two noise sources, the calculated LCS is higher than A 1 (which is equal to 0.847).

[0101] Calculated LCS parameters in Table 1

[0102]

[0103] Figure 3B Illustrated are another example location distribution 330 and another example location distribution 340 of noise sources for samples from two sources. In this example, the mean of the second source is shifted closer to the mean of the first source, i.e., The calculated parameters for obtaining the LCS are listed in Table 2. Since the positions reported by different sources support each other more, the LCS increases to

[0104] Calculated LCS parameters in Table 2

[0105]

[0106] Figure 3C Illustrated is another example position distribution 350 of the noise source for samples from two sources and another example position distribution 360. In Figure 3C the example, the two sources provide noise labels with the following means and variances: Table 3 below shows the parameters calculated using the above (1) to (4). In this example, as shown in Table 3 and Figure 3C shown, as A 2 increases, and the KL divergence between the distributions decreases. Thus, the LCS achieves a higher score. That is, having two highly overlapping and confidence label sources by reducing the variance of the second source will result in a higher LCS.

[0107] LCS parameters calculated by Table 3

[0108]

[0109] By using the example embodiment, training samples from the example noise source can be evaluated before transmission to the second device 202. In this way, the training samples used in AI / ML model training can be cleaned. It will enhance the training of the AI / ML model and thus improve the positioning accuracy. In addition, such sample reports will also reduce the overhead.

[0110] Example method

[0111] Figure 4 Illustrated is a flowchart of a method 400 implemented at a first device according to some example embodiments of the present disclosure. For example, the first device may include a terminal device or a network device. For the purpose of discussion, method 400 will be described from Figure 2 the perspective of the first device 201 in

[0112] At block 410, the first device 201 receives first information from the second device 202, the first information indicating: a target accuracy for positioning, and a set of parameters for evaluating the label quality of training samples. The training samples include: radio measurements, and label information associated with the radio measurements.

[0113] In some example embodiments, the first device 201 may include a terminal device, and the second device 202 may include a core network device. Alternatively, in some example embodiments, the first device 201 may include a network device, and the second device 202 may include a core network device.

[0114] In some example embodiments, the parameter set includes: a set of coefficients needed to determine a quality parameter. For example, the set of coefficients may include at least one of the following: a set of exponential coefficients, or a set of decay rates.

[0115] In some example embodiments, radio measurements and label information associated with the radio measurements are obtained from at least one of the first device 201 or the second device 202.

[0116] At block 420, the first device 201 determines a quality parameter of a training sample based on the parameter set, the label information, and the target accuracy.

[0117] At block 430, the first device 201 sends a report to the second device 202, the report including at least the quality parameter.

[0118] In some example embodiments, the information further indicates a label quality threshold. The first device 201 may determine whether the quality parameter is less than the label quality threshold. Based on determining that the quality parameter is not less than the label quality threshold, at block 430, the first device 201 sends a report to the second device 202 including the quality parameter, a location estimate of the first device, and the radio measurements. Alternatively or in addition, in some example embodiments, based on determining that the quality parameter is less than the label quality threshold, at block 430, the first device 201 sends a report including the quality parameter to the second device 202.

[0119] In some example embodiments, the first device 201 may perform a label quality assessment of the training sample based on the target accuracy and the mean and variance of the location estimates obtained for the positioning source associated with the radio measurements.

[0120] In some example embodiments, the first device 201 may receive second information from the second device 202, the second information indicating: the required type of radio measurements and location estimates, and an indication of whether label quality assessment is enabled. The first device 201 may determine whether the first device 201 is capable of providing the required type of radio measurements based on the capability information of the first device. Based on determining that the first device 201 is capable of providing the required type of radio measurements, the first device 201 sends third information to the second device 202, the third information indicating that the first device 201 is capable of providing the required type of radio measurements.

[0121] Figure 5 A flowchart of a method 500 implemented at a second device according to some example embodiments of the present disclosure is illustrated. For example, the second device may include a core network device. For purposes of discussion, method 400 will be described from Figure 2 the perspective of the second device 202 in

[0122] At block 510, the second device 202 sends first information to the first device 201, the first information indicating: the target accuracy for positioning, and a set of parameters for evaluating the label quality of training samples. The training samples include: radio measurements, and label information associated with the radio measurements.

[0123] In some example embodiments, the first device 201 may include a terminal device, and the second device 202 may include a core network device. Alternatively, in some example embodiments, the first device 201 may include a network device, and the second device 202 may include a core network device.

[0124] In some example embodiments, the set of parameters may include: a set of coefficients needed to calculate a quality parameter. For example, the set of coefficients may include at least one of the following: a set of exponential coefficients, or a set of decay rates.

[0125] In some example embodiments, the radio measurements and the label information associated with the radio measurements are obtained from at least one of the first device 201 or the second device 202.

[0126] At block 520, the second device 202 receives a report from the first device 201, the report including at least a quality parameter, the quality parameter being determined based on the set of parameters, the label information, and the target accuracy.

[0127] In some example embodiments, the information further indicates a label quality threshold. If the quality parameter is not less than the label quality threshold, then at block 520, the second device 202 receives from the first device 201 a report including the quality parameter, a position estimate of the first device 201, and the radio measurements. Alternatively or in addition, in some example embodiments, if the quality parameter is less than the label quality threshold, then at block 520, the second device 202 receives from the first device 201 a report including the quality parameter.

[0128] In some example embodiments, the second device 202 may determine the label quality threshold based on the target accuracy and the size of the training data set for positioning.

[0129] In some example embodiments, the second device 202 may send second information to the first device 201, the second information indicating: the required type of radio measurements and position estimates, and an indication of whether label quality assessment is enabled. The second device 202 may receive third information from the first device 201, the third information indicating that the first device 201 is capable of providing the required type of radio measurements.

[0130] In some example embodiments, the second device 202 may determine whether another positioning source at the second device 202 is available. Based on determining that another positioning source at the second device 202 is available, the second device 202 determines another tag quality parameter based on the position estimate from the first device 201 and another position estimate from another positioning source at the second device 202.

[0131] In some example embodiments, the second device 202 may store radio measurements and position estimates together with another quality parameter.

[0132] Example apparatus, device, and medium

[0133] In some example embodiments, a first apparatus (e.g., Figure 2 the device 201 in) that can perform any of the methods 400 may include components for performing the corresponding operations of the method 400. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module. The first apparatus may be implemented as Figure 2 the first device 201 in, or be included in the first device 201.

[0134] In some example embodiments, the first apparatus includes components for receiving first information from a second apparatus, the first information indicating: a target accuracy for positioning and a set of parameters for label quality assessment of training samples. The training samples include: radio measurements and label information associated with the radio measurements. The first apparatus further includes components for determining a quality parameter of the training samples based on the set of parameters, the label information, and the target accuracy; and components for sending a report to the second apparatus, the report including at least the quality parameter.

[0135] In some example embodiments, the first apparatus may include a terminal device, and the second apparatus may include a core network device. Alternatively, in some example embodiments, the first apparatus may include a network device, and the second apparatus may include a core network device.

[0136] In some example embodiments, the radio measurements and the label information associated with the radio measurements are obtained from at least one of the first apparatus or the second apparatus.

[0137] In some example embodiments, the set of parameters includes: a set of coefficients needed to determine the quality parameter. For example, the set of coefficients includes at least one of the following: a set of exponential coefficients, or a set of attenuation rates.

[0138] In some example embodiments, the information further indicates a tag quality threshold. The components for sending a report include: a component for determining whether a quality parameter is less than the tag quality threshold; and a component for sending a report including the quality parameter, a location estimate of the first device, and radio measurements to a second device based on determining that the quality parameter is not less than the tag quality threshold.

[0139] In some example embodiments, the information further indicates a tag quality threshold. The components for sending a report include: a component for determining whether a quality parameter is less than the tag quality threshold; and a component for sending a report including the quality parameter to a second device based on determining that the quality parameter is less than the tag quality threshold.

[0140] In some example embodiments, the first device further includes: a component for performing a tag quality assessment of training samples based on a target accuracy, and a mean and variance of a location estimate obtained for a positioning source associated with radio measurements.

[0141] In some example embodiments, the first device further includes: a component for receiving second information from the second device, the second information indicating: radio measurements and location estimates of a required type, and an indication of whether tag quality assessment is enabled; a component for determining whether the first device is capable of providing radio measurements of the required type based on the capability information of the first device; and a component for sending third information to the second device based on determining that the first device is capable of providing radio measurements of the required type, the third information indicating that the first device is capable of providing radio measurements of the required type.

[0142] In some example embodiments, the first device further includes components for performing other operations in some example embodiments of method 400 or the first device 201. In some example embodiments, the component includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first device to perform.

[0143] In some example embodiments, a second device (e.g., Figure 2 the second device 202 therein) capable of performing any of method 500 may include components for performing corresponding operations of method 500. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit system or a software module. The second device may be implemented as Figure 2 the second device 202 therein, or included in the second device 202.

[0144] In some example embodiments, the second device includes components for sending first information to the first device, the first information indicating: the target accuracy for positioning, and a set of parameters for evaluating the label quality of training samples. The training samples include: radio measurements, and label information associated with the radio measurements. The second device further includes components for receiving a report from the first device that includes at least quality parameters, the quality parameters being determined based on the set of parameters, the label information, and the target accuracy.

[0145] In some example embodiments, the first device may include a terminal device, and the second device may include a core network device. Alternatively, in some example embodiments, the first device may include a network device, and the second device may include a core network device.

[0146] In some example embodiments, the set of parameters includes: a set of coefficients needed to calculate the quality parameters. For example, the set of coefficients includes at least one of the following: a set of exponential coefficients, or a set of attenuation rates.

[0147] In some example embodiments, the radio measurements and the label information associated with the radio measurements are obtained from at least one of the first device or the second device.

[0148] In some example embodiments, the information further indicates a label quality threshold. The component for receiving the report includes: a component for receiving from the first device a report that includes the quality parameters, the position estimate of the first device, and the radio measurements based on a determination that the quality parameters are not less than the label quality threshold. Alternatively or in addition, in some example embodiments, the component for receiving the report includes: a component for receiving from the first device a report that includes the quality parameters based on a determination that the quality parameters are less than the label quality threshold.

[0149] In some example embodiments, the second device further includes: a component for determining the label quality threshold based on the target accuracy and the size of the training data set for positioning.

[0150] In some example embodiments, the second device further includes: a component for sending second information to the first device, the second information indicating: the required types of radio measurements and position estimates, and an indication of whether label quality evaluation is enabled; and a component for receiving third information from the first device, the third information indicating that the first device is capable of providing the required types of radio measurements.

[0151] In some example embodiments, the second device further includes: components for determining whether another positioning source is available at the second device; and components for determining another tag quality parameter based on the determination that another positioning source is available at the second device, based on a position estimate from the first device and another position estimate from the other positioning source at the second device.

[0152] In some example embodiments, the second device further includes: components for storing radio measurements and position estimates together with another quality parameter.

[0153] In some example embodiments, the second device further includes components for performing method 500 or other operations in some example embodiments of the second device 202. In some example embodiments, the components include at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second device to execute.

[0154] Figure 6 is a simplified block diagram of a device 600 suitable for implementing example embodiments of the present disclosure. The device 600 may be provided to implement a communication device, e.g., Figure 2 the first device 201 or the second device 202 as shown in. As shown, the device 600 includes one or more processors 610, one or more memories 620 coupled to the processors 610, and one or more communication modules 640 coupled to the processors 610.

[0155] The communication module 640 is for two-way communication. The communication module 640 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface may represent any interface necessary for communicating with other network elements. In some example embodiments, the communication module 640 may include at least one antenna.

[0156] The processor 610 may be of any type suitable for a local technical network and may include one or more of the following: by way of non-limiting example, a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. The device 600 may have multiple processors, such as an application-specific integrated circuit chip that is subordinate in time to a clock synchronized with a main processor.

[0157] The memory 620 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to: read-only memory (ROM) 624, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), optical disc, laser disc, and other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to: random access memory (RAM) 622, and other volatile memories that will not persist during a power outage.

[0158] The computer program 630 includes computer-executable instructions executed by the associated processor 610. The instructions of the program 630 may include instructions for performing the operations / actions of some example embodiments of the present disclosure. The program 630 may be stored in a memory (e.g., ROM 624). The processor 610 may execute any suitable actions and processes by loading the program 630 into the RAM 622.

[0159] Example embodiments of the present disclosure may be implemented by means of the program 630 such that the device 600 may execute any process of the present disclosure discussed with reference to Figure 2 , Figure 4 and Figure 5 Example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0160] In some example embodiments, the program 630 may be tangibly embodied in a computer-readable medium, which may be included in the device 600 (such as in the memory 620) or in other storage devices accessible by the device 600. The device 600 may load the program 630 from the computer-readable medium into the RAM 622 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. The term "non-transitory" as used herein is a limitation on the medium itself (i.e., tangible, not a signal), rather than a limitation on the persistence of data storage (e.g., RAM vs. ROM).

[0161] Figure 7 An example of a computer-readable medium 700 that may be in the form of a CD, DVD, or other optical storage disc is shown. The computer-readable medium 700 has the program 630 stored thereon.

[0162] In general, the various embodiments of the present disclosure can be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. Although the various aspects of the embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or otherwise using some other graphical representation, it should be understood that the blocks, devices, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0163] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer-readable medium (such as a non-transitory computer-readable medium). The computer program product includes computer-executable instructions, such as those included in program modules, which are executed in a device on a target physical or virtual processor to perform any of the above methods. In general, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or split as needed among program modules. The machine-executable instructions for program modules can be executed within a local device or a distributed device. In a distributed device, program modules can be located in both local storage media and remote storage media.

[0164] The program code for performing the methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when the program code is executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, executed as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0165] In the context of the present disclosure, the computer program code or related data can be carried by any suitable carrier so that a device, apparatus, or processor can perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc.

[0166] A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium will include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0167] Further, although operations are depicted in a particular order, this should not be construed as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although many specific implementation details are included in the above discussion, these implementation details should not be construed as limiting the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment, unless explicitly stated otherwise. Conversely, various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments, unless explicitly stated otherwise.

[0168] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the above specific features and acts are disclosed as example forms of implementing the claims.

[0169] List of abbreviations

[0170] LMF Location Management Function

[0171] PRS Positioning Reference Signal

[0172] SRS Sounding Reference Signal

[0173] PRU Positioning Reference Unit

[0174] TRP Transmission and Reception Point

[0175] GNSS Global Navigation Satellite System

[0176] IE Information Element

[0177] NR New Radio

[0178] NRPPa NR Positioning Protocol Appendix

[0179] TA Target Accuracy

[0180] LCS Label Consistency Score

[0181] CIR Channel Impulse Response

[0182] 2D Two-Dimensional

[0183] 3D Three-Dimensional

[0184] RAT Radio Access Technology

[0185] UE User Equipment

[0186] 5G Fifth Generation

[0187] LTE Long-Term Evolution

[0188] LTE-A LTE Advanced

[0189] LPP LTE Positioning Protocol

[0190] WCDMA Wideband Code Division Multiple Access

[0191] BS Base Station

[0192] AP Access Point

[0193] eNodeB Evolved NodeB

[0194] gNB / NR NB Next Generation NodeB

[0195] Tx Transmit

[0196] Rx Receive

[0197] DL Downlink

[0198] UL Uplink

[0199] SL Sidelink

[0200] SL-PRS Sidelink Positioning Reference Signal

[0201] AI Artificial Intelligence

[0202] ML Machine Learning

[0203] NWDAF Network Data Analytics Function

[0204] NLOS Non-Line-of-Sight

[0205] RAN Radio Access Network

[0206] NG-RAN Next Generation Radio Access Network

Claims

1. A first device, comprising: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the first device to at least perform: receive first information from a second device, the first information indicating: a target accuracy for positioning, and a set of parameters for label quality assessment of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; determine a quality parameter of the training samples based on the set of parameters, the label information, and the target accuracy; and send a report to the second device, the report at least including the quality parameter.

2. The first device according to claim 1, wherein the set of parameters comprises: a set of coefficients required to determine the quality parameter.

3. The first device according to claim 2, wherein the set of coefficients includes at least one of the following: a set of exponential coefficients, or a set of attenuation rates.

4. The first device according to any one of claims 1 to 3, wherein the information further indicates a label quality threshold, and wherein sending the report comprises: determine whether the quality parameter is less than the label quality threshold; and based on determining that the quality parameter is not less than the label quality threshold, send the report including the quality parameter, a position estimate of the first device, and the radio measurements to the second device.

5. The first device according to any one of claims 1 to 3, wherein the information further indicates a label quality threshold, and wherein sending the report comprises: determine whether the quality parameter is less than the label quality threshold; and based on determining that the quality parameter is less than the label quality threshold, send the report including the quality parameter to the second device.

6. The first device according to any one of claims 1 to 3, wherein the first device is caused to perform: perform the label quality assessment of the training samples based on the target accuracy, and a mean and variance of position estimates obtained for a positioning source associated with the radio measurements.

7. The first device according to any one of claims 1 to 6, wherein the first device is caused to perform: receive second information from the second device, the second information indicating a required type of radio measurement and position estimate, and an indication of whether the label quality assessment is enabled; determine whether the first device is capable of providing the required type of radio measurement based on the capability information of the first device; and based on determining that the first device is capable of providing the required type of radio measurement, send third information to the second device, the third information indicating: the first device is capable of providing the required type of radio measurement.

8. The first device according to any one of claims 1 to 7, wherein the radio measurements, and the label information associated with the radio measurements are obtained from at least one of the following: the first device, or the second device.

9. The first device according to any one of claims 1 to 8, wherein the first device includes a terminal device, and the second device includes a core network device, or wherein the first device includes a network device, and the second device includes the core network device.

10. A second device, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second device to at least perform: sending first information to a first device, the first information indicating: a target accuracy for positioning, and a set of parameters for evaluating the label quality of training samples, the training samples including: radio measurements, and label information associated with the radio measurements; and receiving a report from the first device, the report at least including a quality parameter determined based on the set of parameters, the label information, and the target accuracy.

11. The second device according to claim 10, wherein the set of parameters comprises: a set of coefficients required to calculate the quality parameter.

12. The second device according to claim 11, wherein the set of coefficients includes at least one of the following: a set of exponential coefficients, or a set of attenuation rates.

13. The second device according to any one of claims 10 to 12, wherein the information further indicates a label quality threshold, and wherein receiving the report comprises: receiving, from the first device, the report including the quality parameter, a position estimate of the first device, and the radio measurement, based on a determination that the quality parameter is not less than the label quality threshold.

14. The second device according to any one of claims 10 to 12, wherein the information further indicates a label quality threshold, and wherein receiving the report comprises: receiving, from the first device, the report including the quality parameter, based on a determination that the quality parameter is less than the label quality threshold.

15. The second device according to any one of claims 10 to 14, wherein the second device is caused to perform: determining the label quality threshold based on the target accuracy and the size of a training data set for positioning.

16. The second device according to any one of claims 10 to 15, wherein the second device is caused to perform: sending second information to the first device, the second information indicating: a required type of radio measurement and position estimate, and an indication of whether the label quality assessment is enabled; and receiving third information from the first device, the third information indicating that the first device is capable of providing the required type of radio measurement.

17. The second device according to any one of claims 10 to 16, wherein the second device is caused to perform: determining whether another positioning source is available at the second device; and Based on determining that the other positioning source at the second device is available, determine another tag quality parameter based on the position estimate from the first device and another position estimate from the other positioning source at the second device.

18. The second device according to claim 17, wherein the second device is caused to perform: Store the radio measurements and the position estimate together with the other quality parameter.

19. The second device according to any one of claims 10 to 18, wherein the radio measurements and the tag information associated with the radio measurements are obtained from at least one of: the first device, or the second device.

20. The second device according to any one of claims 10 to 19, wherein the first device includes a terminal device and the second device includes a core network device, or wherein the first device includes a network device and the second device includes the core network device.

21. A method, comprising: Receiving, at a first device, first information from a second device, the first information indicating: a target accuracy for positioning and a set of parameters for tag quality assessment of training samples, the training samples including: radio measurements and tag information associated with the radio measurements; Determining a quality parameter of the training sample based on the set of parameters, the tag information, and the target accuracy; and Sending a report to the second device, the report at least including the quality parameter.

22. The method according to claim 21, wherein the set of parameters comprises: A set of coefficients required to determine the quality parameter.

23. The method according to claim 22, wherein the set of coefficients includes at least one of: a set of exponential coefficients, or a set of decay rates.

24. The method according to any one of claims 21 to 23, wherein the information further indicates a tag quality threshold, and wherein sending the report comprises: Determining whether the quality parameter is less than the tag quality threshold; and and Based on determining that the quality parameter is not less than the tag quality threshold, sending the report including the quality parameter, a position estimate of the first device, and the radio measurements to the second device.

25. The method according to any one of claims 21 to 23, wherein the information further indicates a tag quality threshold, and wherein sending the report comprises: Determining whether the quality parameter is less than the tag quality threshold; and and Based on determining that the quality parameter is less than the tag quality threshold, sending the report including the quality parameter to the second device.

26. The method according to any one of claims 21 to 23, wherein the first device is caused to perform: Perform the tag quality assessment of the training sample based on the target accuracy and the mean and variance of the position estimates obtained for the positioning source associated with the radio measurements.

27. The method according to any one of claims 21 to 26, wherein the first device is caused to perform: Receive second information from the second device, the second information indicating: radio measurements and position estimates of a required type, and an indication as to whether the tag quality assessment is enabled; Based on the capability information of the first device, determine whether the first device is capable of providing the radio measurements of the required type; And Based on determining that the first device is capable of providing the radio measurements of the required type, send third information to the second device, the third information indicating: the first device is capable of providing the radio measurements of the required type.

28. The method according to any one of claims 21 to 27, wherein the radio measurements and the tag information associated with the radio measurements are obtained from at least one of: the first device, or the second device.

29. The method according to any one of claims 21 to 28, wherein the first device includes a terminal device and the second device includes a core network device, or wherein the first device includes a network device and the second device includes the core network device.

30. A method, comprising: At a second device, send first information to a first device, the first information indicating: a target accuracy for positioning, and a set of parameters for tag quality assessment of training samples, the training samples including: radio measurements and tag information associated with the radio measurements; and Receive a report from the first device, the report including at least a quality parameter, the quality parameter being determined based on the set of parameters, the tag information, and the target accuracy.

31. The method according to claim 30, wherein the set of parameters comprises: A set of coefficients required to calculate the quality parameter.

32. The method according to claim 31, wherein the set of coefficients includes at least one of: a set of exponential coefficients, or a set of attenuation rates.

33. The method according to any one of claims 30 to 32, wherein the information further indicates a tag quality threshold, and wherein receiving the report comprises: According to a determination that the quality parameter is not less than the tag quality threshold, receive the report including the quality parameter, a position estimate of the first device, and the radio measurements from the first device.

34. The method according to any one of claims 30 to 32, wherein the information further indicates a tag quality threshold, and wherein receiving the report comprises: According to a determination that the quality parameter is less than the tag quality threshold, receive the report including the quality parameter from the first device.

35. The method according to any one of claims 30 to 34, wherein the second device is caused to perform: Based on the target accuracy and the size of a training data set for positioning, determine the tag quality threshold.

36. The method according to any one of claims 30 to 35, wherein the second device is caused to perform: Send second information to the first device, the second information indicating: radio measurements and position estimates of a required type, and an indication as to whether the tag quality assessment is enabled; and Receive third information from the first device, the third information indicating that the first device is capable of providing radio measurements of the required type.

37. The method according to any one of claims 30 to 36, wherein the second device is caused to perform: Determine whether another positioning source is available at the second device; and Based on determining that the other positioning source is available at the second device, determine another tag quality parameter based on the position estimate from the first device and another position estimate from the other positioning source at the second device.

38. The method according to claim 37, wherein the second device is caused to perform: Store the radio measurements and the position estimate together with the other quality parameter.

39. The method according to any one of claims 30 to 38, wherein the radio measurements and the tag information associated with the radio measurements are obtained from at least one of: the first device, or the second device.

40. The method according to any one of claims 30 to 39, wherein the first device comprises a terminal device and the second device comprises a core network device, or wherein the first device comprises a network device and the second device comprises the core network device.

41. A first apparatus, comprising: means for receiving first information from a second device, the first information indicating: a target accuracy for positioning and a set of parameters for tag quality assessment of training samples, the training samples comprising: radio measurements and tag information associated with the radio measurements; means for determining a quality parameter of the training samples based on the set of parameters, the tag information, and the target accuracy; and means for sending a report to the second device, the report comprising at least the quality parameter.

42. A second apparatus, comprising: means for sending first information to a first device, the first information indicating: a target accuracy for positioning and a set of parameters for tag quality assessment of training samples, the training samples comprising: radio measurements and tag information associated with the radio measurements; and means for receiving a report from the first device, the report comprising at least a quality parameter determined based on the set of parameters, the tag information, and the target accuracy.

43. A computer-readable medium comprising instructions stored thereon for causing a device to perform at least the method according to any one of claims 21 to 29, or the method according to any one of claims 30 to 40.

Images