Noise localization data processing

Abstract

The embodiment of the invention relates to a method, equipment and device for noise positioning data processing and a computer readable storage medium. In one method, a first device obtains measurement data and first positioning data associated with the measurement data. The first device generates second positioning data from the first positioning data based on network assistance information. The first device at least sends the measurement data and the second positioning data. In this way, the precision of positioning data can be improved.

Description

Technical Field

[0001] Various example embodiments of the present disclosure relate generally to the field of telecommunications, and in particular, to methods, devices, apparatuses, and computer-readable storage media for noise localization data processing. 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 used to locate devices in communication networks. In this case, a large dataset of training samples can be used to train AI / ML models to improve positioning accuracy. However, positioning data of training samples such as labels may not be completely accurate. Therefore, it is worth studying how to process noisy positioning data of training samples. 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, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the first device: obtains measurement data and first positioning data associated with the measurement data; generates second positioning data from the first positioning data based on network assistance information; and at least sends the measurement data and the second positioning data.

[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, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the second device: sends network assistance information to a first device, the network assistance information is to be used by the first device to generate second positioning data from first positioning data associated with measurement data; and receives at least the measurement data and the second positioning data from the first device.

[0005] In a third aspect of the present disclosure, a third device is provided. The third device includes: at least one processor; and at least one memory, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the third device: receives a request from a first device or a second device to send a rule to the first device, wherein the rule is to be used by the first device to generate second positioning data from first positioning data associated with measurement data; and in response to receiving the request, sends network assistance information including the rule to the first device.

[0006] In a fourth aspect of the present disclosure, a method is provided, comprising: acquiring measurement data and first positioning data associated with the measurement data at a first device; generating second positioning data from the first positioning data based on network assistance information; and sending at least the measurement data and the second positioning data.

[0007] In a fifth aspect of the present disclosure, a method is provided. The method comprises: sending network assistance information at a second device to a first device, the network assistance information to be used by the first device to generate second positioning data from first positioning data associated with measurement data; and receiving at least the measurement data and the second positioning data from the first device.

[0008] In a sixth aspect of the present disclosure, a method is provided. The method includes: receiving, at a third device, a request from a first device or a second device to send a rule to the first device, the rule to be used by the first device to generate second positioning data from first positioning data associated with measurement data; and in response to receiving the request, sending network assistance information including the rule to the first device.

[0009] In a seventh aspect of the present disclosure, a first device is provided. The first device includes: a component for acquiring measurement data and first positioning data associated with the measurement data; a component for generating second positioning data from the first positioning data based on network assistance information; and a component for sending at least the measurement data and the second positioning data.

[0010] In an eighth aspect of the present disclosure, a second device is provided. The second device comprises: a component for sending network assistance information to a first device, the network assistance information to be used by the first device to generate second positioning data from first positioning data associated with measurement data; and a component for receiving at least the measurement data and the second positioning data from the first device.

[0011] In a ninth aspect of the present disclosure, a third device is provided. The third device includes: a component for receiving a request from a first device or a second device to send a rule to the first device, the rule to be used by the first device to generate second positioning data from first positioning data associated with measurement data; and a component for sending network assistance information including the rule to the first device in response to receiving the request.

[0012] In a tenth aspect of the present disclosure, a computer-readable medium is provided, wherein the computer-readable medium includes instructions stored thereon for causing a device to execute the method according to the fourth, fifth or sixth aspect.

[0013] It should be understood that the invention summary is not intended to identify the key 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 understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0015] Figure 1An example communication environment is shown in which example embodiments of the present disclosure may be implemented;

[0016] Figure 2 shows a signaling diagram for noise localization data processing according to some example embodiments of the present disclosure;

[0017] Figure 3 A flowchart illustrating a process for determining rules for noise localization data processing according to some example embodiments of the present disclosure;

[0018] Figure 4 shows another signaling diagram for noise localization data processing according to some example embodiments of the present disclosure;

[0019] Figure 5A and Figure 5B An example framework of AI / ML-based positioning with noise positioning data processing according to some example embodiments of the present disclosure is respectively shown;

[0020] Figure 6 A flowchart showing a method implemented at a first device according to some example embodiments of the present disclosure is shown;

[0021] Figure 7 A flowchart showing a method implemented at a second device according to some example embodiments of the present disclosure is shown;

[0022] Figure 8 A flowchart of a method implemented at a third device according to some example embodiments of the present disclosure is shown;

[0023] Fig. 9 shows a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure; and

[0024] Fig.10 A block diagram of an example computer-readable medium is shown according to some example embodiments of the present disclosure.

[0025] Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. DETAILED DESCRIPTION

[0026] The principle of the present disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described only to illustrate and help those skilled in the art to understand and implement the present disclosure, and do not imply any limitation on the scope of the present disclosure. The embodiments described herein can be implemented in various ways except the way described below.

[0027] In the following description and claims, unless defined otherwise, 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 belongs.

[0028] References in this disclosure to "one embodiment," "an embodiment," "an example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered within the knowledge of those skilled in the art that other embodiments may be combined to affect such feature, structure, or characteristic, whether or not explicitly described.

[0029] It should be understood that although the terms "first", "second", etc. may be used to describe various elements in this article, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0030] As used herein, “at least one of: ” and “at least one of ” and similar expressions, where a list of two or more elements is combined 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.

[0031] 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 may include one or more intermediate steps.

[0032] The terms used herein are used only to describe specific embodiments 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 will be further understood that the terms "comprise", "including", "having", "having", "including" and / or "comprising", when used herein, specify the presence of the features, elements and / or components, etc., but do not exclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0033] The term "circuitry" as used in this application may refer to one or more or all of the following: (a) hardware circuit implementation only (such as implementation in analog and / or digital circuits only) and (b) a combination of hardware circuitry and software such as (where applicable): (i) a combination of analog and / or digital hardware circuits and software / firmware and (ii) any portion of a hardware processor(s) with software (including digital signal processor(s), software and memory(s) that work together to enable a device (such as a mobile phone or server) to perform various functions) and (c) Hardware circuits and / or processor(s), such as microprocessor(s) or portions of microprocessor(s), that require software (e.g., firmware) to operate, but which may not be present when the software is not required to operate.

[0034] The definition of circuitry applies to all uses of the term in this application, including any claims. As yet another example, as used in this application, the term circuitry also covers an implementation of only a hardware circuit or processor (or multiple processors) or a portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example (and if applicable to a particular claim element), a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in a server, cellular network device, or other computing or network device.

[0035] As used herein, the term "communication network" refers to a network that complies with any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), Advanced LTE (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 the terminal equipment and the network equipment in the communication network can be performed according to any suitable generation communication protocol, including but not limited to the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G) communication protocol and / or any other protocol currently known or developed in the future. The embodiments of the present disclosure can be applied to various communication systems. In view of the rapid development of communication, there will certainly be future types of communication technologies and systems that can implement the present disclosure. The scope of the present disclosure should not be limited to the above-mentioned system.

[0036] As used herein, the term "network device" or "network access device" refers to a node in a communication network, via which a terminal device accesses the network and receives services from it. A network device may refer to a base station (BS) or an access point (AP), such as a Node B (NodeB or NB), an evolved Node B (eNodeB or eNB), a NR NB (also referred to as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a relay, an integrated access and backhaul (IAB) node, a low-power node (such as a femto, a micro, a non-terrestrial network (NTN)) or a non-terrestrial network device (such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous orbit (GEO) satellite, an aircraft network device), etc., depending on the terminology and technology applied. In some example embodiments, a radio access network (RAN) split architecture includes a centralized unit (CU) and a distributed unit (DU) located at an IAB donor node. The IAB node includes a mobile terminal (IAB-MT) part, which behaves like a UE towards a parent node, and the DU part of the IAB node behaves like a base station towards a next-hop IAB node.

[0037] The term "terminal device" refers to any terminal device that may be capable of wireless communication. As an example and not limitation, a terminal device may also be referred to as a communication device, a user equipment (UE), a user station (SS), a portable user station, a mobile station (MS), or an access terminal (AT). The terminal device may include, but is not limited to, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless regional loop phone, a tablet computer, a wearable terminal device, a personal digital assistant (PDA), a portable computer, a desktop computer, an image capture terminal device (such as a digital camera), a game terminal device, a music storage and playback device, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop embedded device (LEE), a laptop device (LME), a USB dongle, a smart device, a wireless client device (CPE), an Internet of Things (IoT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, medical equipment and applications (e.g., remote surgery), industrial equipment and applications (e.g., robots and / or other wireless devices operating in the context of an industrial and / or automated processing chain), consumer electronic devices, devices operating on commercial and / or industrial wireless networks, etc. The terminal device may also correspond to the mobile terminal (MT) part of an IAB node (eg, a relay node).In the following description, the terms "terminal device", "communication device", "terminal", "user equipment" and "UE" may be used interchangeably.

[0038] As used herein, the term "resource", "transmission resource", "resource block", "physical resource block" (PRB), "uplink resource" or "downlink resource" may refer to any resource used to perform communication, for example, communication between a terminal device and a network device, such as time domain resources, frequency domain resources, spatial domain resources, code domain resources, or any other resource capable of communication. In the following, unless explicitly stated, resources in both the frequency domain and the time domain will be used as examples of transmission resources to describe some example embodiments of the present disclosure. Note that the example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0039] As used herein, the term "model" is referred to as an association between inputs and outputs learned from training data, and thus a corresponding output can be generated for a given input after training. The generation of the model can be based on ML techniques. ML techniques can also be referred to as AI techniques. Typically, an ML model can be constructed that receives input information and makes predictions based on the input information. As used herein, a model is equivalent to an AI / ML model or a data-driven / data processing algorithm / process.

[0040] As described above, AI / ML models can be applied in the NR radio interface to assist model functions or communication-related functions, such as channel state information (CSI) feedback overhead reduction, beam management, enhanced positioning, etc. For example, AI / ML-based positioning can be used for positioning accuracy enhancement in different scenarios (e.g., scenarios with severe non-line-of-sight (NLOS) conditions).

[0041] AI / ML models can be trained using datasets of training samples. In order to better train AI / ML models, large datasets with accurate true values ​​or clean labels are required. In AI / ML-based positioning, training AI / ML models using supervised learning methods relies on obtaining a large amount of diverse training data characterized by clean labels. It is expected that labeled data will be collected from field UEs (and potential gNBs for assisted positioning) with the assistance of the network (NW). Therefore, it is the UE's responsibility to provide clean labels for the data.

[0042] As used herein, the term "tag" or "positioning data" may refer to the value of a target parameter. For example, in an AI / ML direct positioning scenario, the term "tag" or "positioning data" may refer to the value of the location of a device (such as a UE location). For another example, in an AI / ML assisted positioning scenario, the term "tag" or "positioning data" may also refer to the value of positioning measurements, such as time of arrival (TOC), channel impulse response (CIR), etc. The term "clean tag" or "clean positioning data" may be referred to as the true value of a target parameter or an exact value of a target parameter, such as a true or actual value at the measurement time. The term "noisy tag" or "noisy positioning data" may refer to an imprecise value of a target parameter, rather than a true or actual value at the measurement time.

[0043] For direct AI / ML based positioning, the truth label may be the location of the device, such as the UE location. In some example embodiments, the location of the UE may be known by a positioning reference unit (PRU). The UE may generate a location based on a non-NR and / or NR RAT related positioning method. The LMF may generate the location of the UE based on the positioning method. The LMF may know the location of the PRU. In some cases, user data privacy needs to be protected.

[0044] For AI / ML assisted positioning, the true value label can be one or more (multiple) intermediate parameters corresponding to the output of the AI / ML model. The PRU can directly generate the label or calculate it based on the measurement / position. The UE can directly generate the label or calculate it based on the measurement / position. The network entity (such as LMF) can directly generate the label or calculate it based on the measurement / position.

[0045] In some mechanisms, at least a PRU is identified to generate a truth label for UE-based positioning with a UE-side model (case 1) and UE-assisted positioning with a UE-side model (case 2a). At least a LMF with known PRU locations is identified to generate a truth label for UE-assisted / LMF-based positioning with a LMF-side model (case 2b) and NG-RAN node-assisted positioning with a LMF-side model (case 3b). A network entity with at least a known PRU location is identified to generate a truth label for NG-RAN node-assisted positioning with a gNB-side model (case 3a).

[0046] In some mechanisms, quality indicators are provided for and / or associated with at least ground truth labels and / or measurements used for model training. The quality indicators can be generated from label and / or measurement data as entity reports and / or as requested reports from different (e.g., data collection, etc.) entities.

[0047] In some mechanisms, timestamps are proposed for at least and / or associated with training data used for model training. For example, separate timestamps for measurements and ground truth labels are supported when the measurements and ground truth labels are generated by different entities. Timestamps can be reported from the data generation entity along with the training data and / or LMF assisted signaling.

[0048] For UE-based UE-side model (case 1) and UE-assisted positioning on the UE side (case 2a) or LMF side model (case 2b), the PRU or UE can generate additional training data corresponding to at least the model input. For network-side model positioning assisted by the next generation (NG) radio access network (RAN) (NG-RAN) node (case 3a and case 3b), the transmit / receive point (TRP) can generate additional training data corresponding to at least the model input.

[0049] In some mechanisms, the UE calculates labels based on non-NR and / or NR radio access technology (RAT) related and / or NR RAT independent through non-AI / ML means (e.g., using traditional positioning methods). However, by doing so, the UE can only obtain estimated labels, i.e., noise, and therefore cannot obtain clean labels. In many applications, it is difficult to obtain accurate labels (also called golden labels) for training samples.

[0050] Therefore, it is worth studying that the noisy positioning data and training models are processed or denoised using training samples with denoised labels. As used herein, the term "denoised labels" or "denoised positioning data" may refer to updated values ​​of target parameters generated by processing or denoising "noise labels" or "noise positioning data".

[0051] In the field of machine learning for video and image processing, several mechanisms have been proposed for dealing with noisy labels or label denoising. In some mechanisms, it has been proposed to clean or discard samples with noisy labels. For example, before training, random training samples can be compared with samples with known clean labels. Based on similarity analysis, it can be determined whether a sample has a noisy label. For another example, during training, parallel neural networks (NNs) are trained, one based on clean labels and the other based on noisy labels. The two NNs share an extraction layer. One NN is used to clean the noisy dataset.

[0052] In some mechanisms, a neural network architecture has been proposed to denoise labels. In this architecture, a noise layer is added to the end of the NN, which has the purpose of multiplying the output with the transformation matrix between the noisy and true labels. The transfer matrix itself is learned in parallel.

[0053] In some mechanisms, it has been proposed to apply (multiple) loss functions to denoise the labels. The loss function can be modified to implement cutoffs. That is, the model is allowed to eliminate predictions for some data points at the cost of incurring a cutoff penalty.

[0054] In some mechanisms, it has been proposed to reweight the data for noisy label handling. Those training samples that are more likely to have incorrect labels can be weighted downward. It requires a separate dataset with clean labels, which is used to determine the weights assigned to training data with noisy labels. For example, in some cases, methods based on the assumption that data samples with incorrect labels may show abnormally high loss values. For training data samples suspected of having incorrect labels, the gradient is scaled by -γ, where 0<γ<1. In other words, scaled gradient ascent is performed on samples with incorrect labels.

[0055] In some mechanisms, it has been proposed to use data and label consistency for noisy label processing. For example, the true label is a hidden variable, and the ML model simultaneously learns the relationship between the true label and the noisy label (i.e., the label noise distribution). An autoencoder model can be used to reconstruct data from the hidden variables.

[0056] In some mechanisms, several training processes have been proposed for noisy label handling. In the training process for curriculum learning, the model can be trained with examples of increasing complexity or difficulty. In the training process for knowledge distillation, an auxiliary model can be trained on a small dataset with clean labels to guide the training of the main model on a large dataset with noisy labels. In the training process for jointly training more than one model, for example, two separate but identical networks are trained simultaneously with random initialization, and the network parameters can be updated only when the predictions of the two networks are different. In some training processes, the settings of the training pipeline, such as learning rate and regularization, can be modified. For example, training strategies for sequential aspects of using different datasets during training and appropriate learning rate adjustments based on the level of label noise in each dataset are proposed.

[0057] However, these mechanisms are proposed for machine learning applications in video and image processing. For AI / ML based positioning, there is a lack of effective methods for noisy label processing. In some mechanisms, in order to evaluate AI / ML based positioning, it is recommended to study the performance impact of the availability of true value labels. For example, some training data may not have true value labels. The learning algorithm (e.g., supervised learning, semi-supervised learning, unsupervised learning) can be reported. However, once the UE is deployed in the field, how to obtain clean labels or clean positioning data remains one of the most important open issues.

[0058] In order to solve at least part of the above problems or other potential problems, a solution for measurement duplication is proposed. According to an example embodiment, a first device (e.g., a terminal device or a network device) obtains measurement data and noise positioning data associated with the measurement data. The first device generates denoised positioning data from the noise positioning data based on network auxiliary information. In some exemplary embodiments, network auxiliary information can be sent to the first device from a second device (e.g., a core network device such as lifecycle management) or a third device (e.g., other terminal devices). The first device sends measurement data and denoised positioning data to at least, for example, a second device or a third device. In this way, the accuracy of the positioning data can be improved. Therefore, AI / ML-based positioning can be enhanced based on denoised positioning data.

[0059] The following will refer to Figure 1-10 The principles and implementations of the present disclosure are described in detail.

[0060] Figure 1 An example communication environment 100 is shown in which example embodiments of the present disclosure may be implemented. Communication environment 100 includes devices 110-1, 110-2, ..., and 110-N, which may be collectively referred to as "device(s) 110", or individually as "device 110". Communication environment 100 also includes device 120 and device 130. Device(s) 110, device 120, and device 130 may communicate with each other.

[0061] exist Figure 1 In the example of , 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.

[0062] In some example embodiments, the ML unit may be located within communication environment 100. For example, the ML unit may be a part of the LMF implemented on device 120. For another example, the ML unit may be implemented on device 110 or device 130. The ML unit trains the AI / ML model using the training samples for positioning. The ML unit may be any suitable unit for data analysis.

[0063] In some example embodiments, the ML unit may collect training samples from a set of data collection devices deployed at certain locations. The data collection devices may include a positioning reference unit (PRU) or any other suitable data collection device. A PRU is a reference unit such as a device or network node at a known location (i.e., with label information). The PRU may take measurements to generate correction data for refining the location of other target devices in the area.

[0064] In some example embodiments, device 110, device 120, and / or device 130 may perform as a data collection device. For example, device 110, device 120, and / or device 130 may provide positioning measurements or estimates in addition to its / their own (multiple) positions via a radio access network (RAN) or non-RAN. Positioning information provided by device 110, device 120, and / or device 130 is collected in communication environment 100 and may therefore be used to analyze propagation properties of communication environment 100.

[0065] The ML unit may train a localized ML framework using a training dataset, which may include positioning measurements from different PRUs or from different devices. The trained ML framework may be deployed at a network entity that runs an ML process and / or algorithm.

[0066] It should be understood that Figure 1 The number of devices and their connections shown in the figure is for illustrative purposes only and does not imply any limitation. The communication environment 100 may include any suitable number of devices configured to implement the exemplary embodiments of the present disclosure. Although not shown, it should be understood that one or more additional devices may be located in a cell of the device 130, and one or more additional cells may be deployed in the communication environment 100. Note that although shown as a network device, the device 130 may be a device other than a network device. Although shown as a terminal device, the device 110 may be a device other than a terminal device.

[0067] In the following, for the purpose of illustration, 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 conjunction with the terminal device may be implemented at a network device or other device, and the operations described in conjunction with the network device may be implemented at a terminal device or other device.

[0068] 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).

[0069] The communication in the communication environment 100 can be implemented according to any appropriate communication protocol, including but not limited to cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), the fifth generation (5G), the sixth generation (6G), etc., wireless local area network communication protocols such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocol currently known or developed in the future. In addition, the communication can utilize any appropriate 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 duplex (FDD), time division duplex (TDD), multiple input multiple output (MIMO), orthogonal frequency division multiple access (OFDM), discrete Fourier transform spread OFDM (DFT-s-OFDM) and / or any other technology currently known or developed in the future.

[0070] As briefly mentioned above, the accuracy of positioning data can be improved based on network assistance information. Figure 2 A signaling diagram 200 for noise localization data processing is shown according to some example embodiments. The signaling diagram 200 involves a first device 210 and a second device 220.

[0071] In some example embodiments, the first device 210 may refer to or include Figure 1 The second device 220 may refer to or include Figure 1 120 shown in . It should be understood that the first device 210 and the second device 220 may refer to or include any suitable device, including but not limited to a UE, a PRU, a transmission / reception 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 respect.

[0072] Despite Figure 2 A single first device 210 and a single second device 220 are shown in FIG. 1 , but it should be understood that there may be multiple devices that perform operations similar to those described below with respect to the first device 210 or the second device 220 .

[0073] Note that embodiments of the present disclosure may be applied to any appropriate scenario, such as beam management, positioning accuracy enhancement, or CSI. For illustrative purposes only, example embodiments of the present disclosure are described with reference to the scenario of positioning accuracy enhancement.

[0074] In operation, the first device 210 obtains (230) measurement data and first positioning data associated with the measurement data. The measurement data may be input to an AI / ML model for model training or model reasoning. As used herein, the measurement data may also be referred to as "model input". The measurement data may be reported from a measurement data generating entity. The measurement data generating entity may be implemented on the first device 210. Examples of the measurement data generating entity may include, but are not limited to, a UE, a PRU, or a TRP.

[0075] In some example embodiments, the measurement data generating entity may be generated based on a reference signal (RS). The (multiple) RS configuration may be a request from the first device 210 (such as the measurement data generating entity) to the second device 210 (such as the LMF) and / or as LMF auxiliary signaling to the first device 210. The measurement data generating entity may generate measurement data based on the (multiple) RS. For example, the measurement data may be a radio measurement or a positioning measurement, such as a measurement of a field NR signal. The measurement data may include any combination of time, angle of arrival, channel impulse response (CIR), etc.

[0076] In some example embodiments, the first positioning data may include coordinates of the first device 210, such as UE coordinates. Alternatively or additionally, the first positioning data may include auxiliary positioning data, such as a binary identifier of line of sight (LOS) or non-line of sight (NLOS), or time of arrival (ToA), etc. The first positioning data may be determined by the first device 210. The first positioning data may not be true positioning data. As used herein, the first positioning data may also be referred to as noise positioning data.

[0077] The first device 210 generates (250) second positioning data from the first positioning data based on the network assistance information. As used herein, the second positioning data may be referred to as denoised positioning data.

[0078] In some example embodiments, the first device 210 may generate (250) second positioning data from the first positioning data based on network assistance information received (245) from the second device 220. The second device 220 may determine (235) the network assistance information. The second device 220 may send (240) the network assistance information to the first device 210.

[0079] In some example embodiments, the first device 210 includes a device 110, such as a terminal device. In such a case, the first device 210 may receive network assistance information from the second device 220 via an LTE Positioning Protocol (LPP) Information Element (IE) (such as a Label Denoiser (LD)-Configuration). In this case, the network assistance information may also be referred to as LPP assistance data.

[0080] Alternatively or additionally, in some example embodiments, the first device 210 includes a device 130 such as a network device. In such cases, the first device 210 may receive network assistance information from the second device 220 via an NR Positioning Protocol Annex (NRPPa) IE or any other suitable signaling. It should be understood that the IEs described below are for illustrative purposes only and do not imply any limitation. The devices may send information having any suitable IE or other information format. The scope of the present disclosure is not limited in this regard.

[0081] In some example embodiments, the network assistance information may include rules to be applied to generate the second positioning data from the first positioning data. As used herein, the term "rule" may also be referred to as a "label denoiser" or "LD". In some example embodiments, the network assistance information may include a plurality of rules to be applied to generate the second positioning data from the first positioning data. One or more rules may be determined by the second device 220. One or more rules may be in an open format.

[0082] In some example embodiments, the rules relate to positioning technology.The positioning technology may be any available proprietary or legacy positioning method, such as a Radio Access Technology (RAT) or a non-RAT positioning technology.

[0083] If the positioning technology is a global navigation satellite system (GNSS) positioning technology, the rule may be a specific GNSS tag denoising rule or a specific GNSS tag denoiser. If the positioning technology is an NR positioning technology, the rule or LD may be an NR tag denoising rule or an NR LD. Similarly, the rule or LD may be classified as a WiFi LD or a 5G LD or any other specific rule or LD based on its corresponding positioning technology. Alternatively, the rule may be independent of the positioning technology.

[0084] In some example embodiments, the rules are associated with a location area. For example, a rule or LD may be determined for a specific area in a cell.

[0085] Alternatively or additionally, in some example embodiments, the rule is related to the type of the first device 210. The type of the first device 210 may include, but is not limited to, a pedestrian device, V2X, and the like.

[0086] The rule or LD may be determined by the second device 220. The second device 220 may determine (235) network assistance information based on the determined one or more rules. Figure 3 An example process 300 for determining network assistance information is shown. The process 300 can be implemented by the second device 220.

[0087] At block 310, the second device 220 may obtain a noise label for the collected data (e.g., the collected measurement data). In some example embodiments, the second device 220 may generate an artificial but known noise label. That is, the noise label may be generated without the assistance of the first device. In this way, the second device 220 may also determine the rule without the assistance of the UE.

[0088] Alternatively or additionally, in some example embodiments, the second device 220 may collect data, such as perfect tags from PRUs in the field, with assistance from the first device 210. The assistance may at least indicate the experienced signal-to-noise ratio radio (SNR) conditions at the first device 210. In this way, the second device 220 may also utilize UE assistance to determine rules.

[0089] At block 320, the second device 220 may determine at least one rule to be applied to generate the second positioning data from the first positioning data. For example, the second device 220 may calculate a rule that is agnostic or specific to positioning technology such as GNSS, NR, etc.

[0090] At block 330, the second device 220 may determine the network assistance information. For example, the second device 220 may include at least one rule in the network assistance information. In some example embodiments, the second device 220 may include additional information in the network assistance information.

[0091] Taking NR specific rules or denoisers as an example, the second device 220 may collect data with perfect labels from NR simulation or ray tracing tools. Alternatively or additionally, in some example embodiments, the second device 220 may collect data with perfect labels from NRPRUs in the field.

[0092] At box 310, the second device 220 can further artificially generate an additional white Gaussian noise (AWGN) with different variances or any other suitable noise, and apply the generated noise to the perfect label. For example, for direct AI / ML-based positioning, the true value label error in each dimension of the x-axis and y-axis can be modeled as a truncated Gaussian distribution with zero mean and a standard deviation of L meters, where the distribution is truncated to the range of [-2*L, 2*L]. The value L is up to the source. Based on such a truncated Gaussian distribution, AWGN noise can be generated.

[0093] Taking AI / ML assisted positioning using TOA as model output as an example, the true value label error of TOA can be calculated based on the position error. The position error in each dimension of the x-axis and y-axis can be modeled as a truncated Gaussian distribution with zero mean and a standard deviation of L meters, where the distribution is truncated to the range [-2*L, 2*L]. The value L depends on the source. Other timing information such as reference signal time difference (RSTD) as model output is not excluded.

[0094] For AI / ML assisted positioning with LOS / NLOS indicators as model output, the ground truth label error of the LOS / NLOS indicator can be modeled as m% LOS label error and n% NLOS label error. The values ​​of m and n depend on the source.

[0095] Based on these label error models, AWGN noise can be generated. It should be understood that these models are only for illustrative purposes and do not imply any limitation. Any other suitable noise model can be applied. The scope of the present disclosure is not limited in this regard.

[0096] In some example embodiments, when evaluating AI / ML-assisted positioning with timing information (e.g., TOA) as a model output, the timing (e.g., TOA) estimation error and the positioning error increase approximately proportionally with L for L in the range of 0.25m to 5m, where L (in meters) is the standard deviation of the truncated Gaussian distribution of the true label error.

[0097] In some example embodiments, the evaluation shows that AI / ML assisted positioning with timing information (e.g., ToA) as model output is robust to certain label errors based on evaluation results of L in the range of (0, 5) meters. The exact range of label errors that can be tolerated depends on the positioning accuracy requirements, where stricter positioning accuracy requirements require smaller label errors.

[0098] Furthermore, the evaluation shows that direct AI / ML localization is robust to certain label errors based on evaluation results for L in the range of (0, 5) meters. The exact range of label errors that can be tolerated depends on the localization accuracy requirements, where stricter localization accuracy requirements require smaller label errors. These evaluations can be used to generate AWGN noise.

[0099] In this way, for each observation point, the second device 220 may know the following items: an input feature set (e.g., channel impulse response (CIR), power delay profile (PDP), etc.), a perfect label L (e.g., LOS probability, TOA, 2D position, 3D position, height, etc.), and a noise label Ln. As used herein, the input feature set may be referred to as "a", the predicted label L may be referred to as "b", and the noise label Ln may be referred to as "c". At block 320, the second device 220 may determine a rule specific to NR based on the generated noise label.

[0100] A similar procedure may be used to obtain a GNSS specific rule or label denoiser. In the case where the second device 220 prepares a technology agnostic denoiser, the second device 220 may collect observation points from NR PRUs, GNSS PRUs, NR simulations, GNSS simulations, etc., and use all collected data to generate an input feature set, a perfect label L, and a noisy label Ln.

[0101] In some example embodiments, the second device 220 may use a pair of (perfect label L, noisy label Ln) to train a rule or label denoiser that takes the noisy label Ln as input and needs to learn how to generate a perfect label As an example implementation, LD can be implemented as a denoising autoencoder that minimizes the perfect label L and the estimated The training is performed using a cost function that is based on the error between and (e.g., mean squared error, cross entropy, etc., depending on the label type).

[0102] The second device 220 may then collect parameter settings (architecture, depth, activation function, weights, and biases) of the LD in an LPP assistance data LD-configuration. In block 330, the second device 220 may determine network assistance information based on one or more LD-configurations. The second device 220 may transmit the network assistance information (such as the LPP assistance data LD-configuration) to the first device 210 in message 3.

[0103] Alternatively, in some example embodiments, a real noise profile may be used instead of an artificially generated AWGN (with a different variance) to determine the rules. In fact, the PRU may have an ideal label (without any noise). In addition, the labels may be generated using conventional means (e.g., GNSS) to obtain the noisy labels. Therefore, for each observation sample, the PRU may have the following: an input feature set (e.g., CIR, PDP, etc.) (referred to as "a"), a known perfect label L (referred to as "b") (such as LOS probability, TOA, 2D position, 3D position, altitude, etc.), and a noise label Ln (referred to as "c") estimated using a conventional positioning method (such as GNSS). The rules or LDs may then be similarly trained by using a pair of (b, c).

[0104] Return to reference Figure 2 If a technology-specific LD has been generated, the second device 220 may send ( 240 ) a corresponding LD-configuration (one or more LD-configurations, depending on the positioning capabilities of the first device 210 ) to the first device 210 .

[0105] In some example embodiments, the network assistance information may include application conditions of the rule. For example, the second device 220 may mark one or more LD-configurations. Each LD-configuration may carry a field for describing the technology to which it applies.

[0106] As described above, the first device 210 obtains measurement data and first positioning data (corresponding to a pair (a, c), i.e., a pair of input features and a noise label). The first device 210 may store the measurement data and the first positioning data. Then, the first device 210 determines (250) second positioning data based on the received (245) network auxiliary information. For example, the first device 210 may determine (250) the second positioning data by applying a rule or LD to the first positioning data such as a noise label. The rule or LD may produce a clean version of the label. The clean version of the label may be referred to as the second positioning data. In some example embodiments, the rule applied to the first positioning data may be selected from a plurality of rules included in the network auxiliary information based on an applicable condition included in the network auxiliary information or based on any other suitable condition.

[0107] In some example embodiments, the first device 210 may send (255) at least the measurement data and the second positioning data to the second device 220. For example, the first device 210 may send (255) the measurement data, the first positioning data, and the second positioning data (e.g., a tuple (a, b, c)) to the second device 220 via message 5. It is beneficial for the second device 220 to obtain both the clean labels and the noisy labels so that the second device 220 can calculate positioning corrections to be applied to other first devices 210 or devices performing traditional positioning sessions.

[0108] In some example embodiments, the network assistance information may include an indication that reception of the measurement data and the second positioning data is prioritized. If the network assistance information includes such an indication, the first device 210 may send (255) the measurement data and the second positioning data to the second device 220 without sending the first positioning data. For situations where the second device 220 reports high overhead in the radio interface, prioritizing only the de-noised tuple information (a, b) may help reduce overhead.

[0109] In some example embodiments, the first device 210 may indicate which rule or LD-configuration to use for each reported tuple (a, b, c). This is beneficial because the second device 220 may use technology-specific weights to weight the importance of different tuples in the second device 220 of the AI / ML positioning model.

[0110] In some example embodiments, the network assistance information may include a request for noise levels during a time period within a region. That is, the second device 220 may request the first device 210 to report the noise level it experienced over a time window T for a given region of interest (ROI).

[0111] In response to receiving the request for the noise level, the first device 210 can send (265) the noise level during the time period within the area to the second device 220. The second device 220 can receive (270) the noise level. In this way, the first device 210 can indicate to the second device 220 the noise level it experienced within the requested time window of a given positioning method.

[0112] Using the received (270) noise level, the second device 220 can apply the given noise level to the artificially generated tags to prepare appropriate rules or LDs for a given positioning method.

[0113] In some example embodiments, second device 220 may configure first device 210 for a time window for reporting noise levels (periodic reporting). For example, second device 220 may configure a time window for noise reporting based on mobility conditions, radio environment characteristics, LOS / NLOS conditions, etc. of first device 210. In this way, less frequent reporting may be achieved.

[0114] In some example embodiments, the first device 210 may determine whether to send (265) the noise level to the second device 220 based on a threshold level. If the noise level is greater than or equal to the threshold level, the first device 210 may send (265) the noise level to the second device 220. Otherwise, the first device 210 may not report the noise level. That is, the first device 210 may actively report the noise level based on the noise level being greater than or equal to the threshold level. Otherwise, the first device 210 may remain silent.

[0115] In some example embodiments, the network assistance information further includes a threshold level. For example, the second device 220 may share the supported noise threshold for determining the LD-configuration as part of the network assistance information.

[0116] In some example embodiments, the second device 220 may design rules or LDs for specific areas in the cell. Such rules or LDs may be obtained using auxiliary information from the first device 210. For example, the second device 220 may request the first device 210 to report its experienced noise level over the time window T and the region of interest (ROI). The second device 220 may apply a given noise level to the artificially generated tags. The second device 220 may prepare appropriate rules or LDs for a given positioning method.

[0117] If the first device 210 is in a static environment, the second device 220 may increase the time window for noise reporting. In another embodiment, if the first device 210 experiences a noise level above a threshold level of a configured LD, the first device 210 may actively report a new value of the noise level, otherwise the first device 210 remains silent.

[0118] It should be appreciated that although a single first device 210 is shown in the signaling diagram 200, in some example embodiments, the second device 220 may broadcast network assistance information to a group of first devices in a cell.

[0119] An example embodiment has been described regarding including rules for denoising noisy labels and / or other information. As described above, the rules or LDs may be determined by the second device 220. A detailed example regarding determination of the rules will be described below.

[0120] In the following description, it is assumed that the positioning reference signal (PRS) samples are labeled with the 2D position of the first device 210. If this position estimate is obtained from cellular positioning, the first device 210 can use a RAT-tuned denoiser to correct the raw position estimate. The RAT-tuned denoiser (RAT-denoiser) can be configured by the second device 220 via parameters sent in the LD-configuration.

[0121] In an example embodiment, a rule such as a RAT-denoiser (referred to herein as a first denoiser) receives as input: a position estimate obtained by the first device 210: p = [x, y], and an estimated SINR for each detected PRS, e.g., s = [SINR (PRS 1 ),SINR(PRS 2 ),…].

[0122] By the function {f 1 ,…f N A set of nonlinear operations characterized by} can be performed on the input to produce a corrected label pc = [xc, yc], which is ideally close to the true position pt = [xt, yt]. The RAT-denoiser can be described as performing the operation:

[0123] To implement (1), the first device 210 may receive a set of functions in an LD-configuration: Among them, in (1) represents an instance of a function (k is 1, ..., N). The first device 210 may also receive an operation or function to be applied in the LD-configuration. The order of the functions and information about what inputs are used in each function, e.g., the position estimate p and the estimated SINRs.

[0124] In some example embodiments, the set of functions can be obtained by the second device 220. That is, the RAT-denoiser is generated by the implementation of the second device 220, that is, determining in represents the function f obtained by the second device 220 k (k is 1, ..., N). This determination is implementation specific, but for illustration purposes, consider training a neural network to implement (1) with a cost function that minimizes the Euclidean distance E(pc,pt) between pc and the true label pt. For example, it can be determined by (2)

[0125] In another embodiment, each function f k Can describe the linear displacement of the input, such as f k (p) = a k p+b k , where a similar cost function and PRU measurement are used to determine the coefficient a k ,b k(ie, the PRU known position is used as pt and the PRU estimated position is used as pc).

[0126] Take the example of a vector consisting of {DL departure angle (AoD) φ, LOS indicator g}: v = [φ, g]. The first device 210 can obtain the label v and correct it using a denoiser (referred to as the second denoiser), which can be: using the following inputs: v, s, etc. The second denoiser can apply another set of operations to each input jointly or independently. The second denoiser can output the corrected label v c =[φ c ,g c ], so that v c ->v t , where v t It’s the ideal label.

[0127] For example, the second denoiser can implement two independent corrections f φ ,f g , one for DL ​​AoD, and one for LOS: φ c =f φ (φ,s), g c =f g (g,s), According to the function f φ Rotate the estimated DL AoD and calculate it according to f g , for example: f φ (φ,s)=φ+Δφ(s), the LOS indicator is modified, where the rotation angle is proportional to the SINR level.

[0128] It should be understood that the above equations or parameters are only for illustrative purposes and do not imply any limitation. Any suitable denoising rules or operations will be applied. The scope of the present disclosure is not limited in this regard.

[0129] Several embodiments for determining denoised positioning data based on network assistance information and several embodiments for network assistance information have been described. Through the network assistance information, the cleanliness of the data collected when the first device 210 such as the UE is triggered to collect data is improved. Therefore, whenever any type of positioning session, AI / ML-based positioning session or traditional positioning session is triggered, the positioning accuracy is improved. Therefore, the AI / ML positioning model that was originally trained by the UE vendor and cannot be accessed by the LMF can be updated. In addition, the additional overhead of the use case where the LMF assists the UE in denoising the data set in the UE-side model can be avoided.

[0130] In About Figure 2In the described example embodiment, the network assistance information may be determined by the second device 220 and sent by the second device 220 to the first device 210. In some example embodiments, the network assistance information may alternatively be sent from a third device instead of the second device 220.

[0131] Figure 4 Another signaling diagram 400 for noise localization data processing according to some example embodiments of the present disclosure is shown. The signaling diagram 400 involves a first device 210, a second device 220, and a third device 410.

[0132] In some example embodiments, the first device 210 may refer to or include Figure 1 The second device 220 may refer to or include Figure 1 The third device 410 may refer to or include Figure 1 In the following description, it is assumed that the third device 410 refers to or includes a PRU.

[0133] although Figure 2 A single first device 210, a single second device 220, and a single third device 410 are shown, but it should be understood that there may be multiple devices that perform operations similar to the operations described below with respect to the first device 210 or the second device 220 or the third device 410.

[0134] Note that embodiments of the present disclosure may be applied to any appropriate scenario, such as beam management, positioning accuracy enhancement, or CSI. For illustrative purposes only, example embodiments of the present disclosure are described with reference to the scenario of positioning accuracy enhancement.

[0135] Similar to the signaling diagram 200, the first device 210 obtains (230) measurement data and first positioning data associated with the measurement data. Figure 4 In the example of , the first device 210 may receive (455) network assistance information from the third device 410. The network assistance information may include at least a rule to be used by the first device 210 to generate the second positioning data from the first positioning data. The first device 210 determines (250) the second positioning data from the first positioning data based on the network assistance information.

[0136] In some example embodiments, the second device 220 may send (415) a request to the first device 210 to receive from the third device 410 a rule to be applied to generate the second positioning data from the first positioning data. For example, the second device 220 may send (415) a request to the first device 210 to obtain a "local" rule or LD from a side link (SL). The first device 210 may receive (420) the request.

[0137] Alternatively or additionally, in some example embodiments, the second device 220 may send 425 a request to send rules to the first device to the third device 410. For example, the second device 220 may send 425 a request to share "local" rules or LDs to the third device 410 via a side link. The third device 410 may receive 430 the request.

[0138] In some example embodiments, the third device 410 may utilize 435 a neighboring device via a side link. For example, the third device 410 may utilize 435 the first device 210.

[0139] In some example embodiments, the first device 210 may send (440) a request for a rule to be applied to generate the second positioning data from the first positioning data to the third device 410. The third device 410 may receive (445) the request. In some example embodiments, the first device 210 may send (440) the request for the rule in response to receiving (420) the request from the second device 220.

[0140] In response to receiving (430 / 445) the request, the third device 410 may send (450) network assistance information including the rule to the first device 210. The network assistance information includes the rule. The first device 210 may receive (455) the network assistance information.

[0141] It should be understood that the network assistance information sent (450) by the third device 410 may include one or more rules or LDs. The one or more rules or LDs may not be aware of or related to the positioning technology. The one or more rules may be related to the positioning area and / or type of the first device 210. Figure 2 The details of the (multiple) rules are described and will not be repeated here. One or more rules can be determined by the third device 410. The determination of the one or more rules can be similar to the determination of the (multiple) rules by the second device 220 and will not be repeated here.

[0142] In some example embodiments, the network assistance information may also include information about Figure 2 The further information mentioned. For example, further information such as the applicable conditions of the rule, an indication that the reception of the measurement data and the second positioning data is prioritized, a request for the noise level during the time period in the area, or a threshold level of the noise level can be determined by the third device 410 itself, or alternatively determined by the second device 220 and sent to the third device 410.

[0143] Alternatively, in some example embodiments, the network assistance information sent (450) by the third device 410 may include one or more rules or LDs. Other information may be sent by the second device 220 to the first device 210, such as the applicable conditions of the rules, an indication that the reception of the measurement data and the second positioning data is prioritized, a request for a noise level during a time period within the area, or a threshold level of the noise level.

[0144] In some example embodiments, the first device 210 may send (460) at least the measurement data and the second positioning data to the third device 410. The third device 410 may receive (465) at least the measurement data and the second positioning data from the first device 210. For example, the first device 210 may send (460) the measurement data, the first positioning data, and the second positioning data to the third device 410.

[0145] In other words, the rules or LD can be prepared by the UE (or PRU, since it is a fixed location) and then shared with other neighboring UEs via the sidelink. In this case, a "local" regional denoiser can be prepared and trained. Afterwards, UEs near the PRU can request the "local" denoiser via the sidelink.

[0146] In this way, the accuracy of the positioning data can be improved based on the local area LD. Therefore, AI / ML-based positioning can be enhanced based on the denoised positioning data.

[0147] Several example embodiments have been described for processing noise localization data or noise labels based on network assistance information. In some example embodiments, the network assistance information or rules for processing noise localization data may be implemented in the framework of AI / ML-based localization. Figure 5A An example framework 500 for AI / ML based positioning with noisy positioning data processing according to some example embodiments of the present disclosure is shown. The framework 500 may be implemented at a first device 210, such as device 110 or device 130 or PRU labeled training data.

[0148] In the framework 500, a data collection module 510 is included. The data collection module 510 can be configured to collect measurement data and first positioning data. If incomplete labels are considered in the evaluation, the data collection module 510 can further store the percentage of training data without labels. The defects of the true value labels can be determined.

[0149] The data collection module may also be configured to send the input data 512 to a denoiser 520. The input data 512 may include measurement data and first positioning data. The denoiser 520 may be a module based on network assistance information. For example, the denoiser 520 may generate second positioning data from the first positioning data using one or more rules included in the network assistance information.

[0150] In some example embodiments, the denoiser 520 may be configured to send the training data 522 to the model training module 530. The training data may include the measurement data and the second positioning data, such as the denoised labels. The model training module 530 may be configured to train the AI / ML model for positioning based on the training data 522.

[0151] In this way, training data such as training labels are cleaned before samples are used for training. In this way, AI / ML models can be better trained.

[0152] In some example embodiments, the model training module 530 and the model reasoning module 540 may be integrated in the framework 500. For example, the model training module 530 may deploy or update the model used in the model reasoning module 540. Model performance feedback of the model reasoning module 540 may be fed back to the model training module 530.

[0153] The data collection module 510 can send the inference data 514 to the model inference module 540. The inference data 514 can include the measurement data and the second positioning data. The model inference module 540 can be configured to determine an output 542 based on the inference data 514 by using the trained AI / ML model.

[0154] Output 542 of model reasoning module 540 may be sent to action 550. Action 550 may be configured to perform random access network (RAN) intelligent operations or functions. The scope of the present disclosure is not limited in this regard. Feedback 552 may be sent from action 550 to data collection module 510.

[0155] In this way, network assistance information such as rules or LDs can be used for training functions integrated within the functional framework of RAN intelligence.

[0156] Figure 5BAnother example framework 560 of AI / ML-based positioning with noise positioning data processing according to some example embodiments of the present disclosure is shown. Similar to the framework 500, a data collection module 510 is included in the framework 560. The data collection module 510 can be configured to collect measurement data and first positioning data. The data collection module can also be configured to send input data 562 to the model training module 530. The input data 562 can include measurement data and first positioning data. The model training module 530 can use the input data 562 to train the AI / ML model.

[0157] In some example embodiments, the model training module 530 and the model reasoning module 540 may be integrated in the framework 500. For example, the model training module 530 may deploy or update the model used in the model reasoning module 540. Model performance feedback of the model reasoning module 540 may be fed back to the model training module 530.

[0158] The data collection module 510 can send the inference data 564 to the model inference module 540. The inference data 514 can include the measurement data and the first positioning data. The model inference module 540 can be configured to determine the output 572 based on the inference data 564 by using the trained AI / ML model.

[0159] The output 572 of the model reasoning module 540 may be sent to the denoiser 520. The denoiser 520 may process the output 572 based on network auxiliary information such as rules or LD to determine the output 574. For example, the denoiser 520 may generate the output 574 from the output 572 using one or more rules included in the network auxiliary information. The output 574 may be referred to as an updated output of the model reasoning or a denoised or cleaned output of the model reasoning.

[0160] Output 574 of model reasoning module 540 may be sent to action 550. Feedback 552 may be sent from action 550 to data collection module 510.

[0161] That is, if the model has not been trained on denoised labels, the denoising rules included in the network auxiliary information can also be used in the inference stage. In this way, the model inference results can be improved.

[0162] In some example embodiments, the goal of the denoising rule or LD is to clean the true value label. Similar tasks can be accomplished during a positioning session of real-time radio measurements, especially on UEs in areas with low signal-to-interference-and-noise ratio (SINR) (e.g., edge cells) and when UE conditions (capabilities) enable high computational complexity tasks. In this case, the denoising rule or LD can be fed the positioning method output and it returns the denoised output, which is then reported as usual via the LPP.

[0163] It should be understood that some example specifications and embodiments are provided above, and the detailed description may vary. It should be understood that these signaling diagrams 200 and 400, processes 300, and frameworks 500 and 560 for AI / ML-based positioning can be used in any suitable combination. In this way, the cleanliness of the data collected when the first device 210 is triggered for data collection can be improved. In addition, the positioning accuracy can be improved whenever any type of positioning session, AI / ML-based or traditional positioning session is triggered. The AI / ML positioning model that has been initially trained by the first device 210 and is not accessible to the second device 220 can be updated. The first device 210 can test the effectiveness or performance of the denoiser itself and then select the correct labeling method.

[0164] Figure 6 600 is a flowchart of an example method 600 implemented at a first device according to some example embodiments of the present disclosure. For example, the first device may be implemented as Figure 1 Device 110 or device 130 in.

[0165] At block 610 , a first device acquires measurement data and first positioning data associated with the measurement data.

[0166] At block 620 , the first device generates second positioning data from the first positioning data based on the network assistance information.

[0167] At block 630 , the first device sends at least the measurement data and the second positioning data.

[0168] In some example embodiments, method 600 further includes receiving network assistance information from a second device, the network assistance information including at least one of: a rule to be applied to generate second positioning data from the first positioning data, an application condition of the rule, an indication that reception of the measurement data and the second positioning data is prioritized, and a request for a noise level in an area during a time period.

[0169] In some example embodiments, the method 600 further comprises, in response to receiving the request for the noise level, sending the noise level to the second device.

[0170] In some example embodiments, the method 600 further includes, based on determining that the noise level is greater than or equal to the threshold level, sending the noise level to the second device.

[0171] In some example embodiments, the network assistance information further comprises a threshold level.

[0172] In some example embodiments, the method 600 further comprises: sending a request to a third device for a rule to be applied to generate the second positioning data from the first positioning data; and receiving network assistance information including the rule from the third device in response to sending the request for the rule.

[0173] In some example embodiments, the rule is related to at least one of: a positioning technology, a positioning area, or a type of the first device.

[0174] In some example embodiments, the method 600 further comprises: sending the measurement data, the first positioning data and the second positioning data to the second device.

[0175] Figure 7 FIG. 7 is a flowchart showing an example method 700 implemented at a second device according to some example embodiments of the present disclosure. For example, the second device may be implemented as Figure 1 Device 120 in.

[0176] At block 710 , the second device sends network assistance information to the first device, the network assistance information to be used by the first device to generate second positioning data from first positioning data associated with measurement data.

[0177] At block 720 , the second device receives at least the measurement data and the second positioning data from the first device.

[0178] In some example embodiments, the network assistance information includes at least one of: a rule to be applied to generate the second positioning data from the first positioning data, an application condition of the rule, an indication that reception of the measurement data and the second positioning data is prioritized, and a request for a noise level in the area during a time period.

[0179] In some example embodiments, the method 700 further comprises, in response to sending the request for the noise level, receiving the noise level from the first device.

[0180] In some example embodiments, the network assistance information further includes a threshold level of noise level.

[0181] In some example embodiments, the rule is related to at least one of: a positioning technology, a positioning area, or a type of the first device.

[0182] In some example embodiments, the method 700 further comprises: receiving the measurement data, the first positioning data and the second positioning data from the first device.

[0183] In some example embodiments, the method 700 further includes sending a request to the first device to receive rules from a third device to be applied to generate second positioning data from the first positioning data; and / or sending a request to the third device to send rules to the first device.

[0184] Figure 8 FIG. 8 is a flowchart showing an example method 800 implemented at a third device according to some example embodiments of the present disclosure. For example, the third device may be implemented as Figure 1 Device 110 or device 130 in.

[0185] At block 810 , the third device receives a request from the first device or the second device to send a rule to the first device, the rule to be used by the first device to generate second positioning data from first positioning data associated with measurement data.

[0186] In block 820 , in response to receiving the request, the third device sends network assistance information including the rules to the first device.

[0187] In some example embodiments, the method 800 further comprises: receiving at least the measurement data and the second positioning data from the first device.

[0188] In some example embodiments, any of the methods 600 can be performed (e.g., Figure 1 The first device (device 110 or device 130 in the embodiment of the present invention) may include a component for performing the corresponding operation of method 600. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit or a software module. The first device may be implemented as or included in Figure 1 In device 110 or device 130.

[0189] In some example embodiments, the first device includes: a component for acquiring measurement data and first positioning data associated with the measurement data; a component for generating second positioning data from the first positioning data based on network assistance information; and a component for sending at least the measurement data and the second positioning data.

[0190] In some example embodiments, the first device further comprises: means for receiving network assistance information from the second device. The network assistance information may include at least one of the following: a rule to be applied to generate the second positioning data from the first positioning data, an application condition of the rule, an indication that the reception of the measurement data and the second positioning data is prioritized, and a request for a noise level in an area during a time period.

[0191] In some example embodiments, the first device further comprises means for sending the noise level to the second device in response to receiving the request for the noise level.

[0192] In some example embodiments, the first device further comprises means for sending the noise level to the second device in response to determining that the noise level is greater than or equal to the threshold level.

[0193] In some example embodiments, the network assistance information further comprises a threshold level.

[0194] In some example embodiments, the first device further comprises: means for sending a request to a third device for a rule to be applied to generate the second positioning data from the first positioning data; and means for receiving network assistance information including the rule from the third device in response to sending the request for the rule.

[0195] In some example embodiments, the rule is related to at least one of: a positioning technology, a positioning area, or a type of the first device.

[0196] In some example embodiments, the first device further comprises means for sending the measurement data, the first positioning data and the second positioning data to the second device.

[0197] In some example embodiments, the first apparatus further comprises means for performing other operations in some example embodiments of method 600. In some example embodiments, the apparatus comprises: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause execution of the first apparatus.

[0198] In some example embodiments, any of the methods 700 can be performed (e.g., Figure 1 The second device of the device 120 in the embodiment of the present invention may include a component for performing the corresponding operation of the method 700. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit or a software module. The second device may be implemented as or included in Figure 1 In the device 120.

[0199] In some example embodiments, the second device includes: a component for transmitting network assistance information to the first device, the network assistance information being used by the first device to generate second positioning data from first positioning data associated with the measurement data; and a component for receiving at least the measurement data and the second positioning data from the first device.

[0200] In some example embodiments, the network assistance information includes at least one of: a rule to be applied to generate the second positioning data from the first positioning data, an application condition of the rule, an indication that reception of the measurement data and the second positioning data is prioritized, and a request for a noise level in the area during a time period.

[0201] In some example embodiments, the second device further comprises means for receiving the noise level from the first device in response to sending the request for the noise level.

[0202] In some example embodiments, the network assistance information further includes a threshold level of noise level.

[0203] In some example embodiments, the rule is related to at least one of: a positioning technology, a positioning area, or a type of the first device.

[0204] In some example embodiments, the second device further comprises means for receiving the measurement data, the first positioning data and the second positioning data from the first device.

[0205] In some example embodiments, the second device further comprises: a component for sending a request to the first device to receive rules from a third device to be applied to generate the second positioning data from the first positioning data; and / or a component for sending a request to the third device to send the rules to the first device.

[0206] In some example embodiments, the second apparatus further comprises means for performing other operations in some example embodiments of method 700. In some example embodiments, the apparatus comprises: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause execution of the second apparatus.

[0207] In some example embodiments, any of the methods 800 can be performed (e.g., Figure 1 The third device of the device 110 or the device 130 in the embodiment may include a component for performing the corresponding operation of the method 800. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit or a software module. The third device may be implemented as or included in Figure 1 In device 110 or device 130.

[0208] In some example embodiments, the third device includes: a component for receiving a request from the first device or the second device to send a rule to the first device, wherein the rule is to be used by the first device to generate second positioning data from first positioning data associated with the measurement data; and a component for sending network assistance information including the rule to the first device in response to receiving the request.

[0209] In some example embodiments, the third apparatus further comprises means for receiving at least the measurement data and the second positioning data from the first apparatus.

[0210] In some example embodiments, the third apparatus further comprises means for performing other operations in some example embodiments of method 800. In some example embodiments, the apparatus comprises: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause execution of the third apparatus.

[0211] Fig. 9900 is a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure. The device 900 may be provided to implement a communication device, such as Figure 1 1. The device 110, the device 120 or the device 130 shown in FIG. As shown in the figure, the device 900 includes one or more processors 910, one or more memories 920 coupled to the processor 910, and one or more communication modules 940 coupled to the processor 910.

[0212] The communication module 940 is used for two-way communication. The communication module 940 has one or more communication interfaces to support communication with one or more other modules or devices. The communication interface may represent any interface necessary for communication with other network elements. In some example embodiments, the communication module 940 may include at least one antenna.

[0213] Processor 910 may be of any type suitable for the local technology network, and may include one or more of: 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, as non-limiting examples. Device 900 may have multiple processors, such as application specific integrated circuit chips, which are time-slaved to the clock of a synchronized master processor.

[0214] The memory 920 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) 924, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disk (CD), digital video disk (DVD), optical disk, laser disk, and other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 922 and other volatile memories that do not persist over the duration of a power outage.

[0215] The computer program 930 includes computer executable instructions executed by the associated processor 910. The instructions of the program 930 may include instructions for performing the operations / actions of some example embodiments of the present disclosure. The program 930 may be stored in a memory, such as ROM 924. The processor 910 may perform any suitable actions and processes by loading the program 930 into the RAM 922.

[0216] The exemplary embodiments of the present disclosure may be implemented by means of a program 930, so that the device 900 may execute the Figures 2 to 8 Any process of the present disclosure discussed. The exemplary embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0217] In some example embodiments, the program 930 may be tangibly embodied in a computer-readable medium that may be included in the device 900 (such as in the memory 920) or in other storage devices accessible to the device 900. The device 900 may load the program 930 from the computer-readable medium to the RAM 922 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 of the medium itself (i.e., tangible, not a signal), not a limitation on data storage persistence (e.g., RAM versus ROM).

[0218] Fig.10 An example of a computer readable medium 1000 is shown which may be in the form of a CD, DVD or other optical storage disk. The computer readable medium 1000 has a program 930 stored thereon.

[0219] In general, various embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0220] 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-transient computer-readable medium). The computer program product includes computer executable instructions, such as those included in a program module executed in a device on a target physical or virtual processor to perform any method as described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of the program modules can be combined or split between program modules as needed. Machine executable instructions for program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in both local and remote storage media.

[0221] The program code for executing the method 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 device so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, as an independent software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0222] In the context of the present disclosure, computer program codes or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform various processes and operations as described above. Examples of carriers include signals, computer readable media, etc.

[0223] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or apparatuses, or any suitable combination of the foregoing. More specific examples of computer readable storage media would include an electrical connection with one or more wires, a portable computer floppy disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0224] In addition, although operations are depicted in a particular order, this should not be understood as requiring such operations to be performed in the particular order shown or in sequence, or to perform all of the operations shown, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limitations on the scope of the present disclosure, but as descriptions of features that may be specific to a particular embodiment. Unless explicitly stated, certain features described in the context of a separate embodiment may also be implemented in combination in a single embodiment. On the contrary, unless explicitly stated, the various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0225] Although the disclosure has been described in language specific to structural features and / or methodological acts, it should be understood that the disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A first device for communication, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the first device to: Acquiring measurement data and first positioning data associated with the measurement data; generating second positioning data from the first positioning data based on network assistance information; and At least the measurement data and the second positioning data are sent.

2. The first device according to claim 1, wherein the first device is further configured to: The network assistance information is received from the second device, where the network assistance information includes at least one of the following: rules to be applied to generate said second positioning data from said first positioning data, The conditions under which the rules are applied, an indication that reception of the measurement data and the second positioning data is prioritized, and A request for noise levels in an area during a time period.

3. The first device according to claim 2, wherein the first device is further configured to: In response to receiving the request for the noise level, the noise level is sent to the second device.

4. The first device according to claim 3, wherein the first device is further configured to: Based on determining that the noise level is greater than or equal to a threshold level, the noise level is sent to the second device. The first device of claim 4 , wherein the network assistance information further comprises the threshold level.

6. The first device according to claim 1, wherein the first device is further configured to: sending a request to a third device for a rule to be applied to generate the second positioning data from the first positioning data; and In response to sending the request for the rule, the network assistance information including the rule is received from the third device.

7. The first device according to any one of claims 2 to 6, wherein the rule is related to at least one of the following: Positioning technology, Locate the area, or The type of the first device.

8. The first device according to any one of claims 1 to 7, wherein the first device: The measurement data, the first positioning data and the second positioning data are sent to the second device.

9. A second device for communication, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the second device to: sending network assistance information to a first device, the network assistance information to be used by the first device to generate second positioning data from first positioning data associated with the measurement data; as well as At least the measurement data and the second positioning data are received from the first device.

10. The second device according to claim 9, wherein the second device is further configured to: sending a request to the first device, the request being for receiving rules from a third device to be applied to generate the second positioning data from the first positioning data; and / or A request is sent to the third device to send the rule to the first device.

Images