Data enhancement for machine learning training in positioning

Abstract

Example embodiments of the present disclosure relate to data enhancement for training models. In this solution, a first device receives a configuration for data enhancement from a second device. The first device determines a set of data enhancement parameters based on the configuration. The first device trains a model based on data obtained based on a set of data enhancement parameters. In this manner, it increases the amount of quality training data and enables robust model training. In addition, it may assess the integrity of the enhanced dataset by using the probability value for each data point or data segment.

Description

Technical Field

[0001] Various example embodiments of the present disclosure relate generally to the field of telecommunications, and more particularly to methods, devices, apparatuses, and computer-readable storage media for data enhancement for machine learning training in positioning. Background Art

[0002] In the telecommunications industry, techniques have been proposed to improve the performance of telecommunications systems. For example, artificial intelligence / machine learning (AI / ML) models have been employed in telecommunications systems to improve the performance of telecommunications systems. Therefore, it is worthwhile to study the training of AI / ML models employed in telecommunications systems. Summary of the invention

[0003] In a first aspect of the present disclosure, a first device is provided. The first device includes at least one processor; and at least one memory storing instructions, which, when executed by the at least one processor, causes the first device to at least perform: receiving a data enhancement configuration for training a positioning model at the first device from a second device; determining a set of data enhancement parameters based on the data enhancement configuration; obtaining data based on a data enhancement process and a set of data enhancement parameters, the data including measurement data and enhancement data of the first device; and training a positioning model based on a combination of the measurement data and the enhancement 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 storing instructions, which, when executed by the at least one processor, causes the second device to at least perform: receiving radio measurements from at least one third device; determining a configuration of data enhancement for training a positioning model at the first device based on the measurements from the at least one third device; and sending the configuration of the data enhancement to the first device.

[0005] In a third aspect of the present disclosure, a first device is provided. The first device includes: at least one processor; and at least one memory storing instructions, which, when executed by the at least one processor, causes the first device to at least perform: sending an auxiliary request for data enhancement to a second device; receiving enhanced data for training a positioning model from the second device; and training the positioning model based on a combination of the enhanced data and the measurement data.

[0006] In a fourth aspect of the present disclosure, a second device is provided. The second device includes: at least one processor; and at least one memory storing instructions, which, when executed by the at least one processor, causes the second device to at least perform: receiving an auxiliary request for data enhancement from a first device; obtaining measurement data from a third device; generating enhanced data for training a positioning model at the first device based on the measurement data; and sending the enhanced data to the first device.

[0007] In a fifth aspect of the present disclosure, a method is provided. The method includes: receiving a configuration of data enhancement for training a positioning model at a first device from a second device; determining a set of data enhancement parameters based on the configuration of the data enhancement; obtaining data based on the data enhancement process and the set of data enhancement parameters, the data including measurement data and enhancement data of the first device; and training the positioning model based on a combination of the measurement data and the enhancement data.

[0008] In a sixth aspect of the present disclosure, a method is provided. The method includes: receiving radio measurements from at least one third device; determining a configuration of data enhancement for training a positioning model at a first device based on the measurements from the at least one third device; and sending the configuration of data enhancement to the first device.

[0009] In a seventh aspect of the present disclosure, a method is provided, comprising: sending an auxiliary request for data enhancement to a second device; receiving enhancement data for training a positioning model from the second device; and training the positioning model based on a combination of the enhancement data and measurement data.

[0010] In an eighth aspect of the present disclosure, a method is provided, comprising: receiving an auxiliary request for data enhancement from a first device; obtaining measurement data from a third device; generating enhancement data for training a positioning model at the first device based on the measurement data; and sending the enhancement data to the first device.

[0011] In a ninth aspect of the present disclosure, a device is provided. The device includes: a component for receiving a configuration of data enhancement for training a positioning model at a first device from a second device; a component for determining a set of data enhancement parameters based on the configuration of the data enhancement; a component for obtaining data based on a data enhancement process and a set of data enhancement parameters, the data including measurement data and enhancement data of the first device; and a component for training a positioning model based on a combination of the measurement data and the enhancement data.

[0012] In a tenth aspect of the present disclosure, an apparatus is provided. The apparatus includes: a component for receiving radio measurements from at least one third device; a component for determining a configuration of data enhancement for training a positioning model at a first device based on the measurements from the at least one third device; and a component for sending the configuration of the data enhancement to the first device.

[0013] In an eleventh aspect of the present disclosure, a device is provided. The device includes: a component for sending an auxiliary request for data enhancement to a second device; a component for receiving enhanced data for training a positioning model from the second device; and a component for training a positioning model based on a combination of the enhanced data and measurement data.

[0014] In a twelfth aspect of the present disclosure, a device is provided. The device includes: a component for receiving an auxiliary request for data enhancement from a first device; a component for obtaining measurement data from a third device; a component for determining enhancement data for training a positioning model at the first device based on the measurement data; and a component for sending the enhancement data to the first device.

[0015] In a thirteenth 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 at least execute a method according to any one of the fifth aspect, the sixth aspect, the seventh aspect, or the eighth aspect.

[0016] 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

[0017] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0018] Figure 1 An example communication environment is shown in which example embodiments of the present disclosure may be implemented;

[0019] Figure 2 A schematic diagram showing data collection according to some example embodiments of the present disclosure;

[0020] Figure 3 A schematic diagram showing a structure for model training with data augmentation according to some example embodiments of the present disclosure;

[0021] Figure 4 shows a signaling diagram for communication according to some example embodiments of the present disclosure;

[0022] Figure 5 A schematic diagram illustrating additional measurements during a measurement request according to some example embodiments of the present disclosure;

[0023] Fig. 6A and Figure 6B shows a signaling diagram for communication according to some example embodiments of the present disclosure;

[0024] Figure 7 shows a signaling diagram for communication according to some example embodiments of the present disclosure;

[0025] Figure 8 A flowchart showing a method according to some example embodiments of the present disclosure is shown;

[0026] Fig. 9 A flowchart showing a method according to some example embodiments of the present disclosure is shown;

[0027] Fig.10 A flowchart showing a method according to some example embodiments of the present disclosure is shown;

[0028] Fig.11 A flowchart showing a method according to some example embodiments of the present disclosure is shown;

[0029] Fig.12 shows a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure; and

[0030] Fig.13 A block diagram of an example computer-readable medium is shown according to some example embodiments of the present disclosure.

[0031] Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. DETAILED DESCRIPTION

[0032] The principles of the present disclosure will now be described with reference to some example embodiments. It should be understood that these embodiments are described only for the purpose of illustration, and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation to the scope of the present disclosure. In addition to the manner described below, the embodiments described herein can be implemented in various ways.

[0033] 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.

[0034] 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 to be within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0035] It should be understood that although the terms "first", "second", etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, without departing from the scope of the exemplary embodiments, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0036] As used herein, “at least one of: ” and “at least one of ” and similar expressions (wherein a list of two or more elements is connected by “and” or “or”) refer to at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0037] As used herein, unless explicitly stated, performing a step “in response to A” does not mean performing the step immediately after “A” occurs, but may include one or more intermediate steps.

[0038] The terms used herein are used only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that when used herein, the terms "comprises", "comprising", "has", "having", "includes", and / or "including" specify the presence of stated features, elements, and / or parts, etc., but do not exclude the presence or addition of one or more other features, elements, parts, and / or combinations thereof.

[0039] As used in this application, the term "circuitry" may refer to one or more or all of the following: (a) hardware circuit implementations only (such as implementations in analog and / or digital circuitry only) and (b) a combination of hardware circuitry and software, such as (if applicable): (i) a combination of analog and / or digital hardware circuitry and software / firmware, and (ii) any portion of a hardware processor with software (including a digital signal processor, software and memory that work together to enable a device such as a mobile phone or server to perform various functions); and (c) A hardware circuit and / or processor, such as a microprocessor or portion of a microprocessor, that requires software (e.g., firmware) for operation, but in which the software may not be present when not required for operation.

[0040] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further 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. For example and if applicable to the particular claim element, the term circuitry also covers 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.

[0041] As used herein, the term "communication network" refers to a network that follows 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 of communication protocols, 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 protocols and / or any other protocols 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 are of course future types of communication technologies and systems that can implement the present disclosure. It should not be considered that the scope of the present disclosure is limited to the above-mentioned system.

[0042] As used herein, the term "network 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), for example, a NodeB (NodeB or NB), an evolved NodeB (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 repeater, 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) at an IAB donor node. An IAB node includes a mobile terminal (IAB-MT) portion that behaves like a UE toward a parent node, and a DU portion of an IAB node behaves like a base station toward a next-hop IAB node.

[0043] The term "terminal device" refers to any terminal device capable of wireless communication. As an example and not limitation, the terminal device may also be referred to as a communication device, a user equipment (UE), a subscriber station (SS), a portable subscriber 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 local 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 mounted device (LME), a USB dongle, a smart device, a wireless customer premises equipment (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 industrial and / or automatic processing chain environments), consumer electronic devices, equipment 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.

[0044] 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 (e.g., communication between a terminal device and a network device), such as a resource in the time domain, a resource in the frequency domain, a resource in the spatial domain, a resource in the code domain, or any other resource that enables communication. In the following, unless explicitly stated, resources in the frequency domain and the time domain will be used as examples of transmission resources for describing 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.

[0045] As mentioned above, AI / ML can be used in communication systems. For example, AI / ML can be used to enhance positioning accuracy. In addition, discussions related to data collection for training have focused on whether data can be collected from the entire simulation area or from a set of grids located within the simulation area. The basic assumption seems to be that positioning data is readily available within the system. However, this assumption is only valid for simulation settings and is not applicable to real-world settings where a limited amount of data will be available.

[0046] Assuming that a supervised AI / ML model is running on the UE side, AI / ML training may require a certain amount (usually a large amount) of labeled data to be able to run AI / ML inference with a certain accuracy. It may take a long time for a single UE to collect all the necessary data. In this case, the network can support the UE by sending additional labeled data. However, this comes at the cost of additional signaling.

[0047] Supervised learning is an important technique for extracting value from big data. However, the effectiveness of supervised learning requires a large amount of high-quality training data. In many cases, the training data is not sufficient to effectively train a supervised learning classifier. Data augmentation is a widely adopted method for increasing the amount of training data. But the quality of the augmented data can be problematic and depends on the use case.

[0048] With the large-scale deployment of 5G cellular infrastructure, traffic prediction has become an indispensable part of cellular resource management systems in order to provide reliable and fast communication services that can meet the growing quality of service requirements. A promising approach to deal with this problem is to introduce intelligent methods to use AI / ML models to achieve highly effective and efficient radio resource management processes. At the same time, the integration of multi-access edge computing frameworks in 5G cellular networks promotes the application of intelligent traffic prediction models by implementing them at the edge of the network. However, data shortages and privacy issues may still be obstacles to training robust and accurate prediction models at the edge. Therefore, training AI / ML models adopted in telecommunication systems is worthy of study. Example Environment

[0049] 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, 110-3, ..., and 110-N, which may be collectively referred to as "devices 110". Communication environment also includes devices 120 and 130. Devices 110, 120, and 130 may communicate with each other.

[0050] 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.

[0051] It should be understood that Figure 1The number of devices and their connections shown in are for illustrative purposes only and do not imply any limitation. Communication environment 100 may include any suitable number of devices configured to implement the example embodiments of the present disclosure. Although not shown, it will be understood that one or more additional devices may be located in a cell of device 130, and one or more additional cells may be deployed in communication environment 100. Note that although shown as a network device, device 130 may be a device other than a network device. Although shown as a terminal device, device 110 may be a device other than a terminal device.

[0052] In the following, for the purpose of illustration, some example embodiments are described, and the device 110 operates as a terminal device and the 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.

[0053] 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).

[0054] 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. Working principles and example signaling for communication

[0055] According to some example embodiments of the present disclosure, a solution for data enhancement for training AI / ML models is provided. In this solution, a first device receives a configuration for data enhancement from a second device. The first device determines a set of data enhancement parameters based on the configuration. The first device trains the model based on a combination of measured data and enhanced data obtained based on the set of data enhancement parameters. In this way, it increases the amount of quality training data and enables robust model training. In addition, it can evaluate the integrity of the enhanced data set by using the probability value of each data point or data segment.

[0056] Figure 2 Schematic diagram showing example data collection according to some example embodiments of the present disclosure. Device 110-1 can collect a set of measurements. For example, device 110-1 can obtain Figure 2 Measurement data 210 is shown. The size of the collected data may not be sufficient to perform AI / ML model training. In this case, data augmentation can be applied. The term "data augmentation" as used herein may refer to a method for increasing the amount of data within a region of interest (ROI). In addition, spatial interpolation techniques may be applied in order to derive additional samples, which means radio measurements for missing position estimates. In this case, device 110-1 may use data augmentation to obtain enhanced data 220 for the missing positions. In addition, the efficiency of this data augmentation method depends on the tuning of the spatial interpolation function: this involves the appropriate selection of parameters that can be performed with the assistance of the network. In this way, the amount of data including measurement data 210 and enhanced data 220 is sufficient to train the model.

[0057] Figure 3 A schematic diagram of an example structure 300 for model training using data augmentation according to some example embodiments of the present disclosure is shown. The structure 300 can be Figure 1 The device 110 shown is implemented. Figure 3 As shown, in some example embodiments, after performing data augmentation using spatial interpolation to reach a target data size, the labeling dataset module 310 can add an indication to indicate whether the data is interpolated or measured so that the AI / ML model training can additionally consider this information. In addition, the spatial interpolation method can provide a level of data augmentation and a probability value for each predicted value or each enhanced segment of the associated data. The value can, for example, indicate the likelihood that the augmented data is equally or less accurate than the measured data. In this way, the AI / ML model can prioritize measured / real data when minimizing training errors compared to interpolated or augmented data.

[0058] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0059] Reference now Figure 4, which shows a signaling diagram of an interaction 400 according to some example embodiments of the present disclosure. Figure 4 As shown, the signaling diagram shows the interaction 400 between device 410, device 420 and device 430. For the purpose of discussion, reference is made to Figure 1 To describe the signaling diagram 200. For example, the device 410 may refer to or include Figure 1 The device 110-1 shown in FIG. 1 and the device 430 may refer to or include Figure 1 Device 420 may refer to or include Figure 1 1. Note that devices 410, 420, and 430 may refer to or include any suitable devices.

[0060] Device 410 may report its capabilities to device 420. For example, the capabilities may include one or more supported models of device 410. Alternatively or in addition, the capabilities may include memory resources of device 410. In some other example embodiments, the capabilities may include computing capabilities of device 410. The capabilities may include computing resources at device 410. In some example embodiments, the capabilities may be reported via Long Term Positioning Protocol (LPP) messages.

[0061] In some example embodiments, device 410 may proactively initiate a request for data collection (e.g., layer 1 (L1) measurements) in order to train a model at device 410. For example, device 410 may send 4005 an assistance request for data enhancement to device 420. In some example embodiments, the assistance request may indicate a ratio of available data relative to a target data size used in training a positioning model. The term "positioning model" as used herein may refer to a processing model or an AIML model for positioning a device. In some example embodiments, the assistance request may be sent along with the capabilities of device 410. For example, the assistance request and the reported capabilities may be in an LPP message.

[0062] In some example embodiments, the assistance request may include an indication of the current percentage of available data relative to the target data size for model training. By way of example only, if the assistance request may indicate 75%, the device 420 may understand that 75% of the target data size has been collected and 25% of the target data size still needs to be collected, meaning that 25% of the data needs to be interpolated to reach the target data size for training. In this way, measurement collection and model training may be accelerated.

[0063] Alternatively, the assistance request may not include an indication of the current percentage of available data. In this case, device 420 may determine the required percentage of data required by device 410. In some example embodiments, device 420 may determine the required data based on feedback received at device 420 regarding data enhancement performance. Alternatively, the required data may be determined without feedback.

[0064] In some example embodiments, if device 410 newly joins the network of device 420, device 410 may send an assistance request to device 420. Alternatively, if device 410 determines that the current data set does not enable model training with the required accuracy, device 410 may send an assistance request to device 420. In this case, in some example embodiments, the required accuracy may be based on a positioning accuracy key performance indicator (KPI). Alternatively or in addition, the required accuracy may be based on one or more intermediate KPIs associated with an intermediate model for line of sight (LOS) or non-LOS (NLOS) classification. In some other example embodiments, the required accuracy may be based on the positioning delay of device 410.

[0065] One or more devices may send their radio measurements to device 420. Figure 4 As shown, device 430 sends 4010 the radio measurement of device 430 to device 420. One or more devices may be within the area specified by device 410. For example, device 430 may be within the surrounding area of ​​device 410. In other words, device 430 may be a neighbor UE of device 410.

[0066] In some example embodiments, the radio measurements may indicate a reference signal received power (RSRP) measured by device 430. Alternatively or in addition, the radio measurements may indicate channel state information. In some other example embodiments, the radio measurements may indicate a channel response, such as a channel impulse response (CIR). Alternatively or in addition, the radio measurements may indicate one or more of: angle of arrival (AoA), angle of departure (AoD), time difference of arrival (TDoA), or round trip time (RTT).

[0067] The device 420 determines 4015 a configuration of data augmentation for training a positioning model based on the radio measurements. In some example embodiments, the device 420 may determine a set of data augmentation parameters based on the radio measurements. For example, the best list of data augmentation parameters may be estimated using radio measurements or feedback from other devices. By way of example only, the set of data augmentation parameters may include one or more parameters associated with an interpolation function for predicting data.

[0068] Device 420 sends 4020 a configuration of data enhancement to device 410. In some example embodiments, the configuration may include a set of data enhancement parameters determined by device 420. Alternatively, the configuration may include radio measurements from device 430. For example, if device 420 determines that device 430 is located in a surrounding area of ​​device 410 based on the rough location of device 410, the configuration of data enhancement may include radio measurements from device 430. By way of example only, Figure 5 As shown, neighbor measurement data 530 from device 430 may be provided to device 410. In some other example embodiments, the configuration of data augmentation may include an indication of whether the data used to train the positioning model is interpolated or measured. The configuration of data augmentation may also indicate the dimension (e.g., time or space) of the data used to train the positioning model.

[0069] In some example embodiments, device 430 may send 4025 the radio measurements directly to device 410. For example, the radio measurements may be sent via a sidelink between device 410 and device 430.

[0070] In some example embodiments, the device 420 may proactively send the data enhancement configuration. In other words, the transmission of the data enhancement configuration may not be based on an assistance request.

[0071] In some example embodiments, the configuration of the data enhancement may be sent aperiodically. Fig. 6A 600 according to some example embodiments of the present disclosure. Fig. 6A As shown, the signaling diagram illustrates an interaction 600 between device 410 and device 420. Device 420 may monitor 6010 the performance at device 410. If device 420 detects or observes a degradation in the performance of device 410, device 420 may refine 6020 or update a set of data enhancement parameters. For example, if device 420 observes a high system position uncertainty of device 410, device 420 may refine the set of data enhancement parameters. Device 420 may send 6030 a configuration of data enhancement to device 410. In this case, the configuration of data enhancement may further indicate a validity period of the configuration of data enhancement. For example, the new parameterization may be accompanied by a validity period, i.e., a maximum duration for which device 420 considers the configuration valid. This may be expressed as the number of subframes for which the configuration is valid, starting from the time the message is received on the device 410 side.

[0072] In some example embodiments, the configuration of the data enhancement may be sent periodically. Figure 6B 601 according to some example embodiments of the present disclosure. Figure 6BAs shown, the signaling diagram illustrates an interaction 601 between device 410 and device 420. Device 420 may refine 6120 or update a set of data enhancement parameters. Device 420 may send 6130 a configuration of data enhancement to device 410. In this case, the data enhancement configuration may further indicate a validity period for the configuration of data enhancement. For example, the new parameterization may be accompanied by a validity period, i.e., a maximum duration for which the configuration is considered valid by device 420. This may be expressed as a number of subframes for which the configuration is valid, starting from the time the message is received on the device 410 side.

[0073] Return to reference Figure 4 , the device 410 determines 4030 a set of data enhancement parameters based on the configuration of data enhancement. For example, in some example embodiments, if the configuration of data enhancement includes the set of data enhancement parameters, the device 410 may extract the set of data enhancement parameters from the configuration of data enhancement.

[0074] Alternatively, if the configuration of data enhancement includes radio measurements from device 430, device 410 may determine a set of data enhancement parameters based on the radio measurements of device 430. For example, device 410 may adjust a set of data enhancement parameters based on the radio measurements. In some example embodiments, the set of data enhancement parameters (e.g., spatial interpolation parameters) may be adjusted by minimizing an error between the interpolated data and the data reported from device 430.

[0075] In some example embodiments, as described above, the radio measurements may be sent via a sidelink between devices 410 and 430. In this case, device 410 may determine a set of data enhancement parameters based on the radio measurements from device 430.

[0076] The device 410 obtains 4035 data for training the positioning model based on a data enhancement procedure and a set of data enhancement parameters. In other words, the device 410 can perform data enhancement using the configuration of the data enhancement from the device 420. For example, the device 410 can select a kriging procedure as the data enhancement procedure. Note that the data enhancement procedure can be any appropriate procedure that can increase the amount of data used for training. The data for training the positioning model includes the measurement data of the device 410 and the enhanced data generated based on a set of data enhancement parameters. Alternatively, the data for training the positioning model may also include radio measurement data from the device 430. For example, as Figure 5 As shown, data used to train a positioning pattern may include measurement data 510, enhancement data 520, and radio measurement data 530. Enhancement data 520 may be estimated for locations not measured by device 410. In this way, the amount of quality training data has been increased.

[0077] The device 410 trains 4040 a positioning model based on a combination of measured data and enhanced data. For example, the combination of measured data and enhanced data may indicate that data at a certain location is measured and data at another certain location is interpolated (i.e., enhanced). In some example embodiments, the combination of measured data and enhanced data may be based on their weights. For example, measured data may have a higher weight than enhanced data. In this way, it enables robust model training. In addition, it enables the method to evaluate the integrity of the enhanced data set by using probability values ​​for each data point or data segment. For example, in the case of predicting only large data segments, then based on the associated probability values, the position estimate may not be used for critical applications.

[0078] As just an example of spatial interpolation, Kriging, a spatial interpolation technique, may be used. Kriging assumes that missing values ​​can be estimated using weighted linear combinations of available neighboring values. The calculation of Kriging weights may be based on the relationship between observed values ​​represented by a spatial autocovariance function.

[0079] In some example embodiments, device 410 may send 4045 feedback information indicating current data enhancement performance to device 420. For example, the feedback information may indicate an interpolation accuracy achieved at device 410. In this case, device 420 may update 4050 a configuration of data enhancement based on the feedback information. For example, device 420 may increase an area for collecting radio measurements of neighbor devices. For example only, if the achieved interpolation accuracy indicated in the feedback information is below a threshold, device 420 may increase an area for collecting radio measurements.

[0080] According to an exemplary embodiment of the present disclosure, a method and a program are proposed, which target data enhancement for AI / ML-based positioning of AI / ML reasoning running on the UE side. For example, it proposes a method that allows increasing the amount of original labeled data: radio measurements and corresponding geographic locations. Additional signaling can ensure efficient data enhancement operations at the UE with network assistance. Regarding data enhancement methods, the case of supervised learning methods running on the UE side can be considered: estimating useful features to estimate its positioning, such as LOS / NLOS classification, or directly estimating its positioning.

[0081] Reference now Figure 7 , which shows a signaling diagram of an interaction 700 according to some example embodiments of the present disclosure. Figure 7 As shown, the signaling diagram shows an interaction 700 between a device 710, a device 720, and a device 730. For the purpose of discussion, reference is made to Figure 1 To describe the signaling diagram 700. For example, the device 710 may refer to or include Figure 1 The device 110-1 shown in FIG. 1 and the device 730 may refer to or include Figure 1 Device 110-2 or device 130 shown in FIG. Device 720 may refer to or include Figure 1 1. Note that devices 710, 720, and 730 may refer to or include any suitable devices.

[0082] Device 710 may report its capabilities to device 720. For example, the capabilities may include one or more supported models of device 710. Alternatively or in addition, the capabilities may include memory resources of device 710. In some other example embodiments, the capabilities may include computing capabilities of device 710. The capabilities may include computing resources at device 710. In some example embodiments, the capabilities may be reported via Long Term Positioning Protocol (LPP) messages.

[0083] In some example embodiments, the device 710 may proactively initiate a request for data collection (e.g., layer 1 (L1) measurements) in order to train a model at the device 710. For example, the device 710 may send 7005 an assistance request for data enhancement to the device 720. In some example embodiments, the assistance request may indicate a ratio of available data relative to a target data size used when training a positioning model. The term "positioning model" as used herein may be substituted for a processing model or an AIML model of a positioning device. In some example embodiments, the assistance request may be sent along with the capabilities of the device 710. For example, the assistance request and the reported capabilities may be in an LPP message.

[0084] In some example embodiments, the assistance request may include an indication of the current percentage of available data relative to the target data size for model training. By way of example only, if the assistance request may indicate 75%, the device 720 may understand that 75% of the target data size has been collected and 25% of the target data size still needs to be collected. In this way, measurement collection and model training may be accelerated.

[0085] Alternatively, the assistance request may not include an indication of the current percentage of available data. In this case, device 720 may determine the required percentage of data required by device 410 based on feedback received at device 720 regarding data enhancement performance.

[0086] In some example embodiments, if device 710 newly joins the network of device 720, device 710 may send an assistance request to device 720. Alternatively, if device 710 determines that the current data set does not enable model training with the required accuracy, device 710 may send an assistance request to device 720. In this case, in some example embodiments, the required accuracy may be based on a positioning accuracy key performance indicator (KPI). Alternatively or in addition, the required accuracy may be based on one or more intermediate KPIs associated with an intermediate model for line of sight (LOS) or non-LOS (NLOS) classification. In some other example embodiments, the required accuracy may be based on the positioning latency of device 410.

[0087] One or more devices may send their radio measurements to device 720. Figure 7 As shown, device 730 sends 7010 radio measurements of device 730 to device 720. In some example embodiments, device 430 may be in a surrounding area of ​​device 410. In other words, device 430 may be a neighbor UE of device 410. In some example embodiments, the radio measurements may indicate a reference signal received power (RSRP) measured by device 730. Alternatively or in addition, the radio measurements may indicate channel state information. In some other example embodiments, the radio measurements may indicate a channel response, such as a channel impulse response (CIR). Alternatively or in addition, the radio measurements may indicate one or more of: angle of arrival (AoA), angle of departure (AoD), time difference of arrival (TDoA), or round trip time (RTT).

[0088] Alternatively, device 730 may be a network device associated with device 710. In this case, data collection is performed by network devices (i.e., device 730) participating in the positioning process of device 710 (i.e., serving gNB and neighboring gNBs). The gNB may specifically collect measurements of UL sounding reference signal (SRS) (or UL SRS for positioning-SRS-P) signals sent by device 710 when device 710 is at a specified location. The gNB may then provide such measurements to device 720, and another device (e.g., device 110-2) may provide the location at which the SRS was sent to device 730. In this manner, it may be applied to DL positioning, UL positioning, and UL plus DL positioning.

[0089] The device 720 determines 7015 data for training the positioning model based on the radio measurements. In other words, the device 720 can perform data enhancement. For example, the device 720 can select a kriging procedure as a data enhancement procedure. Note that the data enhancement procedure can be any suitable procedure that can increase the amount of data used for training. The data for training the positioning model includes the measurement data and the enhancement data of the device 730. Alternatively, the data for training the positioning model can also include radio measurement data from the device 730.

[0090] The device 720 sends 7020 the data to the device 710 for training the positioning model. For example, the data may be sent in an LPP message.

[0091] The device 710 trains 7025 a positioning model based on a combination of measured data and enhanced data. For example, the combination of measured data and enhanced data may indicate that data at a certain location is measured and data at another certain location is interpolated (i.e., enhanced). In some example embodiments, the combination of measured data and enhanced data may be based on their weights. For example, measured data may have a higher weight than enhanced data. In this way, it enables robust model training. In addition, it enables the method to evaluate the integrity of the enhanced data set by using probability values ​​for each data point or data segment. For example, in the case of predicting only large data segments, then based on the associated probability values, the position estimate may not be used for critical applications. Example Methods

[0092] Figure 8 FIG. 8 is a flowchart of an example method 800 implemented at or performed by a first device according to some example embodiments of the present disclosure. For discussion purposes, Figure 1 Method 800 is described from the perspective of device 110 in FIG.

[0093] At block 810, the first device receives a configuration of data augmentation for training a positioning model at the first device from the second device. In some example embodiments, the first device may send an auxiliary request for data augmentation to the second device. For example, the auxiliary request may also indicate a ratio of available data relative to a target data size used when training the positioning model. In some example embodiments, the configuration of data augmentation may include an indication of whether the data used to train the positioning model is interpolated or measured.

[0094] At block 820, the first device determines a set of data enhancement parameters based on the configuration of data enhancement. In some example embodiments, the configuration of data enhancement may include a set of data enhancement parameters based on radio measurements of the third device. In this case, the first device may extract a set of data enhancement parameters from the configuration of data enhancement.

[0095] Alternatively, the configuration of the data enhancement may include radio measurements of the third device. In this case, the first device may determine a set of data enhancement parameters based on the radio measurements of the third device.

[0096] In other example embodiments, the first device may receive radio measurements of the third device via a sidelink between the first device and the third device. In this case, the first device may determine a set of data enhancement parameters based on the radio measurements of the third device.

[0097] At block 830, the first device obtains data based on a data enhancement process and a set of data enhancement parameters. The data includes measurement data and enhanced data of the first device.

[0098] At box 840, the first device trains a positioning model based on a combination of measured data and enhanced data. For example, the combination of measured data and enhanced data may indicate that data at a certain location is measured and data at another certain location is interpolated (i.e., enhanced). In some example embodiments, the combination of measured data and enhanced data may be based on their weights. For example, measured data may have a higher weight than enhanced data. In this way, it enables robust model training. In some example embodiments, the first device may send feedback information indicating the current data enhancement performance at the first device to the second device.

[0099] Fig. 9 FIG. 9 is a flowchart of an example method 900 implemented at or performed by a second device according to some example embodiments of the present disclosure. For discussion purposes, Figure 1 Method 900 is described from the perspective of device 120 in FIG.

[0100] At block 910 , the second device receives radio measurements from a third device.

[0101] At block 920, the second device determines a configuration of data augmentation for training a positioning model at the first device based on measurements from the third apparatus. In some example embodiments, the configuration of data augmentation may also indicate a validity period of the configuration of data augmentation.

[0102] At block 930, the second device sends a configuration of data enhancement to the first device. In some example embodiments, the second device may determine a set of data enhancement parameters based on radio measurements. In this case, the configuration of data enhancement may include a set of data enhancement parameters. Alternatively, the configuration of data enhancement may include radio measurements of a third device.

[0103] In some example embodiments, the second device may receive an auxiliary request for data enhancement from the first device. For example, the auxiliary request may also indicate a ratio of available data relative to a target data size used when training the positioning model.

[0104] In some example embodiments, the second device may monitor the performance of the first device. In this case, if performance degradation of the first device is detected, the second device may send a configuration of data enhancement to the first device. Alternatively, the second device may periodically send a configuration of data enhancement.

[0105] In some example embodiments, the second device may receive feedback information from the first device indicating current data enhancement performance at the first device. In this case, the second device may update the configuration of the data enhancement based on the feedback information.

[0106] Fig.10 FIG. 1 is a flowchart of an example method 1000 implemented at or performed by a first device according to some example embodiments of the present disclosure. For discussion purposes, Figure 1 Method 1000 is described from the perspective of device 110 in FIG.

[0107] At block 1010, the first device sends an assistance request for data augmentation to the second device. In some example embodiments, the assistance request may also indicate a ratio of available data relative to a target data size used in training the positioning model.

[0108] At block 1020 , the first device receives augmentation data from the second device for training a positioning model.

[0109] At box 1030, the first device trains a positioning model based on a combination of enhanced data and measured data. For example, the combination of measured data and enhanced data may indicate that data at a certain location is measured and data at another certain location is interpolated (i.e., enhanced). In some example embodiments, the combination of measured data and enhanced data may be based on their weights. For example, measured data may have a higher weight than enhanced data. In a device manner, it enables robust model training.

[0110] Fig.11 FIG. 1 is a flowchart of an example method 1100 implemented at or performed by a second device according to some example embodiments of the present disclosure. For discussion purposes, Figure 1 Method 1100 is described from the perspective of device 120 in FIG.

[0111] At block 1110, the second device receives an assistance request for data augmentation from the first device. In some example embodiments, the assistance request may also indicate a ratio of available data relative to a target data size used in training the positioning model.

[0112] At block 1120, the second device obtains measurement data from the third device. In some example embodiments, the measurement data may include at least one of: uplink measurement data or downlink measurement data.

[0113] At block 1130 , the second device produces enhancement data for training a positioning model at the first device based on the measurement data.

[0114] At block 1140 , the second device sends the enhancement data to the first device. Example devices, equipment, and media

[0115] In some example embodiments, any of the methods 800 can be performed (e.g., Figure 1 The first device of the device 110 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.

[0116] In some example embodiments, a first device includes: a component for receiving a configuration of data enhancement for training a positioning model at a first device from a second device; a component for determining a set of data enhancement parameters based on the configuration of the data enhancement; a component for obtaining data based on a data enhancement process and a set of data enhancement parameters, the data including measurement data and enhancement data of the first device; and a component for training a positioning model based on a combination of the measurement data and the enhancement data.

[0117] In some example embodiments, the first apparatus comprises means for sending an assistance request for data enhancement to the second device.

[0118] In some example embodiments, the assistance request also indicates a ratio of available data relative to the target data size used in training the localization model.

[0119] In some example embodiments, the configuration of data augmentation includes a set of data augmentation parameters based on radio measurements of the third device. In some example embodiments, the means for determining the set of data augmentation parameters includes means for extracting the set of data augmentation parameters from the configuration of data augmentation.

[0120] In some example embodiments, the configuration of the data augmentation includes radio measurements of the third device.

[0121] In some example embodiments, the means for determining a set of data enhancement parameters comprises means for determining the set of data enhancement parameters based on radio measurements of the third device.

[0122] In some example embodiments, the first apparatus comprises: means for receiving radio measurements of the third device from the third device via a sidelink between the first device and the third device; and means for determining a set of data enhancement parameters based on the radio measurements of the third device.

[0123] In some example embodiments, the configuration of data augmentation includes an indication of whether data used to train the positioning model is interpolated or measured.

[0124] In some example embodiments, the first apparatus comprises means for sending feedback information indicative of current data enhancement capabilities at the first device to the second device.

[0125] In some example embodiments, the first device comprises a terminal device and the second device comprises a network device.

[0126] In some example embodiments, any of the methods 900 can be performed (e.g., Figure 1 The second device of the device 120 in the embodiment may include components for performing the corresponding operations of the method 900. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit or a software module.

[0127] In some example embodiments, the second apparatus includes: a component for receiving radio measurements from a third device; a component for determining a configuration of data augmentation for training a positioning model at the first device based on the measurements from the third device; and a component for sending the configuration of data augmentation to the first device.

[0128] In some example embodiments, the second apparatus comprises: means for determining a set of data enhancement parameters based on radio measurements; and means for sending a configuration of data enhancement including the set of data enhancement parameters to the first device.

[0129] In some example embodiments, the configuration of the data augmentation includes radio measurements of the third device.

[0130] In some example embodiments, the second apparatus comprises means for receiving an assistance request for data enhancement from the first device.

[0131] In some example embodiments, the assistance request also indicates a ratio of available data relative to the target data size used in training the localization model.

[0132] In some example embodiments, the means for sending the configuration of data enhancement includes: means for monitoring performance of the first device; and means for sending the configuration of data enhancement to the first device based on determining that performance degradation of the first device is detected.

[0133] In some example embodiments, means for sending the configuration of data augmentation includes means for periodically sending the configuration of data augmentation.

[0134] In some example embodiments, the configuration of the data enhancement further indicates a validity period of the configuration of the data enhancement.

[0135] In some example embodiments, the second apparatus includes: means for receiving feedback information from the first device indicating current data enhancement performance at the first device; and means for updating a configuration of data enhancement based on the feedback information.

[0136] In some example embodiments, the first device comprises a terminal device, the second device comprises a network device, and the third device comprises another terminal device.

[0137] In some example embodiments, any of the methods 1000 can be performed (e.g., Figure 1 The first device of the apparatus 110 in the method 1000 may include components for performing corresponding operations of the method 1000. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit or a software module.

[0138] In some example embodiments, the first apparatus includes: a component for sending an auxiliary request for data enhancement to the second device; a component for receiving enhancement data for training a positioning model from the second device; and a component for training the positioning model based on a combination of the enhancement data and the measurement data.

[0139] In some example embodiments, the assistance request also indicates a ratio of available data relative to the target data size used in training the localization model.

[0140] In some example embodiments, the first device comprises a terminal device and the second device comprises a network device.

[0141] In some example embodiments, any of the methods 1100 can be performed (e.g., Figure 1 The second device of the device 120 in the embodiment may include components for performing the corresponding operations of the method 1100. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit or a software module.

[0142] In some example embodiments, the second apparatus includes: a component for receiving an auxiliary request for data enhancement from the first device; a component for obtaining measurement data from a third device; a component for generating enhancement data for training a positioning model at the first device based on the measurement data; and a component for sending the enhancement data to the first device.

[0143] In some example embodiments, the assistance request also indicates a ratio of available data relative to the target data size used in training the localization model.

[0144] In some example embodiments, the measurement data includes at least one of the following: uplink measurement data or downlink measurement data.

[0145] In some example embodiments, the first device comprises a terminal device, the second device comprises a network device, and the third device comprises another terminal device or another network device.

[0146] Fig.12 1 is a simplified block diagram of a device 1200 suitable for implementing an example embodiment of the present disclosure. The device 1200 may be provided to implement a communication device, such as Figure 1 The device 110 or device 120 shown in FIG. As shown in the figure, the device 1200 includes one or more processors 1210, one or more memories 1220 coupled to the processor 1210, and one or more communication modules 1240 coupled to the processor 1210.

[0147] The communication module 1240 is used for two-way communication. The communication module 1240 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface may represent any interface necessary to communicate with other network elements. In some example embodiments, the communication module 1240 may include at least one antenna.

[0148] As non-limiting examples, processor 1210 may be of any type suitable for a local technology network, and may include one or more of the following: 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. Device 1200 may have multiple processors, such as application specific integrated circuit chips that are time slaved to a clock synchronized with a main processor.

[0149] The memory 1220 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) 1224, 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 devices. Examples of volatile memories include, but are not limited to, random access memory (RAM) 1222 and other volatile memories that will not persist for the duration of a power outage.

[0150] The computer program 1230 includes computer executable instructions executed by the associated processor 1210. The instructions of the program 1230 may include instructions for performing the operations / actions of some example embodiments of the present disclosure. The program 1230 may be stored in a memory (e.g., ROM 1224). The processor 1210 may perform any suitable actions and processes by loading the program 1230 into the RAM 1222.

[0151] The exemplary embodiments of the present disclosure may be implemented by means of the program 1230, so that the device 1200 may execute the Figures 4 to 11 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.

[0152] In some example embodiments, the program 1230 may be tangibly embodied in a computer-readable medium that may be included in the device 1200 (such as in the memory 1220) or in other storage devices accessible to the device 1200. The device 1200 may load the program 1230 from the computer-readable medium to the RAM 1222 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).

[0153] Fig.13 An example of a computer readable medium 1300 is shown, which may be in the form of a CD, DVD, or other optical storage disk. The computer readable medium 1300 has the program 1230 stored thereon.

[0154] Generally, 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 illustrated and described as block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the blocks, 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.

[0155] 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-volatile computer-readable medium). The computer program product includes computer executable instructions, such as those included in a program module that are 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. The functionality of the program modules can be combined or split between program modules as needed in various embodiments. The machine executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0156] 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 causes the realization of the functions / operations specified in the flow chart and / or block diagram when executed by the processor or controller. 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.

[0157] 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.

[0158] 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, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or apparatus, 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 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.

[0159] In addition, although the operations are depicted in a specific order, this should not be understood as requiring the specific order shown or in a sequential order to perform these operations, or to perform all the operations shown, to achieve the desired result. In some cases, multitasking and parallel processing can 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 should be interpreted as descriptions of features that may be specific to a specific 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.

[0160] 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, 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 at least perform: receiving, from a second device, a configuration for data augmentation for training a positioning model at the first device; Determining a set of data enhancement parameters based on the configuration of the data enhancement; Obtaining data based on the data enhancement process and the set of data enhancement parameters, the data comprising measurement data and enhanced data of the first device; as well as The positioning model is trained based on a combination of the measurement data and the augmentation data.

2. The first device according to claim 1, wherein the first device is caused to execute: An assistance request for the data enhancement is sent to the second device. 3 . The first device of claim 2 , wherein the assistance request further indicates a ratio of available data relative to a target data size used in training the positioning model.

4. The first device according to any one of claims 1-3, wherein the configuration of the data enhancement comprises the set of data enhancement parameters based on radio measurements of the third device; and Determining the set of data enhancement parameters includes: The set of data augmentation parameters is extracted from the data augmentation configuration.

5. The first device according to any one of claims 1-3, wherein the configuration of the data enhancement comprises radio measurements of a third device.

6. The first device of claim 5, wherein determining the set of data augmentation parameters comprises: The set of data enhancement parameters is determined based on the radio measurements of the third device.

7. The first device according to any one of claims 1 to 6, wherein the first device is further caused to execute: receiving, from a third device via a sidelink between the first device and the third device, radio measurements of the third device; and The set of data enhancement parameters is determined based on the radio measurements of the third device.

8. The first device according to any one of claims 1 to 7, wherein the configuration of the data enhancement comprises: An indication of whether the data used to train the positioning model is interpolated or measured.

9. The first device according to any one of claims 1 to 8, wherein the first device is further caused to execute: Feedback information indicating current data enhancement performance at the first device is sent to a second device.

10. The first device according to any one of claims 1-9, wherein the first device comprises a terminal device, and the second device comprises a network device.

11. A second device, 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 at least perform: receiving radio measurements from a third device; determining, based on the measurements from the third device, a configuration for data augmentation for training a positioning model at the first device; as well as The configuration of the data enhancement is sent to the first device.

12. The second device according to claim 11, wherein the second device is further caused to execute: determining a set of data enhancement parameters based on the radio measurements; and Sending a configuration of the data enhancement including the set of data enhancement parameters to the first device.

13. The second device according to any one of claims 11-12, wherein the configuration of the data enhancement comprises the radio measurements of the third device.

14. The second device according to any one of claims 11 to 13, wherein the second device is caused to execute: An assistance request for the data enhancement is received from the first device. 15 . The second device of claim 14 , wherein the assistance request further indicates a ratio of available data relative to a target data size used in training the positioning model.

16. The second device according to any one of claims 11-13, wherein sending the data enhancement configuration comprises: monitoring performance of the first device; as well as Based on determining that performance degradation of the first device is detected, the configuration of the data enhancement is sent to the first device.

17. The second device according to any one of claims 11 to 13, wherein sending the data enhancement configuration comprises: The data enhancement configuration is sent periodically. 18 . The second device according to claim 16 , wherein the data enhancement configuration further indicates a validity period of the data enhancement configuration.

19. The second device according to any one of claims 11 to 18, wherein the second device is further caused to execute: receiving, from the first device, feedback information indicating current data enhancement performance at the first device; and The configuration of the data enhancement is updated based on the feedback information.

20. The second device according to any one of claims 11-19, wherein the first device comprises a terminal device, the second device comprises a network device, and the third device comprises another terminal device.

21. A first device, 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 at least perform: sending an auxiliary request for data enhancement to a second device; receiving, from the second device, augmented data for training a positioning model; and The positioning model is trained based on a combination of the augmented data and the measurement data.

22. The first device of claim 21, wherein the assistance request further indicates a ratio of available data relative to a target data size used in training the positioning model.

23. The first device according to any one of claims 21-22, wherein the first device comprises a terminal device, and the second device comprises a network device.

24. A second device, 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 at least perform: receiving an auxiliary request for data enhancement from a first device; obtaining measurement data from a third device; Based on the measurement data, generating enhancement data for training a positioning model at the first device; as well as The enhanced data is sent to the first device.

25. The second device of claim 24, wherein the assistance request further indicates a ratio of available data relative to a target data size used in training the positioning model.

26. The second device according to claim 24 or 25, wherein the measurement data comprises at least one of the following: uplink measurement data or downlink measurement data.

27. The second device according to any one of claims 24-26, wherein the first device comprises a terminal device, the second device comprises a network device, and the third device comprises another terminal device or another network device.

28. A method comprising: At a first device, receiving from a second device a configuration for data augmentation for training a positioning model at the first device; Based on the configuration of the data enhancement, determining a set of data enhancement parameters; Obtaining data based on the data enhancement process and the set of data enhancement parameters, the data comprising measurement data and enhanced data of the first device; as well as The positioning model is trained based on a combination of the measurement data and the augmentation data.

29. A method comprising: At the second device, receiving radio measurements from a third device; determining, based on the measurements from the third device, a configuration for data augmentation for training a positioning model at the first device; as well as The data enhanced configuration is sent to the first device.

30. A method comprising: At the first device, sending an auxiliary request for data enhancement to the second device; receiving, from the second device, augmented data for training a positioning model; as well as The positioning model is trained based on a combination of the augmented data and the measurement data.

31. A method comprising: receiving an auxiliary request for data enhancement from a first device; obtaining measurement data from a third device; determining, based on the measurement data, augmentation data for training a positioning model at the first device; as well as The enhanced data is sent to the first device.

32. An apparatus comprising: means for receiving, from a second device, a configuration for data augmentation for training a positioning model at the first device; means for determining a set of data augmentation parameters based on the configuration of the data augmentation; means for obtaining data based on a data enhancement process and the set of data enhancement parameters, the data comprising measurement data and enhanced data of the first device; as well as Means for training the positioning model based on a combination of the measurement data and the augmentation data.

33. An apparatus comprising: means for receiving radio measurements from a third device; means for determining a configuration of data augmentation for training a positioning model at said first device based on said measurements from said third device; as well as Means for sending the configuration of data enhancement to the first device.

34. An apparatus comprising: means for sending an auxiliary request for data enhancement to a second device; means for receiving, from the second device, augmentation data for training a positioning model; as well as Means for training the positioning model based on a combination of the augmented data and the measurement data.

35. An apparatus comprising: means for receiving an auxiliary request for data enhancement from a first device; means for obtaining measurement data from a third device; means for determining, based on the measurement data, augmentation data for training a positioning model at the first device; as well as Means for sending the enhancement data to the first device.

36. A computer-readable medium comprising instructions stored thereon, the instructions being configured to cause a first device to at least perform: receiving, from a second device, a configuration for data augmentation for training a positioning model at the first device; Determining a set of data enhancement parameters based on the configuration of the data enhancement; obtaining data based on a data enhancement procedure and the set of data enhancement parameters, the data comprising measurement data and enhanced data of the first device; as well as A positioning model is trained based on a combination of the measurement data and the augmentation data.

37. A computer-readable medium comprising instructions stored thereon, the instructions being configured to cause a second device to at least perform: receiving radio measurements from a third device; determining a configuration of data augmentation for training a positioning model at the first device based on the measurements from the third device; and The configuration of the data enhancement is sent to the first device.

38. A computer-readable medium comprising instructions stored thereon, the instructions being configured to cause a first device to at least perform: sending an auxiliary request for data enhancement to a second device; receiving, from the second device, augmented data for training a positioning model; and The positioning model is trained based on a combination of the augmented data and the measurement data.

39. A computer-readable medium comprising instructions stored thereon, the instructions being configured to cause a second device to at least perform: receiving an auxiliary request for data enhancement from a first device; obtaining measurement data from a third device; generating, based on the measurement data, augmentation data for training a positioning model at the first device; and The enhanced data is sent to the first device.

Images