WO2025166643A1

WO2025166643A1 - Devices, methods and computer readable medium for communication

Info

Publication number: WO2025166643A1
Application number: PCT/CN2024/076745
Authority: WO
Inventors: Zhaobang MIAO; Wei Chen; Zhen He; Peng Guan; Gang Wang
Original assignee: NEC Corp
Current assignee: NEC Corp
Priority date: 2024-02-07
Filing date: 2024-02-07
Publication date: 2025-08-14
Anticipated expiration: 2026-08-07

Abstract

Embodiments of the present disclosure relate to devices, methods and computer readable medium for communication. In one aspect, a device determines a quality indicator for data based on at least one of the following: a first quality indicator for a ground truth label associated with a measurement for positioning a terminal device, or a second quality indicator for the measurement, wherein the data comprises at least one of the following: the ground truth label or the measurement.

Description

DEVICES, METHODS AND COMPUTER READABLE MEDIUM FOR COMMUNICATION

TECHNICAL FIELD

Embodiments of the present disclosure generally relate to the field of telecommunication, and in particular, to devices, methods and computer readable medium for communication.

BACKGROUND

Data collection may be a function that provides input data to a model training function, a model management function, and a model inference function. Regarding data or dataset generation, multiple types of data may be involved. For example, the data may comprise at least one of the following: ideal label data, noisy label data, data with or without a quality indicator, data with or without a ground truth label. Thus, there is a need to address different types of data in a data generation entity, a data collection entity, a model training entity, and a model monitoring entity.

SUMMARY

In general, example embodiments of the present disclosure provide devices, methods and computer readable medium for communication.

In a first aspect, there is provided a device. The device comprises a processor. The processor is configured to cause the device to: determine a quality indicator for data based on at least one of the following: a first quality indicator for a ground truth label associated with a measurement for positioning a terminal device, or a second quality indicator for the measurement, wherein the data comprises at least one of the following: the ground truth label or the measurement.

In a second aspect, there is provided a first device. The first device comprises a processor. The processor is configured to cause the first device to: receive a request for data from a second device; and transmit the data to the second device after generating the data.

In a third aspect, there is provided a second device. The second device comprises a processor. The processor is configured to cause the second device to: transmit a request for data to a first device; receive the data from the first device; and determine multiple sets of data based on types of the received data.

In a fourth aspect, there is provided a method for communication. The method comprises: determining a quality indicator for data based on at least one of the following: a first quality indicator for a ground truth label associated with a measurement for positioning a terminal device, or a second quality indicator for the measurement, wherein the data comprises at least one of the following: the ground truth label or the measurement.

In a fifth aspect, there is provided a method for communication. The method comprises: receiving a request for data from a second device; and transmitting the data to the second device after generating the data.

In a sixth aspect, there is provided a method for communication. The method comprises: transmitting a request for data to a first device; receiving the data from the first device; and determining multiple sets of data based on types of the received data.

In a seventh aspect, there is provided a computer readable medium having instructions stored thereon. The instructions, when executed on at least one processor of a device, cause the device to perform the method according to any of the fourth aspect, the fifth aspect or the sixth aspect.

It is to be understood that the summary section is not intended to identify key or essential features of 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 easily comprehensible through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

Through the more detailed description of some embodiments of the present disclosure in the accompanying drawings, the above and other objects, features and advantages of the present disclosure will become more apparent, wherein:

Fig. 1 illustrate an example communication network in which embodiments of the present disclosure can be implemented;

Fig. 2 illustrate another example communication network in which embodiments of the present disclosure can be implemented;

Fig. 3 illustrates a flowchart of an example method in accordance with some embodiments of the present disclosure;

Fig. 4 illustrates a flowchart of an example method in accordance with some embodiments of the present disclosure;

Fig. 5 illustrates a flowchart of an example method in accordance with some embodiments of the present disclosure; and

Fig. 6 is a simplified block diagram of a device that is suitable for implementing embodiments of the present disclosure.

Throughout the drawings, the same or similar reference numerals represent the same or similar element.

DETAILED DESCRIPTION

Principle of the present disclosure will now be described with reference to some example embodiments. It is to 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 limitations as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below.

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 skills in the art to which this disclosure belongs.

As used herein, the term “terminal device” refers to any device having wireless or wired communication capabilities. Examples of the terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, internet of things (IoT) devices, Ultra-reliable and Low Latency Communications (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, device on vehicle for V2X communication where X means pedestrian, vehicle, or infrastructure/network, devices for Integrated Access and Backhaul (IAB) , Small Data Transmission (SDT) , mobility, Multicast and Broadcast Services (MBS) , positioning, dynamic/flexible duplex in commercial networks, reduced capability (RedCap) , Space borne vehicles or Air borne vehicles in Non-terrestrial networks (NTN) including Satellites and High Altitude Platforms (HAPs) encompassing Unmanned Aircraft Systems (UAS) , eXtended Reality (XR) devices including different types of realities such as Augmented Reality (AR) , Mixed Reality (MR) and Virtual Reality (VR) , the unmanned aerial vehicle (UAV) commonly known as a drone which is an aircraft without any human pilot, devices on high speed train (HST) , or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or Internet appliances enabling wireless or wired Internet access and browsing and the like. The ‘terminal device’ can further has ‘multicast/broadcast’ feature, to support public safety and mission critical, V2X applications, transparent IPv4/IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communications and IoT applications. It may also incorporate one or multiple Subscriber Identity Module (SIM) as known as Multi-SIM. The term “terminal device” can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.

The term “network device” refers to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of a network device include, but not limited to, a Node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNB) , a transmission reception point (TRP) , a remote radio unit (RRU) , a radio head (RH) , a remote radio head (RRH) , an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS) , Network-controlled Repeaters, and the like.

The terminal device or the network device may have Artificial intelligence (AI) or Machine learning capability. It generally includes a model which has been trained from numerous collected data for a specific function, and can be used to infer some target information.

The terminal or the network device may work on several frequency ranges, e.g. FR1 (410 MHz –7125 MHz) , FR2 (24.25GHz to 71GHz) , frequency band larger than 100GHz as well as Tera Hertz (THz) . It can further work on licensed/unlicensed/shared spectrum. The terminal device may have more than one connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.

The network device may have the function of network energy saving, Self-Organizing Networks (SON) /Minimization of Drive Tests (MDT) . The terminal may have the function of power saving.

The embodiments of the present disclosure may be performed in test equipment, e.g. signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator.

The embodiments of the present disclosure may be performed according to any generation communication protocols either currently known or to be developed in the future. Examples of the communication protocols include, but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or the sixth generation (6G) networks.

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. The term ‘includes’ and its variants are to be read as open terms that mean ‘includes, but is not limited to. ’ The term ‘based on’ is to be read as ‘at least in part based on. ’ The term ‘some embodiments’ and ‘an embodiment’ are to be read as ‘at least some embodiments. ’ The term ‘another embodiment’ is to be read as ‘at least one other embodiment. ’ The terms ‘first, ’ ‘second, ’ and the like may refer to different or same objects. Other definitions, explicit and implicit, may be included below.

In some examples, values, procedures, or apparatus are referred to as ‘best, ’ ‘lowest, ’ ‘highest, ’ ‘minimum, ’ ‘maximum, ’ or the like. It will be appreciated that such descriptions are intended to indicate that a selection among many used functional alternatives can be made, and such selections need not be better, smaller, higher, or otherwise preferable to other selections.

As described above, data collection may be a function that provides input data to a model training function, a model management function, and a model inference function. Regarding data or dataset generation, multiple types of data may be involved.

For example, the data collection may provide training data to the model training function. The training data may comprise data needed as input for an artificial intelligence (AI) /machine learning (ML) model training function.

For another example, the data collection may provide monitoring data to the model management function. The monitoring data may comprise data needed as input for the management of AI/ML models or AI/ML functionalities. Model performance monitoring may be one component of model management of AI/ML models or AI/ML functionalities.

For a further example, the data collection may provide inference data to the model inference function. The inference data may comprise data needed as input for the AI/ML inference function.

Regarding data or dataset generation, multiple types of data may be involved. For example, the data may comprise at least one of the following: ideal label data, noisy label data, data with or without a quality indicator, data with or without a ground truth label. In addition to PRU and network device or LMF with known PRU location, a regular terminal device or network device can also generate ground truth label to overcome data shortage.

A quality indicator may be defined for a ground truth label associated with a measurement for positioning the terminal device. Alternatively, a quality indicator may be defined for the measurement. Alternatively, a quality indicator may be defined for the ground truth label and the measurement.

The 3rd Generation Partnership Project (3GPP) evaluation shows that noisy labels along with the corresponding quality can improve positioning performance. Evaluation also shows that unlabeled data can also improve positioning performance along with labelled data in semi-supervised learning.

Thus, there is a need to address different types of data in a data generation entity, a data collection entity, a model training entity, and a model monitoring entity.

In view of the above, embodiments of the present disclosure provide a solution for communication. In this solution, a device determines a quality indicator for data based on at least one of the following: a first quality indicator for a ground truth label associated with a measurement for positioning a terminal device, or a second quality indicator for the measurement, wherein the data comprises at least one of the following: the ground truth label or the measurement. With this solution, a quality indicator for data may be determined. In this way, a data collection entity or a model training entity can evaluate, based on the quality indicator for data, quality per data so as to determine whether or how to use the data.

Hereinafter, principle of the present disclosure will be described with reference to Figs. 1 to 6.

Fig. 1 illustrates a schematic diagram of an example communication network 100 in which embodiments of the present disclosure can be implemented. As shown in Fig. 1, the communication network 100 comprises a terminal device or a positioning reference unit (PRU) 110, a network device 120 and a location server 130.

In some embodiments, the location server 130 may be a physical or logical entity that manages positioning for a target device by obtaining measurements and other location information from one or more positioning units and providing assistance data to positioning units to help determine this. The location server 130 may also compute or verify the final location estimate.

In some embodiments, the location server 130 may comprise one of the following: an Enhanced Serving Mobile Location Centre (E-SMLC) , a Location Management Function (LMF) or Secure User Plane Location (SUPL) Location Platform (SLP) .

In some embodiments, the terminal device or PRU 110 may communicate with the location server 130 based on Long Term Evolution (LTE) Positioning Protocol (LPP) . LPP is used point-to-point between the location server 130 and a target device in order to position the target device using position-related measurements obtained by one or more reference sources. For example, the target device may comprise a UE or SUPL Enabled Terminal (SET) .

In some embodiments, the network device 120 may communicate with the location server 130 based on a New Radio (NR) Positioning Protocol A (NRPPa) . The NRPPa procedure modules are divided into two modules as follows: NRPPa Location Information Transfer Procedures and NRPPa Management Procedures.

The NRPPa Location Information Transfer Procedures module contains procedures used to handle the transfer of positioning related information between NG-RAN Node and LMF. The Management Procedures module contains procedures that are not related specifically to positioning, i.e., error handling.

It is to be understood that the number of network devices and terminal devices is only for the purpose of illustration without suggesting any limitations. The communication network 100 may comprise any suitable number of network devices and terminal devices adapted for implementing embodiments of the present disclosure.

Fig. 2 illustrates a schematic diagram of another example communication network 200 in which embodiments of the present disclosure can be implemented. As shown in Fig. 2, the communication network 200 may comprise a first device 210 and a second device 220.

In some embodiments, the first device 210 may be implemented as a data generation entity and the second device 220 may be implemented as a data collection entity or a model training entity. For example, the first device 210 may be implemented as the terminal device or PRU 110, or the network device 120 in Fig. 1, and the second device 220 may be implemented as the location server 130 in Fig. 1.

Fig. 3 illustrates a flowchart of an example method in accordance with some embodiments of the present disclosure. In some embodiments, the method 300 can be implemented at a device, such as the first device 210 and the second device 220 as shown in Fig. 2. For the purpose of discussion, the method 300 will be described with reference to Fig. 2 by taking the first device 210 as an example of the device.

At block 310, the first device 210 determine a quality indicator for data based on at least one of the following: a first quality indicator for a ground truth label associated with a measurement for positioning a terminal device, or a second quality indicator for the measurement. The data comprises at least one of the following: the ground truth label or the measurement.

As used herein, the term “data” may be used interchangeably with the term “data sample” or “model input” .

As used herein, the term “ground truth label” may be used interchangeably with the term “ground truth” or “label” .

In some embodiments, the data may comprise at least one of the following: data for training in AI/ML based positioning, or data for monitoring in AI/ML based positioning.

In some embodiments, the measurement may at least comprise the measurement for model input. For example, the measurement may at least comprise the measurement for at least one of the following: model training, or model monitoring.

In some embodiments, the model training may refer to a process to train an AI/ML model by learning the input/output relationship in a data driven manner and obtain the trained AI/ML model for inference.

In some embodiments, the model monitoring may be defined as a procedure that monitors performance of an AI/ML model.

In some embodiments, the model inference may refer to a process of using a trained AI/ML model to generate a set of outputs based on a set of inputs.

In some embodiments, a model may be used interchangeably with AI model, ML model, AI or ML model, (AI/ML/auto-) encoder, channel state information (CSI) generation part or UE part/side model, functionality, AI-enabled feature/FG, which means a data driven algorithm that applies AI/ML techniques to generate a set of (AI/ML) outputs based on a set of (AI/ML) inputs.

In some embodiments, the first device 210 may determine the first quality indicator for the ground truth label based on at least one of the following: a location of a data generation entity, or a method for positioning the terminal device.

In some embodiments, if the location of the data generation entity is known in the data generation entity or known in a data collection entity associated with the data generation entity, the first device 210 may determine the first quality indicator for the ground truth label as a first value. For example, the first value may be a first pre-configured or pre-defined value.

In some embodiments, the data generation entity may be a PRU, and the first value may indicate that the ground truth label is accurate or ideal.

Alternatively, in some embodiments, if the location of the data generation entity is unknown in the data generation entity or unknown in a data collection entity associated with the data generation entity, the first device 210 may determine the first quality indicator for the ground truth label based on the method for positioning the terminal device.

In some embodiments, the location of the data generation entity is unknown in the data generation entity or unknown in the data collection entity, but the location can be estimated based on a non-new radio (NR) positioning method and/or an NR positioning method in the data generation entity. In such embodiments, if the location is estimated based on the non-NR positioning method, the first device 210 may determine the first quality indicator for the ground truth label as a second value. For example, the second value may be a second pre-configured or pre-defined value. The second value may indicate that the ground truth label is obtained from the non-NR positioning method.

In some embodiments, the non-NR positioning method may comprise at least one of the following: Global Navigation Satellite System (GNSS) satellite positioning, Wi-Fi positioning, radio frequency identification (RFID) positioning, infrared positioning, ultrasonic technology positioning, Bluetooth technology positioning, inertial navigation positioning, ultra-wideband (UWB) technology positioning, visible light technology positioning, Geomagnetic positioning, visual positioning. For example, the GNSS satellite positioning may comprise one of the following: Global Position System (GPS) positioning, GALILEO positioning, GLONAS positioning, or Beidou positioning.

In some embodiments, if the ground truth label is obtained from the non-NR positioning method, the first device 210 may determine the different values of the first quality indicator for the ground truth label for each of above non-NR positioning methods

Alternatively, if the location of the data generation entity is estimated based on an NR positioning method, the first device 210 may determine the first quality indicator for the ground truth label based on one of the following: a result of positioning the terminal device, or the second quality indicator for the measurement, or a predefined value. The NR positioning method is also referred to as NR Radio Access Technology (RAT) -dependent positioning method.

In some embodiments, if the location of the data generation entity is not obtained in the data generation entity, the first device 210 may determine the first quality indicator for the ground truth label as a third value. The third value may indicate that there is not the ground truth label. For example, the third value may be a third pre-configured or pre-defined value.

Alternatively, in some embodiments, if the location of the data generation entity is not obtained in the data generation entity, the content of the ground truth label can set as “NA” (i.e., no ground truth label is reported) .

In some embodiments, if the data comprises the measurement only (without ground truth label) , the first quality indicator for the ground truth label may be set as a pre-configured or pre-defined value. For example, the first quality indicator for the ground truth label may be set as a value indicating there is no label.

In some embodiments, if the data comprises the measurement only (without ground truth label) , the second quality indicator for the measurement may be set according to measurement result.

In some embodiments, if both the first quality indicator for the ground truth label and the second quality indicator for the measurement are defined or available, the first device 210 may determine the quality indicator for data based on the first quality indicator for the ground truth label and the second quality indicator for the measurement.

In some embodiments, the first device 210 may determine the quality indicator for data as a larger one of the first quality indicator for the ground truth label and the second quality indicator for the measurement.

Alternatively, the first device 210 may determine the quality indicator for data as a smaller one of the first quality indicator for the ground truth label and the second quality indicator for the measurement.

Alternatively, the first device 210 may determine the quality indicator for data as a combination of the first quality indicator for the ground truth label and the second quality indicator for the measurement. Namely, the quality indicator for data is determined based on the first quality indicator for the ground truth label and the second quality indicator for the measurement. For example, the first device 210 may determine the quality indicator for data as a sum of the first quality indicator and the second quality indicator. For another example, the first device 210 may determine the quality indicator for data as a product of the first quality indicator and the second quality indicator. For a further example, the first device 210 may determine the quality indicator for data as an average of the first quality indicator and the second quality indicator.

In some embodiments, a first unit for the first quality indicator for the ground truth label may be different from a second unit for the second quality indicator for the measurement. In such embodiments, the first device 210 may convert the first unit and the second unit to a unit for the quality indicator for data. For example, the first device 210 may convert the first unit and the second unit to unit of metres.

In some embodiments, a first unit for the first quality indicator for the ground truth label and a second unit for the second quality indicator for the measurement may be the same as a unit for the quality indicator for data. For example, the first quality indicator for the ground truth label, the second quality indicator for the measurement and the quality indicator for data are in unit of metres.

In some embodiments, if only the first quality indicator for the ground truth label is defined or available, the first device 210 may determine the quality indicator for data as the first quality indicator for the ground truth label. Alternatively, the first device 210 may determine the quality indicator for data based on the first quality indicator for the ground truth label.

In such embodiments, if a first unit for the first quality indicator for the ground truth label is different from a unit for the quality indicator for data, the first device 210 may convert the first unit to the unit for the quality indicator for data.

In some embodiments, if only the second quality indicator for the measurement is defined or available, the first device 210 may determine the quality indicator for data as the second quality indicator for the measurement. Alternatively, the first device 210 may determine the quality indicator for data based on the second quality indicator for the measurement.

In such embodiments, if a second unit for the second quality indicator for the measurement is different from a unit for the quality indicator for data, the first device 210 may convert the second unit to the unit for the quality indicator for data.

In some embodiments, the first device 210 may determine the quality indicator for data based on the relationship between the measurement and the ground truth label. For example, the first device 210 may determine the quality indicator for data based on the corresponding timestamps of the measurement and the ground truth label.

In some embodiments, each of the first quality indicator for the ground truth label, the second quality indicator for the measurement and the quality indicator for data may comprise at least a quality value and a resolution used in the quality value.

In some embodiments, optionally, the first device 210 may provide the quality indicator for data to the second device 220 at block 320.

With the method 300, a quality indicator for data may be determined. In this way, a data collection entity or a model training entity can evaluate, based on the quality indicator for data, quality per data so as to determine whether or how to use the data.

It shall be understood that although the method 300 has been described by taking the first device 210 as an example, the method 300 may be performed by the second device 220 in a similar way. The scope of the present disclosure is not limited in this regard.

Fig. 4 illustrates a flowchart of an example method in accordance with some embodiments of the present disclosure. In some embodiments, the method 400 can be implemented at a device, such as the first device 210 as shown in Fig. 2. For the purpose of discussion, the method 400 will be described with reference to Fig. 2.

At block 410, the first device 210 receives a request for data from the second device 220.

At block 420, the first device 210 transmits the data to the second device 220 after generating the data.

In some embodiments, the request may indicate a first threshold for a first quality indicator for a ground truth label. The ground truth label is associated with a measurement for positioning a terminal device. In such embodiments, the first device 210 may transmit the measurement and the ground truth label to the second device 220. In this way, the understanding of requested data between the first device 210 and the second device 220 may be aligned.

In some embodiments, the request may indicate a second threshold for a second quality indicator for a measurement for positioning a terminal device. In some embodiments, the first device 210 may transmit the measurement with the ground truth label to the second device 220. Alternatively, the first device 210 may transmit the measurement without the ground truth label to the second device 220. In this way, the understanding of requested data between the first device 210 and the second device 220 may be aligned.

In some embodiments, the request may indicate a threshold for a quality indicator for data and the request may indicate to request the data with the ground truth label. In such embodiments, the first device 210 may transmit the data the measurement with the ground truth label to the second device 220. In this way, the understanding of requested data between the first device 210 and the second device 220 may be aligned.

Alternatively, in some embodiments, the request may indicate a threshold for a quality indicator for data and the request may indicate to request the data without the ground truth label. In such embodiments, the first device 210 may transmit the measurement without the ground truth label the second device 220. In this way, the understanding of requested data between the first device 210 and the second device 220 may be aligned.

In some embodiments, the request may indicate a first threshold for the first quality indicator for the ground truth label and a second threshold for the second quality indicator for the measurement for positioning a terminal device. In such embodiments, the first device 210 may transmit the measurement and the ground truth label. In this way, the understanding of requested data between the first device 210 and the second device 220 may be aligned.

In some embodiments, the request may indicate a threshold for a quality indicator for data. The first device 210 may transmit a first set of data and a second set of data to the second device 220. The first set of data comprises data whose quality indicators satisfy the threshold (e.g., higher quality than the threshold or quality indicators above the threshold) . The second set of data comprises data whose quality indicator can not satisfy the threshold (e.g., lower quality than the threshold) and the data has no quality indicator information. Such embodiments may avoid the case that the collected data samples are not enough in the second device 220 (such as a data collection entity) .

In some embodiments, the request may indicate a threshold for a quality indicator for data and a first number of samples of the data. If a second number of samples of the data with quality indicators above the threshold exceeds the first number, the first device 210 may transmit the first number of samples of the data to the second device 220.

In some embodiments, the request may indicate a threshold for a quality indicator for data and a first number of samples of the data. If a second number of samples of the data with quality indicators above the threshold is below the first number, the first device 210 may transmit the second number of samples of the data and a third number of samples of the data to the second device 220. The third number is equal to a difference between the first number and the second number. The third number of samples of the data are selected in a decreasing order of the quality indicators if it is assumed that a higher quality indicator means higher quality. Alternatively, the third number of samples of the data are selected in an increasing order of the quality indicators if it is assumed that a lower quality indicator means higher quality. Such embodiments may avoid the case that the collected data samples are not enough in the second device 220 (such as a data collection entity) .

In some embodiments, the first device 210 may transmit multiple sets of data to the second device 220. Each of the multiple sets comprises data with a quality indicator above one of multiple thresholds. For example, the multiple sets of data may comprise a data set #1, a data set #2, …, a data set #m. Quality indicators for data in the data set #1 may be above threshold #1, quality indicators for data in the data set #2 may be above threshold #2 and below threshold #1, …, quality indicators for data in the data set #m may be above threshold #m and below threshold #n, where threshold #m is a lowest quality threshold satisfying requirement configuration of the second device 220 (such as a data collection entity) . Such embodiments may avoid the case that the collected data samples are not enough in the second device 220 (such as a data collection entity) .

In some embodiments, for data collection from various entities, for example, from entities in different cells, the threshold configuration should be determined and signaled from the location server 130.

It shall be noted that the method 400 may be performed in combination with the method 300.

Fig. 5 illustrates a flowchart of an example method in accordance with some embodiments of the present disclosure. In some embodiments, the method 500 can be implemented at a device, such as the second device 220 as shown in Fig. 2. For the purpose of discussion, the method 500 will be described with reference to Fig. 2.

At block 510, the second device 220 transmits a request for data to the first device 210.

At block 520, the second device 220 receives the data from the first device 210.

In some embodiments, the data received from the first device 210 may comprise all of data generated by the first device 210.

At block 530, the second device 220 determines multiple sets of data based on types of the received data.

With the method 500, the case that the collected data samples are not enough in the second device 220 (such as a data collection entity) may be avoided.

In some embodiments, the multiple sets of data may comprise a first set of data. At least one first quality indicator for the data in the first set is above a threshold.

Additionally or alternatively, in some embodiments, the multiple sets of data may comprise a second set of data. At least one second quality indicator for the data in the second set is below the threshold.

Additionally or alternatively, in some embodiments, the multiple sets of data may comprise a third set of data without quality information.

Additionally or alternatively, in some embodiments, the multiple sets of data may comprise a fourth set of data without a ground truth label. The ground truth label is associated with a measurement for positioning a terminal device.

Additionally or alternatively, in some embodiments, the multiple sets of data may comprise a fifth set of data which comprises all of data generated by the first device 210.

In some embodiments, the second device 220 may determine a quality indicator for one of the multiple sets of data based on quality indicators for the data in a respective one of the multiple sets of data. In such embodiments, the second device 220 may determine a data set level quality indicator for each of the multiple sets of data.

In some embodiments, the second device 220 may uses above different sets of data based on different model life cycle management (LCM) related requirements, data set level quality requirement or use a subset of each of the above sets based on data set level quality requirement and quality requirement of each data sample. For example, the subset of each of the above sets may comprise data for model training with different training type, model monitoring, and so on.

Fig. 6 is a simplified block diagram of a device 600 that is suitable for implementing embodiments of the present disclosure. The device 600 can be considered as a further example embodiment of the first device 210 or the second device 220 as shown in Fig. 2. Accordingly, the device 600 can be implemented at or as at least a part of the first device 210 or the second device 220.

As shown, the device 600 includes a processor 610, a memory 620 coupled to the processor 610, a suitable transceiver 640 coupled to the processor 610, and a communication interface coupled to the transceiver 640. The memory 610 stores at least a part of a program 630. The transceiver 640 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 640 may include at least one of a transmitter 642 and a receiver 644. The transmitter 642 and the receiver 644 may be functional modules or physical entities. The transceiver 640 has at least one antenna to facilitate communication, though in practice an Access Node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2/Xn interface for bidirectional communications between eNBs/gNBs, S1/NG interface for communication between a Mobility Management Entity (MME) /Access and Mobility Management Function (AMF) /SGW/UPF and the eNB/gNB, Un interface for communication between the eNB/gNB and a relay node (RN) , or Uu interface for communication between the eNB/gNB and a terminal device.

The components included in the apparatuses and/or devices of the present disclosure may be implemented in various manners, including software, hardware, firmware, or any combination thereof. In one embodiment, one or more units may be implemented using software and/or firmware, for example, machine-executable instructions stored on the storage medium. In addition to or instead of machine-executable instructions, parts or all of the units in the apparatuses and/or devices may be implemented, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs) , Application-specific Integrated Circuits (ASICs) , Application-specific Standard Products (ASSPs) , System-on-a-chip systems (SOCs) , Complex Programmable Logic Devices (CPLDs) , and the like.

Claims

A device, comprising:

a processor configured to cause the device to:

determine a quality indicator for data based on at least one of the following:

a first quality indicator for a ground truth label associated with a measurement for positioning a terminal device, or

a second quality indicator for the measurement, wherein the data comprises at least one of the following: the ground truth label or the measurement.
The device of claim 1, wherein the device is further caused to:

determine the first quality indicator for the ground truth label based on at least one of the following:

a location of a data generation entity, or

a method for positioning the terminal device.
The device of claim 2, wherein the device is caused to determine the first quality indicator for the ground truth label by:

based on determining that the location is known in the data generation entity or known in a data collection entity associated with the data generation entity, determining the first quality indicator for the ground truth label as a first value.
The device of claim 2, wherein the device is caused to determine the first quality indicator for the ground truth label by:

based on determining that the location is unknown in the data generation entity or unknown in a data collection entity associated with the data generation entity, determining the first quality indicator for the ground truth label based on the method for positioning the terminal device.
The device of claim 4, wherein the device is caused to determine the first quality indicator for the ground truth label based on the method for positioning the terminal device by:

based on determining that the location is estimated based on a non-new radio (NR) positioning method, determining the first quality indicator for the ground truth label as a second value.
The device of claim 4, wherein the device is caused to determine the first quality indicator for the ground truth label based on the method for positioning the terminal device by:

based on determining that the location is estimated based on an NR positioning method, determining the first quality indicator for the ground truth label based on one of the following:

a result of positioning the terminal device, or

the second quality indicator for the measurement.
The device of claim 2, wherein the device is caused to determine the first quality indicator for the ground truth label by:

based on determining that the location is not obtained in the data generation entity, determining the first quality indicator for the ground truth label as a third value.
The device of claim 1, wherein the device is caused to determine the quality indicator for data as one of the following:

a larger one of the first quality indicator for the ground truth label and the second quality indicator for the measurement,

a smaller one of the first quality indicator for the ground truth label and the second quality indicator for the measurement, or

a combination of the first quality indicator for the ground truth label and the second quality indicator for the measurement.
The device of claim 1, wherein a first unit for the first quality indicator for the ground truth label is different from a second unit for the second quality indicator for the measurement; and

the device is further caused to:

convert the first unit and the second unit to a unit for the quality indicator for data.
The device of claim 1, wherein the first quality indicator for the ground truth label, the second quality indicator for the measurement and the quality indicator for data are in unit of metres.
A first device, comprising:

a processor configured to cause the first device to:

receive a request for data from a second device; and

transmit the data to the second device after generating the data.
The first device of claim 11, wherein the request indicates a first threshold for a first quality indicator for a ground truth label, the ground truth label is associated with a measurement for positioning a terminal device;

wherein the first device is caused to transmit the data by:

transmitting the measurement and the ground truth label.
The first device of claim 11, wherein the request indicates a second threshold for a second quality indicator for a measurement for positioning a terminal device;

wherein the first device is caused to transmit the data by:

transmitting the measurement with the ground truth label; or

transmitting the measurement without the ground truth label.
The first device of claim 11, wherein the request indicates a threshold for a quality indicator for data and the request indicates to request the data with or without a ground truth label, the ground truth label is associated with a measurement for positioning a terminal device;

wherein the first device is caused to transmit the data by:

transmitting the measurement with the ground truth label, or

transmitting the measurement without the ground truth label.
The first device of claim 11, wherein the request indicates a first threshold for a first quality indicator for a ground truth label and a second threshold for a second quality indicator for a measurement for positioning a terminal device, the ground truth label is associated with the measurement;

wherein the first device is caused to transmit the data by:

transmitting the measurement and the ground truth label.
The first device of claim 11, wherein the request indicates a threshold for a quality indicator for data; and

wherein the first device is caused to transmit the data by transmitting the following:

a first set of data, wherein the first set of data comprises data whose quality indicators satisfy the threshold; and

a second set of data, wherein comprises data whose quality indicator can not satisfy the threshold or the second set of data has no quality information.
The first device of claim 11, wherein the request indicates a threshold for a quality indicator for data and a first number of samples of the data;

wherein the first device is caused to transmit the data by:

based on determining that a second number of samples of the data with quality indicators above the threshold exceeds the first number, transmitting the first number of samples of the data.
The first device of claim 11, wherein the request indicates a threshold for a quality indicator for data and a first number of samples of the data;

wherein the first device is caused to transmit the data by:

based on determining that a second number of samples of the data with quality indicators above the threshold is below the first number, transmitting the second number of samples of the data and a third number of samples of the data, wherein the third number is equal to a difference between the first number and the second number, and the third number of samples of the data are selected in a decreasing order of the quality indicators.
The first device of claim 11, wherein the first device is caused to transmit the data by:

transmitting multiple sets of data, wherein each of the multiple sets comprises data with a quality indicator above one of multiple thresholds.
A second device, comprising:

a processor configured to cause the second device to:

transmit a request for data to a first device;

receive the data from the first device; and

determine multiple sets of data based on types of the received data.
The second device of claim 20, wherein the multiple sets of data comprises at least one of the following:

a first set of data, wherein at least one first quality indicator for the data in the first set is above a threshold;

a second set of data, wherein at least one second quality indicator for the data in the second set is below the threshold;

a third set of data without quality information;

a fourth set of data without a ground truth label, wherein the ground truth label is associated with a measurement for positioning a terminal device; or

a fifth set of data which comprises all of data generated by the first device.
The second device of claim 20, wherein the second device is further caused to:

determine a quality indicator for one of the multiple sets of data based on quality indicators for the data in a respective one of the multiple sets of data.