EP4721486A1

EP4721486A1 - Devices, methods, and medium for communication

Info

Publication number: EP4721486A1
Application number: EP23938960.4A
Authority: EP
Inventors: Wei Chen; Peng Guan; Zhen He; Gang Wang
Original assignee: NEC Corp
Current assignee: NEC Corp
Priority date: 2023-06-01
Filing date: 2023-06-01
Publication date: 2026-04-08
Also published as: WO2024243973A1

Abstract

Example embodiments of the present disclosure relate to devices, methods, and computer storage medium for communication. A first device may obtain multiple input data items and multiple ground truth label data items of an AI/ML positioning model. In some examples, the multiple input data items and multiple ground truth label data items are collected by different entities. The first device may further determine a match between at least one of the multiple input data items and at least one of the multiple ground truth label data items, to determine at least one matched instance. As such, the instance for model training and/or monitoring may be determined based on the multiple input data items and the multiple ground truth label data items collected by different entities. Therefore, the instances may be further used for model training and/or monitoring for positioning.

Description

DEVICES, METHODS, AND MEDIUM FOR COMMUNICATION

FIELD

Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to devices, methods, and a computer readable medium for communication.

BACKGROUND

Supporting various positioning methods to provide reliable, timely and accurate user equipment (UE) location has always been one of the key features of the third generation partnership project (3GPP) standard. It has been agreed to investigate the potential for artificial intelligence (AI) /ML in air interface to improve comprehensive performance in 5G-adcanced. AI/ML based mechanism to improve the positioning accuracy is one of the use cases to apply AI/ML in air interface in release 18 (Rel-18 or R18) .
The process of collecting data for model training and monitoring is a crucial step in supporting AI/ML-based positioning. The input and label of this data may come from different entities. A significant challenge that needs to be addressed is how to effectively match these inputs and labels from different sources as instances.

SUMMARY

In general, example embodiments of the present disclosure provide devices, methods, and a computer storage medium for communication.
In a first aspect, there is provided a first device. The first device comprises at least one processor configured to cause the first device at least to: obtain a plurality of input data items of an AI or ML positioning model; obtain a plurality of ground truth label data items of the AI or ML positioning model; and determine a match between at least one of the plurality of input data items and at least one of the plurality of ground truth label data items, to obtain at least one matched instance.
In a second aspect, there is provided a terminal device. The terminal device comprises at least one processor configured to cause the terminal device at least to: determine a plurality of input data items of an AI or ML positioning model; and transmit, to a location management function (LMF) , an indication of a time segment set of the plurality of input data items.
In a third aspect, there is provided a network device. The network device comprises at least one processor configured to cause the network device at least to: determine a plurality of input data items or a plurality of ground truth label data items of an AI or ML positioning model; and transmit, to a terminal device or a further network device, the plurality of input data items or the plurality of ground truth label data items.
In a fourth aspect, there is provided an LMF. The LMF comprises at least one processor configured to cause the LMF at least to: receive, from a terminal device, an indication of a time segment set of a plurality of input data items of an AI or ML positioning model; and transmit, to the terminal device, information comprising a plurality of ground truth label data items associated with the plurality of time segments; wherein the plurality of input data items comprise a plurality of channel impulse response (CIR) , power delay profile (PDP) , or delay of path (DP) items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In a fifth aspect, there is provided a method of communication. The method comprises: obtaining, at a first device, a plurality of input data items of an AI or ML positioning model; obtaining a plurality of ground truth label data items of the AI or ML positioning model; and determining a match between at least one of the plurality of input data items and at least one of the plurality of ground truth label data items, to obtain at least one matched instance.
In a sixth aspect, there is provided a method of communication. The method comprises: determining, at a terminal device, a plurality of input data items of an AI or ML positioning model; and transmitting, to an LMF, an indication of a time segment set of time segments of the plurality of input data items.
In a seventh aspect, there is provided a method of communication. The method comprises: determining, at a network device, a plurality of input data items or a plurality of ground truth label data items of an AI or ML positioning model; and transmitting, to a terminal device or a further network device, the plurality of input data items or the plurality of ground truth label data items.
In an eighth aspect, there is provided a method of communication. The method comprises: receiving, at an LMF from a terminal device, an indication of a time segment set of a plurality of input data items of an AI or ML positioning model; and transmitting, to the terminal device, information comprising a plurality of ground truth label data items associated with the plurality of time segments; wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In a ninth aspect, there is provided a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to carry out the method according to any one of the fifth to the eighth aspects above.
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 example 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 illustrates an overall sequence of events applicable to the UE, NG-RAN, and LMF for any location service;
FIG. 2A illustrates an example communication system in which some embodiments of the present disclosure can be implemented;
FIG. 2B illustrates another example communication system in which embodiments of the present disclosure can be implemented;
FIG. 3A illustrates a schematic diagram for UE-assisted positioning with an LMF-side model;
FIG. 3B illustrates a schematic diagram of work deployment for indoor scenario;
FIG. 3C illustrates a schematic diagram of positioning with UE side model;
FIG. 3D illustrates a schematic diagram of data matching between multiple inputs and multiple labels;
FIGS. 4A-4B illustrate the scenarios of AI/ML based positioning with single TRP and multiple TRPs respectively;
FIG. 5 illustrates a signalling chart illustrating communication process in accordance with some example embodiments of the present disclosure;
FIG. 6 illustrates a signalling chart illustrating communication process in accordance with some example embodiments of the present disclosure;
FIG. 7 illustrates a signalling chart illustrating communication process in accordance with some example embodiments of the present disclosure;
FIGS. 8A-8B illustrate schematic diagrams of the input and ground truth label data items in accordance with some embodiments of the present disclosure;
FIG. 9 illustrates a signalling chart illustrating communication process of data matching at UE in accordance with some example embodiments of the present disclosure;
FIG. 10 illustrates a signalling chart illustrating communication process of data matching at DF in accordance with some example embodiments of the present disclosure;
FIG. 11A illustrates a schematic diagram of the first threshold in accordance with some example embodiments of the present disclosure;
FIG. 11B illustrates a schematic diagram of time duration for data matching in accordance with some example embodiments of the present disclosure;
FIG. 12 illustrates a signalling chart illustrating communication process in accordance with some example embodiments of the present disclosure;
FIG. 13 illustrates a signalling chart illustrating communication process in accordance with some example embodiments of the present disclosure;
FIG. 14 illustrates a schematic diagram of the input and ground truth label data items in accordance with some embodiments of the present disclosure;
FIG. 15 illustrates a signalling chart illustrating communication process of data matching at UE in accordance with some example embodiments of the present disclosure;
FIG. 16 illustrates a signalling chart illustrating communication process of data matching at LMF in accordance with some example embodiments of the present disclosure;
FIG. 17A illustrates a schematic diagram of determining a time segment in accordance with some example embodiments of the present disclosure;
FIG. 17B illustrates a schematic diagram of a time segment in accordance with some example embodiments of the present disclosure;
FIG. 17C illustrates a schematic diagram of a change of a time segment in accordance with some example embodiments of the present disclosure;
FIG. 17D illustrates a schematic diagram of a relationship between a time segment and location information in accordance with some example embodiments of the present

disclosure;

FIG. 17E illustrates a schematic diagram 1750 of an association of the indication and the information in FIG. 12 in accordance with some example embodiments of the present disclosure;
FIG. 18 illustrates a schematic diagram of the input and ground truth label data items in accordance with some embodiments of the present disclosure;
FIG. 19 illustrates a flowchart of an example method implemented at a first device in accordance with some embodiments of the present disclosure;
FIG. 20 illustrates a flowchart of an example method implemented at a terminal device in accordance with some embodiments of the present disclosure;
FIG. 21 illustrates a flowchart of an example method implemented at a network device in accordance with some embodiments of the present disclosure;
FIG. 22 illustrates a flowchart of an example method implemented at an LMF in accordance with some embodiments of the present disclosure; and
FIG. 23 illustrates 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 limitation as to the scope of the disclosure. Embodiments 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.
References in the present disclosure to “one embodiment, ” “an embodiment, ” “an example embodiment, ” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
It shall be understood that although the terms “first” and “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. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and/or” includes any and all combinations of one or more of the listed terms.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example 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 the terms “comprises” , “comprising” , “has” , “having” , “includes” and/or “including” , when used herein, specify the presence of stated features, elements, and/or components etc., but do not preclude the presence or addition of one or more other features, elements, components and/or combinations thereof.
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 used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR) , Long Term Evolution (LTE) , LTE-Advanced (LTE-A) , Wideband Code Division Multiple Access (WCDMA) , High-Speed Packet Access (HSPA) , Narrow Band Internet of Things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, 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) , 5.5G, 5G-Advanced networks, or the sixth generation (6G) communication protocols, and/or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.
As used herein, the term “terminal device” refers to any device having wireless or wired communication capabilities. Examples of 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) , 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 be incorporated 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.
As used herein, 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 satellite, a unmanned aerial systems (UAS) platform, 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) , and the like.
In one embodiment, the terminal device may be connected with a first network device and a second network device. One of the first network device and the second network device may be a master node and the other one may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs) . In one embodiment, the first network device may be a first RAT device and the second network device may be a second RAT device. In one embodiment, the first RAT device is eNB and the second RAT device is gNB. Information related with different RATs may be transmitted to the terminal device from at least one of the first network device and the second network device. In one embodiment, first information may be transmitted to the terminal device from the first network device and second information may be transmitted to the terminal device from the second network device directly or via the first network device. In one embodiment, information related with configuration for the terminal device configured by the second network device may be transmitted from the second network device via the first network device. Information related with reconfiguration for the terminal device configured by the second network device may be transmitted to the terminal device from the second network device directly or via the first network device.
Communications discussed herein may conform to any suitable standards including, but not limited to, New Radio Access (NR) , Long Term Evolution (LTE) , LTE-Evolution, LTE-Advanced (LTE-A) , Wideband Code Division Multiple Access (WCDMA) , Code Division Multiple Access (CDMA) , cdma2000, and Global System for Mobile Communications (GSM) and the like. Furthermore, the communications 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, 2.85G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) , and the sixth (6G) communication protocols. The techniques described herein may be used for the wireless networks and radio technologies mentioned above as well as other wireless networks and radio technologies. 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.
The terminal device or the network device may have AI or ML capability. It generally includes a model which has been trained from numerous collected data for a specific function, and can be used to predict some information.
The terminal device 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 200GHz 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 device 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 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, or 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.
The term “circuitry” used herein may refer to hardware circuits and/or combinations of hardware circuits and software. For example, the circuitry may be a combination of analog and/or digital hardware circuits with software/firmware. As a further example, the circuitry may be any portions of hardware processors with software including digital signal processor (s) , software, and memory (ies) that work together to cause an apparatus, such as a terminal device or a network device, to perform various functions. In a still further example, the circuitry may be hardware circuits and or processors, such as a microprocessor or a portion of a microprocessor, that requires software/firmware for operation, but the software may not be present when it is not needed for operation. As used herein, the term circuitry also covers an implementation of merely a hardware circuit or processor (s) or a portion of a hardware circuit or processor (s) and its (or their) accompanying software and/or firmware.
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 “based at least in part on. ” The term “one embodiment” and “an embodiment” are to be read as “at least one embodiment. ” 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.
To support positioning of a target UE and delivery of location assistance data to a UE with next generation –radio access network (NG-RAN) access in the fifth generation system (5GS) , location related functions are distributed in the UE positioning overall architecture applicable to NG-RAN. FIG. 1 illustrates an overall sequence 100 of events applicable to the UE, NG-RAN, and LMF for any location service. The UE is assumed to be in connected mode before the beginning of the flow shown in FIG. 1; that is, any signalling that might be required to bring the UE to connected mode prior to step 1a is not shown. There are multiple steps shown in FIG. 1, which are described below.
1a. Either: some entity in the fifth generation core (5GC) (e.g. gateway mobile location center (GMLC) ) requests some location service (e.g. positioning) for a target UE to the serving access and mobility management function (AMF) .
1b. Or: the serving AMF for a target UE determines the need for some location service (e.g. to locate the UE for an emergency call) .
1c. Or: the UE requests some location service (e.g. positioning or delivery of assistance data) to the serving AMF at the non-access stratum (NAS) level.
2. The AMF transfers the location service request to an LMF.
3a. The LMF instigates location procedures with the serving and possibly neighbouring ng-eNB or gNB in the NG-RAN –e.g. to obtain positioning measurements or assistance data.
3b. In addition to step 3a or instead of step 3a, the LMF instigates location procedures with the UE –e.g. to obtain a location estimate or positioning measurements or to transfer location assistance data to the UE.
4. The LMF provides a location service response to the AMF and includes any needed results –e.g. success or failure indication and, if requested and obtained, a location estimate for the UE.
5a. If step 1a was performed, the AMF returns a location service response to the 5GC entity in step 1a and includes any needed results –e.g. a location estimate for the UE.
5b. If step 1b occurred, the AMF uses the location service response received in step 4 to assist the service that triggered this in step 1b (e.g. may provide a location estimate associated with an emergency call to a GMLC) .
5c. If step 1c was performed, the AMF returns a location service response to the UE and includes any needed results –e.g. a location estimate for the UE.
As discussed in step 3a or 3b, positioning measurements are needed. The positioning measurements may include time difference of arrival (TDOA) measurements or line of sight (LOS) -non line of sight (NLOS) indicators which are listed below:
As mentioned above, it has been agreed to investigate the potential for AI/ML in air interface to improve positioning performance. The following text box describes some agreements that have been made.
It is agreed to study and provide inputs on benefit (s) and potential specification impact at least for the following cases of AI/ML based positioning accuracy enhancement:
● Case 1: UE-based positioning with UE-side model, direct AI/ML or AI/ML assisted positioning.
● Case 2a: UE-assisted/LMF-based positioning with UE-side model, AI/ML assisted positioning.
● Case 2b: UE-assisted/LMF-based positioning with LMF-side model, direct AI/ML positioning.
● Case 3a: NG-RAN node assisted positioning with gNB-side model, AI/ML assisted positioning.
● Case 3b: NG-RAN node assisted positioning with LMF-side model, direct AI/ML positioning.
In the present disclosure, the term “XX-side model” may indicate that the AI/ML model inference will be performed at the XX side. For example, the UE-side model may refer to that the AI/ML inference is performed at the UE. For example, the LMF-side model may refer to that the AI/ML inference is performed at the LMF. For example, the gNB-side model may refer to that the AI/ML inference is performed at the gNB.
The process of collecting data for model training and monitoring is a crucial step in supporting AI/ML-based positioning. The input and label of this data may come from different entities, e.g., the input of the AI/ML model may be collected at the UE side and the label using for monitoring, fine-tuning or training the AI/ML model may be collected at a TRP. However, how to effectively match these inputs and labels from different sources as instances is still needed to be studied.
In the present disclosure, the data for model training, fine-tuning and/or monitoring may also be referred to as data instances or instances. An instance may include an input data item and a matched label, and accordingly, the instance may be called as a matched instance. In the present disclosure, the input data item may also be called as input information, input data, input, input of AI/ML model, or the like. In the present disclosure, the label may be also be called as ground truth label data item, ground truth label, ground truth data item, output information data item, output information, output data, output of AI/ML model, or the like. In some embodiments, the terms label, label data, ground truth label data item, ground truth label, ground truth data item, output information data item, output information, output data, output of AI/ML model can be used interchangeably.
In the present disclosure, the input data item (or input) may include one or more of: a CIR, a PDP, or a DP. In the present disclosure, the ground truth label data item (or ground truth label) may include one or more of: time of arrival (TOA) , TDOA, LOS/NLOS indicator, or a terminal location (i.e., a UE location) .
In the present disclosure, the AI/ML positioning model may refer to an AI positioning model or an ML positioning model. The AI/ML positioning model may be interchangeably used with an AI or ML positioning model, an AI/ML model, an AI positioning model, an ML positioning model, an AI/ML model, an AI/ML algorithm, or the like, the present disclosure does not limit this aspect.
As used herein, an AI/ML positioning model may be equivalent to at least one of the following: a model, an AI/ML model, an ML model, an AI model, a data-driven, a data processing model, an algorithm, a functionality, a procedure, a process, an entity, a function, a feature, a feature group, a model ID, a functionality ID, a configuration ID, a scenario ID, a site ID, or a dataset ID. As a result, the above terms may be used interchangeably.
In some embodiments, the AI/ML positioning model may be represented by or associated with a channel, a resource, a resource set, a RS resource, a RS resource set, a RS port, a set of RS ports, a RS port ID, or a set of RS port IDs.
In some embodiments, the AI/ML positioning model may comprise a set of weights values that may be learned during training, for example for a specific architecture or configuration, where a set of weights values may also be called a parameter set.
In some embodiments, the AI/ML positioning model may be used to predict a target cell, or measurements of a set of beams of a set of candidate cells in future based on at least historical measurements (e.g., L1-RSRP, L1-SINR) of a set of beams of a set of candidate cells.
In some embodiments, an input of the AI/ML model (i.e., AI input) may refer to the input of a model and indicate data inputted into the model, which may be equivalent to input data or input data item.
In some embodiments, an output of the AI/ML model (i.e., AI output) may refer to the output of a model and indicate result (s) outputted by the model, which may be equivalent to label, output data, output data item, label data, or label data item.
Embodiments of the present disclosure provide a solution of communication. In the solution, a first device may obtain multiple input data items and multiple ground truth label data items of an AI/ML positioning model. In some examples, the multiple input data items and multiple ground truth label data items are collected by different entities. The first device may further determine a match between at least one of the multiple input data items and at least one of the multiple ground truth label data items, to determine at least one matched instance. As such, the instance for model training and/or monitoring may be determined based on the multiple input data items and the multiple ground truth label data items collected by different entities. Therefore, the instances may be further used for model training and/or monitoring for positioning. Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
FIG. 2A illustrates an example communication system 200 in which some embodiments of the present disclosure can be implemented. The communication system 200 may also be called as a network environment, a network system, a communication environment, a communication network, or the like, the present disclosure does not limit this aspect. The communication system 200 includes a terminal device 210 and a network device 220-0. The network device 220-0 can provide services to the terminal device 210.
FIG. 2B illustrates another example communication system 250 in which embodiments of the present disclosure can be implemented. The communication system 250 may also be called as a network environment, a network system, a communication environment, a communication network, or the like, the present disclosure does not limit this aspect. The system 250, which is a part of a communication network, includes a terminal device 210. The system 250 further includes a network device 220-1, a network device 220-2, a network device 220-3 as shown in FIG. 2B. It is noted that only 3 network devices 220-1 to 220-3 that used for transmitting or receiving reference signaling are shown in FIG. 2B, but the number of such network devices may be more than three, and the network devices 220-1 to 220-3 in FIG. 2B are given for the purpose of illustration without suggesting any limitations. In some embodiments, the network devices 220-1 to 220-3 may be referred to as access network devices. In some embodiments, the network devices 220-1 to 220-3 may be implemented as multi-transmission and reception point (multi-TRP) .
For ease of description, the network device 220-0, or any of the network devices 220-1 to 220-3 can be collectively or respectively referred to as “network device 220” .
The system 200/250 may further include an LMF 230, in some examples, the LMF 230 may also be called as a location and mobility function. It should be appreciated that the LMF 230 may be located at an access network device or a core network device.
In the system 200/250, the network device 220 can communicate/transmit data and control information to the terminal device 210, and the terminal device 210 can also communicate/transmit data and control information to the network device 220. A link from the network device 220 to the terminal device 210 is referred to as a downlink (DL) , while a link from the terminal device 210 to the network device 220 is referred to as an uplink (UL) . DL may comprise one or more logical channels, including but not limited to a Physical Downlink Control Channel (PDCCH) and a Physical Downlink Shared Channel (PDSCH) . UL may comprise one or more logical channels, including but not limited to a Physical Uplink Control Channel (PUCCH) and a Physical Uplink Shared Channel (PUSCH) . As used herein, the term “channel” may refer to a carrier or a part of a carrier consisting of a contiguous set of resource blocks (RBs) on which a channel access procedure is performed in shared spectrum.
Communications in the system 200/250, between the network device 220 and the terminal device 210 for example, may be implemented according to any proper communication protocol (s) , comprising, 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) and the sixth generation (6G) and on the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and/or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, comprising but not limited to: Code Divided Multiple Address (CDMA) , Frequency Divided Multiple Address (FDMA) , Time Divided Multiple Address (TDMA) , Frequency Divided Duplexer (FDD) , Time Divided Duplexer (TDD) , Multiple-Input Multiple-Output (MIMO) , Orthogonal Frequency Divided Multiple Access (OFDMA) and/or any other technologies currently known or to be developed in the future.
In the system 200/250, the terminal device 210 can communicate with the LMF 230 according to any proper communication protocol, such as an LTE positioning protocol (LPP) . It is to be understood that other protocol may also be applied and will not be listed herein.
Embodiments of the present disclosure can be applied to any suitable scenarios. For example, embodiments of the present disclosure can be implemented at reduced capability NR devices. Alternatively, embodiments of the present disclosure can be implemented in one of the followings: NR multiple-input and multiple-output (MIMO) , NR sidelink enhancements, NR systems with frequency above 52.6GHz, an extending NR operation up to 71GHz, narrow band-Internet of Thing (NB-IOT) /enhanced Machine Type Communication (eMTC) over non-terrestrial networks (NTN) , NTN, UE power saving enhancements, NR coverage enhancement, NB-IoT and LTE-MTC, Integrated Access and Backhaul (IAB) , NR Multicast and Broadcast Services, or enhancements on Multi-Radio Dual-Connectivity.
It is to be understood that the numbers of devices (i.e., the terminal devices 210 and the network device 220) and their connection relationships and types shown in FIGS. 2A-2B are only for the purpose of illustration without suggesting any limitation. The system 200/250 may include any suitable numbers of devices adapted for implementing embodiments of the present disclosure.
As an agreement discussed during R18, the entity responsible for deploying the AI/ML model is accountable for determining the monitoring metric. However, the entity designated to collect model monitoring data may not possess the capability to gather both input and label, thus requiring a mechanism to match these inputs and labels as instances of the AI/ML model.
It is to be understood that the inputs and the labels are collected at different entities for multiple reasons. One of the reasons is associated with feasibility. FIG. 3A illustrates a schematic diagram 310 for UE-assisted positioning with an LMF-side model, such as case 2b discussed above. As shown in FIG. 3A, if the input of the model is CIR and the output is UE location, it is necessary to match the CIR and the UE location as an instance of data since the CIR is measured on the UE side generally (e.g., based on the PRSs from multiple TRPs) and the UE location is calculated on the LMF side, if the UE is not capability to UE based positioning.
One of the reasons is associated with load. FIG. 3B illustrates a schematic diagram 320 of work deployment for indoor scenario. If the input and the label are collected from the same entity, it is evident that the workload will be too heavy, especially when deploying AI/ML models at the UE side, such as cases 1 and 2a discussed above. For example, the mainstream input of the AI/ML model for positioning has a dimension of N_TRP × Nport × Nt, where N_TRP is the number of TRPs, Nport is the number of transmit/receive antenna port pairs, and Nt is the number of time domain samples. For indoor factory scenarios, assuming a port count of 2 and 256 time domain samples (a typical assumption) , if the AI/ML model is deployed at the LMF side, it is necessary to transmit a single instance containing 18 (TRP) × 2 (ports) × 256 *2 (I/Q) = 18432 real values to the NW side via the LPP or a physical layer protocol, which can be a heavy load for the UE. If the UE location data is collected at the UE side, the load on the UE side will become even heavier. Therefore, it is reasonable to collect input at the UE side and label at the NW side to avoid excessive load on the UE side.
One of the reasons is associated with privacy. FIG. 3C illustrates a schematic diagram 330 of positioning with UE side model, such as case 1 discussed above. For example, the AI/ML model is deployed at the UE side, if the network operator (i.e., the NW side) is responsible for providing timely ground truth labels based on NR RAT-dependent positioning methods, they may need to disclose the UE's positioning in a time-ordered manner, which may not be acceptable from a privacy perspective. A more reasonable solution is for the NW to transmit the UE's positioning out of order, in this event, the UE should have a capability to match the positioning and input (e.g., CIR) using pre-established rules.
One of the reasons is associated with semi-supervised learning. FIG. 3D illustrates a schematic diagram 340 of data matching between multiple inputs and multiple labels. For example, if semi-supervised learning for AI/ML based positioning is supported, one of the faced problems may be how to match the input and label as an instance since the number of inputs is larger than the number of labels. As shown in FIG. 3D, assuming the input is provided by the NW and the label is provided by the UE. If the number of inputs is 8 and the number of labels is 5, after a mechanism of data matching is implemented, the entity has determined that the data set { (input b, label a) , (input c, label b) , (input e, label c) , (input f, label d) , (input h, label e) } is used for supervised learning and the data set {input a, input d, input g} is used for unsupervised learning.
Accordingly, to guarantee effective monitoring of an AI/ML model, it is imperative to pinpoint the entity responsible for deploying it and align the data accordingly. This becomes particularly crucial when input and label originate from distinct entities prior to monitoring the model. Furthermore, matching the data is also essential before deciding whether to fine-tune or train the AI/ML model.
The input of an AI/ML model may be CIR, PDP, or DP, which can be determined by using a single TRP (e.g., shown in FIG. 2A) or multiple TRPs (e.g., shown in FIG. 2B) . FIGS. 4A-4B illustrate the scenarios of AI/ML based positioning with single TRP 410 and multiple TRPs 420 respectively. The positioning model in the scenario of single TRP may be an AI/ML assisted positioning model, where the output may be intermediate measurement. The positioning model in the scenario of multiple TRPs may be a direct AI/ML positioning model or an AI/ML assisted positioning model, where the output may be the UE location and the intermediate measurement respectively.
For ease of description, the following description will be stated with respect to the single TRP scenario and the multiple TRPs scenario respectively.
The single TRP scenario (scenario 1) : A combination of entity for input collection, entity for output collection, output type, and entity for matching the data is shown in Table 1 below:
Table 1
The subcases 1-1, 1-3, and 1-5 are related to AI/ML assisted positioning model with data matching at UE side, while the subcases 1-2, 1-4, and 1-6 are related to AI/ML assisted positioning model with data matching at network (such as gNB) side. Detailed description will be stated with reference to FIGS. 5-11B below.
The multiple TRPs scenario (scenario 2) : A combination of entity for input collection, entity for output collection, output type, and entity for matching the data is shown in Table 2 below:
Table 2
The subcase 2-1 is related to a direct AI/ML positioning model with data matching at UE side, while the subcase 2-2 is related to a direct AI/ML positioning model with data matching at the LMF side. The subcase 2-3 is related to AI/ML assisted positioning model with data matching at UE side, while the subcase 2-4 is related to AI/ML assisted positioning model with data matching at network (such as gNB) side. Detailed description will be stated with reference to FIGS. 12-18 below.
Reference is further made to FIG. 5, which illustrates a signalling chart illustrating communication process 500 in accordance with some example embodiments of the present disclosure. Only for the purpose of discussion, the process 500 will be described with reference to FIG. 2A. The process 500 may involve the terminal device 210 and the network device 220-0. It is assumed that the data matching is performed at the terminal device 210 in FIG. 5, e.g., related to subcase 1-1, 1-3, or 1-5 in Table 1.
A process 510 or 530 may be performed so that the terminal device 210 may obtain multiple input data items and multiple ground truth label data items.
In the process 510, the terminal device 210 determines 512 multiple input data items of an AI/ML positioning model. In some examples, the terminal device 210 may measure one or more downlink reference signals, such as PRSs or other downlink RS (s) , to determine the multiple input data items, such as CIR, PDP, or DP. The network device 220-0 determines 514 multiple ground truth label data items of the AI/ML positioning model. In some examples, the network device 220-0 may measure one or more uplink reference signals to determine the multiple ground truth label data items, such as TOA. In addition, the network device 220-0 transmits 520 the multiple ground truth label data items 522 to the terminal device 210, and accordingly the terminal device 210 receives 524 the multiple ground truth label data items 522.
In the process 530, the network device 220-0 determines 534 multiple input data items of an AI/ML positioning model. In some examples, the network device 220-0 may measure one or more uplink reference signals to determine the multiple input data items, such as CIR, PDP, or DP. The terminal device 210 determines 532 multiple ground truth label data items of the AI/ML positioning model. In some examples, the terminal device 210 may measure one or more downlink reference signals, such as PRSs, to determine multiple ground truth label data items, such as TOA, or LOS/NLOS indicator. In addition, the network device 220-0 transmits 540 the multiple input data items 542 to the terminal device 210, and accordingly the terminal device 210 receives 544 the multiple input data items 542.
The terminal device 210 matches 550 at least one of the multiple input data items and at least one of the multiple ground truth label data items, to obtain at least one matched instance for the AI/ML positioning model.
In some example embodiments, the terminal device 210 may determine a first time stamp of a first input data item; determine a second time stamp of a first ground truth label data item. In some example embodiments, if a time difference between the first time stamp and the second stamp is not larger than a first threshold, the terminal device 210 may determine a matched instance which includes the first input data item and the first ground truth label data item. In some other example embodiments, if the time length between the first time stamp and the second stamp is larger than the first threshold, the terminal device 210 may determine an instance which includes the first input data item for unsupervised learning of the AI/ML positioning model.
For example, the first time stamp may be represented as t1, the second time stamp may be represented as t2, and the first threshold may be represented as T1. If |t1-t2|<T1, then the first input data item (i.e., first input) and the first ground truth label data item (i.e., first label) may be regarded as a valid instance.
In some examples, a time stamp of an input data item (such as the first time stamp) may represent a CIR/PDP/DP time stamp when the timing the RS for the CIR/PDP/DP measurement is received.
In some examples, a time stamp of a ground truth label data item (such as the second time stamp) may represent: (1) a reference signal reception timing of TOA if the output of the AI/ML positioning model is TOA, where the reference signal is used at least for determining the TOA; or (2) the reference signal reception timing provided in LOS-NLOS indicator if the output of the AI/ML positioning model is LOS/NLOS indicator, where the reference signal is used at least for determining LOS/NLOS indicator.
In some examples, the first threshold (T1) may be predefined or may be provided by the network. For example, the network device 220-0 may transmit information indicating the first threshold. For example, the network device 220-0 may determine the first threshold based on one or more of: a positioning accuracy, or a transmission delay between the terminal device 210 and the network device 220-0. For example, the first threshold may be carried in any of: downlink control information (DCI) , a medium access control (MAC) control element (CE) , or a radio resource control (RRC) message or RRC signalling.
In this way, the terminal device 210 may determine one or more matched instances based on the multiple input data items and the multiple ground truth label data items.
In some other example embodiments, the terminal device 210 may determine a time duration for data matching. In some example embodiments, the terminal device 210 may determine a subset of the plurality of input data items and a subset of the plurality of ground truth label data items within the time duration, where the plurality of input data items and the plurality of ground truth label data items are ordered in a chronological order; and may match the subset of the plurality of input data items with the subset of the plurality of ground truth label data items in a descending order or in an ascending order.
In some examples, the time duration for data matching may be predefined or may be provided by the network. For example, the network device 220-0 may transmit information indicating the time duration. For example, the information may include one or more of the following to indicate the time duration: a start of the time duration, a length of the time duration, or an end of the time duration. For example, the start of the time duration is indicated by a first system frame number (SFN) and a first slot number. For example, the end of the time duration is indicated by a second SFN and a second slot number. For example, the length of the time duration may be indicated by a quantity of slots.
In some examples, the terminal device 210 may determine a subset of input data items (may be called as an input subset) during the time duration, where all input data items in the subset are ordered in a chronological order. In some examples, the terminal device 210 may determine a subset of ground truth label data items (may be called as a label subset) during the time duration, where all ground truth label data items in the subset are ordered in a chronological order.
In some examples, the terminal device 210 may match at least one in the subset of input data items and at least one in the subset of ground truth label data items, to determine at least one matched instance. For example, the matching may be performed in a descending order or in an ascending order, in other words, the first input in the input subset and the first (or the last) label in the label subset may be matched to be a matched instance.
In some examples, the terminal device 210 will not match any data items out the time duration.
It is to be understood that the input subset and the label subset may be in different size, in other words, a number of input data items in the input subset does not equal to the number of ground truth label data items in the label subset. In some examples, if the number of input data items in the input subset is larger than the number of ground truth label data items in the label subset, there may be one or more input data items unmatched with any label. In some examples, the terminal device 210 may determine that one or more input data items in the input subset which are not matched with any of the subset of ground truth label data items as one or more instances for unsupervised learning of the AI/ML positioning model.
In this way, the input data items may be used in an efficient way to train the AI/ML positioning model.
In addition or alternatively, the terminal device 210 may transmit a report to the network device 220-0 or to an LMF 230, where the report may indicate the number of matched instances. For example, the report may be carried in an uplink transmission, and the report may indicate the number of valid instances.
According to the example embodiments described with reference to FIG. 5, the terminal device 210 may be the entity performing data matching.
FIG. 6 illustrates a signalling chart illustrating communication process 600 in accordance with some example embodiments of the present disclosure. Only for the purpose of discussion, the process 600 will be described with reference to FIG. 2A. The process 600 may involve the terminal device 210 and the network device 220-0. It is assumed that the data matching is performed at the network device 220-0 in FIG. 6, e.g., related to subcase 1-2, 1-4, or 1-6 in Table 1.
A process 610 or 630 may be performed so that the network device 220-0 may obtain multiple input data items and multiple ground truth label data items.
In the process 610, the network device 220-0 determines 612 multiple input data items of an AI/ML positioning model. In some examples, the network device 220-0 may measure one or more uplink reference signals to determine the multiple input data items, such as CIR, PDP, or DP. The terminal device 210 determines 614 multiple ground truth label data items of the AI/ML positioning model. In some examples, the terminal device 210 may measure one or more downlink reference signals, such as PRSs, to determine multiple ground truth label data items, such as TOA, or LOS/NLOS indicator. In addition, the terminal device 210 transmits 620 the multiple ground truth label data items 622 to the network device 220-0, and accordingly the network device 220-0 receives 624 the multiple ground truth label data items 622.
In the process 630, the terminal device 210 determines 634 multiple input data items of an AI/ML positioning model. In some examples, the terminal device 210 may measure one or more downlink reference signals, such as PRSs or other downlink RS (s) , to determine the multiple input data items, such as CIR, PDP, or DP. The network device 220-0 determines 632 multiple ground truth label data items of the AI/ML positioning model. In some examples, the network device 220-0 may measure one or more uplink reference signals to determine the multiple ground truth label data items, such as TOA. In addition, the terminal device 210 transmits 640 the multiple input data items 642 to the network device 220-0, and accordingly the network device 220-0 receives 644 the multiple input data items 642.
The network device 220-0 matches at least one of the multiple input data items and at least one of the multiple ground truth label data items at 650, to obtain at least one matched instance for the AI/ML positioning model.
In some example embodiments, the network device 220-0 may determine a first time stamp of a first input data item; determine a second time stamp of a first ground truth label data item. In some example embodiments, if a time difference between the first time stamp and the second stamp is not larger than a first threshold, the network device 220-0 may determine a matched instance which includes the first input data item and the first ground truth label data item. In some other example embodiments, if the time length between the first time stamp and the second stamp is larger than the first threshold, the network device 220-0 may determine an instance which includes the first input data item for unsupervised learning of the AI/ML positioning model.
For example, the first time stamp may be represented as t1, the second time stamp may be represented as t2, and the first threshold may be represented as T1. If |t1-t2|<T1, then the first input data item (i.e., first input) and the first ground truth label data item (i.e., first label) may be regarded as a valid instance.
In some examples, a time stamp of an input data item (such as the first time stamp) may represent a CIR/PDP/DP time stamp when the timing the RS for the CIR/PDP/DP measurement is received.
In some examples, a time stamp of a ground truth label data item (such as the second time stamp) may represent: (1) a reference signal reception timing of TOA if the output of the AI/ML positioning model is TOA, where the reference signal is used at least for determining the TOA; or (2) the reference signal reception timing provided in LOS-NLOS indicator if the output of the AI/ML positioning model is LOS/NLOS indicator, where the reference signal is used at least for determining LOS/NLOS indicator.
In some examples, the first threshold (T1) may be predefined or may be determined by the network device 220-0. For example, the network device 220-0 may determine the first threshold based on one or more of: a positioning accuracy, or a transmission delay between the terminal device 210 and the network device 220-0. In some examples, the network device 220-0 may transmit information indicating the first threshold. For example, the first threshold may be carried in any of: a DCI, a MAC CE, or a RRC message or RRC signalling.
In this way, the network device 220-0 may determine one or more matched instances based on the multiple input data items and the multiple ground truth label data items.
In some other example embodiments, the network device 220-0 may determine a time duration for data matching. In some example embodiments, the network device 220-0 may determine a subset of the plurality of input data items and a subset of the plurality of ground truth label data items within the time duration, where the plurality of input data items and the plurality of ground truth label data items are ordered in a chronological order; and may match the subset of the plurality of input data items with the subset of the plurality of ground truth label data items in a descending order or in an ascending order.
In some examples, the time duration for data matching may be predefined or may be determined by the network device 220-0. For example, the network device 220-0 may determine one or more of the following to indicate the time duration: a start of the time duration, a length of the time duration, or an end of the time duration. For example, the start of the time duration is indicated by a first SFN and a first slot number. For example, the end of the time duration is indicated by a second SFN and a second slot number. For example, the length of the time duration may be indicated by a quantity of slots or a quantity of symbols.
In some examples, the network device 220-0 may determine a subset of input data items (may be called as an input subset) during the time duration, where all input data items in the subset are ordered in a chronological order. In some examples, the network device 220-0 may determine a subset of ground truth label data items (may be called as a label subset) during the time duration, where all ground truth label data items in the subset are ordered in a chronological order.
In some examples, the network device 220-0 may match at least one in the subset of input data items and at least one in the subset of ground truth label data items, to determine at least one matched instance. For example, the matching may be performed in a descending order or in an ascending order, in other words, the first input in the input subset and the first (or the last) label in the label subset may be matched to be a matched instance.
In some examples, the network device 220-0 will not match any data items out the time duration.
It is to be understood that the input subset and the label subset may be in different size, in other words, a number of input data items in the input subset does not equal to the number of ground truth label data items in the label subset. In some examples, if the number of input data items in the input subset is larger than the number of ground truth label data items in the label subset, there may be one or more input data items unmatched with any label. In some examples, the network device 220-0 may determine that one or more input data items in the input subset which are not matched with any of the subset of ground truth label data items as one or more instances for unsupervised learning of the AI/ML positioning model.
A specific example may be similar with that described refer to FIG. 11B below. For example, for the time duration 1, the input subset includes CIR1, CIR2, CIR3, and CIR4; and the label subset includes (LOS/NLOS indicator 1) /TOA1, (LOS/NLOS indicator 2)/TOA2, and (LOS/NLOS indicator 3) /TOA3. The network device 220-0 may match {CIR1, (LOS/NLOS indicator 1) /TOA1} , {CIR2, (LOS/NLOS indicator 2) /TOA2} , and {CIR3, (LOS/NLOS indicator 3) /TOA3} as three instances for monitoring/training/fine-tuning the positioning model. For example, for the time duration 2, the input subset includes CIR7, and CIR8; and the label subset includes (LOS/NLOS indicator 6) /TOA6, (LOS/NLOS indicator 7) /TOA7, and (LOS/NLOS indicator 8) /TOA8. The network device 220-0 may match {CIR7, (LOS/NLOS indicator 6) /TOA6} and {CIR8, (LOS/NLOS indicator 7) /TOA7} as two valid instances for monitoring/training/fine-tuning the positioning model.
In this way, the input data items may be used in an efficient way to train the AI/ML positioning model.
It is to be understood that the operation 650 performed by the network device 220-0 is similar with the operation 550 performed by the terminal device 210 described with reference to FIG. 5.
According to the example embodiments described with reference to FIG. 6, the network device 220-0 may be the entity performing data matching.
FIG. 7 illustrates a signalling chart illustrating communication process 700 in accordance with some example embodiments of the present disclosure. Only for the purpose of discussion, the process 700 will be described with reference to FIG. 2A. The process 700 may involve the terminal device 210 and the network device 220-0. The process 700 further involves a further network device 701 and it is assumed that the data matching is performed at the further network device 701 in FIG. 7.
A process 715 or 735 may be performed so that the further network device 701 may obtain multiple input data items and multiple ground truth label data items. In some example embodiments, the further network device 701 may be another access network device different from the network device 220-0, an LMF (such as the LMF 230 in FIG. 2A) , or a data function (DF) . In some other example embodiments, the further network device 701 may be another network entity and the present disclosure does not limit this aspect.
In the process 715, the terminal device 210 transmits 710 multiple input data items 712 to the further network device 701, and accordingly the further network device 701 receives 714 the multiple input data items 712. For example, the terminal device 210 may determine the multiple input data items 712 (such as CIR, PDP, or DP) by measuring one or more downlink reference signals. The network device 220-0 transmits 720 multiple ground truth label data items 722 to the further network device 701, and accordingly the further network device 701 receives 724 the multiple ground truth label data items 722. For example, the network device 220-0 may determine the multiple ground truth label data items 722 (such as TOA) by measuring one or more uplink reference signals.
In the process 735, the terminal device 210 transmits 730 multiple ground truth label data items 732 to the further network device 701, and accordingly the further network device 701 receives 734 the multiple ground truth label data items 732. For example, the terminal device 210 may determine the multiple ground truth label data items 732 (such as TOA, or LOS/NLOS indicator) by measuring one or more downlink reference signals. The network device 220-0 transmits 740 multiple input data items 742 to the further network device 701, and accordingly the further network device 701 receives 724 the multiple input data items 742. For example, the network device 220-0 may determine the multiple input data items 742 (such as CIR, PDP, or DP) by measuring one or more uplink reference signals.
The further network device 701 matches at least one of the multiple input data items and at least one of the multiple ground truth label data items at 750, to obtain at least one matched instance for the AI/ML positioning model.
It is to be understood that the operation 750 performed by the further network device 701 is similar with the operation 550 performed by the terminal device 210 described with reference to FIG. 5 or the operation 650 performed by the network device 220-0 described with reference to FIG. 6, and thus will not be repeated herein for brevity.
According to the example embodiments described with reference to FIG. 7, the further network device 701 may be the entity performing data matching.
FIG. 8A illustrates a schematic diagram 810 of the input and ground truth label data items. As shown in FIG. 8A, the network device 220-0 may determine the CIR, PDP, or DP by measuring of UL RS, and the terminal device 210 may determine TOA or LOS/NLOS indicator by measuring of DL RS.
FIG. 8B illustrates a schematic diagram 820 of the input and ground truth label data items. As shown in FIG. 8B, the terminal device 210 may determine the CIR, PDP, or DP by measuring of DL RS, and the network device 220-0 may determine TOA by measuring of UL RS.
FIG. 9 illustrates a signalling chart illustrating communication process 900 of data matching at UE in accordance with some example embodiments of the present disclosure. The process 900 may include the label collection procedures 910 and the input collection procedures 920.
As shown in the FIG. 9, in the label collection procedures 910, the LMF transmits a TRP information request to the serving gNB or the TRP, and the serving gNB/TRP transmits a TRP information response back to the LMF, where the response may include a PRS configuration. The LMF may further provide the PRS configuration to the UE, so that the UE may perform PRS measurement based on one or more label collection request from the serving gNB/TRP and/or LMF.
As shown in FIG. 9, in the input collection procedures 920, the gNB determines UL resources for SRS. The serving gNB/TRP transmits SRS configuration to the UE. Accordingly, the UE may transmit SRS based on the input collection request from the serving gNB/TRP, and the serving gNB/TRP may perform SRS measurement.
In addition, the serving gNB/TRP transmits the collected input to the UE, so that the UE may perform the data matching. In some embodiments, the UE may further transmit a feedback to the serving gNB/TRP and/or the LMF, where the feedback may include a report of the number of valid instances.
FIG. 10 illustrates a signalling chart illustrating communication process 1000 of data matching at DF in accordance with some example embodiments of the present disclosure. The process 1000 may include the label collection procedures 1010 and the input collection procedures 1020.
As shown in the FIG. 10, in the label collection procedures 1010, the LMF transmits a TRP information request to the serving gNB or the TRP, and the serving gNB/TRP transmits a TRP information response back to the LMF, where the response may include a PRS configuration. The LMF may further provide the PRS configuration to the UE, so that the UE may perform PRS measurement based on one or more label collection request from the serving gNB/TRP, LMF, and/or DF. In addition, the UE may transmit the collected label to the DF.
As shown in FIG. 10, in the input collection procedures 1020, the gNB determines UL resources for SRS. The serving gNB/TRP transmits SRS configuration to the UE. Accordingly, the UE may transmit SRS based on the input collection request from the serving gNB/TRP or DF, and the serving gNB/TRP may perform SRS measurement. In addition, the serving gNB/TRP transmits the collected input to the DF.
In addition, the DF may perform the data matching. In some embodiments, the DF may further transmit a feedback to the serving gNB/TRP, where the feedback may include a report of the number of valid instances.
FIG. 11A illustrates a schematic diagram 1110 of the first threshold in accordance with some example embodiments of the present disclosure. In FIG. 11A, t2 may represent CIR/PDP/DP timestamp when the timing the RS for CIR/PDP/DP measurement is received, and t1 may represent the RS reception timing (not shown in FIG. 11A) of TOA or provided in LOS/NLOS indicator. As shown in FIG. 11A, the time difference between t2 and t1 is less than the first threshold (T1) , thus the input with a time stamp t1 and the label with a time stamp t2 may be regarded as a valid instance.
FIG. 11B illustrates a schematic diagram 1120 of time duration for data matching in accordance with some example embodiments of the present disclosure. It is assumed that a time duration 1 and a time duration 2 are provide by a network device, such as the network device 220-0, to the terminal device 210, and the time duration 1 is from t1 (start point) to t2 (end point) , while the time duration 2 is from t3 (start point) to t4 (end point) .
The terminal device 210 may determine an input subset and a label subset within the time duration 1. For example, the input subset includes CIR1, CIR2, CIR3, and CIR4. For example, the label subset includes (LOS/NLOS indicator 1) /TOA1, (LOS/NLOS indicator 2) /TOA2, and (LOS/NLOS indicator 3) /TOA3. The terminal device 210 may match {CIR1, (LOS/NLOS indicator 1) /TOA1} , {CIR2, (LOS/NLOS indicator 2) /TOA2} , and {CIR3, (LOS/NLOS indicator 3) /TOA3} as three valid instances for monitoring/training/fine-tuning the positioning model.
The terminal device 210 may determine an input subset and a label subset within the time duration 2. For example, the input subset includes CIR7, and CIR8. For example, the label subset includes (LOS/NLOS indicator 6) /TOA6, (LOS/NLOS indicator 7) /TOA7, and (LOS/NLOS indicator 8) /TOA8. The terminal device 210 may match {CIR7, (LOS/NLOS indicator 6) /TOA6} and {CIR8, (LOS/NLOS indicator 7) /TOA7} as two valid instances for monitoring/training/fine-tuning the positioning model.
The terminal device 110 will not match any of CIR5, CIR6, (LOS/NLOS indicator 4)/TOA4, or (LOS/NLOS indicator 5) /TOA5, since they are outside of the time durations 1 and 2.
According to the example embodiments described with reference to FIGS. 5-11B, the data matching for single TRP scenario is discussed. Specifically, at least one matched instance may be determined and be used for AI/ML positioning model.
Reference is further made to FIG. 12, which illustrates a signalling chart illustrating communication process 1200 in accordance with some example embodiments of the present disclosure. Only for the purpose of discussion, the process 1200 will be described with reference to FIG. 2B. The process 1200 may involve the terminal device 210 and the LMF 230. It is assumed that the data matching is performed at the terminal device 210 in FIG. 12, e.g., related to subcase 2-1 in Table 2.
The terminal device 210 determines 1210 multiple input data items of an AI/ML positioning model. In some examples, the terminal device 210 may measure multiple downlink reference signals, such as PRSs, from multiple TRPs to determine the multiple input data items, such as CIR, PDP, or DP.
The LMF 230 determines 1220 multiple ground truth label data items of the AI/ML positioning model. In some examples, the multiple ground truth label data items include multiple locations, such as UE locations. For example, the LMF 230 may determine the UE locations by calculating the measurement (s) from the terminal device 210 or from a network device 220.
The terminal device 210 transmits 1230 an indication 1232 of a time segment set of the multiple input data items to the LMF 230. In some examples, the time segment set may include one or more time segments.
In some example embodiments, the terminal device 210 may determine a time segment for an input data item, such as CIR, PDP, or DP. Take CIR as an example, since the CIR is determined by measuring multiple reference signals from multiple TRPs, the arrival times of the multiple reference signals may be different. The terminal device 210 may mark a time segment for the specific CIR. For example, the specific CIR is valid during the time segment from the time that receives the first RS to the time that received the last RS, where the RS is transmitted from multiple TRPs (a TRP group) that are involved in the CIR measurement.
In some examples, a time segment may include a start time and an end time. In some examples, the start time indicates a receiving time of a first received reference signal from a first TRP among multiple TRPs. In some examples, the end time indicates a receiving time of a last received reference signal from a second TRP among multiple TRPs.
In some examples, the start time may be indicated by a first SFN and a first slot number. In some examples, the start time may be further indicated by a first symbol number. For example, if the start time is represented as t01, then t01 may be an integration of the first SFN, the first slot number, and the first symbol number.
In some examples, the end time may be indicated by a second SFN and a second slot number. In some examples, the end time may be further indicated by a second symbol number. For example, if the end time is represented as t02, then t02 may be an integration of the second SFN, the second slot number, and the second symbol number.
In some example embodiments, the time segment set may include all time segments of the multiple input data items. For example, the terminal device 210 may report all time segments corresponding to the CIR/PDP/DP as soon as the terminal device 210 marked it.
In some other example embodiments, the time segment set may include some of all time segments of the multiple input data items. For example, if a change of a first time segment is larger than a second threshold, the terminal device 210 may determine that the time segment set comprises the first time segment.
In some examples, if a time length between a first middle of the first time segment and a second middle of the second time segment is larger than the second threshold, the terminal device 210 may determine that the change of the first time segment is larger than the second threshold. For example, the second time segment is a precedent time segment closest to the first time segment.
It is to be understood that the change of a time segment may be determined based the change of the middle time, or based on the change of the start time, or based on the change of the end time. The present disclosure does not limit this aspect.
In some examples, the indication 1232 of the time segment set may include a sequence of timing and multiple input identities. For example, multiple time segments may be represented as the sequence of timing. For example, every two adjacent timings in the sequence may indicate a time segment associated with one of the multiple input identities. For example, the first one of the every two adjacent timings in the sequence may indicate a start time of the time segment, and the second one of the every two adjacent timings in the sequence may indicate an end time of the time segment.
In some examples, the report of the indication of the time segment set may be event triggered. For example, each two adjacent and non-overlapping timings in the sequence may represent a time segment of a specific CIR.
For example, the sequence may be [t1, t2, t3, …, tn] and the input identities include [1, 2, …] , where the time segment from t1 to t2 may be associated with the input identity 1, the time segment from t3 to t4 may be associated with the input identity 2, ….
In some cases, there may be no time segment for an input data item, such as a specific CIR, the input identities may not include an identity of the specific CIR in this case. For example, the input identities may not be continuous.
In some cases, a report for an input data item (e.g., a specific CIR) may not be required. The input identities may include an identity of the specific CIR, and the timings associated with the specific CIR in the sequence may be predefined values, such as 0. In other words, a special indicia (e.g., 0) may be inserted for the specific CIR if the report of the time segment is not required.
In some example embodiments, the indication of the time segment set may be transmitted during a specific time resource. In some examples, the specific time resource may be configured by a network device. For example, the specific time resource may be a time window for the indication of the time segment set. For example, the specific time resource may be configured occasion for transmitting the indication of the time segment set. In some examples, the terminal device 210 may collects the multiple input data items during the time window, and transmit the indication of the time segment set at the end of the time window.
On the other side of communication, the LMF 230 receives 1234 the indication 1232 of the time segment set. The LMF 230 transmits 1240 information 1242 including multiple ground truth label data items associated with the time segment set.
In some example embodiments, the LMF 230 may choose (or determine) a suitable ground truth label data item (i.e., location or UE location information) based on the indication of time segment set. In some examples, the indication of time segment set may indicate a specific time segment, if a timestamp of a specific ground truth label data item (i.e., location or UE location information) which is determined or calculated by a reported measurement of reference signal (such as PRS, or SRS) is located within the specific time segment, then the specific ground truth label data item (i.e., location or UE location information) may be returned back to the terminal device 210.
In some example embodiments, there may be not available ground truth label data item (i.e., location) for some input data item (s) . For example, the LMF 230 cannot provide corresponding locations for some CIRs, PDPs, or DPs.
In some examples, the number of the multiple ground truth label data items may be less than the number of time segments in the indication 1232. In some examples, the information 1242 may further include multiple input identities associated with the multiple ground truth label date items. For example, the information 1242 may include a bitmap, and the bitmap may include multiple bits corresponding to the multiple time segments in the indication. For example, a bit equaling to a first value (such as 1) may represent that the corresponding location is provided in the information 1242, and another bit equaling to a second value (such as 0) may represent that the corresponding location is not provided in the information 1242.
On the other side of communication, the terminal device 210 receives 1244 the information 1242 including multiple ground truth label data items. The terminal device 210 matches 1250 at least one of the multiple input data items and at least one of the multiple ground truth label data items, to determine at least one matched instance. In some examples, a matched instance may include an input (such as CIR, PDP, or DP) and a label (such as UE location) .
FIG. 13 illustrates a signalling chart illustrating communication process 1300 in accordance with some example embodiments of the present disclosure. Only for the purpose of discussion, the process 1300 will be described with reference to FIG. 2B. The process 1300 may involve the terminal device 210 and the LMF 230. It is assumed that the data matching is performed at the LMF 230 in FIG. 13, e.g., related to subcase 2-2 in Table 2.
The terminal device 210 determines 1310 multiple input data items of an AI/ML positioning model. The LMF 230 determines 1320 multiple ground truth label data items of the AI/ML positioning model. It is to be understood that the operations 1310 and 1320a are similar with the operations 1210 and 1220 described with reference to FIG. 12, thus will not be repeat for brevity.
The terminal device 210 transmits 1330 the multiple input data items 1332 to the LMF 230, and accordingly the LMF 230 receives 1334 the multiple input data items 1332.
In some examples, the terminal device 210 may transmit an indication of a time segment set to the LMF 230, where one time segment may be associated with one input data item. It is to be understood that the operation 1330 is similar with the operation 1230 described with reference to FIG. 12, thus will not be repeat for brevity.
The LMF 230 matches 1350 at least one of the multiple input data items and at least one of the multiple ground truth label data items, to determine at least one matched instance. In some examples, a matched instance may include an input (such as CIR, PDP, or DP) and a label (such as UE location) .
FIG. 14 illustrates a schematic diagram 1400 of the input and ground truth label data items in accordance with some embodiments of the present disclosure. As shown in FIG. 14, the terminal device 210 may determine the CIR, PDP, or DP by measuring of DL RS, and the LMF 230 may determine UE location by calculating based on the measurement from UE and/or serving gNB.
FIG. 15 illustrates a signalling chart illustrating communication process 1500 of data matching at UE in accordance with some example embodiments of the present disclosure. As shown in FIG. 15, a procedure of input collection may be performed, so that the UE collects multiple inputs, such as CIR/PDP/DP. A procedure of label collection may be performed, so that the LMF collects multiple labels, such as UE location.
The UE may report CIR with time segment (s) and corresponding ID (s) to the LMF. The LMF may choose suitable location information, and return the chosen location information and a correspondence with the ID (s) to the UE. The UE may further perform the data matching.
FIG. 16 illustrates a signalling chart illustrating communication process 1600 of data matching at LMF in accordance with some example embodiments of the present disclosure. As shown in FIG. 16, a procedure of input collection may be performed, so that the UE collects multiple inputs, such as CIR/PDP/DP. A procedure of label collection may be performed, so that the LMF collects multiple labels, such as UE location. The UE may report CIR with time segment (s) and corresponding ID (s) to the LMF. The LMF may further perform the data matching.
FIG. 17A illustrates a schematic diagram 1710 of determining a time segment in accordance with some example embodiments of the present disclosure. It is assumed there are 18 TRPs, e.g., N_TRP=18, for a CIR. Suppose that the terminal device receives the first PRS from TRP 3 at time t1, and receives the last PRS from TRP 17 at time t2, then the terminal device may determine a time segment [t1, t2] for the CIR.
FIG. 17B illustrates a schematic diagram 1720 of a time segment in accordance with some example embodiments of the present disclosure. It is assumed that a time segment is indicated by a start time t01 and an end time t02.
The start time t01 may be represented by an integration of a first SFN and a first slot number (and a first symbol number alternatively) when the first RS is received at the terminal device. For example, the start time t01 may be an integration of: SFN0 and slot 1. For example, the start time t01 may be an integration of: SFN0, slot 1, and symbol 6.
The end time t02 may be represented by an integration of a second SFN and a second slot number (and a second symbol number alternatively) when the last RS is received at the terminal device. For example, the end time t02 may be an integration of: SFN1 and slot 0. For example, the end time t02 may be an integration of: SFN1, slot 0, and symbol 10.
FIG. 17C illustrates a schematic diagram 1730 of a change of a time segment in accordance with some example embodiments of the present disclosure. Suppose that a change of a time segment for a CIR is characterized by a center time of the time segment.
As shown in FIG. 17C, a time segment for CIR 1 is [t1, t2] , a time segment for CIR 2 is [t3, t4] , and a time segment for CIR 3 is [t5, t6] . Since a change of a time center of [t3, t4] relative to a time center of [t1, t2] is less than the second threshold (T2) , the time segment of CIR 2 will not be reported. Since a change of a time center of [t5, t6] relative to a time center of [t3, t4] is greater than the second threshold (T2) , the time segment of CIR 3 will be reported.
In other words, the time difference between the center times of CIR1 and CIR2 is less than T2, the time segment of CIR2 will not be reported, and the time difference between the center times of CIR2 and CIR3 is larger than T2, the time segment of CIR3 will be reported.
FIG. 17D illustrates a schematic diagram 1740 of a relationship between a time segment and location information in accordance with some example embodiments of the present disclosure. As shown in FIG. 17D, it is assumed that the time segment is [t1, t2] determined and reported by the terminal device. If a UE location is determined by the LMF after the time t2, i.e., outside the time segment, the UE location will not be transmitted back to the terminal device.
FIG. 17E illustrates a schematic diagram 1750 of an association of the indication 1232 and the information 1242 in accordance with some example embodiments of the present disclosure.
The terminal device 210 may transmit an indication 1232, which indicate 4 time segments and associated with 4 IDs of CIRs. For example, the indication 1232 may indicate: a CIR with ID 1 and its time segment (valid time 1) , a CIR a with ID 2 and its time segment (valid time 2) , a CIR with ID 3 and its time segment (valid time 3) , and a CIR with ID 4 and its time segment (valid time 4) .
The LMF 230 may determine corresponding location (s) . For example, the LMF 230 may determine location 1 for CIR 2 and location 2 for CIR 3. The LMF 230 may transmit information 1242 including the location 1 and the location 2 to the terminal device 210. In addition, the LMF 230 may further indicate the correspondence of the location (s) with the CIR (s) . For example, the information 1242 may further include the corresponding IDs of CIRs, such as {2, 3} . For example, the information 1242 may further include a bitmap to indicate the corresponding IDs of CIRs, such as {0110} .
FIG. 18 illustrates a schematic diagram 1800 of the input and ground truth label data items in accordance with some embodiments of the present disclosure. As shown in FIG. 18, the terminal device 210 may determine the CIR, PDP, or DP by measuring of DL RS, and the network device 220 may determine TOA/TDOA by measuring of UL RS.
It is assumed that the data matching is performed at the terminal device 210 or at a network device 220 (such as a serving gNB) , e.g., related to subcases 2-3 and 2-4 in Table 2.
In some examples, the data matching may be performed at the terminal device 210. For example, the terminal device 210 may determine multiple input data items of an AI/ML positioning model, where the multiple input data items may include CIR, PDP, or DP. The terminal device 210 may further receive multiple ground truth label data items (such as TOA, or TDOA) of the AI/ML positioning model, e.g., from the serving gNB which may be one of the network devices 220-1 to 220-3 or may be a further network device different from any of the network devices 220-1 to 220-3. In addition, the terminal device 210 may further match to determine at least one matched instance.
In some other examples, the data matching may be performed at a network device 220 (such as a serving gNB) . For example, the serving gNB may be one of the network devices 220-1 to 220-3 or may be a further network device different from any of the network devices 220-1 to 220-3. For example, the serving gNB may receive multiple input data items (such as CIR, PDP, or DP) from the terminal device 210. The serving gNB may determine or receive multiple ground truth label data items (such as TOA or TDOA) of the AI/ML positioning model. In addition, the serving gNB may further match to determine at least one matched instance.
According to the example embodiments described with reference to FIGS. 12-18, the data matching for multiple TRPs scenario is discussed. Specifically, at least one matched instance may be determined and be used for AI/ML positioning model.
FIG. 19 illustrates a flowchart of an example method 1900 implemented at a first device in accordance with some embodiments of the present disclosure. For example, the first device may be one of: a terminal device 210, a network device 220, or an LMF with reference to FIGS. 2A-2B, or may be a further network device (such as a DF) .
At block 1910, the first device obtains multiple input data items of an AI/ML positioning model. At block 1920, the first device obtains multiple ground truth label data items of the AI/ML positioning model. At block 1930, the first device determines a match between at least one of the multiple input data items and at least one of the multiple ground truth label data items, to obtain at least one matched instance.
In some example embodiments, the first device determines a first time stamp of a first input data item; determines a second time stamp of a first ground truth label data item; and if a time difference between the first time stamp and the second stamp is not larger than a first threshold, the first device determines a matched instance comprising the first input data item and the first ground truth label data item.
In some example embodiments, if the time length between the first time stamp and the second stamp is larger than the first threshold, the first device determines an instance comprising the first input data item for unsupervised learning of the AI/ML positioning model.
In some example embodiments, the first device determines a time duration for data matching; determines a subset of the multiple input data items and a subset of the multiple ground truth label data items within the time duration, wherein the multiple input data items and the multiple ground truth label data items are ordered in a chronological order; and matches the subset of the multiple input data items with the subset of the multiple ground truth label data items in a descending order or in an ascending order.
In some example embodiments, a number of the subset of the multiple input data items is larger than a number of the subset of the multiple ground truth label data items. In some example embodiments, the first device determines that one or more of the subset of the multiple input data items which are not matched with any of the subset of the multiple ground truth label data items as one or more instances for unsupervised learning of the AI or ML positioning model.
In some example embodiments, the first device is a terminal device, and the terminal device receives, from a network device, information indicating the first threshold, where the first threshold is associated with at least one of: a positioning accuracy, or a transmission delay between the terminal device and the network device.
In some example embodiments, the first device is a terminal device, and the terminal device receives, from a network device, information indicating the time duration, wherein the information comprises at least one of: a start of the time duration, a length of the time duration, or an end of the time duration.
In some example embodiments, the start of the time duration is indicated by a first SFN and a first slot number, and/or the end of the time duration is indicated by a second SFN and a second slot number.
In some example embodiments, the first device is a terminal device, and the terminal device receives, from a network device, the multiple ground truth label data items, wherein the multiple ground truth label data items comprise at least multiple TOA items or multiple TDOA items, where the multiple input data items are determined by the terminal device and comprise multiple CIR, PDP, or DP items.
In some example embodiments, the first device is a terminal device, and the terminal device receives, from the network device, the multiple input data items, wherein the multiple input data items comprise multiple CIR, PDP, or DP items, where the multiple ground truth label data items are determined by the terminal device and comprise at least multiple TOA items or multiple LOS or NLOS indicators.
In some example embodiments, the terminal device transmits, to the network device or to an LMF, a number of the at least one matched instance.
In some example embodiments, the first device is a network device, and the network device receives, from the terminal device, the multiple input data items, wherein the multiple input data items comprise multiple CIR, PDP, or DP items, where the multiple ground truth label data items are determined by the network device and comprise at least multiple TOA items or multiple TDOA items.
In some example embodiments, the first device is a network device, and the network device receives, from a terminal device, the multiple ground truth label data items, wherein the multiple ground truth label data items comprise at least multiple TOA items or multiple LOS or NLOS indicators, where the multiple input data items are determined by the network device and comprise multiple CIR, PDP, or DP items.
In some example embodiments, the first device is a further network device, and the further network device receives, from a terminal device, the multiple ground truth label data items, and receives, from a network device, the multiple input data items.
In some example embodiments, the first device is a further network device, and the further network device receives, from a terminal device, the multiple input data items, and receives, from a network device, the multiple ground truth label data items.
In some example embodiments, the further network device comprises an LMF or a data function (DF) .
In some example embodiments, the first device is a terminal device, and the terminal device transmits, to an LMF, an indication of a time segment set of the multiple input data items; and receives, from the LMF, information comprising the multiple ground truth label data items associated with the time segment set; where the multiple input data items comprise multiple CIR, PDP, or DP items, and the multiple ground truth label data items comprise multiple terminal locations.
In some example embodiments, the time segment set comprises all time segments of the multiple input data items.
In some example embodiments, if a change of a first time segment is larger than a second threshold, the terminal device determines that the time segment set comprises the first time segment.
In some example embodiments, if a time length between a first middle of the first time segment and a second middle of the second time segment is larger than the second threshold, the terminal device determines that the change of the first time segment is larger than the second threshold, where the second time segment is a precedent time segment closest to the first time segment.
In some example embodiments, the indication of the time segment set comprises a sequence of timings and multiple input identities, wherein every two adjacent timings in the sequence indicate a time segment associated with one of the multiple input identities.
In some example embodiments, a number of the multiple ground truth label data items is smaller than a number of time segments in the time segment set, and wherein the information further comprises one or more input identities associated with the multiple ground truth label data items.
In some example embodiments, the one or more input identities are indicated by a bitmap comprising multiple bits, wherein a number of the multiple bits equals to the number of the time segments in the time segment set.
In some example embodiments, the first device is an LMF, and the LMF receives, from a terminal device, an indication of a time segment set containing the multiple input data items; where the multiple input data items comprise multiple CIR, PDP, or DP items, and the multiple ground truth label data items comprise multiple terminal locations.
In some example embodiments, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among multiple TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the multiple TRPs.
In some example embodiments, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
FIG. 20 illustrates a flowchart of an example method 2000 implemented at a terminal device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 2000 will be described from the perspective of the terminal device 210 with reference to FIG. 2B.
At block 2010, the terminal device determines multiple input data items of an AI/ML positioning model. At block 2020, the terminal device transmits, to an LMF, an indication of a time segment set of the multiple input data items.
In some example embodiments, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among multiple TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the multiple TRPs.
In some example embodiments, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
In some example embodiments, the multiple input data items comprise multiple multiple CIR, PDP, or DP items.
FIG. 21 illustrates a flowchart of an example method 2100 implemented at a network device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 2100 will be described from the perspective of the network device 220 with reference to FIGS. 2A-2B.
At block 2110, the network device determines multiple input data items or multiple ground truth label data items of an AI or machine learning (ML) positioning model. At block 2120, the network device transmits, to a terminal device or a further network device, the multiple input data items or the multiple ground truth label data items.
In some example embodiments, the network device transmits, to the terminal device, information indicating a first threshold, wherein the first threshold is used for data matching by the terminal device and the first threshold is associated with at least one of: a positioning accuracy, or a transmission delay between the terminal device and the network device.
In some example embodiments, the network device transmits, to the terminal device, information indicating a time duration, wherein the time duration is used for data matching by the terminal device and the information comprises at least one of: a start of the time duration, a length of the time duration, or an end of the time duration.
In some example embodiments, the start of the time duration is indicated by a first SFN and a first slot number, and/or the end of the time duration is indicated by a second SFN and a second slot number.
In some example embodiments, the multiple input data items comprise multiple CIR, PDP, or DP items.
In some example embodiments, the multiple ground truth label data items comprise at least one of: multiple LOS or NLOS indicators, multiple TOA items, or multiple TDOA items.
FIG. 22 illustrates a flowchart of an example method 2200 implemented at an LMF in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 2200 will be described from the perspective of the LMF 230 with reference to FIG. 2B.
At block 2210, the LMF receives, from a terminal device, an indication of a time segment set of multiple input data items of an AI/ML positioning model. At block 2220, the LMF transmits, to the terminal device, information comprising multiple ground truth label data items associated with the multiple time segments; where the multiple input data items comprise multiple CIR, PDP, or DP items, and the multiple ground truth label data items comprise multiple terminal locations.
In some example embodiments, the indication of the time segment set comprises a sequence of timings and multiple input identities, wherein every two adjacent timings in the sequence indicate a time segment associated with one of the multiple input identities.
In some example embodiments, a number of the multiple ground truth label data items is smaller than a number of time segments in the time segment set, and wherein the information further comprises one or more input identities associated with the multiple ground truth label data items.
In some example embodiments, the one or more input identities are indicated by a bitmap comprising multiple bits, wherein a number of the multiple bits equals to the number of time segments in the time segment set.
In some example embodiments, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among multiple TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the multiple TRPs.
In some example embodiments, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
Details of some embodiments according to the present disclosure have been described with reference to FIGS. 5-22. Now an example implementation of the terminal device and the network device will be discussed below.
In some example embodiments, a first device comprises circuitry configured to: obtain a plurality of input data items of an AI or ML positioning model; obtain a plurality of ground truth label data items of the AI or ML positioning model; and determine a match between at least one of the plurality of input data items and at least one of the plurality of ground truth label data items, to obtain at least one matched instance.
In some example embodiments, the first device comprises circuitry configured to: determine a first time stamp of a first input data item; determine a second time stamp of a first ground truth label data item; and in accordance with a determination that a time difference between the first time stamp and the second stamp is not larger than a first threshold, determine a matched instance comprising the first input data item and the first ground truth label data item.
In some example embodiments, the first device comprises circuitry configured to: in accordance with a determination that the time length between the first time stamp and the second stamp is larger than the first threshold, determine an instance comprising the first input data item for unsupervised learning of the AI or ML positioning model.
In some example embodiments, the first device comprises circuitry configured to: determine a time duration for data matching; determine a subset of the plurality of input data items and a subset of the plurality of ground truth label data items within the time duration, wherein the plurality of input data items and the plurality of ground truth label data items are ordered in a chronological order; and match the subset of the plurality of input data items with the subset of the plurality of ground truth label data items in a descending order or in an ascending order.
In some example embodiments, a number of the subset of the plurality of input data items is larger than a number of the subset of the plurality of ground truth label data items, and the first device comprises circuitry configured to: determine that one or more of the subset of the plurality of input data items which are not matched with any of the subset of the plurality of ground truth label data items as one or more instances for unsupervised learning of the AI or ML positioning model.
In some example embodiments, the first device is a terminal device, and the first device comprises circuitry configured to: receive, from a network device, information indicating the first threshold, wherein the first threshold is associated with at least one of: a positioning accuracy, or a transmission delay between the terminal device and the network device.
In some example embodiments, the first device is a terminal device, and the first device comprises circuitry configured to: receive, from a network device, information indicating the time duration, wherein the information comprises at least one of: a start of the time duration, a length of the time duration, or an end of the time duration.
In some example embodiments, the start of the time duration is indicated by a first SFN and a first slot number, and/or the end of the time duration is indicated by a second SFN and a second slot number.
In some example embodiments, the first device is a terminal device, and the first device comprises circuitry configured to: receive, from a network device, the plurality of ground truth label data items, wherein the plurality of ground truth label data items comprise at least a plurality of TOA items or a plurality of TDOA items, wherein the plurality of input data items are determined by the terminal device and comprise a plurality of CIR, PDP, or DP items.
In some example embodiments, the first device is a terminal device, and the first device comprises circuitry configured to: receive, from the network device, the plurality of input data items, wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, wherein the plurality of ground truth label data items are determined by the terminal device and comprise at least a plurality of TOA items or a plurality of LOS or NLOS indicators.
In some example embodiments, the first device comprises circuitry configured to: transmit, to the network device or to an LMF, a number of the at least one matched instance.
In some example embodiments, the first device is a network device, and the first device comprises circuitry configured to: receive, from the terminal device, the plurality of input data items, wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, wherein the plurality of ground truth label data items are determined by the network device and comprise at least a plurality of TOA items or a plurality of TDOA items.
In some example embodiments, the first device is a network device, and the first device comprises circuitry configured to: receive, from a terminal device, the plurality of ground truth label data items, wherein the plurality of ground truth label data items comprise at least a plurality of TOA items or a plurality of LOS or NLOS indicators, wherein the plurality of input data items are determined by the network device and comprise a plurality of CIR, PDP, or DP items.
In some example embodiments, the first device is a further network device, and the first device comprises circuitry configured to: receive, from a terminal device, the plurality of ground truth label data items, and receive, from a network device, the plurality of input data items.
In some example embodiments, the first device is a further network device, and the first device comprises circuitry configured to: receive, from a terminal device, the plurality of input data items, and receive, from a network device, the plurality of ground truth label data items.
In some example embodiments, the further network device comprises an LMF or a data function (DF) .
In some example embodiments, the first device is a terminal device, and the first device comprises circuitry configured to: transmit, to an LMF, an indication of a time segment set of the plurality of input data items; and receive, from the LMF, information comprising the plurality of ground truth label data items associated with the time segment set; wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In some example embodiments, the time segment set comprises all time segments of the plurality of input data items.
In some example embodiments, the first device comprises circuitry configured to: in accordance with a determination that a change of a first time segment is larger than a second threshold, determine that the time segment set comprises the first time segment.
In some example embodiments, the first device comprises circuitry configured to: in accordance with a determination that a time length between a first middle of the first time segment and a second middle of the second time segment is larger than the second threshold, determine that the change of the first time segment is larger than the second threshold, wherein the second time segment is a precedent time segment closest to the first time segment.
In some example embodiments, the indication of the time segment set comprises a sequence of timings and a plurality of input identities, wherein every two adjacent timings in the sequence indicate a time segment associated with one of the plurality of input identities.
In some example embodiments, a number of the plurality of ground truth label data items is smaller than a number of time segments in the time segment set, and wherein the information further comprises one or more input identities associated with the plurality of ground truth label data items.
In some example embodiments, the one or more input identities are indicated by a bitmap comprising a plurality of bits, wherein a number of the plurality of bits equals to the number of the time segments in the time segment set.
In some example embodiments, the first device is an LMF, and the first device comprises circuitry configured to: receive, from a terminal device, an indication of a time segment set containing the plurality of input data items; wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In some example embodiments, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.
In some example embodiments, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
In some example embodiments, a terminal device comprises circuitry configured to:determine a plurality of input data items of an AI or ML positioning model; and transmit, to an LMF, an indication of a time segment set of the plurality of input data items.
In some example embodiments, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.
In some example embodiments, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
In some example embodiments, the plurality of input data items comprise a plurality of a plurality of CIR, PDP, or DP items.
In some example embodiments, a network device comprises circuitry configured to: determine a plurality of input data items or a plurality of ground truth label data items of an AI or ML positioning model; and transmit, to a terminal device or a further network device, the plurality of input data items or the plurality of ground truth label data items.
In some example embodiments, the network device comprises circuitry configured to: transmit, to the terminal device, information indicating a first threshold, wherein the first threshold is used for data matching by the terminal device and the first threshold is associated with at least one of: a positioning accuracy, or a transmission delay between the terminal device and the network device.
In some example embodiments, the network device comprises circuitry configured to: transmit, to the terminal device, information indicating a time duration, wherein the time duration is used for data matching by the terminal device and the information comprises at least one of: a start of the time duration, a length of the time duration, or an end of the time duration.
In some example embodiments, the start of the time duration is indicated by a first SFN and a first slot number, and/or the end of the time duration is indicated by a second SFN and a second slot number.
In some example embodiments, the plurality of input data items comprise a plurality of CIR, PDP, or DP items.
In some example embodiments, the plurality of ground truth label data items comprise at least one of: a plurality of LOS or NLOS indicators, a plurality of TOA items, or a plurality of TDOA items.
In some example embodiments, an LMF comprises circuitry configured to: receive, from a terminal device, an indication of a time segment set of a plurality of input data items of an AI or ML positioning model; and transmit, to the terminal device, information comprising a plurality of ground truth label data items associated with the plurality of time segments; wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In some example embodiments, the indication of the time segment set comprises a sequence of timings and a plurality of input identities, wherein every two adjacent timings in the sequence indicate a time segment associated with one of the plurality of input identities.
In some example embodiments, a number of the plurality of ground truth label data items is smaller than a number of time segments in the time segment set, and wherein the information further comprises one or more input identities associated with the plurality of ground truth label data items.
In some example embodiments, the one or more input identities are indicated by a bitmap comprising a plurality of bits, wherein a number of the plurality of bits equals to the number of time segments in the time segment set.
In some example embodiments, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.
In some example embodiments, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
FIG. 23 illustrates a simplified block diagram of a device 2300 that is suitable for implementing embodiments of the present disclosure. The device 2300 can be considered as a further example implementation of the first device, the terminal device, the network device, or the LMF as described above. Accordingly, the device 2300 can be implemented at or as at least a part of the terminal device or the network device.
As shown, the device 2300 includes a processor 2310, a memory 2320 coupled to the processor 2310, a suitable transceiver 2340 coupled to the processor 2310, and a communication interface coupled to the transceiver 2340. The memory 2320 stores at least a part of a program 2330. The transceiver 2340 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 2340 may include at least one of a transmitter and a receiver. The transmitter and the receiver may be functional modules or physical entities. The transceiver2340 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) /serving gateway (SGW) /user plane function (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 program 2330 is assumed to include program instructions that, when executed by the associated processor 2310, enable the device 2300 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 3-7. The embodiments herein may be implemented by computer software executable by the processor 2310 of the device 2300, or by hardware, or by a combination of software and hardware. The processor 2310 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 2310 and memory 2320 may form processing means 2350 adapted to implement various embodiments of the present disclosure.
The memory 2320 may be of any type suitable to the local technical network and may be implemented using any suitable data storage technology, such as a non-transitory computer readable storage medium, semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. While only one memory 2320 is shown in the device 2300, there may be several physically distinct memory modules in the device 2300. The processor 2310 may be of any type suitable to the local technical network, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 2300 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.
In summary, embodiments of the present disclosure may provide the following solutions.
The present disclosure provides a first device, comprising at least one processor configured to cause the first device at least to: obtain a plurality of input data items of an AI or ML positioning model; obtain a plurality of ground truth label data items of the AI or ML positioning model; and determine a match between at least one of the plurality of input data items and at least one of the plurality of ground truth label data items, to obtain at least one matched instance.
In one embodiment, the first device as above, the first device is caused to: determine a first time stamp of a first input data item; determine a second time stamp of a first ground truth label data item; and in accordance with a determination that a time difference between the first time stamp and the second stamp is not larger than a first threshold, determine a matched instance comprising the first input data item and the first ground truth label data item.
In one embodiment, the first device as above, the first device is caused to: in accordance with a determination that the time length between the first time stamp and the second stamp is larger than the first threshold, determine an instance comprising the first input data item for unsupervised learning of the AI or ML positioning model.
In one embodiment, the first device as above, the first device is caused to: determine a time duration for data matching; determine a subset of the plurality of input data items and a subset of the plurality of ground truth label data items within the time duration, wherein the plurality of input data items and the plurality of ground truth label data items are ordered in a chronological order; and match the subset of the plurality of input data items with the subset of the plurality of ground truth label data items in a descending order or in an ascending order.
In one embodiment, the first device as above, a number of the subset of the plurality of input data items is larger than a number of the subset of the plurality of ground truth label data items, and wherein the first device is caused to: determine that one or more of the subset of the plurality of input data items which are not matched with any of the subset of the plurality of ground truth label data items as one or more instances for unsupervised learning of the AI or ML positioning model.
In one embodiment, the first device as above, the first device is a terminal device, and wherein the terminal device is caused to: receive, from a network device, information indicating the first threshold, wherein the first threshold is associated with at least one of: a positioning accuracy, or a transmission delay between the terminal device and the network device.
In one embodiment, the first device as above, the first device is a terminal device, and wherein the terminal device is caused to: receive, from a network device, information indicating the time duration, wherein the information comprises at least one of: a start of the time duration, a length of the time duration, or an end of the time duration.
In one embodiment, the first device as above, the start of the time duration is indicated by a first SFN and a first slot number, and/or the end of the time duration is indicated by a second SFN and a second slot number.
In one embodiment, the first device as above, the first device is a terminal device, and wherein the terminal device is caused to: receive, from a network device, the plurality of ground truth label data items, wherein the plurality of ground truth label data items comprise at least a plurality of TOA items or a plurality of TDOA items, wherein the plurality of input data items are determined by the terminal device and comprise a plurality of CIR, PDP, or DP items.
In one embodiment, the first device as above, the first device is a terminal device, and wherein the terminal device is caused to: receive, from the network device, the plurality of input data items, wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, wherein the plurality of ground truth label data items are determined by the terminal device and comprise at least a plurality of TOA items or a plurality of LOS or NLOS indicators.
In one embodiment, the first device as above, the terminal device is caused to: transmit, to the network device or to an LMF, a number of the at least one matched instance.
In one embodiment, the first device as above, the first device is a network device, and wherein the network device is caused to: receive, from the terminal device, the plurality of input data items, wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, wherein the plurality of ground truth label data items are determined by the network device and comprise at least a plurality of TOA items or a plurality of TDOA items.
In one embodiment, the first device as above, the first device is a network device, and wherein the network device is caused to: receive, from a terminal device, the plurality of ground truth label data items, wherein the plurality of ground truth label data items comprise at least a plurality of TOA items or a plurality of LOS or NLOS indicators, wherein the plurality of input data items are determined by the network device and comprise a plurality of CIR, PDP, or DP items.
In one embodiment, the first device as above, the first device is a further network device, and wherein the further network device is caused to: receive, from a terminal device, the plurality of ground truth label data items, and receive, from a network device, the plurality of input data items.
In one embodiment, the first device as above, the first device is a further network device, and wherein the further network device is caused to: receive, from a terminal device, the plurality of input data items, and receive, from a network device, the plurality of ground truth label data items.
In one embodiment, the first device as above, the further network device comprises an LMF or a data function (DF) .
In one embodiment, the first device as above, the first device is a terminal device, and wherein the terminal device is caused to: transmit, to an LMF, an indication of a time segment set of the plurality of input data items; and receive, from the LMF, information comprising the plurality of ground truth label data items associated with the time segment set; wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In one embodiment, the first device as above, the time segment set comprises all time segments of the plurality of input data items.
In one embodiment, the first device as above, the terminal device is caused to: in accordance with a determination that a change of a first time segment is larger than a second threshold, determine that the time segment set comprises the first time segment.
In one embodiment, the first device as above, the terminal device is caused to: in accordance with a determination that a time length between a first middle of the first time segment and a second middle of the second time segment is larger than the second threshold, determine that the change of the first time segment is larger than the second threshold, wherein the second time segment is a precedent time segment closest to the first time segment.
In one embodiment, the first device as above, the indication of the time segment set comprises a sequence of timings and a plurality of input identities, wherein every two adjacent timings in the sequence indicate a time segment associated with one of the plurality of input identities.
In one embodiment, the first device as above, a number of the plurality of ground truth label data items is smaller than a number of time segments in the time segment set, and wherein the information further comprises one or more input identities associated with the plurality of ground truth label data items.
In one embodiment, the first device as above, the one or more input identities are indicated by a bitmap comprising a plurality of bits, wherein a number of the plurality of bits equals to the number of the time segments in the time segment set.
In one embodiment, the first device as above, the first device is an LMF, and wherein the LMF is caused to: receive, from a terminal device, an indication of a time segment set containing the plurality of input data items; wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In one embodiment, the first device as above, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.
In one embodiment, the first device as above, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
The present disclosure provides a terminal device, comprising at least one processor configured to cause the terminal device at least to: determine a plurality of input data items of an AI or ML positioning model; and transmit, to an LMF, an indication of a time segment set of the plurality of input data items.
In one embodiment, the terminal device as above, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.
In one embodiment, the terminal device as above, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
In one embodiment, the terminal device as above, the plurality of input data items comprise a plurality of a plurality of CIR, PDP, or DP items.
The present disclosure provides a network device, comprising at least one processor configured to cause the network device at least to: determine a plurality of input data items or a plurality of ground truth label data items of an AI or ML positioning model; and transmit, to a terminal device or a further network device, the plurality of input data items or the plurality of ground truth label data items.
In one embodiment, the network device as above, the network device is caused to: transmit, to the terminal device, information indicating a first threshold, wherein the first threshold is used for data matching by the terminal device and the first threshold is associated with at least one of: a positioning accuracy, or a transmission delay between the terminal device and the network device.
In one embodiment, the network device as above, the network device is caused to: transmit, to the terminal device, information indicating a time duration, wherein the time duration is used for data matching by the terminal device and the information comprises at least one of: a start of the time duration, a length of the time duration, or an end of the time duration.
In one embodiment, the network device as above, the start of the time duration is indicated by a first SFN and a first slot number, and/or the end of the time duration is indicated by a second SFN and a second slot number.
In one embodiment, the network device as above, the plurality of input data items comprise a plurality of CIR, PDP, or DP items.
In one embodiment, the network device as above, the plurality of ground truth label data items comprise at least one of: a plurality of LOS or NLOS indicators, a plurality of TOA items, or a plurality of TDOA items.
The present disclosure provides an LMF, comprising at least one processor configured to cause the LMF at least to: receive, from a terminal device, an indication of a time segment set of a plurality of input data items of an AI or ML positioning model; and transmit, to the terminal device, information comprising a plurality of ground truth label data items associated with the plurality of time segments; wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
In one embodiment, the LMF as above, the indication of the time segment set comprises a sequence of timings and a plurality of input identities, wherein every two adjacent timings in the sequence indicate a time segment associated with one of the plurality of input identities.
In one embodiment, the LMF as above, a number of the plurality of ground truth label data items is smaller than a number of time segments in the time segment set, and wherein the information further comprises one or more input identities associated with the plurality of ground truth label data items.
In one embodiment, the LMF as above, the one or more input identities are indicated by a bitmap comprising a plurality of bits, wherein a number of the plurality of bits equals to the number of time segments in the time segment set.
In one embodiment, the LMF as above, each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first TRP among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.
In one embodiment, the LMF as above, the start time is indicated by at least one of: a first SFN, a first slot number, or a first symbol number, and the end time is indicated by at least one of: a second SFN, a second slot number, or a second symbol number.
The present disclosure provides a method of communication, comprising the operations implemented at the first device discussed above.
The present disclosure provides a method of communication, comprising the operations implemented at the terminal device discussed above.
The present disclosure provides a method of communication, comprising the operations implemented at the network device discussed above.
The present disclosure provides a method of communication, comprising the operations implemented at the LMF discussed above.
The present disclosure provides a first device, comprising: a processor; and a memory storing computer program codes; the memory and the computer program codes configured to, with the processor, cause the first device to perform the method implemented at the first device discussed above.
The present disclosure provides a terminal device, comprising: a processor; and a memory storing computer program codes; the memory and the computer program codes configured to, with the processor, cause the terminal device to perform the method implemented at the terminal device discussed above.
The present disclosure provides a network device, comprising: a processor; and a memory storing computer program codes; the memory and the computer program codes configured to, with the processor, cause the network device to perform the method implemented at the network device discussed above.
The present disclosure provides an LMF, comprising: a processor; and a memory storing computer program codes; the memory and the computer program codes configured to, with the processor, cause the LMF to perform the method implemented at the LMF discussed above.
The present disclosure provides a computer readable medium having instructions stored thereon, the instructions, when executed by a processor of an apparatus, causing the apparatus to perform the method implemented at a first device, a terminal device, an LMF, or a network device discussed above.
Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representation, it will be appreciated that the blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.
The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the process or method as described above with reference to FIGS. 5-22. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowcharts and/or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
The above program code may be embodied on a machine readable medium, which may be any tangible medium that may contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine readable medium may be a machine readable signal medium or a machine readable storage medium. A machine readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or Flash memory) , an optical fiber, a portable compact disc read-only memory (CD-ROM) , an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.
Although the present disclosure has been described in language specific to structural features and/or methodological acts, it is to be understood that the present 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

A first device comprising at least one processor configured to cause the first device at least to:

obtain a plurality of input data items of an artificial intelligence (AI) or machine learning (ML) positioning model;

obtain a plurality of ground truth label data items of the AI or ML positioning model; and

determine a match between at least one of the plurality of input data items and at least one of the plurality of ground truth label data items, to obtain at least one matched instance.
The first device of claim 1, wherein the first device is caused to:

determine a first time stamp of a first input data item;

determine a second time stamp of a first ground truth label data item; and

in accordance with a determination that a time difference between the first time stamp and the second stamp is not larger than a first threshold, determine a matched instance comprising the first input data item and the first ground truth label data item.
The first device of claim 1, wherein the first device is caused to:

determine a time duration for data matching;

determine a subset of the plurality of input data items and a subset of the plurality of ground truth label data items within the time duration, wherein the plurality of input data items and the plurality of ground truth label data items are ordered in a chronological order; and

match the subset of the plurality of input data items with the subset of the plurality of ground truth label data items in a descending order or in an ascending order.
The first device of claim 2, wherein the first device is a terminal device, and wherein the terminal device is caused to:

receive, from a network device, information indicating the first threshold, wherein the first threshold is associated with at least one of:

a positioning accuracy, or

a transmission delay between the terminal device and the network device.
The first device of claim 3, wherein the first device is a terminal device, and wherein the terminal device is caused to:

receive, from a network device, information indicating the time duration, wherein the information comprises at least one of:

a start of the time duration,

a length of the time duration, or

an end of the time duration.
The first device of any of claims 2-5, wherein the first device is a terminal device, and wherein the terminal device is caused to:

receive, from a network device, the plurality of ground truth label data items, wherein the plurality of ground truth label data items comprise at least a plurality of time of arrival (TOA) items or a plurality of time difference of arrival (TDOA) items,

wherein the plurality of input data items are determined by the terminal device and comprise a plurality of channel impulse response (CIR) , power delay profile (PDP) , or delay of path (DP) items.
The first device of any of claims 2-5, wherein the first device is a terminal device, and wherein the terminal device is caused to:

receive, from the network device, the plurality of input data items, wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items,

wherein the plurality of ground truth label data items are determined by the terminal device and comprise at least a plurality of TOA items or a plurality of line of sight (LOS) or non line of sight (NLOS) indicators.
The first device of claim 6 or 7, wherein the terminal device is caused to:

transmit, to the network device or to a location management function (LMF) , a number of the at least one matched instance.
The first device of claim 2 or 3, wherein the first device is a network device, and wherein the network device is caused to:

receive, from the terminal device, the plurality of input data items, wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items,

wherein the plurality of ground truth label data items are determined by the network device and comprise at least a plurality of TOA items or a plurality of TDOA items.
The first device of claim 2 or 3, wherein the first device is a network device, and wherein the network device is caused to:

receive, from a terminal device, the plurality of ground truth label data items, wherein the plurality of ground truth label data items comprise at least a plurality of TOA items or a plurality of LOS or NLOS indicators,

wherein the plurality of input data items are determined by the network device and comprise a plurality of CIR, PDP, or DP items.
The first device of claim 9 or 10, wherein the network device comprises an LMF or a data function (DF) .
The first device of claim 1, wherein the first device is a terminal device, and wherein the terminal device is caused to:

transmit, to an LMF, an indication of a time segment set of the plurality of input data items; and

receive, from the LMF, information comprising the plurality of ground truth label data items associated with the time segment set;

wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
The first device of claim 12, wherein the terminal device is caused to:

in accordance with a determination that a change of a first time segment is larger than a second threshold, determine that the time segment set comprises the first time segment.
The first device of claim 13, wherein the terminal device is caused to:

in accordance with a determination that a time length between a first middle of the first time segment and a second middle of the second time segment is larger than the second threshold, determine that the change of the first time segment is larger than the second threshold,

wherein the second time segment is a precedent time segment closest to the first time segment.
The first device of any of claims 12-14, wherein the indication of the time segment set comprises a sequence of timings and a plurality of input identities, wherein every two adjacent timings in the sequence indicate a time segment associated with one of the plurality of input identities.
The first device of any of claims 12-15, wherein a number of the plurality of ground truth label data items is smaller than a number of time segments in the time segment set, and wherein the information further comprises one or more input identities associated with the plurality of ground truth label data items.
The first device of claim 1, wherein the first device is an LMF, and wherein the LMF is caused to:

receive, from a terminal device, an indication of a time segment set containing the plurality of input data items;

wherein the plurality of input data items comprise a plurality of CIR, PDP, or DP items, and the plurality of ground truth label data items comprise a plurality of terminal locations.
The first device of any of claims 12-17, wherein each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first transmission reception point (TRP) among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.
A terminal device comprising at least one processor configured to cause the terminal device at least to:

determine a plurality of input data items of an artificial intelligence (AI) or machine learning (ML) positioning model; and

transmit, to a location management function (LMF) , an indication of a time segment set of the plurality of input data items.
The terminal device of claim 19, wherein each of time segments in the time segment set is indicated by a start time and an end time, and wherein the start time indicates a receiving time of a first received reference signal from a first transmission reception point (TRP) among a plurality of TRPs and the end time indicates a receiving time of a last received reference signal from a second TRP among the plurality of TRPs.