WO2024108445A1

WO2024108445A1 - Methods, devices and medium for communication

Info

Publication number: WO2024108445A1
Application number: PCT/CN2022/133833
Authority: WO
Inventors: Wei Chen; Zhen He; Peng Guan; Gang Wang
Original assignee: Nec Corporation; Gang Wang
Priority date: 2022-11-23
Filing date: 2022-11-23
Publication date: 2024-05-30

Abstract

Example embodiments of the present disclosure relate to a solution for monitoring artificial intelligence/machine learning (AI/ML) model for positioning. In this solution, a terminal device receives from a first network device, a positioning reference signal (PRS) resource configuration. The terminal device determines at least one reference positioning parameter of the terminal device by detecting a PRS for at least one time based on the PRS resource configuration. The terminal device determines at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of an AI/ML model. The terminal device transmits, to a second network device, information indicating the at least one deviation.

Description

METHODS, DEVICES AND MEDIUM FOR COMMUNICATION

FIELDS

Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to methods, devices, and medium for monitoring artificial intelligence/machine learning (AI/ML) model for positioning.

BACKGROUND

In the telecommunication industry, artificial intelligence/machine learning (AI/ML) models have been employed in telecommunication systems to improve the performance of telecommunications systems. For example, the AI/ML models have been employed in air interface for positioning of devices in a communication network. Works are on going regarding how to ensure accuracy of output of the AI/ML model, in order to improve AI/ML based positioning accuracy.

SUMMARY

In general, embodiments of the present disclosure provide methods, devices and computer storage medium for monitoring artificial intelligence/machine learning (AI/ML) model for positioning.

In a first aspect, there is provided a communication method. The method comprises: receiving, at a terminal device and from a first network device, a positioning reference signal (PRS) resource configuration; determining at least one reference positioning parameter of the terminal device by detecting a PRS for at least one time based on the PRS resource configuration; determining at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of an artificial intelligence/machine learning (AI/ML) model; and transmitting, to a second network device, information indicating the at least one deviation.

In a second aspect, there is provided a communication method. The method comprises: determining, at a terminal device, a first reference location of the terminal device by detecting a positioning reference signal (PRS) ; transmitting, to a network device, information indicating a first location deviation between the first reference location and a first predicted location of the terminal device, the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model; receiving, from the network device, a device configuration for configuring the terminal device as a positioning reference unit (PRU) ; and transmitting, to the network device, a feedback indicating acceptance or rejection of the device configuration.

In a third aspect, there is provided a communication method. The method comprises: receiving, at a network device and from at least one terminal device, information indicating a plurality of deviations between reference positioning parameters and predicted positioning parameters, the reference positioning parameters being determined by the at least one terminal device by detecting a positioning reference signal (PRS) based on the at least one resource configuration, and the predicted positioning parameters being determined by the at least one terminal device from outputs of an artificial intelligence/machine learning (AI/ML) model; and determining an action to be performed on the AI/ML model based on the plurality of deviations.

In a fourth aspect, there is provided a communication method. The method comprises: receiving, at a network device and from a terminal device, information indicating a first location deviation between a first reference location and a first predicted location of the terminal device, the first reference location being determined by detecting a positioning reference signal (PRS) , and the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model transferred to the terminal device; determining, based at least in part on the first location deviation, whether the terminal device is capable of acting as a positioning reference unit (PRU) ; in accordance with a determination that the terminal device is capable of acting as a PRU, transmitting, to the terminal device, a device configuration for configuring the terminal device as a PRU; and receiving, from the terminal device, a feedback indicating acceptance or rejection of the device configuration.

In a fifth aspect, there is provided a terminal device. The terminal device comprises at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the terminal device to perform the method according to the first, or second aspect.

In a sixth aspect, there is provided a network device. The network device comprises at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the network device to perform the method according to the third, or fourth aspect.

In a seventh 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 the first, second, third, or fourth aspect.

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 example communication environment in which example embodiments of the present disclosure can be implemented;

FIG. 2 illustrates example architecture for positioning of a terminal device according to some example embodiments of the present disclosure;

FIG. 3 illustrates a signaling flow for AI/ML model monitoring according to some example embodiments of the present disclosure;

FIG. 4A and FIG. 4B illustrate examples of PRS resource configuration according to some example embodiments of the present disclosure;

FIG. 5 illustrates example common PRS configuration for AI/ML model monitoring according to some example embodiments of the present disclosure;

FIG. 6A and FIG. 6B illustrate further examples of PRS resource configuration for AI/ML model monitoring according to some example embodiments of the present disclosure;

FIG. 7 illustrates a signaling flow of PRU configuration in accordance with some embodiments of the present disclosure;

FIG. 8 illustrates a flowchart of a method implemented at a terminal device according to some example embodiments of the present disclosure;

FIG. 9 illustrates another flowchart of a method implemented at a terminal device according to some example embodiments of the present disclosure;

FIG. 10 illustrates a flowchart of a method implemented at a network device according to some example embodiments of the present disclosure;

FIG. 11 illustrates another flowchart of a method implemented at a network device according to some example embodiments of the present disclosure;

FIG. 12 illustrates a simplified block diagram of an apparatus that is suitable for implementing example 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.

As used herein, the term ‘terminal device’ refers to any device having wireless or wired communication capabilities. Examples of the terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, internet of things (IoT) devices, Ultra-reliable and Low Latency Communications (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, devices 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 incorporate one or multiple Subscriber Identity Module (SIM) as known as Multi-SIM. The term “terminal device” can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.

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

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

The terminal or the network device may work on several frequency ranges, e.g., FR1 (e.g., 450 MHz to 6000 MHz) , FR2 (e.g., 24.25GHz to 52.6GHz) , frequency band larger than 100 GHz as well as Tera Hertz (THz) . It can further work on licensed/unlicensed/shared spectrum. The terminal device may have more than one connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.

The embodiments of the present disclosure may be performed in test equipment, e.g., signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator. In some embodiments, 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 some embodiments, the first network device may be a first RAT device and the second network device may be a second RAT device. In some embodiments, 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 or the second network device. In some embodiments, 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 some embodiments, 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.

As used herein, the singular forms ‘a’ , ‘an’ and ‘the’ are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term ‘includes’ and its variants are to be read as open terms that mean ‘includes, but is not limited to. ’ The term ‘based on’ is to be read as ‘at least in part based on. ’ The term ‘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.

As used herein, the term “resource, ” “transmission resource, ” “uplink resource, ” or “downlink resource” may refer to any resource for performing a communication, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

As mentioned above, AI/ML models have been used for positioning of the terminal device. For example, in some mechanisms, the terminal device, the network device and a location management function (LMF) for an AI/ML model may cooperate to ensure an accurate positioning. In some mechanisms, an AI/ML-based positioning is proposed to output a predicted location of the terminal device by an AI/ML model. In some mechanisms, an AI/ML-assisted positioning is proposed to output predicted intermediate measurements by an AI/ML model to assist the network device to calculate a location of the terminal device.

However, in some situations, if the AI/ML model is deteriorating, the outputs for the AI/ML-based positioning and the AI/ML-assisted positioning may become inaccurate. For example, if the environment of the terminal device changes, the AI/ML model may no longer predict an accurate positioning result or intermediate measurements for the terminal device located in the changed environment. Therefore, the performance of the AI/ML model need to be monitored to make sure that an accurate result for positioning can be achieved.

In some mechanisms, it is proposed to obtain ground truth labels and/or other training data by an entity. In some mechanisms, it is proposed to study potential signaling and procedure to enable data collection. In some mechanisms, the AI/ML model can be monitored based on the positioning related measurement results and associated ground truth labels collected at training/model entity. For example, the ground truth labels may be the actual location of the terminal device. For another example, the ground truth labels may be the ideal measured information such as terminal device measurement or reporting or other intermediate feature. However, the ground truth labels are difficult to collect.

In addition, compared with model training, model monitoring is more real-time and online since the model can be trained offline previously and transferred to the terminal device or network device for positioning inference when needed. However, it stills lack an efficient way for the AI/ML monitoring.

In some mechanisms, it is proposed that the terminal device receives a reference signal from a neighboring node via a non-line-of-sight (NLOS) transmission, and transmits an identification of the neighboring node to network equipment implementing the wireless communications network to facilitate estimating locations of the obstacles to signal transmission based on estimates of the location of the UE and the neighboring node. It is also proposed that the terminal device generates location information by receiving Global Positioning System (GPS) signals and further transmits the location information to the network equipment to facilitate estimation of the location of the terminal device. However, the terminal device location information obtained from GPS signals may not be reliable especially for an indoor scenario since no LOS path exists here, therefore the estimated locations of the obstacles may also not be reliable enough.

In order to solve at least part of the above problems or other potential problems, a solution for AI/ML model monitoring is proposed. According to embodiments of the present disclosure, a first network device transmits at least one positioning reference signal (PRS) resource configuration to at least one terminal device. The at least one terminal device determines at least one reference positioning parameter of the at least one terminal device by detecting a PRS for at least one time based on the PRS resource configuration. The at least one terminal device determines at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of an artificial intelligence/machine learning (AI/ML) model. A second network device receives information indicating a plurality of deviations between reference positioning parameters and predicted positioning parameters from the at least one terminal device and determines an action to be performed on the AI/ML model based on the plurality of deviations. In this way, the AI/ML model can be monitored based on the deviations between the reference positioning parameters and the predicted positioning parameters. By monitoring the AI/ML model and performing a proper action on the AI/ML model, the accuracy of AI/ML model-based positioning can be ensured.

In order to solve at least part of the above problems or other potential problems, another solution on AI/ML model monitoring is proposed. According to embodiments of the present disclosure, a terminal device determines a first reference location of the terminal device by detecting a positioning reference signal (PRS) . The terminal device transmits information indicating a first location deviation between the first reference location and a first predicted location of the terminal device to a network device, which may additionally be associated with an expected action which indicates the follow-up behavior for this AI/ML model. The first predicted location is determined from a first output of an artificial intelligence/machine learning (AI/ML) model. The network device determines whether the terminal device is capable of acting as a positioning reference unit (PRU) . If the network device determines that the terminal device is capable of acting as a PRU, the network transmits a device configuration for configuring the terminal device as a PRU to the terminal device. The terminal device receives the device configuration from the network device and transmits a feedback indicating acceptance or rejection of the device configuration to the network device. In this way, the network device can configure the terminal device as the PRU based on location deviation of a reference location and a predicted location determined based on the output of AI/ML model. In this way, the accuracy of the configured PRU can be ensured.

Principles and implementations of the present disclosure will be described in detail below with reference to the figures.

EXAMPLE COMMUNICATION ENVIRONMENT

FIG. 1 illustrates a schematic diagram of an example communication environment 100 in which example embodiments of the present disclosure can be implemented. In the communication environment 100, a plurality of communication devices, including a terminal device 110-1, a terminal device 110-2, . . . , a terminal device 110-N and a network device 120, can communicate with each other. The terminal device 110-1, terminal device 110-2, . . . , and terminal device 110-N can be collectively referred to as “terminal device (s) 110. ” The number N can be any suitable integer number.

In the example of FIG. 1, the terminal device 110 may be a UE and the network device 120 may be a base station serving the UE. The serving area of the network device 120 may be called a cell (not shown) . In the communication environment 100, the network device 120 and the terminal devices 110 may communicate data and control information to each other. The terminal devices 110 may also communicate with each other.

The communication environment 100 further comprises a network device 130. In some example embodiments, the network device 130 provides an AI/ML model 140 to one or more terminal devices 110. By way of example, the network device 130 may comprise an LMF. The network device 130 may train the AI/ML model 140 and transfer the trained AI/ML model 140 to the one or more terminal devices 110. In some other example embodiments, although not illustrated, the AI/ML model 140 may be trained and/or transferred by the network device 120 to the terminal devices 110. It would be appreciated that the AI/ML model 140 may be trained and/or transferred by any other entity in the communication environment 100.

In some example embodiments, the transferred AI/ML model 140 may be a trained model with a channel impulse response (CIR) as its input and a location of a terminal device as its output.

In some example embodiments, the network device 130 such as a LMF and/or the network device 120 such as a gNB may perform life cycle management for the AI/ML model 140. For example, the network device 130 and/or the network device 120 may retrain or fine-tune the AI/ML model 140.

As used herein, the term “AI/ML” model may be interchangeably with the term “model” . The term “AI/ML model training” may refer to a process to train an AI/ML model for example by learning the input/output relationship and obtained a trained AI/ML model for inference. The term “model monitoring” used herein may refer to a procedure that monitors the inference performance of the AI/ML model.

In some example embodiments, the network device 130 may perform a plurality of actions on the AI/ML model 140, including but not limited to data collection, model training, model registration, model deployment, model configuration, model inference operation, model selection, activation, deactivation, switching, and fallback operation, model monitoring, model update, model transfer, or other terminal device capability.

It is to be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number of devices configured to implementing example embodiments of the present disclosure. Although not shown, it would be appreciated that one or more additional devices may be located in the cell, and one or more additional cells may be deployed in the communication environment 100. It is noted that although illustrated as a network device, the network device 120 may be another device than a network device. Although illustrated as a terminal device, the terminal device 110 may be other device than a terminal device.

In the following, for the purpose of illustration, some example embodiments are described with the terminal device 110 operating as a UE and the network device 120 operating as a base station. However, in some example embodiments, operations described in connection with a terminal device may be implemented at a network device or other device, and operations described in connection with a network device may be implemented at a terminal device or other device.

In some example embodiments, if the terminal device 110 is a terminal device and the network device 120 is a network device, a link from the network device 120 to the terminal device 110 is referred to as a downlink (DL) , while a link from the terminal device 110 to the network device 120 is referred to as an uplink (UL) . In DL, the network device 120 is a transmitting (TX) device (or a transmitter) and the terminal device 110 is a receiving (RX) device (or a receiver) . In UL, the terminal device 110 is a TX device (or a transmitter) and the network device 120 is a RX device (or a receiver) .

The communications in the communication environment 100 may conform to any suitable standards including, but not limited to, Global System for Mobile Communications (GSM) , Long Term Evolution (LTE) , LTE-Evolution, LTE-Advanced (LTE-A) , New Radio (NR) , Wideband Code Division Multiple Access (WCDMA) , Code Division Multiple Access (CDMA) , GSM EDGE Radio Access Network (GERAN) , Machine Type Communication (MTC) and the like. 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.

In some example embodiments, the terminal device 110 may obtain its positioning information. FIG. 2 illustrates example architecture 200 of positioning of the terminal device 110 with NR or evolved universal terrestrial radio access (E-UTRA) access according to some example embodiments of the present disclosure.

In the architecture 200, position information may be requested by and reported to a client (e.g., an application) associated with the terminal device 110, or by a client within or attached to the core network. By way of example, an access and mobility management function (AMF) 250 may receive a request for some location service associated with a particular target terminal device from another entity (e.g., Gateway Mobile Location Centre (GMLC) or terminal device 110) . Alternatively, the AMF 250 itself may decide to initiate some location service on behalf of a particular target terminal device 110 (e.g., for an emergency call from the terminal device 110.

In some example embodiments, the AMF 250 may then send a location services request to an LMF 240. The LMF 240 may be the network device 130 in FIG. 1. The LMF 240 may process the location services request which may include transferring assistance data to the target terminal device 110 to assist with terminal device-based and/or terminal device-assisted positioning and/or may include positioning of the target terminal device 110. The LMF 240 may then return the result of the location service back to the AMF 250 (e.g., a position estimate for the terminal device 110. In the case of a location service requested by an entity other than the AMF 250 (e.g., a GMLC or terminal device) , the AMF 250 may return the location service result to this entity.

In some example embodiments, a next generation (NG) radio access network (RAN) (NG-RAN) node 210 may control several TRPs/TPs, such as remote radio heads, or DL-PRS-only TPs for support of PRS-based TBS. For example, the NG-RAN node 210 may control a NG-eNB 220 and/or a gNB 230. The NG-eNB 220 and/or the gNB 230 may be the network device 120 in FIG. 1.

In some example embodiments, the LMF 240 may have a proprietary signalling connection to an enhanced serving mobile location centre (E-SMLC) 260 which may enable the LMF 240 to access information from evolved universal terrestrial radio access network (E-UTRAN) , for example, to support the Observed Time Difference Of Arrival (OTDOA) for E-UTRA positioning method using downlink measurements obtained by a target terminal device of signals from eNBs 220 and/or PRS-only TPs in E-UTRAN.

Alternatively, or in addition, in some example embodiments, the LMF 240 may have a proprietary signaling connection to a secure user plane location (SUPL) location platform (SLP) 270. The SLP 270 is an SUPL entity responsible for positioning over the user plane.

It is to be understood that the above architecture 200 is only for the purpose of illustration, without suggesting any limitation. The terminal device 110 may obtain the positioning information by using any suitable architecture.

EXAMPLES OF MODEL MONITORING

Embodiments of the present disclosure will be described in detail below. FIG. 3 illustrates a signaling flow 300 for AI/ML model monitoring according to some example embodiments of the present disclosure. As shown in FIG. 3, the signaling flow 300 involves one or more terminal devices 110, the network device 120 and the network device 130 in FIG. 1. As used herein, the network device 130 may be referred to as a “first network device” , and the network device 120 may be referred to as a “second network device” . It is to be understood that the signaling flow 300 may involves more devices or less devices, and the number of devices illustrated in FIG. 3 is only for the purpose of illustration without suggesting any limitations.

In operation, the network device 130 transmits 305 a PRS resource configuration to the at least one terminal device 110. For example, the network device 130 may transmit 305 the PRS resource configuration to one terminal device 110 such as the terminal device 110-1. Alternatively, or in addition, in some example embodiments, the network device 130 may transmit 305 the PRS resource configuration to a plurality of terminal devices 110 by LTE Positioning Protocol (LPP) or other protocol. The at least one terminal device 110 receives 310 the PRS resource configuration.

In some example embodiments, the PRS resource configuration may indicate a PRS resource for AI/ML monitoring. In some example embodiments, a DL PRS resource set may be configured by NR-DL-PRS-ResourceSet. The NR-DL-PRS-ResourceSet may consist of one or more DL PRS resources defined by at least one of the followings: nr-DL-PRS-ResourceSetID, dl-PRS-Periodicity-and-ResourceSetSlotOffset, dl-PRS-ResourceRepetitionFactor, dl-PRS-ResourceTimeGap, dl-PRS-MutingOption1, dl-PRS-MutingOption2, NR-DL-PRS-SFN0-Offset, dl-PRS-ResourceList, dl-PRS-CombSizeN, dl-PRS-ResourceBandwidth, dl-PRS-StartPRB, dl-PRS-NumSymbols.

The parameter nr-DL-PRS-ResourceSetID defines the identity of the DL PRS resource set configuration.

The parameter dl-PRS-Periodicity-and-ResourceSetSlotOffset defines the DL PRS resource periodicity and takes values

slots. The DL PRS resources within one DL PRS resource set may be configured with the same DL PRS resource periodicity.

The parameter dl-PRS-ResourceRepetitionFactor defines how many times each DL-PRS resource is repeated for a single instance of the DL-PRS resource set and takes values

The DL PRS resources within one resource set have the same resource repetition factor.

The parameter dl-PRS-ResourceTimeGap defines the offset in number of slots between two repeated instances of a DL PRS resource with the same nr-DL-PRS-ResourceSetId within a single instance of the DL PRS resource set. The DL PRS resources within one resource set have the same value of dl-PRS-ResourceTimeGap.

The parameter dl-PRS-MutingOption1 and dl-PRS-MutingOption2 define the time locations where the DL PRS resource is expected to not be transmitted for a DL PRS resource set. If dl-PRS-MutingOption1 is configured, each bit in the bitmap of dl-PRS-MutingOption1 corresponds to a configurable number provided by higher layer parameter dl-prs-MutingBitRepetitionFactor of consecutive instances of a DL PRS resource set where all the DL PRS resources within the set are muted for the instance that is indicated to be muted. The length of the bitmap may be {2, 4, 6, 8, 16, 32} bits. If dl-PRS-MutingOption2 is configured each bit in the bitmap of dl-PRS-MutingOption2 corresponds to a single repetition index for each of the DL PRS resources within each instance of a nr-DL-PRS-ResourceSet and the length of the bitmap is equal to the values of dl-PRS-ResourceRepetitionFactor. Both dl-PRS-MutingOption1 and dl-PRS-MutingOption2 may be configured at the same time in which case the logical AND operation is applied to the bit maps.

The parameter NR-DL-PRS-SFN0-Offset defines the time offset of the SFN0 slot 0 for the transmitting cell with respect to SFN0 slot 0 of reference cell.

The parameter dl-PRS-ResourceList determines the DL PRS resources that are contained within one DL PRS resource set.

The parameter dl-PRS-CombSizeN defines the comb size of a DL PRS resource where the allowable values are predefined. All DL PRS resource sets belonging to the same positioning frequency layer have the same value of dl-PRS-CombSizeN.

The parameter dl-PRS-ResourceBandwidth defines the number of resource blocks configured for DL PRS transmission. The parameter has a granularity of 4 PRBs with a minimum of 24 PRBs and a maximum of 272 PRBs. All DL PRS resources sets within a positioning frequency layer have the same value of dl-PRS-ResourceBandwidth.

The parameter dl-PRS-StartPRB defines the starting PRB index of the DL PRS resource with respect to reference Point A, where reference Point A is given by the higher-layer parameter dl-PRS-PointA. The starting PRB index has a granularity of one PRB with a minimum value of 0 and a maximum value of 2176 PRBs. All DL PRS resource sets belonging to the same positioning frequency layer have the same value of dl-PRS-StartPRB.

The parameter dl-PRS-NumSymbols defines the number of symbols of the DL PRS resource within a slot where the allowable values are predefined.

In some example embodiments, a DL PRS resource may be defined by at least one of the followings: nr-DL-PRS-ResourceID, dl-PRS-SequenceID, dl-PRS-CombSizeN-AndReOffset, dl-PRS-ResourceSlotOffset, dl-PRS-ResourceSymbolOffset, dl-PRS-QCL-Info.

The parameter nr-DL-PRS-ResourceID determines the DL PRS resource configuration identity. DL PRS resource IDs are locally defined within a DL PRS resource set.

The parameter dl-PRS-SequenceID is used to initialize cinit value used in pseudo random generator for generation of DL PRS sequence for a given DL PRS resource.

The parameter dl-PRS-CombSizeN-AndReOffset defines the starting RE offset of the first symbol within a DL PRS resource in frequency. The relative RE offsets of the remaining symbols within a DL PRS resource are defined based on the initial offset and a predefined rule.

The parameter dl-PRS-ResourceSlotOffset determines the starting slot of the DL PRS resource with respect to corresponding DL PRS resource set slot offset.

The parameter dl-PRS-ResourceSymbolOffset determines the starting symbol of a slot configured with the DL PRS resource.

The parameter dl-PRS-QCL-Info defines any quasi co-location information of the DL PRS resource with other reference signals. The DL PRS may be configured with QCL 'typeD' with a DL PRS from a serving cell or a non-serving cell, or with rs-Type set to 'typeC' , 'typeD' , or 'typeC-plus-typeD' with a SS/PBCH Block from a serving or non-serving cell.

FIG. 4A illustrates an example of PRS resource configuration 400 for AI/ML model monitoring according to some example embodiments of the present disclosure. In the example of FIG. 4A, the repetition factor is set as 4, and the time gap is set as 2. PRS resources 401, 403, 405 and 407 may be configured for a first terminal device, such as the terminal device 110-1, and PRS resources 402, 404, 406 and 408 may be configured for a second terminal device, such as the terminal device 110-2.

FIG. 4B illustrates another example of PRS resource configuration 440 for AI/ML model monitoring according to some example embodiments of the present disclosure. In the example of FIG. 4B, the repetition factor is set as 4, and the time gap is set as 1. PRS resources 441, 443, 445 and 447 may be configured for a first terminal device, such as the terminal device 110-1, and PRS resources 442, 444, 446 and 448 may be configured for a second terminal device, such as the terminal device 110-2.

Still referring to FIG. 3, the at least one terminal device 110 determines 335 at least one reference positioning parameter of the at least one terminal device 110 by detecting a PRS for at least one time based on the PRS resource configuration. In some example embodiments, the at least one reference positioning parameter may indicate at least one location of the terminal device 110. For example, the at least one reference positioning parameter may comprise location information such as location coordinates or ground truth information of the location.

Alternatively, or in addition, in some example embodiments, the at least one reference positioning parameter may indicate measurement results from PRS receiving for positioning the terminal device 110. For example, the at least one reference positioning parameter may comprise intermediate results of the location information, including but not limited to time of arrival (TOA) , time difference of arrival (TDOA) , non-line of slight (NLOS) /line of sight (LOS) identification, or the like.

In some example embodiments, to support model monitoring, the PRS resource configuration may indicate a PRS resource with a specific pattern. The PRS resource configuration may be shared with a plurality of terminal devices 110 to which a same AI/ML model 140 is transferred from the network device 120 or 130. By way of example, the network device 130 may configure a constant PRS pattern and an optional duration for AI/ML model monitoring among the plurality of terminal devices 110. The plurality of terminal devices 110 may configured with a same AI/ML model 140 may use the same PRS pattern to collect dataset at least for AI/ML model monitoring. In the example embodiments where the PRS resource configuration indicates a PRS resource with a specific pattern, the PRS resource configuration may comprise the following parameters: dl-PRS-Periodicity, NR-DL-PRS-SFN0-Offset, dl-PRS-NumSymbols, dl-PRS-SequenceID, dl-PRS-CombSizeN-AndReOffset, dl-PRS-ResourceSymbolOffset. In addition, in some example embodiments, the PRS resource configuration may further comprise the following parameters: dl-PRS-ResourceRepetitionFactor, dl-PRS-ResourceTimeGap, dl-PRS-MutingOption1 and dl-PRS-MutingOption2, or dl-PRS-timer.

By configuring a fixed pattern of PRS resource, the signaling overhead for resource configuration may be reduced.

In the embodiments where the PRS resource configuration indicates a PRS resource with a specific pattern such as the PRS resource configuration 400 or 440, the network device 120 may transmit 315 a slot indication to the at least one terminal device 110. The slot indication indicates a slot for detecting the PRS. The at least one terminal device 110 may receive 320 the slot indication. For example, the slot indication may comprise a slot gap. In such cases, the at least one terminal device 110 determines 335 at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot indicated by the slot indication.

In some example embodiments, the slot indication transmitted 315 by the terminal device 120 may be comprised in signaling for an activation indication of the AI/ML model 140. For example, the network device 120 may transmit signaling comprising an activation indication of the AI/ML model 140 to the at least one terminal device 110. The at least one terminal device 110 may receive the signaling. The signaling may indicate a slot gap between a slot for receiving the signaling and a slot for detecting the PRS. In such cases, the PRS may be detected based on the slot gap. The at least one terminal device 110 determines 335 the at least one reference positioning parameter by detecting the PRS based on the slot gap.

In some example embodiments, the network device 120 may transmit downlink control information (DCI) comprising the signaling. Alternatively, or in addition, the signaling may transmit a radio resource control (RRC) or a medium access control (MAC) control element (CE) (MAC CE) comprising the signaling. The signaling may be transmitted by any suitable information element or protocol. Scope of the present disclosure is not limited in this regard.

In some example embodiments, the network device 120 may transmit 315 a plurality of slot indications to the plurality of terminal devices 110 to indicate respective slots for detecting the PRS.

FIG. 5 illustrates example PRS slots for AI/ML model monitoring according to some example embodiments of the present disclosure. As shown in FIG. 5, a PRS slot 510 and a PRS 550 may be configured for AI/ML model monitoring for a first terminal device, such as the terminal device 110-1. A PRS slot 520 and a PRS 560 may be configured for AI/ML model monitoring for a second terminal device such as the terminal device 110-2. A PRS slot 530 and a PRS 570 may be configured for AI/ML model monitoring for a third terminal device such as the terminal device 110-N. A PRS slot 540 and a PRS 580 may be configured for AI/ML model monitoring for a fourth terminal device such as a further terminal device 110 other than the terminal devices 110-1, 110-2 and 110-N.

The term “slot” used herein refers to a dynamic scheduling unit. One slot comprises a predetermined number of symbols. The slot used herein may refer to a normal slot which comprises a predetermined number of symbols and also refer to a sub-slot which comprises fewer symbols than the predetermined number of symbols.

FIG. 6A illustrates an example of PRS resource configuration 600 for AI/ML model monitoring according to some example embodiments of the present disclosure. In the example of FIG. 6A, the PRS resource configuration indicates a PRS resource with a specific pattern. In the PRS slot 610, a first terminal device such as the terminal device 110-1 receives the signaling (such as the DCI, RRC, MAC CE or the like) indicating to activate the AI/ML model 140 with a slot gap (such as a parameter Km) equal to 3. In the PRS slot 620, a second terminal device such as the terminal device 110-2 receives the signaling (such as the DCI, RRC, MAC CE or the like) indicating to activate the AI/ML model 140 with a slot gap (such as a parameter Km) equal to 2.

According to the Km equal to 3, the terminal device 110-1 determines to perform AI/ML model monitoring by detecting a PRS within the PRS slot 630. According to the Km equal to 2, the terminal device 110-2 determines to perform model monitoring by detecting a PRS within the PRS slot 640. According to the PRS resource configuration from the network device 130, the PRS resource is configured with a same pattern in each of the PRS slots 630 and 640. Specifically, in the PRS slot 630, the symbols 652, 654 may be configured for the terminal device 110-1 to receive a PRS for collecting the dataset using for AI/ML monitoring. In the PRS slot 640, the symbols 656, 658 may be configured for the terminal device 110-2 to receive a PRS for collecting the dataset using for AI/ML monitoring. Since the PRS resource is periodic, other PRS instance occurred after dl-PRS-Periodicity-and-ResourceSetSlotOffset slot does not need to be indicated by the network device 130 additionally.

Alternatively, or in addition, in some example embodiments, the PRS resource configuration may indicate a PRS resource set with a plurality of PRS resources for flexible schedule purpose. The PRS resource set may be shared with a plurality of terminal devices to which the AI/ML model 140 is transferred from the network device 120 or 130. That is, the network device 130 may configure a dividable and specific PRS resource set across all slots for the plurality of terminal devices 110. By configuring a dividable and specific PRS resource set across all slots for the plurality of terminal devices 110, it can provide flexible configuration of PRS resources.

In the embodiments where the PRS resource configuration indicates the PRS resource set with the plurality of PRS resources, the network device 120 may transmit 315 a slot indication to the at least one terminal device 110. The slot indication indicates a slot for detecting the PRS and an identity (ID) of a PRS resource within the PRS resource set. The at least one terminal device 110 may receive 320 the slot indication. The at least one terminal device 110 determines 335 the at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot.

In some example embodiments, the slot indication and the optional ID of PRS resource may be comprised in signaling for an activation indication of the AI/ML model 140. For example, the network device 120 may transmit signaling comprising an activation indication of the AI/ML model to each of the at least one terminal device 110. In some example embodiments, the network device 120 may transmit DCI comprising the signaling. Alternatively, or in addition, the network device 120 may transmit RRC or MAC CE comprising the signaling. The at least one terminal device 110 may receive the signaling. The signaling may indicate a slot gap between a slot for receiving the signaling and a slot for detecting the PRS. In the examples where a terminal device 110 is configured with the PRS resource set, the signaling may further indicate PRS ID in the PRS resource set. In such cases, the PRS may be detected by the terminal device 110 based on the slot gap and the PRS ID. The terminal device 110 determines 335 the at least one reference positioning parameter based on the detection results of the PRS.

FIG. 6B illustrates an example of PRS resource configuration 660 for AI/ML model monitoring according to some example embodiments of the present disclosure. In the example of FIG. 6B, the PRS resource configuration indicates a PRS resource set for the plurality of terminal devices 110 across the slots. In the PRS slot 610, a first terminal device such as the terminal device 110-1 receives, from the network device 120, signaling (such as the DCI, RRC, MAC CE or the like) indicating activation of the AI/ML model 140 with a slot gap (such as a parameter Km) equal to 3 and a PRS_id equal to 1. In the PRS slot 620, a second terminal device such as the terminal device 110-2 receives, from the network device 120, signaling (such as the DCI, RRC, MAC CE or the like) indicating activation of the AI/ML model 140 with a slot gap (such as a parameter Km) equal to 2 and a PRS_id equal to 2.

According to the Km equal to 3, the terminal device 110-1 determines to perform AI/ML model monitoring by detecting a PRS within the PRS slot 630. According to the Km equal to 2, the terminal device 110-2 determines to perform model monitoring by detecting a PRS within the PRS slot 640.

According to the PRS resource configuration from the network device 130, a plurality of PRS resources are configured in each PRS slot for flexible schedule purpose, where each PRS resource may be configured with a dedicated pattern. In the PRS slots 630 and 640, each of the symbol 671 and 676 is configured as a PRS resource with a PRS_id equal to 2. Further, the symbols 672 and 674 in the PRS slot 630 are configured as a PRS resource with a PRS_id equal to 1, and the symbols 673 and 675 in the PRS slot 630 are configured with a PRS resource with a PRS_id equal to 1. According to the signaling received from the network device 120 indicating a PRS_id equal to 1, the terminal device 110-1 may receive a PRS in the PRS slot 630 using the symbols 672, 674. According to the signaling received from the network device 120 indicating a PRS_id equal to 2, the terminal device 110-2 may receive a PRS in the PRS slot 640 using the symbol 676.

In some example embodiments, depending on the periodicity of the PRS resource with PRS_id equal to 1, the terminal device 110-1 may or may not perform further PRS detections in slots following the PRS slot 630. Similarly, depending on the periodicity of the PRS resource with PRS_id equal to 2, the terminal 110-1 may or may not perform further PRS detections in slots following the PRS slot 640. Note that the periodicity of PRS resources may be configured in the PRS resource configuration from the network device 130.

Still referring to FIG. 3, the at least one terminal device 110 determines 340 at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of the AI/ML model 140. In some example embodiments, the at least one predicted positioning parameter may indicate at least one location of the terminal device 110. The at least one location of the terminal device 110 may be obtained via global positioning system (GPS) , ultra mobile broadcast (UWB) , or the like.

Alternatively, or in addition, in some example embodiments, the at least one predicted positioning parameter may indicate measurement results from PRS receiving for positioning the terminal device 110. For example, the measurement results may comprise but not limited to time of arrival (TOA) , time difference of arrival (TDOA) , non-line of slight (NLOS) /line of sight (LOS) identification, or the like.

In some example embodiments, a terminal device 110 may determine 335 a plurality of reference positioning parameters by detecting the PRS for a plurality of times (e.g., N times) . The terminal device 110 may determine 340 a plurality of deviations between the plurality of reference positioning parameters and a plurality of predicted positioning parameters determined from outputs of the AI/ML model 140. The plurality of reference positioning parameters may be determined a plurality of times in consecutive individual slots or consecutive slots for PRS resource receiving. The slots may be indicated by signaling such as DCI, RRC or LPP parameter, or accompanying with AI/ML model activation.

The at least one terminal device 110 transmit 360 information indicating the at least one deviation to the network device 120. In the example embodiments where the terminal device 110 determines 340 a plurality of deviations, the terminal device 110 may perform a plurality of transmissions to the network device 120. Each of the plurality of transmissions may comprise information indicating one of the plurality of deviations.

In some example embodiments, the terminal device 110 may determine 345 a movement state of the terminal device 110 based on movement range of the terminal device 110 during the plurality of times of detecting the PRS. The terminal device 110 may transmit 350 an indication of the movement state to the network device 120, the movement state indicating whether the movement range exceeds or is below a movement threshold. The movement threshold may be predetermined or predefined. The movement state may be indicated by 1 bit and the range across at least the whole N times of PRS detections. The report timing for the movement range may be the first occasion, configured from a LPP message ProvideLocationInformation, after N times of PRS detections.

In some example embodiments, if the movement range is below the movement threshold, the terminal device 110 may transmit 360 first information indicating an aggregated deviation to the network device 120. The aggregated deviation may be aggregated from the plurality of deviations. That is, if the terminal device 110 is unmoving or moving in a very small range, the terminal device 110 may transmit an average value of each measurement or all times measurements.

Alternatively, or in addition, in some example embodiments, if the movement range exceeds the movement threshold, the terminal device 110 may transmit 360 second information indicating respective deviations of the plurality of deviations to the network device 120. That is, if the terminal device 110 is moving in a big range, the terminal device 110 may transmit all times measurements.

In some example embodiments, the network device 120 receives 365 information indicating the plurality of deviations between reference positioning parameters and predicted positioning parameters from the at least one terminal device 110.

The network device 120 determines 370 an action to be performed on the AI/ML model 140 based on the plurality of deviations. The action may be chosen from a plurality of candidate actions, including but not limited to a type 1 action for model deactivation, a type 2 action for model reselection, a type 3 action for model retraining or another type 3 action for model refining, or a type 4 action for no change of the AI/ML model 140. In this way, the network device 120 may determine an action to be performed on the AI/ML model based on self-monitoring or joint-monitoring for the AI/ML model.

By determining the action based on the plurality of deviations, the network device 120 may determine a proper action with the plurality of deviations reported from a single terminal device 110 or from a plurality of terminal devices 110. The reference positioning parameters may be infected by factors such as a clock error at a terminal device, a synchronization error between the terminal device and the network device, an oscillator-drift or heavy NLOS propagation environment, and/or the like. Thus, by determining the plurality of deviations by a single terminal device for a plurality of times or by determining the plurality of deviations from a plurality of terminal devices, it can ensure that the deviations are not result from the above factors. In this way, the network device 120 may determine the actual performance status of the AI/ML model 140. It can overcome error indication of model monitoring caused by some instantaneous factors.

For example, an imperfect factor may occur instantaneously and captured by a terminal device in the PRS measurement moment, like impulse noise, lightning, etc., which result in the ‘label’ , i.e., terminal device positioning estimation, distortion in the moment but undistorted in the next moment. Such imperfect factor can be eliminated by using the plurality of deviations from a single terminal device. In this way, it can assist the network to judge how reliable the model monitoring from terminal device side is if the terminal device reports the measurement across multiple moments.

In some example embodiments, the network device 120 receives 365 a plurality of transmissions from a single terminal device 110. Each of the plurality of transmissions comprises information indicating one of the plurality of deviations. In such cases, the network device 120 may determine 370 an action to be performed on the AI/ML model 140 based on the plurality of deviations from that terminal device 110. In this way, the terminal device may perform self-monitoring for the AI/ML model 140.

Alternatively, or in addition, in some example embodiments, the network device 120 receives information comprising the plurality of deviations from the plurality of terminal devices 110. In such cases, the network device 120 may determine 370 an action to be performed on the AI/ML model 140 based on the plurality of deviations from the plurality of terminal devices 110. In this way, those terminal devices 110 may perform joint-monitoring for the AI/ML model 140. By performing the joint-monitoring, it can monitor the AI/ML model timely and efficiently.

In some example embodiments, the at least one terminal device 110 may determine an expected action to be performed on the AI/ML model from a plurality of candidate actions based on the at least one deviation. The plurality of candidate actions may include but not limited to a type 1 action for model deactivation, a type 2 action for model reselection, a type 3 action for model retraining or another type 3 action for model refining. In some example embodiments, the at least one terminal device 110 may transmit at least one report about the expected action to the network device 120. The network device 120 may receive the at least one report from the at least one terminal device 110. In some example embodiments, the report about the expected action may be transmitted 360 together with the information indicating the deviation (s) . In some other example embodiments, the report about the expected action may be transmitted separately from the information indicating the deviation (s) .

In some example embodiments, the network device 120 may determine 375 a specific action from the plurality of candidate actions to be performed on the AI/ML model 140 based on the plurality of deviations and the at least one report. The plurality of candidate actions includes but not limited to a type 1 action for model deactivation, a type 2 action for model reselection, a type 3 action for model retraining or another type 3 action for model refining, or a type 4 action for no change of the AI/ML model 140. The network device 120 may transmit 380 an indication of the specific action to the at least one terminal device 110. The at least one terminal device 110 may receive 385 the indication of the specific action.

In this way, the network device 120 may determine a specific action to be performed on the AI/ML model based on self-monitoring or joint-monitoring together with the report indicating an expected action. Such AI/ML monitoring may be timely and reliable.

By using the signaling flow 700, the AI/ML model 140 can be monitored in a self-monitoring way or a joint-monitoring way. If the AI/ML model 140 is deteriorating, the AI/ML model 140 may be reported invalid and a proper action to be performed on the AI/ML model 140 may be determined and reported.

Example embodiments regarding self-monitoring or joint-monitoring for the AI/ML model 140 have been described with respect to FIG. 3. With the AI/ML model monitoring, the network device 120 may determine or configure a PRU. FIG. 7 illustrates a signaling flow 700 of PRU configuration in accordance with some embodiments of the present disclosure. As shown in FIG. 7, the signaling flow 700 involves the terminal device 110 and the network device 120 in FIG. 1. It is to be understood that the terminal device 110 may be any one in the communication environment 100, and the signaling flow 700 may involves more devices or less devices, and the number of devices illustrated in FIG. 7 is only for the purpose of illustration without suggesting any limitations.

In operation, the terminal device 110 determines 705 a first reference location of the terminal device 110 by detecting a positioning reference signal (PRS) . The process for detecting the PRS have been described with respect to FIG. 3, and thus will not be repeated here.

The terminal device 110 transmits 710, to the network device 120, information indicating a first location deviation between the first reference location and a first predicted location of the terminal device 110. The first predicted location is determined from a first output of the AI/ML model 140.

In some example embodiments, the first reference location may be is (x, y, z) , and the first predicted location may be

where

and

represent latitude degrees, longitude degrees, altitude respectively. The first location deviation ε may be determined by

or other suitable calculations. It is to be understood that the fist reference location and the first predicted location may be represented in other form. Scope of the present disclosure is not limited in this regard.

In some example embodiments, the AI/ML model 140 is indicated to output a predicted location (e.g., the first predicted location) of the terminal device 110. Alternatively, or in addition, in some example embodiments, the AI/ML model 140 is indicated to output intermediate results for positioning the terminal device 110. The predicted location (e.g., first predicted location) may be determined from the intermediate results.

The network device 120 receives 715 the information indicating the first location deviation. The network device 120 determines 720 whether the terminal device 110 is capable of acting as a positioning reference unit (PRU) based at least in part on the first location deviation. In some embodiments, the network device 120 may receive from the terminal device 110 information indicating location deviations for a plurality of times. If all or most of the received information indicates small or zero location deviations, the network device 120 may determine that the terminal device 110 is capable of acting as the PRU. In some embodiments, in addition to the location deviation (s) reported by the terminal device 110, the network device 120 may use additional assistance information to determine whether the terminal device 110 is capable of acting as the PRU. The scope of the present disclosure is not limited in this regard.

If the network device 120 determines that the terminal device 110 is capable of acting as the PRU, the network device 120 transmits 725, to the terminal device 110, a device configuration for configuring the terminal device 110 as a PRU.

As used herein, the term “PRU” may represent a device at a known location which can perform positioning measurements such as reference signals time difference (RSTD) , reference signals reception power (RSRP) , UE Rx-Tx time difference measurements, or the like. The PRU may report these measurements to a location server. In addition, the PRU may transmit sounding reference signal (SRS) to enable transmission and receiving points (TRPs) to measure and report UL positioning measurements such as relative time of arrival (RTOA) , UL-angles of arrival (AoA) , gNB Rx-Tx time difference from PRU at a known location. The PRU measurements may be compared by a location server with the measurements expected at the known PRU location to determine correction terms for other nearby target devices. The DL and/or UL location measurements for other target devices can then be corrected based on the previously determined correction items.

The terminal device 110 receives 730 the device configuration from the network device 120. The terminal device 110 transmits 730, to the network device 120, a feedback indicating acceptance or rejection of the device configuration. The network device 120 receives 735 the feedback. For example, if the terminal device 110 transmits 730 an acknowledgement (ACK) to the network device 120, the terminal device 110 may accept the device configuration and become a PRU automatically to assist in model monitoring. If the terminal device 110 transmits 730 a negative ACK (NACK) to the network device 120, the terminal device 110 may refuse the device configuration and will not become the PRU.

In this way, the network device 120 can configure a PRU for positioning based on AI/ML monitoring. The PRU functionality can thus be realized by a terminal device with known location. In this way, it can achieve a more reliable model monitoring by configuring a terminal device 110 as a PRU. In addition, such solution involves minor specification work since it reuses the current PRS resource configuration.

In some example embodiments, the network device 120 may be responsible for making the positioning calculation/inference using AI/ML model 140 or non-AI mechanism from PRS/SRS positioning measurement, therefore the terminal device 110 need to report the location deviation to the network. It is to be understood that other procedures for assigning the terminal device as a PRU for model monitoring are the same as terminal device based positioning.

In some example embodiments, the terminal device 110 may determine a second reference location of the terminal device c110 by detecting a further PRS. The terminal device 110 may transmit information indicating a second location deviation between the second reference location and a second predicted location of the terminal device 110 to the network device 120. The second predicted location is determined from a second output of the AI/ML model 140. In the case where the AI/ML model 140 is indicated to output a predicted location of a terminal device, the second predicted location may be a direct output of the AI/ML model 140. In the case where the AI/ML model 140 is indicated to intermediate results for positioning a terminal device, the second predicted location may be determined by the terminal device based on the intermediate results output by the AI/ML model 140.

The second location deviation may be used as a reference for determining an action to be performed on the AI/ML model 140. The network device 120 may receive, from the terminal device 110, the information indicating the second location deviation. Since the information is received from a terminal device 110 which acts as a PRU, it means that the location deviation may be more reliable in determining whether the AI/ML model is deteriorating. In some example embodiments, the network device 120 may determine an action to be performed on the AI/ML model based on at least in part on the second location deviation. The action may be determined from a plurality of candidate actions including but not limited to a type 1 action for model deactivation, a type 2 action for model reselection, a type 3 action for model retraining or another type 3 action for model refining, or a type 4 action for no change of the AI/ML model 140.

In this way, the network device 120 may determine an action to be performed on the AI/ML model based on the location deviations from the terminal device 110.

It is to be understood that the above signaling flow 300 and/or signaling flow 700 may be used in combination or separately. Any suitable combination of these methods may be applied. Scope of the present disclosure is not limited in this regard.

By using these signaling flows 300 and 700 separately or in combination, the AI/ML model monitoring may be improved. In this way, positioning accuracy of the devices can be improved.

In some example embodiments, the common NR positioning information element (IE) NR-DL-PRS-info defining the DL PRS configuration may be specified as below:

It would be appreciated that some example specifications are provided above, and the detailed description may be varied.

EXAMPLE METHODS

FIG. 8 illustrates a flowchart of a communication method 800 implemented at a terminal device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 800 will be described from the perspective of the terminal device 110 in FIG. 1.

At block 810, the terminal device 110 receives, from a first network device such as the network device 130, a positioning reference signal (PRS) resource configuration.

At block 820, the terminal device 110 determines at least one reference positioning parameter of the terminal device 110 by detecting a PRS for at least one time based on the PRS resource configuration.

At block 830, the terminal device 110 determines at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of an artificial intelligence/machine learning (AI/ML) mode 140.

At block 840, the terminal device 110 transmits, to a second network device such as the network device 120, information indicating the at least one deviation.

In some example embodiments, the PRS resource configuration indicates a PRS resource with a specific pattern. the PRS resource may be shared with a plurality of terminal devices 110 to which the AI/ML model 140 is transferred from the first network device such as the network device 130 or the second network device such as the network device 120. In some example embodiments, the terminal device 110 may receive, from the network device 120, a slot indication indicating a slot for detecting the PRS. The terminal device 110 may determine the at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot at block 820.

In some example embodiments, the PRS resource configuration indicates a PRS resource set with a plurality of PRS resources. The PRS resource set may be shared with a plurality of terminal devices 110 to which the AI/ML model 140 is transferred from the network device 130 or the second network device such as the network device 120. In some example embodiments, the terminal device 110 may receive, from the network device 120, a slot indication indicating a slot for detecting the PRS and an identity of a PRS resource within the PRS resource set. The terminal device 110 may determine the at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot at block 820.

In some example embodiments, the terminal device 110 may determine a plurality of reference positioning parameters by detecting the PRS for a plurality of times at block 820. In addition, the terminal device 110 may determine a plurality of deviations between the plurality of reference positioning parameters and a plurality of predicted positioning parameters determined from outputs of the AI/ML model 140.

In some example embodiments, the terminal device 110 may perform a plurality of transmissions to the network device 120 at block 840. Each of the plurality of transmissions comprises information indicating one of the plurality of deviations.

In some example embodiments, the terminal device 110 may determine a movement range of the terminal device 110 during the plurality of times of detecting the PRS. The terminal device 110 may transmit, to the network device 120, an indication of whether the movement range exceeds or is below a movement threshold. If the terminal device 110 determines that the movement range is below the movement threshold, the terminal device 110 may transmit, to the network device 120, first information indicating an aggregated deviation at block 840. The aggregated deviation may be aggregated from the plurality of deviations.

Alternatively, or in addition, in some example embodiments, if the terminal device 110 determines that the movement range exceeds the movement threshold, the terminal device 110 may transmit, to the network device 120, second information indicating respective deviations of the plurality of deviations at block 840.

In some example embodiments, the method 800 further comprises: receiving, from the network 120, signaling comprising an activation indication of the AI/ML model 140. The signaling may indicate a slot gap between a slot for receiving the signaling and a slot for detecting the PRS. The PRS may be detected based on the slot gap. In some example embodiments, the terminal device 110 may receive downlink control information (DCI) , radio resource control (RRC) or medium access control (MAC) control element (CE) (MAC CE) from the network device 120. The DCI, the RRC, or the MAC CE may comprise the signaling.

In some example embodiments, the terminal device 110 may determine, based on the at least one deviation and from a plurality of candidate actions, an expected action to be performed on the AI/ML model 140. The terminal device 110 may further transmit, to the network device 120, a report about the expected action.

In some example embodiments, the terminal device 110 may receive, from the network device 120, an indication of a specified action to be performed on the AI/ML model 140. The specified action may be selected from the plurality of candidate actions. By way of example, the plurality of candidate actions comprises at least one of the following: model deactivation, model reselection, model retraining, model fine-tuning, or no change of the AI/ML model.

In some example embodiments, the at least one reference positioning parameter or the at least one predicated positioning parameter indicates at least one location of the terminal device 110. Alternatively, in some example embodiments, the at least one reference positioning parameter or the at least one predicated positioning parameter indicates measurement results from the PRS receiving for positioning the terminal device 110.

FIG. 9 illustrates a flowchart of a communication method 900 implemented at a terminal device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 900 will be described from the perspective of the terminal device 110 in FIG. 1.

At block 910, the terminal device 110 determines a first reference location of the terminal device 110 by detecting a positioning reference signal (PRS) .

At block 920, the terminal device 110 transmits, to the network device 120, information indicating a first location deviation between the first reference location and a first predicted location of the terminal device 110. The first predicted location is determined from a first output of an artificial intelligence/machine learning (AI/ML) model 140.

At block 930, the terminal device 110 receives, from the network device 120, a device configuration for configuring the terminal device 110 as a positioning reference unit (PRU) .

At block 940, the terminal device 110 transmits, to the network device 110, a feedback indicating acceptance or rejection of the device configuration.

In some example embodiments, the feedback indicates acceptance of the device configuration. In such cases, the method 900 further comprising: determining a second reference location of the terminal device 110 by detecting a further PRS. The method 900 further comprises transmitting, to the network device 120, information indicating a second location deviation between the second reference location and a second predicted location of the terminal device 110. The second predicted location may be determined from a second output of the AI/ML model 140. The second location deviation may be used as a reference for determining an action to be performed on the AI/ML model 140.

In some example embodiments, the AI/ML model 140 may be indicated to output the first predicted location or the second predicted location of the terminal device 110. Alternatively, or in addition, in some example embodiments, the AI/ML model 140 may be indicated to output intermediate results for positioning the terminal device 110. The first predicted location or the second predicted location is determined from the intermediate results.

FIG. 10 illustrates a flowchart of a communication method 1000 implemented at a network device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 1000 will be described from the perspective of the network device 120 in FIG. 1.

At block 1010, the network device 120 receives, from at least one terminal device 110, information indicating a plurality of deviations between reference positioning parameters and predicted positioning parameters. The reference positioning parameters are determined by the at least one terminal device 110 by detecting a positioning reference signal (PRS) based on the at least one resource configuration. The predicted positioning parameters are determined by the at least one terminal device 110 from outputs of an artificial intelligence/machine learning (AI/ML) model 140.

At block 1020, the network device 120 determines an action to be performed on the AI/ML model 140 based on the plurality of deviations.

In some example embodiments, the at least one terminal device 110 comprises a plurality of terminal devices 110 configured with a PRS resource configuration. The PRS resource configuration may indicate a PRS resource with a specific pattern.

In some example embodiments, the at least one terminal device 110 comprises a plurality of terminal devices 110 configured with a PRS resource configuration. The PRS resource configuration may indicate a PRS resource with a specific pattern. In such cases, the method 1000 may further comprise transmitting, to the at least one terminal device 110, at least one slot indication indicating at least one slot for detecting the PRS.

In some example embodiments, the at least one terminal device comprises a plurality of terminal devices 110 configured with a PRS resource configuration. The PRS resource configuration may indicate a PRS resource set with a plurality of PRS resources. In such cases, the method 1000 may further comprise: transmitting, to the at least one terminal device 110, at least one slot indication indicating at least one slot for detecting the PRS and at least one identity of at least one PRS resource within the PRS resource set.

In some example embodiments, the at least one terminal device 110 comprises a first terminal device such as terminal device 110-1 configured to detect the PRS for a plurality of times.

In some example embodiments, the network device 120 may receive a plurality of transmissions from the first terminal device at block 1010. Each of the plurality of transmissions comprises information indicating one of the plurality of deviations.

In some example embodiments, the network device 120 may receive, from the first terminal device, an indication of whether a movement range of the first terminal device during the plurality of times of detecting the PRS exceeds or is below a movement threshold. If the movement range is below the movement threshold, the network device 120 may receive, from the first terminal device, first information indicating an aggregated deviation, the aggregated deviation being aggregated from the plurality of deviations at block 1010. If the movement range exceeds the movement threshold, the network device 120 may receive, from the first terminal device, second information indicating respective deviations of the plurality of deviations at block 1010.

In some example embodiments, the method 1000 further comprises: transmitting, to the at least one terminal device 110, signaling comprising an activation indication of the AI/ML model 140. The signaling may indicate at least one slot gap between a slot for receiving the signaling and at least one slot for detecting the PRS by the at least one terminal device 110. In some example embodiments, the network device 120 may transmit DCI, RRC or MAC CE to the terminal device 110. The DCI, RRC or MAC CE comprises the signaling.

In some example embodiments, the method 1000 further comprises receiving, from the at least one terminal device 110, at least one report about at least one expected action to be performed on the AI/ML model 140. The at least one expected action may be from a plurality of candidate actions.

In some example embodiments, the network device 120 may determine, based on the plurality of deviations and the at least one report, a specified action from the plurality of candidate actions to be performed on the AI/ML model 140. The specified action may be selected from a plurality of candidate actions. In some example embodiments, the plurality of candidate actions comprises at least one of the following: model deactivation, model reselection, model retraining, model fine-tuning, or no change of the AI/ML model.

In some example embodiments, the method 1000 may further comprise transmitting, to the at least one terminal device 110, an indication of the specified action.

FIG. 11 illustrates a flowchart of a communication method 1100 implemented at a network device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 1100 will be described from the perspective of the network device 120 in FIG. 1.

At block 1110, the network device 120 receives, from a terminal device 110, information indicating a first location deviation between a first reference location and a first predicted location of the terminal device 110. The first reference location is determined by detecting a positioning reference signal (PRS) . The first predicted location is determined from a first output of an artificial intelligence/machine learning (AI/ML) model 140 transferred to the terminal device 110.

At block 1120, the network device 120 determines, based at least in part on the location deviation, whether the terminal device 110 is capable of acting as a positioning reference unit (PRU) .

If the network device 120 determines that the terminal device 110 is capable of acting as a PRU, the network device 120 transmits, to the terminal device 110, a device configuration for configuring the terminal device 110 as a PRU at block 1130.

At block 1140, the network device 120 receives, from the terminal device 110, a feedback indicating acceptance or rejection of the device configuration.

In some example embodiments, the feedback indicates acceptance of the device configuration. The method 1100 may further comprise: receiving, from the terminal device 110, information indicating a second location deviation between a second reference location and a second predicted location of the terminal device 110. The second predicted location may be determined from a second output of the AI/ML model 140. The network device 120 may determine an action to be performed on the AI/ML model 140 based at least in part on the second location deviation.

In some example embodiments, the AI/ML model may be indicated to output the first predicted location or the second predicted location of the terminal device 110. Alternatively, or in addition, in some example embodiments, the AI/ML model may be indicated to output intermediate results for positioning the terminal device 110. The first predicted location or the second predicted location is determined from the intermediate results.

EXAMPLE DEVICE

FIG. 12 is a simplified block diagram of a device 1200 that is suitable for implementing embodiments of the present disclosure. The device 1200 can be considered as a further example implementation of any of the devices as shown in FIG. 1. Accordingly, the device 1200 can be implemented at or as at least a part of the terminal device 110 or the network device 120.

As shown, the device 1200 includes a processor 1210, a memory 1220 coupled to the processor 1210, a suitable transmitter (TX) /receiver (RX) 1240 coupled to the processor 1210, and a communication interface coupled to the TX/RX 1240. The memory 1210 stores at least a part of a program 1230. The TX/RX 1240 is for bidirectional communications. The TX/RX 1240 has at least one antenna to facilitate communication, though in practice an Access Node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2/Xn interface for bidirectional communications between eNBs/gNBs, S1/NG interface for communication between a Mobility Management Entity (MME) /Access and Mobility Management Function (AMF) /SGW/UPF and the eNB/gNB, Un interface for communication between the eNB/gNB and a relay node (RN) , or Uu interface for communication between the eNB/gNB and a terminal device.

The program 1230 is assumed to include program instructions that, when executed by the associated processor 1210, enable the device 1200 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1 to 11. The embodiments herein may be implemented by computer software executable by the processor 1210 of the device 1200, or by hardware, or by a combination of software and hardware. The processor 1210 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1210 and memory 1220 may form processing means 1250 adapted to implement various embodiments of the present disclosure.

The memory 1220 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 1220 is shown in the device 1200, there may be several physically distinct memory modules in the device 1200. The processor 1210 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 1200 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 some embodiments, a terminal device comprises a circuitry configured to: receiving, at a terminal device and from a first network device, a positioning reference signal (PRS) resource configuration; determining at least one reference positioning parameter of the terminal device by detecting a PRS for at least one time based on the PRS resource configuration; determining at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of an artificial intelligence/machine learning (AI/ML) model; and transmitting, to a second network device, information indicating the at least one deviation. According to embodiments of the present disclosure, the circuitry may be configured to perform any of the method implemented by the terminal device as discussed above.

In some embodiments, a terminal device comprises a circuitry configured to: determining, at a terminal device, a first reference location of the terminal device by detecting a positioning reference signal (PRS) ; transmitting, to a network device, information indicating a first location deviation between the first reference location and a first predicted location of the terminal device, the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model; receiving, from the network device, a device configuration for configuring the terminal device as a positioning reference unit (PRU) ; and transmitting, to the network device, a feedback indicating acceptance or rejection of the device configuration. According to embodiments of the present disclosure, the circuitry may be configured to perform any of the method implemented by the terminal device as discussed above.

In some embodiments, a network device comprises a circuitry configured to: receiving, at a network device and from at least one terminal device, information indicating a plurality of deviations between reference positioning parameters and predicted positioning parameters, the reference positioning parameters being determined by the at least one terminal device by detecting a positioning reference signal (PRS) based on the at least one resource configuration, and the predicted positioning parameters being determined by the at least one terminal device from outputs of an artificial intelligence/machine learning (AI/ML) model; and determining an action to be performed on the AI/ML model based on the plurality of deviations. According to embodiments of the present disclosure, the circuitry may be configured to perform any of the method implemented by the network device as discussed above.

In some embodiments, a network device comprises a circuitry configured to: receiving, at a network device and from a terminal device, information indicating a first location deviation between a first reference location and a first predicted location of the terminal device, the first reference location being determined by detecting a positioning reference signal (PRS) , and the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model transferred to the terminal device; determining, based at least in part on the location deviation, whether the terminal device is capable of acting as a positioning reference unit (PRU) ; in accordance with a determination that the terminal device is capable of acting as a PRU, transmitting, to the terminal device, a device configuration for configuring the terminal device as a PRU; and receiving, from the terminal device, a feedback indicating acceptance or rejection of the device configuration. According to embodiments of the present disclosure, the circuitry may be configured to perform any of the method implemented by the network device as discussed above.

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.

In summary, embodiments of the present disclosure provide the following aspects.

In an aspect, a communication method comprising: receiving, at a terminal device and from a first network device, a positioning reference signal (PRS) resource configuration; determining at least one reference positioning parameter of the terminal device by detecting a PRS for at least one time based on the PRS resource configuration; determining at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of an artificial intelligence/machine learning (AI/ML) model; and transmitting, to a second network device, information indicating the at least one deviation.

In some embodiments, the PRS resource configuration indicates a PRS resource with a specific pattern, the PRS resource being shared with a plurality of terminal devices to which the AI/ML model is transferred from the first network device or the second network device. In some embodiments, determining the at least one reference positioning parameter comprises: receiving, from the second network device, a slot indication indicating a slot for detecting the PRS; and determining the at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot.

In some embodiments, the PRS resource configuration indicates a PRS resource set with a plurality of PRS resources, the PRS resource set being shared with a plurality of terminal devices to which the AI/ML model is transferred from the first network device or the second network device; and wherein determining the at least one reference positioning parameter comprises: receiving, from the second network device, a slot indication indicating a slot for detecting the PRS and an identity of a PRS resource within the PRS resource set; and determining the at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot.

In some embodiments, determining the at least one reference positioning parameter comprises: determining a plurality of reference positioning parameters by detecting the PRS for a plurality of times; and wherein determining the at least one deviation comprises: determining a plurality of deviations between the plurality of reference positioning parameters and a plurality of predicted positioning parameters determined from outputs of the AI/ML model.

In some embodiments, transmitting the information indicating the at least one deviation comprises: performing a plurality of transmissions to the second network device, each of the plurality of transmissions comprising information indicating one of the plurality of deviations.

In some embodiments, transmitting the information indicating the at least one deviation comprises: determining a movement range of the terminal device during the plurality of times of detecting the PRS; transmitting, to the second network device, an indication of whether the movement range exceeds or is below a movement threshold; in accordance with a determination that the movement range is below the movement threshold, transmitting, to the second network device, first information indicating an aggregated deviation, the aggregated deviation being aggregated from the plurality of deviations; and in accordance with a determination that the movement range exceeds the movement threshold, transmitting, to the second network device, second information indicating respective deviations of the plurality of deviations.

In some embodiments, the method further comprises: receiving signaling comprising an activation indication of the AI/ML model from the second network device, the signaling indicating a slot gap between a slot for receiving the signaling and a slot for detecting the PRS, and wherein the PRS is detected based on the slot gap. In some embodiments, the method further comprises receiving DCI, RRC or MAC CE from the second network device. The DCI, RRC or MAC CE comprises the signaling.

In some embodiments, the at least one reference positioning parameter or the at least one predicated positioning parameter indicates at least one location of the terminal device, or wherein the at least one reference positioning parameter or the at least one predicated positioning parameter indicates measurement results from the PRS receiving for positioning the terminal device.

In some embodiments, the method further comprises: determining, based on the at least one deviation and from a plurality of candidate actions, an expected action to be performed on the AI/ML model; and transmitting, to the second network device, a report about the expected action.

In some embodiments, the method further comprises: receiving, from the second network device, an indication of a specified action to be performed on the AI/ML model, the specified action being selected from the plurality of candidate actions.

In some embodiments, the plurality of candidate actions comprises at least one of the following: model deactivation, model reselection, model retraining, model fine-tuning, or no change of the AI/ML model.

In an aspect, a communication method comprising: determining, at a terminal device, a first reference location of the terminal device by detecting a positioning reference signal (PRS) ; transmitting, to a network device, information indicating a first location deviation between the first reference location and a first predicted location of the terminal device, the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model; receiving, from the network device, a device configuration for configuring the terminal device as a positioning reference unit (PRU) ; and transmitting, to the network device, a feedback indicating acceptance or rejection of the device configuration.

In some embodiments, the feedback indicates acceptance of the device configuration, the method further comprises: determining a second reference location of the terminal device by detecting a further PRS; and transmitting, to the network device, information indicating a second location deviation between the second reference location and a second predicted location of the terminal device, the second predicted location being determined from a second output of the AI/ML model, the second location deviation being used as a reference for determining an action to be performed on the AI/ML model.

In some embodiments, the AI/ML model is indicated to output the first predicted location or the second predicted location of the terminal device, or wherein the AI/ML model is indicated to output intermediate results for positioning the terminal device, and the first predicted location or the second predicted location is determined from the intermediate results.

In an aspect, a communication method comprising: receiving, at a network device and from at least one terminal device, information indicating a plurality of deviations between reference positioning parameters and predicted positioning parameters, the reference positioning parameters being determined by the at least one terminal device by detecting a positioning reference signal (PRS) based on the at least one resource configuration, and the predicted positioning parameters being determined by the at least one terminal device from outputs of an artificial intelligence/machine learning (AI/ML) model; and determining an action to be performed on the AI/ML model based on the plurality of deviations.

In some embodiments, the at least one terminal device comprises a plurality of terminal devices configured with a PRS resource configuration, the PRS resource configuration indicating a PRS resource with a specific pattern.

In some embodiments, the at least one terminal device comprises a plurality of terminal devices configured with a PRS resource configuration, the PRS resource configuration indicating a PRS resource with a specific pattern, and wherein the method further comprises: transmitting, to the at least one terminal device, at least one slot indication indicating at least one slot for detecting the PRS.

In some embodiments, the at least one terminal device comprises a plurality of terminal devices configured with a PRS resource configuration, the PRS resource configuration indicating a PRS resource set with a plurality of PRS resources; and wherein the method further comprises: transmitting, to the at least one terminal device, at least one slot indication indicating at least one slot for detecting the PRS and at least one identity of at least one PRS resource within the PRS resource set.

In some embodiments, the at least one terminal device comprises a first terminal device configured to detect the PRS for a plurality of times.

In some embodiments, receiving the information indicating the plurality of deviations comprises: receiving a plurality of transmissions from the first terminal device, each of the plurality of transmissions comprising information indicating one of the plurality of deviations.

In some embodiments, receiving the information indicating the at least one deviation comprises: receiving, from the first terminal device, an indication of whether a movement range of the first terminal device during the plurality of times of detecting the PRS exceeds or is below a movement threshold; in accordance with a determination that the movement range is below the movement threshold, receiving, from the first terminal device, first information indicating an aggregated deviation, the aggregated deviation being aggregated from the plurality of deviations; and in accordance with a determination that the movement range exceeds the movement threshold, receiving, from the first terminal device, second information indicating respective deviations of the plurality of deviations.

In some embodiments, the method further comprises: transmitting, to the at least one terminal device, signaling comprising an activation indication of the AI/ML model, the signaling indicating at least one slot gap between a slot for receiving the signaling and at least one slot for detecting the PRS by the at least one terminal device. In some example embodiments, the method further comprises transmitting DCI, RRC or MAC CE to the at least one terminal device. The DCI, RRC or MAC CE comprises the signaling.

In some embodiments, the method further comprises: receiving, from the at least one terminal device, at least one report about at least one expected action to be performed on the AI/ML model, the at least one expected action being from a plurality of candidate actions.

In some embodiments, determining an action to be performed on the AI/ML model comprises: determining, based on the plurality of deviations and the at least one report, a specified action from the plurality of candidate actions to be performed on the AI/ML model, the specified action being selected. In some embodiments, the method further comprises: transmitting, to the at least one terminal device, an indication of the specified action.

In an aspect, a communication method comprising: receiving, at a network device and from a terminal device, information indicating a first location deviation between a first reference location and a first predicted location of the terminal device, the first reference location being determined by detecting a positioning reference signal (PRS) , and the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model transferred to the terminal device; determining, based at least in part on the location deviation, whether the terminal device is capable of acting as a positioning reference unit (PRU) ; in accordance with a determination that the terminal device is capable of acting as a PRU, transmitting, to the terminal device, a device configuration for configuring the terminal device as a PRU; and receiving, from the terminal device, a feedback indicating acceptance or rejection of the device configuration.

In some embodiments, the feedback indicates acceptance of the device configuration, the method further comprises: receiving, from the terminal device, information indicating a second location deviation between a second reference location and a second predicted location of the terminal device, the second predicted location being determined from a second output of the AI/ML model; and determining an action to be performed on the AI/ML model based at least in part on the second location deviation.

In an aspect, a terminal device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the terminal device discussed above.

In an aspect, a network device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the network device discussed above.

In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the terminal device discussed above.

In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the network device discussed above.

In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the terminal device discussed above.

In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the 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. 3 and 7 to 11. 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 communication method comprising:

receiving, at a terminal device and from a first network device, a positioning reference signal (PRS) resource configuration;

determining at least one reference positioning parameter of the terminal device by detecting a PRS for at least one time based on the PRS resource configuration;

determining at least one deviation between the at least one reference positioning parameter and at least one predicted positioning parameter determined from at least one output of an artificial intelligence/machine learning (AI/ML) model; and

transmitting, to a second network device, information indicating the at least one deviation.
The method of claim 1, wherein the PRS resource configuration indicates a PRS resource with a specific pattern, the PRS resource being shared with a plurality of terminal devices to which the AI/ML model is transferred from the first network device or the second network device, and

wherein determining the at least one reference positioning parameter comprises:

receiving, from the second network device, a slot indication indicating a slot for detecting the PRS; and

determining the at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot.
The method of claim 1, wherein the PRS resource configuration indicates a PRS resource set with a plurality of PRS resources, the PRS resource set being shared with a plurality of terminal devices to which the AI/ML model is transferred from the first network device or the second network device; and

wherein determining the at least one reference positioning parameter comprises:

receiving, from the second network device, a slot indication indicating a slot for detecting the PRS and an identity of a PRS resource within the PRS resource set; and

determining the at least one reference positioning parameter by detecting the PRS on the PRS resource within the slot.
The method of claim 1, wherein determining the at least one reference positioning parameter comprises:

determining a plurality of reference positioning parameters by detecting the PRS for a plurality of times; and

wherein determining the at least one deviation comprises:

determining a plurality of deviations between the plurality of reference positioning parameters and a plurality of predicted positioning parameters determined from outputs of the AI/ML model.
The method of claim 4, wherein transmitting the information indicating the at least one deviation comprises:

performing a plurality of transmissions to the second network device, each of the plurality of transmissions comprising information indicating one of the plurality of deviations.
The method of claim 1, further comprising:

receiving, from the second network device, signaling comprising an activation indication of the AI/ML model, the signaling indicating a slot gap between a slot for receiving the signaling and a slot for detecting the PRS, and

wherein the PRS is detected based on the slot gap.
The method of claim 1, wherein the at least one reference positioning parameter or the at least one predicated positioning parameter indicates at least one location of the terminal device, or

wherein the at least one reference positioning parameter or the at least one predicated positioning parameter indicates measurement results from the PRS receiving for positioning the terminal device.
A communication method comprising:

determining, at a terminal device, a first reference location of the terminal device by detecting a positioning reference signal (PRS) ;

transmitting, to a network device, information indicating a first location deviation between the first reference location and a first predicted location of the terminal device, the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model;

receiving, from the network device, a device configuration for configuring the terminal device as a positioning reference unit (PRU) ; and

transmitting, to the network device, a feedback indicating acceptance or rejection of the device configuration.
The method of claim 8, wherein the feedback indicates acceptance of the device configuration, the method further comprising:

determining a second reference location of the terminal device by detecting a further PRS; and

transmitting, to the network device, information indicating a second location deviation between the second reference location and a second predicted location of the terminal device, the second predicted location being determined from a second output of the AI/ML model, the second location deviation being used as a reference for determining an action to be performed on the AI/ML model.
A communication method comprising:

receiving, at a network device and from at least one terminal device, information indicating a plurality of deviations between reference positioning parameters and predicted positioning parameters, the reference positioning parameters being determined by the at least one terminal device by detecting a positioning reference signal (PRS) based on the at least one resource configuration, and the predicted positioning parameters being determined by the at least one terminal device from outputs of an artificial intelligence/machine learning (AI/ML) model; and

determining an action to be performed on the AI/ML model based on the plurality of deviations.
The method of claim 10, wherein the at least one terminal device comprises a plurality of terminal devices configured with a PRS resource configuration, the PRS resource configuration indicating a PRS resource with a specific pattern, and

wherein the method further comprises:

transmitting, to the at least one terminal device, at least one slot indication indicating at least one slot for detecting the PRS.
The method of claim 10, wherein the at least one terminal device comprises a plurality of terminal devices configured with a PRS resource configuration, the PRS resource configuration indicating a PRS resource set with a plurality of PRS resources; and

wherein the method further comprises:

transmitting, to the at least one terminal device, at least one slot indication indicating at least one slot for detecting the PRS and at least one identity of at least one PRS resource within the PRS resource set.
The method of claim 10, wherein the at least one terminal device comprises a first terminal device configured to detect the PRS for a plurality of times.
The method of claim 13, wherein receiving the information indicating the plurality of deviations comprises:

receiving a plurality of transmissions from the first terminal device, each of the plurality of transmissions comprising information indicating one of the plurality of deviations.
The method of claim 10, further comprising:

transmitting, to the at least one terminal device, signaling comprising an activation indication of the AI/ML model, the signaling indicating at least one slot gap between a slot for receiving the signaling and at least one slot for detecting the PRS by the at least one terminal device.
A communication method comprising:

receiving, at a network device and from a terminal device, information indicating a first location deviation between a first reference location and a first predicted location of the terminal device, the first reference location being determined by detecting a positioning reference signal (PRS) , and the first predicted location being determined from a first output of an artificial intelligence/machine learning (AI/ML) model transferred to the terminal device;

determining, based at least in part on the first location deviation, whether the terminal device is capable of acting as a positioning reference unit (PRU) ;

in accordance with a determination that the terminal device is capable of acting as a PRU, transmitting, to the terminal device, a device configuration for configuring the terminal device as a PRU; and

receiving, from the terminal device, a feedback indicating acceptance or rejection of the device configuration.
The method of claim 16, wherein the feedback indicates acceptance of the device configuration, the method further comprising:

receiving, from the terminal device, information indicating a second location deviation between a second reference location and a second predicted location of the terminal device, the second predicted location being determined from a second output of the AI/ML model; and

determining an action to be performed on the AI/ML model based at least in part on the second location deviation.
A terminal device comprising:

at least one processor; and

at least one memory storing instructions that, when executed by the at least one processor, cause the device to perform the method according to any of claims 1-9.
A network device comprising:

at least one processor; and

at least one memory storing instructions that, when executed by the at least one processor, cause the device to perform the method according to any of claims 10-17.
A computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method according to any of claims 1-9 or any of claims 10-17.