Device, method, and medium for communication
By determining timestamps and TRP combinations for AI/ML-based positioning, the method addresses the inefficiency in selecting TRPs, enhancing accuracy and reducing overhead in 5G networks.
Patent Information
- Application Number
- PCT/CN2024/083384
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-03-22
- Publication Date
- 2025-09-25
AI Technical Summary
The challenge in selecting the appropriate transmission reception points (TRPs) for AI/ML-based positioning in 5G networks is unresolved, leading to inefficiencies in determining the optimal TRP combinations for model inference, which affects positioning accuracy and increases overhead.
A device determines timestamps and TRP combinations for model inference, generating outputs based on integrated channel measurements from each combination, and selects the most suitable TRP combination for further inference, balancing accuracy and overhead.
This approach reduces overhead while maintaining positioning accuracy by strategically selecting TRP combinations, optimizing the AI/ML model's performance in determining UE location.
Smart Images

Figure CN2024083384_25092025_PF_FP_ABST
Abstract
Description
DEVICE, METHOD, AND MEDIUM FOR COMMUNICATIONFIELD
[0001] Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to a device, a method, and a computer readable medium for communication.BACKGROUND
[0002] Supporting various positioning methods to provide reliable, timely and accurate user equipment (UE) location is one of the key features of the third generation partnership project (3GPP) standard. It has been agreed to investigate the potential for artificial intelligence (AI) / machine learning (ML) in air interface to improve comprehensive performance in 5G-adcanced (5G-A) . AI / ML based mechanism to improve the positioning accuracy is one of the use cases to apply AI / ML in air interface.
[0003] The model input data may be based on data from multiple transmission reception points (TRPs) . It has been agreed that the number of TRPs is in a range of 3~18. However, how to select the involved TRPs from all TRPs is needed to be studied.SUMMARY
[0004] In general, example embodiments of the present disclosure provide a device, a method, and a computer storage medium for communication.
[0005] In a first aspect, there is provided a device deployed with at least one positioning model. The device comprises at least one processor configured to cause the device at least to:determine at least one timestamp for model inference; determine a plurality of TRP combinations, where each of the plurality of TRP combinations comprises at least three TRPs; for each of the plurality of TRP combinations, generate an output at the at least one timestamp by inputting model input data related to each TRP combination into the at least one positioning model; and determine, based on a plurality of outputs corresponding to the plurality of TRP combinations, one of the plurality of TRP combinations for further model inference.
[0006] In a second aspect, there is provided a method of communication performed by a device deployed with at least one positioning model. The method comprises: determining, at the device deployed with at least one positioning model, at least one timestamp for model inference; determining a plurality of TRP combinations, where each of the plurality of TRP combinations comprises at least three TRPs; for each of the plurality of TRP combinations, generating an output at the at least one timestamp by inputting model input data related to each TRP combination into the at least one positioning model; and determining, based on a plurality of outputs corresponding to the plurality of TRP combinations, one of the plurality of TRP combinations for further model inference.
[0007] In a third aspect, there is provided a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to carry out the method according to any one of the second aspect above.
[0008] It is to be understood that the summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0009] 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:
[0010] FIG. 1A an example communication network in which some embodiments of the present disclosure can be implemented;
[0011] FIGS. 1B-1E illustrate some example schematics for AI / ML based positioning;
[0012] FIG. 1F illustrates an example schematic of a TRP layout;
[0013] FIG. 2 illustrates a signalling chart illustrating a communication process in accordance with some example embodiments of the present disclosure;
[0014] FIGS. 3A-3C illustrate some example schematics for determining multiple TRP combinations in accordance with some example embodiments of the present disclosure;
[0015] FIGS. 4A-4C illustrate some example schematics for determining multiple time stamps in accordance with some example embodiments of the present disclosure;
[0016] FIG. 4D illustrates an example schematic for determining outputs in accordance with some example embodiments of the present disclosure;
[0017] FIG. 5 illustrates an example schematic of a report including center values in accordance with some example embodiments of the present disclosure;
[0018] FIG. 6 illustrates a flowchart of an example method implemented at a device deployed with at least one positioning model in accordance with some embodiments of the present disclosure; and
[0019] FIG. 7 illustrates a simplified block diagram of a device that is suitable for implementing embodiments of the present disclosure.
[0020] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION
[0021] 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.
[0022] 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.
[0023] References in the present disclosure to “one embodiment, ” “an embodiment, ” “an example embodiment, ” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
[0024] It shall be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.
[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a” , “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” , “comprising” , “has” , “having” , “includes” and / or “including” , when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.
[0026] 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.
[0027] As used herein, the term “communication network” refers to a network following any suitable communication standards or technologies, such as New Radio (NR) , Long Term Evolution (LTE) , LTE-Advanced (LTE-A) , Code Divided Multiple Address (CDMA) , Frequency Divided Multiple Address (FDMA) , Time Divided Multiple Address (TDMA) , Frequency Divided Duplexer (FDD) , Time Divided Duplexer (TDD) , Multiple-Input Multiple-Output (MIMO) , Orthogonal Frequency Divided Multiple Access (OFDMA) , cdma2000, Wideband Code Division Multiple Access (WCDMA) , High-Speed Packet Access (HSPA) , Global System for Mobile Communications (GSM) , Narrow Band Internet of Things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) , 5.5G, 5G-Advanced networks, beyond 5G (B5G) , the sixth generation (6G) communication protocols, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols either currently known or to be developed in the future. The techniques described herein may be used for the wireless networks and radio technologies mentioned above as well as other wireless networks and radio technologies. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.
[0028] As used herein, the term “terminal device” refers to any device having wireless or wired communication capabilities. Examples of terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, internet of things (IoT) devices, Ultra-reliable and Low Latency Communications (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, device on vehicle for V2X communication where X means pedestrian, vehicle, or infrastructure / network, devices for Integrated Access and Backhaul (IAB) , Space borne vehicles or Air borne vehicles in Non-terrestrial networks (NTN) including Satellites and High Altitude Platforms (HAPs) encompassing Unmanned Aircraft Systems (UAS) , eXtended Reality (XR) devices including different types of realities such as Augmented Reality (AR) , Mixed Reality (MR) and Virtual Reality (VR) , the unmanned aerial vehicle (UAV) commonly known as a drone which is an aircraft without any human pilot, devices on high speed train (HST) , or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or Internet appliances enabling wireless or wired Internet access and browsing and the like. The ‘terminal device’ can further has ‘multicast / broadcast’ feature, to support public safety and mission critical, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communications and IoT applications. It may also be incorporated one or multiple Subscriber Identity Module (SIM) as known as Multi-SIM. The term “terminal device” can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.
[0029] As used herein, the term “network device” refers to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of a network device include, but not limited to, a satellite, an unmanned aerial systems (UAS) platform, a Node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNB) , a transmission reception point (TRP) , a remote radio unit (RRU) , a radio head (RH) , a remote radio head (RRH) , an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS) , and the like.
[0030] As used herein, the term “TRP” may refer to an antenna port or an antenna array (with one or more antenna elements) available to the network device located at a specific geographical location, or a set of geographically co-located antennas (e.g. antenna array (with one or more antenna elements) ) supporting transmission point (TP) and / or reception point (RP) functionality. For example, a network device may be coupled with multiple TRPs in different geographical locations to achieve better coverage. Alternatively, or in addition, multiple TRPs may be incorporated into a network device, or in other words, the network device may comprise the multiple TRPs. The term “TRP” may be also referred to as a cell, such as a macro-cell, a micro-cell, a small cell, a pico-cell, a femto-cell, a remote radio head, a relay node, etc. It is to be understood that the term “TRP” may refer to a logical concept which may be physically implemented by various manners. There may be an explicit TRP identification for a TRP.
[0031] In one embodiment, the terminal device may be connected with a first network device and a second network device. One of the first network device and the second network device may be a master node (MN) and the other one may be a secondary node (SN) . The first network device and the second network device may use different radio access technologies (RATs) . In one embodiment, the first network device may be a first RAT device and the second network device may be a second RAT device. In one embodiment, the first RAT device is eNB and the second RAT device is gNB. Information related with different RATs may be transmitted to the terminal device from at least one of the first network device and the second network device. In one embodiment, first information may be transmitted to the terminal device from the first network device and second information may be transmitted to the terminal device from the second network device directly or via the first network device. In one embodiment, information related with configuration for the terminal device configured by the second network device may be transmitted from the second network device via the first network device. Information related with reconfiguration for the terminal device configured by the second network device may be transmitted to the terminal device from the second network device directly or via the first network device.
[0032] 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.
[0033] The terminal device or the network device may work on several frequency ranges, e.g. frequency range 1 (FR1) (410 MHz –7125 MHz) , frequency range 2 (FR2) (24.25GHz to 71GHz) , frequency band larger than 100GHz as well as Tera Hertz (THz) . It can further work on licensed / unlicensed / shared spectrum. The terminal device may have more than one connection with the network device under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.
[0034] The embodiments of the present disclosure may be performed in test equipment, e.g., signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, or channel emulator.
[0035] 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 1G, 2G, 2.5G, 2.75G, 3G, 4G, 4.5G, 5G, 5.5G, 5G-Advanced networks, or 6G networks.
[0036] 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.
[0037] As used herein, the singular forms “a” , “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term “includes” and its variants are to be read as open terms that mean “includes, but is not limited to. ” The term “based on” is to be read as “based at least in part on. ” The term “one embodiment” and “an embodiment” are to be read as “at least one embodiment. ” The term “another embodiment” is to be read as “at least one other embodiment. ” The terms “first, ” “second, ” and the like may refer to different or same objects. Other definitions, explicit and implicit, may be included below.
[0038] 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.
[0039] The terminal device or the network device may have AI or ML capability. It generally includes a model which has been trained from numerous collected data for a specific function, and can be used to predict some information.
[0040] As used herein, a model may be equivalent to at least one of the following: an AI / ML model, an ML model, an AI model, a data-driven, a data processing model, an algorithm, a functionality, a procedure, a process, an entity, a function, a feature, a feature group, a model identifier (ID) , an ID, a functionality ID, a configuration ID, a scenario ID, a site ID, or a dataset ID. As a result, the above terms may be used interchangeably. An “ID” may refer to an identifier, an identity, an identification, etc.
[0041] In some embodiments, the model may be represented by or associated with a channel, a resource, a resource set, a reference signal (RS) resource, an RS resource set, an RS port, a set of RS ports, an RS port ID, or a set of RS port IDs.
[0042] In some embodiments, the model may comprise a set of weights values that may be learned during training, e.g. for a specific architecture or configuration, where a set of weights values may also be called a parameter set.
[0043] In some embodiments, the model may be used to predict a target cell, or measurements of a set of beams of a set of candidate cells in future based on at least historical measurements (e.g., layer 1 (L1) -reference signal received power (RSRP) , L1-signal to interference plus noise ratio (SINR) ) of a set of beams of a set of candidate cells.
[0044] In some embodiments, an input of the AI / ML model (i.e., AI input) may refer to the input of a model and indicate data inputted into the model, which may be equivalent to data.
[0045] In some embodiments, an output of AI / ML model (i.e., AI output) may refers to the output of a model and indicate result (s) outputted by the model, which is equivalent to label / data.
[0046] In some embodiments, “ground truth” , “ground truth label” , “ground truth label of data” , “input label” , “input data” and “data” can be used interchangeably.
[0047] In some embodiments, a ground truth label of data (or ground-truth label) for monitoring or training the ML model (i.e., AI output) may refers to the authoritative, accepted data, or true answer or outcome for AI / ML model.
[0048] In some embodiments, the ground truth can be interpreted as actual / factual (i.e. actual / factual measured) data / values / results / collections / parameters, which can be used as reference, compared to prediction or inference.
[0049] AI / ML techniques play a significant role in enhancing the accuracy and reliability of positioning, which is particularly useful in indoor environments where global position system (GPS) signals might be weak or unavailable.
[0050] An AI / ML model may be deployed at a terminal device (such as a UE) , a network device (such as one or more gNBs or TRPs) , or a core network entity (such as a location management function (LMF) ) . The AI / ML model may be used for positioning, e.g. determining a positon (or location) of a UE. Some cases (case 1, case 2b, and case 3b below) are discussed as direct AI / ML positioning, and some other cases (case 2a, and case 3a below) are discussed as AI / ML assisted positioning:
[0051] · (1st priority) Case 1: UE-based positioning with UE-side model, direct AI / ML positioning.
[0052] · (2nd priority) Case 2b: UE-assisted / LMF-based positioning with LMF-side model, direct AI / ML positioning.
[0053] · (1st priority) Case 3b: NG-RAN node assisted positioning with LMF-side model, direct AI / ML positioning.
[0054] · (2nd priority) Case 2a: UE-assisted / LMF-based positioning with UE-side model, AI / ML assisted positioning.
[0055] · (1st priority) Case 3a: NG-RAN node assisted positioning with gNB-side model, AI / ML assisted positioning.
[0056] An enhancement for the accuracy of the AI / ML positioning is a work item (WI) in release 19. An AI / ML model can be deployed at UE side, gNB side, or LMF side. A model input may be integrated information of timing, power and phase, such as channel impulse response (CIR) , power delay profile (PDP) , or delay of path (DP) . A model output may be a UE location (e.g. a direct AI / ML positioning) or an intermediate measurement (e.g. AI / ML assisted positioning) . For example, an intermediate measurement may be a time of arrival (TOA) , which is obtained by extracting the model input from one or more reference signals, such as channel state information reference signal (CSI-RS) for downlink (DL) , PRS for DL, or sounding reference signal (SRS) for uplink (UL) .
[0057] Compared with legacy positioning methods, AI / ML based positioning will adopt separate measurements from multiple TRPs as model input. From UE side perspective, there may be extensive reception and measurement from multiple TRPs for case 1, case 2a, and case 2b; extensive transmission of measurement report among multiple TRP for case 2b; and extensive transmission of UL positioning reference signaling to multiple TRP for case 3a and case 3b. From network side perspective, there may be extensive transmission of DL positioning reference signaling from multiple TRPs for case 1, case 2a, and case 2b; extensive reception and measurement in multiple TRPs for case 3a and case 2b; and extensive transmission of the measurement from multiple TRP for case 3b.
[0058] According to some existing CSI reporting ways, reporting the measurement after compression will significantly reduce the overhead at the cost of possible performance degradation. The compression methods may include: truncating the measurement in time domain, and / or reducing the number of TRPs.
[0059] For evaluating an effectiveness of an AI / ML model, model input data is needed. The dimension of the model input data depends on the number of TRPs, the number of samples, and the number of antenna ports. It is noted that the input data with a reduced number of TRPs can achieve a comparable positioning accuracy, however, how to determine the involved TRPs within all TRPs for the AI / ML model should be studied.
[0060] Embodiments of the present disclosure provide a solution of communication. In the solution, a device with a deployed positioning model determines at least one timestamp and a plurality of TRP combinations. The device may generate a corresponding out at the at least one timestamp by inputting model input data related to each TRP combination into the positioning model, and determines one TRP combination for further model inference. As such, one TRP combination may be determined and there is no need to use all TRPs, therefore, the overhead can be reduced. In addition, the one TRP combination is determined based on outputs associated with multiple TRP combinations, making a balance between the positioning accuracy and the overhead. Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
[0061] FIG. 1A illustrates an example communication network 100 in which some embodiments of the present disclosure can be implemented. The communication network 100 may also be called as a network environment, a network system, a communication environment, a communication system, or the like, the present disclosure does not limit this aspect. The communication network 100 includes a terminal device 110, multiple network devices 120-1 to 120-N, and an LMF 130. It should be appreciated that the LMF 130 may be a location server, which is located in the access network or in a core network.
[0062] The multiple network devices 120-1 to 120-N (N is a positive integer, e.g. N>3) may be separately or collectively be referred to as a network device 120, which may be a gNB or a TRP. For example, N may equal to 18 or another integer.
[0063] In the communication network 100, the network device 120 can communicate / transmit data and control information to the terminal device 110, and the terminal device 110 can also communicate / transmit data and control information to the network device 120. A link from the network device 120 to the terminal device 110 is referred to as a DL, while a link from the terminal device 110 to the network device 120 is referred to as a UL. DL may comprise one or more logical channels, including but not limited to a Physical Downlink Control Channel (PDCCH) and a Physical Downlink Shared Channel (PDSCH) . UL may comprise one or more logical channels, including but not limited to a Physical Uplink Control Channel (PUCCH) and a Physical Uplink Shared Channel (PUSCH) . As used herein, the term “channel” may refer to a carrier or a part of a carrier consisting of a contiguous set of resource blocks (RBs) on which a channel access procedure is performed in shared spectrum.
[0064] In the communication network 100, the terminal device 110 can communicate with the LMF 130 according to any proper communication protocol, such as an LTE positioning protocol (LPP) . In the communication network 100, the network device 120 can communicate with the LMF 130 according to any proper communication protocol, such as an NR positioning protocol A (NRPPa) . It is to be understood that other protocol may also be applied and will not be listed herein.
[0065] Embodiments of the present disclosure can be applied to any suitable scenarios. For example, embodiments of the present disclosure can be implemented at reduced capability NR devices. Alternatively, embodiments of the present disclosure can be implemented in one of the followings: NR multiple-input and multiple-output (MIMO) , NR sidelink enhancements, NR systems with frequency above 52.6GHz, an extending NR operation up to 71GHz, narrow band-Internet of Thing (NB-IOT) / enhanced Machine Type Communication (eMTC) over non-terrestrial networks (NTN) , NTN, UE power saving enhancements, NR coverage enhancement, NB-IoT and LTE-MTC, Integrated Access and Backhaul (IAB) , NR Multicast and Broadcast Services, or enhancements on Multi-Radio Dual-Connectivity.
[0066] It is to be understood that the numbers of devices (i.e., the terminal devices 110 and the network device 120) and their connection relationships and types shown in FIG. 1A are only for the purpose of illustration without suggesting any limitation. The communication network 100 may include any suitable numbers of devices adapted for implementing embodiments of the present disclosure. The communication network 100 may include one or more entities which are not shown in FIG. 1A.
[0067] For AI / ML-assisted positioning, a “single-TRP construction” and a “multi-TRP construction” are being discussed. Single-TRP construction: the input of the ML model is the channel measurement between the target UE and a single TRP, and the output of the ML model is for the same pair of UE and TRP. Multi-TRP construction: the input of the ML model contains N sets of channel measurements between the target UE and N (N>1) TRPs, and the output of the ML model contains N sets of values, one for each of the N TRPs.
[0068] In some cases, three constructions may be evaluated for the AI / ML assisted positioning: Single-TRP, same model for N TRPs; Single-TRP, N models for N TRPs; and Multi-TRP (i.e., one model for N TRPs) .
[0069] In some cases, there may be N TRPs (TRP 0, TRP 1, …, TRP (N-1) ) used for AI / ML based positioning, and direct AI / ML positioning (FIG. 1B) and assisted AI / ML positioning (FIGS. 1C-1E) may be evaluated. FIG. 1B illustrates an example schematic of direct AI / ML positioning with an output is the UE location. FIG. 1C illustrates an example schematic of assisted AI / ML positioning with multi-TRP construction, FIG. 1D illustrates an example schematic of assisted AI / ML positioning with single-TRP construction and one model for N TRPs, and FIG. 1E illustrates an example schematic of assisted AI / ML positioning with single-TRP construction and N models for N TRPs.
[0070] As shown in FIGS. 1C-1E, the assisted AI / ML positioning (may also be referred to as AI / ML assisted positioning) can be applied using input data (such as CIR, PDP, or DP) associated with one single TRP or multiple TPRs. For the former scenario, N models with different parameters or a single model may be deployed to estimate time information (e.g., time of arrival (TOA) ) for N TRPs, which may be regarded as a distributed model on each TRP. In the latter scenario, a single comprehensive model (i.e. a centralized model) utilizes the data from multiple TRPs as the input and produces the multiple TOAs corresponding to the multiple TRPs.
[0071] For the model input used in evaluations of AI / ML based positioning, if time-domain CIR or PDP is used as model input in the evaluation, companies report the input dimension NTRP *Nport *Nt, where NTRP is the number of TRPs, Nport is the number of transmit / receive antenna port pairs, and Nt is the number of consecutive time domain samples. If N’t (N’t <Nt) samples with the strongest power are selected as model input, with remaining (Nt -N’t) time domain samples set to zero, then companies report value N’ t in addition to Nt. It is also assumed that timing info for the N’t samples need to be provided as model input.
[0072] For the evaluation of AI / ML based positioning, the study of model input due to different number of TRPs include the following approaches. Approach 1: Model input size stays constant as NTRP=18. The number of TRPs (N’TRP) that provide measurements to model input varies. When N’TRP < NTRP, the remaining (NTRP -N’TRP) TRPs do not provide measurements to model input, i.e., measurement value is set such that the (NTRP -N’TRP) TRPs do not affect model output. Approach 2: The TRP dimension of model input is equal to the number of TRPs (N’TRP) that provide measurements as model input. When N’TRP < NTRP, the remaining (NTRP -N’TRP) TRPs are ignored by the given model. FIG. 1F illustrates an example schematic of a TRP layout. As shown in FIG. 1F, there are NTRP=18 TRPs with indices 0-17, the layout has a length L and a width W, a distance between two adjacent TPPs is D, and a distance of an edge TRP to the edge of the layout is D / 2.
[0073] During a simulation, it is assumed that 18 TRPs are deployed for the indoor factory scenario for generating input data. However, when considering the actual model deployment, it is difficult to guarantee that all 18 TRPs are always available for positioning process since the part of TRPs is inefficient to position the UE. For example, some of the TRPs may cease PRS transmission for the network energy saving or load control purpose, or there may be poor transmission environment between some TRPs and the UE. In this event, reducing the number of TRPs used for positioning can reduce the overhead of measurement and reporting at the cost of possible performance degradation. There may be a trade-off between the number of TRPs and positioning performance for both direct AI / ML positioning and AI / ML assisted positioning.
[0074] In the present disclosure, “AI / ML model” is a data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs; “data collection” is a process of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics and inference; “model training” is a process to train an AI / ML Model by learning the input / output relationship in a data driven manner and obtain the trained AI / ML Model for inference; “model inference” is a process of using a trained AI / ML model to produce a set of outputs based on a set of inputs; and “model monitoring” is a procedure that monitors the inference performance of the AI / ML model.
[0075] In the present disclosure, a TRP combination may be called as a TRP group which includes at least three TRPs.
[0076] It is to be noted that the physical environment between the terminal device and a specific TRP is variable and the UE location is uncertain, thus the dominant TPRs involved in positioning procedure will be changed at different time stamps. In this event, it is necessary to change the TRP combination for positioning the UE, if only part of the TRPs are requires to involve the positioning procedure for indoor factory scenario, so as to reduce the overhead for collecting model input data. However, how to determine the TPR combination involved in positioning procedure is a critical issue, especially when the model is deployed at UE side (case 1 and case 2a mentioned above) .
[0077] Reference is further made to FIG. 2, which illustrates a signalling chart illustrating communication process 200 in accordance with some example embodiments of the present disclosure. The process 200 may involve a terminal device 110 and a further device 202, where the further device 202 may be a network device 120, an LMF 130 as shown in FIG. 1A, or may be another network entity not shown in FIG. 1A. It would be appreciated that the process 200 may be applied to other communication scenarios, which will not be described in detail.
[0078] There is at least one deployed positioning model at the terminal device 110, and a deployed model may be an AI / ML model for positioning. A model input of the deployed model may be input data related to a TRP combination. A model output of the deployed model may be an intermediate measurement or a UE location.
[0079] In the process 200, the terminal device 110 determines at least one timestamp at 210. In some implementations, the at least one timestamp may be used for model inference to determine a TRP combination. In some example embodiments, the at least one timestamp may also be referred to as implementation time of model inference, predefined timing for model inference, or the like, the present disclosure does not limit for this aspect. In some example embodiments, the at least one timestamps may include multiple time points. For example, each time point may be represented as a frame number and a slot number.
[0080] In some implementations, the terminal device 110 may receive information about the multiple time points from the further device 202. In some examples, the information from the further device 202 may be timing information. In some examples, the further device 202 may be any of: an access network device (such as the network device 120) , an LMF (such as the LMF 130) , or an entity associated with an activation of the at least one positioning model.
[0081] In some examples, the multiple time points may be periodic, for example, the multiple time points may be an explicit set of periodic timing points. In some examples, the timing information from the further device 202 may include a start time point and a periodicity value. In some instances, the terminal device 110 can determine the multiple time points based on the start time point and the periodicity value, for example, each of the multiple time points can be characterized by a frame number and a slot number based on the start time point and the periodicity value.
[0082] In some examples, the multiple time points may be aperiodic, for example, the multiple time points may be an explicit set of timing points each characterized by a frame number and a slot number. In some examples, the timing information from the further device 202 may include the explicit set of timing points. In some instances, the terminal device 110 can obtain the multiple time points from the timing information.
[0083] In some embodiments, the further device 202 may be a network device 120, such as a serving gNB of the terminal device 110. In some examples, the timing information may be transmitted from the serving gNB via a DL transmission. For example, the timing information may be carried in a radio resource control (RRC) message, a medium access control (MAC) control element (CE) , or downlink control information (DCI) . It is to be noted that the timing information can be carried in some other message, signalling, or data packet, the present disclosure does not limit for this aspect.
[0084] In some implementations, the terminal device 110 may determine the at least one timestamp according to the deployed scenario. In some examples, the terminal device 110 may determine a difference of a model input (e.g., CIR / PDP / DP) at a first time point and a further model input prior to the first time point, and may determine that the at least one timestamp comprises the first time point if the difference exceeds a first threshold. In some examples, the terminal device 110 may determine a difference of a model output (e.g., UE location or an intermediate measurement) at a second time point and a further model output prior to the second time point, and may determine that the at least one timestamp comprises the second time point if the difference exceeds a second threshold. In some examples, the terminal device 110 may determine a difference of a location of the terminal device at a third time point and a further location of the terminal device prior to the third time point, and may determine that the at least one timestamp comprises the third time point if the difference exceeds a third threshold.
[0085] In the process 200, the terminal device 110 determines a plurality of TRP combinations at 220. In some implementations, the plurality of TRP combinations may be referred to as a set of TRP combinations, a group of TRP combinations, or the like, the present disclosure does not limit for this aspect. In some implementations, each TRP combination includes at least three TRPs.
[0086] In the present disclosure, the model input data may be associated with a TRP combination. For example, a model input is determined based on the integration of channel information between each TRP within the TRP combination and the terminal device 110.
[0087] In the present disclosure, a TRP can be represented by a TRP identification, accordingly a TRP combination can be represented by a set of TRP identifications which may include at least three TRP identifications. In some examples, the TRP identification may be implemented as a TRP ID, or an index of the TRP that shown in the layout of FIG. 1F.
[0088] In some implementations, the terminal device 110 may receive information about the plurality of TRP combinations from the further device 202. In some examples, the information from the further device 202 may be TRP information. In some examples, the further device 202 may be any of: an access network device (such as the network device 120) , an LMF (such as the LMF 130) , or a network entity which is not shown in FIG. 1A.
[0089] In some examples, the TRP information may include an indication indicating an inference mode. For example, the inference mode may be a first mode or a second mode. The first mode represents that the model input data is related to the TRPs nearest to the terminal device 110, and the second mode represents that the model input data is related to TRPs nearest to a central point. In some examples, the terminal device 110 may determine the plurality of TRP combinations based on the indication.
[0090] In some examples, the indication may further indicate a quantity of TRPs in each TRP combinations. In some examples, the indication may further indicate a number of the plurality of TRP combinations.
[0091] In some embodiments, the first mode may be represented as mode 0, which may include multiple sub-modes, such as mode 0-0, mode 0-1, mode 0-2, …, mode 0-n. In some examples, mode 0-0 may refer to TRP combinations each with three TRPs that are closest to the terminal device 110, mode 0-1 may refer to TRP combinations each with four TRPs that are closest to the terminal device 110, …and mode 0-n may refer to TRP combinations each with n+3 TRPs that are closest to the terminal device 110. In some instances, the quantity of TRPs may be implemented as an index of the sub-mode.
[0092] For example, if mode 0-0 is indicated and the number of the plurality of TRP combinations is 4, then the terminal device 110 determines 4 TRP combinations that are closest to the terminal device 110, and each of the 4 TRP combinations includes three TRPs closest to the terminal device 110.
[0093] In some embodiments, the second mode may be represented as mode 1, which may include multiple sub-modes, such as mode 1-0, mode 1-1, mode 1-2, …, mode 1-n. In some examples, mode 1-0 may refer to TRP combinations each with three most central TRPs, mode 1-1 may refer to TRP combinations each with four most central TRPs, …and mode 1-n may refer to TRP combinations each with n+3 most central TRPs. In some instances, the quantity of TRPs may be implemented as an index of the sub-mode.
[0094] For example, if mode 1-0 is indicated and the number of the plurality of TRP combinations is 4, then the terminal device 110 determines 4 TRP combinations that are closest to the central point, and each of the 4 TRP combinations includes three most central TRPs.
[0095] In the process 200, the terminal device 110 generates outputs by inputting the data that integrate the channel impulse response or measurement of each TRP within each TRP combination at 230. In some implementations, model inference can be performed by the terminal device 110 by using the at least one positioning model, to generate the outputs.
[0096] Specifically, it is assumed that the at least one timestamp determined at 210 includes Nt time points, and the plurality of TRP combinations include Nc TRP combinations.
[0097] In some implementations, model input data can be determined for each TRP combination, for example, data associated with each TRP combination can be determined. In this way, the terminal device 110 can determine Nc data corresponding to Nc TRP combinations respectively. As a specific example, for model input data {input 1, input 2, …, input Nc} , {output 1, output 2, …, output Nc} can be generated.
[0098] In some implementations, for each TRP combination, corresponding data can be inputted into a positioning model at a time point, to generate an output. In some examples, an output for a TRP combination may include Nt output data at Nt time points. For example, the terminal device 110 may perform Nc times of model inference based on corresponding data (among Nc data) . As such, Nc outputs for Nc TRP combinations can be generated.
[0099] In some example embodiments, there may be more than one positioning model deployed at the terminal device 110, for example, there may be Nm positioning models. In this case, the above procedure for generating outputs can be applied for each of the Nm positioning models. As such, Nm*Nc outputs can be generated for Nc TRP combinations.
[0100] In addition or alternatively, the terminal device 110 may transmit a report to the further device 202 at 240. In some implementations, the terminal device 110 may generate the report based on the outputs determined at 230, i.e. outputs for Nc TRP combinations. In some implementations, the report may be used by the further device 202 to determine (or select) one TRP combination, e.g. a best TRP combination in the current physical environment, to generate the model input data in the next period.
[0101] In some implementations, the terminal device 110 may be capable to access the ground truth, e.g. which is corresponding to the outputs. In some example embodiments, the terminal device 110 can determine a comparison result based on an output of a TRP combination and the ground truth. For Nc TRP combinations, Nc comparison results may be determined accordingly. In some example embodiments, the terminal device 110 may further generate the report based on Nc comparison results.
[0102] In some example embodiments, the report may include Nc comparison results corresponding to Nc TRP combinations. In some examples, an order of the Nc comparison results in the report is the same as the order of corresponding Nc TRP combinations.
[0103] As a specific example, Nc TRP combinations may include TRP combination 1, TRP combination 2, …., TRP combination Nc. Nc comparison results may include comparison result 1, comparison result 2, …, comparison result Nc. The comparison result x is corresponding to TRP combination x, where x=1, 2, …, Nc. Comparison result x may be determined as |output x-G|, where “output x” corresponds to the model output by inputting the data related to TRP combination x, “G” represents to the ground truth, and “| |” represents an absolute value.
[0104] If there are multiple positioning models deployed at the terminal device 110, e.g. Nm positioning models, then multiple sets of comparison results can be determined, e.g. Nm sets of comparison results. For example, the Nm positioning models may be ordered according to the model IDs, e.g. in an increasing order or in a decreasing order of the model IDs. For example, the y-th set of comparison results corresponds to the y-th positioning model in the Nm positioning models. For example, each set of comparison results includes Nc comparison results in a same order as Nc TRP combinations.
[0105] In some example embodiments, the report may include a predefined number of comparison results in Nc comparison results, for example, the predefined number may be represented as N0. That is, the report includes N0 comparison results, but not all comparison results. In some instances, N0 comparison results may be N0 smallest ones among Nc comparison results.
[0106] In some examples, the report may also include N0 model input data corresponding to the N0 comparison results, for example, the x-th model input data in the report corresponds to the x-th comparison result. In some instances, N0 comparison results can be ordered in an increasing order or in a decreasing order.
[0107] In some other examples, the report may also include N0 identifiers of N0 TRP combinations corresponding to the N0 comparison results, for example, the x-th identifier is used for identifying a TRP combination that corresponds to the x-th comparison result in the report. In some instances, N0 comparison results can be ordered in an increasing order or in a decreasing order.
[0108] If there are multiple positioning models deployed at the terminal device 110, e.g. Nm positioning models, then multiple sets of comparison results can be determined, e.g. Nm sets of comparison results. For example, the Nm positioning models may be ordered according to the model IDs, e.g. in an increasing order or in a decreasing order of the model IDs. For example, the y-th set of comparison results corresponds to the y-th positioning model in the Nm positioning models. For example, each set of comparison results includes N0 comparison results which are smallest among Nc comparison results corresponding to Nc TRP combinations.
[0109] As a specific example, the terminal device 110 may determine multiple model input data, such as {input1, input2, input 3, …} , and generate corresponding multiple outputs, such as {output1, output2, output3, …} , by inputting the multiple model input data into a deployed positioning model, where output x correspond to the input x. In addition, multiple comparison results can be determined as {|output1 -G|, |output2 -G|, |output3 -G|, …} , where G is the ground truth. In some instances, the terminal device 110 can select N0 smallest values among multiple comparison results and report the N0 smallest comparison results to the further device 202. N0 identifiers of N0 TRP combinations corresponding to the N0 comparison results may further be reported. For example, for a specific comparison result in the N0 smallest comparison results, it is a comparison result y among {|output1 -G|, |output2 -G|, |output3 -G|, …} , then TRP combination y is corresponding to the specific comparison result, and the identifier of TRP combination y will be reported.
[0110] In some other implementations, the terminal device 110 may be incapable to access the ground truth. In some examples, the model outputs or corresponding results can be transferred to the further device 202 for determining a best TRP combination.
[0111] In some example embodiments, the report may include Nc outputs corresponding to Nc TRP combinations. As a specific example, for model input data {input 1, input 2, …, input Nc} , {output 1, output 2, …, output Nc} can be generated, and the terminal device 110 may report {output 1, output 2, …, output Nc} to the further device 202, where output x corresponds to input x, and input x is generated based on TRP combination x within Nc TRP combinations.
[0112] In some other example embodiments, the report may include another predefined number of outputs that are center values among all outputs (i.e. Nc outputs) . For example, another predefined number may be represented as N1, which may be pre-configured by the further device 202. In some instances, N1 outputs may be N1 central values among Nc outputs.
[0113] In the process 200, the terminal device 110 determines one or more TRP combinations at 250. In some implementations, the further device 202 can select one or more TRP combinations from the plurality of TRP combinations based on the report from the terminal device 110. In some implementations, the further device 202 may transmit indication information of the selected TRP combination (s) to the terminal device 110 at 245. In some examples, the terminal device 110 can be aware of the selected TRP combination based on the indication information from the further device 202.
[0114] As one specific example, one TRP combination can be selected by the further device 202. For example, the indication information at 245 can be an identifier of the selected TRP combination.
[0115] In some instances, the selected TRP combination (s) can be regarded as best TRP combination (s) in the current physical environment, and the TRP combination (s) will be used for further data collection. For example, model input data may be collected based on the TRP combination (s) , and the model inference can be performed accordingly. As one specific example, one best TRP combination can be further used.
[0116] FIG. 3A illustrates an example schematic 310 for determining multiple TRP combinations in accordance with some example embodiments of the present disclosure. It is assumed that the TRP information from the further device 202 to the terminal device 110 include an indication indicating that the inference mode is the first mode, i.e. mode 0 and further mode 0-0 as mentioned above. That means, each TRP combination should include at least three TRPs that are closest to the terminal device 110, which locates at 312 as shown in FIG. 3A.
[0117] As one example, if the TRP information indicates model 0-0, and the number of TRP combinations is indicated as 4, then 4 TRP combinations can be determined as: {TRP 0, TRP 1, TRP 3} , {TRP 0, TRP 1, TRP 4} , {TRP 1, TRP 3, TRP 4} , and {TRP 0, TRP 3, TRP 4} . Accordingly, the terminal device 110 will determine the model input data as: data 1 associated with {TRP 0, TRP 1, TRP 3} , data 2 associated with {TRP 0, TRP 1, TRP 4} , data 3 associated with {TRP 1, TRP 3, TRP 4} , and data 4 associated with {TRP 0, TRP 3, TRP 4} .
[0118] As another example, if the TRP information indicates model 0-1, and the number of TRP combinations is indicated as 4, then 4 TRP combinations can be determined as: {TRP 0, TRP 1, TRP 3, TRP 4} , {TRP 3, TRP 1, TRP 4, TRP 2} , {TRP 1, TRP 3, TRP 4, TRP 5} , and {TRP 3, TRP 1, TRP 4, TRP 6} . Accordingly, the terminal device 110 will determine the model input data as: data 1 associated with {TRP 0, TRP 1, TRP 3, TRP 4} , data 2 associated with {TRP 3, TRP 1, TRP 4, TRP 2} , data 3 associated with {TRP 1, TRP 3, TRP 4, TRP 5} , and data 4 associated with {TRP 3, TRP 1, TRP 4, TRP 6} .
[0119] FIG. 3B illustrates an example schematic 320 for determining multiple TRP combinations in accordance with some example embodiments of the present disclosure. It is assumed that the TRP information from the further device 202 to the terminal device 110 include an indication indicating that the inference mode is the first mode, i.e. mode 0 as mentioned above. That means, each TRP combination should include at least three TRPs that are closest to the terminal device 110, which locates at 322 as shown in FIG. 3B. Similar with that with reference to FIG. 3A, if the TRP information indicates model 0-0, and the number of TRP combinations is indicated as 4, then 4 TRP combinations can be determined as: {TRP 13, TRP 14, TRP 16} , {TRP 13, TRP 14, TRP 17} , {TRP 13, TRP 16, TRP 17} , and {TRP 14, TRP 16, TRP 17} .
[0120] FIG. 3C illustrates an example schematic 330 for determining multiple TRP combinations in accordance with some example embodiments of the present disclosure. It is assumed that the TRP information from the further device 202 to the terminal device 110 include an indication indicating that the inference mode is the second mode, i.e. mode 1 as mentioned above. That means, each TRP combination should include at least three TRPs that are closest to the central point, although the terminal device 110 locates at 332 as shown in FIG. 3C. For example, the most central TPRs in InF scenario include TRP 6, TRP 7, TRP 8, TRP 9, TRP 10, and TRP 11.
[0121] As one example, if the TRP information indicates model 1-0, and the number of TRP combinations is indicated as 4, then 4 TRP combinations can be determined as: {TRP 7, TRP 10, TRP 8} , {TRP 7, TRP 10, TRP 11} , {TRP 7, TRP 10, TRP 6} , and {TRP 7, TRP 10, TRP 9} . Accordingly, the terminal device 110 will determine the model input data as: data 1 associated with {TRP 7, TRP 10, TRP 8} , data 2 associated with {TRP 7, TRP 10, TRP 11} , data 3 associated with {TRP 7, TRP 10, TRP 6} , and data 4 associated with {TRP 7, TRP 10, TRP 9} .
[0122] As another example, if the TRP information indicates model 1-1, and the number of TRP combinations is indicated as 2, then 2 TRP combinations can be determined as: {TRP 7, TRP 10, TRP 8, TRP 11} , and {TRP 7, TRP 10, TRP 6, TRP 9} . Accordingly, the terminal device 110 will determine the model input data as: data 1 associated with {TRP 7, TRP 10, TRP 8, TRP 11} , and data 2 associated with {TRP 7, TRP 10, TRP 6, TRP 9} .
[0123] FIG. 4A illustrates an example schematic 410 for determining multiple time stamps in accordance with some example embodiments of the present disclosure. As shown in FIG. 4A, multiple time stamps include time 1, time 2, time 3, and time 4 which are periodic. For example, the timing information from the further device 202 may include a start time point and a periodicity value.
[0124] FIG. 4B illustrates an example schematic 420 for determining multiple time stamps in accordance with some example embodiments of the present disclosure. As shown in FIG. 4B, multiple time stamps include time 1, time 2, and time 3 which are aperiodic. For example, the timing information from the further device 202 may include a set of timing points each characterized by a frame number and a slot number.
[0125] FIG. 4C illustrates an example schematic 430 for determining multiple time stamps in accordance with some example embodiments of the present disclosure. As shown in FIG. 4C, multiple time stamps include time 1 and time 2, e.g., determined based on various deployed scenarios.
[0126] Assume that the multiple TRP combinations includes Nc TRP combination, as shown in FIGS. 4A-4C, the model input data at each timestamp include: data 0 associated with TRP 0, TRP 1, and TRP 2; data 1 associated with TRP 0, TRP 1, and TRP 3; …and data n associated with TRP 15, TRP 16, and TRP 17, where n=Nc-1.
[0127] FIG. 4D illustrates an example schematic 440 for determining outputs in accordance with some example embodiments of the present disclosure. There may be Nc TRP combinations, and the model input data include: model input associated with combination 1 (TRP 0, TRP 1, and TRP 2) , model input associated with combination 2 (TRP 0, TRP 1, and TRP 3) , model input associated with combination 3 (TRP 1, TRP 2, and TRP 3) , …and model input associated with combination Nc (TRP 15, TRP 16, and TRP 17) . The model input can be input into the positioning model, and the outputs can be obtained respectively, such as output 1, output 2, output 3, …, output Nc as shown in FIG. 4D.
[0128] FIG. 5 illustrates an example schematic 500 of a report including center values in accordance with some example embodiments of the present disclosure. It is assumed that the terminal device 110 is incapable to access the ground truth, and the report may include N1 outputs that are center values among Nc outputs. As an example, Nc=7, and N1=1. The terminal device 110 may determine the outputs {k1, k2, k3, k4, k5, k6, k7} by inputting the model input data {input 1, input 2, input 3, …, input 7} into the positioning model respectively. The most center value is identified as k2 since it is closest to all points k1-k7.
[0129] Some embodiments with reference to FIGS. 2-5 are provided for a scenario that the terminal device 110 has at least one deployed positioning model, in the solution, the terminal device 110 may determine at least one timestamp and a plurality of TRP combinations, may generate outputs for the plurality of TRP combinations, and provide a report to the further device 202 for selecting one (such as a best) TRP combination.
[0130] In some other scenarios, the at least one positioning model may be deployed at a network device 120 such as a serving gNB of the terminal device 110 to be positioned, or deployed at an LMF 130.
[0131] In some implementations, the at least one positioning model is deployed at gNB side (case 3a mentioned above) . The network device 120 with at least one deployed positioning model may determine at least one timestamp and determine a plurality of TRP combinations. For example, the network device 120 may receive timing information from the LMF 130 or a network entity associated with the activation of the at least one positioning model. For example, the network device 120 may receive TRP information from the LMF 130 or a network entity which is not shown in FIG. 1A. For example, the network device 120 may determine the at least one timestamp according to various deployed scenarios of the terminal device 110 to be positioned. In some examples, the network device 120 may determine (or select) the best TRP combination based on the outputs. In some other examples, the network device 120 may further transmit a report to the LMF 130 or a network entity which is not shown in FIG. 1A. It is to be appreciated that details of related information may refer to those discussed with reference to FIGS. 2-5, and will not be repeated herein for brevity.
[0132] In some implementations, the at least one positioning model is deployed at LMF side (case 2b and case 3b mentioned above) . The LMF 130 with at least one deployed positioning model may determine at least one timestamp and determine a plurality of TRP combinations. For example, the LMF 130 may receive timing information from the terminal device 110 to be positioned or a network entity associated with the activation of the at least one positioning model. For example, the LMF 130 may receive TRP information from the terminal device 110 to be positioned or a network entity which is not shown in FIG. 1A. For example, the LMF 130 may determine the at least one timestamp according to various deployed scenarios of the terminal device 110 to be positioned. In some examples, the LMF 130 may determine (or select) the best TRP combination based on the outputs. It is to be appreciated that details of related information may refer to those discussed with reference to FIGS. 2-5, and will not be repeated herein for brevity.
[0133] According to some embodiments with reference to FIGS. 2-5, a solution for determining one TRP combination, such as a best TRP combination, is provided. This solution supports a dynamic adjustment of the TRP combination used for positioning. The number of TRPs in the TRP combination used for positioning may be varied, so as to save the power at UE and / or gNB side, thereby reducing the transmission overhead of measurement if needed. Therefore, a balance between the overhead and the positioning accuracy can be made.
[0134] FIG. 6 illustrates a flowchart of an example method 600 implemented at a device in accordance with some embodiments of the present disclosure. For example, the device may be the terminal device 110, the network device 120, or the LMF 130, which has at least one deployed positioning model.
[0135] At block 610, the device determines at least one timestamp for model inference. At block 620, the device determines a plurality of TRP combinations, wherein each of the plurality of TRP combinations comprises at least three TRPs. At block 630, for each of the plurality of TRP combinations, the device generates an output at the at least one timestamp by inputting model input data related to each TRP combination into the at least one positioning model. At block 640, the device determines, based on a plurality of outputs corresponding to the plurality of TRP combinations, one of the plurality of TRP combinations for further model inference.
[0136] In some example embodiments, the device generates a report based on the plurality of outputs corresponding to the plurality of TRP combinations; the device transmits, to a further device, the report that is used by the further device to select the one of the plurality of TRP combinations; and the device receives, from the further device, indication information of the one of the plurality of TRP combinations for collecting further model input data.
[0137] In some example embodiments, the further device comprises at least one of: an access network device, an LMF, or a network entity.
[0138] In some example embodiments, for each TRP combination of the plurality of TRP combinations, the device determines a comparison result based on the output of each TRP combination and a ground truth; and generates the report based on the plurality of comparison results for the plurality of TRP combinations respectively.
[0139] In some example embodiments, the report comprises the plurality of comparison results for the plurality of TRP combinations respectively.
[0140] In some example embodiments, an order of the plurality of comparison results is determined based on an order of the plurality of TRP combinations.
[0141] In some example embodiments, the report comprises one or more comparison results in the plurality of comparison results, wherein the one or more comparison results are the smallest results among the plurality of comparison results. In some example embodiments, a number of the one or more comparison results is predefined.
[0142] In some example embodiments, the report further comprises one or more identifiers for one or more TRP combinations corresponding to the one or more comparison results. In some other example embodiments, the report further comprises one or more model input data associated with one or more TRP combinations corresponding to the one or more comparison results.
[0143] In some example embodiments, the report comprises: the plurality of outputs corresponding to the plurality of TRP combinations, or one or more outputs in the plurality of outputs, wherein the one or more outputs are in a center of an increasing or decreasing order of the plurality of outputs. In some example embodiments, a number of the one or more outputs is predefined.
[0144] In some example embodiments, the at least one timestamp comprises a plurality of time points, and each of the plurality of time points is represented by a frame number and a slot number.
[0145] In some example embodiments, the device receives, from a further device, information about the plurality of time points, wherein the further device comprises at least one of: an access network device, an LMF, a terminal device to be positioned, or an entity associated with an activation of the at least one positioning model. In some example embodiments, the information comprises a start time point and a periodicity value.
[0146] In some example embodiments, if a difference of a model input at a first time point and a further model input prior to the first time point exceeds a first threshold, the device determines that the at least one timestamp comprises the first time point. In some example embodiments, if a difference of a model output at a second time point and a further model output prior to the second time point exceeds a second threshold, the device determines that the at least one timestamp comprises the second time point. In some example embodiments, if a difference of a location of the terminal device at a third time point and a further location of the terminal device prior to the third time point exceeds a third threshold, the device determines that the at least one timestamp comprises the third time point.
[0147] In some example embodiments, the device receives, from a further device, information about the plurality of TRP combinations, wherein the further device comprises at least one of: an access network device, an LMF, a terminal device to be positioned, or a network entity.
[0148] In some example embodiments, the device comprises a terminal device, and the terminal device receives, from an access network device or an LMF, an indication indicating an inference mode; and determines, based on the indication, the plurality of TRP combinations.
[0149] In some example embodiments, the inference mode is a first mode or a second mode, the first mode is associated with TRPs nearest to the terminal device, and the second mode is associated with TRPs nearest to a central point.
[0150] In some example embodiments, the indication further indicates a series of TRPs identification in each of the plurality of TRP combination which equals to or is larger than three.
[0151] In some example embodiments, the indication further indicates a number of the plurality of TRP combinations.
[0152] Details of some embodiments according to the present disclosure have been described with reference to FIGS. 1A-6. Now an example implementation of the device deployed with at least one positioning model will be discussed below.
[0153] In some example embodiments, a device comprises circuitry configured to: determine at least one timestamp for model inference; determine a plurality of TRP combinations, wherein each of the plurality of TRP combinations comprises at least three TRPs; for each of the plurality of TRP combinations, generate an output at the at least one timestamp by inputting model input data related to each TRP combination into the at least one positioning model; and determine, based on a plurality of outputs corresponding to the plurality of TRP combinations, one of the plurality of TRP combinations for further model inference.
[0154] In some example embodiments, the device comprises circuitry configured to: generate a report based on the plurality of outputs corresponding to the plurality of TRP combinations; transmit, to a further device, the report that is used by the further device to select the one of the plurality of TRP combinations; and receive, from the further device, indication information of the one of the plurality of TRP combinations for collecting further model input data.
[0155] In some example embodiments, the further device comprises at least one of: an access network device, an LMF, or a network entity.
[0156] In some example embodiments, the device comprises circuitry configured to: for each TRP combination of the plurality of TRP combinations, determine a comparison result based on the output of each TRP combination and a ground truth; and generate the report based on the plurality of comparison results for the plurality of TRP combinations respectively.
[0157] In some example embodiments, the report comprises the plurality of comparison results for the plurality of TRP combinations respectively.
[0158] In some example embodiments, an order of the plurality of comparison results is determined based on an order of the plurality of TRP combinations.
[0159] In some example embodiments, the report comprises one or more comparison results in the plurality of comparison results, wherein the one or more comparison results are the smallest results among the plurality of comparison results.
[0160] In some example embodiments, the report further comprises one or more identifiers for one or more TRP combinations corresponding to the one or more comparison results.
[0161] In some example embodiments, the report further comprises one or more model input data associated with one or more TRP combinations corresponding to the one or more comparison results.
[0162] In some example embodiments, a number of the one or more comparison results is predefined.
[0163] In some example embodiments, the report comprises: the plurality of outputs corresponding to the plurality of TRP combinations, or one or more outputs in the plurality of outputs, wherein the one or more outputs are in a center of an increasing or decreasing order of the plurality of outputs.
[0164] In some example embodiments, a number of the one or more outputs is predefined.
[0165] In some example embodiments, the at least one timestamp comprises a plurality of time points, and each of the plurality of time points is represented by a frame number and a slot number.
[0166] In some example embodiments, the device comprises circuitry configured to: receive, from a further device, information about the plurality of time points, wherein the further device comprises at least one of: an access network device, an LMF, a terminal device to be positioned, or an entity associated with an activation of the at least one positioning model.
[0167] In some example embodiments, the information comprises a start time point and a periodicity value.
[0168] In some example embodiments, the device comprises circuitry configured to: in accordance with a determination that a difference of a model input at a first time point and a further model input prior to the first time point exceeds a first threshold, determine that the at least one timestamp comprises the first time point; in accordance with a determination that a difference of a model output at a second time point and a further model output prior to the second time point exceeds a second threshold, determine that the at least one timestamp comprises the second time point; or in accordance with a determination that a difference of a location of the terminal device at a third time point and a further location of the terminal device prior to the third time point exceeds a third threshold, determine that the at least one timestamp comprises the third time point.
[0169] In some example embodiments, the device comprises circuitry configured to: receive, from a further device, information about the plurality of TRP combinations, wherein the further device comprises at least one of: an access network device, an LMF, a terminal device to be positioned, or a network entity.
[0170] In some example embodiments, the device comprises a terminal device, and the terminal device comprises circuitry configured to: receive, from an access network device or an LMF, an indication indicating an inference mode; and determine, based on the indication, the plurality of TRP combinations.
[0171] In some example embodiments, the inference mode is a first mode or a second mode, the first mode is associated with TRPs nearest to the terminal device, and the second mode is associated with TRPs nearest to a central point.
[0172] In some example embodiments, the indication further indicates a series of TRPs identification in each of the plurality of TRP combination which equals to or is larger than three.
[0173] In some example embodiments, the indication further indicates a number of the plurality of TRP combinations.
[0174] In some example embodiments, the device comprises one of: a terminal device, an access network device, or an LMF.
[0175] FIG. 7 illustrates a simplified block diagram of a device 700 that is suitable for implementing embodiments of the present disclosure. The device 700 can be considered as a further example implementation of a terminal device, a network device, or an LMF as described above. Accordingly, the device 700 can be implemented at or as at least a part of the terminal device 110 or the network device 120 or the LMF 130 as shown in FIG. 1A.
[0176] As shown, the device 700 includes a processor 710, a memory 720 coupled to the processor 710, a suitable transceiver 740 coupled to the processor 710, and a communication interface coupled to the transceiver 740. The memory 720 stores at least a part of a program 730. The transceiver 740 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 740 may include at least one of a transmitter and a receiver. The transmitter and the receiver may be functional modules or physical entities. The transceiver 740 has at least one antenna to facilitate communication, though in practice an Access Node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2 / Xn interface for bidirectional communications between eNBs / gNBs, S1 / NG interface for communication between a Mobility Management Entity (MME) / Access and Mobility Management Function (AMF) / serving gateway (SGW) / user plane function (UPF) and the eNB / gNB, Un interface for communication between the eNB / gNB and a relay node (RN) , or Uu interface for communication between the eNB / gNB and a terminal device.
[0177] The program 730 is assumed to include program instructions that, when executed by the associated processor 710, enable the device 700 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1A-6. The embodiments herein may be implemented by computer software executable by the processor 710 of the device 700, or by hardware, or by a combination of software and hardware. The processor 710 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 710 and memory 720 may form processing means 750 adapted to implement various embodiments of the present disclosure.
[0178] The memory 720 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 720 is shown in the device 700, there may be several physically distinct memory modules in the device 700. The processor 710 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 700 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.
[0179] In summary, embodiments of the present disclosure may provide the following solutions.
[0180] The present disclosure provides a device deployed with at least one positioning model, comprising at least one processor configured to cause the device at least to: determine at least one timestamp for model inference; determine a plurality of TRP combinations, wherein each of the plurality of TRP combinations comprises at least three TRPs; for each of the plurality of TRP combinations, generate an output at the at least one timestamp by inputting model input data related to each TRP combination into the at least one positioning model; and determine, based on a plurality of outputs corresponding to the plurality of TRP combinations, one of the plurality of TRP combinations for further model inference.
[0181] In one embodiment, the device as above, the device is caused to determine the one of the plurality of TRP combinations by: generating a report based on the plurality of outputs corresponding to the plurality of TRP combinations; transmitting, to a further device, the report that is used by the further device to select the one of the plurality of TRP combinations; and receiving, from the further device, indication information of the one of the plurality of TRP combinations for collecting further model input data.
[0182] In one embodiment, the device as above, the further device comprises at least one of: an access network device, an LMF, or a network entity.
[0183] In one embodiment, the device as above, the device is caused to generate the report by: for each TRP combination of the plurality of TRP combinations, determining a comparison result based on the output of each TRP combination and a ground truth; and generating the report based on the plurality of comparison results for the plurality of TRP combinations respectively.
[0184] In one embodiment, the device as above, the report comprises the plurality of comparison results for the plurality of TRP combinations respectively.
[0185] In one embodiment, the device as above, an order of the plurality of comparison results is determined based on an order of the plurality of TRP combinations.
[0186] In one embodiment, the device as above, the report comprises one or more comparison results in the plurality of comparison results, wherein the one or more comparison results are the smallest results among the plurality of comparison results.
[0187] In one embodiment, the device as above, the report further comprises one or more identifiers for one or more TRP combinations corresponding to the one or more comparison results.
[0188] In one embodiment, the device as above, the report further comprises one or more model input data associated with one or more TRP combinations corresponding to the one or more comparison results.
[0189] In one embodiment, the device as above, a number of the one or more comparison results is predefined.
[0190] In one embodiment, the device as above, the report comprises: the plurality of outputs corresponding to the plurality of TRP combinations, or one or more outputs in the plurality of outputs, wherein the one or more outputs are in a center of an increasing or decreasing order of the plurality of outputs.
[0191] In one embodiment, the device as above, a number of the one or more outputs is predefined.
[0192] In one embodiment, the device as above, the at least one timestamp comprises a plurality of time points, and each of the plurality of time points is represented by a frame number and a slot number.
[0193] In one embodiment, the device as above, the device is further caused to: receive, from a further device, information about the plurality of time points, wherein the further device comprises at least one of: an access network device, an LMF, a terminal device to be positioned, or an entity associated with an activation of the at least one positioning model.
[0194] In one embodiment, the device as above, the information comprises a start time point and a periodicity value.
[0195] In one embodiment, the device as above, the device is caused to determine the at least one timestamp by at least one of: in accordance with a determination that a difference of a model input at a first time point and a further model input prior to the first time point exceeds a first threshold, determining that the at least one timestamp comprises the first time point; in accordance with a determination that a difference of a model output at a second time point and a further model output prior to the second time point exceeds a second threshold, determining that the at least one timestamp comprises the second time point; or in accordance with a determination that a difference of a location of the terminal device at a third time point and a further location of the terminal device prior to the third time point exceeds a third threshold, determining that the at least one timestamp comprises the third time point.
[0196] In one embodiment, the device as above, the device is further caused to: receive, from a further device, information about the plurality of TRP combinations, wherein the further device comprises at least one of: an access network device, an LMF, a terminal device to be positioned, or a network entity.
[0197] In one embodiment, the device as above, the device comprises a terminal device, and the terminal device is caused to determine the plurality of TRP combinations by: receiving, from an access network device or an LMF, an indication indicating an inference mode; and determining, based on the indication, the plurality of TRP combinations.
[0198] In one embodiment, the device as above, the inference mode is a first mode or a second mode, the first mode is associated with TRPs nearest to the terminal device, and the second mode is associated with TRPs nearest to a central point.
[0199] In one embodiment, the device as above, the indication further indicates a series of TRPs identification in each of the plurality of TRP combination which equals to or is larger than three.
[0200] In one embodiment, the device as above, the indication further indicates a number of the plurality of TRP combinations.
[0201] In one embodiment, the device as above, the device comprises one of: a terminal device, an access network device, or an LMF.
[0202] The present disclosure provides a method of communication, comprising the operations implemented at the device deployed with at least one positioning model discussed above.
[0203] The present disclosure provides a device deployed with at least one positioning model, comprising: a processor; and a memory storing computer program codes; the memory and the computer program codes configured to, with the processor, cause the device to perform the method implemented at the device discussed above.
[0204] The present disclosure provides a non-transient computer readable medium having instructions stored thereon, the instructions, when executed by a processor of an apparatus, causing the apparatus to perform the method implemented at a device deployed with at least one positioning model discussed above.
[0205] The present disclosure provides a computer program product having instructions stored thereon, the instructions, when executed by a processor of an apparatus, causing the apparatus to perform the method implemented at a device deployed with at least one positioning model discussed above.
[0206] 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.
[0207] 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. 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.
[0208] 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.
[0209] 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.
[0210] 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.
[0211] 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
1.A device deployed with at least one positioning model, the device comprising at least one processor configured to cause the device to:determine at least one timestamp for model inference;determine a plurality of transmission reception point (TRP) combinations, wherein each of the plurality of TRP combinations comprises at least three TRPs;for each of the plurality of TRP combinations, generate an output at the at least one timestamp by inputting model input data related to each TRP combination into the at least one positioning model; anddetermine, based on a plurality of outputs corresponding to the plurality of TRP combinations, one of the plurality of TRP combinations for further model inference.2.The device of claim 1, wherein the device is caused to determine the one of the plurality of TRP combinations by:generating a report based on the plurality of outputs corresponding to the plurality of TRP combinations;transmitting, to a further device, the report that is used by the further device to select the one of the plurality of TRP combinations; andreceiving, from the further device, indication information of the one of the plurality of TRP combinations for collecting further model input data.3.The device of claim 2, wherein the further device comprises at least one of:an access network device,a location management function (LMF) , ora network entity.4.The device of claim 2, wherein the device is caused to generate the report by:for each TRP combination of the plurality of TRP combinations, determining a comparison result based on the output of each TRP combination and a ground truth; andgenerating the report based on the plurality of comparison results for the plurality of TRP combinations respectively.5.The device of claim 4, wherein the report comprises the plurality of comparison results for the plurality of TRP combinations respectively.6.The device of claim 5, wherein an order of the plurality of comparison results is determined based on an order of the plurality of TRP combinations.7.The device of claim 4, wherein the report comprises one or more comparison results in the plurality of comparison results, wherein the one or more comparison results are the smallest results among the plurality of comparison results.8.The device of claim 7, wherein the report further comprises one or more identifiers for one or more TRP combinations corresponding to the one or more comparison results.9.The device of claim 7, wherein the report further comprises one or more model input data associated with one or more TRP combinations corresponding to the one or more comparison results.10.The device of claim 2, wherein the report comprises:the plurality of outputs corresponding to the plurality of TRP combinations, orone or more outputs in the plurality of outputs, wherein the one or more outputs are in a center of an increasing or decreasing order of the plurality of outputs.11.The device of claim 1, wherein the at least one timestamp comprises a plurality of time points, and each of the plurality of time points is represented by a frame number and a slot number.12.The device of claim 11, wherein the device is further caused to:receive, from a further device, information about the plurality of time points, wherein the further device comprises at least one of:an access network device,an LMF,a terminal device to be positioned, oran entity associated with an activation of the at least one positioning model.13.The device of claim 1, wherein the device is caused to determine the at least one timestamp by at least one of:in accordance with a determination that a difference of a model input at a first time point and a further model input prior to the first time point exceeds a first threshold, determining that the at least one timestamp comprises the first time point;in accordance with a determination that a difference of a model output at a second time point and a further model output prior to the second time point exceeds a second threshold, determining that the at least one timestamp comprises the second time point; orin accordance with a determination that a difference of a location of the terminal device at a third time point and a further location of the terminal device prior to the third time point exceeds a third threshold, determining that the at least one timestamp comprises the third time point.14.The device of claim 1, wherein the device is further caused to:receive, from a further device, information about the plurality of TRP combinations, wherein the further device comprises at least one of:an access network device,an LMF,a terminal device to be positioned, ora network entity.15.The device of claim 1, wherein the device comprises a terminal device, and the terminal device is caused to determine the plurality of TRP combinations by:receiving, from an access network device or an LMF, an indication indicating an inference mode; anddetermining, based on the indication, the plurality of TRP combinations.16.The device of claim 15, wherein the inference mode is a first mode or a second mode, the first mode is associated with TRPs nearest to the terminal device, and the second mode is associated with TRPs nearest to a central point.17.The device of claim 15, wherein the indication further indicates a series of TRPs identification in each of the plurality of TRP combination which equals to or is larger than three.18.The device of claim 1, wherein the device comprises one of: a terminal device, an access network device, or an LMF.19.A method of communication, comprising:determining, at a device deployed with at least one positioning model, at least one timestamp for model inference;determining a plurality of transmission reception point (TRP) combinations, wherein each of the plurality of TRP combinations comprises at least three TRPs;for each of the plurality of TRP combinations, generating an output at the at least one timestamp by inputting model input data related to each TRP combination into the at least one positioning model; anddetermining, based on a plurality of outputs corresponding to the plurality of TRP combinations, one of the plurality of TRP combinations for further model inference.20.A computer readable medium having instructions stored thereon, the instructions, when executed by a processor of an apparatus, causing the apparatus to perform the method according to claim 19.
Citation Information
Patent Citations
Method and apparatus for efficient positioning
CN114944855A
Node selection for radio frequency fingerprint (RFFP) federated learning
US20240037441A1
Machine learning model positioning performance monitoring and reporting
WO2023211604A1
Machine learning assisted position determination
WO2023212224A2