Devices and methods for communication
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-01-24
- Publication Date
- 2026-08-13
Smart Images

Figure CN2024073912_13082026_PF_FP_ABST
Abstract
Description
DEVICES AND METHODS FOR COMMUNICATION
[0001] FIELDS
[0002] Example embodiments of the present disclosure generally relate to the field of communication techniques and in particular, to devices and methods for artificial intelligence / machine learning (AI / ML) data transmission.BACKGROUND
[0003] In the telecommunication industry, artificial intelligence / machine learning (AI / ML) models have been employed in telecommunication systems to improve the performance of telecommunications systems. For example, supporting various positioning mechanisms to provide reliable and accurate UE location has always been one of the key features of in the telecommunications systems. It has been agreed to investigate the potential for AI / ML in air interface to improve comprehensive performance in 5G-adcanced. AI / ML based positioning mechanism to improve the positioning accuracy is one of the use cases to apply AI / ML in air interface. Works are on-going regarding data collection for model training, updating / fine-tuning, monitoring of the AI / ML models.SUMMARY
[0004] In general, embodiments of the present disclosure provide a solution for artificial intelligence / machine learning (AI / ML) data transmission.
[0005] In a first aspect, there is provided a first communication device. The first communication device comprises: a processor configured to cause the first communication device to: determine model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and transmit the model data to at least one second communication device for use in an artificial intelligence / machine learning (AI / ML) model, the AI / ML model being configured for positioning of a second terminal device.
[0006] In a second aspect, there is provided a second communication device. The second communication device comprises: a processor configured to cause the second communication device to: receive, from the first communication device, model data for use in an artificial intelligence / machine learning (AI / ML) model. The model data at least comprises positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and wherein the AI / ML model is configured for positioning of a second terminal device.
[0007] In a third aspect, there is provided a communication method performed by a first communication device. The method comprises: determining model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and transmitting the model data to at least one second communication device for use in an artificial intelligence / machine learning (AI / ML) model, the AI / ML model being configured for positioning of a second terminal device.
[0008] In a fourth aspect, there is provided a communication method performed by a second communication device. The method comprises: receiving, from a first communication device, model data for use in an artificial intelligence / machine learning (AI / ML) model. The model data at least comprises positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and wherein the AI / ML model is configured for positioning of a second terminal device.
[0009] In a fifth aspect, there is provided a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to carry out the method according to the third, or fourth aspect.
[0010] Other features of the present disclosure will become easily comprehensible through the following description.BRIEF DESCRIPTION OF THE DRAWINGS
[0011] 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:
[0012] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;
[0013] FIG. 2 illustrates an example architecture for an artificial intelligence / machine learning (AI / ML) model;
[0014] FIG. 3 illustrates a signaling flow of model data transmission for an AI / ML model in accordance with some embodiments of the present disclosure;
[0015] FIG. 4 illustrates an example of zone division and location coordination classification based on zones accordance with some embodiments of the present disclosure;
[0016] FIGS. 5-10 illustrates signaling flows of model data transmission in example use cases of A / ML positioning in accordance with some embodiments of the present disclosure;
[0017] FIG. 11 illustrates a flowchart of a method implemented at a first communication device according to some example embodiments of the present disclosure;
[0018] FIG. 12 illustrates a flowchart of a method implemented at a second communication device according to some example embodiments of the present disclosure; and
[0019] FIG. 13 illustrates a simplified block diagram of an apparatus that is suitable for implementing example 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] As used herein, the term ‘terminal device’ refers to any device having wireless or wired communication capabilities. Examples of the terminal device include, but not limited to, user equipment (UE) , personal computers, desktops, mobile phones, cellular phones, smart phones, personal digital assistants (PDAs) , portable computers, tablets, wearable devices, internet of things (IoT) devices, Ultra-reliable and Low Latency Communications (URLLC) devices, Internet of Everything (IoE) devices, machine type communication (MTC) devices, devices on vehicle for V2X communication where X means pedestrian, vehicle, or infrastructure / network, devices for Integrated Access and Backhaul (IAB) , Space borne vehicles or Air borne vehicles in Non-terrestrial networks (NTN) including Satellites and High Altitude Platforms (HAPs) encompassing Unmanned Aircraft Systems (UAS) , eXtended Reality (XR) devices including different types of realities such as Augmented Reality (AR) , Mixed Reality (MR) and Virtual Reality (VR) , the unmanned aerial vehicle (UAV) commonly known as a drone which is an aircraft without any human pilot, devices on high speed train (HST) , or image capture devices such as digital cameras, sensors, gaming devices, music storage and playback appliances, or Internet appliances enabling wireless or wired Internet access and browsing and the like. The ‘terminal device’ can further has ‘multicast / broadcast’ feature, to support public safety and mission critical, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communications and IoT applications. It may also incorporate one or multiple Subscriber Identity Module (SIM) as known as Multi-SIM. The term “terminal device” can be used interchangeably with a UE, a mobile station, a subscriber station, a mobile terminal, a user terminal or a wireless device.
[0024] The term “network device” refers to a device which is capable of providing or hosting a cell or coverage where terminal devices can communicate. Examples of a network device include, but not limited to, a Node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNB) , a transmission reception point (TRP) , a remote radio unit (RRU) , a radio head (RH) , a remote radio head (RRH) , an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS) , and the like.
[0025] 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.
[0026] The terminal or the network device may work on several frequency ranges, e.g., FR1 (e.g., 450 MHz to 6000 MHz) , FR2 (e.g., 24.25GHz to 52.6GHz) , frequency band larger than 100 GHz as well as Tera Hertz (THz) . It can further work on licensed / unlicensed / shared spectrum. The terminal device may have more than one connection with the network devices under Multi-Radio Dual Connectivity (MR-DC) application scenario. The terminal device or the network device can work on full duplex, flexible duplex and cross division duplex modes.
[0027] The embodiments of the present disclosure may be performed in test equipment, e.g., signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator. In some embodiments, the terminal device may be connected with a first network device and a second network device. One of the first network device and the second network device may be a master node and the other one may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs) . In some embodiments, the first network device may be a first RAT device and the second network device may be a second RAT device. In some embodiments, the first RAT device is eNB and the second RAT device is gNB. Information related with different RATs may be transmitted to the terminal device from at least one of the first network device or the second network device. In some embodiments, first information may be transmitted to the terminal device from the first network device and second information may be transmitted to the terminal device from the second network device directly or via the first network device. In some embodiments, information related with configuration for the terminal device configured by the second network device may be transmitted from the second network device via the first network device. Information related with reconfiguration for the terminal device configured by the second network device may be transmitted to the terminal device from the second network device directly or via the first network device.
[0028] As used herein, the singular forms ‘a’ , ‘an’ and ‘the’ are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term ‘includes’ and its variants are to be read as open terms that mean ‘includes, but is not limited to. ’ The term ‘based on’ is to be read as ‘at least in part based on. ’ The term ‘one embodiment’ and ‘an embodiment’ are to be read as ‘at least one embodiment. ’ The term ‘another embodiment’ is to be read as ‘at least one other embodiment. ’ The terms ‘first, ’ ‘second, ’ and the like may refer to different or same objects. Other definitions, explicit and implicit, may be included below.
[0029] 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.
[0030] As used herein, the term “resource, ” “transmission resource, ” “uplink resource, ” or “downlink resource” may refer to any resource for performing a communication, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.
[0031] As used herein, the term “model” is referred to as an association between an input and an output learned from training data, and thus a corresponding output may be generated for a given input after the training. The generation of the model may be based on a machine learning technique. The machine learning techniques may also be referred to as artificial intelligence (AI) techniques. In general, a machine learning model can be built, which receives input information and makes predictions based on the input information. For example, a classification model may predict a class of the input information among a predetermined set of classes. As used herein, “model” may also be referred to as “machine learning model” , “learning model” , “machine learning network” , or “learning network, ” which are used interchangeably herein.
[0032] Generally, machine learning may usually involve three stages, i.e., a training stage, a validation stage, and an application stage (also referred to as an inference stage) . At the training stage, a given machine learning model may be trained (or optimized) iteratively using a great amount of training data until the model can obtain, from the training data, consistent inference similar to those that human intelligence can make. During the training, a set of parameter values of the model is iteratively updated until a training objective is reached. Through the training process, the machine learning model may be regarded as being capable of learning the association between the input and the output (also referred to an input-output mapping) from the training data. At the validation stage, a validation input is applied to the trained machine learning model to test whether the model can provide a correct output, so as to determine the performance of the model. Generally, the validation stage may be considered as a step in a training process, or sometimes may be omitted. At the application stage, the resulting machine learning model may be used to process a real-world model input based on the set of parameter values obtained from the training process and to determine the corresponding model output.
[0033] Principles and implementations of the present disclosure will be described in detail below with reference to the figures.
[0034] FIG. 1 illustrates a schematic diagram of an example communication environment 100 in which example embodiments of the present disclosure can be implemented. In the communication environment 100, a plurality of communication devices, including a terminal device 110-1, a terminal device 110-2, ..., a terminal device 110-N and a network device 120, can communicate with each other. The terminal device 110-1, terminal device 110-2, ..., and terminal device 110-N can be collectively referred to as “terminal device (s) 110. ” The number N can be any suitable integer number.
[0035] In the example of FIG. 1, the terminal device 110 may be a UE and the network device 120 may be a base station serving the UE. The serving area of the network device 120 may be called a cell (not shown) . In the communication environment 100, the network device 120 and the terminal devices 110 may communicate data and control information to each other. The terminal devices 110 may also communicate with each other.
[0036] The communication environment 100 further comprises a location management function (LMF) 130 which may be included in a core network (CN) . In some example embodiments, In some embodiments, one or more AI / ML models 140 may be trained and provided for use by one or more terminal devices 110. An AI / ML model 140 may be trained to implement a certain communication related function at a terminal device 110 or at a network device 120.
[0037] As used herein, the term “AI / ML” model may be interchangeably with the term “model” . The term “AI / ML model training” may refer to a process to train an AI / ML model for example by learning the input / output relationship and obtained a trained AI / ML model for inference. The term “model monitoring” used herein may refer to a procedure that monitors the inference performance of the AI / ML model.
[0038] In some embodiments, the AI / ML models 140 may comprise AI / ML models for positioning of a second terminal device 110. In some embodiments, an AI / ML model 140 may be a direct AI / ML positioning model. An input to the direct AI / ML positioning model may comprise information related to a channel between a terminal device 110 and a network device, such as Channel Impulse Response (CIR) . The input may be collected by transmitting a reference signal, such as a positioning reference signal (PRS) , a sounding reference signal (SRS) , or a channel state information reference signal (CSI-RS) over the channel between the terminal device 110 and the network device. An output of the direct AI / ML positioning model may comprise a location of the terminal device 110.
[0039] In some embodiments, an AI / ML model 140 may be an AI / ML assisted positioning model. An input to the AI / ML assisted positioning model may comprise may be the same or similar to that of the direct AI / ML positioning model. An output of the AI / ML assisted positioning model may comprise intermediate results of location information for a terminal device 110. The intermediate results of the location information may include, but are not limited to, time of arrival (TOA) , time difference of arrival (TDOA) , non-line of slight (NLOS) / line of sight (LOS) identification of a channel, or the like. Such intermediate results may be used to assist in determining a location of the terminal device 110.
[0040] In the embodiments illustrated in FIG. 1, the AI / ML model 140 deployed at different devices may be the same or different, and may be of the same type or different types of direct AI / ML positioning model and AI / ML assisted positioning model.
[0041] In some embodiments, an AI / ML model 140 may be trained at the network device 120 and then transferred to one or more suitable terminal devices 110 for use. In some embodiments, an AI / ML model 140 may be trained at a terminal device 110 and then applied locally or transferred to one or more other terminal devices 110 by a network device for use. It would be appreciated that the AI / ML model 140 may be trained and / or transferred by any other entity in the communication environment 100.
[0042] It is to be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number of devices configured to implementing example embodiments of the present disclosure. Although not shown, it would be appreciated that one or more additional devices may be located in the cell, and one or more additional cells may be deployed in the communication environment 100. It is noted that although illustrated as a network device, the network device 120 may be another device than a network device. Although illustrated as a terminal device, the terminal device 110 may be other device than a terminal device.
[0043] In the following, for the purpose of illustration, some example embodiments are described with the terminal device 110 operating as a UE and the network device 120 operating as a base station. However, in some example embodiments, operations described in connection with a terminal device may be implemented at a network device or other device, and operations described in connection with a network device may be implemented at a terminal device or other device.
[0044] In some example embodiments, if the terminal device 110 is a terminal device and the network device 120 is a network device, a link from the network device 120 to the terminal device 110 is referred to as a downlink (DL) , while a link from the terminal device 110 to the network device 120 is referred to as an uplink (UL) . In DL, the network device 120 is a transmitting (TX) device (or a transmitter) and the terminal device 110 is a receiving (RX) device (or a receiver) . In UL, the terminal device 110 is a TX device (or a transmitter) and the network device 120 is a RX device (or a receiver) .
[0045] The communications in the communication environment 100 may conform to any suitable standards including, but not limited to, Global System for Mobile Communications (GSM) , Long Term Evolution (LTE) , LTE-Evolution, LTE-Advanced (LTE-A) , New Radio (NR) , Wideband Code Division Multiple Access (WCDMA) , Code Division Multiple Access (CDMA) , GSM EDGE Radio Access Network (GERAN) , Machine Type Communication (MTC) and the like. The embodiments of the present disclosure may be performed according to any generation communication protocols either currently known or to be developed in the future. Examples of the communication protocols include, but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or the sixth generation (6G) networks.
[0046] FIG. 2 illustrates an example architecture for an AI / ML model, e.g., an AI / ML model 140 in FIG. 1. At data collection 210, one or more communication devices may collect training data, monitoring data, and inference data for the AI / ML model.
[0047] The training data and the monitoring data may generally include inputs of the AI / ML model 140 and ground-truth labels for the corresponding inputs. The inference data generally include inputs of the AI / ML model 140 for inference.
[0048] As used herein, the term “data collection” may refer to 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. The data collection can further be referred to a function that provides input data to the Model Training, Management, and Inference functions. For example, the data collection comprises training data, monitoring data, and inference data. The training data refers to the data input for the AI / ML Model Training function. The monitoring data refers to the data input for the Management of AI / ML models or AI / ML functionalities. The inference data refers to the data input for the AI / ML Inference function.
[0049] At model training 220, an AI / ML model may be trained or updated using the collected training data, to provide a trained or updated AI / ML model. At model management 230, performance of an AI / ML mode may be evaluated using the collected monitoring data. The model management 230 may provide performance feedback or retraining request to the model training 220 for fine-tune or update the AI / ML model. The model management 230 may further provide a management instruction for model inference 240, e.g., for deploy or activate the AI / ML model with satisfied performance. At model inference 240, the AI / ML model is applied to output direct positioning of a terminal device or assisted positioning data of a terminal device based on inference data collected. Inference output of the AI / ML model may be provided for the model management, e.g., to evaluate whether the AI / ML model still runs with satisfied performance. In some cases, the AI / ML model with satisfied performance may be stored in model storage 250 in response to a model transfer or delivery request. The AI / ML model may then be transferred or delivered for use in model inference.
[0050] In some embodiments, AI / ML positioning comprises two representative sub-use cases, direct AI / ML positioning and AI / ML assisted positioning. For direct AI / ML positioning, the AI / ML model outputs UE location, for example, fingerprinting based on channel observation as the input of the AI / ML model. For the AI / ML assisted positioning, the AI / ML model outputs new measurement and / or enhancement of existing measurement, for example, LOS / NLOS identification, timing and / or angle of measurement, and likelihood of measurement.
[0051] In order to enhance positioning accuracy, AI / ML for NR Air Interface comprises direct AI / ML positioning and AI / ML assisted positioning. Furthermore, the direct AI / ML positioning may include multiple cases. For example, Case 1 defines UE-based positioning with a UE-side model for direct AI / ML positioning; Case 2 defines UE-assisted / LMF-based positioning with a LMF-side model for direct AI / ML positioning; and Case 3 defines NG-RAN node assisted positioning with a LMF-side model for direct AI / ML positioning. The AI / ML assisted positioning may also include multiple cases. For example, Case 2a defines UE-assisted / LMF-based positioning with a UE-side model for AI / ML assisted positioning; and Case 3a defines NG-RAN node assisted positioning with a gNB-side model for AI / ML assisted positioning.
[0052] In the following description, for the purpose of positioning accuracy enhancement, unless defined otherwise, necessary measurements, signalling / mechanism (s) may be specified to facilitate lifecycle management (LCM) operations specific to the positioning accuracy enhancements use cases. Further, the necessary signalling of necessary measurement enhancements may be investigated and specified. Methods may be enabled to ensure consistency between training and inference regarding network-side additional conditions (if identified) for inference at UE for relevant positioning sub-use cases.
[0053] Regarding training data generation for AI / ML based positioning, the following options of entity and mechanisms to generate ground-truth label are identified:
[0054] -UE with estimated / known location generates ground-truth label and corresponding label quality indicator, which may be based on non-NR and / or NR RAT-dependent and / or NR RAT-independent positioning methods, and can be applied at least for UE-based positioning with UE-side model (Case 1) and UE-assisted positioning with UE-side model (Case 2a) ;
[0055] -Network entity generates ground-truth label and corresponding label quality indicator, which may be based on non-NR and / or NR RAT-dependent and / or NR RAT-independent positioning methods; and can be applied at least for UE-assisted / LMF-based positioning with LMF-side model (Case 2b) , NG-RAN node assisted positioning with gNB-side model (Case 3a) and NG-RAN node assisted positioning with LMF-side model (Case 3b) ;
[0056] Considering the cases where network entity generates ground-truth label and corresponding label quality indicator, at least a positioning reference unit (PRU) is identified to generate ground-truth label for UE-based positioning with UE-side model (Case 1) and UE-assisted positioning with UE-side model (Case 2a) ; at least LMF with known PRU location is identified to generate ground-truth label for UE-assisted / LMF-based positioning with LMF-side model (Case 2b) and NG-RAN node assisted positioning with LMF-side model (Case 3b) ; and at least network entity with known PRU location is identified to generate ground-truth label for NG-RAN node assisted positioning with gNB-side model (Case 3a) .
[0057] Regarding data collection for AI / ML based positioning, at least the following information of data with potential specification impact are identified.
[0058] - Ground-truth label, which may be reported from the label data generation entity
[0059] - Measurement (corresponding to model input) , which may be reported from the measurement data generation entity
[0060] - Quality indicator, which may be used for and / or associated with ground-truth label and / or measurement, and may be reported from the label and / or the measurement data generation entity and / or as request from a different (e.g., data collection, etc. ) entity.
[0061] It is also possible for transfer of training data from the entity generating training data to a different entity.
[0062] Scenario / configuration specific (including site-specific configuration / channel conditions) models may provide performance benefits in some studied use cases (i.e., when a single model cannot generalize well to multiple scenarios / configurations / sites) . It has been studied that at least, when UE has limitation to store all related models, model delivery / transfer, if feasible, to UE may be beneficial, at the cost of overhead / latency associated with model delivery / transfer. It is noted that on-device finetuning / retraining, if feasible, of a single model may be an alternative to model delivery / transfer.
[0063] A Positioning Reference Unit (PRU) at a known location can perform positioning measurements, e.g., Reference Signal Time Difference (RSTD) , Reference Signal Received Power (RSRP) , UE Rx-Tx Time Difference measurements, etc., and report these measurements to a location server. In addition, the PRU can transmit SRS to enable TRPs to measure and report UL positioning measurements (e.g., Relative Time of Arrival (RTOA) , uplink Angle-of-Arrival (UL-AoA) , gNB Rx-Tx Time Difference, etc. ) from PRU at a known location. The PRU measurements can be compared by a location server with the measurements expected at the known PRU location to determine correction terms for other nearby target devices. The DL-and / or UL location measurements for other target devices can then be corrected based on the previously determined correction terms. From a location server perspective, the PRU functionality is realized by a UE with known location.
[0064] For an AI / ML model for positioning, the procedure of collected data transmission has important impacts. It is desired to define procedure and data format for the data transmission between different entities, to reduce data transmission overhead, and to address other potential issues, such as to update data for finetuning or retraining, to match model input data and associated data, to design measurement format for certain measurement information, to reduce data transmission delay, and the like.
[0065] Embodiments of the present disclosure will be described in detail below. FIG. 3 illustrates a signaling flow 300 for AI / ML data transmission according to some example embodiments of the present disclosure. As shown in FIG. 3, the signaling flow 300 involves a first communication device 301 and one or more second communication devices 302. It is to be understood that the signaling flow 300 may involve more devices or less devices, and the number of devices illustrated in FIG. 3 is only for the purpose of illustration without suggesting any limitations.
[0066] Depending on different use cases in data transfer for the AI / ML model, the first communication device 301 may be different devices which are responsible for transmitting model data, and the at least one second communication device 302 may be different devices which are responsible for receiving model data.
[0067] In some embodiments, the first communication device 301 may comprise a positioning reference unit (PRU) , and the at least one second commination device may comprise a network device. In some embodiments, the first communication device 301 may comprise a network device, and the at least one second communication device 302 may comprise at least one first terminal device with the AI / ML model deployed therein. In some embodiments, the first communication device 301 may comprise a location management function (LMF) , and the at least one second communication device 302 may comprise at least one first terminal device with the AI / ML model deployed therein. In some embodiments, the first communication device 301 may comprise a network device, and the at least one second communication device 302 may comprise a LMF with the AI / ML model deployed therein.
[0068] In operation, the first communication device 301 determines (305) model data which at least includes positioning data of at least one first terminal device. Further, the first communication device 301 transmits (310) the model data to the at least one second communication device 302 for use in an AI / ML model. The AI / ML model may be configured for positioning of a second terminal device. In some examples, the AI / ML mode may be configured for direct AI / ML positioning. In some other examples, the AI / ML mode may be configured for AI / ML assisted positioning. The second terminal device to be positioned with the AI / ML model may be the same or different from the at least one first terminal device from which the model data are collected.
[0069] The at least one second communication device 302 receives (315) the model data from the first communication device 301 and may apply the model data for use in the AI / ML model.
[0070] In example embodiments of the present disclosure, the positioning data for an AI / ML model may include: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone.
[0071] In some example embodiments, coordinate information of the first terminal device may be classified based on zones. In some embodiments, a zone may be a 2-dimensional (2D) region of a predetermined size.
[0072] In some example embodiments, a geographical zone amongst the plurality of predetermined geographical zones at least may have a predetermined width and a predetermined height. By way of example, each zone may have a predetermined width and a predetermined height.
[0073] Alternatively, the zone may also be a three-dimensional (3D) region, further including an altitude coordinate additionally. In some example embodiments, a geographical zone amongst the plurality of predetermined geographical zones may be a 3D region, and the location coordinate information of the first terminal device may comprise width, height, and altitude coordinates. The positioning data of the first terminal device may be in the format of zone ID and associated with the location coordinate information of the first terminal device within the zone.
[0074] In some example embodiments, a geographical zone amongst the plurality of predetermined geographical zones may be in the form of a 2D ellipse or the form of a 3D ellipse. By way of example, the zone may be in the form of a 2D / 3D uncertainty ellipse as specified in the communication specifications, e.g., 3GPP TS 23.032, and the location of the terminal device may be defined within the ellipse.
[0075] By way of example, FIG. 4 illustrates an example 400 of zone division and location coordination classification for AI / ML data transmission based on zones accordance with some embodiments of the present disclosure. As shown in FIG. 4, there are 8 zones in a global coordinate system XY. The terminal devices (for example, PRU or UE located in locations a, b, c) may have coordinate values defined within a zone coordinate system X1Y1. For example, for a terminal device in Zone 4, its positioning data may include a zone ID of 4 and two coordinate values within a zone coordinate system X1Y1.
[0076] As the number of zones may be limited, and the coordinate values within a zone coordinate system may be smaller than the global coordinate system, the data overhead for positioning data of a terminal device may thus be reduced.
[0077] In some example embodiments, when a plurality of first terminal devices is located within a first geographical zone amongst the plurality of predetermined geographical zones, the positioning data may comprise a first identity of the first geographical zone, and respective location coordinate information for the plurality of first terminal devices within the first geographical zone. FIG. 5 illustrates a signaling flow 500 for AI / ML data transmission according to some example embodiments of the present disclosure. The example of FIG. 5 shows a use case of UE-based positioning with a UE-side model for direct AI / ML positioning.
[0078] As shown in FIG. 5, in some example embodiments, in the case of UE-based positioning with the UE-side model, direct AI / ML positioning may include the following steps. As shown in FIG. 5, the signaling flow 500 involves a network device 501, a PRU 502, and a terminal device 503. An AI / ML model is used by the terminal device 503 for positioning. Although one PRU and one terminal device are shown, the signaling flow 500 may involve multiple PRUs and / or multiple terminal devices.
[0079] In step 510, a network device 501 transmits a reference signal to a PRU 502. The reference signal may be, for example, PRS, CSI-RS, and other proper reference signals.
[0080] In step 515, the PRU 502 performs a PRS measurement to obtain channel status. The PRS measurement may be, for example, a channel impulse response (CIR) , a power delay profile (PDP) or a delay profile (DP) . DP is considered as a degenerated version of PDP, where the path power is not provided.
[0081] In step 520, the PRU 502 transmits measurement results (and optionally, the PRU location) to the network device 501. The data format of the PRU location may be the same design as Step 525 in the following. In some cases, the PRU location may be known to the network device 501, thus transmission is not required. The PRU location is positioning data of the PRU 502, which is considered as a terminal device with known location.
[0082] In step 525, the network device 501 transmits model data which includes measurement results and the PRU location to the terminal device 503 for use in the AI / ML model. In some cases, the network device 501 may receive the measurement results and the PRU locations of multiple PRUs and decide to transmit those to the terminal device 503. It should be understood that the PRU locations may be classified into multiple sets where each set corresponds to one zone. By way of example, there may be multiple coordinates of the terminal device within one zone ID. The format structure of the PRU locations may be zone-based as follows:
[0083] – Zone ID, e.g., 1
[0084] ● coordinate 1, coordinate 2…,
[0085] – ……
[0086] – Zone ID, e.g., 4
[0087] ● coordinate a, coordinate b, coordinate c
[0088] – ……
[0089] Alternatively, in Step 520 and Step 525, the PRU location corresponding to the measurement results of the PRU 502 may be transmitted from LMF to the terminal device 503.
[0090] In step 530, the terminal device 503 conducts model training based on the received measurement results and the PRU location. In steps 535 and 540, the terminal device 503 measures a PRS transmitted from the network device 501 and then conducts model inference by inputting a PRS reference signal measurement results to the trained AI / ML model.
[0091] In some example embodiments, the model data may further comprise measurement data. The measurement data may comprise a measurement result of a reference signal that is obtained by each of the at least one first terminal device. Herein, within the model data, location coordinate information of each terminal device may be paired with a measurement result of the terminal device. Alternatively, within the model data, an order of a respective measurement result of the at least one first terminal device may be the same as an order of respective location coordinate information of the at least one first terminal device. Alternatively, for each first terminal device, location coordinate information and the measurement result of the terminal device may be embedded with the same time stamp.
[0092] As described above, in the use cases of FIG. 5, the network device transmits the measurement results and the PRU location to the terminal device with the AI / ML mode deployed. Regarding the association between the measurement results and the positioning data of at least one first terminal device, three alternative format structures of the location of the terminal device are provided.
[0093] [Corrected under Rule 26, 11.06.2026]In a first alternative format structure, location coordinate information of each first terminal device may be paired with a measurement result of the first terminal device. For example, a measurement result is embedded with the location coordinate information of each first terminal device to pair each measurement result and location of each first terminal device. For example, the measurement result may be in a format structure as the following:
[0094] [Corrected under Rule 26, 11.06.2026]
[0095] [Corrected under Rule 26, 11.06.2026]
[0096] [Corrected under Rule 26, 11.06.2026]
[0097] [Corrected under Rule 26, 11.06.2026]
[0098] [Corrected under Rule 26, 11.06.2026]
[0099] [Corrected under Rule 26, 11.06.2026]
[0100] In a second alternative format structure, within the model data, an order of a respective measurement result of the at least one first terminal device may be the same as an order of respective location coordinate information of the at least one first terminal device. For example, the measurement result and the location coordinate information of the first terminal device are implicitly paired based on the same order with respect to the location of the first terminal device. For example, the measurement result may be in a format structure as the following:
[0101] – PRU Locations:
[0102] ● Zone 1
[0103] ● coordinate 1, coordinate 2…,
[0104] ● ......
[0105] ● Zone 4
[0106] ● coordinate a, coordinate b, coordinate c
[0107] ● ......
[0108] – Measurement results:
[0109] ● Measurement 1, Measurement 2…,
[0110] ● ......
[0111] ● Measurement a, Measurement b, Measurement c
[0112] ● ......
[0113] In a third alternative format structure, a time stamp is embedded with each measurement result and location of each first terminal device.
[0114] In some example embodiments, the first communication device 301 may receive, from the second communication device 302 or a third communication device which is not the direct receiver of the model data, a data update request. The data update request may comprise a second identity of a second geographical zone amongst the plurality of predetermined geographical zones. In some embodiments, the second geographical zone may be a zone where the AI / ML model has a bad positioning performance. The first communication device 301 may determine, based on the data update request, updated model data. The updated model data at least may include further positioning data of at least one further terminal device located within the second geographical zone. The first communication device 301 may transmit the updated model data to the second communication device or the third communication device. The updated model data may be used to perform zone-level model data.
[0115] FIG. 6 illustrates a signaling flow 600 for AI / ML data transmission according to some example embodiments of the present disclosure. The example of FIG. 6 shows a use case of UE-based positioning with a UE-side model for direct AI / ML positioning.
[0116] As shown in FIG. 6, in some example embodiments, in the case of UE-based positioning with the UE-side model, direct AI / ML positioning may include the following steps. As shown in FIG. 6, the signaling flow 600 also involves the network device 501, the PRU 502, and the terminal device 503 of FIG. 5. An AI / ML model is used by the terminal device 503 for positioning. Although one PRU and one terminal device are shown, the signaling flow 500 may involve multiple PRUs and / or multiple terminal devices. The steps 610 to 640 in the signaling flow 500 are the same as those in the signaling flow 500 of FIG. 5.
[0117] As shown in FIG. 6, at step 650, the terminal device 503 performs model monitoring for the AI / ML mode. In some example embodiments, through the model monitoring, the terminal device 503 may determine which zone has bad model performance.
[0118] In accordance with a determination that a metric of model performance monitoring cannot fulfill a metric threshold, the terminal device 503 may determine which zone the target UE location belongs to. By way of example, the output UE destination, located in zone X, may have a bad performance. It is noted that the reason may be wrong PRU information (e.g., LOS / NLOS status, coordinate acknowledge) in previous data set. Subsequently, training data may be updated based on the zone granularity. In some embodiments, the terminal device 503 may update the training data (may include the measurement results and the location of terminal devices) of zone X to finetune or retrain the model.
[0119] It should be noted that the reason for the bad model performance may be wrong PRU information (e.g., LOS / NLOS status, coordinate acknowledgment) existed in a previous data set.
[0120] The updated training data may be requested from the network device 501, by transmitting a data update request to the network device 501 by the terminal device 503. Herein, at least the zone ID may be indicated to the network device 501 in the requested signaling. It should further be noted that the terminal device 503 may determine data samples. As shown in FIG. 6, at step 655, the terminal device 503 transmits a data update request which include a zone ID with the bad performance. At step 660, the network device 501 initiates data pre-obtaining to one or more PRUs 502 (which may be in the zone identified by the zone ID) .
[0121] At steps 665 and 670, the PRU 502 receives a PRS which may be transmitted from the network device 501 and performs PRU measurements. Then at step 675, the PRU 502 may transmit updated model data to the network device 501. The updated model data may include the updated measurement results of the PRU 502 and the positioning data of the PRU 502 (e.g., PRU location) . At step 680, the network device 501 transmits the updated model data to the terminal device 503. At step 685, the terminal device 503 applies the updated measurement results and the positioning data for model training or re-training on the AI / ML model.
[0122] In some example embodiments, the measurement data transmitted together with the positioning data in the model data may comprise a measurement result of a reference signal that is obtained by each of the at least one first terminal device. Herein, the measurement result may comprise a first number of time domain samples in a channel impulse response (CIR) or power delay profile (PDP) , and timing information of the first number of time domain samples.
[0123] In some example embodiments, when the measurement metric is a CIR or PDP, the measurement result may include following components (with their definitions provided below) :
[0124] – N_sample: PRU sample number;
[0125] – Values to represent CIR or PDP:
[0126] ● {value 1, value 2} to represent the {real, imaginary} or {magnitude, phase} of each CIR sample (total Nt samples) in case of CIR report.
[0127] ● Value 1 to represent the value of each PDP sample (total Nt samples) in case of PDP report.
[0128] ● Bit length of the values above is configured, e.g., 32 bits.
[0129] – Size dimension of the data set includes:
[0130] ● number of TRPs,
[0131] ● number of transmit / receive antenna port pairs,
[0132] ● Nt: number of consecutive time domain samples (i.e., time domain taps to truncate a larger time domain window size) .
[0133] – Nt': Actual number of time domain samples if sub-sampling is applied which has none-zero values, i.e., Nt'< Nt. Otherwise, Nt'= Nt.
[0134] In some example embodiments, for each of the first number of time domain samples (e.g., each of the Nt' time domain samples within the Nt consecutive time domain samples) , timing information may comprise a time information value of the time domain sample. Herein, the time information value may be selected from a reporting value range. The reporting value range may be determined based on the total number of time domain samples in the CIR or PDP and a reporting resolution.
[0135] By way of example, timing information of the Nt’ samples may be selected from the total of Nt consecutive time domain samples. Herein, the reporting value range of the timing information of the Nt' samples depends on a value of Nt. Thus, the reporting value range is defined as 0*T_u to (Nt-1) *T_u. Herein, T_u is the reporting resolution which may be the time offset between two consecutive samples. In addition, log2 (Nt-1) bits are needed for timing information of each of the Nt' time domain samples.
[0136] Examples of the timing information are provided in the following Table 1 and Table 2, wherein Nt=256 in Table 1 and Nt=128 in Table 2.
[0137] Table 1: Timing information for time domain sample value 256 (Nt=256)
[0138] Table 2: Timing information for time domain sample value 128 (Nt=128)
[0139] In some example embodiments, the first communication device 301 may establish with the at least one second communication device a multicast radio bearer (MRB) for AI / ML related data transmission. the first communication device 301 may perform an MBS transmission of the model data to the at least one second communication device through the MRB.
[0140] In some example embodiments, the first communication device, which is the transmitter of model data, may establish with the at least one second communication device a multicast radio bearer (MRB) for AI / ML-related data transmission. The first communication device may perform an MBS transmission of the model data to the at least one second communication device through the MRB. By way of example, the network device 501 may establish an MRB for AI / ML-related data transmission.
[0141] FIG. 7 illustrates a signaling flow 700 for AI / ML data transmission according to some example embodiments of the present disclosure. As shown in FIG. 7, the signaling flow 700 also involves the network device 501, the PRU 502, and the terminal device 503 of FIG. 5. An AI / ML model is used by the terminal device 503 for positioning. Although one PRU and one terminal device are shown, the signaling flow 500 may involve multiple PRUs and / or multiple terminal devices. The steps 710 to 740 in the signaling flow 500 are the same as those in the signaling flow 500 of FIG. 5.
[0142] As shown in FIG. 7, at step 710 and 715, the PRU 502 may receive a PRS from the network device 501 and perform PRS measurements. At step 720, the PRU 502 transmits the measurement results and its positioning data to the network device 501.
[0143] In some example embodiments, at step 725, the data set (for example, the measurement results and positioning data of the terminal devices, e.g., PRU or UE) may be transmitted from the network device 501 (for example, gNB, LMF) to a plurality of terminal devices 502 via MBS (multi-cast or broadcast) transmission.
[0144] In some example embodiments, the first communication device 301 which is the transmitter of model data, may transmit control information and the model data to the at least one second communication device 302. The control information may be scrambled by a radio network temporary identifier (RNTI) dedicated to AI / ML-related data transmission. As an example, the AI / ML data set may be transmitted by means of the DCI format X, with CRC scrambled by G-RNTI / AI-RNTI dedicated to AI data MBS transmission. In addition, the terminal device 503, configured to receive the data set, may be required to monitor a PDCCH addressed by the RNTI.
[0145] In some example embodiments, the first communication device 301 which is the transmitter of model data, may establish a sidelink connection with a second communication device 302 which is the receiver of model data. The first communication device 301 may transmit the model data to the second communication device through the sidelink connection.
[0146] In some example embodiments, the data set (for example, the measurement results and positioning data of the terminal devices, e.g., PRU or UE) may be transmitted from one terminal device to another terminal device via a sidelink transmission. By way of example, as shown in FIG. 7, the sidelink may be between the PRU 502 and the terminal device 503. Then at step 730, the PRU 502 may transmit the measurement results and positioning data directly to the terminal device 503 via the sidelink connection. The technical effect of data set transmission via sidelink may reduce latency and save DL / UL resources.
[0147] It should be noted that, for data set transmission sidelink, an associated traffic priority may be preconfigured with a value mapped to the data set of AI / ML. Furthermore, the AI / ML data set transmission may better be in unicast with Hybrid Automatic Repeat reQuest acknowledgment (HARQ-ACK) enabling or groupcast option 2 with both ACK and negative acknowledgment (NACK) feedback. A resource allocation mode may better be set as model 1 with a resource allocated by the network device 501. Herein, if mode 2 resource allocation is configured, a priority value of the data set may be set as value "1" .
[0148] In order to protect the AI / ML data set transmission, dedicated resource pools may be configured for terminal devices. In addition, capability information of the terminal device 503 of supporting sidelink may be transmitted or aligned between the terminal device 503 (with AI / ML model) and the network device 501.
[0149] Some examples use cases for AI / ML data transmissions according to the data format and other designs according to the example embodiments of the present disclosure are descried with respect to FIG. 5 to FIG. 7. Some further use cases are also applicable, as shown in FIGS. 8-10. FIG. 8 relates to Case 1 of UE-based positioning with UE-side model for direct AI / ML positioning, where a LMF 801 is further involved for transmitting PRU locations. FIG. 9 relates to Case 1 of UE-based positioning with UE-side model for direct AI / ML positioning. FIG. 10 relates to Case 3b of NG-RAN node assisted positioning with LMF-side model for direct AI / ML positioning.
[0150] As shown in the signaling flows 800 to 1000, some steps include the transmission of PRU locations, and some steps include transmission of PRU locations together with the measurements. In those steps, the transmitter of the model data may be considered as a first communication device 301 and the receiver of the model data may be considered as a second communication device 302.
[0151] It would be appreciated that there would be other use cases for AI / ML data transmissions and the data format and other designs according to the example embodiments of the present disclosure can also be applicable.
[0152] FIG. 11 illustrates a flowchart of a communication method 1100 implemented at a first communication device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 1100 will be described from the perspective of the first communication device 301 in FIG. 2.
[0153] At block 1110, the first communication device 301 determines model data at least comprising positioning data of at least one first terminal device. The positioning data comprises: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone.
[0154] At block 1120, the first communication device 301 transmit the model data to at least one second communication device for use in an artificial intelligence / machine learning (AI / ML) model. The AI / ML model may be configured for positioning of a second terminal device.
[0155] In some example embodiments, a geographical zone amongst a plurality of predetermined geographical zones at least has a predetermined width and a predetermined height.
[0156] In some example embodiments, a geographical zone amongst a plurality of predetermined geographical zones is a three-dimensional (3D) region, and the location coordinate information of the first terminal device comprise width, height, and altitude coordinates.
[0157] In some example embodiments, a geographical zone amongst a plurality of predetermined geographical zones is in a form of two-dimensional (2D) ellipse or in a form of 3D ellipse.
[0158] In some example embodiments, when a plurality of first terminal devices locate within a first geographical zone amongst the plurality of predetermined geographical zones, the positioning data comprises a first identity of the first geographical zone, and respective location coordinate information for the plurality of first terminal devices within the first geographical zone.
[0159] In some example embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and wherein within the model data, location coordinate information of each first terminal device is paired with a measurement result of the first terminal device, the model data, an order of a respective measurement result of the at least one first terminal device is the same as an order of respective location coordinate information of the at least one first terminal device, or for each first terminal device, location coordinate information and a measurement result of the first terminal device is embedded with a same time stamp.
[0160] In some example embodiments, the communication method 1100 further comprises: receiving, from the second communication device or a third communication device, a data update request, the data update request comprising a second identity of a second geographical zone amongst the plurality of predetermined geographical zones; determine, based on the data update request, updated model data, the updated model data at least comprising further positioning data of at least one further terminal device located within the second geographical zone; and transmit the updated model data to the second communication device or the third communication device.
[0161] In some example embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and where the measurement result comprises a first number of time domain samples in a channel impulse response (CIR) or power delay profile (PDP) , and timing information of the first number of time domain samples.
[0162] In some example embodiments, for each of the first number of time domain samples, the timing information comprises a time information value of the time domain sample, the time information value being selected from a reporting value range, the reporting value range being determined based on a total number of time domain samples in the CIR or PDP and a reporting resolution.
[0163] In some example embodiments, the transmitting the model data comprises: establishing with the at least one second communication device a multicast radio bearer (MRB) for AI / ML related data transmission; and performing an MBS transmission of the model data to the at least one second communication device through the MRB.
[0164] In some example embodiments, the transmitting the model data comprises: transmitting control information and the model data to the at least one second communication device, the control information being scrambled by a radio network temporary identifier (RNTI) dedicated for AI / ML related data transmission.
[0165] In some example embodiments, the transmitting the model data comprises: establishing a sidelink connection with a second communication device; and transmitting the model data to the second communication device through the sidelink connection.
[0166] In some example embodiments, the first communication device comprises a positioning reference unit (PRU) , and the at least one second commination device comprises a network device; or wherein the first communication device comprises a network device, and the at least one second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a location management function (LMF) , and the at least one second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a network device, and the at least one second communication device comprises a LMF with the AI / ML model deployed therein.
[0167] FIG. 12 illustrates a flowchart of a communication method 1200 implemented at a second communication device in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 1200 will be described from the perspective of the second communication device 302 in FIG. 1.
[0168] At block 1210, the second communication device 302 receives, from the first communication device 301, model data for use in an artificial intelligence / machine learning (AI / ML) model. The model data at least comprises positioning data of at least one first terminal device. The positioning data comprises: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and wherein the AI / ML model is configured for positioning of a second terminal device.
[0169] In some example embodiments, the method 1200 further comprises: transmitting the model data to a third communication device with the AI / ML model deployed therein; or apply the model data for training or monitoring the AI / ML model, the AI / ML model being deployed in the second communication device.
[0170] In some example embodiments, a geographical zone amongst a plurality of predetermined geographical zones at least has a predetermined width and a predetermined height.
[0171] In some example embodiments, a geographical zone amongst a plurality of predetermined geographical zones is a three-dimensional (3D) region, and the location coordinate information of the terminal device comprises width, height, and altitude coordinates.
[0172] In some example embodiments, a geographical zone amongst a plurality of predetermined geographical zones is in a form of two-dimensional (2D) ellipse or in a form of 3D ellipse.
[0173] In some example embodiments, when a plurality of first terminal devices locate within a first geographical zone amongst the plurality of predetermined geographical zones, the positioning data comprises a first identity of the first geographical zone, and respective location coordinate information for the plurality of first terminal devices within the first geographical zone.
[0174] In some example embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and wherein within the model data, location coordinate information of each first terminal device is paired with a measurement result of the first terminal device, the model data, an order of a respective measurement result of the at least one first terminal device is the same as an order of respective location coordinate information of the at least one first terminal device, or for each first terminal device, location coordinate information and a measurement result of the first terminal device is embedded with a same time stamp.
[0175] In some example embodiments, the method 1200 further comprises: transmitting, to the first communication device, a data update request, the data update request comprising a second identity of a second geographical zone amongst the plurality of predetermined geographical zones; and receiving, from the first communication device, updated model data, the updated model data at least comprising further positioning data of at least one further terminal device located within the second geographical zone.
[0176] In some example embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and where the measurement result comprises a first number of time domain samples in a channel impulse response (CIR) or power delay profile (PDP) , and timing information of the first number of time domain samples.
[0177] In some example embodiments, for each of the first number of time domain samples, the timing information comprises a time information value of the time domain sample, the time information value being selected from a reporting value range, the reporting value range being determined based on a total number of time domain samples in the CIR or PDP and a reporting resolution.
[0178] In some example embodiments, the receiving the model data comprises: establishing with the first communication device a multicast radio bearer (MRB) for AI / ML related data transmission; and receiving the model data transmitted from the first communication device through the MRB.
[0179] In some example embodiments, the receiving the model data comprises: monitoring control information and the model data using a radio network temporary identifier (RNTI) dedicated for AI / ML related data transmission.
[0180] In some example embodiments, the receiving the model data comprises: establishing a sidelink connection with the first communication device; and receiving the model data transmitted from the first communication device through the sidelink connection.
[0181] In some example embodiments, the first communication device comprises a positioning reference unit (PRU) , and the second commination device comprises a network device; or wherein the first communication device comprises a network device, and the second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a location management function (LMF) , and the second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a network device, and the second communication device comprises a LMF with the AI / ML model deployed therein.
[0182] FIG. 13 is a simplified block diagram of a device 1300 that is suitable for implementing embodiments of the present disclosure. The device 1300 can be considered as a further example implementation of any of the devices as shown in FIG. 1, FIG. 3, and FIGS. 5-10. Accordingly, the device 1300 can be implemented at or as at least a part of the first communication device 301 or the second communication device 302) .
[0183] As shown, the device 1300 includes a processor 1310, a memory 1320 coupled to the processor 1310, a suitable transceiver 1340 coupled to the processor 1310, and a communication interface coupled to the transceiver 1340. The memory 1320 stores at least a part of a program 1330. The transceiver 1340 may be for bidirectional communications or a unidirectional communication based on requirements. The transceiver 1340 may include at least one of a transmitter 1342 and a receiver 1344. The transmitter 1342 and the receiver 1344 may be functional modules or physical entities. The transceiver 1340 has at least one antenna to facilitate communication, though in practice an Access Node mentioned in this application may have several ones. The communication interface may represent any interface that is necessary for communication with other network elements, such as X2 / Xn interface for bidirectional communications between eNBs / gNBs, S1 / NG interface for communication between a Mobility Management Entity (MME) / Access and Mobility Management Function (AMF) / SGW / UPF and the eNB / gNB, Un interface for communication between the eNB / gNB and a relay node (RN) , or Uu interface for communication between the eNB / gNB and a terminal device.
[0184] The program 1330 is assumed to include program instructions that, when executed by the associated processor 1310, enable the device 1300 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1 to 12. The embodiments herein may be implemented by computer software executable by the processor 1310 of the device 1300, or by hardware, or by a combination of software and hardware. The processor 1310 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1310 and memory 1320 may form processing means 1350 adapted to implement various embodiments of the present disclosure.
[0185] The memory 1320 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 1320 is shown in the device 1300, there may be several physically distinct memory modules in the device 1300. The processor 1310 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 1300 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.
[0186] According to embodiments of the present disclosure, a first communication device comprising a circuitry is provided. The circuitry is configured to: determine model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the terminal device within the geographical zone; and transmit the model data to at least one second communication device for use in an artificial intelligence / machine learning (AI / ML) model, the AI / ML model being configured for positioning of a second terminal device. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the first communication device as discussed above.
[0187] According to embodiments of the present disclosure, a second communication device comprising a circuitry is provided. The circuitry is configured to: receive, from a first communication device, model data for use in an artificial intelligence / machine learning (AI / ML) model, the model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the terminal device within the geographical zone; and wherein the AI / ML model is configured for positioning of a second terminal device. According to embodiments of the present disclosure, the circuitry may be configured to perform any method implemented by the second communication device as discussed above.
[0188] 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.
[0189] According to embodiments of the present disclosure, a first communication apparatus is provided. The first communication apparatus comprises means for determining model data at least comprising positioning data of at least one first terminal device. The positioning data comprises: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone. The first communication apparatus further comprises means for transmitting the model data to at least one second communication device for use in an artificial intelligence / machine learning (AI / ML) model, the AI / ML model being configured for positioning of a second terminal device. In some embodiments, the first apparatus may comprise means for performing the respective operations of the method 1100. In some example embodiments, the first apparatus may further comprise means for performing other operations in some example embodiments of the method 1100. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0190] According to embodiments of the present disclosure, a second communication apparatus is provided. The second communication apparatus comprises means for receiving, from a first communication device, model data for use in an artificial intelligence / machine learning (AI / ML) model. The model data at least comprises positioning data of at least one first terminal device. The positioning data comprises: for each of the at least one first terminal device, an identity of a geographical zone where the terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and wherein the AI / ML model is configured for positioning of a second terminal device. In some embodiments, the second apparatus may comprise means for performing the respective operations of the method 1200. In some example embodiments, the second apparatus may further comprise means for performing other operations in some example embodiments of the method 1200. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.
[0191] In summary, embodiments of the present disclosure provide the following aspects.
[0192] In an aspect, it is proposed a first communication device comprising: a processor configured to cause the first communication device to: determine model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and transmit the model data to at least one second communication device for use in an artificial intelligence / machine learning (AI / ML) model, the AI / ML model being configured for positioning of a second terminal device.
[0193] In some embodiments, a geographical zone amongst a plurality of predetermined geographical zones at least has a predetermined width and a predetermined height.
[0194] In some embodiments, a geographical zone amongst a plurality of predetermined geographical zones is a three-dimensional (3D) region, and the location coordinate information of the first terminal device comprises width, height, and altitude coordinates.
[0195] In some embodiments, a geographical zone amongst a plurality of predetermined geographical zones is in a form of two-dimensional (2D) ellipse or in a form of 3D ellipse.
[0196] In some embodiments, when a plurality of first terminal devices locate within a first geographical zone amongst the plurality of predetermined geographical zones, the positioning data comprises a first identity of the first geographical zone, and respective location coordinate information for the plurality of first terminal devices within the first geographical zone.
[0197] In some embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and wherein within the model data, location coordinate information of each terminal device is paired with a measurement result of the terminal device, the model data, an order of a respective measurement result of the at least one first terminal device is the same as an order of respective location coordinate information of the at least one first terminal device, or for each first terminal device, location coordinate information and a measurement result of the first terminal device is embedded with a same time stamp.
[0198] In some embodiments, the processor is further configured to cause the first communication device to: receive, from the second communication device or a third communication device, a data update request, the data update request comprising a second identity of a second geographical zone amongst the plurality of predetermined geographical zones; determine, based on the data update request, updated model data, the updated model data at least comprising further positioning data of at least one further terminal device located within the second geographical zone; and transmit the updated model data to the second communication device or the third communication device.
[0199] In some embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and where the measurement result comprises a first number of time domain samples in a channel impulse response (CIR) or power delay profile (PDP) , and timing information of the first number of time domain samples.
[0200] In some embodiments, for each of the first number of time domain samples, the timing information comprises a time information value of the time domain sample, the time information value being selected from a reporting value range, the reporting value range being determined based on a total number of time domain samples in the CIR or PDP and a reporting resolution.
[0201] In some embodiments, the processor is configured to cause the first communication device to: establish with the at least one second communication device a multicast radio bearer (MRB) for AI / ML related data transmission; and perform an MBS transmission of the model data to the at least one second communication device through the MRB.
[0202] In some embodiments, the processor is configured to cause the first communication device to: transmit control information and the model data to the at least one second communication device, the control information being scrambled by a radio network temporary identifier (RNTI) dedicated for AI / ML related data transmission.
[0203] In some embodiments, the processor is configured to cause the first communication device to: establish a sidelink connection with a second communication device; and transmit the model data to the second communication device through the sidelink connection.
[0204] In some embodiments, the first communication device comprises a positioning reference unit (PRU) , and the at least one second commination device comprises a network device; or wherein the first communication device comprises a network device, and the at least one second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a location management function (LMF) , and the at least one second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a network device, and the at least one second communication device comprises a LMF with the AI / ML model deployed therein.
[0205] In an aspect, it is proposed a second communication device comprising: a processor configured to cause the second communication device to: receive, from a first communication device, model data for use in an artificial intelligence / machine learning (AI / ML) model, the model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device, an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, and location coordinate information of the first terminal device within the geographical zone; and wherein the AI / ML model is configured for positioning of a second terminal device.
[0206] In some embodiments, the processor is further configured to cause the second communication device to: transmit the model data to a third communication device with the AI / ML model deployed therein; or apply the model data for training or monitoring the AI / ML model, the AI / ML model being deployed in the second communication device.
[0207] In some embodiments, a geographical zone amongst a plurality of predetermined geographical zones at least has a predetermined width and a predetermined height.
[0208] In some embodiments, a geographical zone amongst a plurality of predetermined geographical zones is a three-dimensional (3D) region, and the location coordinate information of the first terminal device comprises width, height, and altitude coordinates.
[0209] In some embodiments, a geographical zone amongst a plurality of predetermined geographical zones is in a form of two-dimensional (2D) ellipse or in a form of 3D ellipse.
[0210] In some embodiments, when a plurality of first terminal devices locate within a first geographical zone amongst the plurality of predetermined geographical zones, the positioning data comprises a first identity of the first geographical zone, and respective location coordinate information for the plurality of first terminal devices within the first geographical zone.
[0211] In some embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and wherein within the model data, location coordinate information of each first terminal device is paired with a measurement result of the first terminal device, the model data, an order of a respective measurement result of the at least one first terminal device is the same as an order of respective location coordinate information of the at least one first terminal device, or for each first terminal device, location coordinate information and a measurement result of the first terminal device is embedded with a same time stamp.
[0212] In some embodiments, the processor is further configured to cause the second communication device to: transmit, to the first communication device, a data update request, the data update request comprising a second identity of a second geographical zone amongst the plurality of predetermined geographical zones; and receive, from the first communication device, updated model data, the updated model data at least comprising further positioning data of at least one further terminal device located within the second geographical zone.
[0213] In some embodiments, the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, and where the measurement result comprises a first number of time domain samples in a channel impulse response (CIR) or power delay profile (PDP) , and timing information of the first number of time domain samples.
[0214] In some embodiments, for each of the first number of time domain samples, the timing information comprises a time information value of the time domain sample, the time information value being selected from a reporting value range, the reporting value range being determined based on a total number of time domain samples in the CIR or PDP and a reporting resolution.
[0215] In some embodiments, the processor is configured to cause the second communication device to: establish with the first communication device a multicast radio bearer (MRB) for AI / ML related data transmission; and receive the model data transmitted from the first communication device through the MRB.
[0216] In some embodiments, the processor is configured to cause the second communication device to: monitor control information and the model data using a radio network temporary identifier (RNTI) dedicated for AI / ML related data transmission.
[0217] In some embodiments, the processor is configured to cause the second communication device to: establish a sidelink connection with the first communication device; and receive the model data transmitted from the first communication device through the sidelink connection.
[0218] In some embodiments, the first communication device comprises a positioning reference unit (PRU) , and the second commination device comprises a network device; or wherein the first communication device comprises a network device, and the second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a location management function (LMF) , and the second communication device comprises at least one first terminal device with the AI / ML model deployed therein; or wherein the first communication device comprises a network device, and the second communication device comprises a LMF with the AI / ML model deployed therein.
[0219] In an aspect, a first communication device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the first communication device discussed above.
[0220] In an aspect, a second communication device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, the instructions, when executed by the at least one processor, causing the device to perform the method implemented by the second communication device discussed above.
[0221] In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the first communication device discussed above.
[0222] In an aspect, a computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the second communication device discussed above.
[0223] In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the first communication device discussed above.
[0224] In an aspect, a computer program comprising instructions, the instructions, when executed on at least one processor, causing the at least one processor to perform the method implemented by the second communication device discussed above.
[0225] 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.
[0226] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the process or method as described above with reference to FIGS. 1 to 13. 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.
[0227] 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.
[0228] 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.
[0229] 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.
[0230] 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.
[0231] To better understand the above description, some terms related to AI / ML model are provided as follows:
[0232] AI / ML-enabled Feature: refers to a Feature where AI / ML may be used.
[0233] AI / ML Model: A data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs.
[0234] AI / ML model delivery: A generic term referring to delivery of an AI / ML model from one entity to another entity in any manner. Note: An entity could mean a network node / function (e.g., gNB, LMF, etc. ) , UE, proprietary server, etc.
[0235] AI / ML model Inference: A process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.
[0236] AI / ML model testing: A subprocess of training, to evaluate the performance of a final AI / ML model using a dataset different from one used for model training and validation. Differently from AI / ML model validation, testing does not assume subsequent tuning of the model.
[0237] AI / ML model training: 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.
[0238] AI / ML model transfer: Delivery of an AI / ML model over the air interface in a manner that is not transparent to 3GPP signalling, either parameters of a model structure known at the receiving end or a new model with parameters. Delivery may contain a full model or a partial model.
[0239] AI / ML model validation: A subprocess of training, to evaluate the quality of an AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.
[0240] Data collection: 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.
[0241] Federated learning / federated training: A machine learning technique that trains an AI / ML model across multiple decentralized edge nodes (e.g., UEs, gNBs) each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples.
[0242] Functionality identification: A process / method of identifying an AI / ML functionality for the common understanding between the NW and the UE. Note: Information regarding the AI / ML functionality may be shared during functionality identification. Where AI / ML functionality resides depends on the specific use cases and sub use cases.
[0243] Management instruction: Information needed to ensure proper inference operation. This information may include selection / (de) activation / switching of AI / ML models or AI / ML functionalities, fallback to non-AI / ML operation, etc.
[0244] Model activation: enable an AI / ML model for a specific AI / ML-enabled feature.
[0245] Model deactivation: disable an AI / ML model for a specific AI / ML-enabled feature.
[0246] Model download: Model transfer from the network to UE.
[0247] Model identification: A process / method of identifying an AI / ML model for the common understanding between the NW and the UE. Note: The process / method of model identification may or may not be applicable. Note: Information regarding the AI / ML model may be shared during model identification.
[0248] Model monitoring: A procedure that monitors the inference performance of the AI / ML model.
[0249] Model parameter update: Process of updating the model parameters of a model.
[0250] Model selection: The process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature. Note: Model selection may or may not be carried out simultaneously with model activation.
[0251] Model switching: Deactivating a currently active AI / ML model and activating a different AI / ML model for a specific AI / ML-enabled feature.
[0252] Model update: Process of updating the model parameters and / or model structure of a model.
[0253] Model upload: Model transfer from UE to the network.
[0254] Network-side (AI / ML) model: An AI / ML Model whose inference is performed entirely at the network.
[0255] Offline field data: The data collected from field and used for offline training of the AI / ML model.
[0256] Offline training: An AI / ML training process where the model is trained based on collected dataset, and where the trained model is later used or delivered for inference. Note: This definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as offline training by commonly accepted conventions.
[0257] Online field data: The data collected from field and used for online training of the AI / ML model.
[0258] Online training: An AI / ML training process where the model being used for inference) is (typically continuously) trained in (near) real-time with the arrival of new training samples. Note: the notion of (near) real-time vs. non real-time is context-dependent and is relative to the inference time-scale. Note: This definition only serves as a guidance. There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Note: Fine-tuning / re-training may be done via online or offline training.
[0259] Reinforcement Learning (RL) : A process of training an AI / ML model from input (a.k.a. state) and a feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with.
[0260] Semi-supervised learning: A process of training a model with a mix of labelled data and unlabelled data.
[0261] Supervised learning: A process of training a model from input and its corresponding labels.
[0262] Test encoder / decoder for TE: AI / ML model for UE encoder / gNB decoder implemented by TE.
[0263] Two-sided (AI / ML) model: A paired AI / ML Model (s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network, i.e, the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.
[0264] UE-side (AI / ML) model: An AI / ML Model whose inference is performed entirely at the UE.
[0265] Unsupervised learning: A process of training a model without labelled data.
[0266] Proprietary-format models: ML models of vendor- / device-specific proprietary format, from 3GPP perspective. They are not mutually recognizable across vendors and hide model design information from other vendors when shared. Note: An example is a device-specific binary executable format.
[0267] Open-format models: ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually recognizable between vendors and do not hide model design information from other vendors when shared.
Claims
1.A first communication device comprising:a processor configured to cause the first communication device to:determine model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device,an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, andlocation coordinate information of the first terminal device within the geographical zone; andtransmit the model data to at least one second communication device for use in an artificial intelligence / machine learning (AI / ML) model, the AI / ML model being configured for positioning of a second terminal device.2.The device of claim 1, wherein, when a plurality of first terminal devices locate within a first geographical zone amongst the plurality of predetermined geographical zones, the positioning data comprises a first identity of the first geographical zone, and respective location coordinate information for the plurality of first terminal devices within the first geographical zone.3.The device of any of claims 1 to 2, wherein the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, andwherein within the model data,location coordinate information of each first terminal device is paired with a measurement result of the first terminal device,the model data, an order of a respective measurement result of the at least one first terminal device is the same as an order of respective location coordinate information of the at least one first terminal device, orfor each first terminal device, location coordinate information and a measurement result of the first terminal device is embedded with a same time stamp.4.The device of any of claim 1 to 3, wherein the processor is further configured to cause the first communication device to:receive, from the second communication device or a third communication device, a data update request, the data update request comprising a second identity of a second geographical zone amongst the plurality of predetermined geographical zones;determine, based on the data update request, updated model data, the updated model data at least comprising further positioning data of at least one further terminal device located within the second geographical zone; andtransmit the updated model data to the second communication device or the third communication device.5.The device of any of claims 1 to 4, wherein the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, andwhere the measurement result comprises a first number of time domain samples in a channel impulse response (CIR) or power delay profile (PDP) , and timing information of the first number of time domain samples.6.The device of claim 5, wherein for each of the first number of time domain samples, the timing information comprises a time information value of the time domain sample, the time information value being selected from a reporting value range, the reporting value range being determined based on a total number of time domain samples in the CIR or PDP and a reporting resolution.7.The device of any of claims 1 to 6, wherein the processor is configured to cause the first communication device to:establish with the at least one second communication device a multicast radio bearer (MRB) for AI / ML related data transmission;perform an MBS transmission of the model data to the at least one second communication device through the MRB; andtransmit control information and the model data to the at least one second communication device, the control information being scrambled by a radio network temporary identifier (RNTI) dedicated for AI / ML related data transmission.8.The device of any of claims 1 to 6, wherein the processor is configured to cause the first communication device to:establish a sidelink connection with a second communication device; andtransmit the model data to the second communication device through the sidelink connection.9.The device of any of claims 1 to 8, wherein the first communication device comprises a positioning reference unit (PRU) , and the at least one second commination device comprises a network device; orwherein the first communication device comprises a network device, and the at least one second communication device comprises at least one first terminal device with the AI / ML model deployed therein; orwherein the first communication device comprises a location management function (LMF) , and the at least one second communication device comprises at least one first terminal device with the AI / ML model deployed therein; orwherein the first communication device comprises a network device, and the at least one second communication device comprises a LMF with the AI / ML model deployed therein.10.A second communication device comprising:a processor configured to cause the second communication device to:receive, from a first communication device, model data for use in an artificial intelligence / machine learning (AI / ML) model, the model data at least comprising positioning data of at least one first terminal device, the positioning data comprising: for each of the at least one first terminal device,an identity of a geographical zone where the first terminal device is located amongst a plurality of predetermined geographical zones, andlocation coordinate information of the first terminal device within the geographical zone; andwherein the AI / ML model is configured for positioning of a second terminal device.11.The device of claim 10, wherein the processor is further configured to cause the second communication device to:transmit the model data to a third communication device with the AI / ML model deployed therein; orapply the model data for training or monitoring the AI / ML model, the AI / ML model being deployed in the second communication device.12.The device of any of claims 10 to 11, wherein, when a plurality of first terminal devices locate within a first geographical zone amongst the plurality of predetermined geographical zones, the positioning data comprises a first identity of the first geographical zone, and respective location coordinate information for the plurality of first terminal devices within the first geographical zone.13.The device of any of claims 10 to 12, wherein the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, andwherein within the model data,location coordinate information of each first terminal device is paired with a measurement result of the first terminal device,the model data, an order of a respective measurement result of the at least one first terminal device is the same as an order of respective location coordinate information of the at least one first terminal device, orfor each first terminal device, location coordinate information and a measurement result of the first terminal device is embedded with a same time stamp.14.The device of any of claim 10 to 13, wherein the processor is further configured to cause the second communication device to:transmit, to the first communication device, a data update request, the data update request comprising a second identity of a second geographical zone amongst the plurality of predetermined geographical zones; andreceive, from the first communication device, updated model data, the updated model data at least comprising further positioning data of at least one further terminal device located within the second geographical zone.15.The device of any of claims 10 to 14, wherein the model data further comprises measurement data, the measurement data comprising a measurement result of a reference signal that is obtained by each of the at least one first terminal device, andwhere the measurement result comprises a first number of time domain samples in a channel impulse response (CIR) or power delay profile (PDP) , and timing information of the first number of time domain samples.16.The device of claim 15, wherein for each of the first number of time domain samples, the timing information comprises a time information value of the time domain sample, the time information value being selected from a reporting value range, the reporting value range being determined based on a total number of time domain samples in the CIR or PDP and a reporting resolution.17.The device of any of claims 10 to 16, wherein the processor is configured to cause the second communication device to:establish with the first communication device a multicast radio bearer (MRB) for AI / ML related data transmission;receive the model data transmitted from the first communication device through the MRB; andmonitor control information and the model data using a radio network temporary identifier (RNTI) dedicated for AI / ML related data transmission.18.The device of any of claims 10 to 16, wherein the processor is configured to cause the second communication device to:establish a sidelink connection with the first communication device; andreceive the model data transmitted from the first communication device through the sidelink connection.19.The device of any of claims 10 to 18, wherein the first communication device comprises a positioning reference unit (PRU) , and the second commination device comprises a network device; orwherein the first communication device comprises a network device, and the second communication device comprises at least one first terminal device with the AI / ML model deployed therein; orwherein the first communication device comprises a location management function (LMF) , and the second communication device comprises at least one first terminal device with the AI / ML model deployed therein; orwherein the first communication device comprises a network device, and the second communication device comprises a LMF with the AI / ML model deployed therein.