Identification and use of nw additional conditions for positioning

Abstract

This disclosure relates to the identification and use of network (NW) additional conditions for positioning. Specifically, one method includes: transmitting first information from a first device to a second device, the first information indicating a set of transmit-receive points having positioning reference signals; receiving second information from the second device, the second information including a set of conditions registered in the second device, the set of conditions being selected based on the set of transmit-receive points; determining correlation information between metadata and the set of conditions registered in the second device, the metadata containing conditions registered in a set of models for positioning in the first device; and determining a target model from the set of models based on the correlation information.

Description

Cross-reference of related applications

[0001] This application claims priority and benefit to GB application number 2402159.4, filed on February 16, 2024, the contents of which are incorporated herein by reference in their entirety. Technical Field

[0002] Various exemplary embodiments of this disclosure generally relate to the telecommunications field, and in particular to methods, apparatuses, devices, and computer-readable storage media for identifying and using additional network (NW) conditions for location. Background Technology

[0003] With the integration of artificial intelligence (AI) and machine learning (ML) into the air interfaces of 5G and the emerging 6G New Radio (NR), new frontiers in network adaptability and efficiency are being explored. The 3GPP Release-18 research project and 3GPP Release-19 work project emphasize the importance of model generalization across various network scenarios to address the need for AI / ML models to maintain robust performance under diverse conditions. This includes strategically incorporating additional conditions to refine model training, ensuring that the model adapts well to the requirements of both the network and user equipment sides. Therefore, capturing these additional conditions warrants in-depth research, as understanding and utilizing these factors is crucial for AI / ML applications in 5G and its subsequent evolution, and can significantly impact network performance and user experience. Summary of the Invention

[0004] In a first aspect of this disclosure, a first apparatus is provided. The first apparatus includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the first apparatus to: transmit to a second apparatus first information indicating a set of transmission receiving points having positioning reference signals; receive from the second apparatus second information, the second information including a set of conditions registered on a network side, the set of conditions being selected based on the set of transmission receiving points; determine correlation information between metadata of a set of models used for positioning and the set of conditions registered on the network side; and determine a target model from the set of models based on the correlation information.

[0005] In a second aspect of this disclosure, a second apparatus is provided. The second apparatus includes at least one processor and at least one memory storing instructions, which, when executed by the at least one processor, cause the second apparatus to: receive from a first apparatus first information indicating a set of transmission receiving points having positioning reference signals; determine a set of conditions for registration on the network side based on the set of transmission receiving points and mapping information between the transmission receiving points and metadata representing channel characteristics; and transmit to the first apparatus the second information including the set of conditions for registration on the network side.

[0006] In a third aspect of this disclosure, a method is provided. The method includes: transmitting to a second device first information indicating a set of transmission and reception points having positioning reference signals; receiving from the second device second information, the second information including a set of conditions registered on a network side, the set of conditions being selected based on the set of transmission and reception points; determining correlation information between metadata of a set of models used for positioning and the set of conditions registered on the network side; and determining a target model from the set of models based on the correlation information.

[0007] In a fourth aspect of this disclosure, a method is provided. The method includes: receiving from a first device the first information indicating a set of transmission receiving points having positioning reference signals; determining a set of conditions for registration on a network side based on the set of transmission receiving points and mapping information between the transmission receiving points and metadata representing channel characteristics; and transmitting to the first device the second information including the set of conditions for registration on the network side.

[0008] In a fifth aspect of this disclosure, a first apparatus is provided. The first apparatus includes: means for transmitting to a second apparatus first information indicating a set of transmission and receiving points having a positioning reference signal; means for receiving from the second apparatus second information, the second information including a set of conditions registered on a network side, the set of conditions being selected based on the set of transmission and receiving points; means for determining correlation information between metadata of a set of models used for positioning and the set of conditions registered on the network side; and means for determining a target model from the set of models based on the correlation information.

[0009] In a sixth aspect of this disclosure, a second apparatus is provided. The second apparatus includes: means for receiving from a first apparatus first information indicating a set of transmission receiving points having positioning reference signals; means for determining a set of conditions registered on the network side based on the set of transmission receiving points and mapping information between the transmission receiving points and metadata representing channel characteristics; and means for transmitting to the first apparatus second information including the set of conditions registered on the network side.

[0010] In a seventh aspect of this disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to perform at least the method according to a third aspect.

[0011] In an eighth aspect of this disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to perform at least the method according to the fourth aspect.

[0012] It should be understood that the summary portion is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] Some exemplary embodiments will now be described with reference to the accompanying drawings, in which: Figure 1 An example communication environment in which example embodiments of this disclosure may be implemented is shown; Figure 2 A schematic diagram of a region with multiple datasets is shown; Figure 3 A schematic diagram showing the mapping of Transmitter Receiver Points (TRPs) within each cluster is shown; Figure 4A and Figure 4B The signaling flow for an LMF-assisted UE for model selection and model update / fine-tuning according to some example embodiments of this disclosure is shown; Figure 5A and Figure 5B The signaling flow selected according to some example embodiments of this disclosure is shown; Figure 6 A flowchart is shown illustrating a method implemented at a first device according to some example embodiments of the present disclosure; Figure 7 A flowchart illustrating a method implemented at a second device according to some example embodiments of the present disclosure is shown; Figure 8 A simplified block diagram of a device suitable for implementing example embodiments of the present disclosure is shown; and Figure 9 A block diagram of an example computer-readable medium according to some example embodiments of the present disclosure is shown.

[0014] Throughout all the accompanying figures, the same or similar reference numerals indicate the same or similar elements. Detailed Implementation

[0015] The principles of this disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and to assist those skilled in the art in understanding and implementing this disclosure, and do not imply any limitation on the scope of this disclosure. The embodiments described herein can be implemented in various ways other than those described below.

[0016] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0017] References to "an embodiment," "embodiment," "example embodiment," etc., in this disclosure indicate that the described embodiments may include specific features, structures, or characteristics, but it is not necessary for every embodiment to include that specific feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same embodiment. Further, when a specific feature, structure, or characteristic is described in connection with an embodiment, it is to be noted that those skilled in the art will recognize, whether explicitly described or not, that such features, structures, or characteristics apply in conjunction with other embodiments.

[0018] It should be understood that although terms such as "first," "second," etc., preceding nouns in this document may be used to describe various elements, these elements should not be limited to these terms. These terms are only used to distinguish one element from another and they do not restrict the order of nouns. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any or all combinations of one or more of the listed terms.

[0019] As used herein, “at least one of the following: ” and “at least one of ” and similar expressions, wherein the list of two or more elements is connected by “and” or “or”, means at least any one of these elements, or at least any two or more of these elements, or at least all of these elements.

[0020] As used herein, unless explicitly stated otherwise, the “responding to A” action does not indicate that the action is performed immediately after “A” occurs, and may include one or more intermediate steps.

[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. As used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising,” “including,” “having,” “possessing,” “containing,” and / or “covering,” as used herein, specify the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0022] As used in this application, the term "circuit" may refer to one or more or all of the following: (a) Hardware circuit implementation only (such as implementation in analog and / or digital circuits only) and (b) A combination of hardware circuitry and software, such as (if applicable): (i) A combination of analog and / or digital hardware circuitry with software / firmware, and (ii) Any part of a hardware processor (including (multiple) digital signal processors), software, and memory that work together to enable a device (such as a mobile phone or server) to perform various functions; and (c) (Multiple) hardware circuits and / or (multiple) processors, such as (multiple) microprocessors or portions of (multiple) microprocessors, which require software (e.g., firmware) to operate, but may not exist when the software is not required to operate.

[0023] This definition of "circuit" applies to all uses of the term in this application (including in any claim). As another example, as used herein, the term "circuit" also encompasses only hardware circuitry or a processor (or multiple processors) or portions thereof, and their accompanying software and / or firmware implementations. The term "circuit" also encompasses, for example and if applicable to a particular claim element, baseband integrated circuits or processor integrated circuits for mobile devices, or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0024] As used herein, the term "communication network" refers to a network that conforms to any suitable communication standard, such as New Radio (NR), LTE (Long Term Evolution), LTE-A Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. Furthermore, communication between terminal devices and network devices in a communication network can be performed according to any suitable generation of communication protocol, including but not limited to first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G), sixth-generation (6G) communication protocols, and / or any other currently known or to be developed in the future. Embodiments of this disclosure can be applied to various communication systems. Given the rapid development of communications, there will naturally be future types of communication technologies and systems that can implement this disclosure. The scope of this disclosure should not be considered limited to the systems described above.

[0025] As used herein, the term "network device" refers to a node in a communication network through which terminal devices access the network and receive services. Depending on the terminology and technology applied, a network device can refer to a base station (BS) or access point (AP), such as a Node B (NodeB or NB), an evolved Node B (eNodeB or eNB), an NR NB (also known as a gNB), a Remote Radio Unit (RRU), a Radio Head (RH), a Remote Radio Head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low-power node (such as a femto or pico), a non-terrestrial network (NTN) or non-terrestrial network equipment (such as satellite network equipment, low Earth orbit (LEO) satellites, and geostationary Earth orbit (GEO) satellites), an aircraft network equipment, etc. In some example embodiments, the Radio Access Network (RAN) split architecture includes a central unit (CU) and a distributed unit (DU) at the IAB host node. An IAB node includes a mobile terminal (IAB-MT) portion similar to the UE facing the parent node, and the DU portion of the IAB node is similar to the base station facing the next-hop IAB node.

[0026] The term "terminal device" refers to any end device with wireless communication capabilities. As an example and not a limitation, a terminal device can refer to communication equipment, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). Terminal devices can include, but are not limited to, mobile phones, cellular phones, smartphones, VoIP phones, wireless local loop phones, tablets, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image acquisition terminal devices (such as digital cameras), gaming terminal devices, music storage and playback devices, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEE), laptop mounted devices (LME), USB dongles, smart devices, wireless client devices (CPE), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of industrial and / or automated processing chains), consumer electronics devices, devices operating on commercial and / or industrial wireless networks, etc. The terminal device may also correspond to the mobile terminal MT portion of an IAB node (e.g., a relay node). In the following description, the terms "terminal device," "communication device," "terminal," "user equipment," and "UE" are used interchangeably.

[0027] As used herein, the terms “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” can refer to any resource used to perform communication, such as communication between a terminal device and a network device, including resources in the time domain, frequency domain, spatial domain, code domain, or any other combination of time-domain, frequency-domain, spatial-domain, and / or code-domain resources that enable communication. In the following, unless explicitly stated otherwise, resources in the frequency and time domains will be used as examples of transmission resources used to describe some exemplary embodiments of this disclosure. Note that the exemplary embodiments of this disclosure are equally applicable to other resources in other domains.

[0028] As used herein, the term "Transmitter Receiver Point (TRP)" can be defined as an antenna array having one or more antenna elements, which can be used in a network located at a specific geographic location in a specific area. In some embodiments, the TRP can be implemented at a network device. The term "conditions registered on the network side" as used herein can refer to network-side conditions that include additional information to help terminal units improve consistency between training and inference models. The terms "conditions registered on the network side," "conditions registered in a second device," and "network (NW) side additional conditions" are used interchangeably. The model identification process accurately interprets the so-called "additional conditions," which can include, for example, training dataset categories, site-related information, timestamps, implicit identification information (such as labels for specific gNB / UE implementation details), statistical information (e.g., latency spread, angle spread, LOS / NLOS data, etc.), and other factors. The term "conditions registered on the UE side" as used herein can refer to UE-side conditions that include additional information to improve consistency between training and inference models. The terms “conditions for registration on the UE side”, “conditions for registration in the first device”, and “additional conditions on the UE side” can be used interchangeably.

[0029] As used herein, a machine learning (ML) entity can be an ML model or can contain ML models and related metadata. ML entities can be managed as a single composite entity. In some example implementations, an ML entity can be implemented as an ML application (MLApp).

[0030] To facilitate understanding of the terminology, the RAN1 convention for the list of terms used in AI / ML is provided below.

[0031] AI / ML Models: Data-driven algorithms that apply AI / ML techniques to generate a set of outputs based on a set of inputs.

[0032] AI / ML Model Delivery: The general term refers to delivering an AI / ML model from one entity to another in any way. Note: An entity can refer to a network node / function (e.g., gNB, LMF, etc.), UE, dedicated server, etc.

[0033] AI / ML model inference: The process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0034] AI / ML Model Testing: A sub-process of training used to evaluate the performance of the final AI / ML model using a different dataset than that used for model training and validation. Unlike AI / ML model validation, testing does not assume subsequent adjustments to the model.

[0035] AI / ML model training: The process of training an AI / ML model in a data-driven manner [by learning input / output relationships] and obtaining the trained AI / ML model for inference.

[0036] AI / ML model transmission: AI / ML models are delivered over the air interface in a manner opaque to 3GPP signaling. These models may contain parameters of a model structure known to the receiving end, or they may be new models with parameters. The transmission may include a complete model or a partial model.

[0037] AI / ML Model Validation: A sub-process of training that evaluates the quality of an AI / ML model using a dataset different from the dataset used for model training, and helps in selecting model parameters that generalize to datasets other than those used for model training.

[0038] Data collection: The process by which network nodes, management entities, or UEs collect data for use in AI / ML model training, data analysis, and inference.

[0039] Federated learning / federated training: A machine learning technique that trains AI / ML models across multiple distributed edge nodes (e.g., UE, gNB), with each node performing local model training using local data samples. This technique requires multiple interactions between models but does not exchange local data samples.

[0040] Function Identification: Identifies the process / method for mutual understanding between the NW and UE regarding AI / ML functions. Note: Information about AI / ML functions can be shared during function identification. The residency of AI / ML functions depends on specific use cases and sub-use cases.

[0041] Model Activation: Enables AI / ML models for specific functions.

[0042] Model deactivation: Disables AI / ML models for specific functions.

[0043] Model download: The transfer of the model from the network to the UE.

[0044] Model Identification: The process / method for identifying the AI / ML model used for mutual understanding between the NW and UE. Note: The process / method for model identification may or may not be applicable. Note: Information about the AI / ML model may be shared during model identification.

[0045] Model monitoring: The process of monitoring the inference performance of AI / ML models.

[0046] Model parameter update: The process of updating the model parameters.

[0047] Model selection: The process of selecting the AI / ML model to be activated from among multiple models that share the same AI / ML-supporting features. Note: Model selection may or may not be performed concurrently with model activation.

[0048] Model switching: Deactivate the currently active AI / ML model and activate different AI / ML models for specific functions.

[0049] Model update: The process of updating the model parameters and / or model structure.

[0050] Model upload: The transfer of the model from the UE to the network.

[0051] Network-side (AI / ML) model: An AI / ML model in which inference is performed entirely at the network.

[0052] Offline field data: Data collected from the field and used for offline training of AI / ML models.

[0053] Offline training: An AI / ML training process in which a model is trained based on a collected dataset, and the trained model is later used or delivered for inference. Note: This definition is for guidance only. There may be cases that do not perfectly fit this definition but can still be classified as offline training through generally accepted conventions.

[0054] Online field data: Data collected from the field and used for online training of AI / ML models.

[0055] Online training: The AI / ML training process in which the model used for inference is trained (usually continuously) (nearly) real-time as new training samples arrive. Note: The concepts of (near) real-time and non-real-time are context-dependent and relative to the inference timescale. Note: This definition is for guidance only. There may be cases that do not perfectly fit this definition but can still be classified as online training by generally accepted conventions. Note: Fine-tuning / retraining can be done via online or offline training. (This note can be removed when we define the term fine-tuning.) Reinforcement learning (RL): The process of training an AI / ML model based on inputs (also called states) and feedback signals (also called rewards) generated by the model's outputs (also called actions) in an environment where the model interacts with itself.

[0056] Semi-supervised learning: The process of training a model using a mixture of labeled and unlabeled data.

[0057] Supervised learning: The process of training a model based on inputs and their corresponding labels.

[0058] Two-sided (AI / ML) model: A pair of AI / ML models that perform joint inference, where joint inference includes AI / ML inference jointly performed across the UE and the network, i.e., the first part of the inference is first performed by the UE, and then the remaining part is performed by the gNB, and vice versa.

[0059] UE-side (AI / ML) model: An AI / ML model where inference is performed entirely at the UE.

[0060] Unsupervised learning: The process of training a model without labeled data.

[0061] Proprietary format models: From a 3GPP perspective, these are ML models using vendor / device-specific proprietary formats. Different vendors cannot recognize these models, and sharing them hides model design information from other vendors. Note: An example is a device-specific binary executable format.

[0062] Open format models: From a 3GPP perspective, these are specified format ML models that are mutually identifiable across suppliers and allow interoperability. They are mutually identifiable between suppliers and do not hide model design information from other suppliers when shared.

[0063] 3GPP has begun to support AI / ML positioning, with the following objectives.

[0064]

[0065] Furthermore, network-side conditions are prioritized over UE-side conditions. For network-side conditions, various scenarios considering the following scenarios have been studied for model generalization:

[0066] Some solutions aim to set standards for identifying additional conditions. One proposed solution encodes potential NW additional conditions. However, it does not expose the identification aspects of NW additional conditions. Furthermore, the solution aims to create dependencies between UE additional conditions and NW additional conditions, which exceeds the scope of the current requirement set. These solutions lack details for targeting AIML use cases.

[0067] Based on the above summary, the identification and use of network-side additional conditions remains an open issue and is very likely to be standardized.

[0068] During the AIML localization study, multiple evaluations were conducted to validate the performance of the AIML model in generalization scenarios. In most of these scenarios, the evaluations indicated poor generalization performance. For example, performance significantly decreased when the model was trained on a dataset generated in a scenario with 60% clutter density and tested on a dataset generated in a scenario with 40% clutter density. When generalization fails to provide good performance, a potential solution is based on fine-tuning, model retraining, or model switching. However, currently, there is no functional framework-based signaling to guide the UE in making optimal decisions to ensure consistency between training and inference. For fine-tuning or retraining, the goal is to select the best-matching / most suitable dataset. For model switching, the goal is to select a model that best matches the channel characteristics of the dataset used for training with the channel conditions of the actual inference scenario.

[0069] Based on some example embodiments of this disclosure, a solution is provided for identifying and defining a process for using network-side additional conditions for AIML localization use cases, and these two aspects will be described below. This can improve the performance of AI / ML models.

[0070] Regarding the identification of network-side additional conditions, the main assumption prior to this is that the LMF has a dataset map over a specific geographic region, independent of the entity performing the data collection. Based on this assumption, the following steps can be performed to identify network-side additional conditions. Truth values ​​and measurements can be mapped to data that can be obtained from N... 数据集 The entire A constitutes 总共 Region. The entire A can be divided based on a square grid. 总共 The area can be defined, and each square can be numerically labeled based on specific channel characteristics. This can be done throughout the entire A... 总共 A set of channel characteristics S is identified in the region. H Clustering techniques can be applied to identify local clusters within each individual dataset, and each cluster can represent a set S. H Each element in the dataset. Each cluster identified in each dataset can represent a specific network-side additional condition.

[0071] The use of network-side additional conditions can be summarized in the following steps. The network-side additional conditions identified in the previous step can be used as additional information that the LMF indicates to the UE to help correctly select the model to be used for the corresponding function. The information decoded from the model metadata and network-side additional conditions can indicate the relevance level, which will support the UE in selecting model switching or a certain degree of model retraining / fine-tuning.

[0072] Figure 1 An example communication environment 100 in which exemplary embodiments of the present disclosure may be implemented is shown. In the communication environment 100, a first device 110 and TRPs 130-1, ..., 130-N (collectively referred to as "TRP 130", and N is an integer) can communicate with each other. The communication environment 100 may also include a second device 120, which may be a core network device. For example, the second device 120 may be a Location Management Function (LMF) entity.

[0073] In some example embodiments, if the first device 110 is a terminal device, the link from TRP 130 to the first device 110 is referred to as a downlink (DL), and the link from the first device 110 to TRP 130 is referred to as an uplink (UL). In the DL, TRP 130 is a transmit (TX) device (or transmitter), and the first device 110 is a receive (RX) device (or receiver). In the UL, the first device 110 is a TX device (or transmitter), and TRP 130 is an RX device (or receiver).

[0074] Communication in communication environment 100 can be implemented according to any suitable communication protocol, including but not limited to cellular communication protocols such as first-generation (1G), second-generation (2G), third-generation (3G), fourth-generation (4G), fifth-generation (5G), and sixth-generation (6G), wireless local network communication protocols such as IEEE 802.11, and / or any other currently known or future-developed protocols. Furthermore, communication can utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple Access (OFDM), Discrete Fourier Transform Extended OFDM (DFT-s-OFDM), and / or any other currently known or future-developed technologies.

[0075] The exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0076] The second device 120 can identify additional conditions on the NW side. In some example embodiments, before identifying the additional conditions on the NW side, the second device 120 may have a map of datasets over a specific geographic area, independent of the entity performing the data collection. For example, the second device 120 may determine an area associated with multiple datasets. In this case, each dataset may include measurement and ground truth labels. The second device 120 may also determine the number of channel characteristics in the area and a set of dominant channel characteristic values ​​in the area. In some embodiments, the second device 120 may determine multiple clusters by performing an evaluation on each of the multiple datasets based on a set of dominant channel characteristic values. In this case, each cluster identified in each dataset represents a spatial set of channel characteristics and corresponds to a set of conditions registered on the network side.

[0077] The second device 120 can obtain a model trained based on a subset of datasets from multiple datasets. In some embodiments, the second device 120 can determine a subset of datasets from multiple datasets. The second device 120 can perform model training on the model based on the subset of datasets. In this case, the metadata of the subset of datasets is included in the trained model as metadata information and corresponds to the conditions registered on the model side. Alternatively, another entity can perform model training on the model based on the subset of datasets and deliver the trained model to the second device 120. In some embodiments, a subset or the entire set of channel characteristics identified in the datasets is used for training the model.

[0078] For example, the second device 120 may perform the following steps to identify additional network-side conditions.

[0079] 1. Considering A 总共 Indicates N 数据集 Data sets (e.g., Figure 2 The dataset comprises the entire region consisting of datasets 01, 02, 3, 04, and 05. Each dataset may include measurement and truth labels. Truth values ​​can be used to map geographic locations, which are mapped to a two-dimensional (2D) dimension, and measurements can be used as sources to identify channel characteristics.

[0080] 2. Identification Area A 总共 H in 类型 The number of channel characteristics. Therefore, in region A... 总共 Define the grid above, and as follows Figure 2 As shown, parameter S can be used 方形 Define the size of the square's sides. Each square in the lattice scheme can be identified, for example, using any of the following channel characteristics with numerical values ​​from all available TRPs: a)H 类型A: The line-of-sight (LOS) / non-line-of-sight (NLOS) ratio in each square (e.g., NLOS links account for 60%).

[0081] b)H 类型 B: Use heuristic time of arrival (ToA) estimates to compare with the true ToA (obtained using the true value) as another complementary scheme to identify the LOS / NLOS ratio in each square (e.g., ToA estimation accuracy is 45%).

[0082] c)H 类型 C: Calculate the multipath root mean square (RMS) delay spread using the empirical cumulative distribution function (CDF) @ 90% of all measurements. A higher RMS CDF @ 90% value indicates a scenario with high clutter density. A lower RMS CDF @ 90% value indicates a scenario with low clutter density (e.g., clutter density of 30%).

[0083] 3. It is possible to combine (e.g., perform a weighted average) each channel characteristic (H) 类型 A, H 类型 B, H 类型 The values ​​of C, etc., are used to obtain the comprehensive channel characteristic value for each square. However, for simplicity, this disclosure discusses only one channel characteristic, but is not limited to it.

[0084] 4. Clustering techniques (e.g., neural network (NN) based clustering) can be applied to identify the entire region A. 总共 A set of dominant channel characteristic values ​​(S) H ).

[0085] 5. Consider the set of S already calculated in step 4. H Evaluate N separately 数据集 Each dataset in the list (i.e., dataset 01, dataset 02, dataset 03, dataset 04, and dataset 05). This evaluation aims to apply clustering techniques to identify local clusters based on the dominant value in each square.

[0086] 6. Each cluster identified in each dataset (e.g., Figure 3 Clusters 301, 302, and 303 in dataset 01 shown can represent a set of squares representing a specific channel characteristic, which will indicate the mapping to A. 总共 Specific network-side additional conditions in the 2D dimension of the region. Figure 3 An example is shown.

[0087] In some example implementations, each cluster may cover more than one TRP in a geographic region. Therefore, the TRPs covered by each specific cluster are mapped to a lookup table as shown in Table 1. Each TRP can be mapped to each specific cluster, and this mapping information can be included as metadata in a specific dataset.

[0088] Table 1 shows a lookup table that maps different channel characteristics to a set of TRPs.

[0089]

[0090] Considering that additional network-side conditions have been identified, signaling can be used to ensure consistency between training and inference for AIML localization use cases. Here, embodiments of this disclosure can divide the steps into two sub-parts: one focusing on the training phase and the other on inference.

[0091] Regarding the training phase, we can start with a set of N... 数据集 One or more datasets are considered / selected for model training. The metadata of these selected datasets can be included as metadata information in the target training model. During the inference phase, this metadata information can be associated with metadata representing additional conditions applied to the network side.

[0092] In some example embodiments, for the metadata under consideration, a set of channel characteristics (S) identified in the previous step can be used. H This is shared with the entities that perform model training. Based on a set of channel characteristics (S... H This allows you to identify subsets or the entire dataset used to train a specific model. These channel features identified during the training phase can be included / encoded into the trained model; for example, they can be encoded into the model ID.

[0093] Regarding the reasoning stage, see the reference... Figure 4A and Figure 4B This illustrates a signaling flow 400 for AI / ML localization using network (NW) side additional conditions, according to some embodiments of this disclosure. For discussion purposes, reference will be made to... Figure 1 For example, the signaling flow 400 can be discussed using the first device 110 and the second device 120.

[0094] In some example embodiments, the first device 110 may transmit (4005) capability information to the second device 120. In other words, the second device 120 may receive (4005) capability information from the first device 110. The capability information may indicate a set of capabilities supported by the first device 110.

[0095] In some embodiments, the second device 120 may transmit (4010) a set of location-related functions to the first device 110. In other words, the first device 110 may receive (4010) a set of location-related functions from the second device 120. The set of functions may be implemented based on AI / ML methods.

[0096] In some embodiments, the second device 120 may transmit (4015) an indication of a function selected by the second device 120. In other words, the first device 110 may receive (4015) an indication of a function selected by the second device 120 from the second device 120. The selected function may be associated with a location.

[0097] In some embodiments, the first device 110 may transmit (4020) a request for conditions for registration on the network side to the second device 120. In other words, the second device 120 may receive (4020) a request for conditions for registration on the network side from the first device 110.

[0098] In some embodiments, the second device 120 may transmit (4025) a request to the first device 110 for a set of transmission receiving points having positioning reference signals. In other words, the first device 110 may receive (4025) a request from the second device 120 for a set of transmission receiving points having positioning reference signals.

[0099] The first device 110 transmits (4030) first information to the second device 120, indicating a set of transmission and receiving points having positioning reference signals. For example, the first information may indicate a set of TRs 130 capable of transmitting positioning reference signals to the first device 110. In other words, the second device 120 receives the first information from the first device 110.

[0100] The second device 120 determines (4035) a set of conditions registered on the network side based on a set of transmission and reception points and mapping information between the transmission and reception points and metadata representing channel characteristics. For example, if the first information indicates Figure 3 If the first information includes a set of TRPs, including TRP0, 1, 2, and 3, then the second device 120 can determine a set of conditions (related to clustering 301) to be registered on the network side based on the set of TRPs included in the first information and the mapping information in Table 1. For example, the second device 120 can use a lookup table (i.e., Table 1) between TRPs and metadata representing channel characteristics to select additional conditions on the network (NW) side.

[0101] The second device 120 transmits (4040) second information to the first device 110, including a set of conditions registered on the network side. In other words, the first device 110 receives the second information from the second device 120.

[0102] The first device 110 determines (4042) the correlation information between metadata of a set of models used for positioning and a set of conditions registered on the network side. For example, the first device 110 may determine the correlation value between metadata and a set of conditions registered on the network side for each model in the set of models, the metadata including conditions registered on the model side and mapped to the model's identifier.

[0103] In some other example embodiments, the second device 120 may determine relevance information between metadata of a set of models used for positioning and a set of conditions registered on the network side. For example, the second device 120 may determine a relevance value between metadata and a set of conditions registered on the network side for each model in the set of models, the metadata including conditions registered on the model side and mapped to the model's identifier. In this case, the second device 120 may transmit the relevance information to the first device 110.

[0104] The first device 110 determines the target model (410-1 and 410-2) from a set of models based on correlation information. An example embodiment for determining the target model is described below.

[0105] In some embodiments, the first device 110 may determine (4050) a first candidate model from a set of models. The correlation value of the first candidate model may be a correlation threshold. In some embodiments, the correlation threshold may be a predetermined percentage. In this case, the first device 110 may transmit (4050) third information indicating the first candidate model to the second device 120. In some example embodiments, after receiving (4050) the third information, the second device 120 may transmit (4055) a trigger indication to the first device 110 for monitoring to evaluate the first candidate model. In this case, the first device 110 may perform (4060) evaluation of the first candidate model by applying monitoring to the first candidate model after receiving (4055) the trigger indication. Alternatively, after receiving (4050) the third information, the second device 120 may monitor the first candidate model and then transmit the monitoring results of the first candidate model to the first device 110. In this case, the first device 110 may perform (4060) evaluation of the first candidate model based on the monitoring results of the first candidate model from the second device 120. In some example embodiments, monitoring may include monitoring one or more specific statistics of the first candidate model.

[0106] In some embodiments, the first device 110 may determine (4065) whether the performance monitoring of the first candidate model is satisfied based on an evaluation. For example, the evaluation may indicate the difference or similarity between one or more monitored statistics and the true value. In some example embodiments, the first device 110 may determine that the performance monitoring of the first candidate model is satisfied if the difference is below a difference threshold or the similarity is above a similarity threshold. Alternatively, the first device 110 may determine that the performance monitoring of the first candidate model is not satisfied if the difference is above a difference threshold or the similarity is below a similarity threshold.

[0107] In some embodiments, if the performance monitoring of the first candidate model is satisfied, the first device 110 may determine the first candidate model as the target model. In this case, the first device 110 may transmit (4070) fourth information to the second device 120, the fourth information indicating that the target model is ready to perform the localization inference of the first device 110. The first device 110 may activate (4090) the target model (i.e., the first model) or the functions associated with the target model.

[0108] In some other example embodiments, if the performance monitoring of the first candidate model is not satisfied, the first device 110 can determine a second candidate model (4070′) from a set of models whose correlation value exceeds a correlation threshold for further evaluation if the performance monitoring of the first candidate model is not satisfied. In this case, the first device 110 can transmit information indicating the second candidate model to the second device 120. In some example embodiments, after receiving the information, the second device 120 can transmit a trigger indication to the first device 110 for monitoring to evaluate the second candidate model. In this case, the first device 110 can perform evaluation on the second candidate model by applying monitoring to the first candidate model after receiving the trigger indication. Alternatively, after receiving the information, the second device 120 can monitor the second candidate model and then transmit the monitoring results of the first candidate model to the first device 110. In this case, the first device 110 can perform evaluation on the second candidate model based on the monitoring results from the second device 120. In some embodiments, the first device 110 can determine whether the performance monitoring of the second candidate model is satisfied based on the evaluation. In some embodiments, if the performance monitoring of the first candidate model is satisfied, the first device 110 can determine the second candidate model as the target model. In this scenario, the first device 110 can transmit information to the second device 120 indicating that the target model is ready to perform the localization inference of the first device 110. The first device 110 can activate (4090) the target model (i.e., the second model) or a function associated with the target model.

[0109] In some embodiments, at 4045', if no correlation value exceeds a correlation threshold, the first device 110 can determine (4045') a third candidate model from a set of models. In some embodiments, the first device 110 can transmit (4050') a request for a dataset to the second device 120, the dataset being mapped to conditions registered on the network side. In other words, the second device 120 can receive (4050') a request for a dataset from the first device 110.

[0110] In some embodiments, the second device 120 may transmit (4055') a response to the first device 110 comprising at least a portion of the dataset. Alternatively, an external entity (e.g., an over-the-top (OTT) server) may transmit at least a portion of the dataset to the first device 110. In other words, the first device 110 may receive at least a portion of the dataset from the second device 120 or an external entity.

[0111] In some embodiments, the first device 110 may update (4060') the third candidate model by retraining or fine-tuning the third candidate model based on at least a portion of the dataset. In some embodiments, the first device 110 may perform (4065') evaluation on the updated third candidate model by applying monitoring to the updated third candidate model or based on the monitoring results of the updated third candidate model. For example, the second device 120 may monitor the updated third candidate model and send the monitoring results of the updated third candidate model to the first device 110. In some embodiments, the first device 110 may determine (4070') whether the performance monitoring of the updated third candidate model is satisfied based on the evaluation. The evaluation (4065') and determination (4070') are similar to the evaluation (4060) and determination (4065), and will not be described again here.

[0112] In some embodiments, if the performance monitoring of the updated third candidate model is satisfied, the first device 110 may determine the updated third candidate as the target model. In this case, the first device 110 may transmit (4075') fifth information to the second device 120, the fifth information indicating that the target model (i.e., the updated third model) is ready to perform the localization inference of the first device 110. The first device 110 may activate (4090) at least one of the functions of the target model (i.e., the updated third model) or the function associated with the target model.

[0113] In some embodiments, based on the determination that the performance monitoring of the updated third candidate model is not satisfied, the first device 110 may determine (4080) a fourth candidate model from a set of models for further retraining or fine-tuning. In this case, if the updated fourth candidate model is determined to be the target model, the first device 110 may activate (4090) at least one of the target model (i.e., the updated fourth model) or a function associated with the target model.

[0114] According to the reference Figure 4A and Figure 4B The described example embodiments allow for the appropriate selection of models to achieve better communication performance. Furthermore, the models can be fine-tuned to improve their accuracy.

[0115] refer to Figure 5A and Figure 5B This illustrates signaling flows 500 and 500' using network (NW) side additional conditions for AI / ML positioning according to some embodiments of this disclosure. For discussion purposes, signaling flow 500 relates to UE 510 and LMF 520. In some example embodiments, a first device 110 may act as UE 510 and a second device 120 may act as LMF 520. Signaling flows 500 and 500' can be applied to situations where UE 510 moves to a new scene / space / cell ID.

[0116] like Figure 5A As shown, UE 510 can report (5005) all group conditions to LMF 520. Based on the conditions reported by the UE, LMF 520 can use the combination of these conditions to set a function list. LMF 520 can assist UE 510 in sending a group of functions, and LMF 520 can indicate (5010) preferred functions.

[0117] Under the selected function, UE 510 can request (5015) network-side additional conditions from LMF 520. LMF 520 can request (5020) a set of TRPs with PRS for the target UE 510. UE 510 can report (5025) a set of TRPs with PRS.

[0118] LMF 520 can use a lookup table (5030) to map metadata of a specific TRP to specific network-side additional conditions, as shown in Table 1, with reference to the TRP associated with the target UE. The network-side additional conditions may or may not be encoded. LMF 520 can deliver (5035) network-side additional conditions to UE 510.

[0119] UE 510 can use (5040) network-side additional condition metadata and check the best match between model metadata and metadata (network-side additional conditions) received from LMF 520 in a set of models. In other words, metric C can be used to indicate the relevance between metadata obtained from a specific target model and metadata (network-side additional conditions) received from LMF 520.

[0120] In some example embodiments, the target model is included in a set of models that are perfectly correlated. In some example embodiments, the target model can be activated (5045) by switching models in a specific region or scene. In this case, the criteria for identifying whether a model is suitable for switching may include a set of models that are perfectly correlated.

[0121] In some example embodiments, only one model (5050) can be selected from all models that are fully relevant. UE 510 can report (5055) that the candidate model is ready for evaluation to LMF 520. LMF 520 can trigger (5060) a monitoring method to evaluate the candidate model. UE 510 can determine (5065) whether the model inference of the candidate model is acceptable.

[0122] If the monitoring decision indicates that the model inference is acceptable, then UE 510 reports (5070) that the selected candidate model is ready for UE location inference. If the monitoring decision is unacceptable (i.e., negative), then UE 510 can select another candidate model and can repeat steps 5050 to 5070.

[0123] In some other example embodiments, the target model is included in a set of models that are not perfectly correlated. Only one model (5145) can be selected from all models that are not perfectly correlated. In this case, the criteria used to identify whether a model is suitable for retraining / fine-tuning may include a set of models that are not perfectly correlated.

[0124] In some example embodiments, UE 510 may request a dataset mapped to specific additional conditions. In this case, a dataset or a set of datasets thereof may be delivered to UE 510 (5152). The dataset may be delivered via an air interface or other interface. UE 510 may use the recently received dataset to retrain (5150) or perform (5150) fine-tuning of the selected candidate model.

[0125] After retraining the candidate model, UE 510 can report (5155) to LMF 520 that the retrained candidate model is ready for evaluation. LMF 520 can trigger (5160) a monitoring method to evaluate the retrained candidate model. UE 510 can determine (5165) whether the model inference of the candidate model is acceptable.

[0126] If the monitoring decision indicates that the model inference is acceptable, then UE 510 reports (5170) that the retrained candidate model is ready for UE localization inference. If the monitoring decision is unacceptable (i.e., negative), then UE 510 can select another candidate model for retraining or fine-tuning, and steps 5145 to 5170 can be repeated. In some embodiments, for the case of retraining / fine-tuning, the relevance level (C) can limit the size of the dataset used for retraining / fine-tuning.

[0127] Figure 6 A flowchart of an example method 600 implemented at a first device according to some example embodiments of the present disclosure is shown. For discussion purposes, [the following will be discussed]. Figure 1 The angle description method of the first device 110 in the middle is 600.

[0128] In frame 610, the first device 110 transmits first information to the second device, indicating a set of transmission and receiving points with positioning reference signals.

[0129] At box 620, the first device 110 receives second information from the second device, the second information including a set of conditions registered in the second device, the set of conditions being selected based on a set of transmission receiving points.

[0130] In box 630, the first device 110 determines the correlation information between metadata of a set of models used for positioning and a set of conditions registered in the second device.

[0131] At box 640, the first device 110 determines the target model from a set of models based on correlation information.

[0132] In some example embodiments, method 600 further includes: for each model in a set of models, determining a correlation value between metadata and a set of conditions registered in a second device, the metadata including conditions registered in a first device and mapped to the identifier of the model; or receiving correlation information from the second device, wherein for each model in the set of models, the correlation information includes a correlation value between metadata and a set of conditions registered in the second device.

[0133] In some example embodiments, method 600 further includes: determining a first candidate model from a set of models whose correlation value exceeds a correlation threshold; transmitting third information indicating the first candidate model to a second device; after receiving a trigger indication from the second device, performing an evaluation on the first candidate model by applying monitoring to the first candidate model, the trigger indication being used for monitoring to evaluate the first candidate model, or performing the evaluation based on monitoring results of the first candidate model from the second device; and determining whether the performance monitoring of the first candidate model is satisfied based on the evaluation.

[0134] In some example embodiments, method 600 further includes: determining the first candidate model as the target model based on determining that the performance monitoring of the first candidate model is satisfied; transmitting fourth information to the second device indicating that the target model is ready to perform localization inference of the first device; and activating at least one of the target model or a function associated with the target model.

[0135] In some example embodiments, method 600 further includes: determining a second candidate model from a set of models whose correlation value exceeds a correlation threshold for further evaluation, based on the determination that the performance monitoring of the first candidate model is not satisfied.

[0136] In some example embodiments, method 600 further includes: determining a third candidate model from a set of models based on determining that no correlation value exceeds a correlation threshold; transmitting a request to a second device for a dataset mapped to conditions registered in the second device; receiving a response from the second device or an external entity including at least a portion of the dataset; and updating the third candidate model by performing retraining or fine-tuning on the third candidate model based on at least a portion of the dataset.

[0137] In some example embodiments, method 600 further includes: performing an evaluation on the updated third candidate model by applying monitoring to the updated third candidate model or based on the monitoring results of the updated third candidate model; and determining, based on the evaluation, whether the performance monitoring of the updated third candidate model is satisfied.

[0138] In some example embodiments, method 600 further includes: determining the updated third candidate model as the target model based on determining that the performance monitoring of the updated third candidate model is satisfied; transmitting fifth information to the second device indicating that the target model is ready to perform localization inference of the first device; and activating at least one of the target model or a function associated with the target model.

[0139] In some example embodiments, method 600 further includes: determining a third candidate model from a set of models for further retraining or fine-tuning based on the determination that the performance monitoring of the updated third candidate model is not satisfied.

[0140] In some example embodiments, method 600 further includes transmitting capability information to a second device that indicates a set of capabilities supported by the first device.

[0141] In some example embodiments, method 600 further includes: receiving a set of functions associated with positioning from the second device; receiving an instruction from the second device indicating functions selected by the second device; and transmitting to the second device a request for conditions registered in the second device.

[0142] In some example embodiments, method 600 further includes receiving a request from a second device for a set of transmission receiving points having positioning reference signals.

[0143] In some example embodiments, the first device includes a terminal device, and the second device includes a network device.

[0144] Figure 7 A flowchart of an example method 700 implemented at a second device according to some example embodiments of the present disclosure is shown. For discussion purposes, [the following will be discussed]. Figure 1 The angle description method 700 of the second device 120 in the middle.

[0145] In block 710, the second device 120 receives first information from the first device indicating a set of transmission receiving points having positioning reference signals.

[0146] In block 720, the second device 120 determines a set of conditions registered in the second device based on a set of transmission and reception points and mapping information between the transmission and reception points and metadata representing channel characteristics.

[0147] At frame 730, the second device 120 transmits second information to the first device, which includes a set of conditions registered in the second device.

[0148] In some example embodiments, method 700 further includes: for each model in a set of models, determining a correlation value between metadata containing conditions registered in a first device and a set of conditions registered in a second device; and transmitting correlation information to the first device, the correlation information including the correlation value determined for each model in the set of models.

[0149] In some example embodiments, method 700 further includes receiving third information indicating a candidate model from the first device.

[0150] In some example embodiments, method 700 further includes: transmitting a trigger indication to a first device for monitoring to evaluate a candidate model; or wherein a second device is configured to: monitor the candidate model; and transmit the monitoring results of the candidate model.

[0151] In some example embodiments, method 700 further includes receiving from the first device a request or instruction for a dataset mapped to conditions registered in the second device.

[0152] In some example embodiments, method 700 further includes transmitting a response comprising at least a portion of the dataset to the first device.

[0153] In some example embodiments, method 700 further includes receiving fourth information from the first device indicating that the target model is ready to perform localization inference of the first device.

[0154] In some example embodiments, method 700 further includes receiving capability information from a first device that indicates a set of capabilities supported by the first device.

[0155] In some example embodiments, method 700 further includes: transmitting to a first device a set of functions associated with positioning; transmitting to the first device an indication of functions selected by a second device; and receiving from the first device a request for conditions registered in the second device.

[0156] In some example embodiments, method 700 further includes transmitting to the first device a request for a set of transmission receiving points having positioning reference signals.

[0157] In some example embodiments, method 700 further includes: determining a region associated with a plurality of datasets, wherein each dataset includes a measurement label and a ground truth label; determining the number of channel characteristics in the region; determining a set of dominant channel characteristic values ​​in the region; and performing an evaluation on each of the plurality of datasets based on the set of dominant channel characteristic values ​​to determine a plurality of clusters, wherein each cluster identified in each dataset represents a space having a channel characteristic and corresponds to a set of conditions registered in a second device.

[0158] In some example embodiments, method 700 further includes: determining a subset of datasets from a plurality of datasets; and performing model training on a model based on the subset of datasets, wherein metadata of the subset of datasets is included as metadata information in the trained model, the metadata information corresponding to conditions registered in the first device.

[0159] In some example implementations, a subset or the entire set of channel characteristics identified in the dataset is used to train the model.

[0160] In some example embodiments, the first device includes a terminal device, and the second device includes a network device.

[0161] In some example embodiments, a first means capable of performing any of the methods in method 600 (e.g., Figure 1The first device 110 may include components for performing the corresponding operations of method 600. The components may be implemented in any suitable form. For example, the components may be implemented as circuits or software modules. The first device may be implemented as... Figure 1 The first device 110 may be included therein.

[0162] In some example embodiments, the first device includes: means for transmitting to a second device first information indicating a set of transmission receiving points having a positioning reference signal; means for receiving second information from the second device, the second information including a set of conditions registered in the second device, the set of conditions being selected based on the set of transmission receiving points; means for determining correlation information between metadata of a set of models for positioning and the set of conditions registered in the second device; and means for determining a target model from the set of models based on the correlation information.

[0163] In some example embodiments, the first device further includes: a component for determining, for each model in a set of models, a correlation value between metadata and a set of conditions registered in the second device, the metadata including conditions registered in the first device and mapped to the identifier of the model; or a component for receiving correlation information from the second device, wherein, for each model in the set of models, the correlation information includes a correlation value between metadata and a set of conditions registered in the second device.

[0164] In some example embodiments, the first device further includes: components for determining a first candidate model from a set of models whose correlation value exceeds a correlation threshold; components for transmitting third information indicating the first candidate model to a second device; components for performing an evaluation of the first candidate model by applying monitoring to the first candidate model after receiving a trigger indication from the second device, wherein the trigger indication is for monitoring to evaluate the first candidate model, or for performing the evaluation based on monitoring results of the first candidate model from the second device; and components for determining whether performance monitoring of the first candidate model is satisfied based on the evaluation.

[0165] In some example embodiments, the first device further includes: components for determining the first candidate model as the target model based on determining that the performance monitoring of the first candidate model is satisfied; components for transmitting fourth information to the second device indicating that the target model is ready to perform the localization inference of the first device; and components for activating at least one of the target model or the functions associated with the target model.

[0166] In some example embodiments, the first apparatus further includes a component for determining a second candidate model from a set of models whose correlation value exceeds a correlation threshold for further evaluation based on the determination that the performance monitoring of the first candidate model is not satisfied.

[0167] In some example embodiments, the first device further includes: components for determining a third candidate model from a set of models based on determining that no correlation value exceeds a correlation threshold; components for transmitting a request to a second device for a dataset mapped to conditions registered in the second device; components for receiving a response from the second device or an external entity including at least a portion of the dataset; and components for updating the third candidate model by performing retraining or fine-tuning on the third candidate model based on at least a portion of the dataset.

[0168] In some example embodiments, the first apparatus further includes: a component for performing an evaluation on the updated third candidate model by applying monitoring to the updated third candidate model or based on the monitoring results of the updated third candidate model; and a component for determining, based on the evaluation, whether the performance monitoring of the updated third candidate model is satisfied.

[0169] In some example embodiments, the first device further includes: components for determining the updated third candidate model as the target model based on performance monitoring of the determined updated third candidate model; components for transmitting fifth information to the second device instructing the target model to be ready to perform localization inference of the first device; and components for activating at least one of the target model or functions associated with the target model.

[0170] In some example embodiments, the first apparatus further includes a component for determining a third candidate model from a set of models for further retraining or fine-tuning based on the determination that the performance monitoring of the updated third candidate model is not satisfied.

[0171] In some example embodiments, the first device further includes a component for transmitting capability information to the second device, indicating a set of capabilities supported by the first device.

[0172] In some example embodiments, the first device further includes: means for receiving from the second device a set of functions associated with positioning; means for receiving from the second device an indication of a function selected by the second device; and means for transmitting to the second device a request for conditions registered in the second device.

[0173] In some example embodiments, the first device further includes a component for receiving a request from the second device for a set of transmission receiving points having a positioning reference signal.

[0174] In some example embodiments, the first device includes a terminal device, and the second device includes a network device.

[0175] In some example embodiments, the first device further includes components for performing other operations in some example embodiments of method 600 or the first device 110. In some example embodiments, the components include: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first device to perform corresponding operations.

[0176] In some example embodiments, a second means capable of performing any of the methods in method 700 (e.g., Figure 1 The second device 120 may include components for performing the corresponding operations of method 700. The components may be implemented in any suitable form. For example, the components may be implemented as circuits or software modules. The second device may be implemented as... Figure 1 The second device 120 may be included therein.

[0177] In some example embodiments, the second device includes: means for receiving from the first device first information indicating a set of transmission receiving points having a positioning reference signal; means for determining a set of conditions registered in the second device based on the set of transmission receiving points and mapping information between the transmission receiving points and metadata representing channel characteristics; and means for transmitting to the first device second information including the set of conditions registered in the second device.

[0178] In some example embodiments, the second device includes: components for determining, for each model in a set of models, a correlation value between metadata containing conditions registered in the first device and a set of conditions registered in the second device; and components for transmitting correlation information to the first device, the correlation information including the correlation value determined for each model in the set of models.

[0179] In some example embodiments, the second device further includes a component for receiving third information indicating a candidate model from the first device.

[0180] In some example embodiments, the second device includes components for transmitting to the first device a trigger indication for monitoring to evaluate a candidate model; or wherein the second device comprises: components for monitoring the candidate model; and components for transmitting monitoring results of the candidate model.

[0181] In some example embodiments, the second device further includes a component for receiving from the first device a request or indication of a dataset mapped to conditions registered in the second device.

[0182] In some example embodiments, the second device includes components for transmitting a response comprising at least a portion of the dataset to the first device.

[0183] In some example embodiments, the second device further includes a component for receiving fourth information from the first device indicating that the target model is ready to perform the localization inference of the first device.

[0184] In some example embodiments, the second device further includes a component for receiving capability information from the first device that indicates a set of capabilities supported by the first device.

[0185] In some example embodiments, the second device further includes: means for transmitting to the first device a set of functions associated with positioning; means for transmitting to the first device an indication of a function selected by the second device; and means for receiving from the first device a request for conditions registered in the second device.

[0186] In some example embodiments, the second device further includes a component for transmitting a request to the first device for a set of transmission receiving points having positioning reference signals.

[0187] In some example embodiments, the second apparatus further includes: components for determining regions associated with a plurality of datasets, wherein each dataset includes measurement and ground truth labels; components for determining the number of channel characteristics in the regions; components for determining a set of dominant channel characteristic values ​​in the regions; and components for performing an evaluation on each of the plurality of datasets based on the set of dominant channel characteristic values ​​to determine a plurality of clusters, wherein each cluster identified in each dataset represents a space having a channel characteristic and corresponds to a set of conditions registered in the second apparatus.

[0188] In some example embodiments, the second apparatus further includes: a component for determining a subset of datasets from a plurality of datasets; and a component for performing model training on a model based on the subset of datasets, wherein metadata of the subset of datasets is included as metadata information in the trained model, the metadata information corresponding to conditions registered in the first apparatus.

[0189] In some example implementations, a subset or the entire set of channel characteristics identified in the dataset is used to train the model.

[0190] In some example embodiments, the first device includes a terminal device, and the second device includes a network device.

[0191] In some example embodiments, the second device further includes components for performing other operations in some example embodiments of method 700 or the second device 120. In some example embodiments, the components include: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second device to perform a corresponding operation.

[0192] Figure 8This is a simplified block diagram of a device 800 suitable for implementing exemplary embodiments of the present disclosure. Device 800 can be provided to implement a communication device, for example, Figure 1 The first device 110 or the second device 120 shown. As shown, the device 800 includes one or more processors 810, one or more memories 820 coupled to the processors 810, and one or more communication modules 840 coupled to the processors 810.

[0193] Communication module 840 is used for bidirectional communication. Communication module 840 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface can represent any interface necessary for communication with other network elements. In some example embodiments, communication module 840 may include at least one antenna.

[0194] Processor 810 can be any type suitable for a local technology network and may include one or more of the following as non-limiting examples: general-purpose computer, special-purpose computer, microprocessor, digital signal processor (DSP), and processor based on a multi-core processor architecture. Device 800 may have multiple processors, such as application integrated circuit chips, which are time-subordinate to a clock synchronized with the main processor.

[0195] Memory 820 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory ROM 824, electrically programmable read-only memory EPROM, flash memory, hard disk, optical disc CD, digital video disc DVD, optical disc, laser disc, and other magnetic and / or optical memories. Examples of volatile memories include, but are not limited to, random access memory RAM 822 and other volatile memories that will not be maintained during power loss.

[0196] Computer program 830 includes computer-executable instructions that are executed by an associated processor 810. The instructions of program 830 may include instructions for performing operations / actions of some example embodiments of this disclosure. Program 830 may be stored in memory, such as ROM 824. Processor 810 can perform any suitable actions and processes by loading program 830 into RAM 822.

[0197] Example embodiments of this disclosure can be implemented using the method of procedure 830, such that device 800 can perform as described in the reference. Figures 2 to 7 Any process discussed in this disclosure. Exemplary embodiments of this disclosure may also be implemented by hardware or a combination of software and hardware.

[0198] In some example embodiments, program 830 may be tangibly contained in a computer-readable medium, which may be included in device 800 (such as in memory 820) or other storage devices accessible by device 800. Device 800 may load program 830 from the computer-readable medium into RAM 822 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. As used herein, the term "non-transitory" is a limitation of the medium itself (i.e., tangible, not tactile), and not a limitation of data storage persistence (e.g., RAM vs. ROM).

[0199] Figure 9 An example of a computer-readable medium 900 is shown, which may be in the form of a CD, DVD, or other optical storage disc. A program 830 is stored on the computer-readable medium 900.

[0200] In general, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, and others can be implemented in firmware or software executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of this disclosure are illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof, as examples of non-limiting examples.

[0201] Some exemplary embodiments of this disclosure also provide at least one computer program product tangibly stored on a computer-readable medium (such as a non-transitory computer-readable medium). The computer program product includes computer-executable instructions, such as those included in a program module, which are executed in a device targeting a physical or virtual processor to implement any of the methods described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform a particular task or implement a particular abstract data type. The functionality of the program module can be combined or split as needed among program modules in various embodiments. The machine-executable instructions for the program module can be executed within a local or distributed device. In a distributed device, the program module can reside on both local and remote storage media.

[0202] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that, when executed by the processor or controller, the program code enables the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0203] In the context of this disclosure, computer program code or related data may be carried on any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc.

[0204] Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable media can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. More specific examples of computer-readable storage media will include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0205] Furthermore, although operations are described in a specific order, this should not be construed as requiring such operations to be performed in the specific order shown or in sequential order, or to perform all shown operations to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the discussion above, these should not be construed as limiting the scope of this disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated otherwise, certain features described in the context of a single embodiment may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated otherwise, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0206] Although this disclosure has been described in language specific to structural features and / or methodological actions, it should be understood that the disclosure as defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms for implementing the claims.

Claims

1. A first device, comprising: At least one processor; as well as At least one memory, the at least one memory storing instructions, the instructions, when executed by the at least one processor, cause the first device to: Transmit first information to the second device, the first information indicating a set of transmission and reception points with positioning reference signals; Receive second information from the second device, the second information including a set of conditions registered in the second device, the set of conditions being selected based on the set of transmission receiving points; Determine the correlation information between metadata and the set of conditions registered in the second device, the metadata being included in a set of models registered in the first device for positioning; as well as The target model is determined from the set of models based on the correlation information.

2. The first device according to claim 1, wherein the first device is configured to: For each model in the set of models, determine a correlation value between the metadata and the set of conditions registered in the second device, the metadata including conditions registered in the first device and mapped to the identifier of the model; or The correlation information is received from the second device, wherein for each of the set of models, the correlation information includes the correlation value between the metadata and the set of conditions registered in the second device.

3. The first device according to claim 1 or 2, wherein the first device is configured to: From the set of models, determine the first candidate model whose correlation value exceeds the correlation threshold; Transmit third information to the second device, the third information indicating the first candidate model; After receiving a trigger indication from the second device, the first candidate model is evaluated by applying monitoring to the first candidate model, the trigger indication being used for the monitoring to evaluate the first candidate model, or the evaluation being performed based on monitoring results from the first candidate model received from the second device; and The performance monitoring of the first candidate model is determined based on the evaluation.

4. The first device according to claim 3, wherein the first device is configured to: Based on the performance monitoring results of the first candidate model, the first candidate model is determined as the target model. Transmit fourth information to the second device, the fourth information instructing the target model to be ready to perform localization inference of the first device; and Activate at least one of the following: the target model or a function related to the target model.

5. The first device according to claim 2, wherein the first device is configured to: Based on the determination that no correlation value exceeds the correlation threshold, a third candidate model is determined from the set of models; A request for a dataset, which is mapped to conditions registered in the second device, is transmitted to the second device. Receive a response from the second device or an external entity, the response comprising at least a portion of the dataset; as well as The third candidate model is updated by retraining or fine-tuning the third candidate model based on at least a portion of the dataset.

6. The first device according to claim 5, wherein the first device is configured to: The updated third candidate model is evaluated by applying monitoring to the updated third candidate model or based on the monitoring results of the updated third candidate model; and The performance monitoring of the updated third candidate model is determined based on the evaluation.

7. The first device according to claim 6, wherein the first device is configured to: Based on the performance monitoring satisfaction of the updated third candidate model, the updated third candidate model is determined as the target model; Transmit fifth information to the second device, the fifth information instructing the target model to prepare to perform localization inference of the first device; and Activate at least one of the following: the target model or a function related to the target model.

8. The first device according to any one of claims 1-7, wherein the first device is configured to: The capability information is transmitted to the second device, the capability information indicating a set of capabilities supported by the first device.

9. The first device according to any one of claims 1-8, wherein the first device is configured to: Receive a set of functions associated with positioning from the second device; Receive from the second device an instruction indicating the function selected by the second device; and The request for the conditions registered in the second device is transmitted to the second device.

10. The first device according to any one of claims 1-9, wherein the first device is configured to: Receive requests from the second device for the set of transmission receiving points having positioning reference signals.

11. The first apparatus according to any one of claims 1-10, wherein the first apparatus includes a terminal device, and the second apparatus includes a network device.

12. A second device, comprising: At least one processor; as well as At least one memory, the at least one memory storing instructions, the instructions, when executed by the at least one processor, cause the second device to: Receive first information from the first device, the first information indicating a set of transmission and reception points having a positioning reference signal; A set of conditions for registration in the second device is determined based on the set of transmission and reception points and the mapping information between the transmission and reception points and metadata representing channel characteristics. as well as Transmit second information to the first device, the second information including the set of conditions registered in the second device.

13. The second device according to claim 12, wherein the second device is configured to: For each model in the set of models, determine a correlation value between the metadata and the set of conditions registered in the second device, the metadata including the conditions registered in the first device; and The first device is transmitted correlation information, which includes the correlation value determined for each model in the set of models.

14. The second device according to claim 12 or 13, wherein the second device is configured to: The third information is received from the first device, which indicates a candidate model.

15. The second device according to claim 14, wherein the second device is configured to: Transmit a trigger indication to the first device, the trigger indication being used to monitor and evaluate the candidate model; or The second device is configured such that: Monitoring the candidate models; and The monitoring results of the candidate model are transmitted.

16. The second device according to claim 14, wherein the second device is configured to: The first device receives a request or instruction for at least a portion of a dataset, which is mapped to conditions registered in the second device.

17. The second device according to any one of claims 12-16, wherein the second device is configured to: The target model receives a fourth message from the first device, the fourth message indicating that the target model is ready to perform localization inference from the first device.

18. The second device according to any one of claims 12-17, wherein the second device is configured to: Identify regions associated with multiple datasets, where each dataset includes measurements and ground truth labels; Determine the number of channel characteristics in the region; Determine a set of dominant channel characteristic values ​​in the region; as well as Multiple clusters are determined by performing an evaluation on each of the plurality of datasets based on the set of dominant channel characteristic values, wherein each cluster identified in each dataset represents a space of a channel characteristic and corresponds to a set of conditions registered in the second device.

19. The second device according to claim 18, wherein the second device is configured to: A model is obtained, which is trained based on a subset of the datasets from the plurality of datasets, wherein metadata of the subset of datasets is included in the trained model as metadata information corresponding to conditions registered in the first device.

20. The second apparatus of claim 19, wherein a subset or the entire set of channel characteristics identified in the dataset is used to train the model.

21. A method implemented at a first device, comprising: Transmit first information to the second device, the first information indicating a set of transmission and reception points with positioning reference signals; Receive second information from the second device, the second information including a set of conditions registered in the second device, the set of conditions being selected based on the set of transmission receiving points; Determine the correlation information between the metadata of a set of models and the set of conditions registered in the second device, the set of models being used for positioning registered in the first device; as well as The target model is determined from the set of models based on the correlation information.

22. A method implemented at a second device, comprising: Receive first information from the first device, the first information indicating a set of transmission and reception points having a positioning reference signal; A set of conditions for registration in the second device is determined based on the set of transmission and reception points and the mapping information between the transmission and reception points and metadata representing channel characteristics. as well as Transmit second information to the first device, the second information including the set of conditions registered in the second device.

23. A first device, comprising: A component for transmitting first information to a second device, the first information indicating a set of transmission and reception points having a positioning reference signal; A component for receiving second information from the second device, the second information including a set of conditions registered in the second device, the set of conditions being selected based on the set of transmission receiving points; A component for determining the correlation information between metadata of a set of models used for positioning and the set of conditions registered in the second device; as well as A component used to determine the target model from the set of models based on correlation information.

24. A second device, comprising: A component for receiving first information from a first device, the first information indicating a set of transmission and receiving points having a positioning reference signal; A component for determining a set of conditions registered in the second device based on the set of transmission and reception points and the mapping information between the transmission and reception points and metadata representing channel characteristics. as well as A component for transmitting second information to the first device, the second information including the set of conditions registered in the second device.

25. A computer-readable medium comprising instructions stored thereon for causing a device to perform at least the method of claim 21 or 22.

Images