Method and apparatus for use in node for wireless communication

Abstract

Provided are a method and apparatus for use in a node for wireless communication. The method comprises: receiving first information, the first information being used for indicating a plurality of positioning estimation values of a first node; and determining a reference position of the first node on the basis of the plurality of positioning estimation values, the reference position being used for monitoring the performance of a first model. Compared with a conventional ground truth-based performance monitoring solution, monitoring the performance of a first model by means of a reference position determined on the basis of a plurality of positioning estimation values helps to reduce the cost and complexity of acquiring real position data.

Description

Methods and apparatus for nodes used in wireless communication Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a method and apparatus for a node used in wireless communication. Background Technology

[0002] In communication systems, the location of a first node can be determined based on a first model (e.g., an artificial intelligence (AI) / machine learning (ML) model). During the localization process, the performance of the first model is evaluated by comparing its estimated location with the ground truth. However, in practical applications, performance monitoring schemes based on ground truth face numerous challenges, potentially limiting the effectiveness of performance monitoring. Summary of the Invention

[0003] This application provides a method and apparatus for use in a node for wireless communication. The various aspects covered by this application are described below.

[0004] In a first aspect, a method is provided for a first node in wireless communication, comprising: receiving first information, the first information indicating a plurality of location estimates of the first node; determining a reference position of the first node based on the plurality of location estimates; wherein the reference position is used to monitor the performance of a first model.

[0005] In a second aspect, a method is provided for a second node in wireless communication, comprising: transmitting first information, the first information being used to indicate a plurality of positioning estimates of a first node, the plurality of positioning estimates being used to determine a reference position of the first node; wherein the reference position is used to monitor the performance of a first model.

[0006] Thirdly, a first node for wireless communication is provided, the first node comprising: a first transceiver for receiving first information, the first information indicating a plurality of positioning estimates of the first node; and determining a reference position of the first node based on the plurality of positioning estimates; wherein the reference position is used to monitor the performance of a first model.

[0007] Fourthly, a second node for wireless communication is provided, the second node comprising: a second transceiver transmitting first information, the first information being used to indicate multiple positioning estimates of a first node, the multiple positioning estimates being used to determine a reference position of the first node; wherein the reference position is used to monitor the performance of a first model.

[0008] Fifthly, a first node for wireless communication is provided, comprising a transceiver, a memory, and a processor, wherein the memory stores a program, the processor invokes the program in the memory, and controls the transceiver to receive or transmit signals to cause the first node to perform the method as described in the first aspect.

[0009] In a sixth aspect, a second node for wireless communication is provided, comprising a transceiver, a memory, and a processor, wherein the memory stores a program, the processor invokes the program in the memory, and controls the transceiver to receive or transmit signals to cause the second node to perform the method as described in the second aspect.

[0010] In a seventh aspect, embodiments of this application provide a communication system including the aforementioned first node and / or second node. In another possible design, the system may further include other devices that interact with the first node or second node as described in the embodiments of this application.

[0011] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps in the methods described above.

[0012] Ninthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of the methods described in the foregoing aspects. In some implementations, the computer program product may be a software installation package.

[0013] In a tenth aspect, embodiments of this application provide a chip including a memory and a processor, the processor being able to call and run a computer program from the memory to implement some or all of the steps described in the methods of the foregoing aspects.

[0014] In this application, the first information received by the first node indicates multiple positioning estimates of the first node. The first node can determine a reference position based on these multiple positioning estimates, and the reference position is used to monitor the performance of the first model. Compared with traditional performance monitoring schemes based on ground truth, monitoring the performance of the first model based on a reference position determined by multiple positioning estimates helps to reduce the cost and complexity of obtaining real location data. Attached Figure Description

[0015] Figure 1 shows the wireless communication system 100 used in an embodiment of this application.

[0016] Figure 2 is a schematic diagram of a network architecture applicable to embodiments of this application.

[0017] Figures 3A and 3B are schematic diagrams of wireless protocol stack structures applicable to embodiments of this application.

[0018] Figure 4 is a schematic diagram of neurons in a neural network applicable to embodiments of this application.

[0019] Figure 5 is a schematic diagram of a neural network applicable to embodiments of this application.

[0020] Figure 6 is a schematic diagram of a convolutional neural network that can be applied to embodiments of this application.

[0021] Figure 7 is a schematic flowchart of a method for a first node in wireless communication provided in an embodiment of this application.

[0022] Figure 8 is an example diagram of multiple basic positioning units used to obtain multiple positioning estimates.

[0023] Figure 9 is an exemplary flowchart of a method for determining the reference position of a first node provided in an embodiment of this application.

[0024] Figure 10 is a schematic diagram of the structure of the first node for wireless communication provided in an embodiment of this application.

[0025] Figure 11 is a schematic diagram of the structure of the second node for wireless communication provided in an embodiment of this application.

[0026] Figure 12 is a schematic structural diagram of the device provided in an embodiment of this application. Detailed Implementation

[0027] Communication system architecture

[0028] Figure 1 is a system architecture example diagram of a wireless communication system 100 to which embodiments of this application can be applied. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographical area and may communicate with the terminal device 120 located within that coverage area.

[0029] Figure 1 exemplarily illustrates a network device and multiple terminal devices, such as terminal devices 120a to 120j in Figure 1. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include other numbers of terminal devices within its coverage area; this application embodiment does not limit this.

[0030] Optionally, the wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in this embodiment.

[0031] It should be understood that the technical solutions of the embodiments of this application can be applied to various communication systems, such as: 5th-generation (5G) systems or new radio (NR) systems, long-term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, advanced long-term evolution (LTE-A) systems, enhanced 5G (5G advanced) systems, etc. The technical solutions provided in this application can also be applied to future communication systems, such as 6th-generation (6G) mobile communication systems, satellite communication systems, etc.

[0032] The terminal device in this application embodiment can also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. The terminal device in this application embodiment can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as a handheld device with wireless connectivity, vehicle-mounted device, etc. The terminal device in the embodiments of this application may be a mobile phone, tablet computer, laptop computer, handheld computer, camera equipment, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. Optionally, the terminal device may be used to act as a base station. For example, the terminal device may act as a scheduling entity, providing sidelink signals between UEs in vehicle-to-everything (V2X) or device-to-device (D2D) connections. For example, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices can communicate without relaying communication signals through base stations.

[0033] The network device in this application embodiment can be a device for communicating with terminal devices. This network device can also be called an access network device or a radio access network device, such as a base station (BS). In this application embodiment, the network device can refer to a radio access network (RAN) node or a next-generation RAN (NG-RAN) node (or device) that connects user equipment to a wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, transmitting and receiving point (TRP), transmitting point (TP), master station (MeNB), secondary station (SeNB), multi-mode radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar, or a combination thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. Base stations can also be mobile switching centers, devices that perform base station functions in D2D, V2X, and machine-to-machine (M2M) communications, network-side devices in 6G networks, and devices that perform base station functions in future communication systems. Base stations can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the network equipment.

[0034] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0035] In some deployments, the network device in this application embodiment may refer to a CU or a DU, or the network device may include both a CU and a DU. The gNB may also include an AAU.

[0036] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located.

[0037] It should be understood that all or part of the functions of the communication device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (e.g., a cloud platform).

[0038] Figure 2 illustrates a schematic diagram of a network architecture 200 according to an embodiment of this application. This network architecture 200 describes the network architecture of a 5G NR / LTE / LTE-A system, which can also be referred to as a 5G system (5GS) / evolved packet system (EPS) network architecture. The network architecture 200 includes at least one of the following: network device 110, terminal device 120, 5G core network (5GC) / evolved packet core (EPC) 210, home subscriber server (HSS) / unified data management (UDM) 220, and Internet service 230. The network device and terminal device in Figure 2 are illustrated using RAN and UE as examples, respectively.

[0039] As shown in Figure 2, network device 110 provides user plane and control plane protocol termination to terminal device 120. Network device 110 is connected to 5GC / EPC 210 via an S1 / NG interface. 5GC / EPC 210 includes a mobility management entity (MME) / authentication management field (AMF) / session management function (SMF) 211, other MMEs / AMFs / SMFs 214, a service gateway (S-GW) / user plane function (UPF) 212, and a packet data network gateway (P-GW) / UPF 213. MME / AMF / SMF 211 is the control node that handles signaling between terminal device 120 and 5GC / EPC 210. Generally, MME / AMF / SMF 211 provides bearer and connection management. All user Internet Protocol (IP) packets are transmitted through the S-GW / UPF212, which is itself connected to the P-GW / UPF213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF213 is connected to Internet service 230. Internet service 230 includes operator-compliant Internet Protocol services, specifically including the Internet, intranet, IP multimedia subsystem (IMS), and packet-switched streaming services. It is evident that network architecture 200 provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented herein can be extended to networks providing circuit-switched services or other cellular networks.

[0040] Figures 3A and 3B respectively illustrate a schematic diagram of a wireless protocol stack structure according to an embodiment of this application. Figures 3A and 3B use a 5G wireless protocol stack as an example for illustration. The 5G wireless protocol stack is divided into two planes: the user plane (UP) protocol stack and the control plane (CP) protocol stack. The user plane protocol stack is the protocol suite used for user data transmission, and the control plane protocol stack is the protocol suite used for control signaling transmission in the 5G system. The specific names of each protocol stack layer are as follows:

[0041] As shown in Figure 3A, the user plane protocol stack includes, from top to bottom, the following layers: Service Data Adaptation Protocol (SDAP) layer, Packet Data Convergence Protocol (PDCP) layer, Radio Link Control (RLC) layer, Medium Access Control (MAC) layer, and Physical (PHY) layer.

[0042] As shown in Figure 3B, the control plane protocol stack includes, from top to bottom: non-access stratum (NAS); radio resource control (RRC) layer, PDCP layer, RLC layer, MAC layer, and PHY layer.

[0043] It should be understood that the different layers in the above protocol stack have different functions, and they work together through inter-layer interaction to achieve communication between terminal devices and network devices. With the development of artificial intelligence technology, AI-assisted computing has permeated the processing implementation methods of the above protocol stack. For example, the scheduling algorithm of the MAC layer and the encoding / decoding algorithm of the PHY layer can apply artificial intelligence algorithms to improve the performance of communication algorithms.

[0044] As an example, the wireless protocol architecture in Figures 3A and 3B is applicable to the first node in this application.

[0045] As an example, the wireless protocol architecture in Figures 3A and 3B is applicable to the second node in this application.

[0046] It should be understood that the interpretation of the terminology in the embodiments of this application may refer to the TS36, TS37 and TS38 series of specifications of the 3rd generation partnership project (3GPP), but may also refer to the specifications of the Institute of Electrical and Electronics Engineers (IEEE).

[0047] Neural Networks

[0048] AI research, exemplified by neural networks, has achieved significant results in many fields and will continue to impact people's lives and work for a long time to come. A neural network can be understood as a computational model composed of multiple interconnected neurons. In a neural network, the connection strength between nodes can be represented as the weighted values ​​corresponding to the input signals, also known as parameters. Each neuron performs a weighted summation of different input signals and outputs the result through a specific activation function. Neurons can achieve nonlinear mappings depending on the activation function.

[0049] Taking the neuron shown in Figure 4 as an example, the input of the neuron can be denoted as A, and each dimension of the input can be denoted as a. j The corresponding weighted value is denoted as w. j Where j takes values ​​of 1, 2, ..., n. The neuron's input can also be set with a bias term to adjust the output, as shown by the constant 1 in Figure 4 (corresponding to the weighting value denoted as b). The weighting value, together with the summation units (SU), enhances or weakens the input. The output of the SU can be input into the activation function f to obtain the output t.

[0050] Common neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), and deep neural networks (DNN).

[0051] The neural network applicable to the embodiments of this application is described below with reference to Figure 5. The neural network shown in Figure 5 can be divided into three categories according to the position of different layers: input layer 510, hidden layer 520, and output layer 530. Generally, the first layer is the input layer 510, the last layer is the output layer 530, and the intermediate layers between the first and last layers are hidden layers 520.

[0052] The input layer 510 is used to input data, which may be, for example, a received signal received by a receiver. The hidden layer 520 is used to process the input data, for example, to decompress the received signal. The hidden layer may also be called an intermediate layer. The output layer 530 is used to output the processed output data, for example, to output the decompressed signal.

[0053] Referring to Figure 5, the neural network consists of multiple layers, each containing multiple neurons. Neurons between layers can be fully connected or partially connected. For connected neurons, the output of a neuron in one layer can serve as the input to a neuron in the next layer.

[0054] To facilitate understanding, the following uses a CNN as an example, with reference to Figure 6, to illustrate the multiple layers in a neural network. A CNN is a deep neural network with convolutional structures. As shown in Figure 6, the structure of a CNN may include an input layer 610, a convolutional layer 620, a pooling layer 630, a fully connected layer 640, and an output layer 650. The convolutional layer 620, pooling layer 630, and fully connected layer 640 are the intermediate layers of this CNN.

[0055] Each convolutional layer (620) can contain multiple convolution operators, also known as kernels. These operators can be viewed as filters that extract specific information from the input signal. Essentially, a convolution operator is a parameter matrix, which is usually predefined. The parameter values ​​in these matrices need to be obtained through extensive training in practical applications to help the CNN make correct predictions. When a CNN has multiple convolutional layers, the initial convolutional layers tend to extract more general features, which can also be called low-level features. As the CNN depth increases, the features extracted by later convolutional layers become increasingly complex.

[0056] Pooling layers 630 are often introduced periodically after convolutional layers to reduce the number of training parameters and the space required for information extraction. Pooling layers can be introduced in various ways; for example, as shown in Figure 6, a pooling layer can follow a convolutional layer, or multiple convolutional layers can be followed by one or more pooling layers.

[0057] A fully connected layer 640 is used to generate the final output information. Since the convolutional layer 620 and pooling layer 630 are only responsible for extracting features and reducing parameters introduced by the input data, their processing is insufficient to generate the required output information; therefore, a fully connected layer 640 is introduced. Typically, the fully connected layer 640 may also include multiple hidden layers, the parameters of which can be pre-trained using training data relevant to the specific task type. For example, this task type may include decoding data signals received by a receiver. Another example is channel estimation based on pilot signals received by the receiver.

[0058] Following the multiple hidden layers in the fully connected layer 640, the final layer of the entire CNN, the output layer 650, is used to output the result. Typically, the output layer 650 is equipped with a loss function (e.g., a loss function similar to classification cross-entropy) to calculate the prediction error, or to evaluate the degree of difference between the output of the CNN model (also known as the predicted value) and the ideal result (also known as the true value).

[0059] It should be noted that the CNN shown in Figure 6 is only an example of a convolutional neural network. In specific applications, convolutional neural networks can also exist in the form of other network models, and this application does not limit this.

[0060] The preceding text, with reference to Figures 4 to 6, introduced the various layers of a neural network and their importance within the network. As can be seen, a neural network model includes an input layer, an output layer, and intermediate layers. Each layer of the neural network has its specific responsibilities and functions. The input layer is responsible for receiving and preprocessing data; the intermediate layers are responsible for feature extraction and processing; and the output layer is responsible for transforming the processed data into the desired output result. Through the interaction of multiple layers, the neural network can process and analyze complex data and extract useful information from it.

[0061] Optionally, the input or output of any intermediate layer in a neural network model can be called an intermediate feature of the model. That is, the intermediate feature of the model can be the output of the input layer or any intermediate layer, or it can be the input of any intermediate layer or output layer.

[0062] AI / ML positioning technology

[0063] In communication systems (e.g., the evolution and enhancement of 5G (5G-Advanced, 5G-A) and the upcoming 6G networks), positioning technology will play a crucial role, especially in applications supporting high accuracy, low latency, and wide coverage, such as autonomous driving, the Internet of Things (IoT), AR, smart cities, and industrial automation. Traditional positioning methods primarily rely on measurement techniques such as multilateral positioning, Doppler frequency shift (e.g., time difference of arrival (TDOA), frequency difference of arrival (FDOA)), and angle-of-arrival (AoA). However, with increasing network complexity, particularly in high-density user environments, non-line-of-sight (NLOS) scenarios, and complex urban terrain, traditional positioning methods require significant computational resources and cannot meet the demands of large-scale IoT and ultra-low latency applications. The introduction of AI / ML provides strong support for overcoming these limitations.

[0064] AI / ML improves positioning accuracy

[0065] AI / ML can improve positioning accuracy by processing large amounts of nonlinear, multi-dimensional data and learning effective features and patterns from complex wireless environments.

[0066] As an example, specific ways in which AI / ML improves positioning accuracy include channel feature extraction based on deep learning. This involves using deep neural networks to capture the spatial and temporal characteristics of wireless signals and automatically learning the complex nonlinear changes during signal propagation. In non-line-of-sight environments, AI models can enhance their understanding of signal paths and thus improve positioning accuracy by learning complex characteristics such as multipath reflection and attenuation.

[0067] As an example, AI / ML improves positioning accuracy by fusing multimodal data. This involves integrating different measurement data, such as time, angle, and power information, through AI / ML models. This multimodal data fusion improves location estimation. Especially in environments with strong NLoS or multipath effects, traditional methods may fail, while AI / ML can infer more accurate locations by fusing this information.

[0068] AI / ML extended coverage

[0069] In communication systems, the application of millimeter wave bands makes signals susceptible to blockage, resulting in limited coverage. AI / ML can help solve this problem.

[0070] As an example, AI / ML can predict and compensate for occlusion effects. By analyzing historical data and environmental information, it can predict potential signal blockages and even continue to provide high-precision positioning when signals are obstructed through compensation techniques. For instance, ML models can utilize cooperative information from surrounding base stations, combined with prior knowledge, to predict the path and location of signals.

[0071] As an example, AI / ML can dynamically adjust positioning strategies. In a wide range of indoor and outdoor environments, AI / ML models can dynamically adjust positioning strategies based on changes in the current environment. For instance, in densely populated urban areas, AI / ML models can dynamically select the optimal base station or network configuration based on complex environmental changes and user density to maximize positioning accuracy and coverage.

[0072] AI / ML improves computational efficiency

[0073] The high data volume transmission of communication systems places higher demands on computing efficiency. AI / ML technologies can reduce computing resource consumption through intelligent data processing and resource management.

[0074] As an example, distributed AI / ML models reduce the load on central servers and achieve distributed processing by deploying AI / ML models at the network edge (such as edge computing nodes and user devices). Edge AI / ML models can process local data in real time, perform rapid location estimation, and collaborate with central models to improve overall performance when needed.

[0075] As an example, model adaptation and compression techniques allow AI / ML models to adaptively adjust based on network conditions and computing resources. Model compression and quantization techniques can reduce computational complexity and energy consumption while maintaining positioning accuracy, making them more suitable for resource-constrained user devices or network environments.

[0076] AI / ML-based positioning methods

[0077] Direct positioning and AI-assisted positioning are two different approaches to positioning technology applications, differing in how they achieve positioning and their reliance on AI / ML technologies.

[0078] Direct localization refers to inferring a device's location directly from raw signal data using an AI / ML model. In other words, the AI / ML model itself handles the entire transformation process from input signal to location coordinates. In direct localization, the AI / ML model directly generates the location output by processing the raw input (such as received signal strength, time of arrival, channel state information, etc.). This approach integrates signal processing and location inference into a single model. Direct localization fully leverages the powerful feature extraction capabilities of AI / ML models, extracting location-related information from complex signal patterns through techniques such as deep learning, typically providing high localization accuracy.

[0079] Typical application scenarios for direct positioning include:

[0080] Case 1: Direct AI / ML positioning based on terminal device positioning and terminal device side model.

[0081] Case 2b: Positioning based on the terminal device's assisted location management function (LMF), using the LMF-side model for direct AI / ML positioning.

[0082] Case 3b: Next-generation radio access network (NG-RAN) node-assisted localization using an LMF-side model for direct AI / ML localization.

[0083] AI / ML-assisted localization refers to using AI / ML technologies to enhance or optimize certain aspects of traditional localization methods, rather than directly inferring location from signals. In this context, AI / ML is typically used to improve or supplement existing localization algorithms, rather than replace them. In AI / ML-assisted localization, AI / ML is usually used to improve certain aspects of the localization system, such as increasing the accuracy of signal processing, optimizing algorithm parameters, and performing error correction, while the final localization calculation still relies on traditional methods (such as geometric algorithms and triangulation). AI / ML-assisted localization focuses more on optimizing existing systems, is highly adaptable, and can be fine-tuned using AI / ML technologies in different scenarios to adapt to environmental changes.

[0084] Typical applications of assisted positioning include:

[0085] Case 2a: Terminal device-assisted / LMF-based localization, using terminal device-side models, AI / ML-assisted localization.

[0086] Case 3a: NG-RAN node-assisted localization, using access network equipment-side model, AI / ML-assisted localization.

[0087] AI / ML-driven localization architecture

[0088] AI / ML-driven positioning architectures can generally be divided into two main parts: the network device side and the terminal device side. These two parts each play different roles in the positioning system and perform different tasks to work together to achieve high-precision and high-efficiency positioning services.

[0089] Network device-side positioning systems typically include key network entities such as access network devices (e.g., gNB) and core network devices (e.g., LMF). The network device side is primarily responsible for centralized computing and data management, handling large-scale network information and complex operations related to positioning tasks. It collects a large amount of positioning-related data, which may originate from multiple access network devices, reference signals (e.g., positioning reference signals (PRS)), and terminal devices. As an example, this data can consist of various measurements, such as time of arrival (TOA) and altitude of arrival (AOA), all collected uniformly by the network device side.

[0090] At the AI / ML model deployment and inference level, network devices can deploy AI / ML models in nodes such as core network devices or access network devices. These models perform localization inference based on collected measurement data. Network devices possess powerful computing resources, capable of processing large amounts of input data and inferring the precise location of terminal devices in real time. When AI / ML models are deployed on the core network device side, they are responsible for executing complex localization algorithms and integrating signals from multiple measurement points, applying deep learning or other AI / ML technologies to improve localization accuracy. Especially in direct AI / ML localization scenarios, the core network device is responsible for performing localization inference independently without the assistance of terminal devices. When AI / ML models are deployed on the access network device side, in AI / ML-assisted localization scenarios, the models on the access network device side work collaboratively with the models on the terminal device side, improving localization accuracy and coverage by optimizing signal processing and data transmission paths.

[0091] At the signaling control layer, network equipment needs to perform numerous control tasks, including coordinating communication between terminal equipment and access network equipment, sending auxiliary data (such as location calculation auxiliary data) to terminal equipment, and managing measurement reports. These control tasks ensure efficient collaboration between the terminal equipment and the positioning system on the network equipment side.

[0092] The advantage of network device-side architecture lies in its stronger computing power, enabling it to handle complex AI / ML models, which supports large-scale user localization. Furthermore, network devices can access global network status and topology information, combining this global data to optimize localization inference.

[0093] The terminal device-side positioning system is primarily responsible for performing distributed positioning tasks, especially in low-latency and high-dynamic scenarios. The terminal device needs to calculate or assist the network device in completing the positioning task in real time based on local signals and some network-side data. The terminal device is responsible for processing local measurement data in real time, such as TOA, signal strength, and angle. Based on this data, the terminal device can perform some preprocessing tasks and, in certain scenarios, independently perform position estimation (e.g., direct positioning using a terminal device-side model).

[0094] At the AI / ML model deployment and inference level, lightweight AI / ML models can be deployed on the terminal device side. These models can perform terminal device location estimation based on local measurement data and auxiliary data received from the network device side. For example, in direct localization using AI / ML models on the terminal device side, the AI / ML model performs inference based on received signals and local data to generate real-time location estimation results. Furthermore, the terminal device side communicates with the network device side via signaling, providing measurement data or requesting auxiliary information, such as location calculation auxiliary data. This collaborative localization architecture enables terminal devices to perform localization inference more flexibly.

[0095] Compared to network device-side architecture, terminal device-side architecture has the advantage of being able to perform local inference, reducing the latency of data upload and processing, and is particularly suitable for application scenarios that require real-time feedback (such as augmented reality, vehicle-to-everything).

[0096] As mentioned above, in communication systems, the location of a first node (e.g., a terminal device) can be determined based on a first model (e.g., an AI / ML model). During the localization process, model performance is evaluated by comparing the difference between the estimated location of the first node given by the first model and the ground truth. However, in practical applications, performance monitoring schemes based on ground truth face many challenges, which may limit the effectiveness of performance monitoring.

[0097] Taking the first node as the terminal device and the first model as the AI / ML model as an example, firstly, obtaining ground truth is costly. Accurate positioning of the terminal device requires high-precision positioning systems or hardware (such as Global Navigation Satellite System (GNSS) equipment or high-precision sensors), and the installation and maintenance costs of these devices are high. Especially in widely distributed device environments, deploying a large number of high-precision positioning systems incurs huge expenses. Secondly, the technical implementation is complex. Particularly in indoor or high-density urban environments, obtaining accurate ground truth is extremely difficult due to multipath effects, signal attenuation, and other factors. Furthermore, obtaining accurate ground truth in real-time is even more challenging when facing rapidly moving devices or dynamically changing environments. Additionally, ground truth-based solutions also have limitations in large-scale deployments. For a vast network, obtaining the ground truth for each user device in real-time is almost impossible, making it difficult to scale this method to monitoring all devices. Finally, in dynamic environments, such as high-speed device movement or frequent terrain and climate changes, obtaining stable and continuous ground truth data is extremely difficult. In such environments, the reliability of ground truth data is difficult to guarantee, making it unsuitable as a long-term, stable monitoring basis.

[0098] It is evident that ground truth-based performance monitoring schemes for AI / ML models may be difficult to implement in practical deployments. Therefore, ground truth-free monitoring schemes may be more applicable and practical. Monitoring the performance of AI / ML models in the absence of ground truth data is a challenge. To address this issue, relevant solutions propose using AI / ML models to predict physical quantities such as TOA (Time of Arrival), which are crucial for determining the location of terminal devices in traditional positioning schemes. Based on this, the performance of the AI / ML model can be evaluated by comparing the difference between the TOA predicted by the AI / ML model and the actual measured TOA. If the difference is significant, it may indicate a problem with the AI / ML model's performance. However, this approach also has several drawbacks.

[0099] First, differences in physical quantities such as TOA (Time of Arrival) are not directly related to the position estimation error of the terminal device given by the AI / ML model. Although TOA does affect the positioning results, its error does not always accurately reflect the final positioning error. Even with a small TOA deviation, the position information estimation of the AI / ML model may still have a large error. Therefore, changes in TOA are insufficient to fully capture the complexity of the model in generating the final position estimate. Second, in real-world scenarios, TOA data acquisition is easily affected by obstructions, especially under NLoS (Near-LoS) conditions, where signal reflection and refraction significantly increase the error in TOA measurement. Line-of-sight (LOS) conditions occur less frequently in many complex environments; therefore, the difference between the TOA predicted by the AI / ML model and the measured TOA may be more influenced by environmental factors, and this difference may not accurately reflect model performance. Furthermore, under NLoS conditions, complex signal paths further increase the error in TOA measurement. Although the AI / ML model may make adjustments in these complex environments, relying solely on TOA differences to evaluate model performance may ignore the influence of environmental factors, leading to inaccurate monitoring results. Physical quantities such as TOA (Time of Arrival) only represent a portion of the information in a positioning system and cannot fully reflect the completeness of the input data. Deviations in a single physical quantity are insufficient to measure the overall model performance in complex environments, especially in handling signal interference, device speed, and dynamic position changes. Finally, in dynamic scenarios, such as mobile devices or complex urban environments, TOA measurements may fluctuate significantly over time or with environmental changes. Even if the AI / ML model performance remains stable, TOA errors can lead to incorrect model failure assessments.

[0100] To address the aforementioned issues, this application provides a method for use in a node of a wireless communication system. In this method, a first node receives first information indicating multiple positioning estimates of the first node, and the first node can determine a reference position based on these multiple positioning estimates. The reference position is used to monitor the performance of a first model. On the one hand, compared to traditional performance monitoring schemes based on ground truth, monitoring the performance of the first model based on a reference position determined by multiple positioning estimates helps reduce the cost and complexity of acquiring real-world location data, thereby lowering the overall cost of maintaining and operating the positioning system.

[0101] On the other hand, compared with traditional performance monitoring schemes without ground truth, monitoring the performance of the first model based on reference positions determined by multiple positioning estimates helps to reduce the positioning error of the first model.

[0102] The method for wireless communication in a first node according to an embodiment of this application is described below with reference to FIG7. FIG7 is a schematic flowchart of the method for wireless communication in a first node according to an embodiment of this application. As shown in FIG7, the method is executed by the first node.

[0103] As an example, the first node can be a network-controlled repeater (NCR).

[0104] As an example, the first node can be a terminal device. For example, terminal devices 120a to 120j in Figure 1.

[0105] As an example, the first node can be a relay, such as a relay terminal.

[0106] The method shown in Figure 7 includes steps S710 to S720, which are described below.

[0107] In step S710, the first node receives the first information. For example, the first node may receive the first information sent by the second node.

[0108] As one embodiment of the above embodiments, the second node can be a network device. For example, the second node is an access network device or a core network device. Another example is a gNB. Yet another example is an LMF.

[0109] In some embodiments, the first information is used to indicate multiple location estimates of the first node.

[0110] As an example, the estimated location of the first node can be the estimated position of the first node.

[0111] As a sub-implementation of the above embodiments, the positioning estimate may be an estimate of the physical location of the first node, or in other words, the positioning estimate may be an estimate of the absolute location of the first node.

[0112] As a sub-implementation of the above embodiments, the positioning estimate includes at least one of the longitude estimate and the latitude estimate of the first node. For example, the positioning estimate includes the longitude estimate and the latitude estimate of the first node.

[0113] In some embodiments, multiple positioning estimates are determined based on the physical locations of multiple sets of transceiver nodes and measurement data for multiple sets of reference signals; in other words, the physical locations of multiple sets of transceiver nodes and measurement data for multiple sets of reference signals are used to determine multiple positioning estimates.

[0114] As an example, the transceiver nodes can be TRPs. For example, multiple transceiver nodes constitute multiple TRPs.

[0115] As a sub-implementation of the above embodiments, the TRP can be a base station or other device capable of transmitting and receiving wireless signals.

[0116] As an example, the transceiver nodes in a group of transceiver nodes can be randomly selected by the second node based on the report reported by the first node. For example, the first node is a terminal device, the second node is an LMF, and the LMF randomly selects three transceiver nodes to form a group of transceiver nodes based on the report reported by the terminal device.

[0117] In this embodiment, the number of transceiver nodes included in each group of transceiver nodes is not limited. In some embodiments, the number of transceiver nodes included in each group of transceiver nodes is the same. For example, there are 5 groups of transceiver nodes, and each group includes 3 transceiver nodes. In other embodiments, the number of transceiver nodes included in each group of transceiver nodes may be different. For example, there are 5 groups of transceiver nodes, the first and second groups of transceiver nodes include 3 transceiver nodes, the third and fourth groups of transceiver nodes include 4 transceiver nodes, and the fifth group of transceiver nodes includes 5 transceiver nodes.

[0118] As an example, the number of transceiver nodes in a group of transceiver nodes is greater than or equal to 3. For example, there are 5 groups of transceiver nodes, and each group of transceiver nodes includes 3 TRPs.

[0119] As an example, the physical location of multiple transceiver nodes can be the geographical location of multiple transceiver nodes.

[0120] As a sub-implementation of the above embodiments, the geographical location can be an absolute location.

[0121] As a sub-implementation of the above embodiments, the absolute location of the multiple sets of transceiver nodes includes at least one of the longitude and latitude of the multiple sets of transceiver nodes. For example, the physical location of the multiple sets of transceiver nodes includes the longitude and latitude of the multiple sets of transceiver nodes.

[0122] As an example, measurement data for multiple sets of reference signals can be understood as data obtained by measuring multiple sets of reference signals.

[0123] As an example, a reference signal is used for positioning.

[0124] As one embodiment, the reference signal includes a positioning reference signal (PRS). For example, the reference signal may be a downlink positioning reference signal (DL-PRS).

[0125] As an example, the reference signal includes a channel state information-reference signal (CSI-RS).

[0126] As one embodiment, the reference signal includes a sounding reference signal (SRS). For example, the reference signal could be an uplink sounding reference signal (UL-SRS).

[0127] As one example, the reference signal includes a newly defined reference signal.

[0128] As one example, multiple sets of reference signals come from multiple sets of transceiver nodes. For example, there are 5 sets of transceiver nodes, each set of transceiver nodes includes 3 TRPs, and each set of reference signals includes DL-PRS sent from the 3 TRPs of one set of transceiver nodes to the first node, for a total of 5 sets of DL-PRS.

[0129] As one embodiment, multiple sets of reference signals originate from reference signals transmitted by the first node to multiple sets of transceiver nodes. For example, the multiple sets of reference signals are multiple sets of UL-SRS.

[0130] In some embodiments, the first node receives second information, which indicates the physical locations of multiple sets of reference signals and multiple sets of transceiver nodes. For example, the first node receives second information transmitted by multiple sets of transceiver nodes.

[0131] As an example, the second information is carried in an RRC message.

[0132] As one embodiment of the above embodiments, the measurement data for multiple sets of reference signals can be one or more of the following: reference signal receiving power (RSRP); reference signal receiving quality (RSRQ); reference signal received signal-to-noise ratio (RSSNR); received signal strength indicator (RSSI); reference signal interference power (RSIP); received signal code power (RSCP); reference signal received path power (RSRPP); channel quality indicator (CQI); downlink time difference of arrival (DL-TDOA); uplink time difference of arrival (UL-TDOA); reference signal time difference (RSTD); reference time of arrival (RTOA); AoA; angle-of-departure (AoD); TOA; channel impulse response. Response (CIR); Observation arrival time difference (OATD); Time of flight (TOF); Transmission and reception time difference at the second node; Transmission and reception time difference at the first node.

[0133] As an example, the measurement data for multiple sets of reference signals is obtained by the first node. For instance, the reference signal is a PRS sent from the transceiver node to the first node. The first node receives multiple sets of PRS sent by the transceiver nodes, measures the multiple sets of PRS, and obtains the measurement data for the multiple sets of reference signals.

[0134] In some embodiments, the first node sends third information, which is used to indicate the physical information of multiple sets of transceiver nodes and the measurement data for multiple sets of reference signals. That is, the first node sends the physical information of multiple sets of transceiver nodes and the measurement data for multiple sets of reference signals to determine multiple positioning estimates.

[0135] As an example, the first node sends third information to the second node, that is, the second node receives the third information.

[0136] As an example, multiple positioning estimates are determined by the second node.

[0137] In some embodiments, the second node receives third information and determines multiple positioning estimates of the first node based on the physical locations of multiple sets of transceiver nodes and measurement data for multiple sets of reference signals.

[0138] In some embodiments, a set of transceiver nodes corresponds to at least one location estimate.

[0139] As an example, one set of transceiver nodes corresponds to one location estimate. For instance, the third information is used to indicate the physical locations of the five sets of transceiver nodes and the measurement data for the five sets of reference signals. The physical location of each set of transceiver nodes and the measurement data for each set of reference signals can be used to determine one location estimate, for a total of five location estimates.

[0140] As one example, a group of transceiver nodes corresponds to multiple positioning estimates. For instance, the third information is used to indicate the physical locations of 5 groups of transceiver nodes and measurement data for 5 sets of reference signals. The physical location of each group of transceiver nodes and the measurement data for each set of reference signals can be used to determine two positioning estimates, for a total of 10 positioning estimates.

[0141] As an example, the second node determines multiple location estimates using triangulation. For instance, triangulation is a technique commonly used in wireless positioning. For each set of reference signals, the measurement data consists of multiple RTOAs or AOAs. Based on these multiple RTOAs or AOAs and the physical location of each transceiver node in each set of transceiver nodes, multiple location estimates for the first node are determined.

[0142] As one example, the method by which the second node determines multiple positioning estimates is the multi-round-trip time (Multi-RTT) positioning method. For example, the reference signals are DL-PRS and UL-SRS, and the measurement data for each set of reference signals consists of multiple transmit / receive time differences on the first node side. The second node converts the multiple transmit / receive time differences on the first node side into distances based on the physical location of each transmit / receive node in each set of transmit / receive nodes, thereby determining multiple positioning estimates for the first node.

[0143] As an example, the method by which the second node determines multiple positioning estimates is the DL-TDOA positioning method. For example, the reference signal is DL-PRS, and the measurement data for each group of DL-PRS consists of multiple RSTDs. The second node converts the multiple RSTDs into distances based on the physical location of each transceiver node in each group of transceiver nodes, thereby forming a hyperbola. By solving the hyperbola equation, multiple positioning estimates of the first node are determined.

[0144] As an example, the method by which the second node determines multiple positioning estimates is the UL-TDOA positioning method. For example, the reference signal is UL-SRS, and the measurement data for each group of UL-SRS consists of multiple RTOAs. The second node converts the multiple RTOAs into distances based on the physical location of each transceiver node in each group, thereby forming a hyperbola. By solving the hyperbola equation, multiple positioning estimates of the first node are determined. In step S720, the first node determines its reference position based on the multiple positioning estimates.

[0145] As an example, the reference position of the first node is determined based on multiple positioning estimates. Therefore, the reference position of the first node in this embodiment can also be referred to as an "estimate of the ground truth".

[0146] Traditional positioning systems typically rely on a single or small number of transceiver nodes to determine the location of the first node. However, in complex environments, such as densely built-up urban areas or indoor locations with severe signal interference, this single-point positioning method may lead to inaccurate or unstable positioning results. As mentioned above, multiple positioning estimates are determined based on the positions of multiple transceiver nodes and measurement data for multiple sets of reference signals. These multiple sets of reference signals can be reference signals transmitted between multiple transceiver nodes and the first node. Therefore, it can be said that the reference position of the first node is determined based on multiple sets of transceiver nodes. Compared to traditional single-point positioning, this distributed method can collect signal data from multiple angles, which helps to improve the accuracy and reliability of positioning.

[0147] In some embodiments, the reference position of the first node is used to monitor the performance of the first model.

[0148] As an example, the first model can be an AI / ML model.

[0149] In this application embodiment, the AI / ML model is not limited. In some embodiments, the AI ​​model may include a deep learning model. For example, deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory networks (LSTM), generative adversarial networks (GAN), variational autoencoders (VAE), transformers, etc. In some embodiments, the ML model may include a model generated through machine learning or by the device itself. For example, deep reinforcement learning (DRL).

[0150] As a sub-implementation of the above embodiments, the first model can be a neural network. For example, the structure of the first model can be seen in Figure 5.

[0151] As a sub-implementation of the above embodiments, the neurons of the first model can be the neurons in Figure 4.

[0152] As a sub-implementation of the above embodiments, the first model may be the CNN in Figure 6.

[0153] As an example, the first model can be deployed on the first node side. For instance, the first node is a terminal device, and the second node is a network device. The first model is deployed on the terminal device side, i.e., the scenario in Case 1 above. The network device does not directly participate in the inference process of the first model. After collecting signal information, the terminal device autonomously calculates and generates a predicted location for itself. To ensure the positioning accuracy of the first model in different environments, a reference position is determined on the terminal device side based on multiple positioning estimates to optimize the performance of the first model. Deploying the first model on the terminal device side results in a fast system response speed and helps reduce the dependence of the positioning process on the network device side resources.

[0154] As an example, the first model can be deployed on the second node side. For instance, the second node is an access network device, and the first model is deployed on the access network device side.

[0155] In some embodiments, the reference position is used to monitor the performance of the first model. This can be understood as monitoring the performance of the first model based on the deviation between the reference position and the predicted position of the first node, where the predicted position is the output of the first model. For example, the reference position of the first node is... The predicted position of the first node is p. The deviation between the reference position and the predicted position of the first node is calculated using the formula... Determined, based on d Monitor the performance of the first model.

[0156] As an example, the first model is deployed on the first node side, and the first node monitors the performance of the first model.

[0157] As an example, the first model is deployed on the second node side, and the second node monitors the performance of the first model.

[0158] As a sub-implementation of the above embodiment, if the second node monitors the performance of the first model, the first node, after determining the reference position of the first node, sends the reference position of the first node to the second node so that the second node can monitor the performance of the first model.

[0159] As an example, the predicted position of the first node is the inference result of the first model, or the predicted position of the first node is the output result of the inference stage of the first model, or the first model is used to predict the position of the first node.

[0160] As a sub-implementation of the above embodiments, the predicted location of the first node is the physical location of the first node obtained through reasoning by the first model, or in other words, the predicted geographical location of the first node.

[0161] As a sub-implementation of the above embodiments, the predicted geographical location of the first node can be the predicted absolute location of the first node.

[0162] As a sub-implementation of the above embodiments, the predicted location of the first node includes at least one of the longitude and latitude of the first node. For example, the physical location of the first node includes the longitude and latitude of the first node.

[0163] In some embodiments, the first node measures K0 sets of reference signals, where K0 is a positive integer greater than or equal to K, and the measurement data for the K0 sets of reference signals is used to train the first model.

[0164] As an example, the measurement data for the K0 group of reference signals is used to train the first model. This can be understood as the measurement data for the K0 group of reference signals being the input to the training phase of the first model, used to train the parameters of the first model.

[0165] As an example, the values ​​of K0 and K can be determined at the training nodes of the first model.

[0166] In some embodiments, the first node receives K0 group of reference signals.

[0167] As an example, the K0 group of reference signals can be sent from one of the multiple groups of transceiver nodes mentioned above to the first node.

[0168] As an example, the K0 group of reference signals can also be sent from other transceiver nodes to the first node.

[0169] In some embodiments, the first node sends a K0 group of reference signals.

[0170] As an example, the K0 group of reference signals can be sent by the first node to the transceiver node among the multiple transceiver nodes mentioned above.

[0171] As an example, the K0 group of reference signals can also be sent by the first node to other transceiver nodes.

[0172] As an example, the performance of the first model is monitored in the following way: if the deviation between the predicted position and the reference position of the first node exceeds a preset threshold, the system can automatically determine that the performance of the current first model has deviated, and then trigger the corresponding adjustment mechanism.

[0173] As a sub-example of the above embodiments, the preset threshold can be flexibly set, which helps to improve the sensitivity and accuracy of performance monitoring of the first model, so that the positioning performance of the first model in practical applications can remain stable and efficient.

[0174] In some embodiments, measurement data of reference signals for multiple sets of transceiver nodes are input to the first model.

[0175] As one embodiment, measurement data of reference signals for multiple sets of transceiver nodes are used as input to the first model, which can be used to monitor the performance of the first model. For example, the first model is deployed on the second node side, and the measurement data of reference signals for multiple sets of transceiver nodes are used as input to the first model. At the same time, the physical locations of multiple sets of transceiver nodes are also used as input to the model. The first model determines multiple location estimates for the first node and sends these estimates to the first node. After the first node determines its reference location, it inputs the reference location into the first model, which is used to automatically monitor the performance of the first model during the inference phase.

[0176] As one embodiment, measurement data of reference signals from multiple sets of transceiver nodes can be used as input to a first model to determine the predicted location of the first node. For example, measurement data of reference signals from multiple sets of transceiver nodes can also be used as input to the first model during the inference phase to infer the predicted location of the first node.

[0177] To improve positioning accuracy, in some embodiments, a weight value is introduced for each positioning estimate, indicating the contribution of each estimate to the reference location. For example, the i-th positioning estimate among multiple positioning estimates... The corresponding weight is α i α i The larger, the better The greater the contribution to the reference position, the higher α becomes. i The smaller, The smaller the contribution to the reference position.

[0178] As an example, i is a positive integer. For instance, i can take the values ​​1, 2, 3, 4, and 5.

[0179] In some embodiments, the first node determines its reference position based on multiple positioning estimates. This can be understood as the reference position being obtained by weighted averaging of the multiple positioning estimates, or in other words, the reference position satisfies the formula... in, This is the reference position for the first node. Let α be the i-th location estimate among multiple location estimates. i The weight corresponds to the i-th location estimate. This ensemble method considers the reliability of location information provided by multiple transceiver nodes, helping to reduce errors that may be introduced by a single transceiver node.

[0180] As an example, the sum of the weights corresponding to multiple location estimates is 1. For instance, the first information indicates 5 location estimates for the first node, and the weight corresponding to the i-th location estimate is α. i Then the sum of the weights corresponding to the five location estimates satisfies the formula

[0181] As an example, the weight corresponding to each positioning estimate is a positive decimal less than or equal to 1.

[0182] In some embodiments, multiple positioning estimates are obtained based on multiple basic positioning units. A group of transceiver nodes constitutes a basic positioning unit, and a group of transceiver nodes includes multiple transceiver nodes. It can be understood that the i-th positioning estimate among the multiple positioning estimates is obtained based on the multiple transceiver nodes of the i-th basic positioning unit, or that the i-th positioning estimate is obtained based on the multiple transceiver nodes of the i-th group of transceiver nodes.

[0183] To more accurately reflect the impact of different positioning estimates on the reference position of the first node, the weights corresponding to each positioning estimate can be dynamically adjusted.

[0184] As an example, the weight corresponding to the current i-th positioning estimate is determined based on the reliability of the i-th positioning estimate. Accordingly, the higher the weight corresponding to the i-th positioning estimate, the higher the reliability of the i-th positioning estimate. For example, the reliability of the i-th positioning estimate can be determined based on measurement data of the reference signal of the i-th basic positioning unit, etc.

[0185] As an example, the reference signal of the i-th basic positioning unit can be understood as the reference signal transmitted between the multiple transceiver nodes included in the i-th basic positioning unit and the first node, or the i-th set of reference signals.

[0186] As an example, the measurement data of the reference signal of the i-th basic positioning unit can be understood as the measurement data of the reference signals transmitted between the multiple transceiver nodes included in the i-th basic positioning unit and the first node, or, in other words, the measurement data of the i-th set of reference signals. For example, the i-th basic positioning unit includes 3 TRPs, and the reference signal is UL-SRS. UL-SRS is the reference signal of the 3 TRPs sent by the first node to the i-th basic positioning unit, and the measurement data of the reference signal of the i-th basic positioning unit is RSRP measured based on UL-SRS. As another example, the reference signal is DL-PRS. DL-PRS is the reference signal of the 3 TRPs sent by the i-th basic positioning unit to the first node, and the measurement data of the reference signal of the i-th basic positioning unit is SINR measured based on DL-PRS.

[0187] In some embodiments, the weight corresponding to the current i-th positioning estimate is determined based on one or more of the following: the weight corresponding to the historical i-th positioning estimate; measurement data of the reference signal of the i-th basic positioning unit; configuration information of the i-th basic positioning unit; geometric features of the i-th basic positioning unit; and positioning accuracy of the i-th basic positioning unit. This weighting strategy ensures that the positioning system can dynamically adjust its dependence on each positioning estimate based on the measurement data of the reference signal of the basic positioning unit and other relevant factors, thus helping to optimize positioning accuracy.

[0188] As an example, the weight corresponding to the i-th historical positioning estimate can be understood as the weight corresponding to the i-th multiple positioning estimates at one or more times before the current time.

[0189] As a sub-implementation of the above embodiments, if the first node periodically updates the weight corresponding to the i-th positioning estimate, then the weight corresponding to the historical i-th positioning estimate can be the weight corresponding to the i-th positioning estimate at one or more fixed time intervals prior to the current time. For example, if the first node is expected to update the weight corresponding to the i-th positioning estimate at time t+Δt, then the weight corresponding to the historical i-th positioning estimate can be the weight corresponding to the i-th positioning estimate at time t and / or the weight corresponding to the i-th positioning estimate at time t-Δt.

[0190] As an example, the configuration information of the i-th basic positioning unit may be the configuration information of the multiple transceiver nodes included in the i-th basic positioning unit.

[0191] As a sub-implementation of the above embodiments, the configuration information of the transceiver node can be the device model of the transceiver node. For example, if the transceiver node is a TRP, the configuration information of the transceiver node is the device model of the TRP.

[0192] As an example, the geometric feature of the i-th basic positioning unit can be the area of ​​the i-th basic positioning unit.

[0193] As a sub-implementation of the above embodiments, the area of ​​the i-th basic positioning unit can be the area of ​​the region formed by the multiple transceiver nodes included in the i-th basic positioning unit. For example, the i-th basic positioning unit includes 3 TRPs, and the area of ​​the i-th basic positioning unit is the area of ​​the triangular region formed by the 3 TRPs.

[0194] As a sub-implementation of the above embodiments, the area of ​​the i-th basic positioning unit can be indicated by the first information. For example, the area of ​​the i-th basic positioning unit can be indicated by the first information sent by the second node. For instance, the second node is a network device, the first node is a terminal device, and the i-th basic positioning unit includes 3 TRPs. The network device sends the first information to the terminal device, and the first information can indicate the area of ​​the triangular region formed by the 3 TRPs included in the i-th basic positioning unit among multiple basic positioning units.

[0195] As a sub-implementation of the above embodiments, the area of ​​the i-th basic positioning unit can be determined based on the physical locations of the i-th group of transceiver nodes obtained by the first node. For example, the second node is a network device, the first node is a terminal device, and the i-th basic positioning unit includes 3 TRPs. The i-th basic positioning unit sends the physical locations of its 3 TRPs to the terminal device through second information. After receiving the information, the terminal device reports third information to the network device. The third information includes the physical locations of the 3 TRPs included in the i-th basic positioning unit. Based on the physical locations of the 3 TRPs included in the i-th basic positioning unit, the network device can determine the area of ​​the i-th basic positioning unit.

[0196] As an example, the positioning accuracy of the i-th basic positioning unit can be the absolute value of the difference between the i-th positioning estimate obtained by the i-th basic positioning unit and the reference position of the first node. For example, the i-th positioning estimate obtained by the i-th basic positioning unit... The reference position of the first node is The smaller the value, the higher the positioning accuracy and the better the positioning effect of the i-th basic positioning unit. The larger the value, the lower the positioning accuracy and the worse the positioning effect of the i-th basic positioning unit.

[0197] In some embodiments, the weights corresponding to multiple positioning estimates can be dynamically adjusted; that is, the weights corresponding to the i-th positioning estimate at multiple times can be determined based on one or more of the above.

[0198] As an example, the weight corresponding to the i-th positioning estimate at the initial time can be determined. Then, the weight corresponding to the current i-th positioning estimate mentioned above can be understood as the weight corresponding to the i-th positioning estimate at the initial time, or the initial value of the weight corresponding to the i-th positioning estimate.

[0199] As a sub-implementation of the above embodiments, the initial time can be the start time of the positioning process based on the first model to predict the position of the first node.

[0200] As a sub-implementation of the above embodiments, the initial value of the weight corresponding to the i-th positioning estimate is determined based on one or more of the following: measurement data of the reference signal of the i-th basic positioning unit; configuration information of the i-th basic positioning unit; and geometric features of the i-th basic positioning unit.

[0201] As a sub-implementation of the above embodiments, the initial value of the weight corresponding to the i-th positioning estimate is based on the measurement data of the reference position of the i-th basic positioning unit. For example, the i-th basic positioning unit includes 3 TRPs, and the initial value of the weight corresponding to the i-th positioning estimate is determined based on the RSRP measured by the reference signal transmitted between the first node and the 3 TRPs at the initial time.

[0202] As a sub-implementation of the above embodiments, the configuration information of the i-th basic positioning unit is the number of basic positioning units, and the initial value of the weight corresponding to the i-th positioning estimate is determined based on the number of basic positioning units.

[0203] As a sub-implementation of the above embodiment, the initial value of the weight corresponding to the i-th localization estimate satisfies Where, α i This is the initial value of the weight corresponding to the i-th location estimate, where N is the number of basic positioning units. In other words, the initial value of the weight corresponding to each location estimate is the same. For example, if the first information indicates 5 location estimates, and the i-th location estimate is obtained based on the i-th basic positioning unit, the initial value of the weight corresponding to each location estimate is the same, which is 0.2. Setting the same initial value for the weight corresponding to each location estimate ensures fair comparison at the beginning.

[0204] As an example, the weight corresponding to the current i-th positioning estimate can be the weight corresponding to the i-th positioning estimate at any time other than the initial time, or in other words, the weight corresponding to the updated i-th positioning estimate. Dynamically updating the weight corresponding to the i-th positioning estimate after the initial time more accurately reflects the impact of the i-th positioning estimate on the positioning result at different times.

[0205] As a sub-implementation of the above embodiment, the first node can periodically adjust the weights corresponding to multiple positioning estimates. For example, the first node updates the weights corresponding to multiple basic positioning units every Δt time interval. By periodically updating the weight values, the first model can adapt to changes in the environment.

[0206] As an example, the weight corresponding to the updated i-th positioning estimate is determined based on the positioning accuracy of the i-th basic positioning unit. For instance, the historical positioning estimate obtained based on the i-th basic positioning unit is... The reference position of the first historical node is A smaller value indicates a higher positioning accuracy for the i-th basic positioning unit in history. Therefore, the weight α corresponding to the current i-th positioning estimate can be increased. i .

[0207] In some embodiments, the weight corresponding to the i-th positioning estimate at time t+Δt satisfies the formula... Where, α′ i (t+Δt) represents the weight corresponding to the i-th positioning estimate at time t+Δt, Δt is the weight update time interval, and α i (t) represents the weight corresponding to the i-th positioning estimate at time t, β, γ, and δ are smoothing factors, and RSSI is... avg,i (t) represents the average received RSSI and SNR of the i-th basic positioning unit at time t. avg,i (t) represents the average SNR of the i-th basic positioning unit at time t. i (t) represents the area of ​​the i-th basic positioning unit at time t, and S represents the total number of basic positioning units at time t. Let be the sum of the RSSIs of the S basic positioning units at time t. Let S be the sum of the SNRs of the S basic positioning units at time t. Let S be the sum of the areas of the S basic positioning units at time t.

[0208] As an example, Δt is the weight update time interval, which can be understood as the frequency at which the first node updates the weights corresponding to multiple positioning estimates once every Δt.

[0209] As a sub-implementation of the above embodiment, the time for updating the weights corresponding to the multiple location estimates can be an integer multiple of Δt. For example, the last update time for the weights corresponding to the multiple location estimates was t, satisfying t = kΔt, where k is a non-negative integer. The current update time for the weights corresponding to the multiple location estimates is t + Δt, satisfying t + Δt = (k + 1)Δt.

[0210] As a sub-implementation of the above embodiment, the total time for updating the weights corresponding to multiple location estimates can be an integer multiple of Δt. For example, the total time for updating the weights corresponding to multiple location estimates is T, satisfying T = NΔt, where N is the total number of updates, and its value is a non-negative integer.

[0211] As an example, α i (t) represents the weight corresponding to the i-th positioning estimate at time t, which can be understood as the weight corresponding to the i-th positioning estimate at historical time t.

[0212] As an example, β, γ, and δ are used to smooth changes in weight values.

[0213] As a sub-example of the above embodiment, the values ​​of β, γ and δ are in the range of (0,1), that is, β, γ and δ are decimals greater than 0 and less than 1.

[0214] As a sub-example of the above embodiment, β is the influence coefficient of the weight corresponding to the i-th historical positioning estimate.

[0215] As a sub-example of the above embodiment, γ and δ control the influence ratio of the RSSI and SNR of the historical i-th basic localization unit on the weight, respectively, to ensure that the weight accurately reflects the influence of the network state and geometric features of the i-th basic localization unit.

[0216] As an example, RSSI avg,i (t) represents the average RSSI of the i-th basic positioning unit at time t, which can be understood as RSSI avg,i (t) represents the average RSSI measured based on the reference signals transmitted between the multiple transceiver nodes of the i-th basic positioning unit and the first node at time t. For example, the first basic positioning unit at time t includes three TRPs, namely TRP1, TRP2, and TRP3. The first node measures the RSSI based on the reference signals transmitted by the three TRPs respectively, and calculates the average of the three measured RSSIs to obtain the RSSI of the first basic positioning unit at time t. avg,1 (t).

[0217] As an example, SNR avg,i (t) represents the average SNR of the i-th basic positioning unit at time t, which can be understood as SNR avg,i (t) represents the average SNR measured based on the reference signals transmitted between the multiple transceiver nodes of the i-th basic positioning unit and the first node at time t. For example, the first basic positioning unit at time t includes three TRPs, namely TRP1, TRP2, and TRP3. The first node measures the SNR based on the reference signals transmitted by the three TRPs respectively, and calculates the average of the three measured SNRs to obtain the SNR of the first basic positioning unit at time t. avg,i (t).

[0218] As an example, Area i (t) represents the area of ​​the i-th basic localization unit at time t, which can be understood as Area i Area1(t) is the area of ​​the region formed by the multiple transceiver nodes of the i-th basic positioning unit at time t, used to reflect the impact of the geometric distribution of the transceiver nodes on positioning accuracy. For example, the first basic positioning unit at time t includes three TRPs, namely TRP1, TRP2 and TRP3, and Area1(t) is the area of ​​the triangular region formed by TRP1, TRP2 and TRP3 at time t.

[0219] As an example, S is the total number of basic positioning units at time t, or in other words, S is the number of positioning estimates.

[0220] As a sub-implementation of the above embodiment, the first information received by the first node indicates S. Exemplarily, S may be indicated by the second node to the first node via the first information.

[0221] As an example, Let be the sum of the RSSIs of the S basic positioning units at time t. For example, if the total number of basic positioning units S at time t is 5, then the average RSSI of the j-th basic positioning unit at time t is RSSI. avg,j (t), j = 0, 1, 2, 3, 4, 5. The sum of the average RSSI of the 5 basic positioning units at time t satisfies the formula

[0222] As an example, Let S be the sum of the average SNR of the S basic positioning units at time t. For example, if the total number of basic positioning units S at time t is 5, then the average SNR of the j-th basic positioning unit at time t is SNR. avg,j (t), j = 0, 1, 2, 3, 4, 5. The sum of the average SNR of the 5 basic positioning units at time t satisfies the formula

[0223] As an example, Let be the sum of the areas of the S basic localization units at time t. For example, if the total number of basic localization units S at time t is 5, and the area of ​​the j-th basic localization unit at time t is Areaj(t), j = 0, 1, 2, 3, 4, 5. The sum of the areas of the 5 basic localization units at time t satisfies the formula...

[0224] To ensure that the sum of the weights corresponding to all positioning estimates is 1, they need to be normalized. In some embodiments, before determining the reference position of the first node based on multiple positioning estimates, or in other words, after determining the weights corresponding to the current multiple basic positioning units, the first node normalizes the weights corresponding to the current positioning estimates.

[0225] In some embodiments, by formula The weight α′ corresponding to the i-th positioning estimate at time t+Δt i (t+Δt) is normalized; where Δt is the weight update time interval, S is the total number of location estimates, and α is the weights. i (t+Δt) represents the weight corresponding to the i-th positioning estimate at time t+Δt. It is the sum of the weights corresponding to the S location estimates.

[0226] As an example, the weight α corresponding to the i-th positioning estimate at time t+Δt can be used. i (t+Δt), determine the reference position of the first node. For example, the estimated position of the i-th node at time t+Δt is... Then the reference position at time t+Δt can satisfy the formula Where S is the total number of location estimates. Let α be the reference position at time t+Δt. i (t+Δt) represents the weight corresponding to the i-th positioning estimate at time t+Δt.

[0227] The method described above for determining the weights corresponding to the current i positioning estimates is applicable when the multiple basic positioning units used to obtain multiple positioning estimates do not change. In some scenarios, multiple basic positioning units will be adjusted. For example, the first node moves to a new location, a new TRP is selected to form a new basic positioning unit, and the second node will obtain positioning estimates based on the new basic positioning unit. For instance, at time t, the total number of basic positioning units used to obtain multiple positioning estimates is S. At the next time t+Δt, K original basic positioning units are removed, and M new basic positioning units are added. That is, the number of basic positioning units at the next time is (S-K+M), which includes (S-K) original basic positioning units and M newly added basic positioning units.

[0228] As a sub-implementation of the above embodiments, the adjustment of multiple basic positioning units used to obtain multiple positioning estimates can be understood as a change in the number of basic positioning units used to obtain multiple positioning estimates and / or a change in the number of basic positioning units. For example, referring to Figure 8, a basic positioning unit includes multiple transceiver nodes, which are TRPs. At time t, a total of 5 basic positioning units are used to obtain positioning estimates, namely U1, U2, U3, U4, and U5. Each basic positioning unit includes the same number of TRPs, namely 3: U1 includes TRP0, TRP1, and TRP2; U2 includes TRP0, TRP1, and TRP3; U3 includes TRP1, TRP2, and TRP3; U4 includes TRP1, TRP3, and TRP4; and U5 includes TRP2, TRP3, and TRP4. At time t+Δt, the number of basic positioning units used to obtain positioning estimates is reduced to 3, namely U1, U2, and U5. Therefore, it can be determined that the adjustment of multiple basic positioning units used to obtain multiple positioning estimates has occurred. For example, referring to Figure 8, the transceiver node is TRP. At time t, the number of basic positioning units used to obtain the positioning estimate is 5, namely U1, U2, U3, U4, and U5. Each basic positioning unit includes the same number of TRPs, namely 3: U1 includes TRP0, TRP1, and TRP2; U2 includes TRP0, TRP1, and TRP3; U3 includes TRP1, TRP2, and TRP3; U4 includes TRP1, TRP3, and TRP4; and U5 includes TRP2, TRP3, and TRP4. At time t+Δt, the number of basic positioning units originally used to obtain the positioning estimate is reduced to 3, namely U1, U2, and U5, and 3 new basic positioning units, U6, U7, and U8, are added. Therefore, it can be determined that the multiple basic positioning units used to obtain multiple positioning estimates have been adjusted.

[0229] To accommodate scenarios where multiple basic positioning units (BRPs) are adjusted, it is necessary to adjust the weights of the original BRPs and assign weights to the positioning estimates obtained based on the new BRPs. In some embodiments, if multiple BRPs used to obtain multiple positioning estimates are adjusted, the weights corresponding to the multiple positioning estimates are determined based on one or more of the following: the number of BRPs before the adjustment; the number of newly added BRPs after the adjustment; the number of BRPs reduced from the original BRPs; and the weights corresponding to the historical positioning estimates obtained based on the remaining BRPs from the original BRPs.

[0230] As an example, the number of basic positioning units before adjustment can be understood as the number of basic positioning units included in the multiple basic positioning units used to obtain multiple positioning estimates before the adjustment. For example, referring to Figure 8, at time t, a total of 5 basic positioning units were used to obtain 5 positioning estimates, namely U1, U2, U3, U4, and U5. At time t+Δt, the number of basic positioning units used to obtain multiple positioning estimates at time t is reduced to 3, namely U1, U2, and U5. Therefore, the number of basic positioning units before adjustment is 5.

[0231] As an example, the number of newly added basic positioning units after adjustment can be understood as the number of basic positioning units that were not among the original basic positioning units after the adjustment of the multiple basic positioning units used to obtain multiple positioning estimates. For example, referring to Figure 8, at time t, a total of 5 basic positioning units were used to obtain 5 positioning estimates, namely U1, U2, U3, U4, and U5. At time t+Δt, the number of basic positioning units originally used to obtain multiple positioning estimates at time t is reduced to 3, namely U1, U2, and U5, and 3 new basic positioning units are added to obtain multiple positioning estimates, U6, U7, and U8. U6, U7, and U8 are not among the 5 basic positioning units used to obtain multiple positioning estimates at time t before the adjustment. Therefore, the number of newly added basic positioning units after adjustment is 3.

[0232] As an example, the number of basic positioning units reduced from the multiple basic positioning units before adjustment can be understood as the number of basic positioning units that are not in the multiple basic positioning units after adjustment, which were used to obtain multiple positioning estimates. For example, referring to Figure 8, at time t, a total of 5 basic positioning units were used to obtain 5 positioning estimates, namely U1, U2, U3, U4, and U5. At time t+Δt, the number of basic positioning units originally used to obtain multiple positioning estimates at time t is reduced to 3, namely U1, U2, and U5, a reduction of 2. Therefore, the number of basic positioning units reduced from the multiple basic positioning units before adjustment is 2.

[0233] As an example, the weights corresponding to the historical positioning estimates obtained based on the remaining basic positioning units among the multiple basic positioning units before adjustment can be understood as the weights corresponding to the positioning estimates obtained based on the basic positioning units that are still in the multiple basic positioning units after adjustment, before the adjustment of the multiple basic positioning units used to obtain multiple positioning estimates. For example, referring to Figure 8, at time t, a total of 5 basic positioning units were used to obtain 5 positioning estimates, namely U1, U2, U3, U4 and U5. At time t+Δt, the number of basic positioning units used to obtain multiple positioning estimates at time t is reduced to 3, namely U1, U2 and U5. Then, the remaining basic positioning units among the 5 basic positioning units before adjustment are U1, U2 and U5. The weights corresponding to the historical positioning estimates obtained based on the remaining 3 basic positioning units among the 5 basic positioning units before adjustment are the weights corresponding to the 3 positioning estimates obtained based on U1, U2 and U5 respectively before time t+Δt (such as α1(t), α2(t) and α5(t)).

[0234] In some embodiments, based on the remaining i-th basic positioning unit among the multiple basic positioning units before adjustment, the weight corresponding to the i-th positioning estimate at time t+Δt satisfies the formula... Where, α i (t+Δt) represents the weight corresponding to the i-th positioning estimate at time t+Δt, Δt is the weight update time interval, S is the number of basic positioning units before adjustment, K is the number of basic positioning units reduced from the multiple basic positioning units before adjustment, M is the number of newly added basic positioning units after adjustment, q is the sum of the weights corresponding to the positioning estimates obtained based on the remaining basic positioning units from the multiple basic positioning units before adjustment at time t, and α i (t) represents the weight corresponding to the i-th positioning estimate obtained at time t based on the i-th remaining basic positioning unit among the multiple basic positioning units before adjustment. For example, to assign initial weights to the positioning estimates obtained based on the M newly added basic positioning units after adjustment, it is necessary to proportionally reduce the weights corresponding to the positioning estimates obtained based on the remaining (S-K) basic positioning units among the S basic positioning units before adjustment. Assuming the sum of the weights corresponding to the positioning estimates obtained based on the remaining (S-K) basic positioning units is q, firstly, the sum of the (S-K) weight values ​​at time t is amplified to 1, and the i-th weight α among the (S-K) weight values... i (t) through the formula Expand, the expanded (S-K) The sum is It remains 1; secondly, it decreases at the next time t+Δt. The reduction ratio is Then the i-th weight value in the reduced time t+Δt (S―K) is

[0235] To facilitate understanding, the following section, with reference to Figure 8, illustrates a method for obtaining the weight corresponding to the i-th positioning estimate at time t+Δt based on the remaining i-th basic positioning unit among multiple basic positioning units before adjustment.

[0236] Referring to Figure 8, at time t, five basic positioning units are used to obtain five positioning estimates, namely U1, U2, U3, U4, and U5. At time t+Δt, the number of basic positioning units originally used at time t to obtain multiple positioning estimates is reduced to three, namely U1, U2, and U5, and three new basic positioning units are added to obtain multiple positioning estimates, U6, U7, and U8. Therefore, S takes the value of 5, K takes the value of 2, M takes the value of 3, and q takes the value of q by satisfying q=α1(t)+α2(t)+α5(t), which can then be expressed by the formula... The weights corresponding to the positioning estimates obtained based on U1 at time t+Δt are determined as follows: Through formula The weights corresponding to the positioning estimates obtained based on U2 at time t+Δt are determined as follows: Through formula The weights corresponding to the positioning estimates obtained based on U5 at time t+Δt are determined as follows:

[0237] In some embodiments, based on the newly added j-th basic positioning unit after adjustment, the weight corresponding to the j-th positioning estimate at time t+Δt satisfies the formula Where αj(t+Δt) is the weight corresponding to the j-th positioning estimate at time t+Δt, Δt is the weight update time interval, S is the number of basic positioning units before adjustment, K is the number of basic positioning units reduced from the multiple basic positioning units before adjustment, and M is the number of basic positioning units added after adjustment. For example, to assign initial weights to positioning estimates obtained based on the M newly added basic positioning units after adjustment, it is necessary to proportionally reduce the weights corresponding to the positioning estimates obtained from the remaining (S-K) basic positioning units from the original S basic positioning units. Assuming the sum of the weights corresponding to the positioning estimates obtained from the remaining (S-K) basic positioning units is q, firstly, the sum of the (S-K) weight values ​​at time t is amplified to 1, and the i-th weight α among the (S-K) weight values ​​is... i (t) through the formula Expand, the expanded (S-K) The sum is It remains 1; secondly, it decreases at the next time t+Δt. The reduction ratio is Then the i-th weight value in the reduced time t+Δt (S―K) is The M newly added basic localization units need to be assigned uniform initial weights. The initial weight of each newly added basic localization unit is: The sum of the adjusted weights is obtained through the formula The verification result is still 1.

[0238] To facilitate understanding, the following section, with reference to Figure 8, illustrates the method for obtaining the weight corresponding to the j-th positioning estimate at time t+Δt based on the newly added j-th basic positioning unit after adjustment.

[0239] Referring to Figure 8, at time t, a total of 5 basic positioning units are used to obtain 5 positioning estimates, namely U1, U2, U3, U4, and U5. At time t+Δt, the number of basic positioning units originally used at time t to obtain multiple positioning estimates is reduced to 3, namely U1, U2, and U5, and 3 new basic positioning units are added to obtain positioning estimates, U6, U7, and U8. Therefore, S takes the value of 5, K takes the value of 2, M takes the value of 3, and q is determined by the formula q=α1(t)+ α2(t)+α5(t) are determined, and then the weight corresponding to the positioning estimate obtained based on U6 at time t+Δt is determined to be 1 / 6 by the formula α6(t+Δt)=1 / (5―2+3), the weight corresponding to the positioning estimate obtained based on U7 at time t+Δt is determined to be 1 / 6 by the formula α7(t+Δt)=1 / (5―2+3), and the weight corresponding to the positioning estimate obtained based on U8 at time t+Δt is determined to be 1 / 6 by the formula α8(t+Δt)=1 / (5―2+3).

[0240] In some embodiments, during the process of the first node predicting its position based on the first model, the second node sends first information to the first node multiple times to update multiple location estimates. Correspondingly, the first node determines the weights corresponding to the current multiple location estimates multiple times. Therefore, the method for determining the reference position of the first node described above can be understood as an iterative process to adapt to changes such as the movement of the first node and changes in network conditions.

[0241] In some embodiments, the above method dynamically adjusts the weights corresponding to multiple localization estimates, enabling the system to adapt to changes in the environment and enhance the adaptability of the first model in complex scenarios. Therefore, the above method can also be called an "adaptive weight update mechanism".

[0242] To ensure the stable performance of the first model in a real-world environment, in some embodiments, the first node can use the aforementioned adaptive weight update mechanism to dynamically generate a reference position for the first node. Then, the performance of the first model is dynamically monitored by comparing the position of the first node predicted by the first model with the reference position.

[0243] As a sub-implementation of the above embodiments, if the deviation between the position of the first node predicted by the first model and the reference position exceeds a preset threshold, the system can automatically determine that the performance of the current first model has deviated, thereby triggering a corresponding adjustment mechanism to retrain or optimize the parameters of the first model, which helps to improve the prediction accuracy of the first model in different scenarios.

[0244] For ease of understanding, the method for determining the reference position of the first node provided by the embodiments of this application is illustrated below with reference to Figure 9. Figure 9 includes steps S910 to S990.

[0245] Assuming the first node is a terminal device and the second node is a network device, the first model is deployed on the terminal device side. The network device sends first information to the terminal device, indicating five location estimates for the terminal device. The number of basic positioning units used to obtain the five location estimates is five, where the i-th basic positioning unit uses U... i This indicates that i takes the value of an integer from 1 to 5, and each basic positioning unit includes 3 TRPs.

[0246] In step S910, the terminal device determines the initial weight values ​​corresponding to multiple positioning estimates.

[0247] The terminal device iterates through all possible values ​​of i, based on U. i The obtained i-th localization estimate The corresponding weight α i Set an initial value, namely α. i (t).

[0248] In step S920, the terminal device receives second information sent by the basic positioning unit, the second information indicating multiple sets of reference signals.

[0249] At time t, the terminal device iterates through all values ​​of i and measures U. i The reference signals transmitted between the three TRPs and the terminal device are used to obtain U. i The three AOA, RSSI, and SNR, and based on U i The three RSSI and SNR were calculated to obtain U i The average RSSI and average SNR, respectively, are calculated using RSSI. avg,i (t) and SNR avg,i (t) represents.

[0250] In step S930, the terminal device receives second information sent by the basic positioning unit, the second information indicating the physical location of the TRP of the multiple basic positioning units.

[0251] The terminal device iterates through all possible values ​​of i, via U i The second message sent to obtain U i The physical location of the TRP.

[0252] In step S940, the network device receives third information sent by the terminal device.

[0253] The third information indicates the physical location of the TRP of the five basic positioning units and the AOA measured from the reference signals of the five basic positioning units. Upon receiving the third information, the network device iterates through all values ​​of i and uses the i-th basic positioning unit U... i Given the physical locations of the three TRPs, calculate the i-th basic positioning unit U. i The area, using Area i (t) represents.

[0254] In step S950, the network device determines multiple location estimates. The network device iterates through all values ​​of i and uses triangulation, combining the AOA measured from the reference signal for the i-th basic positioning unit with the physical locations of the three TRPs of the i-th basic positioning unit, to calculate U. i Corresponding positioning estimate

[0255] In step S960, the network device sends the first information to the terminal device.

[0256] The first information sent by the network device to the terminal device indicates the area of ​​five location estimates and five basic location units.

[0257] In step S970, the terminal device determines the weights corresponding to the updated multiple positioning estimates and performs normalization processing.

[0258] After receiving the first information, the terminal device iterates through all possible values ​​of i and measures U according to step S920. i RSSI avg,i (t) and SNR avg,i (t), and the Area indicated by the first information i (t), through the formula Determine the i-th positioning estimate at time t+Δt. The corresponding weight α′ i (t+Δt), α i(t) represents the initial weight value corresponding to the i-th positioning estimate at time t, and is determined by the formula... For α′ i (t+Δt) is normalized to ensure that the sum of the weights corresponding to the five positioning estimates is 1.

[0259] In step S980, the terminal device determines the reference position of the terminal device.

[0260] Based on the data obtained from 5 basic positioning units and α i (t+Δt), through the formula Calculate the reference position of the terminal device at time t+Δt.

[0261] In step S990, the terminal device monitors the performance of the first model.

[0262] At time t+Δt, the predicted position of the terminal device is P(t+Δt), and the deviation between the predicted position and the reference position is expressed by the formula... Determined, through judgment Determine the performance of the first model by checking whether it exceeds a preset threshold.

[0263] In some embodiments, the first node receives first configuration information, which is used to indicate a first model. Exemplarily, the first configuration information is sent from the second node to the first node. For example, the first model is deployed on the second node's side, and the second node indicates the first model to the first node.

[0264] As an example, the first configuration information is used to indicate the parameters of the first model.

[0265] As one embodiment, the first configuration information is used to indicate the update of the parameters of the first model. Accordingly, upon receiving the first configuration information, the first node can determine that the weights corresponding to multiple positioning estimates need to be updated to update the reference position of the first node used to monitor the first model.

[0266] The method embodiments of this application have been described in detail above with reference to Figures 1 to 9. The apparatus embodiments of this application will be described in detail below with reference to Figures 10 to 12. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be referred to the preceding method embodiments.

[0267] Figure 10 illustrates a first node for wireless communication provided in an embodiment of this application. As shown in Figure 10, the first node 1000 includes a first transceiver 1010.

[0268] A first transceiver 1010 is configured to receive first information, the first information indicating multiple positioning estimates of the first node; and determine a reference position of the first node based on the multiple positioning estimates; wherein the reference position is used to monitor the performance of the first model.

[0269] In some embodiments, the first node further includes: the first transceiver 1010 is further configured to receive second information, the second information being used to indicate the physical locations of multiple sets of reference signals and multiple sets of transceiver nodes; the first transceiver 1010 is further configured to transmit third information, the third information being used to indicate the physical locations of the multiple sets of transceiver nodes and measurement data for the multiple sets of reference signals; wherein the physical locations of the multiple sets of transceiver nodes and the measurement data for the multiple sets of reference signals are used to determine the multiple positioning estimates.

[0270] In some embodiments, the reference position is used to monitor the performance of the first model, including: monitoring the performance of the first model based on the deviation between the reference position and the predicted position of the first node, wherein the predicted position is the output of the first model.

[0271] In some embodiments, the measurement data for the reference signals of the plurality of transceiver nodes is the input to the first model.

[0272] In some embodiments, the reference position satisfies the formula in, The reference position is... Let α be the i-th location estimate among the plurality of location estimates. i Let be the weight corresponding to the i-th location estimate, where i is a positive integer.

[0273] In some embodiments, the weight corresponding to the current i-th positioning estimate is determined based on one or more of the following: the weight corresponding to the historical i-th positioning estimate; the measurement data of the reference signal of the i-th basic positioning unit; the geometric features of the i-th basic positioning unit; the positioning accuracy of the i-th basic positioning unit; wherein a group of transceiver nodes constitutes a basic positioning unit.

[0274] In some embodiments, the first node further includes: the first transceiver 1010 is further configured to receive K0 sets of reference signals, where K0 is a positive integer greater than or equal to K; wherein measurement data for the K0 sets of reference signals is used to train the first model.

[0275] In some embodiments, the first node further includes: the first transceiver 1010 is further configured to receive first configuration information, the first configuration information being used to indicate the first model.

[0276] Figure 11 illustrates a second node for wireless communication provided in an embodiment of this application. As shown in Figure 11, the second node 1100 includes a second transceiver 1110.

[0277] The second transceiver 1110 is used to transmit first information, which indicates multiple positioning estimates of the first node, the multiple positioning estimates being used to determine a reference position of the first node; wherein the reference position is used to monitor the performance of the first model.

[0278] In some embodiments, the second node further includes: the second transceiver 1110 is also configured to receive third information, the third information being used to indicate the physical locations of multiple sets of transceiver nodes and measurement data for the multiple sets of reference signals.

[0279] In some embodiments, the reference position is used to monitor the performance of the first model, including: monitoring the performance of the first model based on the deviation between the reference position and the predicted position of the first node, wherein the predicted position is the output of the first model.

[0280] In some embodiments, the measurement data for the reference signals of the plurality of transceiver nodes is the input to the first model.

[0281] In some embodiments, the second node further includes: a second processor, configured to determine multiple positioning estimates of the first node based on the physical locations of the multiple sets of transceiver nodes and measurement data for the multiple sets of reference signals; wherein each set of transceiver nodes corresponds to at least one positioning estimate.

[0282] In some embodiments, the reference position satisfies the formula in, The reference position is... Let α be the i-th location estimate among the plurality of location estimates. i Let be the weight corresponding to the i-th location estimate, where i is a positive integer.

[0283] In some embodiments, the weight corresponding to the current i-th positioning estimate is determined based on one or more of the following: the weight corresponding to the historical i-th positioning estimate; the measurement data of the reference signal of the i-th basic positioning unit; the configuration information of the i-th basic positioning unit; the geometric features of the i-th basic positioning unit; and the positioning accuracy of the i-th basic positioning unit; wherein a group of transceiver nodes constitutes a basic positioning unit.

[0284] In some embodiments, the second node further includes: the second transceiver 1110 is also configured to send first configuration information, the first configuration information being used to indicate the first model.

[0285] In an optional embodiment, the first transceiver 1010 may be a transceiver 1230. The first node 1000 may also include a processor 1210 and a memory 1220, as shown in FIG12.

[0286] In an optional embodiment, the second transceiver 1110 may be a transceiver 1230. The second node 1100 may also include a processor 1210 and a memory 1220, as shown in FIG12.

[0287] Figure 12 is a schematic structural diagram of a communication device according to an embodiment of this application. The dashed lines in Figure 12 indicate that the unit or module is optional. This device 1200 can be used to implement the methods described in the above method embodiments. Device 1200 can be a chip, a terminal device, or a network device.

[0288] Apparatus 1200 may include one or more processors 1210. The processor 1210 may support apparatus 1200 in implementing the methods described in the preceding method embodiments. The processor 1210 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0289] The apparatus 1200 may further include one or more memories 1220. The memories 1220 store a program that can be executed by the processor 1210, causing the processor 1210 to perform the methods described in the preceding method embodiments. The memories 1220 may be independent of the processor 1210 or integrated within the processor 1210.

[0290] The device 1200 may also include a transceiver 1230. The processor 1210 can communicate with other devices or chips via the transceiver 1230. For example, the processor 1210 can send and receive data with other devices or chips via the transceiver 1230.

[0291] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal or network device provided in this application, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0292] This application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in this application embodiment, and the program causes a computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0293] This application also provides a computer program. This computer program can be applied to the terminal or network device provided in this application, and the computer program causes the computer to execute the methods performed by the terminal or network device in various embodiments of this application.

[0294] It should be understood that the terms "system" and "network" in this application can be used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the application. The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0295] In the embodiments of this application, the term "instruction" can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0296] In the embodiments of this application, the term "correspondence" can indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship such as instruction and being instructed, configuration and being configured.

[0297] In this application embodiment, the "protocol" may refer to a standard protocol in the field of communication, such as the LTE protocol, the NR protocol, and related protocols applied to future communication systems. This application does not limit this.

[0298] In the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0299] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0300] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0301] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0302] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0303] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs, DVDs) or semiconductor media (e.g., solid-state disks, SSDs), etc.

[0304] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for a first node in wireless communication, characterized in that, include: Receive first information, which is used to indicate multiple positioning estimates of the first node; Based on the multiple positioning estimates, the reference position of the first node is determined; The reference position is used to monitor the performance of the first model.

2. The method as described in claim 1, characterized in that, The method further includes: Receive second information, which is used to indicate the physical locations of multiple sets of reference signals and multiple sets of transceiver nodes; Send a third message, which is used to indicate the physical location of the multiple sets of transceiver nodes and measurement data for the multiple sets of reference signals; The physical locations of the multiple sets of transceiver nodes and the measurement data for the multiple sets of reference signals are used to determine the multiple positioning estimates.

3. The method as described in claim 1 or 2, characterized in that, The reference location is used to monitor the performance of the first model, including: The performance of the first model is monitored based on the deviation between the reference position and the predicted position of the first node, wherein the predicted position is the output of the first model.

4. The method as described in claim 2, characterized in that, The measurement data for the reference signals of the multiple sets of transceiver nodes is the input to the first model.

5. The method according to any one of claims 1-4, characterized in that, The reference position satisfies the formula in, The reference position is... Let α be the i-th location estimate among the plurality of location estimates. i Let be the weight corresponding to the i-th location estimate, where i is a positive integer.

6. The method as described in claim 5, characterized in that, The weight corresponding to the i-th positioning estimate is determined based on one or more of the following: The weights corresponding to the i-th location estimate mentioned in the history; Measurement data of the reference signal of the i-th basic positioning unit; The geometric features of the i-th basic positioning unit; The positioning accuracy of the i-th basic positioning unit; A set of transceiver nodes constitutes a basic positioning unit.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Receive K0 sets of reference signals, where K0 is a positive integer greater than or equal to K; The measurement data for the K0 group of reference signals were used to train the first model.

8. The method according to any one of claims 1-6, characterized in that, The method further includes: Receive first configuration information, which is used to instruct the first model.

9. A method for a second node in wireless communication, characterized in that, include: Send first information, which is used to indicate multiple positioning estimates of the first node, and the multiple positioning estimates are used to determine the reference position of the first node; The reference position is used to monitor the performance of the first model.

10. The method as described in claim 9, characterized in that, The method further includes: Receive third information, which is used to indicate the physical locations of multiple sets of transceiver nodes and measurement data for the multiple sets of reference signals.

11. The method as described in claim 9 or 10, characterized in that, The reference location is used to monitor the performance of the first model, including: The performance of the first model is monitored based on the deviation between the reference position and the predicted position of the first node, wherein the predicted position is the output of the first model.

12. The method as described in claim 10, characterized in that, The measurement data for the reference signals of the multiple sets of transceiver nodes is the input to the first model.

13. The method as described in claim 10, characterized in that, The method further includes: Based on the physical locations of the multiple sets of transceiver nodes and the measurement data for the multiple sets of reference signals, multiple positioning estimates of the first node are determined. Each set of transmitting and receiving nodes corresponds to at least one location estimate.

14. The method according to any one of claims 9-13, characterized in that, The reference position satisfies the formula in, The reference position is... Let α be the i-th location estimate among the plurality of location estimates. i Let be the weight corresponding to the i-th location estimate, where i is a positive integer.

15. The method as described in claim 14, characterized in that, The weight corresponding to the i-th positioning estimate is determined based on one or more of the following: The weights corresponding to the i-th location estimate mentioned in the history; Measurement data of the reference signal of the i-th basic positioning unit; The geometric features of the i-th basic positioning unit; The positioning accuracy of the i-th basic positioning unit; A set of transceiver nodes constitutes a basic positioning unit.

16. The method according to any one of claims 9-15, characterized in that, The method further includes: Send first configuration information, which is used to instruct the first model.

17. A first node for wireless communication, characterized in that, The first node includes: A first transceiver is configured to receive first information, the first information being used to indicate multiple positioning estimates of the first node; Based on the multiple positioning estimates, the reference position of the first node is determined; The reference position is used to monitor the performance of the first model.

18. The first node as described in claim 17, characterized in that, The first node also includes: The first transceiver is also used to receive second information, which indicates multiple sets of reference signals and the physical locations of multiple sets of transceiver nodes; The first transceiver is also used to transmit third information, which is used to indicate the physical location of the plurality of transceiver nodes and measurement data for the plurality of reference signals; The physical locations of the multiple sets of transceiver nodes and the measurement data for the multiple sets of reference signals are used to determine the multiple positioning estimates.

19. The first node as described in claim 17 or 18, characterized in that, The reference location is used to monitor the performance of the first model, including: The performance of the first model is monitored based on the deviation between the reference position and the predicted position of the first node, wherein the predicted position is the output of the first model.

20. The first node as described in claim 18, characterized in that, The measurement data for the reference signals of the multiple sets of transceiver nodes is the input to the first model.

21. The first node as claimed in any one of claims 17-20, characterized in that, The reference position satisfies the formula in, The reference position is... Let α be the i-th location estimate among the plurality of location estimates. i Let be the weight corresponding to the i-th location estimate, where i is a positive integer.

22. The first node as described in claim 21, characterized in that, The weight corresponding to the i-th positioning estimate is determined based on one or more of the following: The weights corresponding to the i-th location estimate mentioned in the history; Measurement data of the reference signal of the i-th basic positioning unit; The geometric features of the i-th basic positioning unit; The positioning accuracy of the i-th basic positioning unit; A set of transceiver nodes constitutes a basic positioning unit.

23. The first node as described in any one of claims 17-22, characterized in that, The first node also includes: The first transceiver is also used to receive K0 sets of reference signals, where K0 is a positive integer greater than or equal to K; The measurement data for the K0 group of reference signals were used to train the first model.

24. The first node as claimed in any one of claims 17-23, characterized in that, The first node also includes: The first transceiver is also configured to receive first configuration information, which is used to indicate the first model.

25. A second node for wireless communication, characterized in that, The second node includes: A second transceiver is used to transmit first information, which indicates multiple positioning estimates of a first node, the multiple positioning estimates being used to determine a reference position of the first node. The reference position is used to monitor the performance of the first model.

26. The second node as described in claim 25, characterized in that, The second node also includes: The second transceiver is also used to receive third information, which indicates the physical locations of multiple sets of transceiver nodes and measurement data for the multiple sets of reference signals.

27. The second node as described in claim 25 or 26, characterized in that, The reference location is used to monitor the performance of the first model, including: The performance of the first model is monitored based on the deviation between the reference position and the predicted position of the first node, wherein the predicted position is the output of the first model.

28. The second node as described in claim 26, characterized in that, The measurement data for the reference signals of the multiple sets of transceiver nodes is the input to the first model.

29. The second node as described in claim 26, characterized in that, The second node also includes: The second processor is configured to determine multiple positioning estimates of the first node based on the physical locations of the multiple sets of transceiver nodes and measurement data for the multiple sets of reference signals. Each set of transmitting and receiving nodes corresponds to at least one location estimate.

30. The second node as described in any one of claims 25-29, characterized in that, The reference position satisfies the formula in, The reference position is... Let α be the i-th location estimate among the plurality of location estimates. i Let be the weight corresponding to the i-th location estimate, where i is a positive integer.

31. The second node as described in claim 30, characterized in that, The weight corresponding to the i-th positioning estimate is determined based on one or more of the following: The weights corresponding to the i-th location estimate mentioned in the history; Measurement data of the reference signal of the i-th basic positioning unit; The geometric features of the i-th basic positioning unit; The positioning accuracy of the i-th basic positioning unit; A set of transceiver nodes constitutes a basic positioning unit.

32. The second node as described in any one of claims 25-31, characterized in that, The second node also includes: The second transceiver is also used to send first configuration information, which is used to instruct the first model.

33. A node used for wireless communication, characterized in that, It includes a transceiver, a memory, and a processor, wherein the memory is used to store a program, the processor is used to invoke the program in the memory, and to control the transceiver to receive or send signals so that the node performs the method as described in any one of claims 1-8 or 9-16.

34. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the apparatus to perform the method as described in any one of claims 1-16.

35. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1-16.

36. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1-16.

37. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1-16.

38. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-16.

Images