Method and device for acquiring label information, equipment and storage medium

Abstract

The embodiment of the invention provides a tag information obtaining method and device and electronic equipment. The method comprises the steps that first network equipment determines a correction parameter; the first network equipment determines label information corresponding to each piece of data in a data set based on the correction parameters; the data set and the label information corresponding to each piece of data in the data set are used for training a first model.

Description

Method, device, equipment, and storage medium for obtaining tag information Technical Field

[0001] The embodiments of the present application relate to the field of mobile communication technology, and specifically to a method, apparatus, device, and storage medium for obtaining tag information. Background Art

[0002] Given the tremendous success of artificial intelligence (AI) or machine learning (ML) in computer vision, natural language processing, and other fields, the communications field has begun to try to use AI / ML technology to seek new technical ideas to solve technical problems that are limited by traditional methods.

[0003] How to improve the positioning accuracy of AI / ML models used for terminal device positioning in the communications field has always been a concern in this field.

[0004] Summary of the Invention

[0005] The embodiments of the present application provide a method, apparatus, device, and storage medium for obtaining tag information.

[0006] In a first aspect, an embodiment of the present application provides a method for obtaining tag information, comprising:

[0007] The first network device determines a correction parameter;

[0008] The first network device determines label information corresponding to each data in the data set based on the correction parameter; the data set and the label information corresponding to each data in the data set are used to train the first model.

[0009] In a second aspect, an embodiment of the present application provides a method for obtaining tag information, including:

[0010] The second terminal device determines a data set and label information corresponding to each data in the data set; the label information is determined based on the correction parameter;

[0011] The second terminal device trains the first model based on the data set and label information corresponding to each data in the data set.

[0012] In a third aspect, an embodiment of the present application provides an apparatus for obtaining tag information, which is applied to a first network device, including:

[0013] The first determination unit is configured to determine a correction parameter, and based on the correction parameter, determine label information corresponding to each data in the data set; the data set and the label information corresponding to each data in the data set are used to train the first model.

[0014] In a fourth aspect, an embodiment of the present application further provides a device for obtaining tag information, which is applied to a second terminal device, comprising:

[0015] A second determining unit is configured to determine a data set and label information corresponding to each data in the data set; the label information is determined based on the correction parameter;

[0016] The second training unit is configured to train the first model based on the data set and label information corresponding to each data in the data set.

[0017] In a fifth aspect, an embodiment of the present application provides a network device, the network device comprising a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method described in the first aspect above.

[0018] In a sixth aspect, an embodiment of the present application provides a terminal device, the terminal device comprising a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method described in the second aspect above.

[0019] The chip provided in the embodiment of the present application is used to implement the above-mentioned model monitoring method.

[0020] Specifically, the chip includes: a processor for calling and running a computer program from a memory, so that a device equipped with the chip executes the method described in the first aspect or the second aspect above.

[0021] The computer-readable storage medium provided in an embodiment of the present application is used to store a computer program, which enables a computer to execute the method described in the first aspect or the second aspect above.

[0022] The computer program product provided in the embodiments of the present application includes computer program instructions, which enable a computer to execute the method described in the first aspect or the second aspect above.

[0023] The computer program provided in the embodiments of the present application, when executed on a computer, enables the computer to execute the method described in the first aspect or the second aspect above.

[0024] In the method for obtaining label information provided in the embodiments of the present application, the first network device can use the correction parameters to determine the label information corresponding to each data item in the data set. In this way, the first network device can train the first model based on the corrected label information, thereby improving the reliability of the data set used to train the first model and thereby improving the positioning accuracy of the first model. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] FIG1 is a schematic diagram of a communication process of a wireless communication system provided in an embodiment of the present application;

[0027] FIG2A is a schematic diagram showing the principle of a downlink-based positioning method provided in an embodiment of the present application;

[0028] FIG2B is a schematic diagram showing the principle of an uplink-based positioning method provided in an embodiment of the present application;

[0029] Figure 3 is a schematic diagram of a neuron structure provided by related technology

[0030] FIG4 is a schematic diagram of the structure of a neural network provided by the related art;

[0031] FIG5 is a schematic diagram of the structure of a convolutional neural network provided by the related art;

[0032] FIG6 is a schematic diagram of the structure of a Long Short-Term Memory (LSTM) network provided by the related art;

[0033] FIG7 is a flowchart of a method for obtaining tag information according to an embodiment of the present application;

[0034] FIG8A is a schematic diagram of a first model direct positioning principle provided by an embodiment of the present application;

[0035] FIG8B is a schematic diagram of a first model-assisted positioning principle provided in an embodiment of the present application;

[0036] FIG9 is a second flow chart of a method for obtaining tag information provided in an embodiment of the present application;

[0037] FIG10 is a third flow chart of a method for obtaining tag information provided in an embodiment of the present application;

[0038] FIG11 is a fourth flow chart of a method for obtaining tag information provided in an embodiment of the present application;

[0039] FIG12 is a fifth flow chart of a method for obtaining tag information provided in an embodiment of the present application;

[0040] FIG13 is a sixth flow chart of a method for obtaining tag information provided in an embodiment of the present application;

[0041] FIG14 is a flow chart of a method for obtaining tag information according to an embodiment of the present application;

[0042] FIG15 is a schematic diagram of the structure of an apparatus 1500 for acquiring tag information provided in an embodiment of the present application;

[0043] FIG16 is a schematic diagram of the structure of an apparatus 1600 for acquiring tag information provided in an embodiment of the present application;

[0044] FIG17 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application;

[0045] FIG18 is a schematic structural diagram of a chip provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0048] FIG1 is a schematic diagram of an application scenario of an embodiment of the present application.

[0049] As shown in Figure 1, a communication system 100 may include a terminal device 110 and a network device 120. The network device 120 may communicate with the terminal device 110 via an air interface. The terminal device 110 and the network device 120 support multi-service transmission.

[0050] It should be understood that the embodiments of the present application are only illustrative of the communication system 100, but the embodiments of the present application are not limited thereto. That is, the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Internet of Things (IoT) system, Narrow Band Internet of Things (NB-IoT) system, enhanced Machine-Type Communications (eMTC) system, 5G communication system (also known as New Radio (NR) communication system), or future communication systems.

[0051] In the communication system 100 shown in Figure 1, the network device 120 may be an access network device that communicates with the terminal device 110. The access network device may provide communication coverage for a specific geographical area and may communicate with the terminal device 110 (eg, UE) located within the coverage area.

[0052] The network device 120 may be an evolved Node B (eNB or eNodeB) in a Long Term Evolution (LTE) system, or a Next Generation Radio Access Network (NG RAN) device, or a gNB in ​​an NR system, or a wireless controller in a Cloud Radio Access Network (CRAN), or the network device 120 may be a relay station, an access point, an in-vehicle device, a wearable device, a hub, a switch, a bridge, a router, or a network device in a future evolved Public Land Mobile Network (PLMN), etc.

[0053] The terminal device 110 may be any terminal device, including but not limited to a terminal device connected to the network device 120 or other terminal devices by wire or wireless connection.

[0054] For example, the terminal device 110 may refer to an access terminal, user equipment (UE), a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user apparatus. An access terminal may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, an IoT device, a satellite handheld terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5G network, or a terminal device in a future evolution network, etc.

[0055] The terminal device 110 can be used for device-to-device (D2D) communication.

[0056] The wireless communication system 100 may further include a core network device 130 that communicates with the network device 120. The core network device 130 may be a 5G core network (5G Core, 5GC) device, such as an Access and Mobility Management Function (AMF), an Authentication Server Function (AUSF), a User Plane Function (UPF), or a Session Management Function (SMF). Optionally, the core network device 130 may also be an Evolved Packet Core (EPC) device of an LTE network, such as a Session Management Function + Core Packet Gateway (SMF+PGW-C) device. It should be understood that SMF+PGW-C can simultaneously implement the functions that can be implemented by SMF and PGW-C. During the network evolution process, the above-mentioned core network device may also be called other names, or a new network entity may be formed by dividing the functions of the core network, which is not limited in the embodiments of the present application.

[0057] The functional units in the communication system 100 may also establish connections and implement communication via next generation (NG) network interfaces.

[0058] For example, the terminal device establishes an air interface connection with the access network device through the NR interface for transmitting user plane data and control plane signaling; the terminal device can establish a control plane signaling connection with the AMF through the NG interface 1 (referred to as N1); the access network device, such as the next generation wireless access base station (gNB), can establish a user plane data connection with the UPF through the NG interface 3 (referred to as N3); the access network device can establish a control plane signaling connection with the AMF through the NG interface 2 (referred to as N2); the UPF can establish a control plane signaling connection with the SMF through the NG interface 4 (referred to as N4); the UPF can exchange user plane data with the data network through the NG interface 6 (referred to as N6); the AMF can establish a control plane signaling connection with the SMF through the NG interface 11 (referred to as N11); the SMF can establish a control plane signaling connection with the PCF through the NG interface 7 (referred to as N7).

[0059] Figure 1 exemplarily shows a network device, a core network device and two terminal devices. 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, which is not limited in this embodiment of the present application.

[0060] It should be noted that Figure 1 is merely an example of a system applicable to this application. Of course, the methods described in the embodiments of this application can also be applied to other systems. Furthermore, the terms "system" and "network" are often used interchangeably herein. The term "and / or" herein simply describes an association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the associated objects are in an "or" relationship. It should also be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association relationship. For example, "A indicates B" can mean that A directly indicates B, for example, B can obtain information through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can obtain information through C; or it can mean that A and B have an association relationship. It should also be understood that the "correspondence" mentioned in the embodiments of this application can mean that there is a direct or indirect correspondence between two objects, or that there is an association relationship between the two objects, or a relationship between an indicator and the indicated, a configuration and the configured, and so on. It should also be understood that the “predefined” or “predefined rules” mentioned in the embodiments of the present application can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in devices (for example, including terminal devices and network devices), and the present application does not limit its specific implementation method. For example, predefined can refer to what is defined in the protocol. It should also be understood that in the embodiments of the present application, the “protocol” may refer to a standard protocol in the field of communications, such as LTE protocols, NR protocols, and related protocols used in future communication systems, and the present application does not limit this.

[0061] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0062] In practical applications, terminal device positioning methods may include the following categories:

[0063] UE-based positioning method: that is, the terminal device directly calculates the position of the target UE.

[0064] UE-assisted / LMF-based positioning method: The terminal reports the measurement results to the LMF, and the LMF calculates the location of the target UE based on the collected measurement results.

[0065] Based on the NG-RAN node assisted positioning method: the base station reports the measurement results of the network transmission / reception point (TRP) to the LMF, and the LMF calculates the position of the target UE based on the collected measurement results.

[0066] It should be noted that multiple TRPs around the terminal device can participate in position positioning. A base station may be a TRP, and a base station may have multiple TRPs under it. The LMF can be the positioning server, responsible for the entire positioning process.

[0067] In traditional positioning methods, for different methods, the UE or LMF applies traditional algorithms, such as the Chan algorithm, Taylor expansion, etc., to estimate the location of the terminal device.

[0068] The following introduces the downlink-based positioning method and the uplink-based positioning method respectively.

[0069] As shown in FIG2A , the downlink-based positioning method may include the following steps:

[0070] Step 1: The LMF network element notifies the TRP of the relevant configuration.

[0071] The relevant configuration may include configuration information of a positioning reference signal (PRS), and / or information such as the type of measurement results that the terminal device needs to report.

[0072] Step 2: TRP sends PRS.

[0073] Step 3: The terminal device receives the positioning signal PRS and performs measurement.

[0074] It should be noted that different positioning methods require different measurement results from the terminal device.

[0075] Step 4: The terminal device feeds back the measurement results to the LMF.

[0076] The terminal device feeds the measurement results back to the LMF through the base station.

[0077] Step 5: LMF calculates the location-related information.

[0078] It should be noted that the above is a schematic diagram of the UE-assisted positioning method. For terminal device-based positioning methods (UE-based), in step 4 above, the terminal device directly calculates the location-related information based on the measurement results, without reporting the measurement results to the LMF, which then performs the calculation. In UE-based positioning methods, the terminal device needs to know the location information corresponding to the TRP, so the LMF needs to notify the terminal device of the location information corresponding to the TRP in advance.

[0079] In addition, referring to FIG2B , the uplink-based positioning method may include the following steps:

[0080] Step 1. LMF notifies TRP of relevant configurations.

[0081] Step 2: The base station sends relevant signaling to the terminal device.

[0082] Step 3: The terminal device sends a sounding reference signal (SRS).

[0083] Step 4: TRP measures the SRS and sends the measurement results to LMF.

[0084] Step 5: LMF calculates location-related information

[0085] In recent years, artificial intelligence research, represented by neural networks, has achieved remarkable results in many fields and will continue to play an important role in people's production and daily lives for a long time to come. A neural network is a computational model composed of multiple interconnected neuron nodes. Figure 3 shows a schematic diagram of a neuron structure. As shown in Figure 3, a neuron structure can be connected to other neuron structures a1 to an. The transmission of signals between neuron structures is affected by weights (for example, the weight value of the signal input to neuron structure a1 is w1). Each neuron structure can perform a weighted summation of multiple input signals and output them through a specific activation function.

[0086] Figure 4 is a schematic diagram of a neural network structure proposed in related art. As shown in Figure 4, a neural network structure can include an input layer, a hidden layer, and an output layer. As shown in Figure 4, the input layer receives data, the hidden layer processes the data, and the output layer produces the final result. Each node represents a processing unit, which can be thought of as simulating a neuron. Multiple neurons form a layer of a neural network. Multiple layers of information transmission and processing construct a complete neural network.

[0087] With the continuous development of neural network research, neural network deep learning algorithms have been proposed in recent years. More hidden layers have been introduced, and feature learning has been performed layer by layer through multi-hidden layer neural network training, which has greatly improved the learning and processing capabilities of neural networks. It has also been widely used in pattern recognition, signal processing, optimization combination, anomaly detection and other aspects.

[0088] Similarly, with the development of deep learning, convolutional neural networks (CNN) have also been further studied.

[0089] Figure 5 is a schematic diagram of a convolutional neural network structure provided by related art. As shown in Figure 5, the structure of a convolutional neural network can include: an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer. The introduction of convolutional and pooling layers effectively controls the rapid increase in network parameters, limits the number of parameters, and exploits the characteristics of local structures, improving the robustness of the algorithm.

[0090] Recurrent neural networks have achieved remarkable results in natural language processing applications such as machine translation and speech recognition. A recurrent neural network models sequential data, memorizing information from past moments and applying it to current output calculations. Specifically, the nodes in the hidden layers are connected, rather than disconnected, and the hidden layer inputs include not only the input layer but also the output of the previous hidden layer.

[0091] Figure 6 is a schematic diagram of the structure of a long short-term memory (LSTM) network provided by related technologies. LSTM is a commonly used type of recurrent neural network. Unlike recurrent neural networks that only consider the most recent state, LSTM determines which states should be retained and which states should be forgotten, thus solving the defects of traditional recurrent neural networks in long-term memory.

[0092] Given the tremendous success of artificial intelligence (AI) technologies or machine learning (ML) technologies such as neural networks and deep learning in computer vision and natural language processing, the communications field has begun to try to use AI technologies to seek new technical ideas to solve technical problems that are limited by traditional methods.

[0093] In practical applications, AI / ML technology can be used to achieve terminal device positioning. In other words, the location of the terminal device can be determined based on the AI / ML model. It should be understood that the more accurate the label information corresponding to each data sample in the dataset used for AI / ML model training, the higher the positioning accuracy of the trained AI / ML model. For example, if the label information is the location of the terminal device, the more accurate the location of the terminal device, the higher the positioning accuracy of the trained AI / ML model.

[0094] Typically, the location of the terminal device can be determined using the traditional positioning method shown in FIG2A or FIG2B to obtain the label information of each sample data in the dataset. In addition, the location of the terminal device can also be determined using a non-NR method, for example, using the Global Positioning System (GPS) to determine the location of the terminal device, thereby obtaining the label information of each sample data in the dataset.

[0095] However, the positioning error of the above-mentioned traditional positioning technology will be greater than 10 meters in scenarios with a large number of non-line of sight (NLOS) paths, and the positioning error of non-NR methods is even greater than that of traditional positioning methods. In addition, the location of ordinary terminal devices is private information, and location-related label information can only be obtained through the above-mentioned methods, which leads to poor accuracy of location-related label information. This will result in poor positioning accuracy of the AI / ML model trained in this way. How to train an AI / ML model with higher positioning accuracy, that is, how to obtain a more reliable data set, is a technical problem that needs to be solved urgently.

[0096] Based on this, an embodiment of the present application provides a method for obtaining tag information. FIG7 is a flow chart of the method for obtaining tag information provided by an embodiment of the present application. As shown in FIG7 , the method includes the following contents.

[0097] Step 710: The first network device determines a correction parameter.

[0098] Step 720: The first network device determines label information corresponding to each data in the data set based on the correction parameter; the data set and the label information corresponding to each data in the data set are used to train the first model.

[0099] It should be understood that the first model can be deployed in the first network device. The first model can be an AI / ML model for terminal device positioning, such as a neural network model, a CNN model, an LSTM model, etc., which is not limited in this embodiment of the present application.

[0100] Optionally, the first network device may be a core network device. Exemplarily, the first network device may be a LMF, a positioning server, or other network element with a positioning management function, which is not limited in the embodiment of the present application.

[0101] It should be noted that the first model can be used directly to determine the location information of the terminal device, or it can be used to assist in determining the location information of the terminal device. The embodiment of the present application does not limit the type of the first model. For example, refer to a schematic diagram of the direct positioning principle of a first model shown in Figure 8A, wherein the input of the first model is the measurement information of the terminal device, and the output of the first model is the estimated location information of the terminal device. Figure 8B shows a schematic diagram of the auxiliary positioning principle of a first model, wherein the input of the first model is the measurement information, and the output of the first model may include intermediate parameters. In this way, the first network device can process the intermediate parameters in combination with the positioning algorithm to obtain the estimated location information of the terminal device.

[0102] It should be understood that before training the first model, the first network device may obtain a dataset for the first model. The dataset for the first model may be used for training the first model or for performance monitoring of the first model. Performance monitoring of the first model may involve comparing the output of the first model with the label information in the dataset to monitor whether the error between the output of the first model and the label information meets performance requirements.

[0103] Optionally, the dataset of the first model may include measurement information of a large amount of terminal devices of different types.

[0104] Exemplarily, the measurement information may include one or more of the following: Channel Impulse Response (CIR), Power Delay Profile (PDP), Time of Arrival (ToA), Uplink Time Difference of Arrival (UL TDoA), Downlink Time Difference of Arrival (DL TdoA), Uplink Angle-of-Departure (UL AoD), Downlink Angle-of-Departure (DL AoD), Uplink Relative Time of Arrival (UL RTOA), Downlink Reference Signal Time Difference (DL RSTD), Reference Signal Receiving Power (RSRP), azimuth, and zenith angle.

[0105] It should be noted that the measurement information may be CIR, PDP, ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, azimuth, zenith angle, etc. of the communication channel between the terminal device and one or more second network devices. Among them, the second network device may be an access network device, such as a base station, a micro base station, TRP, etc., which is not limited in this embodiment of the present application.

[0106] In the embodiment of the present application, before using the data set to train the first model, the first network device may further determine correction parameters, and use the correction parameters to determine label information corresponding to each data in the data set.

[0107] Optionally, the tag information may be the location information of the terminal device, such as the two-dimensional spatial location coordinates (x, y) of the terminal device. In addition, the tag information may also be an intermediate parameter related to the location information of the terminal device. Exemplarily, the intermediate parameter may include one or more of the following:

[0108] ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, and Line of Sight (LOS) / NLOS identification results.

[0109] It should be noted that for the first model shown in FIG8A , the label information for each data item in its data set can be the location information of the terminal device. For the first model shown in FIG8B , the label information for each data item in its data set can be an intermediate parameter related to the location of the terminal device. In other words, in this embodiment of the present application, the type of label information can be the same as the type of the output data of the first model.

[0110] In the embodiments of the present application, each data item in the data set has associated initial tag information. The initial tag information associated with each data item in the data set can be determined using a traditional positioning method, such as the method shown in Figure 2A or Figure 2B, or a GPS method, or an AI / ML model, and the embodiments of the present application do not limit this.

[0111] It is understood that the first network device can use the correction parameters to correct the initial label information associated with each data item in the dataset to obtain label information corresponding to each data item in the dataset. In this way, the first network device can train the first model based on the corrected label information, thereby improving the reliability of the dataset used to train the first model and thus improving the positioning accuracy of the first model.

[0112] The following describes in detail how the first network device determines the correction parameter.

[0113] In the embodiment of the present application, the first network device may determine the correction parameter by one or more of the following:

[0114] Preset rules, protocol predefinition, other network device configurations, and reporting by the first terminal device.

[0115] In some embodiments, the first network device determines the correction parameter according to a preset rule, which can be implemented in the following manner:

[0116] The first network device determines a correction parameter based on an error value between actual information and estimated information of the first terminal device.

[0117] It should be noted that the first terminal device may be a terminal device whose actual information is known. For example, the first terminal device may be a terminal device whose actual location is known, or a device whose actual intermediate parameters are known.

[0118] Optionally, the first terminal device may be a positioning reference unit (PRU).

[0119] Among them, the PRU can perform downlink positioning-related measurements (for example, downlink signal time difference, reference signal received power, UE-side received signal and transmitted signal Rx-Tx time difference, etc.), and report these measurement results to the positioning server. For example, the PRU receives PRS and performs downlink positioning-related measurements based on PRS. In addition, the PRU can send SRS, and the base station performs measurements based on the SRS and reports uplink positioning measurement results (for example, uplink relative arrival time, uplink arrival angle, base station-side Rx-Tx time difference, etc.).

[0120] In the embodiment of the present application, since the first terminal device is a terminal device whose actual information is known, the first network device can use the error value between the actual information of the first terminal device and the estimated information of the first terminal device to correct the label information of the ordinary terminal device.

[0121] It should be noted that the ordinary terminal device here may be the terminal device whose tag information is to be corrected. In the embodiment of the present application, the ordinary terminal device may also refer to the second terminal device in the embodiment of the present application. The second terminal device and the ordinary terminal device may refer to the same type of terminal devices.

[0122] Among them, the estimated information of the first terminal device can be determined according to a traditional positioning method, such as the method shown in Figure 2A or Figure 2B, or determined by a GPS method, or determined by an AI / ML model, and the embodiments of the present application do not impose any restrictions on this.

[0123] Optionally, the actual information of the first terminal device may be actual location information, and correspondingly, the estimated information of the first terminal device may be estimated location information.

[0124] In this scenario, the correction parameter may be the distance error between the actual position information and the estimated position information. Optionally, the correction parameter may include a first position correction parameter in a first direction and / or a second position correction parameter in a second direction. For example, the first direction may be the horizontal direction (x-direction). The second direction may be the vertical direction (y-direction).

[0125] For example, the horizontal distance error between the actual location information and the estimated location information of the first terminal device PRU1 is h1, and the vertical distance error is v1. If the location coordinates of the terminal device to be corrected are (x, y), the corrected location coordinates can be (x±h1, y±v1). The first network device can use the corrected location coordinates (x±h1, y±v1) as tag information for the measurement parameters associated with the terminal device.

[0126] That is to say, the first network device can correct the location information only in the first direction or the second direction, or can correct it in both directions at the same time, flexibly correcting the tag information of the terminal device and improving the accuracy of the tag information corresponding to the terminal device.

[0127] Optionally, the actual information of the first terminal device may be an actual intermediate parameter, for example, the actual information may be one or more of an actual ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, and LOS / NLOS identification result. The estimated information of the first terminal device may be an estimated intermediate parameter, for example, the estimated information may be one or more of a ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, and LOS / NLOS identification result estimated by a traditional method.

[0128] To sum up, in the method for obtaining label information provided in the embodiment of the present application, the first network device can use the actual information of the special terminal device to correct the label information of the ordinary terminal device, thereby improving the reliability of the data set used to train the first model and further improving the positioning accuracy.

[0129] It should be noted that the number of the aforementioned first terminal device is one, that is, the first network device can determine the correction parameter based on the error between the actual information and the estimated information of a single first terminal device. It should be understood that the first network device can manage multiple first terminal devices, that is, the first network device can manage multiple terminal devices whose actual information is known. The aforementioned single first terminal device can be any one of the multiple first terminal devices managed by the first network device.

[0130] In other embodiments, the number of first terminal devices may include multiple. That is, the first network device may also determine the correction parameter based on the actual information and estimated information of multiple first terminal devices. In other words, the first network device determines the correction parameter based on preset rules, which can be achieved in the following manner:

[0131] The first network device may determine the correction parameter based on an average of error values ​​between actual information and estimated information of a plurality of first terminal devices.

[0132] In this embodiment of the present application, when the number of first terminal devices is N, the first network device may determine the error value between the actual information and the estimated information of each first terminal device to obtain N error values. Furthermore, the first network device may calculate the average of the N error values ​​to obtain a correction parameter.

[0133] Optionally, when the tag information is location information, the correction parameter may include the average error value between the actual location information and the estimated location information of N first terminal devices in the first direction (for example, the horizontal direction), and / or the average error value in the second direction (for example, the vertical direction).

[0134] Exemplarily, multiple first terminal devices may include PRU1 and PRU2. The horizontal distance error between the actual position information and the estimated position information of PRU1 is h1, and the vertical distance error is v1. The horizontal distance error between the actual position information and the estimated position information of PRU2 is h2, and the vertical distance error is v2. The average value of the horizontal distance error is (h1+h2) / 2, and the average value of the vertical distance error is (v1+v2) / 2. If the position coordinates of the terminal device to be corrected are (x, y), the corrected tag information can be (x±(h1+h2) / 2, y±(v1+v2) / 2)).

[0135] To sum up, the correction parameters determined based on the actual information and estimated information of a single first terminal device have large errors and do not seem to be suitable for terminal device position correction in some scenarios. This solution can determine the correction parameters based on the actual information and estimated information of multiple first terminal devices, thereby improving the accuracy of the correction parameters.

[0136] In some other embodiments, the first network device determines the correction parameter according to a preset rule, which can be implemented in the following manner:

[0137] The first network device determines a correction parameter based on an error value between actual information and estimated information of the first terminal device, and a first proportional parameter, where the first proportional parameter is used to characterize a positional relationship between the first terminal device and the second terminal device; the second terminal device is associated with at least part of the data in the data set.

[0138] The second terminal device may be a terminal device whose tag information is to be corrected. For example, the second terminal device may be a terminal device other than the first terminal device. As described in the above embodiment, the second terminal device may also be referred to as a common terminal device, and the second terminal device and the common terminal device may refer to the same type of terminal device.

[0139] It should be noted that the dataset used to train the first model may include a large amount of measurement information of the second terminal device. The measurement information of the second terminal device and the corresponding label information belong to the dataset used to train the first model.

[0140] It should also be noted that the at least some of the data may include one or more data. Each data in the at least some of the data may represent measurement information of the second terminal device. The measurement information may include one or more of CIR, PDP, ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, azimuth, and zenith angle, as described in the above embodiment.

[0141] In an embodiment of the present application, the first network device may determine a correction parameter for the second terminal device based on an error between the actual information and the estimated information of the first terminal device, as well as a first ratio parameter. The first ratio parameter may represent the positional relationship between the first terminal device and the second terminal device. A larger first ratio parameter indicates a closer position between the first terminal device and the second terminal device; conversely, a smaller first ratio parameter indicates a greater distance between the first terminal device and the second terminal device.

[0142] Optionally, the first ratio parameter may be determined based on characteristic information of the first terminal device and characteristic information of the second terminal device, wherein the characteristic information may represent characteristics of a channel between the terminal device and the second network device.

[0143] It should be noted that the larger the first ratio parameter, the closer the characteristic information of the first terminal device is to the characteristic information of the second terminal device, that is, the closer the locations of the first terminal device and the second terminal device are. Conversely, the smaller the first ratio parameter, the further the characteristic information of the first terminal device is from the characteristic information of the second terminal device, that is, the farther the locations of the first terminal device and the second terminal device are.

[0144] For example, the characteristic information may include one or more of the following:

[0145] Channel information, measurement information, first path power, channel impulse response, and spatial consistency related information.

[0146] It is understandable that the closer the characteristic information of the first terminal device is to that of the second terminal device, the closer the positions of the first terminal device and the second terminal device are. In actual applications, the location information of the second terminal device determined by traditional methods is not accurate. Therefore, in the embodiment of the present application, the first network device can use the characteristic information of the terminal devices to determine the positional relationship between the first terminal device and the second terminal device.

[0147] Exemplarily, the first network device may calculate the Euclidean distance or cosine similarity between the feature information of the first terminal device and the feature information of the second terminal device to obtain the first scale parameter.

[0148] In this embodiment of the present application, the closer the positions of the first terminal device and the second terminal device are, the closer the error value determined by the actual information and estimated information of the first terminal device will be to the error value between the actual information and estimated information of the second terminal device. Based on this, the first network device can determine the correction parameter for the second terminal device based on the error value between the actual information and estimated information of the first terminal device and the first proportional parameter.

[0149] Optionally, the correction parameter can be a function between the error value and the first proportional parameter. For example, correction parameter = F (error value, first proportional parameter). Exemplarily, the correction parameter can be error value * first proportional parameter, or error value / first proportional parameter, which is not limited in the embodiments of the present application. Exemplarily, the F function can be a normal distribution function, that is, the error value is normally distributed when the first proportional parameter has different values.

[0150] It should be noted that different second terminal devices may correspond to different correction parameters. In other words, the first network device may use the correction parameters associated with the second terminal device to correct the tag information of the second terminal device.

[0151] Optionally, the first ratio parameter may be greater than or equal to a first threshold. That is, the first network device may select a first terminal device that is located close to the second terminal device, and determine the correction parameter for the second terminal device based on the error between the actual information and the estimated information of the selected first terminal device and the first ratio parameter.

[0152] Optionally, the first threshold may be a parameter predefined by the protocol, such as 95%, or a parameter determined according to a preset rule, which is not limited in the present embodiment.

[0153] Exemplarily, the data set used to train the first model may include measurement information of UE1. The first network device may traverse the PRUs near UE1 based on the characteristic information of UE1, and select the PRU1 that is closest to the characteristic information of UE1. Specifically, the first network device may determine the PRU1 that is closest to the characteristic information of UE1 based on the characteristic information of UE1 and the characteristic information of the PRUs around it. After the first network device determines PRU1, it may determine the correction parameter of UE1 based on the error value between the actual location information and the estimated location information of PRU1, and the characteristic information of UE1 and the ratio parameter determined by the characteristic information of PRU1. In this way, the first network device can correct the label information corresponding to the measurement information related to UE1 based on the correction parameter of UE1.

[0154] To sum up, the first network device can select the actual information and estimated information of the first terminal device that is closest to the characteristic parameters of the terminal device to be corrected to determine the correction parameters, thereby obtaining label information, which can improve the accuracy of the label information and further improve the positioning accuracy of the first model.

[0155] In some embodiments, in addition to determining the correction parameter based on the above rules, the first network device may also determine a value predefined by the protocol. For example, the correction parameter may be 1 meter, 0.5 meter, etc., which is not limited in this embodiment of the present application.

[0156] In other embodiments, the correction parameter may be configured by another device other than the first network device. For example, the correction parameter may be a value configured by the positioning server through dedicated signaling, such as 1 meter, 0.5 meter, etc., which is not limited in this embodiment of the present application.

[0157] In some other embodiments, the correction parameter may also be a parameter reported by the first terminal device. It is understandable that a terminal device (e.g., a PRU) for which actual information in the network is known may determine the correction parameter according to a preset rule and send the determined correction parameter to the first network device via dedicated signaling or other signaling.

[0158] It should be noted that the manner in which the first terminal device determines the correction parameters according to preset rules is similar to the manner in which the first network device determines the correction parameters according to preset rules in the above embodiment. For the sake of brevity, it will not be repeated here.

[0159] In some embodiments, the correction parameter may also be determined based on a preset rule and a value predefined by the protocol. The value predefined by the protocol may be an adjustment step size of the correction parameter.

[0160] Optionally, the first network device may perform multiple rounds of training on the first model, using different correction parameters in each round of training to obtain label information corresponding to each data item in the dataset. During the first round of training on the first model, the first network device may determine the first correction parameters according to the preset rules in the above embodiment. In this way, the first network device can determine the label information for each data item in the dataset based on the first correction parameters to train the first model.

[0161] During the second round of training for the first model, the first network device can adjust the first correction parameter according to a value predefined in the protocol (i.e., the adjustment step size of the correction parameter) to obtain a second correction parameter. In this way, the first network device can determine the label information of each data item in the data set based on the second correction parameter to train the first model.

[0162] The first network device may continue to adjust the correction parameters based on the values ​​predefined in the protocol (ie, the adjustment step of the correction parameters) to perform multiple rounds of training on the first model until the first model meets actual requirements.

[0163] It should be noted that the first correction parameter and the second correction parameter can be correction parameters for different training processes. The training process may also include a third correction parameter, a fourth correction parameter, etc., which are not exhaustive in the embodiments of the present application. The first correction parameter and the second correction parameter can be different, and the first correction parameter and the second correction parameter can be determined according to different methods.

[0164] For example, the error between the actual position of the first PRU and the estimated position of the first PRU is 10 meters. Based on the characteristic information of the first PRU and UE1, it can be determined that the first correction parameter in the first round of training is 2 meters. The first network device can use the first correction parameter to correct the label information of the terminal device to be corrected to train and obtain the first model. In the second round of training, the first network device can continue to calculate the error between the actual position of the first PRU and the estimated position of the first PRU. If the positioning accuracy of the first model still needs to be improved, the correction parameter is adjusted to obtain the second correction parameter. The second correction parameter can be 3 meters. In this way, the first network device can continue to use the correction parameter to correct the label information of the terminal device to be corrected, and train to obtain the first model. The training is repeated until the positioning accuracy reaches the first accuracy, so as to facilitate the adaptive adjustment of the correction parameter so that the accuracy of the first model meets the positioning accuracy requirements.

[0165] In summary, the first network device can determine the correction parameters in different ways, flexibly adjust the label information of each data in the data set, improve the reliability of the data set used to train the first model, and thus improve the positioning accuracy of the first model.

[0166] The following is a detailed introduction to the dataset construction process.

[0167] In an embodiment of the present application, referring to FIG9 , the method for obtaining tag information provided in the embodiment of the present application may further include the following steps:

[0168] Step 730: The first network device obtains measurement information related to the terminal device, where the measurement information is used to construct a data set; the terminal device includes the first terminal device and / or the second terminal device.

[0169] It should be noted that before training the first model, the first network device may also obtain measurement information related to multiple terminal devices in the network. In this way, the first network device can construct a data set based on the measurement information of multiple terminal devices. The data set may include measurement information of the terminal device to be corrected (the second terminal device) and / or measurement information of the terminal device whose actual information is known (i.e., the first terminal device).

[0170] Optionally, the measurement information associated with each terminal device may include one or more of the following: CIR, PDP, ToA, UL TDoA, DL TdoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, azimuth, and zenith angle.

[0171] It should be noted that the measurement information associated with each terminal device may be measurement information between each terminal device and a second network device. The measurement information associated with a terminal device may be for a single second network device or for multiple second network devices. In other words, the number of measurement information pieces may include one or more. When the number of measurement information pieces includes multiple pieces, the multiple measurement information pieces may be measurement results between the terminal device and multiple second network devices.

[0172] Exemplarily, multiple measurement information may correspond to n TRPs, where the multiple measurement information may be the CIR of the terminal device relative to the n TRPs, the RSRP of the terminal device relative to the n TRPs, the DL RSTD of the terminal device relative to the n TRPs, the ToA of the terminal device relative to the n TRPs, and the AoD of the terminal device relative to the n TRPs. The number of DL TDOA, RSRP, DL RSTD, TOA, and AoD corresponding to each TRP may be greater than 1.

[0173] Optionally, in an embodiment of the present application, referring to FIG9 , before the first network device acquires measurement information related to the terminal device in step 730, the first network device may further perform the following steps:

[0174] Step 740: The first network device sends trigger information, where the trigger information is used to trigger one or more of the following devices to send measurement information: the second network device, the first terminal device, and the second terminal device.

[0175] It should be understood that the first network device can trigger the terminal device and / or the second network device in the network to report measurement information related to the terminal device. In this way, the first network device can construct a data set of the first model based on the measurement information reported by various devices.

[0176] It should be noted that the data set of the first model can be used for training the first model and can also be used for performance monitoring of the first model.

[0177] Among them, the first network device triggers the terminal device to report measurement information, which can be the first network device alone triggering the first terminal device in the terminal device to report measurement information, or the first network device alone triggering the second terminal device in the terminal device to report measurement information, or the first network device can simultaneously trigger the first terminal device and the second terminal device to report measurement information. This embodiment of the present application does not limit this. It is understandable that the first network device can trigger the first terminal device and the second terminal device to report measurement information separately.

[0178] Optionally, the trigger information may include a reference signal type and / or a measurement type.

[0179] Optionally, the reference signal type may include one or more of the following:

[0180] Positioning Reference Signal (PRS), Synchronization Signal and PBCH Block (SSB), Sounding Reference Signal (SRS).

[0181] Optionally, the measurement type may include any of:

[0182] Periodic measurement, non-periodic measurement, semi-continuous measurement, and time window measurement.

[0183] Among them, for periodic measurement, the first network device can configure the time period for the terminal device and / or the second network device to measure the reference signal, as well as the number of measurements in each time period, etc., and the embodiments of the present application do not limit this.

[0184] Aperiodic measurement can be understood as measuring the reference signal only a preset number of times. For aperiodic measurement, the first network device can configure the number of times the terminal device and / or the second network device measures the reference signal.

[0185] For the semi-continuous measurement, the first network device may configure information such as a continuous measurement time period, a measurement cycle within the continuous measurement time period, and the number of measurements in each cycle.

[0186] For time window measurement, the first network device may configure information such as the starting position of the time window, the length of the time window, and the number of measurements within the time window.

[0187] In some embodiments, the first network device may trigger the terminal device to report downlink-related measurement information related to the terminal device, and the downlink-related measurement information may include one or more of CIR, PDP, ToA, DL TDoA, DL AoD, DL RSTD, RSRP, azimuth, and zenith angle between the terminal device and one or more second network devices.

[0188] Exemplarily, the first model is deployed in a scenario where the first network device is used. If the positioning method uses a downlink-based positioning technology, an example of a flowchart is shown in FIG10 . It should be noted that the dotted lines in FIG10 represent optional steps. Referring to FIG10 , the first network device is an LMF, the second network device is a gNB, the first terminal device is a PRU, and the second terminal device is a UE. The LMF may send trigger information to the PRU and the UE. The trigger information may trigger the UE and the PRU to measure the downlink reference signal (e.g., PRS and / or SSB) sent by the gNB. The UE and the PRU report to the LMF one or more of the CIR, PDP, ToA, DL TDoA, DL AoD, DL RSTD, RSRP, azimuth, and zenith angle measured for the downlink reference signal.

[0189] In other embodiments, the first network device may trigger the second network device to report uplink-related measurement information related to the terminal device, and the uplink-related measurement information may include one or more of CIR, PDP, ToA, UL TDoA, UL AoD, UL RTOA, RSRP, azimuth, and zenith angle between one or more second network devices and the terminal device.

[0190] Exemplarily, in a scenario where the first model is deployed in a first network device, if the positioning method uses an uplink-based positioning technology, an example flowchart is shown in FIG11 . It should be noted that the dashed lines in FIG11 represent optional steps. Referring to FIG11 , the first network device is an LMF, the second network device is a gNB, the first terminal device is a PRU, and the second terminal device is a UE. The LMF may send trigger information to the PRU and UE to trigger the PRU and UE to send uplink reference signals (e.g., SRS) to the gNB. The gNB may measure the uplink reference signals sent by the UE / PRU. The gNB may report one or more of the following to the LMF: CIR, PDP, ToA, UL TDoA, UL AoD, UL RTOA, RSRP, azimuth, and zenith angle.

[0191] It should be noted that, as shown in Figures 10 and 11, in some embodiments, the first terminal device and the second terminal device may also report reference correction parameters to the first network device. The reference correction parameters may be determined by the first terminal device and the second terminal device themselves for use by the LMF when determining the correction parameters.

[0192] The following describes in detail the process of the first network device training the first model.

[0193] In an embodiment of the present application, the method for obtaining tag information provided in the embodiment of the present application may further include the following steps:

[0194] Step 750: The first network device trains a first model based on the data set and label information corresponding to each data in the data set.

[0195] In an embodiment of the present application, when training the first model, AI / ML technology can be used to build the first model. During the training process, the first network device can input each data set obtained in the above embodiment into the first model, process the data through the first model, and obtain a first output result corresponding to each data. The first output result can be location information or an intermediate parameter related to the location information.

[0196] In this way, the first network device can compare the first output result corresponding to the data with the label information corresponding to the data to obtain a comparison result. Furthermore, the parameters in the first model can be updated based on the comparison result. The first network device can continue to input the measurement information into the updated first model to obtain a second output result. The first network device can then compare the second output result with the label information corresponding to the data and, based on the comparison result, further update the parameters in the first model. In this way, the first model is iteratively trained based on each data point in the data set and the label information corresponding to each data point to obtain the first model.

[0197] Optionally, when the accuracy of the first model is less than the first accuracy, the correction parameters are re-determined, and the label information corresponding to each data in the data set is updated based on the re-determined correction parameters. The updated labels are used to continue training the first model until the accuracy of the first model is greater than or equal to the first accuracy.

[0198] It should be noted that the accuracy of the first model can refer to the processing accuracy or positioning accuracy of the first model. If the accuracy of the first model is less than the first accuracy, it can be understood that the processing accuracy / positioning accuracy of the first model is low, that is, the positioning accuracy is low. Correspondingly, if the accuracy of the first model is greater than or equal to the first accuracy, it can be understood that the processing accuracy / positioning accuracy of the first model is high, that is, the positioning accuracy is high.

[0199] In this embodiment of the present application, if the accuracy of the first model does not meet the actual positioning requirements, that is, if the position information determined based on the first model differs significantly from the actual position information, the first network device may re-determine the correction parameters in step 710 and update the label information corresponding to each data item in the data set based on the new correction parameters. Furthermore, the first network device may continue to train the first model based on the updated label information corresponding to each data item until the accuracy of the first model meets the actual positioning requirements.

[0200] It is understood that, as shown in Figures 10 and 11, the first network device can perform multiple rounds of training on the first model, using different correction parameters in each round of training to obtain label information corresponding to each data item in the dataset. During the first round of training on the first model, the first network device can determine the first correction parameter based on the preset rules in the above embodiment. In this way, the first network device can determine the label information for each data item in the dataset based on the second correction parameter to train the first model.

[0201] During the second round of training for the first model, the first network device can adjust the first correction parameter according to a value predefined in the protocol (i.e., the adjustment step size of the correction parameter) to obtain a second correction parameter. In this way, the first network device can determine the label information of each data item in the data set based on the second correction parameter to train the first model.

[0202] The first network device may continue to adjust the correction parameters based on the values ​​predefined in the protocol (ie, the adjustment step of the correction parameters) to perform multiple rounds of training on the first model until the first model meets actual requirements.

[0203] It should be noted that the first correction parameter and the second correction parameter can be correction parameters for different training processes. The training process may also include a third correction parameter, a fourth correction parameter, etc., which are not exhaustive in the embodiments of the present application. The first correction parameter and the second correction parameter can be different, and the first correction parameter and the second correction parameter can be determined according to different methods.

[0204] For example, the error between the actual position of the first PRU and the estimated position of the first PRU is 10 meters. Based on the characteristic information of the first PRU and UE1, it can be determined that the first correction parameter in the first round of training is 2 meters. The first network device can use the first correction parameter to correct the label information of the terminal device to be corrected to train and obtain the first model. In the second round of training, the first network device can continue to calculate the error between the actual position of the first PRU and the estimated position of the first PRU. If the positioning accuracy of the first model still needs to be improved, the correction parameter is adjusted to obtain the second correction parameter. The second correction parameter can be 3 meters. In this way, the first network device can continue to use the correction parameter to correct the label information of the terminal device to be corrected, and train to obtain the first model. The training is repeated until the positioning accuracy reaches the first accuracy, so as to facilitate the adaptive adjustment of the correction parameter so that the accuracy of the first model meets the positioning accuracy requirements.

[0205] To sum up, in the embodiment of the present application, the first network device can gradually adjust the correction parameters according to the training results of the first model to gradually improve the processing accuracy / positioning accuracy of the first model.

[0206] In one embodiment of the present application, the first network device may send one or more of the following to the second terminal device:

[0207] Correct the parameters, data set, label information corresponding to each data in the data set, and the first model.

[0208] It is understandable that the first network device can send relevant parameters in the first model training process to the second terminal device.

[0209] In one possible implementation, the second terminal device can implement the training of the first model. In this scenario, the first network device can collect measurement information of multiple terminal devices in the network to construct a data set and determine correction parameters. The first network device can send the data set and the correction parameters to the second terminal device, so that the second terminal device can implement the training of the first model based on the data set and the correction parameters. Alternatively, the first network device can determine the label information corresponding to each data in the data set based on the correction parameters, and then send the data set and the label information corresponding to each data in the data set directly to the second terminal device, so that the second terminal device can implement the training of the first model. In this way, the first network device can directly send the data set, as well as the label information or correction parameters of each data in the data set to the second terminal device, which can reduce the complexity of the second terminal device in the data collection stage.

[0210] In another possible implementation, the second terminal device may not perform training on the first model; instead, the first network device collects and trains the first model dataset. In this scenario, the first network device can send the trained first model to the second terminal device. This allows the second terminal device to directly deploy the first model and use it for positioning. Because model training consumes significant processing resources, using the first network device to collect the dataset and train the first model can reduce the complexity and power consumption of the terminal device.

[0211] Optionally, the first network device may send the relevant information to the second terminal device via the LTE Positioning Protocol (LPP). Alternatively, the first network device may send the relevant information to the second network device, and the second network device may forward the relevant information to the first terminal device via high-layer signaling, physical layer signaling, or dedicated signaling.

[0212] In one embodiment of the present application, the first network device may actively send the above information to the second terminal device, and the first network device may also respond to a request from the second terminal device and send the above information to the second terminal device.

[0213] Optionally, the first network device receives request information sent by the second terminal device, where the request information is used to request correction of one or more items of parameters, a data set, label information corresponding to each data in the data set, and the first model.

[0214] Among them, the second terminal device can forward the request information to the first network device through the second network device, and the second terminal device can also send the above request information directly to the first network device through LPP. This embodiment of the present application does not limit this.

[0215] In summary, in the embodiments of the present application, correction parameters can be used to improve the accuracy of the label information of each data in the data set, thereby improving the reliability of the data set for model training and further improving the positioning accuracy of the model.

[0216] Based on the same inventive concept as above, an embodiment of the present application further provides a method for obtaining tag information. Referring to FIG12 , the method for obtaining tag information may include the following steps:

[0217] Step 1210: The second terminal device determines a data set and label information corresponding to each data in the data set; the label information is determined based on the correction parameter;

[0218] Step 1220: The second terminal device trains the first model based on the data set and the label information corresponding to each data in the data set.

[0219] It should be noted that the training of the first model can be implemented on the terminal device side.

[0220] Optionally, the data set used to train the first model and the label information corresponding to each data in the data set can be sent by the first network device to the second terminal device.

[0221] That is, the second terminal device can determine the data set used to train the first model and the label information corresponding to each data point in the data set based on the information sent by the first network device. In this way, the second terminal device can train the first model based on the received data set and the label information corresponding to each data point in the data set.

[0222] Optionally, the data set used to train the first model may be sent by the first network device to the second terminal device, and the label information corresponding to each data in the data set may be determined by the second terminal device based on the correction parameters. The correction parameters may be configured by the first network device for the second terminal device.

[0223] In other words, the second terminal device can determine the label information corresponding to each data item in the data set used to train the first model based on the correction parameters sent by the first network device. In this way, the second terminal device can train the first model based on the received data set and the label information corresponding to each data item in the data set determined by itself.

[0224] This shows that the second terminal device can use the corrected label information to train the first model, thereby improving the reliability of the data set used for training the first model and thus improving the positioning accuracy of the first model.

[0225] In one embodiment of the present application, in step 1210, the second terminal device determines the data set and the label information corresponding to each data in the data set, which can be achieved by:

[0226] The second terminal device receives the data set sent by the first network device, and the label information corresponding to each data in the data set; the label information corresponding to each data in the data set is determined by the first network device based on the correction parameter.

[0227] It is understood that the collection of the dataset and the label information corresponding to each data item in the dataset can be determined by the first network device and sent to the second terminal device. In other words, the second terminal device can determine the dataset used to train the first model and the label information corresponding to each data item in the dataset based on the information sent by the first network device.

[0228] In an embodiment of the present application, the second terminal device can use the received data set and the label information corresponding to each data in the data set to train the first model.

[0229] It can be seen that model training will take up a lot of processing resources. Collecting data sets and training the first model through the first network device can reduce the complexity of the terminal device and reduce the power consumption of the terminal device.

[0230] In another embodiment of the present application, the second terminal device determines the data set and the label information corresponding to each data in the data set in step 1210, which can also be implemented in the following manner:

[0231] The second terminal device receives the correction parameter and data set sent by the first network device;

[0232] The second terminal device determines label information corresponding to each data in the data set based on the correction parameter.

[0233] It is understood that the data set used to train the first model can be sent by the first network device to the second terminal device, and the label information corresponding to each data in the data set can be determined by the second terminal device based on the correction parameters. It should be noted that the correction parameters here can also be configured by the first network device for the second terminal device.

[0234] The first network device can send the data set and correction parameters to the second terminal device, so that the second terminal device can determine the label information corresponding to each data in the data set based on the received correction parameters, and thus train the first model based on the data set and the label information corresponding to each data in the data set.

[0235] It should be noted that the correction parameter can be determined by the first network device according to one or more of preset rules, protocol pre-defined, other network device configurations, and reports from the first terminal device. The determination of the correction parameter is the same as described in the above embodiment and will not be repeated here for the sake of brevity.

[0236] It can be seen from this that the first network device can directly send the data set and modify the parameters to the second terminal device, which can reduce the complexity of the second terminal device in the data collection stage.

[0237] It should be noted that the correction parameters, data set, and label information corresponding to each data in the data set may be actively sent by the first network device to the second terminal device, or requested by the second terminal device to the first network device.

[0238] In some embodiments, the second terminal device sends a request message to the first network device, where the request message is used to request correction parameters, a data set, label information corresponding to each data in the data set, and one or more items in the first model.

[0239] Optionally, the second terminal device may forward the request information to the first network device through the second network device, or the second terminal device may directly send the request information to the first network device through LPP, which is not limited in this embodiment of the present application.

[0240] It should be noted that the dataset used to train the first model may include a large amount of measurement information of the second terminal device. The second terminal device may send the measurement information to the first network device and / or send a first reference signal to the second network device. The first reference signal is used by the second network device to determine measurement information related to the second terminal device, and the measurement information is used to construct the dataset.

[0241] Optionally, the measurement information includes one or more of the following:

[0242] CIR, PDP, ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, azimuth, zenith angle.

[0243] It should be noted that the measurement information associated with each terminal device may be measurement information between each terminal device and a second network device. The measurement information associated with a terminal device may be for a single second network device or for multiple second network devices. In other words, the number of measurement information pieces may include one or more. When the number of measurement information pieces includes multiple pieces, the multiple measurement information pieces may be measurement results between the terminal device and multiple second network devices.

[0244] Optionally, the second terminal device may measure the downlink reference signal sent by the second network device, obtain and report the measurement information to the first network device. The second terminal device may also send the first reference signal, allowing the second network device to measure the first reference signal, obtain and report the measurement information to the first network device. In this way, the first network device can construct a data set based on the measurement information reported by the second terminal device and the second network device.

[0245] It should be noted that the first reference signal may be an uplink reference signal.

[0246] In an embodiment of the present application, before the second terminal device sends the measurement information to the first terminal device and / or the second terminal device, the method further includes:

[0247] The second terminal device receives trigger information, where the trigger information is used to trigger sending measurement information to the first network device and / or sending a first reference signal to the second network device.

[0248] Optionally, the trigger information includes: a reference signal type and / or a measurement type. The reference signal type includes one or more of the following:

[0249] PRS, SSB, SRS; wherein the first reference signal includes SRS.

[0250] Optionally, the measurement type can include any of the following:

[0251] Periodic measurement, non-periodic measurement, semi-continuous measurement, and time window measurement.

[0252] In an exemplary scenario, in which the first model is deployed in a second terminal device and the positioning method employs uplink-based positioning technology, an example flowchart is shown in FIG13 . It should be noted that the dashed lines in FIG13 represent optional steps. Referring to FIG13 , the first network device is a LMF, the second network device is a gNB, the first terminal device is a PRU, and the second terminal device is a UE. The UE may send a request message to the LMF to request a dataset for training the first model. After receiving the request message, the LMF may send a trigger message to the PRU and UE to trigger the PRU and UE to send an uplink reference signal (e.g., SRS) to the gNB. The gNB may measure the uplink reference signal sent by the UE / PRU. The gNB may report measurement information to the LMF. The measurement information may include one or more of CIR, PDP, ToA, UL TDoA, UL AoD, UL RTOA, RSRP, azimuth, and zenith angle. Furthermore, the LMF may determine correction parameters and send the determined correction parameters and the dataset to the UE. In this way, the UE can determine the label information corresponding to each data in the data set according to the correction parameter, and then the UE can train the first model based on the data set and the label information corresponding to each data in the data set.

[0253] In addition, in a scenario where the first model is deployed in a second terminal device and the positioning method uses downlink-based positioning technology, an example flowchart is shown in FIG14 . It should be noted that the dashed lines in FIG14 represent optional steps. Referring to FIG14 , the first network device is a LMF, the second network device is a gNB, the first terminal device is a PRU, and the second terminal device is a UE. The UE can send a request message to the LMF to request a dataset for training the first model. After receiving the request message, the LMF can send a trigger message to the PRU and UE. The trigger message can trigger the UE and PRU to measure downlink reference signals (e.g., PRS and / or SSB) sent by the gNB. The UE and PRU report measurement information obtained from the downlink reference signal measurements to the LMF, including one or more of CIR, PDP, ToA, DL TDoA, DL AoD, DL RSTD, RSRP, azimuth, and zenith angle. Furthermore, the LMF can determine correction parameters and send the determined correction parameters and the dataset to the UE. In this way, the UE can determine the label information corresponding to each data in the data set according to the correction parameter, and then the UE can train the first model based on the data set and the label information corresponding to each data in the data set.

[0254] In summary, in the embodiments of the present application, correction parameters can be used to improve the accuracy of the label information of each data in the data set, thereby improving the reliability of the data set for model training and further improving the positioning accuracy of the model.

[0255] The preferred embodiments of the present application are described in detail above in conjunction with the accompanying drawings. However, the present application is not limited to the specific details in the above embodiments. Within the technical concept of the present application, the technical solution of the present application can be subjected to a variety of simple modifications, and these simple modifications all fall within the scope of protection of the present application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present application will no longer describe the various possible combinations separately. For another example, the various different embodiments of the present application can also be arbitrarily combined, as long as they do not violate the idea of ​​the present application, they should also be regarded as the contents disclosed in the present application. For another example, under the premise of no conflict, the various embodiments and / or the technical features in each embodiment described in the present application can be arbitrarily combined with the prior art, and the technical solution obtained after the combination should also fall within the scope of protection of the present application.

[0256] It should also be understood that in the various method embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean 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 the present application.

[0257] FIG15 is a schematic diagram of the structure of an apparatus 1500 for obtaining tag information provided in an embodiment of the present application, which is applied to a first network device. As shown in FIG15 , the apparatus 1500 for obtaining tag information includes:

[0258] The first determination unit 1501 is configured to determine a correction parameter, and based on the correction parameter, determine label information corresponding to each data in the data set; the data set and the label information corresponding to each data in the data set are used to train the first model.

[0259] Optionally, the correction parameter is determined based on an error value between actual information and estimated information of the first terminal device.

[0260] Optionally, the number of the first terminal devices includes multiple, and the correction parameter is determined based on the average of the error values ​​between the actual information and the estimated information of the multiple first terminal devices.

[0261] Optionally, the correction parameter is determined based on the error value between the actual information and the estimated information of the first terminal device, and a first proportional parameter, wherein the first proportional parameter is used to characterize the positional relationship between the first terminal device and the second terminal device; the second terminal device is associated with at least part of the data in the data set.

[0262] Optionally, the first ratio parameter is greater than or equal to a first threshold.

[0263] Optionally, the first ratio parameter is determined based on feature information of the first terminal device and feature information of the second terminal device.

[0264] Optionally, the characteristic information includes one or more of the following:

[0265] Channel information, measurement information, first path power, channel impulse response, and spatial consistency related information.

[0266] Optionally, the correction parameter is determined based on one or more of the following:

[0267] The protocol is predefined, other network devices are configured, and the first terminal device reports.

[0268] Optionally, the tag information is location information, the actual information includes actual location information, the estimated information includes estimated location information, and the correction parameter includes a first location correction parameter in a first direction and / or a second location correction parameter in a second direction.

[0269] Optionally, the tag information is an intermediate parameter related to the location; the actual information includes the actual intermediate parameter, the estimated information includes the estimated intermediate parameter, and the intermediate parameter includes one or more of the following:

[0270] ToA, DL TDoA, DL AoD, DL RSTD, RSRP, and LOS / NLOS identification results.

[0271] Optionally, the apparatus for acquiring tag information further includes an acquiring unit configured to acquire measurement information related to a terminal device, where the measurement information is used to construct the data set; the terminal device includes a first terminal device and / or a second terminal device.

[0272] Optionally, the measurement information includes one or more of the following:

[0273] CIR, PDP, ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, azimuth, zenith angle.

[0274] Optionally, the apparatus for acquiring tag information further includes a first transceiver unit configured to send trigger information, where the trigger information is used to trigger one or more of the following devices to send the measurement information:

[0275] A second network device, a first terminal device, and a second terminal device.

[0276] Optionally, the trigger information includes: a reference signal type and / or a measurement type.

[0277] Optionally, the reference signal type includes one or more of the following:

[0278] Positioning reference signal PRS, synchronization signal block SSB, and sounding reference signal SRS.

[0279] Optionally, the measurement type includes any one of the following:

[0280] Periodic measurement, non-periodic measurement, semi-continuous measurement, and time window measurement.

[0281] Optionally, the measurement information sent by the first terminal device and / or the second terminal device includes one or more of the following:

[0282] CIR, PDP, ToA, DL TDoA, DL AoD, DL RSTD, RSRP, azimuth, zenith angle;

[0283] The measurement information sent by the second network device includes one or more of the following:

[0284] CIR, PDP, ToA, UL TDoA, UL AoD, UL RTOA, RSRP, azimuth, zenith angle.

[0285] Optionally, the device for obtaining label information further includes a first training unit configured to train the first model based on the data set and label information corresponding to each data in the data set.

[0286] Optionally, the first determination unit 1501 is configured to redetermine the correction parameters when the accuracy of the first model is less than the first accuracy, and update the label information corresponding to each data in the data set based on the redetermined correction parameters, and the updated labels are used to continue training the first model until the accuracy of the first model is greater than or equal to the first accuracy.

[0287] Optionally, the first transceiver unit is further configured to send one or more of the following to the second terminal device:

[0288] Correction parameters, a data set, label information corresponding to each data in the data set, and the first model.

[0289] Optionally, the first transceiver unit is further configured to receive request information sent by the second terminal device, where the request information is used to request one or more of the correction parameters, the data set, the label information corresponding to each data in the data set, and the first model.

[0290] Optionally, the first network device is a core network device, the second network device is an access network device, and the first terminal device is a terminal device whose actual information is known.

[0291] Those skilled in the art should understand that the relevant description of the above-mentioned device for obtaining tag information in the embodiment of the present application can be understood with reference to the relevant description of the method for obtaining tag information in the embodiment of the present application.

[0292] FIG16 is a schematic diagram of the structure of an apparatus 1600 for obtaining tag information provided in an embodiment of the present application, which is applied to a second terminal device. As shown in FIG16 , the apparatus 1600 for obtaining tag information includes:

[0293] The second determining unit 1601 is configured to determine a data set and label information corresponding to each data in the data set; the label information is determined based on the correction parameter;

[0294] The second training unit 1602 is configured to train the first model based on the data set and label information corresponding to each data in the data set.

[0295] Optionally, the device 1600 for obtaining label information also includes a second transceiver unit, which is configured to receive a data set sent by the first network device and label information corresponding to each data in the data set; the label information corresponding to each data in the data set is determined by the first network device based on the correction parameter.

[0296] Optionally, the second transceiver unit is further configured to receive the correction parameter and the data set sent by the first network device;

[0297] The second determining unit 1601 is further configured to determine label information corresponding to each data in the data set based on the correction parameter.

[0298] Optionally, the second transceiver unit is further configured to send a request message to the first network device, wherein the request message is used to request one or more of the correction parameters, the data set, the label information corresponding to each data in the data set, and the first model.

[0299] Optionally, the second transceiver unit is further configured to send measurement information to the first network device, and / or send a first reference signal to the second network device, wherein the first reference signal is used by the second network device to determine measurement information related to the second terminal device, and the measurement information is used to construct the data set.

[0300] Optionally, the measurement information includes one or more of the following:

[0301] CIR, PDP, ToA, UL TDoA, DL TDoA, UL AoD, DL AoD, UL RTOA, DL RSTD, RSRP, azimuth, zenith angle.

[0302] Optionally, the second transceiver unit is further configured to receive trigger information, where the trigger information is used to trigger sending measurement information to the first network device and / or sending the first reference signal to the second network device.

[0303] Optionally, the trigger information includes: a reference signal type and / or a measurement type.

[0304] Optionally, the reference signal type includes one or more of the following:

[0305] Positioning reference signal PRS, synchronization signal block SSB, sounding reference signal SRS; wherein the first reference signal includes the SRS.

[0306] Optionally, the measurement type includes any one of the following:

[0307] Periodic measurement, non-periodic measurement, semi-continuous measurement, and time window measurement.

[0308] Optionally, the first network device is a core network device, and the second network device is an access network device.

[0309] Those skilled in the art should understand that the relevant description of the above-mentioned device for obtaining tag information in the embodiment of the present application can be understood with reference to the relevant description of the method for obtaining tag information in the embodiment of the present application.

[0310] Figure 17 is a schematic diagram of a communication device 1700 provided in an embodiment of the present application. The electronic device can be a network device or a terminal device. The communication device 1700 shown in Figure 17 includes a processor 1710, which can call and execute a computer program from a memory to implement the method in the embodiment of the present application.

[0311] Optionally, as shown in FIG17 , the communication device 1700 may further include a memory 1720. The processor 1710 may call and execute a computer program from the memory 1720 to implement the method in the embodiment of the present application.

[0312] The memory 1720 may be a separate device independent of the processor 1710 , or may be integrated into the processor 1710 .

[0313] Optionally, the communication device 1700 may specifically be the first network device of the embodiment of the present application, and the communication device 1700 may implement the corresponding processes implemented by the first network device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0314] Optionally, the communication device 1700 may specifically be the second terminal device of the embodiment of the present application, and the communication device 1700 may implement the corresponding processes implemented by the second terminal device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0315] Figure 18 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 1800 shown in Figure 18 includes a processor 1810, which can call and run a computer program from a memory to implement the method according to the embodiment of the present application.

[0316] Optionally, as shown in FIG18 , the chip 1800 may further include a memory 1820 , wherein the processor 1810 may call and execute a computer program from the memory 1820 to implement the method in the embodiment of the present application.

[0317] The memory 1820 may be a separate device independent of the processor 1810 , or may be integrated into the processor 1810 .

[0318] Optionally, the chip 1800 may further include an input interface 1830. The processor 1810 may control the input interface 1830 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0319] Optionally, the chip 1800 may further include an output interface 1840. The processor 1810 may control the output interface 1840 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0320] Optionally, the chip can be applied to the first network device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the first network device in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0321] Optionally, the chip can be applied to the second terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the second terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0322] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0323] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0324] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0325] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0326] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0327] Optionally, the computer-readable storage medium can be applied to the first network device in the embodiment of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the first network device in the various methods of the embodiment of the present application. For the sake of brevity, they are not repeated here.

[0328] Optionally, the computer-readable storage medium can be applied to the second terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the second terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0329] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0330] Optionally, the computer program product can be applied to the first network device in the embodiment of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the first network device in the various methods of the embodiment of the present application. For the sake of brevity, they are not repeated here.

[0331] Optionally, the computer program product can be applied to the second terminal device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the second terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0332] The embodiment of the present application also provides a computer program.

[0333] Optionally, the computer program can be applied to the first network device in the embodiment of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the first network device in the various methods of the embodiment of the present application. For the sake of brevity, they are not repeated here.

[0334] Optionally, the computer program can be applied to the second terminal device in the embodiment of the present application. When the computer program runs on the computer, the computer executes the corresponding processes implemented by the second terminal device in the various methods of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0335] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0336] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0337] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0338] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0339] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0340] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0341] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for obtaining tag information, the method comprising: The first network device determines a correction parameter; The first network device determines, based on the correction parameter, label information corresponding to each data in the data set; The data set and label information corresponding to each data in the data set are used to train the first model.

2. The method according to claim 1, wherein The correction parameter is determined based on an error value between actual information and estimated information of the first terminal device.

3. The method according to claim 2, wherein: The number of the first terminal devices includes multiple, The correction parameter is determined based on an average of error values ​​between actual information and estimated information of multiple first terminal devices.

4. The method according to any one of claims 1 to 3, wherein: The correction parameter is determined based on an error value between actual information and estimated information of the first terminal device, and a first proportional parameter, where the first proportional parameter is used to characterize a positional relationship between the first terminal device and the second terminal device; The second terminal device is associated with at least part of the data in the data set.

5. The method according to claim 4, wherein The first ratio parameter is greater than or equal to a first threshold.

6. The method according to claim 4 or 5, wherein: The first ratio parameter is determined based on feature information of the first terminal device and feature information of the second terminal device.

7. The method according to claim 6, wherein: The characteristic information includes one or more of the following: Channel information, measurement information, first path power, channel impulse response, and spatial consistency related information.

8. The method according to claim 1, wherein The correction parameter is determined based on one or more of the following: The protocol is predefined, other network devices are configured, and the first terminal device reports.

9. The method according to any one of claims 1 to 8, wherein: The tag information is position information, the actual information includes actual position information, the estimated information includes estimated position information, and the correction parameter includes a first position correction parameter in a first direction and / or a second position correction parameter in a second direction.

10. The method according to any one of claims 1 to 8, wherein: The tag information is an intermediate parameter related to the location; the actual information includes the actual intermediate parameter, and the estimated information includes the estimated intermediate parameter, and the intermediate parameter includes one or more of the following: Time of arrival (ToA), uplink time difference of arrival (UL TdoA), downlink time difference of arrival (DL TDoA), uplink angle of departure (UL AoD), downlink angle of departure (DL AoD), uplink relative time of arrival (UL RTOA), downlink signal time difference (DL RSTD), reference signal received power (RSRP), and line-of-sight / non-line-of-sight (LOS / NLOS) identification results.

11. The method according to any one of claims 1 to 10, wherein: The method further comprises: The first network device obtains measurement information related to the terminal device, and the measurement information is used to construct the data set; the terminal device includes a first terminal device and / or a second terminal device.

12. The method according to claim 11, wherein The measurement information includes one or more of the following: Channel impulse response (CIR), power delay profile (PDP), time of arrival (ToA), uplink time difference of arrival (UL TDoA), downlink time difference of arrival (DL TDoA), uplink angle of departure (UL AoD), downlink angle of departure (DL AoD), uplink relative time of arrival (UL RTOA), downlink signal time difference (DL RSTD), reference signal received power (RSRP), azimuth angle, and zenith angle.

13. The method according to claim 11, wherein Before the first network device obtains the measurement information related to the terminal device, the method further includes: The first network device sends trigger information, where the trigger information is used to trigger one or more of the following devices to send the measurement information: A second network device, a first terminal device, and a second terminal device.

14. The method according to claim 13, wherein The trigger information includes: a reference signal type and / or a measurement type.

15. The method according to claim 14, wherein The reference signal type includes one or more of the following: Positioning reference signal PRS, synchronization signal block SSB, and sounding reference signal SRS.

16. The method according to claim 14, wherein The measurement type includes any of the following: Periodic measurement, non-periodic measurement, semi-continuous measurement, and time window measurement.

17. The method according to claims 13-16, wherein: The measurement information sent by the first terminal device and / or the second terminal device includes one or more of the following: CIR, PDP, ToA, DL TDoA, DL AoD, DL RSTD, reference signal received power RSRP, azimuth, zenith angle; The measurement information sent by the second network device includes one or more of the following: CIR, PDP, ToA, UL TDoA, UL AoD, UL RTOA, RSRP, azimuth, zenith angle.

18. The method according to any one of claims 1 to 17, wherein: The method further comprises: The first network device trains the first model based on the data set and label information corresponding to each data in the data set.

19. The method according to claim 18, wherein The method further comprises: When the accuracy of the first model is less than the first accuracy, the correction parameters are re-determined, and the label information corresponding to each data in the data set is updated based on the re-determined correction parameters. The updated labels are used to continue training the first model until the accuracy of the first model is greater than or equal to the first accuracy.

20. The method according to any one of claims 1 to 19, wherein: The method further comprises: The first network device sends one or more of the following to the second terminal device: Correction parameters, a data set, label information corresponding to each data in the data set, and the first model.

21. The method according to claim 20, wherein The method further comprises: The first network device receives a request message sent by the second terminal device, where the request message is used to request one or more of the correction parameters, the data set, label information corresponding to each data in the data set, and the first model.

22. The method according to any one of claims 1 to 20, wherein: The first network device is a core network device, the second network device is an access network device, and the first terminal device is a terminal device whose actual information is known.

23. A method for obtaining label information of a data set, the method comprising: The second terminal device determines a data set and label information corresponding to each data in the data set; The label information is determined based on the correction parameter; The second terminal device trains the first model based on the data set and label information corresponding to each data in the data set.

24. The method according to claim 23, wherein The second terminal device determines a data set and label information corresponding to each data in the data set, including: The second terminal device receives the data set sent by the first network device, and the label information corresponding to each data in the data set; the label information corresponding to each data in the data set is determined by the first network device based on the correction parameter.

25. The method according to claim 23, wherein The second terminal device determines a data set and label information corresponding to each data in the data set, including: The second terminal device receives the correction parameter and the data set sent by the first network device; The second terminal device determines label information corresponding to each data in the data set based on the correction parameter.

26. The method according to any one of claims 23 to 25, wherein: The method further comprises: The second terminal device sends a request message to the first network device, where the request message is used to request one or more of the correction parameters, the data set, label information corresponding to each data in the data set, and the first model.

27. The method according to any one of claims 23 to 26, wherein: The method further comprises: The second terminal device sends measurement information to the first network device, and / or sends a first reference signal to the second network device, where the first reference signal is used by the second network device to determine measurement information related to the second terminal device, and the measurement information is used to construct the data set.

28. The method according to claim 27, wherein The measurement information includes one or more of the following: Channel impulse response (CIR), power delay profile (PDP), time of arrival (ToA), uplink time difference of arrival (UL TDoA), downlink time difference of arrival (DL TDoA), uplink angle of departure (UL AoD), downlink angle of departure (DL AoD), uplink relative time of arrival (UL RTOA), downlink signal time difference (DL RSTD), reference signal received power (RSRP), azimuth angle, and zenith angle.

29. The method according to claim 27 or 28, wherein Before the second terminal device sends the measurement information to the first terminal device and / or the second terminal device, the method further includes: The second terminal device receives trigger information, where the trigger information is used to trigger sending measurement information to the first network device and / or sending the first reference signal to the second network device.

30. The method according to claim 29, wherein The trigger information includes: a reference signal type and / or a measurement type.

31. The method according to claim 30, wherein The reference signal type includes one or more of the following: Positioning reference signal PRS, synchronization signal block SSB, sounding reference signal SRS; wherein the first reference signal includes the SRS.

32. The method according to claim 30, wherein The measurement type includes any of the following: Periodic measurement, non-periodic measurement, semi-continuous measurement, and time window measurement.

33. The method according to any one of claims 23 to 32, wherein: The first network device is a core network device, and the second network device is an access network device.

34. A device for obtaining tag information, applied to a first network device, comprising: a first determining unit configured to determine a correction parameter, and determine label information corresponding to each data in the data set based on the correction parameter; The data set and label information corresponding to each data in the data set are used to train the first model.

35. A device for obtaining tag information, applied to a second terminal device, comprising: A second determining unit is configured to determine a data set and label information corresponding to each data in the data set; The label information is determined based on the correction parameter; The second training unit is configured to train the first model based on the data set and label information corresponding to each data in the data set.

36. A network device comprising: Memory, processors, and transceivers, The transceiver is used to realize communication with the terminal device; The memory stores a computer program executable on the processor. When the processor executes the program in conjunction with the transceiver, the method according to any one of claims 1 to 22 is implemented.

37. A terminal device comprising: Memory, processors, and transceivers, The transceiver is used to realize communication with the terminal device; The memory stores a computer program executable on the processor. When the processor executes the program in conjunction with the transceiver, the method according to any one of claims 23 to 33 is implemented.

38. A computer storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the method according to any one of claims 1 to 22, or 23 to 33.

39. A chip comprising: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 22, or 23 to 33.

40. A computer program product, comprising a computer storage medium storing a computer program, wherein the computer program comprises instructions executable by at least one processor, and wherein when the instructions are executed by the at least one processor, the method according to any one of claims 1 to 22, or 23 to 33 is implemented.

41. A computer program, which enables a computer to execute the method according to any one of claims 1 to 22, or 23 to 33.

Images