Model acquisition method, apparatus, and system

Abstract

The present application provides a model acquisition method, an apparatus, and a system, for use in enabling a location management function network element to select a model more adapted to the current environment, so as to achieve a better locating effect. The method comprises: a location management function network element sends a first message to a network data analytics function network element, wherein the first message is used for requesting to acquire a locating model; and on the basis of the first message, the network data analytics function network element trains a first locating model and sends the first locating model to the location management function network element, wherein the first locating model is used for locating a terminal device.

Description

Model acquisition method, device and system

[0001] This application claims priority to the Chinese patent applications filed with the State Intellectual Property Office on July 20, 2023, with application number 202310902021.1 and application name “Model Acquisition Method, Device and System” and filed with the State Intellectual Property Office on January 12, 2024, with application number 202410051647.0 and application name “Model Acquisition Method, Device and System”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] This application relates to the field of AI positioning, and in particular to model acquisition methods, devices and systems. Background Art

[0003] Traditional wireless positioning algorithms have poor positioning accuracy in certain scenarios and cannot meet the requirements of high-precision positioning. To improve positioning accuracy, artificial intelligence (AI) positioning solutions have been proposed. In current AI positioning solutions, a location management function (LMF) acquires training data and feeds it into an AI / machine learning (ML) model deployed locally on the LMF. The LMF then estimates the terminal device's location based on the output of the AI / ML model.

[0004] However, obtaining high-precision terminal device location information in different environments places different demands on AI / ML models. In current AI positioning solutions, the local AI / ML models in LMF are pre-configured within the LMF. As the environment changes, they may no longer meet the positioning requirements in the current environment.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a model acquisition method, device and system for solving the problem that a location management network element can only be positioned according to a local pre-configured model, and the positioning effect may be poor.

[0007] To achieve the above objectives, this application adopts the following technical solutions:

[0008] In a first aspect, a model acquisition method is provided. The method can be executed by a location management function network element, or by a component of the location management function network element, such as a processor, chip, or chip system of the location management function network element, or by a logic module or software that implements all or part of the location management function network element's functions. The method includes: the location management function network element sending a first message to a network data analysis function network element, the first message being used to request acquisition of a positioning model; the location management function network element receiving the first positioning model from the network data analysis function network element; and using the first positioning model to locate the position of a terminal device.

[0009] Based on this solution, the location management function network element can obtain the trained positioning model from the network data analysis function network element, and does not have to use only the locally deployed positioning model. This enables the location management function network element to select a model that is more suitable for the current environment to achieve better positioning effects.

[0010] In one possible design, the first message includes model requirement information; the model requirement information is used to indicate the requirements of the location management function network element for the positioning model; the model requirement information includes at least one item of model structure requirement information and model generalization capability requirement information; wherein, the model structure requirement information is used to indicate the requirements of the location management function network element for the model structure of the positioning model; the model generalization capability requirement information is used to indicate the requirements of the location management function network element for the model generalization capability of the positioning model.

[0011] In a possible design, the model structure requirement information is identification information of the model structure type required by the location management function network element.

[0012] In one possible design, the model generalization capability requirement information includes information indicating the requirements of the location management function network element on the model performance of the positioning model under different test data sets.

[0013] In one possible design, the different test data sets are test data sets under different terminal device transmission powers; or, the different test data sets are test data sets under different network synchronization errors; or, the different test data sets are test data sets under different terminal device timing errors.

[0014] In one possible design, the first message includes model type indication information; the model type indication information is used to indicate that the type of model requested by the location management function network element is a positioning model.

[0015] In one possible design, the method further includes: the location management function network element receives model information from the network data analysis function network element; the model information includes one or more model feature information of the first positioning model.

[0016] In one possible design, the first message includes second information; the second information is used to instruct the network data analysis function network element to autonomously determine a positioning model that meets the current environmental requirements.

[0017] Based on this solution, the network data analysis function network element can independently determine what kind of positioning model to provide to the location management function network element, providing a solution to the problem that some location management function network elements cannot independently determine what kind of model they need.

[0018] In one possible design, the method also includes: the location management function network element receives first environment identification information from the network data analysis function network element; the first environment identification information corresponds to the first positioning model, and the first environment identification information is used to identify the environment corresponding to the first positioning model.

[0019] Based on this solution, the network data analysis function network element can provide the location management function network element with first environment identification information for identifying the environment corresponding to the first positioning model, so that the location management function network element can determine the environment to which the first positioning model is applicable.

[0020] In one possible design, the method also includes: the location management function network element obtains second environment identification information, and the second environment identification information is used to identify the current environment; the location management function network element selects a target positioning model from multiple positioning models based on the environment identification information corresponding to the multiple positioning models; the multiple positioning models include a first positioning model and one or more second positioning models; the environment identification information corresponding to the target positioning model is the same as the second environment identification information.

[0021] Based on this solution, if multiple positioning models have been deployed on the location management function network element, the location management function network element can obtain environmental identification information that identifies the current environment from other network elements, and select a positioning model suitable for the current environment for positioning based on the environmental identification information.

[0022] In one possible design, the second positioning model is locally deployed by the location management function network element; or, the second positioning model is sent by the network data analysis function network element to the location management function network element.

[0023] In one possible design, the method also includes: the location management function network element receives a second message from the network data analysis function network element, the second message is used to request to obtain training data, and the second message includes event identification information; the event identification information is used to identify the requested training data, and the training data includes at least one of the following: channel impulse response, channel energy response, and channel power delay distribution; the location management function network element obtains the training data based on the event identification information; the location management function network element sends the training data to the network data analysis function network element; the training data is used to train the first positioning model.

[0024] Based on an embodiment of the present application, a method is provided for a network data analysis function network element to obtain at least one piece of data among channel impulse response, channel energy response, and channel power delay distribution as training data for a positioning model. The network data analysis function network element can train the positioning model based on the obtained data to improve the model accuracy of the positioning model.

[0025] In one possible design, the method also includes: the location management function network element receives a third message from the network data analysis function network element, the third message is used to request the location information of the terminal device; the third message includes first indication information, the first indication information is used to indicate a first capability of the terminal device, the first capability is the ability of the terminal device to provide its own first location information; the location management function network element obtains the first location information of the terminal device based on the correspondence between the pre-configured terminal device and the first capability; the location management function network element sends the first location information of the terminal device to the network data analysis function network element; the first location information of the terminal device is used to train the first positioning model.

[0026] Based on the embodiment of the present application, a method is provided for a network data analysis function network element to obtain terminal location information with a smaller error than the actual terminal device location, which can improve the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0027] In one possible design, the location management function network element obtains the first location information of the terminal device, including: the location management function network element obtains the first location information of the pre-configured terminal device; or, the location management function network element receives the first location information from the terminal device.

[0028] In a second aspect, a data acquisition method is provided. The method can be executed by a location management function network element, or by a component of the location management function network element, such as a processor, chip, or chip system of the location management function network element, or by a logic module or software that can implement all or part of the location management function network element's functions. The method includes: the location management function network element receiving a second request message from the network data analysis function network element; the location management function network element sending a second response message to the network data analysis function network element; wherein the second request message is used to request the acquisition of the location information of a terminal device; and the second response message is used to indicate the location information of M terminal devices, where M is a positive integer.

[0029] Based on this solution, a method is provided for a network data analysis function network element to request to obtain the location information of a terminal device. The first network element can send more location information of terminal devices, expand the data training set, and thus improve the model accuracy of the positioning model.

[0030] In one possible design, the location management function network element receives identification information of a positioning reference unit (PRU) PRU of a terminal device from a network data analysis function network element; or, the second request message includes identification information of the PRU of the terminal device; wherein the location information of the M terminal devices is location information corresponding to the identification information of the PRU of the M terminal devices.

[0031] Based on the embodiments of the present application, the network data analysis function network element can request to obtain the location information corresponding to the identification information of the terminal device or the PRU of the terminal device, so that the label of the training data can better meet the needs of positioning model training, and provide a feasible solution for the network data analysis function network element to request to obtain the location information of the PRU of the terminal device.

[0032] In one possible design, the location management function network element receives second indication information from the network data analysis function network element; or, the second request message also includes second indication information; wherein the second indication information is used to indicate the acquisition of location information of the terminal device used for model training; the location information of the M terminal devices is the location information of one or more terminal devices with PRU and / or the location information of one or more terminal devices without PRU.

[0033] Based on the embodiment of the present application, the first network element can send more location information of terminal devices, expand the data training set, and thus improve the model accuracy of the positioning model.

[0034] In one possible design, the location management function network element receives third indication information from the network data analysis function network element; or, the second request message also includes third indication information; wherein the third indication information is used to indicate the acquisition of the location information of the PRU of the terminal device; the location information of M terminal devices is the location information of M terminal devices with PRU.

[0035] Based on the embodiments of the present application, the network data analysis function network element can request to obtain the location information of the PRU of the terminal device. Since the positioning accuracy of the location information of the PRU of the terminal device is relatively high, the accuracy of the label of the training data of the positioning model (the label of the training data is the location information of the terminal device) can be improved, thereby improving the model accuracy of the positioning model.

[0036] In one possible design, the location management function network element receives quantity threshold information from the network data analysis function network element; or, the second request message also includes quantity threshold information; wherein the quantity threshold information is used to indicate the quantity threshold of the location information of the terminal device that is expected to be obtained.

[0037] Based on the embodiments of the present application, the amount of location information of the terminal device sent by the first network element can be limited. On the one hand, it can ensure as much as possible that the amount of location information of the terminal device obtained by the network data analysis function network element meets the requirements of positioning model training, and the model accuracy of the positioning model can be improved; on the other hand, it can ensure as much as possible that the amount of location information of the terminal device obtained by the network data analysis function network element is limited to a certain range, which can reduce transmission overhead and improve the training efficiency of the positioning model.

[0038] In one possible design, the location management function network element receives fourth indication information from the network data analysis function network element; or, the second request message also includes fourth indication information; the location management function network element determines the location information of M terminal devices based on the fourth indication information; wherein the fourth indication information is used to indicate quality requirement information; the quality of the location information of the M terminal devices meets the quality requirements.

[0039] Based on the embodiment of the present application, the location management function network element determines the location information of M terminal devices according to the fourth indication information, which can ensure that the positioning accuracy of the location information of each terminal device in the M terminal devices is as high as possible, and then ensure that the accuracy of the label of the training data of the positioning model is as high as possible, thereby improving the model accuracy of the positioning model.

[0040] In one possible design, the location management function network element receives the fifth indication information from the network data analysis function network element; or, the second request message also includes the fifth indication information; the location management function network element determines the location information of M terminal devices based on the fifth indication information; wherein the fifth indication information is used to indicate the ratio threshold of the number of terminal devices with PRUs and the number of all terminal devices in the location information of the terminal devices to be obtained; the ratio of the number of terminal devices with PRUs in the M terminal devices to M meets the ratio threshold.

[0041] Based on the embodiment of the present application, the first network element determines the location information of M terminal devices according to the fifth indication information, so that the number of terminal devices with PRUs can be larger (that is, the positioning accuracy of the location information of the PRUs of the terminal devices is higher), and thus the accuracy of the labels of the training data of the positioning model can be ensured as much as possible, thereby improving the model accuracy of the positioning model.

[0042] In one possible design, the location management function network element sends quality information corresponding to the location information of M terminal devices to the network data analysis function network element; or, the second response message also includes quality information corresponding to the location information of M terminal devices.

[0043] In one possible design, the location management function network element receives a third request information from the network data analysis function network element; or, the second request message also includes a third request information; wherein the third request information is used to request quality information corresponding to the location information of the terminal device.

[0044] Based on the above two possible designs, the location management function network element can actively send quality information to the network data analysis function network element, or send quality information to the network data analysis function network element based on the third request information; in addition, the network data analysis function network element can determine the quality corresponding to the location information of M terminal devices, and then determine the location information of N terminal devices based on the quality, so as to ensure that the positioning accuracy of the location information of each terminal device in the N terminal devices is as high as possible, and the accuracy of the labels of the training data of the positioning model can be improved, thereby improving the model accuracy of the positioning model.

[0045] In one possible design, the location management function network element sends sixth indication information to the network data analysis function network element; or, the second response message also includes sixth indication information; wherein the sixth indication information is used to indicate whether a PRU exists for each of the M terminal devices.

[0046] Based on the embodiments of the present application, the network data analysis function network element can determine the location information of the PRU of the terminal device as much as possible (that is, the positioning accuracy of the location information of the PRU of the terminal device is high), which can improve the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0047] In one possible design, the location management function network element sends seventh indication information to the network data analysis function network element; or, the second response message also includes seventh indication information; wherein the seventh indication information is used to indicate the location generation method corresponding to the location information of each terminal device among the M terminal devices.

[0048] Based on the embodiments of the present application, the positioning accuracy of the terminal device's location information corresponding to different generation methods is different, which can enable the network data analysis function network element to determine the terminal device's location information with higher positioning accuracy based on the generation method corresponding to the terminal device's location information; or, the network data analysis function network element can determine the terminal device's location information with higher positioning accuracy based on quality information, thereby improving the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0049] In one possible design, the location management function network element receives a fourth request message from the network data analysis function network element; or, the second request message also includes a fourth request message; the location management function network element sends the first data corresponding to the location information of M terminal devices to the network data analysis function network element; wherein the fourth request information is used to request the first data corresponding to the location information of the M terminal devices; the first data is used to train a first positioning model.

[0050] Based on the embodiments of the present application, the network data analysis function network element can receive the first data corresponding to the location information of the terminal device at the same time as receiving the location information of the terminal device, and can ensure that the first data and the label of the first data are consistent in time as much as possible, and propose a feasible solution for associating the first data and the label of the first data.

[0051] In one possible design, the location information of each terminal device also includes time information; or, the second response message includes time information corresponding to the location information of each terminal device; wherein the time information is used to indicate the time when the location information is obtained.

[0052] Based on the embodiments of the present application, a feasible solution is provided for determining the time corresponding to the location information.

[0053] In a third aspect, a model acquisition method is provided. The method can be executed by a network data analysis function network element, or by a component of the network data analysis function network element, such as a processor, chip, or chip system of the network data analysis function network element. The method can also be implemented by a logic module or software that can implement all or part of the functions of the network data analysis function network element. The method includes: the network data analysis function network element receives a first message from a location management function network element, the first message being used to request acquisition of a positioning model; the network data analysis function network element trains a first positioning model based on the first message; and the network data analysis function network element sends the first positioning model to the location management function network element.

[0054] Based on this solution, the location management function network element can obtain the trained positioning model from the network data analysis function network element, and does not have to use only the locally deployed positioning model. This enables the location management function network element to select a model that is more suitable for the current environment to achieve better positioning effects.

[0055] In one possible design, the first message includes model requirement information; the model requirement information is used to indicate the requirements of the location management function network element for the positioning model; the model requirement information includes at least one of model structure requirement information and model generalization capability requirement information; wherein, the model structure requirement information is used to indicate the requirements of the location management function network element for the model structure of the positioning model; the model generalization capability requirement information is used to indicate the requirements of the location management function network element for the model generalization capability of the positioning model.

[0056] In a possible design, the model structure requirement information is identification information of the structure type required by the location management function network element.

[0057] In a possible design, the model generalization capability requirement information is used to indicate the requirements of the location management function network element on the model performance of the positioning model under different test data sets.

[0058] In one possible design, the different test data sets are test data sets under different terminal device transmission powers; or, the different test data sets are test data sets under different network synchronization errors; or, the different test data sets are test data sets under different terminal device timing errors.

[0059] In one possible design, the first message includes model type indication information; the model type indication information is used to indicate that the type of model requested by the location management function network element is a positioning model.

[0060] In one possible design, the method also includes: the network data analysis function network element sends model information to the location management function network element; the model information includes one or more model feature information of the first positioning model.

[0061] In one possible design, the first message includes second information; the second information is used to instruct the network data analysis function network element to autonomously determine a positioning model that meets the current environmental requirements.

[0062] Based on this solution, the network data analysis function network element can independently determine what kind of positioning model to provide to the location management function network element, providing a solution to the problem that some location management function network elements cannot independently determine what kind of model they need.

[0063] In one possible design, the network data analysis function network element trains a first positioning model based on the first message, including: the network data analysis function network element determines the first environment identification information corresponding to the current environment based on the first message; the network data analysis function network element trains the first positioning model corresponding to the first environment identification information based on the first environment identification information.

[0064] Based on this solution, the network data analysis function network element can determine the environmental identifier of the current environment, and determine the model that needs to be trained based on the environmental identifier, thereby training a positioning model suitable for the current environment.

[0065] In one possible design, the method also includes: the network data analysis function network element sends first environment identification information to the location management function network element.

[0066] Based on this solution, the network data analysis function network element can provide the location management function network element with first environment identification information for identifying the environment corresponding to the first positioning model, so that the location management function network element can determine the environment to which the first positioning model is applicable.

[0067] In one possible design, the method also includes: the network data analysis function network element receives a first request message from the location management function network element; the first request message is used to request the network data analysis function network element to provide environment identification information; the network data analysis function network element determines the second environment identification information based on the first request information; the network data analysis function network element sends the second environment identification information to the location management function network element.

[0068] Based on this solution, the network data analysis function network element can provide the location management function network element with environment identification information that identifies the current environment, so as to assist the location management function network element in selecting a positioning model that is suitable for the current environment.

[0069] In one possible design, the method also includes: the network data analysis function network element sends a second message to the first network element, the second message is used to request training data, and the second message includes event identification information; the event identification information is used to identify the requested training data, and the training data includes at least one of the following: channel impulse response, channel energy response, and channel power delay distribution; the network data analysis function network element receives the training data from the first network element; the network data analysis function network element trains the first positioning model, including: the network data analysis function network element trains the first positioning model based on the training data.

[0070] Based on an embodiment of the present application, a method is provided for a network data analysis function network element to obtain at least one piece of data among channel impulse response, channel energy response, and channel power delay distribution as training data for a positioning model. The network data analysis function network element can train the positioning model based on the obtained data to improve the model accuracy of the positioning model.

[0071] In one possible design, the first network element is a location management function network element, an operation, supervision and management function network element, a session management function network element, an access and mobility management function network element, or an application function network element.

[0072] In one possible design, the method also includes: the network data analysis function network element sends a third message to the location management function network element: the third message is used to request the location information of the terminal device; the network data analysis function network element receives the first location information of the terminal device from the location management function network element; the network data analysis function network element trains the first positioning model, including: the network data analysis function network element trains the first positioning model based on the first location information of the terminal device.

[0073] Based on the embodiment of the present application, a method is provided for a network data analysis function network element to obtain terminal location information with a smaller error than the actual terminal device location, which can improve the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0074] In one possible design, before the network data analysis function network element sends the third message to the location management function network element, the method also includes: the network data analysis function network element sends a fourth message to the data management network element, the fourth message includes first indication information, the first indication information is used to indicate the first capability of the terminal device, the first capability is the ability of the terminal device to provide its own first location information; the fourth message is used to request the identification of the terminal device with the first capability; the network data analysis function network element receives the identification information of the terminal device corresponding to the first indication information from the data management network element; the identification information of the terminal device is carried in the third message, and the identification information of the terminal device is used by the location management function network element to determine the first location information of the terminal device.

[0075] In one possible design, the method also includes: the network data analysis function network element sends a third message to the data management network element, the third message includes first indication information, the first indication information is used to indicate the first capability of the terminal device, the first capability is the ability of the terminal device to provide its own first location information: the third message is used to request to obtain the first location information of the terminal device with the first capability; the network data analysis function network element receives the first location information of the terminal device from the data management network element; the network data analysis function network element trains the first positioning model, including: the network data analysis function network element trains the first positioning model according to the first location information of the terminal device.

[0076] In one possible design, the method also includes: the network data analysis function network element receives information on the effective time corresponding to the first location information of the terminal device from the data management network element.

[0077] In a fourth aspect, a data acquisition method is provided, which can be executed by a network data analysis function network element, or by a component of the network data analysis function network element, such as a processor, chip, or chip system of the network data analysis function network element, or can be implemented by a logic module or software that can realize all or part of the network data analysis function network element function. The method includes: the network data analysis function network element sends a second request message to the first network element; the network data analysis function network element receives a second response message from the first network element; the network data analysis function network element determines the location information of N terminal devices based on the second response message; the network data analysis function network element trains a first positioning model based on the location information of the N terminal devices. The second request message is used to request the location information of the terminal device; the second response message is used to indicate the location information of M terminal devices; M is a positive integer; and N is a positive integer less than or equal to M.

[0078] Based on an embodiment of the present application, a method is provided for a network data analysis function network element to request the location information of a terminal device. The network data analysis function network element can obtain the location information of more terminal devices, expand the data training set, and thus improve the model accuracy of the positioning model.

[0079] In one possible design, the network data analysis function network element sends the identification information of the PRU of the terminal device to the first network element; or, the second request message includes the identification information of the PRU of the terminal device; wherein, the location information of the M terminal devices is the location information corresponding to the identification information of the PRU of the M terminal devices.

[0080] Based on the embodiment of the present application, the network data analysis function network element can request to obtain the location information corresponding to the identification information of the terminal device or the PRU of the terminal device, so that the label of the training data can better meet the requirements of positioning model training, and provide a feasible solution for the network data analysis function network element to request to obtain the location information of the PRU of the terminal device.

[0081] In one possible design, the network data analysis function network element sends a second indication information to the first network element; or, the second request message also includes the second indication information; wherein the second indication information is used to indicate the acquisition of the location information of the terminal device used for model training; the location information of the M terminal devices is the location information of one or more terminal devices with PRUs and / or the location information of one or more terminal devices without PRUs.

[0082] Based on the embodiment of the present application, the network data analysis function network element receives location information of more terminal devices, which can expand the data training set and thus improve the model accuracy of the positioning model.

[0083] In one possible design, the network data analysis function network element sends a third indication information to the first network element; or, the second request message also includes a third indication information; wherein the third indication information is used to indicate the acquisition of the location information of the PRU of the terminal device; the location information of the M terminal devices is the location information of the M terminal devices with PRUs.

[0084] Based on the embodiment of the present application, the network data analysis function network element can request to obtain the location information of the PRU of the terminal device. Since the positioning accuracy of the location information of the PRU of the terminal device is relatively high, the accuracy of the label of the training data of the positioning model (the label of the training data is the location information of the terminal device) can be improved, thereby improving the model accuracy of the positioning model.

[0085] In one possible design, the network data analysis function network element sends quantity threshold information to the first network element; or, the second request message also includes quantity threshold information; wherein the quantity threshold information is used to indicate the quantity threshold of the location information of the terminal device that is expected to be obtained.

[0086] Based on the embodiments of the present application, the network data analysis function network element can limit the amount of location information of terminal devices that it is desired to obtain. On the one hand, it can ensure that the amount of location information of terminal devices obtained meets the requirements of positioning model training as much as possible, and the model accuracy of the positioning model can be improved; on the other hand, it can ensure that the amount of location information of terminal devices obtained is limited to a certain range as much as possible, which can reduce transmission overhead and improve the training efficiency of the positioning model.

[0087] In one possible design, the network data analysis function network element sends fourth indication information to the first network element; or, the second request message also includes fourth indication information; wherein, the fourth indication information is used to indicate quality requirement information; the quality of the location information of the M terminal devices meets the quality requirements.

[0088] Based on the embodiment of the present application, the first network element can determine the location information of M terminal devices according to the fourth indication information, and can ensure that the positioning accuracy of the location information of each terminal device in the M terminal devices is as high as possible, and then can ensure that the accuracy of the label of the training data of the positioning model is as high as possible, thereby improving the model accuracy of the positioning model.

[0089] In one possible design, the network data analysis function network element sends fifth indication information to the first network element; or, the second request message also includes fifth indication information; wherein the fifth indication information is used to indicate a ratio threshold of the number of terminal devices with PRUs in the location information of the terminal devices to be obtained and the number of all terminal devices obtained; the ratio of the number of terminal devices with PRUs in M ​​terminal devices to M satisfies the ratio threshold.

[0090] Based on the embodiment of the present application, the first network element can determine the location information of M terminal devices according to the fifth indication information, so that the number of terminal devices with PRUs can be large (that is, the positioning accuracy of the location information of the PRUs of the terminal devices is high), and thus the accuracy of the labels of the training data of the positioning model can be ensured as high as possible, thereby improving the model accuracy of the positioning model.

[0091] In one possible design, the network data analysis function network element receives quality information corresponding to the location information of M terminal devices from the first network element; or, the second response message also includes quality information corresponding to the location information of M terminal devices; or, the network data analysis function network element determines the quality corresponding to the location information of M terminal devices based on the positioning accuracy of the location information of the terminal devices; the network data analysis function network element determines the location information of N terminal devices based on the quality information corresponding to the location information of M terminal devices.

[0092] In one possible design, the network data analysis function network element sends a third request information to the first network element; or, the second request message also includes a third request information; wherein the third request information is used to request quality information corresponding to the location information of the terminal device.

[0093] Based on the above two possible designs, the network data analysis function network element can directly receive the quality information, or it can request the first network element to send the third request information through the third request information and then receive the quality information; in addition, the network data analysis function network element can determine the quality corresponding to the location information of the terminal device according to the quality information or positioning accuracy, and can determine the location information of N terminal devices according to the quality corresponding to the location information of the terminal device, and can ensure that the positioning accuracy of the location information of each terminal device in the N terminal devices is as high as possible, and can improve the accuracy of the label of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0094] In one possible design, the network data analysis function network element receives the sixth indication information from the first network element; or, the second response message also includes the sixth indication information; the network data analysis function network element determines the location information of N terminal devices from the location information of M terminal devices based on the sixth indication information; wherein the sixth indication information is used to indicate whether each terminal device in the M terminal devices has a PRU; the location information of the N terminal devices includes the location information of the terminal device with the PRU.

[0095] Based on the embodiments of the present application, the network data analysis function network element can determine the location information of the PRU of the terminal device as much as possible (that is, the positioning accuracy of the location information of the PRU of the terminal device is high), which can improve the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0096] In one possible design, the network data analysis function network element receives the seventh indication information from the first network element; or, the second response message also includes the seventh indication information; the network data analysis function network element determines the location information of N terminal devices from the location information of M terminal devices based on the seventh indication information; wherein the seventh indication information is used to indicate the location generation method corresponding to the location information of each terminal device in the M terminal devices.

[0097] Based on the embodiments of the present application, the positioning accuracy of the terminal device's location information corresponding to different generation methods is different. The network data analysis function network element can determine the location information of the terminal device with higher positioning accuracy based on the generation method corresponding to the terminal device's location information; or, the network data analysis function network element can determine the location information of the terminal device with higher positioning accuracy based on the quality information, thereby improving the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0098] In one possible design, the network data analysis function network element sends a fourth request message to the second network element; the network data analysis function network element receives first data corresponding to the location information of M terminal devices from the second network element; the network data analysis function network element trains a first positioning model based on the location information of the M terminal devices and the first data corresponding to the location information of the M terminal devices; wherein the fourth request message is used to request the first data corresponding to the location information of the M terminal devices; and the first data is used to train the first positioning model.

[0099] Based on the embodiment of the present application, the network data analysis function network element can receive the first data corresponding to the location information of the terminal device at the same time as receiving the location information of the terminal device, and can ensure that the first data and the label of the first data are consistent in time as much as possible, and propose a feasible solution for associating the first data and the label of the first data.

[0100] In one possible design, the location information of each terminal device also includes time information; or, the second response message also includes time information corresponding to the location information of each terminal device; wherein the time information is used to indicate the time when the location information is obtained.

[0101] In one possible design, the network data analysis function network element receives first data corresponding to M terminal devices from a third network element; the network data analysis function network element trains a first positioning model based on the location information corresponding to the time information and the first data.

[0102] Based on the above two possible designs, the network data analysis function network element can determine the first data at the same time according to the time information in the location information of the terminal device, ensure that the first data and the label of the first data are consistent in time, and propose a feasible solution for associating the first data and the label of the first data.

[0103] In one possible design, the third network element is a location management function network element, an operation, supervision and management function network element, a gateway mobile positioning center network element, a session management function network element, an access and mobility management function network element, or an application function network element.

[0104] In one possible design, the second network element is a location management function network element, an operation, supervision and management function network element, a gateway mobile positioning center network element, a session management function network element, an access and mobility management function network element, or an application function network element.

[0105] In one possible design, the first network element is a location management function network element, an operation, supervision and management function network element, a gateway mobile positioning center network element, a session management function network element, an access and mobility management function network element, or an application function network element.

[0106] Based on the above three possible designs, several possible designs are provided for the first network element, the second network element, and the third network element.

[0107] In a fifth aspect, a model acquisition method is provided, the method comprising: a location management function network element sending a first message to a network data analysis function network element, the first message being used to request acquisition of a positioning model; the network data analysis function network element receiving the first message; the network data analysis function network element training a first positioning model based on the first message; the first positioning model being used to locate the position of a terminal device; the network data analysis function network element sending the first positioning model to the location management function network element; and the location management function network element receiving the first positioning model.

[0108] In a sixth aspect, a communication device is provided for implementing various methods. The communication device includes modules, units, or means corresponding to the implementation method. The modules, units, or means can be implemented through hardware, software, or hardware executing corresponding software implementation. The hardware or software includes one or more modules or units corresponding to the functions.

[0109] In some possible designs, the communication device may include a processing module and a transceiver module. The processing module may be configured to implement the processing functionality of any of the above aspects and any possible implementations thereof. The transceiver module may include a receiving module and a transmitting module, respectively configured to implement the receiving functionality and the transmitting functionality of any of the above aspects and any possible implementations thereof.

[0110] In some possible designs, the transceiver module may be composed of a transceiver circuit, a transceiver, a transceiver or a communication interface.

[0111] In a seventh aspect, a communication device is provided, comprising: a processor and a memory; the memory is used to store computer instructions, and when the processor executes the instructions, the communication device executes the method described in any one of the aspects.

[0112] In an eighth aspect, a communication device is provided, comprising: a processor and a communication interface; the communication interface is used to communicate with a module outside the communication device; the processor is used to execute a computer program or instruction so that the communication device executes the method described in any aspect.

[0113] In a ninth aspect, a communication device is provided, comprising: at least one processor; the processor is configured to execute a computer program or instruction stored in a memory, so that the communication device performs the method described in any one of the aspects. The memory may be coupled to the processor, or may be independent of the processor.

[0114] In a tenth aspect, a computer-readable storage medium is provided, in which a computer program or instruction is stored. When the computer-readable storage medium is run on a communication device, the communication device can execute the method described in any one of the aspects.

[0115] In an eleventh aspect, a computer program product comprising instructions is provided, which, when executed on a communication device, enables the communication device to perform the method described in any one of the aspects.

[0116] In a twelfth aspect, a communication device is provided (for example, the communication device may be a chip or a chip system), which includes a processor for implementing the functions involved in any aspect.

[0117] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0118] In some possible designs, when the device is a chip system, it can be composed of a chip or include a chip and other discrete devices.

[0119] The communication device provided in any one of aspects 6 to 12 may be the location management function network element in the first aspect, or a device included in the location management function, such as a chip or a chip system; or, the communication device may be the network data analysis function network element in the second aspect, or a device included in the network data analysis function network element, such as a chip or a chip system.

[0120] It can be understood that when the communication device provided in any one of the sixth to twelfth aspects is a chip, the sending action / function of the communication device can be understood as output information, and the receiving action / function of the communication device can be understood as input information.

[0121] Among them, the technical effects brought about by any design method in the sixth to twelfth aspects can refer to the technical effects brought about by different design methods in the first to fifth aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0122] Figure 1 is a schematic diagram of the three model structures;

[0123] FIG2 is a schematic diagram of a 5G network architecture based on a service-oriented interface;

[0124] FIG3 is a schematic diagram of the structure of a communication system provided in an embodiment of the present application;

[0125] FIG4 is an interactive diagram of a model acquisition method provided in an embodiment of the present application;

[0126] FIG5 is a flow chart of a model acquisition method according to an embodiment of the present application;

[0127] FIG6 is a second flow chart of a model acquisition method provided in an embodiment of the present application;

[0128] FIG7 is an interactive diagram of a training data acquisition method provided in an embodiment of the present application;

[0129] FIG8 is a flow chart of a method for acquiring training data according to an embodiment of the present application;

[0130] FIG9 is an interactive diagram of another training data acquisition method provided in an embodiment of the present application;

[0131] FIG10 is a flow chart of another method for acquiring training data according to an embodiment of the present application;

[0132] FIG11 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0133] FIG12 is a schematic structural diagram of another communication device provided in an embodiment of the present application;

[0134] FIG13 is an interactive diagram of another training data acquisition method provided in an embodiment of the present application;

[0135] FIG14 is an interactive diagram of a method for training a positioning model provided in an embodiment of the present application;

[0136] FIG15 is an interactive diagram of a method for training a positioning model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0137] In order to facilitate understanding of the technical solutions of the embodiments of the present application, a brief introduction to the relevant technologies of the present application is first given as follows.

[0138] 1. AI positioning method:

[0139] Traditional wireless positioning algorithms rely on reference signal measurements between terminal devices and access network equipment and positioning algorithms. However, these algorithms suffer from poor positioning accuracy in certain scenarios and cannot meet the requirements for high-precision positioning. To improve positioning accuracy, researchers have proposed using AI / ML models for positioning. In fifth-generation (5G) communication systems, LMF network elements can locate terminal devices based on locally deployed AI / ML models. The following describes different scenarios.

[0140] In the downlink positioning scenario, the access network device sends a downlink positioning reference signal (PRS) to the terminal device. The terminal device measures the PRS to obtain measurement data and sends the measurement data to the LMF network element. The LMF network element locates the terminal device based on the local AI / ML model and the measurement data of the terminal device to obtain the terminal device position estimation result.

[0141] In the uplink positioning scenario, the terminal device sends an uplink channel sounding reference signal (SRS) to the access network device. The access network device measures the SRS to obtain measurement data and sends the measurement data to the LMF network element. The LMF network element locates the terminal device based on the local AI / ML model and the measurement data of the access network device to obtain the terminal device position estimation result.

[0142] Among them, AI / ML models deployed on LMF network elements can be mainly divided into three categories based on the model structure, which are introduced below with reference to Figure 1.

[0143] As shown in Figure 1, assuming that positioning requires obtaining measurement data between the terminal device and N transmission reception points (TRPs), where N is a positive integer greater than 1. These N TRPs may belong to the same access network device or to M different access network devices, where M ≤ N. These N TRPs may be arbitrary, not fixed, TRPs.

[0144] Model structure 1 (same model for N TRPs): N identical models are used, such as ML model 0 in model structure 1 in Figure 1. The input data for these N models is the measurement data between the terminal device and the N TRPs. That is, the input data for the first model is the measurement data between the terminal device and TRP 1, the input data for the second model is the measurement data between the terminal device and TRP 2, and so on. The input data for the Nth model is the measurement data between the terminal device and TRP N. These N models are AI-assisted positioning (A-AIML) models, and LMF uses the output results of these N models to calculate the estimated terminal device position.

[0145] Model Structure 2 (N models for N TRPs): N different models are used (e.g., ML model 1, ML model 2, and ML model N in Model Structure 2 in Figure 1). The input data for these N models is the measurement data between the terminal device and N TRPs. That is, the input data for the first model is the measurement data between the terminal device and TRP 1, the input data for the second model is the measurement data between the terminal device and TRP 2, and so on, and the input data for the Nth model is the measurement data between the terminal device and TRP N. These N models are A-AIML models, and LMF uses the output results of these N models to calculate the estimated terminal device position.

[0146] Model Structure 3 (One Model for N TRPs): One model is used for N TRPs (e.g., ML model x in Model Structure 3 in Figure 1). The input data for this model is the measurement data between the end device and the N TRPs. This model is a direct AI positioning (D-AIML) model, and its output is the estimated end device location.

[0147] 2. Model distribution process:

[0148] The 5G system introduces the network data analytics function (NWDAF) element, which is divided into two categories: the model training logical function (MTLF) and the analytics logical function (AnLF). The MTLF collects network data and trains AI / ML models based on this data, providing trained models to the AnLF upon request. The AnLF performs data statistics and inference, or performs model inference based on the AI / ML model, deriving corresponding analysis results upon user request, and making these analysis results available to users.

[0149] Currently, the NWDAF service consumer can be either AnLF or another MTLF. NWDAF service consumers can subscribe to models from MTLF using the following model distribution process. The following process is applicable to subscribing to AI / ML models, and is explained below using ML model subscription as an example.

[0150] Step 1: The NWDAF service consumer sends a model subscription request message to the NWDAF containing MTLF. The model subscription request message contains the following parameters:

[0151] 1. A list of Analytics ID(s): This is used to identify the analytics type of the model. MTLF uses this parameter to determine which model to train (for example, if Analytics ID = service experience, MTLF determines to train the service experience model).

[0152] 2. Notification target address: the target address used to notify the model, that is, to whom the model will be notified.

[0153] 3. Model filter information (ML model filter information): used to indicate the range of data that needs to be collected for training the model.

[0154] 4. Target of ML model reporting: used to indicate the end device for which the model is targeted, i.e. the object requesting the model.

[0155] 5. Model reporting information (ML model reporting information): used to indicate the conditions for reporting the model, such as immediate reporting, periodic reporting, and reporting upon reaching a threshold.

[0156] 6. Model vendor-related information (ML model interoperability information): Used for cross-vendor model sharing. When the NWDAF network element requesting the model and the NWDAF network element providing the model belong to different vendors, this parameter needs to be included in the request message to assist the model provider in determining whether to provide the model.

[0157] 7. Indication of supporting multiple ML models: used to indicate that MTLF can provide multiple models.

[0158] 8. Expected model accuracy level (Accuracy level of Interest): used to indicate the accuracy level of the model expected by the NWDAF service consumer.

[0159] Step 2: The NWDAF containing MTLF sends a notification message to the NWDAF service consumer. The notification message contains the following information:

[0160] 1. Analytics ID and one or more tuples of unique ML Model identifier and ML Model Information. Each tuple contains a model identifier and corresponding model information (Analytics ID, one or more tuples of unique ML Model identifier and ML Model Information). The model information includes the model file address, such as a uniform resource locator (URL) address or a fully qualified domain name (FQDN) address.

[0161] 2. Validity period: used to indicate the time period for which the model is applicable.

[0162] 3. Spatial validity: used to indicate the area where the model is applicable.

[0163] Currently, MTLF-trained models are typically used to generate statistical and / or predictive analysis results, such as statistical results of network element load and prediction results of application service experience, and are not supported for locating terminal devices.

[0164] 3. Fifth generation (5G) network architecture based on service-oriented interfaces:

[0165] Currently, the 5G network architecture based on service-oriented interfaces defined by the 3rd Generation Partnership Project (3GPP) is shown in Figure 2, which mainly includes the following network functions and entities: terminal equipment, access network (AN) equipment, user plane function (UPF) network element, data network (DN), access and mobility management function (AMF) network element, session management function (SMF) network element, LMF network element, policy control function (PCF) network element, application function (AF) network element, network exposure function (NEF) network element, network data analytics function (NWDAF) network element, network repository function (NRF) network element, unified data management function (UDM) network element, unified data repository (UDR) network element, etc. Optionally, operations, administration and management (OAM) network elements may also be included.

[0166] Among them, terminal devices, access network devices, UPF network elements, and DN are generally referred to as user-plane network functions and entities. User data traffic can be transmitted through the protocol data unit (PDU) session established between the terminal device and the DN. The transmission of data traffic will pass through the access network device and the UPF network element. The other parts are called control-plane network functions and entities, which are mainly responsible for functions such as authentication and authorization, access and mobility management, session management, and policy control, thereby achieving user access, session establishment, and reliable and stable transmission of user-plane traffic.

[0167] The following is a brief introduction to the main network elements of the 5G network architecture based on service-oriented interfaces.

[0168] Terminal equipment can refer to a user-side device with wireless transceiver capabilities. Terminal equipment can also be called user equipment (UE), terminal, access terminal, subscriber unit, subscriber station, mobile station (MS), remote station, remote terminal, mobile terminal (MT), user terminal, wireless communication device, user agent, or user device.

[0169] Exemplarily, the terminal device may be a drone, an Internet of Things (IoT) device (e.g., a sensor, an electricity meter, a water meter, etc.), a V2X device, a station (ST) in a wireless local area network (WLAN), a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA) device, 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 (also referred to as a wearable smart device), a tablet computer or a computer with wireless transceiver capabilities, a virtual reality (VR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a smart home, or a similar device. The present application does not specifically limit the terminals to mobile or fixed devices.

[0170] Access network equipment: Access network equipment can be devices deployed in the access network to provide communication functions for terminals. Access network equipment can be radio access network (RAN) equipment, wired access network equipment, non-3GPP access network equipment, 3GPP access network equipment, etc. Access network equipment can include various types of base stations (BS). As an example, access network equipment can include various forms of macro base stations, micro base stations, pico base stations, femto base stations, relay stations, access points, remote radio units (RRUs), radio heads (RHs), remote radio heads (RRHs), etc. In systems using different wireless access technologies, the names of access network equipment may be different. For example, it is called NodeB (NB) in 3G networks, evolved NodeB (eNB or eNodeB) in long term evolution (LTE) networks, and the next generation NodeB (gNB or gNodeB) or / new radio NodeB (NR NB) in 5G networks, and so on. In some scenarios, the access network equipment may include a central unit (CU) and / or a distributed unit (DU). The CU and DU can be placed in different places, for example, the DU is placed in an area with high traffic volume, and the CU is placed in a central computer room. Alternatively, the CU and DU can be placed in the same computer room. The CU and DU can also be different components under the same rack.

[0171] The LMF network element is primarily responsible for the overall coordination and scheduling of resources required to manage the location of terminal devices registering or accessing the 5G core network, and can calculate or verify the estimated terminal device location or speed, etc.

[0172] The AMF network element is primarily responsible for signaling processing, such as access control, mobility management, attach and detach, and gateway selection. The AMF network element also provides transport for location service messages between terminal devices and LMF network elements, and between access network devices and LMF.

[0173] The SMF network element is mainly responsible for providing session management (such as session establishment, modification, and release), IP address allocation and management, and UPF network element selection and control.

[0174] The PCF network element is mainly responsible for policy control decisions, providing policy rules for control plane functions, and flow-based charging control functions.

[0175] The NWDAF network element is mainly responsible for data collection, model training, data analysis, model reasoning and other functions. It can be used to collect relevant data from network elements, third-party service servers, terminal devices or network management systems, perform data analysis or model training based on the relevant data, and provide data analysis results to network elements, third-party service servers, terminal devices or network management systems, or provide trained models to other data analysis function network elements.

[0176] The AF network element is mainly responsible for conveying the requirements of the application side to the network side, such as quality of service (QoS) requirements or user status event subscriptions. The AF network element can be a third-party functional entity or an application server deployed by the operator.

[0177] The UPF network element is mainly responsible for forwarding and receiving user data in terminal devices.

[0178] NEF network elements are mainly responsible for managing network data open to the outside world.

[0179] The NRF network element is mainly responsible for network function service registration and status monitoring, realizing the automated management, selection and scalability of network function services, and allowing each network function to discover the services provided by other network functions.

[0180] OAM network elements primarily perform routine network and service analysis, forecasting, planning, and configuration, as well as network and service testing and fault management. OAM network elements can interact with access network devices to obtain terminal device location information measured by access network devices or reported by terminal devices.

[0181] The UDM network element is mainly responsible for user contract management, access authorization, authentication information generation, etc.

[0182] The UDR network element is mainly responsible for providing storage capabilities for contract data, policy data, and capability exposure-related data.

[0183] In addition, Figure 2 also shows the interaction relationship between various network functions and entities and the corresponding interfaces. As shown in Figure 2, the terminal device accesses the 5G network through the access network device; the access network device communicates with the AMF network element through the N2 interface (referred to as N2); the access network device communicates with the UPF network element through the N3 interface (referred to as N3); the SMF network element communicates with the UPF network element through the N4 interface (referred to as N4), and the UPF network element accesses the DN through the N6 interface (referred to as N6). In addition, the network functions such as the AMF network element, SMF network element, NEF network element, NRF network element, PCF network element, UDM network element, UDR network element, or AF network element shown in Figure 2 use service-oriented interfaces to interact. For example, the service interface provided by the AMF network element to the outside is Namf; the service interface provided by the SMF network element to the outside is Nsmf; the service interface provided by the NEF network element to the outside is Nnef; the service interface provided by the NRF network element to the outside is Nnrf; the service interface provided by the PCF network element to the outside is Npcf; the service interface provided by the UDM network element to the outside is Nudm; the service interface provided by the UDR network element to the outside is Nudr; the service interface provided by the AF network element to the outside is Naf; the service interface provided by the NWDAF network element to the outside is Nnwdaf; and the service interface provided by the LMF network element to the outside is Nlmf.

[0184] Based on the above introduction to the existing technology, it can be seen that the existing AI positioning method requires the LMF network element to infer the location information of the terminal device based on the locally deployed AI / ML model and the measurement data collected from the terminal device / access network device, but the LMF itself may not be able to train the AI ​​model. Although the NWDAF network element can train the AI / ML model and send the AI / ML model to other NWDAF network elements, the NWDAF network element currently does not support training positioning models, nor does it support collecting positioning-related training data, nor does it support providing AI / ML models to LMF network elements. Therefore, in the existing AI positioning method, the LMF can only infer the location information of the terminal device based on the locally deployed AI / ML model.

[0185] It can be seen that the existing AI positioning methods have the following problems: obtaining high-precision terminal device location information in different environments requires different positioning models, and the AI / ML model deployed locally on the LMF network element is pre-configured in the LMF network element. The LMF network element itself may not be able to train an AI / ML model that meets the requirements of the current environment. Therefore, as the environment changes, the AI / ML model deployed locally on the LMF may not meet the positioning requirements in the current environment, and it is impossible to obtain high-precision terminal device location information.

[0186] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0187] In the embodiment of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the first indication information, the second indication information, or the third indication information below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein the other information and the information to be indicated have an association relationship. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can be achieved by means of the arrangement order of each information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each information can be identified and indicated uniformly to reduce the indication overhead caused by indicating the same information separately.

[0188] In addition, the specific indication method can also be various existing indication methods, such as but not limited to the above-mentioned indication methods and various combinations thereof. The specific details of the various indication methods can be referred to the prior art and will not be repeated herein. As can be seen from the above, for example, when it is necessary to indicate multiple information of the same type, there may be a situation where the indication methods for different information are different. In the specific implementation process, the required indication method can be selected according to specific needs. The embodiment of the present application does not limit the selected indication method. In this way, the indication method involved in the embodiment of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0189] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited in the embodiments of this application. The sending period and / or sending time of these sub-information can be predefined, for example, predefined according to a protocol, or can be configured by the transmitting device by sending configuration information to the receiving device.

[0190] In the embodiment of the present application, "pre-definition", "pre-definition", "pre-configuration" or "pre-configuration" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the device, and the embodiment of the present application does not limit its specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, which is not limited by the embodiment of the present application.

[0191] The "protocol" involved in the embodiments of the present application may refer to a protocol family in the communication field, a standard protocol with a similar protocol family frame structure, or a related protocol used in future communication systems. The embodiments of the present application do not make specific limitations on this.

[0192] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if" and "if" all mean that the device will perform corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the device to perform judgment actions when implemented, nor does it mean that there are other limitations.

[0193] The technical solution provided in this application can be used in various communication systems, which may be a third generation partnership project (3GPP) communication system, for example, a fourth generation (4G) long term evolution (LTE) system, a fifth generation (5G) mobile communication system and its evolution system, a vehicle to everything (V2X) system, a LTE and NR hybrid networking system, or a device to device (D2D) system, a machine to machine (M2M) communication system, an Internet of Things (IoT), and other next generation communication systems.

[0194] It should be noted that the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0195] For example, referring to Figure 3, a communication system provided by the present application and applicable to the solution of the present application is shown. The communication system may include at least one location management function network element and at least one network data analysis function network element.

[0196] Optionally, the communication system may also include terminal equipment, access network equipment, network management network elements, session management network elements, access and mobility management function network elements, application function network elements, unified data management function network elements, unified data storage network elements, etc.

[0197] Optionally, in a 5G communication system, the location management function network element may be an LMF network element. In future communication systems such as a 6G communication system, the location management function network element may still be an LMF network element, or may have other names. This is not limited in the embodiments of the present application.

[0198] Optionally, in a 5G communication system, the network data analysis function network element may be an NWDAF network element. In future communication systems such as a 6G communication system, the network data analysis function network element may still be an NWDAF network element, or may have other names. This embodiment of the present application does not limit this.

[0199] Similarly, the names of the network management network element, session management network element, access and mobility management function network element, application function network element, unified data management function network element or unified data storage network element in the 5G system can refer to the above introduction to the various network elements in the 5G network architecture part. In future communication systems such as 6G communication systems, these network elements can still reuse the names in the 5G system, or may have other names, which is not limited in the embodiments of the present application.

[0200] Optionally, for descriptions of the product forms of terminal devices and access network devices, please refer to the above descriptions of terminal devices and access network devices in the 5G network architecture section, which will not be repeated here.

[0201] Taking the 5G communication system as an example, a possible network architecture diagram corresponding to the communication system shown in Figure 3 applicable to the embodiment of the present application can be shown in Figure 2.

[0202] It should be noted that the communication system and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0203] The model acquisition method provided in the embodiment of the present application is described below in conjunction with the communication system shown in FIG3 .

[0204] It should be noted that in the following embodiments of the present application, the message names, parameter names, or information names between network elements are only examples. In other embodiments, they may also be other names, and the method provided in the present application does not make specific limitations on this.

[0205] It is understood that in the embodiments of the present application, each network element or entity may perform some or all of the steps in the embodiments of the present application. These steps or operations are merely examples, and the embodiments of the present application may also perform other operations or variations of various operations. In addition, the steps may be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be performed.

[0206] For example, the methods provided in the following embodiments of this application can be applied to the positioning of terminal devices, and for example, can be applied to scenarios where a location management function network element positions a terminal device. Of course, this is merely an example of the application scenario of this application, and this application scenario does not impose any limitation on this application, nor does this application specifically limit the application scenario of the methods provided below.

[0207] 4 , the model acquisition method provided in the embodiment of the present application includes steps S401 to S403:

[0208] S401: The location management function network element sends a first message to the network data analysis function network element, where the first message is used to request to obtain a positioning model. Correspondingly, the network data analysis function network element receives the first message.

[0209] S402. The network data analysis function network element trains a first positioning model according to the first message; the first positioning model is used to locate the position of the terminal device.

[0210] S403: The network data analysis function network element sends the first positioning model to the location management function network element. Correspondingly, the location management function network element receives the first positioning model from the network data analysis function network element.

[0211] Based on this solution, the location management function network element can obtain the trained positioning model from the network data analysis function network element, and does not have to use only the locally deployed positioning model. This enables the location management function network element to select a model that is more suitable for the current environment to achieve better positioning effects.

[0212] The following is an introduction to S401-S403 respectively.

[0213] In S401, the first message may optionally include model requirement information, wherein the model requirement information is used to indicate the location management function element's requirements for the positioning model. It is understandable that the network data analysis function element may train a positioning model that meets the requirements indicated by the model requirement information based on the model requirement information.

[0214] Exemplarily, the model requirement information may be a model requirements profile parameter included in the first message.

[0215] Optionally, the model requirement information may include at least one of the following:

[0216] 1. Model algorithm requirement information, used to indicate the requirements for the algorithm used by the positioning model. Optionally, one or more required model algorithms can be indicated, for example, algorithms such as convolutional neural networks (CNN), recurrent neural networks (RNN), residual neural networks (ResNet), and long short-term memory (LSTM). The network data analysis function element can use any model algorithm required by the model algorithm requirement information to train the positioning model.

[0217] 2. Model input requirement information, which indicates the requirements for the positioning model's input data. This input data can be training data, test data, validation data, or inference data. The network data analysis function element can train a model that meets the input requirements based on the model input requirement information.

[0218] Optionally, the model input requirement information may indicate the type of one or more input data, for example, it may indicate data of types such as channel impulse response (CIR), channel energy response (CER), and channel power delay profile (PDP).

[0219] Optionally, the model input requirement information may indicate one or more characteristics of the input data, for example, it may indicate at least one item such as the input file type (such as json, xls, dat, etc.), the input data format (such as numeric, character, binary number), the input data dimension (such as the input data dimension is 10 dimensions, indicating that 10 numeric values / characters / binary numbers, etc. need to be input in parallel each time), the data length (such as the length of a binary number is 10 bits), etc.

[0220] In one possible implementation, the model input requirement information may include a specific event identifier (Event ID) information. The location management function network element and the network data analysis function network element may pre-configure a correspondence between the event identifier information and one or more types of data, so that the location management function network element can indicate the training data that needs to be input into the positioning model by sending the event identifier information. For example, assuming that event identifier information 1 corresponds to CIR and CER, and event identifier information 2 corresponds to PDP, if the location management function network element sends event identifier information 1 to the network data analysis function network element, the network data analysis function network element can determine, based on event identifier information 1, that the input data that needs to be input into the positioning model includes CIR and CER.

[0221] In one possible implementation, the model input requirement information may include feature identification information. The location management function network element and the network data analysis function network element may pre-configure a correspondence between the feature identification information and one or more data features, so that the location management function network element can indicate the feature requirements for the input data of the positioning model by sending the feature identification information. For example, assuming that feature identification information 1 corresponds to the following features: the input file type is json, the input data format is binary, the input data dimension is 10 dimensions, and the input data length is 10 bits, if the location management function network element sends feature identification information 1 to the network data analysis function network element, the network data analysis function network element can determine the different feature information of the input data that needs to be input into the positioning model based on feature identification information 1.

[0222] Optionally, the event identification information and feature identification information included in the model input requirement information may be the same identification information. In other words, the identification information may correspond to one or more data types and one or more data characteristics. The network data analysis function element may determine the type and characteristics of the input data required for the positioning model based on the identification information. Alternatively, the event identification information and feature identification information included in the model input requirement information may be different identification information.

[0223] 3. Model output requirement information, which is used to indicate the requirements for the output results of the positioning model. The network data analysis function element can train a positioning model that can output the required output results based on the model output requirement information.

[0224] Optionally, the model output requirement information may indicate the type of data output by the positioning model, for example, may indicate that the positioning model outputs terminal device location (UE location) information, or may indicate that the positioning model outputs terminal device timing estimation (timing estimation) information.

[0225] Optionally, the model output requirement information may indicate one or more characteristics of the data output by the positioning model, for example, it may indicate the output file type (such as json, xls, dat, etc.), the output data format (such as numeric, character, binary number), the output data dimension (such as the output data dimension is 10 dimensions, indicating that 10 numeric values / characters / binary numbers are to be output in parallel each time), the data length (such as the length of binary numbers is 10 bits), etc.

[0226] In one possible implementation, the model output requirement information may include event identification information and / or feature identification information, where the event identification information corresponds to one or more types of model output data, and the feature identification information corresponds to one or more features of the model output data. The location management function network element may indicate requirements for the output results of the positioning model by sending the event identification information and / or feature identification information. For details, please refer to the above description of the model input requirement information and will not be elaborated here.

[0227] 4. Model complexity requirement information, used to indicate the complexity requirement for the positioning model. Optionally, the model complexity requirement information may indicate a requirement for at least one of the following: model size, number of model layers, and number of model parameters. For example, the model complexity requirement information may indicate that the model size needs to be less than 100 Kbit, and / or that the number of model layers needs to be greater than 18 and less than 128, and / or that the number of model parameters needs to be less than 106.

[0228] 5. Computational complexity requirement information, used to indicate the requirement for the amount of computation required for the positioning model. For example, the computational complexity requirement information may indicate that the amount of computation required for the positioning model must be less than 108 floating point operations (FLOPs).

[0229] 6. Model accuracy requirement information is used to indicate the requirements for the accuracy of the positioning model. For example, the model accuracy requirement information may indicate that the probability that the positioning error of the positioning model is less than 0.5 meters is 90%. In other words, a positioning model with a probability greater than or equal to 90% of a positioning error less than 0.5 meters is a positioning model that meets the model accuracy requirements.

[0230] 7. Model structure requirement information, which is used to indicate the location management functional element's requirements for the model structure of the positioning model. The network data analysis functional element can determine the model structure of the positioning model to be trained based on the instructions of the model structure requirement information.

[0231] Optionally, the model structure requirement information may indicate the model structure of the positioning model required by the location management function network element.

[0232] Optionally, the model structure requirement information may indicate one or more model structures. In the case where the model structure requirement information indicates multiple model structures, the network data analysis function element may determine any one of the indicated multiple model structures as the model structure of the positioning model to be trained.

[0233] Optionally, the model structure requirement information may be identification information of the structure type required by the location management function network element. In this implementation, the location management function network element and the network data analysis function network element may pre-configure a correspondence between the identification information of the structure type and the corresponding structure type, so that the network data analysis function network element can determine the model structure of the positioning model to be trained based on the identification information of the structure type sent by the location management function network element.

[0234] Exemplarily, the model structures indicated by the model structure requirement information may include three model structures as shown in Figure 1: model structure 1 (same model for N TRPs), model structure 2 (N models for N TRPs), and model structure 3 (one model for N TRPs). If the model structure requirement information indicates model structure 1, the network data analysis function network element can determine, based on the model structure requirement information, that one positioning model needs to be trained, and the input of the positioning model to be trained is the measurement result of a single TRP. If the model structure requirement information indicates model structure 2, the network data analysis function network element can determine, based on the model structure requirement information, that N (N is a positive integer greater than 1) positioning models need to be trained, and the input of a single positioning model among the N positioning models is the measurement result of a single TRP, and the inputs of different positioning models correspond to the measurement results of different TRPs. If the model structure requirement information indicates model structure 3, the network data analysis function network element can determine, based on the model structure requirement information, that one positioning model needs to be trained, and the input of the positioning model to be trained is the measurement results of N TRPs.

[0235] Optionally, the model structure requirement information may further indicate the number of positioning models corresponding to the model structure. For example, if the model structure indicated by the model structure requirement information is model structure 1 or model structure 2 as shown in FIG1 , the model structure requirement information may further indicate the value of N.

[0236] 8. Model generalization capability requirement information, used to indicate the location management function network element's requirements for the model generalization capability of the positioning model. The network data analysis function network element can determine whether the model generalization capability of the positioning model it has trained meets the location management function network element's requirements based on the model generalization capability requirement information. Furthermore, if the positioning model trained by the network data analysis function network element does not meet the model generalization capability requirements of the model generalization capability requirement information, the network data analysis function network element can continue training the positioning model until the trained positioning model meets the model generalization capability requirements of the model generalization capability requirement information.

[0237] Model generalization ability measures whether a model can produce appropriate outputs for different input data. One possible implementation can measure model generalization ability by its performance on different test datasets. A model with good generalization ability should perform well on different test datasets. Conversely, a model with poor generalization ability may perform well on one test dataset but poorly on another.

[0238] Optionally, the model generalization capability requirement information may include information indicating the requirements of the location management function network element on the model performance of the positioning model under different test data sets.

[0239] Among them, exemplary, model performance may include at least one of the following: model accuracy (or model precision), error rate, precision, recall, mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), etc.

[0240] Optionally, the location management function network element may provide the network data analysis function network element with corresponding different test data sets. Alternatively, the network data analysis function network element may obtain the corresponding different test data sets through other means, for example, the network data analysis function network element may request the corresponding different test data sets from other network elements.

[0241] Exemplarily, different test data sets may be test data sets under different terminal device transmit powers, or may be test data sets under different network synchronization errors, or may be test data sets under different terminal device timing errors, or may be test data sets under different target deployment environments. The target deployment environment refers to a specific environment in which the positioning model may be deployed. Optionally, the test data sets under different target deployment environments may correspond to different fine-tuning training data sets, wherein the fine-tuning training data set is a training data set from the target deployment environment of the positioning model.

[0242] The following takes the example of measuring the model generalization ability by the model accuracy under different test data sets to introduce four possible situations in which the model generalization ability requirement information indicates the requirements for the model generalization ability of the positioning model.

[0243] (1) Model generalization capability requirement information may indicate the requirements for the model accuracy under the test data set corresponding to different terminal device transmission powers. In a possible implementation, the model generalization capability requirement information may include a parameter indicating the terminal device transmission power and the corresponding model accuracy. Assume that the parameter is List of<UE power,accuracy requirements> Parameter (or, the parameter may also be in other forms, which is not limited in the embodiments of the present application), for example, when UE power is 3 and accuracy requirements is 96%, it means that the model accuracy is required to be no less than 96% when the terminal device transmit power is 3dBm, and when UE power is 23 and accuracy requirements is 97%, it means that the model accuracy is required to be no less than 97% when the terminal device transmit power is 23dBm. The network data analysis function network element can measure the model accuracy of the trained positioning model under the test data set corresponding to the terminal device transmit power of 3dBm and the model accuracy of the positioning model under the test data set corresponding to the terminal device transmit power of 23dBm according to the model generalization capability requirement information, and determine whether the model accuracy of the positioning model under different test data sets meets the requirements of the model generalization capability requirement information.

[0244] Optionally, the location management function network element may also provide the network data analysis function network element with corresponding test data sets, for example, a test data set corresponding to a terminal device transmission power of 3dBm and a test data set corresponding to a terminal device transmission power of 23dBm.

[0245] (2) Model generalization capability requirement information can indicate the requirements for the model accuracy under test data sets corresponding to different network synchronization errors. In a possible implementation, the model generalization capability requirement information can include parameters indicating the network synchronization error and the corresponding model accuracy. Assume that the parameter is List of<network synchronization error,accuracy requirements> Parameter (or, the parameter may also be in other forms, which is not limited in the embodiments of the present application), for example, when the network synchronization error is 2 and the accuracy requirements is 96%, it means that the model accuracy is required to be no less than 96% when the network synchronization error is 2ns, and when the network synchronization error is 20 and the accuracy requirements is 95%, it means that the model accuracy is required to be no less than 95% when the network synchronization error is 20ns. The network data analysis function network element can measure the model accuracy of the trained positioning model under the test data set corresponding to the network synchronization error of 2ns and the model accuracy of the positioning model under the test data set corresponding to the network synchronization error of 20ns based on the model generalization capability requirement information, and determine whether the model accuracy of the positioning model under different test data sets meets the requirements of the model generalization capability requirement information.

[0246] Optionally, the location management function network element may also provide the network data analysis function network element with corresponding test data sets, for example, a test data set corresponding to a network synchronization error of 2 ns and a test data set corresponding to a network synchronization error of 20 ns.

[0247] (3) Model generalization capability requirement information may indicate the requirements for the model accuracy under test data sets corresponding to different terminal device synchronization errors. In a possible implementation, the model generalization capability requirement information may include parameters indicating the terminal device synchronization error and the corresponding model accuracy. Assume that the parameter is List of<UE timing error,accuracy requirements> Parameter (or the parameter may be in other forms, which is not limited in the embodiments of the present application), for example, when the UE timing error is 2 and the accuracy requirements is 96%, it means that the model accuracy is required to be no less than 96% when the terminal device synchronization error is 2ns, and when the UE timing error is 20 and the accuracy requirements is 95%, it means that the model accuracy is required to be no less than 95% when the terminal device synchronization error is 20ns. The network data analysis function network element can measure the model accuracy of the trained positioning model under the test data set corresponding to the terminal device synchronization error of 2ns and the model accuracy of the positioning model under the test data set corresponding to the terminal device synchronization error of 20ns based on the model generalization capability requirement information, and determine whether the model accuracy of the positioning model under different test data sets meets the requirements of the model generalization capability requirement information.

[0248] Optionally, the location management function network element may also provide the network data analysis function network element with corresponding test data sets, for example, a test data set corresponding to a terminal device synchronization error of 2ns and a test data set corresponding to a terminal device synchronization error of 20ns.

[0249] (4) Model generalization capability requirement information may indicate the requirements for the model accuracy after the model is retrained using different fine-tuning training datasets. In one possible implementation, the model generalization capability requirement information may include a parameter indicating the model retraining dataset (fine-tuning training dataset) under a specific environment and the corresponding model accuracy. Assume that the parameter is List of<environment parameters(e.g.,Area of Interest,time period),accuracy requirements> Parameter (or, the parameter may also be in other forms, which is not limited in the embodiments of the present application), for example, when the Area of ​​Interest is cell 1, the time period is 10:00-11:00, and the accuracy requirements is 97%, it means that after the model is retrained using the training data set collected from the network area indicated by cell 1 during the period of 10:00-11:00, the model accuracy of the retrained model is required to be not less than 97%, and when the Area of ​​Interest is cell 2, the time period is 17:30-18:00, and the accuracy requirements is 98%, it means that after the model is retrained using the training data set collected from the network area indicated by cell 2 during the period of 17:30-18:00, the model accuracy of the retrained model is required to be not less than 98%. The network data analysis function network element can measure, based on the model generalization capability requirement information, the model accuracy of the trained positioning model after retraining using the training data set collected from the network area indicated by cell 1 during the period from 10:00 to 11:00, and the model accuracy of the positioning model after retraining using the training data set collected from the network area indicated by cell 2 during the period from 17:30 to 18:00, and determine whether the model accuracy of the positioning model after retraining using different training data sets meets the requirements of the model generalization capability requirement information.

[0250] Optionally, the location management function network element may also provide the network data analysis function network element with a corresponding fine-tuning training data set and a corresponding test data set.

[0251] It should be noted that the model algorithm requirement information, model input requirement information and other information introduced above are information that may be included in several types of model requirement information provided in the embodiments of this application, and do not constitute a limitation on the specific content of the model requirement information.

[0252] Optionally, the first message may include model type indication information, where the model type indication information is used to indicate that the type of model requested by the location management function network element is a positioning model. The network data analysis function network element may determine, based on the model type indication information, that the model that needs to be trained and provided to the location management function network element is a positioning model.

[0253] Exemplarily, the model type indication information may be a model type indication (Model Type Indicator) parameter included in the first message.

[0254] Optionally, the model type indication information may be identification information of the positioning model type. In this implementation, the location management function network element and the network data analysis function network element may pre-configure a correspondence between the identification information of the model type and the corresponding model type, so that the network data analysis function network element can determine that the type of the model to be trained is a positioning model based on the identification information of the positioning model type sent by the location management function network element.

[0255] Optionally, the first message may also include parameters contained in the model subscription request message in the existing model distribution process. For details, please refer to the above introduction to parameters such as A list of Analytics ID(s) and Notification Target Address in the existing model distribution process, which will not be repeated here.

[0256] In S402, after receiving the first message, the network data analysis function network element may determine the positioning model to be trained according to the first message, thereby training and obtaining the corresponding positioning model.

[0257] In the embodiment of the present application, the positioning model obtained by the network data analysis function element according to the first message training can be referred to as the first positioning model. Wherein, the first positioning model can be an AI / ML model.

[0258] Optionally, if the first message includes model requirement information, the network data analysis function element can train a positioning model that meets the requirements based on the model requirement information to obtain the first positioning model. For details, please refer to the above introduction to the model requirement information content, which will not be elaborated here.

[0259] Optionally, if the first message does not include model requirement information, that is, the location management function network element does not indicate the requirements for the positioning model to the network data analysis function network element, the network data analysis function network element can autonomously train a positioning model that meets the current environment requirements to obtain the first positioning model.

[0260] In one possible implementation, if the first message does not include model requirement information, the first message may include second information, where the second information is used to instruct the network data analysis function element to autonomously train a positioning model that meets the requirements of the current environment. The network data analysis function element may autonomously train a positioning model that meets the requirements of the current environment based on the instruction of the received second information.

[0261] Exemplarily, the second information may be a model selection indicator parameter included in the first message.

[0262] The following introduces the specific implementation of the network data analysis function network element autonomously determining the positioning model that meets the current environment requirements.

[0263] Implementation method 1: After receiving the first message, the network data analysis function network element can determine an environment identification information (for the sake of ease of introduction, this environment identification information can be referred to as the first environment identification information). The first environment identification information can be used to identify the current environment, thereby determining the positioning model to be trained based on the environment identification information.

[0264] The current environment identified by the first environment identification information can be understood as the current environment corresponding to the applicable area of ​​the positioning model to be trained (i.e., the positioning model requested by the location management function network element). Optionally, the applicable area of ​​the positioning model to be trained can be indicated by the location management function network element to the network data analysis function network element. For example, the first message may include area of ​​interest (AOI) information to indicate the applicable area of ​​the positioning model requested by the location management function network element.

[0265] It can be understood that since the positioning model obtained by the network data analysis function network element according to the first message training is called the first positioning model, that is, the positioning model to be trained is called the first positioning model after the training is completed, therefore, the first environment identification information can also be understood as the current environment corresponding to the applicable area of ​​​​the first positioning model (or called the environment corresponding to the first positioning model).

[0266] Optionally, the environment identified by the environmental identification information may be classified based on geographical features, for example, environmental identification 1 indicates an urban canyon, environmental identification 2 indicates a plain rural area, and environmental identification 3 indicates a plateau mountainous area. Alternatively, the environment identified by the environmental identification information may be classified based on the degree of non-line of sight (NLOS), for example, environmental identification 1 indicates a mild NLOS environment, environmental identification 2 indicates a moderate NLOS environment, and environmental identification 3 indicates a severe NLOS environment.

[0267] Regarding determining the first environment identification information, in one possible implementation, the network data analysis function network element may determine the first environment identification information through measurement data related to the current environment corresponding to the applicable area of ​​the positioning model to be trained. For example, the network data analysis function network element may pre-train a classification model, the output of which is environment identification information. After receiving the first message, the network data analysis function network element obtains measurement data related to the current environment corresponding to the applicable area of ​​the positioning model to be trained, and inputs one or more data in the obtained measurement data into the classification model. The environment identification information output by the classification model is the first environment identification information.

[0268] Optionally, in this implementation, the measurement data related to the current environment corresponding to the applicable area of ​​the positioning model to be trained, obtained by the network data analysis function network element, can be used to characterize information such as geographical characteristics and communication quality of the current environment corresponding to the applicable area of ​​the positioning model to be trained. For example, the measurement data related to the current environment corresponding to the applicable area of ​​the positioning model to be trained can include at least one of the following:

[0269] Channel measurement data measured within the applicable area of ​​the positioning model to be trained, such as reference signal received power (RSRP), reference signal received quality (RSRQ), signal to interference plus noise ratio (SINR), RAN throughput for DL ​​and UL, RAN packet delay for DL ​​and UL, RAN packet loss rate for DL ​​and UL, etc.; positioning results of terminal devices within the applicable area of ​​the positioning model to be trained, auxiliary data related to positioning, and location information (such as physical cell identity, global cell identity, downlink reference signal time difference, downlink positioning reference signal received power, etc.); session information within the applicable area of ​​the positioning model to be trained, such as QoS flow bit rate, QoS flow packet delay, number of packet transmissions, packet retransmissions, etc. geographical environment information (information used to characterize the geographical environment in which the terminal device is currently located within the applicable area of ​​the positioning model to be trained), such as whether the terminal device is currently located indoors or outdoors, in the suburbs, cities or rural areas, in plains or mountains, etc.

[0270] Among them, optionally, in the above-mentioned measurement data related to the current environment corresponding to the applicable area of ​​the positioning model to be trained, the channel measurement data can be obtained from the network management network element. The positioning result can be obtained from the location management function network element (which can be the location management function network element that sends the first message, or other location management function network elements) / gateway mobile location center (GMLC) / application function network element (for example, it can be a third-party application function network element). Session information can be obtained from the session management network element / user plane function network element. Geographic environment information can be obtained from the application function network element (for example, it can be a third-party application function network element).

[0271] Among them, optionally, if the network data analysis function network element obtains the above-mentioned measurement data from the location management function network element (which can be the location management function network element that sends the first message or other location management function network elements), the message requesting the above-mentioned measurement data sent by the network data analysis function network element to the location management function network element, and / or the corresponding measurement data fed back by the location management function network element to the network data analysis function network element can be forwarded by the access and mobility management function network element.

[0272] Optionally, the positioning result may be the location information of the terminal device. In one possible implementation, the location information of the terminal device may be obtained using a specific positioning algorithm. For example, the network data analysis function element may send a request message to the location management function element / gateway mobile location center. The request message may specify a specific positioning algorithm. The location management function element / gateway mobile location center uses the positioning algorithm to calculate the location of the terminal device and feeds the obtained terminal device location back to the network data analysis function element.

[0273] Optionally, when the network data analysis function network element obtains measurement data related to the current environment corresponding to the applicable area of ​​the positioning model to be trained, it can also obtain timestamp information corresponding to the measurement data.

[0274] Optionally, the network data analysis function network element may send a request message to a corresponding network element to request measurement data related to the current environment corresponding to the applicable area of ​​the positioning model to be trained. Correspondingly, the network element that receives the request message may send the corresponding measurement data to the network data analysis function network element.

[0275] For determining the first environmental identification information, in another possible implementation method, the network data analysis function network element can pre-configure the correspondence between the positioning error (or positioning accuracy) of a specific positioning algorithm and the environmental identification information, thereby determining an environmental identification corresponding to the positioning error based on the positioning error of the specific positioning algorithm, that is, the first environmental identification information.

[0276] Optionally, the network data analysis function network element may calculate the positioning error (or positioning accuracy) of the specific positioning algorithm based on the acquired specific positioning algorithm and its corresponding positioning result, as well as at least one piece of information such as regional information (used to indicate the applicable area of ​​the positioning model to be trained), LOS / NLOS measurement information (indicating whether the positioning result is obtained based on LOS / NLOS measurement), and geographic environment information (used to indicate the geographical environment in which the terminal device is currently located within the applicable area of ​​the positioning model to be trained, such as whether the terminal device is currently located indoors or outdoors, in the suburbs, cities or rural areas, in plains or mountains, etc.). Optionally, the network data analysis function network element may obtain the specific positioning algorithm and its corresponding positioning result, regional information, LOS / NLOS measurement information, geographic environment information, and at least one piece of information from the location management function network element / gateway mobile location center / application function network element.

[0277] For example, the network data analysis function element trains a positioning error prediction model. The model's input includes information such as the positioning algorithm, the positioning results corresponding to the positioning algorithm, regional information, LOS / NLOS measurement information, and geographic environment information. The model's output is the positioning error of the positioning algorithm. Based on the positioning error of the specific positioning algorithm output by the model and a preconfigured correspondence, the network data analysis function element determines an environmental identifier corresponding to the positioning error, namely, first environmental identifier information.

[0278] It should be noted that the embodiments of the present application do not impose any specific restrictions on the specific positioning algorithm mentioned above. It can be any algorithm that can be applied to wireless positioning scenarios, such as downlink time difference of arrival (DL-TDOA) algorithm, downlink angle of departure (DL-AOD), uplink time difference of arrival (UL-TDOA), uplink angle of arrival (UL-AOA) and other algorithms.

[0279] In implementation method one, for determining the positioning model to be trained based on the first environment identification information, in a possible implementation, the network data analysis function network element can pre-configure the mapping relationship between the environment identification information and one or more model identification information, or pre-configure the correspondence between the environment identification information and a set of model feature information. After the network data analysis function network element determines the first environment identification information, it can determine the model identification information or the corresponding model feature information corresponding to the first environment identification information based on the pre-configured correspondence, and thus determine the positioning model to be trained based on the corresponding model identification information or the corresponding model feature information.

[0280] The model identification information is used to identify a specific model. Optionally, the model may be an untrained model, and the network data analysis function element may perform model training based on the model to obtain the first positioning model. Alternatively, the model may be a trained model, and the network data analysis function element may perform retraining based on the model to obtain the first positioning model. Alternatively, the network data analysis function element may directly use the model as the first positioning model.

[0281] Among them, the model feature information includes feature information that can be used to characterize the model, such as model input, model output, model complexity, model calculation complexity and other features. For details, please refer to the above introduction to the multiple information indicating the requirements for model features that may be included in the model requirement information.

[0282] Implementation method 2: The network data analysis function network element can pre-configure the mapping relationship between the positioning error of a specific positioning algorithm and one or more model identification information, or pre-configure the mapping relationship between the positioning error of a specific positioning algorithm and a set of model feature information. The network data analysis function network element can calculate the positioning error of the specific positioning algorithm according to the method described above, and determine the model identification information or model feature information corresponding to the positioning error according to the pre-configured correspondence, thereby determining the positioning model to be trained according to the corresponding model identification information or the corresponding model feature information. Among them, the model identification information and model feature information can be specifically referred to the above introduction to implementation method 1, and will not be repeated here.

[0283] Based on this solution, the network data analysis function element can autonomously determine what positioning model to provide to the location management function element. The network data analysis function element can collect relevant measurement data and determine the environmental identifier of the current environment, thereby determining the model to be trained based on the environmental identifier. Alternatively, the network data analysis function element can determine the model to be trained based on the positioning error of a specific positioning algorithm. The network data analysis function element can send the autonomously trained positioning model to the location management function element, providing a solution to the problem that some location management function elements cannot autonomously determine what model to use.

[0284] In S403, optionally, the network data analysis function network element may send a model file of the first positioning model, or an address of the model file of the first positioning model, such as a URL address or an FQDN address, to the location management function network element.

[0285] Optionally, the network data analysis function network element may also send model information of the first positioning model to the location management function network element. The model information includes one or more pieces of model feature information of the first positioning model. The model feature information of the first positioning model is used to characterize the characteristics of the first positioning model, such as the model type, model algorithm, model structure, model generalization capability, model input, model output, model complexity, model computational complexity, and model accuracy of the first positioning model. For details, please refer to the above description of the multiple pieces of information indicating the requirements for model features that may be included in the model requirement information, which will not be elaborated here.

[0286] Exemplarily, the model information may be a model information parameter in the information fed back by the network data analysis function network element to the location management function network element.

[0287] Optionally, if the first message includes model requirement information, the model feature information of the first positioning model included in the model information may correspond to the model requirements indicated by the model requirement information. For example, if the model requirement information includes model structure requirement information and model generalization capability requirement information, the network data analysis function element may provide feedback on the corresponding model structure information and model generalization capability information.

[0288] Optionally, if the first positioning model is a positioning model that is independently determined by the network data analysis function network element and meets the current environmental requirements, the network data analysis function can also send first environmental identification information to the location management function network element. The specific details of the first environmental identification information can be referred to the above introduction to S402 and will not be expanded here.

[0289] Furthermore, after receiving the first positioning model, the location management function network element may locate the terminal device based on the output of the first positioning model, that is, obtain estimated location information of the terminal device.

[0290] Optionally, the first positioning model may directly output the estimated location information of the terminal device, in which case the first positioning model may be a D-AIML model. Alternatively, the first positioning model may output intermediate information used to assist the location management function network element in estimating the location of the terminal device, in which case the first positioning model may be an A-AIML model.

[0291] Optionally, when positioning the terminal device based on the first positioning model, the input of the first positioning model may be measurement data obtained by the terminal device or the access network device measuring a reference signal, such as CIR, PDP and other data.

[0292] Optionally, if after obtaining the first positioning model, the location management function network element deploys one or more additional positioning models (which can be called second positioning models) in addition to the first positioning model, that is, the location management function network element deploys multiple positioning models, and these multiple positioning models include the first positioning model and one or more second positioning models, then the location management function network element can select the target positioning model actually used to locate the terminal device from these multiple positioning models.

[0293] Optionally, the second positioning model may be locally deployed by the location management function network element, i.e., pre-configured in the location management function network element. Alternatively, the second positioning model may be sent to the location management function network element by the network data analysis function network element. Alternatively, the second positioning model may be obtained by the location management function network element from another network element. This embodiment of the present application does not specifically limit the method for obtaining the second positioning model.

[0294] In a possible implementation, the location management function network element may select a target positioning model according to the environment identification information.

[0295] Specifically, the multiple positioning models deployed by the location management function network element each have corresponding environment identification information. Among the multiple positioning models, the first environment identification information corresponding to the first positioning model may be sent to the location management function network element by the network data analysis function network element. If the second positioning model is deployed locally by the location management function network element, the environment identification information corresponding to the second positioning model may be configured together with the second positioning model. If the second positioning model is sent to the location management function network element by the network data analysis function network element or another network element, the environment identification information corresponding to the second positioning model may be sent to the location management function network element together with the second positioning model. When preparing to select a target positioning model, the location management function network element obtains second environment identification information used to identify the current environment (referring to the current environment of the area to which the target positioning model will be applied), and then selects, from the multiple positioning models, a positioning model whose corresponding environment identification information is identical to the second environment identification information as the target positioning model. Furthermore, if the environment identification information corresponding to the multiple positioning models does not contain the same environment identification information as the second environment identification information, the location management function network element may select, as the target positioning model, a positioning model whose environment identified by the corresponding environment identification information is similar to the environment identified by the second environment identification information.

[0296] Among them, optionally, the second environment identification information can be obtained by the location management function network element from the network data analysis function network element, the terminal device or the access network device. In one possible implementation, the location management function network element can send a subscription message to the network data analysis function network element, the terminal device or the access network device, and the subscription message is used to request feedback of the environment identification information. The network data analysis function network element, the terminal device or the access network device can feedback the second environment identification information based on the subscription information. Optionally, the subscription message can include some filtering information, such as information for indicating a specific area (i.e., the area where the target positioning model is to be applied) or information such as a time period, which can be used to indicate the acquisition of an environment identification that identifies the environment of a specific area within a specific time. Optionally, the subscription information can also include conditions for feedback of the environment identification information, such as periodic feedback or feedback of the environment identification information when specific conditions are met (for example, the determined environment identification is a specific environment identification).

[0297] Among them, the specific implementation of determining the second environment identification information can refer to the above introduction of the network data analysis function network element determining the first environment identification information, which will not be elaborated here.

[0298] Based on this solution, if multiple positioning models have been deployed on the location management function network element, the location management function network element can obtain environmental identification information that identifies the current environment from other network elements, and select a positioning model suitable for the current environment for positioning based on the environmental identification information.

[0299] In another possible implementation, the location management function network element may select a target positioning model based on a positioning error of a specific positioning algorithm.

[0300] Specifically, the multiple positioning models deployed by the location management function network element each have positioning error information of a corresponding specific positioning algorithm. Among the multiple positioning models, the positioning error between the first positioning model and the specific positioning algorithm may be sent to the location management function network element by the network data analysis function network element. If the second positioning model is deployed locally by the location management function network element, the positioning error of the specific positioning algorithm corresponding to the second positioning model may be configured together with the second positioning model. If the second positioning model is sent to the location management function network element by the network data analysis function network element or other network elements, the positioning error of the specific positioning algorithm corresponding to the second positioning model may be sent to the location management function network element together with the second positioning model. When preparing to select a target positioning model, the location management function network element may calculate the positioning error of the specific positioning algorithm in the current environment (referring to the current environment of the area where the target positioning model will be applied), and then select, from the multiple positioning models, the positioning model with the smallest deviation between the positioning error corresponding to the specific positioning algorithm and the positioning error of the specific positioning algorithm in the current environment as the target positioning model.

[0301] Among them, the positioning error of the specific positioning algorithm corresponding to the positioning model, as well as the specific implementation of calculating the positioning error of the specific positioning algorithm in the current environment, can be referred to the above introduction to the specific implementation of the network data analysis function network element autonomously determining the positioning model that meets the current environment requirements, which will not be expanded here.

[0302] Based on this solution, if multiple positioning models have been deployed on the location management function network element, the location management function network element can select the positioning model suitable for the current environment for positioning based on the positioning error of the specific positioning algorithm in the current environment and the positioning errors of the specific positioning algorithms corresponding to multiple positioning models.

[0303] Assume that the above embodiment is applied to a 5G system, in which case the location management function network element is the LMF network element, the network data analysis function network element is the NWDAF network element, the network management network element is the OAM network element, the application function network element is the AF network element, and the access and mobility management function network element is the AMF network element. In this scenario, an exemplary process for the LMF network element to obtain a positioning model from the NWDAF network element can be shown in Figure 5, including the following steps:

[0304] S501: The LMF network element sends a first message to the NWDAF network element, where the first message is used to request a model. The first message may include a Model requirements profile parameter and a Model Type Indicator parameter. The Model requirements profile parameter is used to indicate the LMF network element's requirements for the positioning model, and the Model Type Indicator parameter is used to indicate that the type of model requested by the LMF network element is a positioning model.

[0305] For details of S501, please refer to the above introduction to S401, which will not be elaborated here.

[0306] S502. The NWDAF network element obtains training data from the OAM network element / other network function (NF).

[0307] Alternatively, S502 may refer to the method for obtaining training data by the existing NWDAF network element, which will not be expanded here. Alternatively, S502 may refer to the method for obtaining training data for training the positioning model by the network data analysis function network element described below, the specific implementation of which will be introduced below and will not be expanded here.

[0308] S503 : The NWDAF network element trains a positioning model that meets the parameter requirements of the Model requirements profile, that is, the first positioning model.

[0309] For details of S503, please refer to the above introduction to S402, which will not be elaborated here.

[0310] S504. The NWDAF network element sends the trained first positioning model (for example, sends the address of the model file, or sends the model file) and model information (model information) of the first positioning model to the LMF network element.

[0311] For details of S504, please refer to the above introduction to S403, which will not be elaborated here.

[0312] Alternatively, another exemplary process of the LMF network element obtaining the positioning model from the NWDAF network element may be shown in FIG6 , including the following steps:

[0313] S601: LMF network element 1 sends a first message to an NWDAF network element, where the first message is used to request a model. The first message may include a Model Type Indicator parameter and a Model Selection Indicator parameter. The Model Type Indicator parameter is used to indicate that the type of model requested by the LMF network element is a positioning model, and the Model Selection Indicator parameter is used to instruct the NWDAF network element to autonomously determine and provide a positioning model that meets the requirements of the current environment.

[0314] For details of S601, please refer to the above introduction to S401, which will not be elaborated here.

[0315] S602: The NWDAF network element obtains relevant measurement data for determining the first environment identification information from the OAM network element / LMF network element 2 / AF network element. LMF network element 2 and LMF network element 1 may be the same network element or different network elements. When LMF network element 2 and LMF network element 1 are different network elements, the NWDAF may also obtain relevant measurement data for determining the first environment identification information from both LMF network element 1 and LMF network element 2.

[0316] Among them, optionally, the message requesting relevant measurement data sent by the NWDAF network element to the LMF network element 2, and / or the relevant measurement data sent by the LMF network element 2 to the NWDAF network element can be forwarded by the AMF network element.

[0317] S603: The NWDAF network element determines first environment identification information, and trains a first positioning model according to the first environment identification information.

[0318] For details of S602 and S603, please refer to the above introduction to S403, which will not be elaborated here.

[0319] S604. The NWDAF network element sends the trained first positioning model, model information of the first positioning model, and first environment identification information to the LMF network element 1.

[0320] For details of S604, please refer to the above introduction to S403, which will not be elaborated here.

[0321] S605. The LMF1 network element sends subscription information to the NWDAF network element, requesting feedback of environment identification information.

[0322] S606. The NWDAF network element obtains measurement data related to the current environment from the OAM network element / LMF network element 2 / AF network element.

[0323] Among them, optionally, the message requesting relevant measurement data sent by the NWDAF network element to the LMF network element 2, and / or the relevant measurement data sent by the LMF network element 2 to the NWDAF network element can be forwarded by the AMF network element.

[0324] S607 : The NWDAF network element determines second environment identification information according to the acquired measurement data related to the current environment.

[0325] S608. The NWDAF network element sends the second environment identification information to the LMF network element 1.

[0326] For details of S605-S608, reference may be made to the above description of the location management function network element selecting the target positioning model according to the second environment identification information, which will not be elaborated here.

[0327] The above describes a method for a location management function network element to obtain a positioning model from a network data analysis function network element. In addition, an embodiment of the present application also provides a method for a network data analysis function network element to obtain training data for training a positioning model.

[0328] Optionally, the method for the network data analysis function network element to obtain training data provided in the embodiment of the present application can be combined with the method for the location management function network element to obtain the positioning model from the network data analysis function network element in the above embodiment. In this case, the network data analysis function network element can execute the training data acquisition method in the following embodiment after receiving the first message to obtain training data to train the positioning model. Alternatively, the method for the network data analysis function network element to obtain training data provided in the embodiment of the present application can also be applied independently with the method for the location management function network element to obtain the positioning model from the network data analysis function network element in the above embodiment.

[0329] 7 , a method for obtaining training data provided in an embodiment of the present application includes steps S701-S702:

[0330] S701: A network data analysis function network element sends a second message to a first network element, and the first network element receives the second message. The second message is used to request training data, and the second message includes event identification information; the event identification information is used to identify the requested training data, and the training data includes at least one of the following: a channel impulse response, a channel energy response, and a channel power delay profile.

[0331] In S701, optionally, the first network element may be a location management function network element, a network management network element, a session management function network element, an access and mobility management function network element, or an application function network element, or may be other network elements.

[0332] In one possible implementation, the first network element and the network data analysis function network element may pre-configure a correspondence between event identification information and one or more types of data, so that the network data analysis function network element may request corresponding types of training data from the first network element by sending event identification information. For example, assuming that event identification information 1 corresponds to CIR and CER, and event identification information 2 corresponds to PDP, if the second message sent by the network data analysis function network element to the first network element includes event identification information 1, the first network element may determine, based on event identification information 1, that the data requested by the network data analysis function network element includes CIR and CER, and thereby feedback the corresponding data to the network data analysis function network element.

[0333] Optionally, the second message may include regional information for indicating that training data is to be obtained within a specific area. Optionally, if the method for obtaining training data shown in FIG. 7 is combined with the model acquisition method shown in FIG. 4 , the area corresponding to the regional information included in the second message may be the applicable area of ​​the positioning model to be trained by the network data analysis function element.

[0334] S702. The first network element sends training data to the network data analysis function network element. Correspondingly, the network data analysis function network element receives the training data from the first network element.

[0335] Based on an embodiment of the present application, a method is provided for a network data analysis function network element to obtain at least one piece of data among channel impulse response, channel energy response, and channel power delay distribution as training data for a positioning model. The network data analysis function network element can train the positioning model based on the obtained data to improve the model accuracy of the positioning model.

[0336] In S702, after receiving the second message, the first network element obtains corresponding training data according to the event identification information therein and sends the obtained training data to the network data analysis function network element.

[0337] Optionally, in the training data sent by the first network element, one piece of training data may be associated with identification information of a terminal device (eg, UE ID) and a timestamp, indicating a measurement result of the terminal device at the moment corresponding to the timestamp.

[0338] Optionally, the first network element may send one or more sets of training data to the network data analysis function network element. A set of training data may include one or more training data. In one possible implementation, the training data may be grouped according to identification information of associated terminal devices, for example, training data associated with the same UE ID is placed in the same group.

[0339] Optionally, if the first network element is a location management function network element, after receiving the second message, the location management function network element may obtain training data from the terminal device through the LTE positioning protocol (LPP). Alternatively, the location management function network element may also obtain training data from the access network device through the NR Positioning Protocol A (NRPPa).

[0340] Optionally, if the first network element is a network management element, the network management element may obtain the training data from the access network device through a process such as minimization of drive tests reporting (MDT reporting).

[0341] Optionally, if the first network element is a session management network element, the session management network element may obtain training data from the terminal device or the access network device through a service request (SR) process or a PDU session establishment / modification / release process.

[0342] Optionally, if the first network element is an access and mobility management function network element, the access and mobility management function network element may obtain training data from the terminal device or access network device through a terminal device configuration update process or a terminal device capability reporting process.

[0343] Optionally, if the first network element is an application function network element, the application function network element may obtain training data from the terminal device through an application on the terminal device.

[0344] Optionally, if the method for obtaining training data as shown in Figure 7 is combined with the method for the location management function network element to obtain the positioning model from the network data analysis function network element as shown in Figure 4, the network data analysis function network element can execute S701 to request training data from the first network element after receiving the first message.

[0345] Optionally, in this scenario, the training data requested by the network data analysis function element from the first network element may be determined based on the first message. For example, if the first message includes model input requirement information indicating the type of training data input to the positioning model, the network data analysis function element may send event identification information indicating the same training data to the first network element based on the indication in the model input requirement information.

[0346] Furthermore, in this scenario, after the network data analysis function network element receives the training data from the first network element, it can train a positioning model based on the obtained training data to obtain a first positioning model. In other words, the above-mentioned method for the network data analysis function network element to obtain training data can also include S703: the network data analysis function network element trains the first positioning model based on the training data.

[0347] Assume that the above-mentioned method for the network data analysis function network element to obtain training data from the first network element is applied to a 5G system. In this case, the location management function network element is the LMF network element, the network data analysis function network element is the NWDAF network element, the network management network element is the OAM network element, the application function network element is the AF network element, the session management network element is the SMF network element, the access and mobility management function network element is the AMF network element, the access network device is the RAN, and the terminal device is the UE. In this scenario, an exemplary process for the NWDAF network element to obtain training data from the first network element can be shown in Figure 8, including the following steps:

[0348] S801a. The NWDAF network element sends a subscription message to the LMF network element. The subscription message includes a specific event identifier (Event ID) for instructing the LMF network element to collect and provide one or more of the following information: CIR, CER, PDP.

[0349] Optionally, the NWDAF network element can send a subscription message through the AMF network element 1.

[0350] S802a. The LMF network element collects corresponding measurement data from the UE / RAN as training data.

[0351] S803a. The LMF network element sends a notification message to the NWDAF network element. The notification message includes one or more sets of training data.

[0352] Optionally, the LMF network element can send a notification message through the AMF1 network element.

[0353] S801b. The NWDAF network element sends a subscription message to the OAM network element. The subscription message includes a specific event identifier, which is used to instruct the OAM network element to collect and provide one or more of the following information: CIR, CER, and PDP.

[0354] S802b: The OAM network element collects corresponding measurement data from the RAN as training data.

[0355] S803b: The OAM network element sends a notification message to the NWDAF network element. The notification message includes one or more sets of training data.

[0356] S801c, NWDAF network element sends a subscription message to the SMF network element. The subscription message contains a specific event identifier, which is used to instruct the SMF network element to collect and provide one or more of the following information: CIR, CER, PDP.

[0357] S802c: The SMF network element collects corresponding measurement data from the UE / RAN as training data.

[0358] S803c. The SMF network element sends a notification message to the NWDAF network element. The notification message includes one or more sets of training data.

[0359] S801d, NWDAF network element sends a subscription message to the AMF network element. The subscription message contains a specific event identifier, which is used to instruct AMF network element 2 to collect and provide one or more of the following information: CIR, CER, PDP.

[0360] Optionally, AMF network element 1 and AMF network element 2 can be the same network element or different network elements.

[0361] S802d, AMF network element 2 collects corresponding measurement data from UE / RAN as training data.

[0362] S803d, AMF network element 2 sends a notification message to the NWDAF network element, where the notification message includes one or more sets of training data.

[0363] S801e, the NWDAF network element sends a subscription message to the AF network element. The subscription message includes a specific event identifier, which is used to instruct the AF network element to collect and provide one or more of the following information: CIR, CER, and PDP.

[0364] S802e. The AF network element collects corresponding measurement data from the UE as training data.

[0365] S803e. The AF network element sends a notification message to the NWDAF network element. The notification message includes one or more sets of training data.

[0366] Among them, the specific implementation of S801a-S803a, S801b-S803b, S801c-S803c, S801d-S803d, and S801e-S803e can be referred to the above introduction to S701-S702, which will not be elaborated here.

[0367] It should be noted that the embodiments of the present application do not limit the timing of S801a-S803a, S801b-S803b, S801c-S803c, S801d-S803d, and S801e-S803e. For example, S801a and S802a may occur simultaneously or at different times. The process shown in FIG8 is merely intended to illustrate the interaction between different network elements and does not limit the timing of the steps shown.

[0368] 9 , another method for obtaining training data provided in an embodiment of the present application includes steps S901-S902:

[0369] S901: The network data analysis function element sends a third message to the location management function element, and the location management function element receives the third message. The third message is used to request the location information of the terminal device.

[0370] Optionally, the third message may include region information for indicating the acquisition of location information of terminal devices within a specific region. Optionally, if the method for acquiring training data shown in FIG9 is combined with the model acquisition method shown in FIG4 , the region corresponding to the region information included in the third message may be the applicable region of the positioning model to be trained by the network data analysis function element.

[0371] Optionally, the third message may include first indication information, where the first indication information is used to indicate a first capability of the terminal device, where the first capability is the ability of the terminal device to provide its own first location information: the third message is used to request the first location information of the terminal device with the first capability.

[0372] That is to say, the terminal device with the first capability can provide its own first location information.

[0373] The first location information is location information having a smaller error than the actual location information of the terminal device. For example, in the prior art, the location information of the terminal device obtained by the network data analysis function from the access and mobility management function network element or the third-party application function network element typically has an error of meter or sub-meter level compared to the actual location information of the terminal device. However, the first location information provided by the terminal device having the first capability may have an error of centimeter or millimeter level compared to the actual location information of the terminal device.

[0374] Optionally, the terminal device with the first capability may be a terminal device that does not move frequently.

[0375] Optionally, for a terminal device with the first capability, the first location information may be pre-configured in the terminal device. For example, the location information of the terminal device, i.e., the first location information, may be obtained through a professional measurement method (e.g., through a high-precision satellite positioning module built into the terminal device) and configured in the terminal device.

[0376] Exemplarily, the first indication information may be Indicator information in the third message.

[0377] S902. The location management function network element sends the first location information of the terminal device to the network data analysis function network element. Correspondingly, the network data analysis function network element receives the first location information of the terminal device.

[0378] Currently, the training data set for a model generally consists of two parts: measurement data and labels corresponding to the measurement data. For a positioning model, the label corresponding to the measurement data is generally the location information of the terminal device. The closer this location information is to the actual location of the terminal device, the more accurate the label, and the higher the accuracy of the trained positioning model. Based on an embodiment of the present application, a method is provided for a network data analysis function network element to obtain terminal location information with a small error from the actual terminal device location, which can improve the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0379] Among them, optionally, the location management function network element can send the first location information of the terminal device to the network data analysis function network element through the access and mobility management function network element, that is, the first location information of the terminal device is forwarded by the access and mobility management function network element.

[0380] Optionally, in S902, after receiving the third message, the location management network element can determine the terminal device with the first capability and obtain the first location information from the terminal device with the first capability, thereby sending the first location information of the terminal device to the network data analysis function network element.

[0381] For determining a terminal device with a first capability, in one possible implementation, the location management function network element may pre-configure the correspondence between the identification information of the terminal device (e.g., UE ID) and whether the terminal device has the first capability. For example, assuming that a terminal device with a UE ID of 1 has the first capability, and another terminal device with a UE ID of 2 does not have the first capability, wherein the terminal device having the first capability is identified by identification information a, and the terminal device not having the first capability is identified by identification information b. In the correspondence pre-configured by the location management function network element, UE ID 1 may correspond to identification information a, and UE ID 2 may correspond to identification information b.

[0382] In another possible implementation, the location management function network element may pre-configure a list of identification information of terminal devices with the first capability (or, the identification information of the terminal devices with the first capability may also be configured in the location management function network element in other forms, which is not limited in the embodiments of the present application). For example, assuming that a terminal device with UE ID 1 and a terminal device with UE ID 3 have the first capability, and another terminal device with UE ID 2 does not have the first capability, then the list of identification information of terminal devices with the first capability pre-configured by the location management function network element includes UE ID1 and UE ID3.

[0383] Optionally, in S902, the location management network element may pre-configure the first location information of the terminal device. After receiving the third message, the location management network element may send the pre-configured first location information of the terminal device to the network data analysis function network element.

[0384] Optionally, the data management network element may also provide identification information of the terminal device with the first capability to the location management network element. Before the network data analysis function network element sends the third message to the location management function network element, the training data acquisition method may further include the following steps:

[0385] S903. The network data analysis function network element sends a fourth message to the data management network element. The fourth message includes first indication information. The first indication information is used to indicate the first capability of the terminal device. The first capability is the ability of the terminal device to provide its own first location information; the fourth message is used to request identification information of the terminal device with the first capability.

[0386] Optionally, the data management network element may pre-configure the correspondence between the identification information of the terminal device and whether the terminal device has the first capability, or the data management network element may pre-configure a list of identification information of terminal devices with the first capability. For details, please refer to the above introduction on how the location management function network element determines the terminal device with the first capability, which will not be elaborated here.

[0387] After receiving the fourth message, the data management network element can obtain the identification information of the terminal device with the first capability based on the fourth message.

[0388] S904. The network data analysis function network element receives identification information of the terminal device corresponding to the first indication information from the data management network element.

[0389] In S904, the data management network element sends the acquired identification information of the terminal device with the first capability to the network data analysis function network element.

[0390] Furthermore, after the network data analysis function network element obtains the identification information of the terminal device with the first capability, it can carry the information in a third message and send it to the location management function network element. After receiving the third message, the location management function network element can obtain the first location information of the terminal device from the corresponding terminal device based on the identification information of the terminal device therein, and send it to the network data analysis function network element; or the location management network element can pre-configure the correspondence between the identification information of the terminal device (such as UE ID) and the first location information of the terminal device, and the location management network element can determine the first location information of the terminal device based on the identification information of the terminal device in the received third message and the locally pre-configured correspondence, and send it to the network data analysis function network element.

[0391] In addition, the data management network element can also provide the first location information of the terminal device to the network data analysis function network element. In this case, S901 is replaced by the network data analysis function network element sending a third message to the data management network element, and correspondingly, the location management function network element receives the third message. The third message is used to request the location information of the terminal device. S902 is replaced by the data management network element sending the first location information of the terminal device to the network data analysis function network element. For details, please refer to the above introduction to S901-S902, which will not be expanded here.

[0392] Exemplarily, the first location information of the terminal device may be a ground-truth UE coordinates parameter carried in a response message of the third message.

[0393] Optionally, after receiving the third message or the fourth message, the data management network element may also send information about the validity period corresponding to the first location information of the terminal device to the network data analysis function network element. Within the validity period, the first location information of the terminal device can be considered reliable. If the validity period is exceeded, the first location information of the terminal device may no longer be reliable. Optionally, the network data analysis function network element may discard the first location information of the terminal device that has exceeded the corresponding validity period.

[0394] Exemplarily, the information on the effective time corresponding to the first location information of the terminal device may be a Time period parameter carried in a response message of the third message or the fourth message.

[0395] Optionally, if the training data acquisition method shown in FIG. 9 is combined with the model acquisition method shown in FIG. 4 , the network data analysis function network element may execute S901 to obtain the first location information of the terminal device after receiving the first message.

[0396] Furthermore, in this scenario, after the network data analysis function element receives the first location information of the terminal device, it can train a positioning model based on the obtained first location information to obtain a first positioning model. In other words, the above-mentioned method for the network data analysis function element to obtain training data can also include S905: the network data analysis function element trains the first positioning model based on the first location information of the terminal device.

[0397] Optionally, the training data acquisition method shown in Figure 7 or the training data acquisition method shown in Figure 9 can be combined with the model acquisition method shown in Figure 4. If the network data analysis function network element obtains the first location information of the training data / terminal device from the location management function network element, the location management network element can be the location management network element that sends the first message, or it can be other location management network elements.

[0398] Assume that the above-mentioned method for the network data analysis function network element to obtain the first location information of the terminal device from the location management function network element is applied to the 5G system. In this case, the location management function network element is the LMF network element, the network data analysis function network element is the NWDAF network element, the access and mobility management function network element is the AMF network element, the terminal device is the UE, and the data management network element is the UDM network element. In this scenario, an exemplary process for the NWDAF network element to obtain the first location information of the UE from the LMF network element can be shown in Figure 10, including the following steps:

[0399] S1000a: The LMF pre-configures a correspondence between the UE ID and the first capability (UE capability) of the UE.

[0400] S1001a. The NWDAF network element subscribes to the UE location information from the LMF network element. The subscription message includes an Indicator parameter, which is used to indicate the first capability of the UE. The subscription message is used to instruct the collection of first location information (ground-truth UE coordinates) of the UE with the first capability.

[0401] Optionally, the NWDAF network element can subscribe to the UE location information from the LMF network element through the AMF network element.

[0402] S1002a. The LMF network element obtains the first location information of these UEs from specific UEs (UEs with first capabilities) based on the Indicator parameters, or the LMF network element pre-configures the first location information of these specific UEs.

[0403] S1003a. The LMF network element sends the first location information of the UE to the NWDAF network element.

[0404] Optionally, the LMF network element can send the first location information of the UE to the NWDAF network element through the AMF network element.

[0405] Optionally, the first location information of the UE may be sent to the NWDAF network element together with the corresponding UE ID.

[0406] Alternatively, as shown in FIG10 , the NWDAF network element may also obtain the first location information of the UE based on the following exemplary process:

[0407] S1000b: The UDM network element pre-configures the correspondence between the UE ID and the UE's first capability. In addition, the UDM network element may also configure the UE's first location information (ground-truth UE coordinates) and the validity period (time period) corresponding to the UE's first location information.

[0408] S1001b: The NWDAF network element subscribes to the UE location subscription information from the UDM network element. The subscription message includes an Indicator parameter for indicating the first capability of the UE. The subscription message is used to instruct the collection of UE IDs of UEs with the first capability.

[0409] S1002b. The UDM network element feeds back the UE ID of the UE with the first capability according to the subscription message.

[0410] Optionally, if the UDM network element stores the first location information of the UE and the corresponding validity time, the UDM network element may feed back the information to the NWDAF network element.

[0411] S1003b. Optionally, if the UDM network element feeds back the UE ID to the NWDAF network element but does not feed back the first location information of the UE, the NWDAF network element may send the UE ID to the LMF network element and request the LMF network element to provide the first location information of the UE corresponding to the UE ID.

[0412] Optionally, the NWDAF network element can send the UE ID to the LMF network element through the AMF network element.

[0413] S1004b. Optionally, the LMF network element obtains the first location information from the corresponding UE according to the UE ID, or obtains the first location information of the UE based on local configuration.

[0414] S1005b. The LMF network element sends the first location information of the UE to the NWDAF network element.

[0415] Optionally, the LMF network element can send the first location information of the UE to the NWDAF network element through the AMF network element.

[0416] Optionally, the first location information of the UE may be sent to the NWDAF network element together with the corresponding UE ID.

[0417] The specific implementation of S1000a-S1003a and S1000b-S1005b can refer to the above introduction to S701-S702, which will not be elaborated here.

[0418] The above describes in detail the model acquisition method and training data acquisition method provided in the embodiments of the present application in combination with Figures 4 to 10.

[0419] Optionally, the present application also proposes a training data acquisition method, which enables the network data analysis function network element to obtain the location information of M terminal devices (or M location information). The specific steps can be shown in Figure 13 below:

[0420] S1301. The network data analysis function network element sends a second request message to the first network element; correspondingly, the first network element receives the second request message from the network data analysis function network element.

[0421] The second request message is used to request the location information of the terminal device.

[0422] Optionally, the first network element can be a location management function network element (LMF network element), an operation, supervision and management function network element (OAM network element), a gateway mobile positioning center network element (GMLC network element), a session management function network element (SMF network element), an access and mobility management function network element (AMF network element), or an application function network element (AF network element), without restriction.

[0423] For the positioning model, the label of the training data is generally the location information of the terminal device. The closer this location information is to the actual location of the terminal device, the more accurate the label is, and the higher the accuracy of the trained positioning model is.

[0424] It is understandable that the location information of the terminal device can be one location information or multiple location information. For the sake of ease of understanding, it is collectively referred to as the location information of the terminal device in this application.

[0425] Optionally, the network data analysis function network element can send the identification information of the PRU of the terminal device to the first network element, and the first network element can determine that the location information of the M terminal devices is the location information corresponding to the identification information of the PRU of the M terminal devices based on the identification information of the PRU of the terminal device; or, the network data analysis function network element can send the identification information of the terminal device to the first network element, and the first network element can determine that the location information of the M terminal devices is the location information corresponding to the identification information of the M terminal devices based on the identification information of the terminal device.

[0426] Among them, the identification information of the PRU of the terminal device is pre-stored, or the identification information of the terminal device is pre-stored.

[0427] For example, taking the identification information of the PRU of the terminal device as an example, the identification information of the PRU of the terminal device can be the unique identification code of the PRU of the terminal device, or the Internet protocol (IP) address of the PRU of the terminal device, or the media access control (MAC) address of the PRU of the terminal device.

[0428] In a possible embodiment, taking the identification information of the PRU of the terminal device indicating identification 1, identification 2, ..., identification 10 as an example, the first network element can send the location information corresponding to identification 1, the location information corresponding to identification 2, ..., the location information corresponding to identification 10 to the network data analysis function network element.

[0429] It can be understood that the identification information of the PRU of the terminal device (or the identification information of the terminal device) can be sent separately, or the second request message can include the identification information of the PRU of the terminal device (or the identification information of the terminal device), that is, the identification information of the PRU of the terminal device (or the identification information of the terminal device) is carried in the second request message.

[0430] Based on the description of the identification information of the PRU of the terminal device (or the identification information of the terminal device), the network data analysis function network element can request to obtain the location information corresponding to the identification information of the terminal device (or the PRU of the terminal device) so that the label of the training data can better meet the needs of positioning model training, and provide a feasible solution for the network data analysis function network element to request to obtain the location information of the terminal device.

[0431] It can be understood that the PRU of the terminal device can be a functional module built into the terminal device, and the position of the PRU can be pre-configured or calculated by a specific positioning method (such as satellite positioning); or, the PRU can be a terminal device (that is, the PRU can be an independent terminal device), and the position information of the PRU can be pre-configured or calculated by a specific positioning method (such as satellite positioning).

[0432] It can be understood that the positioning accuracy of the location information of the PRU of the terminal device (positioning accuracy can be understood as the error between the location information of the PRU of the terminal device and the actual location information) is high, that is, the error between the location information of the PRU of the terminal device and the actual location is small. For example, the positioning accuracy of the PRU location information can reach the centimeter level.

[0433] It can be understood that the location information of the terminal device can be obtained by the first network element from the PRU of the terminal device (that is, the location information of the PRU of the terminal device is pre-configured); or, the location information of the terminal device can be obtained by collecting measurement data from the first network element and then calculating the measurement data according to different positioning methods.

[0434] Specifically, the measurement data may be the arrival time, arrival angle, arrival time difference of the signal sent by the terminal device to the first network element, and the departure angle or departure time of the signal sent by the terminal device.

[0435] Optionally, the network data analysis function network element may send a second indication message to the first network element. When the PRU is not an independent terminal device, the first network element may determine, based on the second indication message, that the location information of the M terminal devices is the location information of one or more terminal devices with PRUs and / or the location information of one or more terminal devices without PRUs (it may also be described as the M terminal devices being one or more terminal devices with PRUs and / or one or more terminal devices without PRUs); when the PRU is an independent terminal device, the first network element may determine, based on the second indication message, that the location information of the M terminal devices is the location information of one or more PRUs and / or the location information of one or more non-PRU terminal devices (it may also be described as the M terminal devices being one or more PRUs and / or one or more non-PRU terminal devices).

[0436] Alternatively, when the PRU is not an independent terminal device, the first network element can determine, based on the second indication information, that the M pieces of location information are the location information corresponding to one or more terminal devices with the PRU and / or the location information corresponding to one or more terminal devices without the PRU (i.e., one terminal device can correspond to one or more pieces of location information); when the PRU is an independent terminal device, the M pieces of location information are the location information corresponding to one or more PRUs and / or the location information corresponding to one or more terminal devices that are not PRUs (i.e., one terminal device can correspond to one or more pieces of location information).

[0437] The second indication information is used to indicate obtaining the location information of the terminal device used for model training.

[0438] It can be understood that the second indication information can be sent separately, or the second request message can also include the second indication information (that is, the second indication information is carried in the second request message).

[0439] Based on the description of the second indication information, the network data analysis function network element can request to obtain more location information of the terminal device, expand the data training set, and thus improve the model accuracy of the positioning model.

[0440] Optionally, the network data analysis function network element can send a third indication message to the first network element. Accordingly, when the PRU is not an independent terminal device, the first network element can determine the location information of the M terminal devices as the location information of the M terminal devices with the PRU based on the third indication information (it can also be described as the M terminal devices are the M terminal devices with the PRU); when the PRU is an independent terminal device, the first network element can determine the location information of the M terminal devices as the location information of the M PRUs based on the third indication information (it can also be described as the M terminal devices are the M PRUs).

[0441] Alternatively, when the PRU is not an independent terminal device, the first network element may determine, based on the third indication information, that the M pieces of location information are the location information corresponding to the terminal device in which the PRU exists (i.e., the PRU of one terminal device may correspond to one or more pieces of location information); when the PRU is an independent terminal device, the first network element may determine, based on the third indication information, that the M pieces of location information are the location information corresponding to the PRU (i.e., one PRU may correspond to one or more pieces of location information).

[0442] The third indication information is used to instruct the acquisition of the location information of the PRU of the terminal device, or it can be described as follows: the third indication information is used to instruct the acquisition of the location information of the PRU.

[0443] It can be understood that the third indication information can be sent separately, or the second request message can also include the third indication information (that is, the third indication information is carried in the second request message).

[0444] Based on the description of the third indication information, the network data analysis function network element can request to obtain the location information of the PRU of the terminal device (or request to obtain the location information of the PRU). Since the positioning accuracy of the location information of the PRU of the terminal device is relatively high, the accuracy of the label of the training data of the positioning model can be improved, thereby improving the model accuracy of the positioning model.

[0445] It can be understood that the network data analysis function network element can request to obtain the location information of M terminal devices (that is, there is no restriction on the type of terminal devices, the terminal device can be a terminal device with a PRU or a terminal device without a PRU), or it can request to obtain the location information of the PRUs of M terminal devices (that is, the terminal devices are limited to terminal devices with a PRU), or it can request to obtain the location information of the terminal device corresponding to the identification information based on the identification information, or it can request to obtain the above three types of information at the same time without restriction.

[0446] Optionally, the network data analysis function network element may send quantity threshold information to the first network element.

[0447] In which, the quantity threshold information is used to indicate the quantity threshold of the terminal device location information that is expected to be obtained, or it can be expressed as, the second request message is used to indicate the quantity threshold of the terminal device location information that is expected to be obtained; or it can be expressed as, the second request message is used to indicate the quantity threshold of the location information that is expected to be obtained.

[0448] Exemplarily, the quantity threshold information may indicate a quantity range, or the quantity threshold information may indicate a lower limit of the quantity, or the quantity threshold information may indicate an upper limit of the quantity.

[0449] For example, taking the quantity threshold information indicating a quantity range as an example, when the quantity threshold information indicates [100, 120], it can mean that the number of terminal device location information that the network data analysis function network element expects to obtain is between 100-120.

[0450] For another example, taking the quantity threshold information indicating a lower limit as an example, when the quantity threshold information indicates 100, it can mean that the number of terminal device location information that the network data analysis function network element expects to obtain is greater than or equal to 100.

[0451] For another example, taking the case where the quantity threshold information indicates an upper limit, when the quantity threshold information indicates 200, it may mean that the number of terminal device location information that the network data analysis function network element expects to obtain is less than or equal to 200.

[0452] It can be understood that the quantity threshold information can be sent separately, or the second request message can also include the quantity threshold information (that is, the quantity threshold information is carried in the second request message).

[0453] It can be understood that the network data analysis function network element can limit the amount of location information of terminal devices that are expected to be obtained. On the one hand, it can ensure that the amount of location information of terminal devices obtained meets the requirements of positioning model training as much as possible, and can improve the model accuracy of the positioning model; on the other hand, it can ensure that the amount of location information of terminal devices obtained is limited to a certain range as much as possible, which can reduce transmission overhead and improve the training efficiency of the positioning model.

[0454] S1302. The first network element sends a second response message to the network data analysis function network element; correspondingly, the network data analysis function network element receives the second response message from the first network element.

[0455] The second response message includes the location information of M terminal devices.

[0456] Wherein, M is a positive integer.

[0457] It can be understood that a terminal device can correspond to one or more location information, then the second response message can also be used to indicate M location information. For ease of understanding, unless otherwise specified, the second response information in this application shall indicate the location information of M terminal devices.

[0458] Specifically, the first network element may determine the location information of M terminal devices according to the requirements of the network data analysis function network element; or, the first network element may determine the location information of any M terminal devices.

[0459] Based on the first network element determining the location information of M terminal devices according to the requirements of the network data analysis function network element, this application proposes two possible designs:

[0460] In a first possible design, the first network element may determine the location information of M terminal devices based on the fourth indication information.

[0461] The fourth indication information is used to indicate quality requirement information.

[0462] Specifically, the network data analysis function network element sends the fourth indication information to the first network element; accordingly, the first network element receives the fourth indication information from the network data analysis function network element. Further, the first network element determines the location information of M terminal devices based on the fourth indication information.

[0463] Among them, the quality of the location information of the M terminal devices meets the quality requirements.

[0464] The quality of the location information of the terminal device may be understood as the error between the location information of the terminal device and the actual location of the terminal device (ie, the positioning accuracy of the location information of the terminal device).

[0465] It is understandable that the positioning accuracy can be determined according to different positioning methods (such as the positioning accuracy of the position information calculated by the traditional positioning method is lower, and the positioning accuracy of the position information calculated by the artificial intelligence positioning method is higher), or the positioning accuracy can be determined according to different measurement data (such as the positioning accuracy of the position information calculated by the signal transmission angle and arrival angle is higher than the positioning accuracy of the position information calculated only by the signal arrival angle); or, the positioning accuracy can be determined based on the error between the actual position of the terminal device obtained and the position information calculated by the measurement data.

[0466] Among them, the quality requirement information can indicate a quality threshold (which can be understood as a threshold for positioning accuracy), a threshold for the degree of positioning accuracy (such as high / medium / low), or a threshold for the positioning accuracy score (such as 80 / 100), without restriction.

[0467] In a possible embodiment, taking the quality requirement information indicating the quality threshold and the quality threshold being a numerical value (such as a first numerical value) as an example, assuming that the error between the location information of terminal device 1 and the actual location of terminal device 1 is less than the first numerical value, and the error between the location information of terminal device 2 and the actual location of terminal device 2 is greater than the first numerical value, then the first network element can send the location information of terminal device 1 to the network data analysis function network element.

[0468] In another possible embodiment, taking the quality requirement information indicating the quality threshold, and the quality threshold being a range (such as a first value - a second value) as an example, assuming that the error between the location information of terminal device 1 and the actual location of terminal device 1 is greater than the first value and less than the second value, and the error between the location information of terminal device 2 and the actual location of terminal device 2 is greater than the second value, the first network element can send the location information of terminal device 1 to the network data analysis function network element.

[0469] It is understandable that the first network element can determine the location information of a group of terminal devices (i.e., the location information of M terminal devices) according to the above two methods, and then send the location information of the group of terminal devices to the network data analysis function network element.

[0470] It can be understood that the fourth indication information can be transmitted separately; or, the second request message can also include the fourth indication information (that is, the fourth indication information is carried in the second request message).

[0471] Based on the first possible design, the first network element can determine the location information of M terminal devices, and can ensure that the positioning accuracy of the location information of each terminal device in the M terminal devices is as high as possible, and can ensure that the accuracy of the labels of the training data of the positioning model is as high as possible, thereby improving the model accuracy of the positioning model.

[0472] In a second possible design, the first network element may determine the location information of M terminal devices based on the fifth indication information.

[0473] Among them, the fifth indication information is used to indicate the ratio threshold of the number of terminal devices with PRUs in the location information of the terminal devices expected to be obtained and the number of all terminal devices obtained; or it is described as, the fifth indication information is used to indicate the ratio threshold of the number of terminal devices with PRUs in the location information of the terminal devices expected to be obtained and the number of all terminal devices fed back to the network data analysis function network element; or, the fifth indication information is used to indicate the ratio threshold of the number of location information corresponding to the terminal devices with PRUs in the location information expected to be obtained and the number of all location information obtained; or it is described as, the fifth indication information is used to indicate the ratio threshold of the number of location information corresponding to the terminal devices with PRUs in the location information expected to be obtained and the number of all location information fed back to the network data analysis function network element.

[0474] Specifically, the network data analysis function network element sends the fifth indication information to the first network element; correspondingly, the first network element receives the fifth indication information from the network data analysis function network element. Further, the first network element determines the location information of M terminal devices based on the fifth indication information.

[0475] Among them, the ratio of the number of terminal devices with PRU in M ​​terminal devices to M meets the ratio threshold; or it is understood that the ratio of the number of location information corresponding to terminal devices with PRU in M ​​location information to M meets the ratio threshold.

[0476] For example, the ratio threshold may be a numerical value, or the ratio threshold may be a range (eg, the ratio threshold may be 0.9-0.95).

[0477] In a possible embodiment, taking the ratio threshold as 0.95 and M as 100 as an example, the number of terminal devices with PRUs should be greater than or equal to 95, and the first network element can send the location information of at least 95 terminal devices with PRUs and the location information of at most 5 terminal devices to the network data analysis function network element; or, the number of location information corresponding to the terminal devices with PRUs should be greater than or equal to 95, and the first network element can send at least 95 second location information (the second location information is the location information corresponding to the PRU of the terminal device) and at most 5 third location information (the third location information is the location information corresponding to the terminal device other than PRU) to the network data analysis function network element.

[0478] It can be understood that the fifth indication information can be transmitted separately; or, the second request message can also include the fifth indication information (ie, the fifth indication information is carried in the second request message).

[0479] Based on the second possible design, the first network element can ensure that the number of terminal devices with PRUs among the M terminal devices meets the required requirements, and can ensure that the accuracy of the labels of the training data of the positioning model is as high as possible, thereby improving the model accuracy of the positioning model.

[0480] It can be understood that the above two possible designs can be combined to enable the first network element to determine the location information of M terminal devices, that is, the location information of M terminal devices can meet the quality threshold, and at the same time, the ratio of the number of terminal devices with PRU in the M terminal devices to M meets the ratio threshold.

[0481] Optionally, the location information of the terminal device may also indicate identification information of the terminal device; or, the first response information may include identification information of each terminal device.

[0482] Exemplarily, the location information of the terminal device may indicate identification information of the terminal device and location information corresponding to the identification information of the terminal device.

[0483] It can be understood that the location information of the PRU of the terminal device may be location information pre-configured on the first network element, and the first network element may determine the location information of the PRU of the terminal device based on the identification information of the PRU of the terminal device.

[0484] Optionally, the location information of each terminal device may further include time information; or, the second response message may include time information corresponding to the location information of each terminal device.

[0485] The time information is used to indicate the time when the location information is obtained.

[0486] It can be understood that when the first network element generates location information based on the collected measurement data, the time information can be the time of generating the location information corresponding to the location information; or, when the first network element receives location information from the terminal device or network device, the time information can be the time of receiving the location information corresponding to the location information.

[0487] For example, the location information of a terminal device may include location information 1 and the time period corresponding to location information 1 for generating location information 1 (such as time 1-time 2), as well as location information 2 and the time period corresponding to location information 2 for generating location information 2 (such as time 2-time 3). The network data analysis function network element can determine the corresponding location information based on the time period.

[0488] For another example, the location information of a terminal device may include location information 1 and the timestamp of generating location information 1 corresponding to location information 1 (such as time 1), as well as location information 2 and the timestamp of generating location information 2 corresponding to location information 2 (such as time 2). The network data analysis function network element can determine the corresponding location information based on the timestamp.

[0489] It can be understood that the time corresponding to the location information may refer to the time when the location information is generated (for example, the time when the location information is measured and calculated using a positioning method based on wireless access technology), or the valid time of the location information (that is, the location information is valid within the time period, and the location information changes at other times outside the time period, or the location information is no longer accurate enough).

[0490] Based on S1302, in a possible embodiment, the location information of a terminal device may include the identification information of the terminal device, one or more location information of the terminal device, and the time information corresponding to each location information; or, the first response information may include the identification information of each terminal device, one or more location information of each terminal device, and the time information corresponding to each location information.

[0491] S1303. The network data analysis function network element determines the location information of N terminal devices based on the second response message.

[0492] Wherein, N is a positive integer less than or equal to M.

[0493] Among them, when the network data analysis function network element sends the fourth indication information and / or the fifth indication information to the first network element, the network data analysis function network element can directly determine the location information of M terminal devices (that is, N is equal to M); or, regardless of whether the network data analysis function network element sends the fourth indication information and / or the fifth indication information to the first network element, the network data analysis function network element can determine the location information of N terminal devices from the location information of M terminal devices (that is, N is less than M).

[0494] It can be understood that the network data analysis function network element can directly obtain the location information of M terminal devices from the first network element, which can reduce the workload of the network data analysis function network element; or, determine the location information of N terminal devices from the location information of M terminal devices, which can improve the accuracy of the labels of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0495] Based on the network data analysis function, the network element determines the location information of N terminal devices according to the second response message. This application proposes three possible designs:

[0496] In a first possible design, the network data analysis function element determines the location information of N terminal devices based on the quality corresponding to the location information of M terminal devices.

[0497] This application proposes two possible implementations for the network data analysis function element to determine the quality corresponding to the location information of M terminal devices:

[0498] In one possible implementation, the network data analysis function network element may determine the quality corresponding to the location information of the M terminal devices based on the quality information corresponding to the location information of the M terminal devices from the first network element.

[0499] The quality information is used to indicate the quality of the location information of the terminal device.

[0500] The quality of the location information of the terminal device may be understood as the error between the location information of the terminal device and the actual location of the terminal device (ie, the positioning accuracy of the location information of the terminal device).

[0501] This application proposes three possible implementations based on the representation of quality information:

[0502] In a first possible embodiment, the quality information may indicate the positioning accuracy of the location information (i.e., a specific numerical value), and the network data analysis function network element may determine the positioning accuracy of the location information of each terminal device, and further determine the location information of N terminal devices with higher positioning accuracy from the location information of M terminal devices.

[0503] For example, the network data analysis function network element receives the location information of 30 terminal devices (i.e., M=30), and the positioning accuracy of the location information of terminal device 1-terminal device 10 is 0.05m (i.e., the error between the location information of the terminal device and the actual location of the terminal device is 0.05m), the positioning accuracy of the location information of terminal device 11-terminal device 20 is 0.3m (i.e., the error between the location information of the terminal device and the actual location of the terminal device is 0.3m), and the positioning accuracy of the location information of terminal device 21-terminal device 30 is 0.5m (i.e., the error between the location information of the terminal device and the actual location of the terminal device is 0.05m). Taking the example of FIG. 0.5m), when the network data analysis function network element requires that the positioning accuracy of the location information is higher than 0.1m (that is, the error between the location information of the terminal device and the actual location of the terminal device is less than 0.1m), the network data analysis function network element can determine that the location information of the terminal device 1-terminal device 10 is the label of the training data, or, when the network data analysis function network element requires that the positioning accuracy of the location information is higher than 0.4m (that is, the error between the location information of the terminal device and the actual location of the terminal device is less than 0.4m), the network data analysis function network element can determine that the location information of the terminal device 1-terminal device 20 is the label of the training data.

[0504] In a second possible embodiment, the quality information may indicate the degree of positioning accuracy. For example, when the positioning accuracy is high (such as the error between the location information of the terminal device and the actual location of the terminal device is less than 0.1m), it may be indicated by "high"; when the positioning accuracy is low (such as the error between the location information of the terminal device and the actual location of the terminal device is greater than 1m), it may be indicated by "low"; when the positioning accuracy is moderate (such as the error between the location information of the terminal device and the actual location of the terminal device is greater than 0.1m and less than 1m), it may be indicated by "medium".

[0505] Exemplarily, the network data analysis function network element receives the location information of 30 terminal devices (i.e., M=30). Taking the positioning accuracy of the location information of terminal devices 1-terminal devices 10 as "high", the positioning accuracy of the location information of terminal devices 11-terminal devices 20 as "medium", and the positioning accuracy of the location information of terminal devices 21-terminal devices 30 as "low" as an example, when the network data analysis function network element requires the positioning accuracy of the location information to be "high", the network data analysis function network element can determine that the location information of terminal devices 1-terminal devices 10 is the label of the training data, or, when the network data analysis function network element requires the positioning accuracy of the location information to be "medium" or "high", the network data analysis function network element can determine that the location information of terminal devices 1-terminal devices 20 is the label of the training data.

[0506] In a third possible embodiment, the quality information may indicate a positioning accuracy score. For example, when the positioning accuracy of the terminal device's location information is higher, the positioning accuracy score is higher; when the positioning accuracy of the terminal device is lower, the positioning accuracy score is lower.

[0507] For example, the network data analysis function network element receives the location information of 30 terminal devices (i.e., M=30). Taking the positioning accuracy score of the location information of terminal devices 1-terminal devices 10 as "100", the positioning accuracy score of the location information of terminal devices 11-terminal devices 20 as "90", and the positioning accuracy score of the location information of terminal devices 21-terminal devices 30 as "80" as an example, when the network data analysis function network element requires the positioning accuracy score of the location information to be greater than "95", the network data analysis function network element can determine that the location information of terminal devices 1-terminal devices 10 is the label of the training data, or, when the network data analysis function network element requires the positioning accuracy score of the location information to be greater than or equal to "90", the network data analysis function network element can determine that the location information of terminal devices 1-terminal devices 20 is the label of the training data.

[0508] Optionally, the first network element may proactively send quality information to the network data analysis function network element, or may send quality information after the network data analysis function network element requests it, without restriction.

[0509] Regarding the first network element sending quality information after the network data analysis function network element requests it, specifically, the network data analysis function network element can send a third request message to the first network element; correspondingly, the first network element can receive the third request message from the network data analysis function network element. Further, the first network element can send quality information corresponding to the location information of N terminal devices to the network data analysis function network element based on the third request message.

[0510] The third request information is used to request quality information corresponding to the location information of the terminal device.

[0511] It can be understood that the third request information can be transmitted separately, or the second request message can further include the third request information (ie, the third request information is carried in the second request message).

[0512] It can be understood that, unlike the first network element actively sending quality information to the network data analysis function network element, the network data analysis function network element can request the first network element to send quality information, which can avoid as much as possible the situation where the network data analysis function network element does not need quality information but the first network element sends quality information, and can improve the efficiency of information interaction between the network data analysis function network element and the first network element.

[0513] In another possible implementation, the network data analysis function network element may determine the quality corresponding to the location information of the M terminal devices based on the positioning accuracy of the location information of the terminal devices.

[0514] Among them, the network data analysis function network element can determine the positioning accuracy of the terminal device's location information by itself. When the positioning accuracy is higher than the quality threshold (or the positioning error is less than the quality threshold) or is within the range of the quality threshold, the terminal device's location information can be used as a label for training data.

[0515] Based on the first possible design, the network data analysis function network element can determine the location information of the terminal device with higher positioning accuracy, which can improve the accuracy of the label of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0516] In a second possible design, the network data analysis function network element can determine the location information of N terminal devices based on the sixth indication information.

[0517] The sixth indication information is used to indicate whether each of the M terminal devices has a PRU; or it can be described as, the sixth indication information indicates whether each of the M terminal devices is a PRU.

[0518] Exemplarily, taking the sixth indication information as a bit map and M as 6 as an example, when the bit value map is 100010, it can indicate that the first terminal device is a PRU, and the fifth terminal device is a PRU.

[0519] Another exemplary example is taking M as 6 and the sixth indication information as six bits. Each bit may correspond to a terminal device. When the bit value is 100010, it may indicate that the first terminal device is a PRU, and the fifth terminal device is a PRU.

[0520] Specifically, the first network element sends the sixth indication information to the network data analysis function network element; accordingly, the network data analysis function network element receives the sixth indication information from the first network element. Further, the network data analysis function network element determines the location information of N terminal devices from the location information of M terminal devices based on the sixth indication information.

[0521] The location information of the N terminal devices includes the location information of the terminal device with the PRU.

[0522] For example, taking the example where the sixth indication information indicates that there is a PRU in terminal device 1-terminal device 10, and there is no PRU in terminal device 11-terminal device 20, when the network data analysis function network element requires the use of the location information of the terminal device with the PRU as the label of the training data, the network data analysis function network element can determine the location information of the terminal device 1-terminal device 10 as the label of the training data.

[0523] It can be understood that the sixth indication information can be transmitted separately, or the second response message can also include the sixth indication information (that is, the sixth indication information is carried in the second response message).

[0524] Optionally, the first network element may proactively send the sixth indication information to the network data analysis function network element, or the first network element may send the sixth indication information after receiving a request from the network data analysis function network element.

[0525] Regarding the first network element sending the sixth indication information after the network data analysis function network element requests it, specifically, the network data analysis function network element can send the fifth request information to the first network element; correspondingly, the first network element can receive the fifth request information from the network data analysis function network element; further, the first network element can send the sixth indication information to the network data analysis function network element based on the fifth request information.

[0526] The fifth request information is used to request information on whether each terminal device has a PRU; or it can be described as the fifth request information is used to request information on whether each terminal device is a PRU.

[0527] It can be understood that the fifth request information can be transmitted separately, or the second request message can further include the fifth request information (ie, the fifth request information is carried in the second request message).

[0528] Based on the second possible design, the network data analysis function network element can determine as many terminal devices as possible with PRUs. Since the positioning accuracy of the location information of the PRUs of the terminal devices is relatively high, the accuracy of the labels of the training data of the positioning model can be improved, thereby improving the model accuracy of the positioning model.

[0529] In a third possible design, the network data analysis function network element can determine the location information of N terminal devices based on the seventh indication information.

[0530] Among them, the seventh indication information is used to indicate the location generation method corresponding to the location information of each terminal device among the M terminal devices.

[0531] Specifically, the first network element sends the seventh indication information to the network data analysis function network element; accordingly, the network data analysis function network element receives the seventh indication information from the first network element. Further, the network data analysis function network element determines the location information of N terminal devices from the location information of M terminal devices based on the seventh indication information.

[0532] Among them, the location generation method is one or more of the following: a positioning method based on wireless access technology (such as time of arrival (ToA), time difference of arrival (TDoA), angle of arrival (AoA), angle of departure (AoD)), an artificial intelligence positioning method (such as an AI / ML model based on a convolutional neural network (CNN), the model input is CIR, and the output is UE location).

[0533] For example, taking the example where the location information of terminal device 1 corresponds to a positioning method based on wireless access technology and the location information of terminal device 2 corresponds to an artificial intelligence positioning method, the network data analysis function network element can determine that the positioning accuracy of the location information of terminal device 1 is lower than the positioning accuracy of the location information of terminal device 2, and then select the location information of terminal device 2 as the label of the training data.

[0534] It can be understood that the seventh indication information can be transmitted separately, or the second response message can also include the seventh indication information (that is, the seventh indication information is carried in the second response message).

[0535] Optionally, the first network element may proactively send the seventh indication information to the network data analysis function network element, or the first network element may send the seventh indication information after receiving a request from the network data analysis function network element.

[0536] Regarding the first network element sending the seventh indication information after the network data analysis function network element requests, specifically, the network data analysis function network element can send the sixth request information to the first network element; correspondingly, the first network element can receive the sixth request information from the network data analysis function network element; further, the first network element can send the seventh indication information to the network data analysis function network element based on the sixth request information.

[0537] The sixth request information is used to request information on a location generation method corresponding to the location information of each terminal device.

[0538] It can be understood that the sixth request information can be transmitted separately, or the second request message can further include the sixth request information (ie, the sixth request information is carried in the second request message).

[0539] Based on the third possible design, different location generation methods correspond to different positioning accuracy of the location information of the terminal device. The network data analysis function network element can determine the location information of the terminal device with higher positioning accuracy based on the location generation method corresponding to the location information of the terminal device, thereby improving the accuracy of the label of the training data of the positioning model, thereby improving the model accuracy of the positioning model.

[0540] It is understandable that the network data analysis function network element can jointly determine the location information of N terminal devices according to the above three possible designs or any two of the above three possible designs. This application proposes two possible embodiments:

[0541] In a possible embodiment, taking the example of the sixth indication information indicating that there is a PRU in terminal devices 1-terminal devices 10, no PRU in terminal devices 11-terminal devices 20, and the seventh indication information indicating that the location generation method corresponding to the location information of terminal devices 1-terminal devices 15 is an artificial intelligence positioning method, and the location generation method corresponding to the location information of terminal devices 16-terminal devices 20 is a positioning method based on wireless access technology, when the network data analysis function network element requires the use of a terminal device with a PRU and the location information generated using the artificial intelligence positioning method as a label for training data, the network data analysis function network element can determine that the location information of terminal devices 1-terminal devices 10 is the label for training data.

[0542] In another possible embodiment, taking the sixth indication information indicating that there is a PRU in terminal devices 1-terminal devices 15, there is no PRU in terminal devices 16-terminal devices 20, and the positioning accuracy score of the location information of terminal devices 1-terminal devices 10 is 100, the positioning accuracy score of the location information of terminal devices 11-terminal devices 15 is 90, and the positioning accuracy score of the location information of terminal devices 16-terminal devices 20 is 80 as an example, when the network data analysis function network element requires the use of location information generated by the terminal device with PRU and a positioning accuracy score greater than or equal to 90 as the label of the training data, the network data analysis function network element can determine the location information of terminal devices 1-terminal devices 15 as the label of the training data.

[0543] After receiving the location information of the M terminal devices, the network data analysis function network element may train a positioning model based on the location information of the N terminal devices to obtain a first positioning model. In other words, the above-mentioned method for the network data analysis function network element to obtain training data may also include S1304: the network data analysis function network element trains the first positioning model based on the location information of the N terminal devices.

[0544] Among them, the training of the first positioning model can refer to the following Figures 14 and 15, which will not be described in detail here.

[0545] Based on the method for obtaining training data shown in Figure 13, a method is provided for a network data analysis function network element to request the location information of a terminal device. The network data analysis function network element can obtain the location information of more terminal devices, expand the data training set, and thus improve the model accuracy of the positioning model.

[0546] It is understandable that the training data set of the first positioning model may include two parts: training data and labels of the training data (ie, location information of the terminal device).

[0547] The labels of the training data may be determined according to the method shown in S1301 - S1303 above, which will not be described in detail here.

[0548] In a possible implementation, the specific steps of the network data analysis function training the first positioning model may be as shown in FIG14 below:

[0549] S1401. The network data analysis function network element sends fourth request information to the second network element; correspondingly, the second network element receives the fourth request information from the network data analysis function network element.

[0550] The fourth request information is used to request the first data corresponding to the location information of N terminal devices.

[0551] The first data is used to train a first positioning model.

[0552] For example, the first data may be one or more of the following: CIR, CER, or PDP.

[0553] Optionally, the second network element can be a location management function network element (LMF network element), an operation, supervision and management function network element (OAM network element), a gateway mobile positioning center network element (GMLC network element), a session management function network element (SMF network element), an access and mobility management function network element (AMF network element), or an application function network element (AF network element), without restriction.

[0554] It is understandable that the second network element may be the same network element as the first network element, or may be a different network element, without limitation.

[0555] It is understandable that when the first network element and the second network element are the same network element, the fourth request information can be transmitted separately; or, the second request message can further include the fourth request information (i.e., the fourth request information is carried in the second request message). When the first network element and the second network element are not the same network element, the fourth request information can be transmitted separately (i.e., the fourth request information is not carried in the second request message).

[0556] S1402. The second network element sends first data corresponding to the location information of N terminal devices to the network data analysis function network element; correspondingly, the network data analysis function network element receives the first data corresponding to the location information of N terminal devices from the second network element.

[0557] Among them, the second network element can send the first data corresponding to the location information of N terminal devices while sending the location information of N terminal devices, which can ensure that the first data and the label corresponding to the first data are temporally associated.

[0558] S1403. The network data analysis function network element trains a first positioning model based on the location information of the N terminal devices and the first data corresponding to the location information of the N terminal devices.

[0559] It can be understood that after the network data analysis function network element determines the location information of N terminal devices, it can determine the first data corresponding to the location information of the N terminal devices.

[0560] Based on the method shown in Figure 14, the network data analysis function network element can receive the first data corresponding to the location information of the terminal device at the same time as receiving the location information of the terminal device, and can ensure that the first data and the label of the first data are consistent in time as much as possible, and propose a feasible solution for associating the first data and the label of the first data.

[0561] In another possible implementation, the steps of training the first positioning model by the network data analysis function may be as shown in FIG15 below:

[0562] S1501. The network data analysis function network element sends a second message to the third network element; correspondingly, the third network element receives the second message from the network data analysis function network element.

[0563] It can be understood that the second message may include identification information of N terminal devices, and the third network element may determine the corresponding first data based on the identification information of the N terminal devices.

[0564] Optionally, the third network element can be a location management function network element (LMF network element), an operation, supervision and management function network element (OAM network element), a gateway mobile positioning center network element (GMLC network element), a session management function network element (SMF network element), an access and mobility management function network element (AMF network element), or an application function network element (AF network element), without restriction.

[0565] It is understandable that the third network element can be the same network element as the first network element, or a different network element; or, the third network element can be the same network element as the second network element, or a different network element, without limitation.

[0566] Among them, S1501 can refer to the above-mentioned S701 and will not be described in detail here.

[0567] S1502. The third network element sends the first data corresponding to N terminal devices to the network data analysis function network element; correspondingly, the network data analysis function network element receives the first data corresponding to N terminal devices from the third network element.

[0568] Among them, S1502 can refer to the above S702 and will not be described in detail here.

[0569] S1503. The network data analysis function network element trains a first positioning model according to the position information corresponding to the time information and the first data.

[0570] Among them, the network data analysis function network element can determine the time of the location information of each terminal device based on the time information corresponding to the location information of the terminal device, and then determine the first data at the same time.

[0571] For example, taking the time corresponding to the location information of the terminal device as moment 1-moment 2 as an example, assuming that in the first data of the terminal device, the time corresponding to the first data 1 is moment 1-moment 2, and the time corresponding to the first data 2 is moment 2-moment 3, the network data analysis function network element can train the first positioning model based on the location information of the terminal device corresponding to moment 1-moment 2 and the first data 1.

[0572] In one possible embodiment, taking the case where the time corresponding to the location information 1 of the terminal device is moment 1-moment 2, and the time corresponding to the location information 2 of the terminal device is moment 2-moment 3 as an example, it is assumed that in the first data of the terminal device, the time corresponding to the first data 1 is moment 1-moment 2, and the time corresponding to the first data 2 is moment 2-moment 3. When the network data analysis function network element determines the location information 1 of the terminal device, the first positioning model can be trained based on the location information 1 of the terminal device corresponding to moment 1-moment 2 and the first data 1; or, when the network data analysis function network element determines the location information 2 of the terminal device, the first positioning model can be trained based on the location information 2 of the terminal device corresponding to moment 2-moment 3 and the first data 2.

[0573] Based on the method shown in Figure 15, the network data analysis function network element can determine the first data at the same time based on the time information in the location information of the terminal device, ensure that the first data and the label of the first data are consistent in time, and propose a feasible solution for associating the first data and the label of the first data.

[0574] The following describes in detail a communication device for executing the model acquisition method or training data acquisition method provided in the embodiments of the present application in conjunction with Figures 11 and 12.

[0575] Figure 11 is a structural diagram of a communication device according to an embodiment of the present application. As shown in Figure 11 , the communication device 1100 includes a transceiver module 1101 and a processing module 1102. For ease of illustration, Figure 11 only shows the main components of the communication device.

[0576] The communication device 1100 can be applied to the communication system shown in Figure 3 to perform the functions of the location management function network element, the network data analysis function network element, or other network elements in the above method embodiments. For example, the transceiver module 1101 is used to perform the transceiver function of the communication device 1100, and the processing module 1102 is used to perform other functions of the communication device 1100 in addition to the transceiver function.

[0577] Optionally, the transceiver module 1101 may include a sending module (not shown in FIG11 ) and a receiving module (not shown in FIG11 ). The sending module is used to implement the sending function of the communication device 1100 , and the receiving module is used to implement the receiving function of the communication device 1100 .

[0578] Optionally, the communication device 1100 may further include a storage module (not shown in FIG11 ) storing a program or instruction. When the processing module 1102 executes the program or instruction, the communication device 1100 may perform the functions of the above method.

[0579] It can be understood that the communication device 1100 can be a network device, a chip (system) or other parts or components that can be set in the network device, or a device that includes a network device. This application does not limit this.

[0580] In addition, the technical effects of the communication device 1100 can refer to the technical effects of the communication method shown in Figures 4 to 10, and will not be repeated here.

[0581] In this application, the communication device 1100 is presented in the form of various functional modules divided in an integrated manner. The "module" here can refer to a specific application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions.

[0582] In some embodiments, when the communication device 1100 in Figure 11 is a chip or a chip system, the function / implementation process of the transceiver module 1101 can be implemented through the input and output interface (or communication interface) of the chip or chip system, and the function / implementation process of the processing module 1102 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0583] Since the communication device 1100 provided in this embodiment can execute the above method, the technical effects that can be obtained can refer to the above method embodiments and will not be repeated here.

[0584] As a possible product form, the various network elements described in the embodiments of the present application, such as the location management function network element or the network data analysis function network element, can be implemented using the following: one or more field programmable gate arrays (FPGA), programmable logic devices (PLD), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits that can perform the various functions described throughout this application.

[0585] As another possible product form, each network element in the embodiment of the present application, such as the location management function network element or the network data analysis function network element, may adopt the composition structure shown in FIG12 , or include the components shown in FIG12 .

[0586] Referring to FIG. 12 , there is shown a schematic diagram of the composition of a communication device 1200 provided in the present application. The communication device 1200 may be each network element in the above method embodiment, or a chip or system on chip therein.

[0587] As shown in FIG12 , the communication device 1200 includes at least one processor 1201 and at least one communication interface ( FIG12 is merely an example of one communication interface 1204 and one processor 1201). Optionally, the communication device 1200 may further include a communication bus 1202 and a memory 1203.

[0588] The processor 1201 may be a general-purpose central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 1201 may also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0589] Communication bus 1202 is used to connect the various components in communication device 1200, enabling communication between them. Communication bus 1202 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, for example. This bus can be categorized as an address bus, a data bus, a control bus, and so on. For ease of illustration, FIG12 shows a single thick line, but this does not necessarily indicate that there is only one bus or only one type of bus.

[0590] Communication interface 1204 is used to communicate with other devices or communication networks. Exemplarily, communication interface 1204 can be a module, circuit, transceiver, or any other device capable of communication. Alternatively, communication interface 1204 can be an input / output interface within processor 1201, used to implement signal input and output to the processor.

[0591] The memory 1203 may be a device with a storage function, used to store instructions and / or data, wherein the instructions may be computer programs.

[0592] Exemplarily, the memory 1203 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0593] It should be noted that the memory 1203 can exist independently of the processor 1201 or can be integrated with the processor 1201. The memory 1203 can be located within the communication device 1200 or outside the communication device 1200, without limitation. The processor 1201 can be used to execute instructions stored in the memory 1203 to implement the methods provided in the above embodiments of the present application.

[0594] As an optional implementation, the communication device 1200 may further include an output device 1205 and an input device 1206. The output device 1205 communicates with the processor 1201 and can display information in a variety of ways. For example, the output device 1205 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 1206 communicates with the processor 1201 and can receive user input in a variety of ways. For example, the input device 1206 can be a mouse, a keyboard, a touch screen device, or a sensor device.

[0595] In some embodiments, in terms of hardware implementation, those skilled in the art may conceive that the above-mentioned communication device 1100 may take the form of the communication device 1200 shown in FIG. 12 .

[0596] As an example, the functions / implementation process of the processing module 1102 in FIG11 can be implemented by the processor 1201 in the communication device 1200 shown in FIG12 calling the computer-executable instructions stored in the memory 1203. The functions / implementation process of the transceiver module 1101 in FIG11 can be implemented by the communication interface 1204 in the communication device 1200 shown in FIG12.

[0597] It should be noted that the structure shown in Figure 12 does not constitute a specific limitation on the network element structure. For example, in other embodiments of the present application, each of the network elements described above may include more or fewer components than shown in the figure, or may combine or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0598] In some embodiments, an embodiment of the present application further provides a communication device, which includes a processor for implementing the method in any of the above method embodiments.

[0599] As a possible implementation, the communication device further includes a memory. The memory is used to store necessary computer programs and data. The computer program may include instructions, and the processor may invoke the instructions in the computer program stored in the memory to instruct the communication device to execute any of the above-described method embodiments. Of course, the memory may not be located in the communication device.

[0600] As another possible implementation, the communication device also includes an interface circuit, which is a code / data read / write interface circuit, and the interface circuit is used to receive computer execution instructions (computer execution instructions are stored in a memory, may be read directly from the memory, or may pass through other devices) and transmit them to the processor.

[0601] As another possible implementation, the communication device further includes a communication interface, where the communication interface is used to communicate with a module outside the communication device.

[0602] It can be understood that the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or include chips and other discrete devices. The embodiments of the present application do not specifically limit this.

[0603] The present application also provides a computer-readable storage medium having a computer program or instruction stored thereon, which implements the functions of any of the above method embodiments when executed by a computer.

[0604] The present application also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

[0605] Those skilled in the art will appreciate that, for the sake of convenience and brevity of description, the specific working processes of the above-described systems, devices, and units may refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0606] It is understood that the systems, devices, and methods described in this application may also be implemented in other ways. For example, the device embodiments described above are merely illustrative. 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. In addition, the coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of devices or units, and may be electrical, mechanical, or other forms.

[0607] The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Components shown as units may or may not be physical units. Some or all of these units may be selected to achieve the objectives of this embodiment as needed.

[0608] 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.

[0609] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)). In the embodiment of the present application, the computer may include the aforementioned device.

[0610] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art can understand and implement other changes to the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit can implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0611] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

Claims

1. A model acquisition method, characterized in that: The method comprises: The location management function network element sends a first message to the network data analysis function network element, where the first message is used to request to obtain a positioning model; The location management function network element receives a first positioning model from the network data analysis function network element; the first positioning model is used to locate the position of the terminal device.

2. The method according to claim 1, characterized in that The first message includes model requirement information; the model requirement information is used to indicate the requirements of the location management function network element for the positioning model; the model requirement information includes at least one of model structure requirement information and model generalization capability requirement information; wherein the model structure requirement information is used to indicate the requirements of the location management function network element for the model structure of the positioning model; the model generalization capability requirement information is used to indicate the requirements of the location management function network element for the model generalization capability of the positioning model.

3. The method according to claim 2, characterized in that The model structure requirement information is identification information of the structure type required by the location management function network element.

4. The method according to claim 2 or 3, characterized in that: The model generalization capability requirement information includes information indicating the requirements of the location management function network element on the model performance of the positioning model under different test data sets.

5. The method according to claim 4, characterized in that The different test data sets are test data sets under different terminal device transmission powers; Alternatively, the different test data sets are test data sets under different network synchronization errors; Alternatively, the different test data sets are test data sets under different terminal device timing errors.

6. The method according to any one of claims 1 to 5, characterized in that: The first message includes model type indication information; the model type indication information is used to indicate that the type of the model requested by the location management function network element is a positioning model.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: The location management function network element receives model information from the network data analysis function network element; the model information includes one or more pieces of model feature information of the first positioning model.

8. The method according to claim 1, 6 or 7, characterized in that: The first message includes second information; the second information is used to instruct the network data analysis function network element to autonomously determine a positioning model that meets the current environmental requirements.

9. The method according to claim 8, characterized in that The method further comprises: The location management function network element receives first environment identification information from the network data analysis function network element; the first environment identification information corresponds to the first positioning model, and the first environment identification information is used to identify the environment corresponding to the first positioning model.

10. The method according to claim 9, characterized in that The method further comprises: The location management function network element acquires second environment identification information; the second environment identification information is used to identify the current environment; The location management function network element selects a target positioning model from the multiple positioning models according to the environmental identification information respectively corresponding to the multiple positioning models; the multiple positioning models include the first positioning model and one or more second positioning models; the environmental identification information corresponding to the target positioning model is the same as the second environmental identification information.

11. The method according to claim 10, characterized in that The second positioning model is locally deployed by the location management function network element; or, the second positioning model is sent by the network data analysis function network element to the location management function network element.

12. The method according to any one of claims 1 to 11, characterized in that: The method further comprises: The location management function network element receives a second message from the network data analysis function network element, the second message is used to request to obtain training data, and the second message includes event identification information; the event identification information is used to identify the requested training data, and the training data includes at least one of the following: channel impulse response, channel energy response, and channel power delay distribution; The location management function network element obtains the training data according to the event identification information; The location management function network element sends the training data to the network data analysis function network element; the training data is used to train the first positioning model.

13. The method according to any one of claims 1 to 12, characterized in that: The method further comprises: The location management function network element receives a third message from the network data analysis function network element, where the third message is used to request to obtain location information of the terminal device; The third message includes first indication information, where the first indication information is used to indicate a first capability of the terminal device. Ability to provide the terminal device with its own first location information; The location management function network element obtains the first location information of the terminal device according to the pre-configured correspondence between the terminal device and the first capability; The location management function network element sends the first location information of the terminal device to the network data analysis function network element; the first location information of the terminal device is used to train the first positioning model.

14. The method according to claim 13, characterized in that The location management function network element obtains the first location information of the terminal device, including: The location management function network element obtains pre-configured first location information of the terminal device; or, The location management function network element receives first location information from the terminal device.

15. A data acquisition method, characterized in that: include: The location management function network element receives a second request message from the network data analysis function network element; wherein the second request message is used to request to obtain the location information of the terminal device; The location management function network element sends a second response message to the network data analysis function network element; wherein the second response message includes the location information of M terminal devices; and M is a positive integer.

16. The method according to claim 15, characterized in that The second request message includes identification information of a positioning reference unit PRU of the terminal device; or, The location management function network element receives the identification information of the PRU of the terminal device from the network data analysis function network element; Among them, the location information of the M terminal devices is the location information corresponding to the PRUs of the M terminal devices.

17. The method according to claim 15 or 16, characterized in that The location management function network element receives second indication information from the network data analysis function network element; or, The second request message also includes second indication information; Among them, the second indication information is used to indicate the acquisition of location information of terminal devices used for model training; the location information of the M terminal devices is the location information of one or more terminal devices configured with PRU and / or the location information of one or more terminal devices not configured with PRU.

18. The method according to any one of claims 15 to 17, characterized in that: The location management function network element receives third indication information from the network data analysis function network element; or, The second request message also includes third indication information; The third indication information is used to indicate the acquisition of the location information of the PRU of the terminal device; the location information of the M terminal devices is the location information of the M terminal devices with PRU.

19. The method according to any one of claims 15 to 18, characterized in that: The location management function network element receives the quantity threshold information from the network data analysis function network element; or, The second request message also includes quantity threshold information; The quantity threshold information is used to indicate the quantity threshold of the location information of the terminal devices that is desired to be obtained.

20. The method according to any one of claims 15 to 19, characterized in that: The location management function network element receives fourth indication information from the network data analysis function network element; or, The second request message also includes fourth indication information; The location management function network element determines the location information of the M terminal devices according to the fourth indication information; The fourth indication information is used to indicate quality requirement information; the quality of the location information of the M terminal devices meets the quality requirement.

21. The method according to any one of claims 15 to 20, characterized in that: The location management function network element receives fifth indication information from the network data analysis function network element; or, The second request message also includes fifth indication information; The location management function network element determines the location information of the M terminal devices according to the fifth indication information; Among them, the fifth indication information is used to indicate the ratio threshold of the number of terminal devices with PRU in the acquired terminal device location information and the number of all acquired terminal devices; the ratio of the number of terminal devices with PRU in the M terminal devices to M satisfies the ratio threshold.

22. The method according to any one of claims 15 to 21, characterized in that: The method further comprises: The location management function network element sends the quality information corresponding to the location information of the M terminal devices to the network data analysis function network element; or, The second response message also includes quality information corresponding to the location information of the M terminal devices.

23. The method according to claim 22, characterized in that The method further comprises: The location management function network element receives third request information from the network data analysis function network element; or, The second request message also includes third request information; The third request information is used to request quality information corresponding to the location information of the terminal device.

24. The method according to any one of claims 15 to 23, characterized in that: The method further comprises: The location management function network element sends sixth indication information to the network data analysis function network element; or, The second response message also includes sixth indication information; The sixth indication information is used to indicate whether there is a PRU for each of the M terminal devices.

25. The method according to any one of claims 15 to 24, characterized in that: The method further comprises: The location management function network element sends seventh indication information to the network data analysis function network element; or, The second response message also includes seventh indication information; Among them, the seventh indication information is used to indicate the location generation method corresponding to the location information of each terminal device among the M terminal devices.

26. The method according to any one of claims 15 to 25, characterized in that: The method further comprises: The location management function network element receives fourth request information from the network data analysis function network element; or, The second request message also includes fourth request information; The fourth request information is used to request to obtain the first data corresponding to the location information of the M terminal devices; The location management function network element sends the first data corresponding to the location information of the M terminal devices to the network data analysis function network element.

27. The method according to any one of claims 15 to 26, characterized in that: The location information of each terminal device also includes time information; or, The second response message also includes time information corresponding to the location information of each terminal device; The time information is used to indicate the time for acquiring the location information.

28. A model acquisition method, characterized in that: The method comprises: The network data analysis function network element receives a first message from the location management function network element, where the first message is used to request to obtain a positioning model; The network data analysis function network element trains a first positioning model according to the first message; The network data analysis function network element sends the first positioning model to the location management function network element.

29. The method according to claim 28, characterized in that The first message includes model requirement information; the model requirement information is used to indicate the requirements of the location management function network element for the positioning model; the model requirement information includes at least one of model structure requirement information and model generalization capability requirement information; wherein the model structure requirement information is used to indicate the requirements of the location management function network element for the model structure of the positioning model; the model generalization capability requirement information is used to indicate the requirements of the location management function network element for the model generalization capability of the positioning model.

30. The method according to claim 29, characterized in that The model structure requirement information is identification information of the structure type required by the location management function network element.

31. The method according to claim 29 or 30, characterized in that The model generalization capability requirement information is used to indicate the requirements of the location management function network element on the model performance of the positioning model under different test data sets.

32. The method according to claim 31, characterized in that The different test data sets are test data sets under different terminal device transmission powers; Alternatively, the different test data sets are test data sets under different network synchronization errors; Alternatively, the different test data sets are test data sets under different terminal device timing errors.

33. The method according to any one of claims 28 to 32, characterized in that: The first message includes model type indication information; the model type indication information is used to indicate that the type of the model requested by the location management function network element is a positioning model.

34. The method according to any one of claims 28 to 33, characterized in that The method further comprises: The network data analysis function network element sends model information to the location management function network element; the model information includes one or more pieces of model feature information of the first positioning model.

35. The method according to claim 28, 33 or 34, characterized in that The first message includes second information; the second information is used to instruct the network data analysis function network element to autonomously determine a positioning model that meets the current environmental requirements.

36. The method according to any one of claims 28, 33-35, characterized in that: The network data analysis function network element trains a first positioning model according to the first message, including: The network data analysis function network element determines, according to the first message, first environment identification information corresponding to the current environment; The network data analysis function network element trains a first positioning model corresponding to the first environment identification information based on the first environment identification information.

37. The method according to claim 36, characterized in that The method further comprises: The network data analysis function network element sends first environment identification information to the location management function network element.

38. The method according to claim 37, characterized in that The method further comprises: The network data analysis function network element receives first request information from the location management function network element; the first request information is used to request the network data analysis function network element to provide environment identification information; The network data analysis function network element determines the second environment identification information according to the first request information; The network data analysis function network element sends the second environment identification information to the location management function network element.

39. The method according to any one of claims 28 to 38, characterized in that The method further comprises: The network data analysis function network element sends a second message to the first network element, the second message is used to request to obtain training data, and the second message includes event identification information; the event identification information is used to identify the requested training data, and the training data includes at least one of the following: channel impulse response, channel energy response, and channel power delay distribution; The network data analysis function network element receives the training data from the first network element; The network data analysis function network element trains a first positioning model, including: The network data analysis function network element trains the first positioning model according to the training data.

40. The method according to claim 39, characterized in that The first network element is the location management function network element, the operation, supervision and management function network element, the session management function network element, the access and mobility management function network element or the application function network element.

41. The method according to any one of claims 28 to 40, characterized in that The method further comprises: The network data analysis function network element sends a third message to the location management function network element: the third message is used to request to obtain the location information of the terminal device; The network data analysis function network element receives first location information of a terminal device from the location management function network element; The network data analysis function network element trains a first positioning model, including: The network data analysis function network element trains the first positioning model according to the first location information of the terminal device.

42. The method according to claim 41, characterized in that Before the network data analysis function network element sends the third message to the location management function network element, the method further includes: The network data analysis function network element sends a fourth message to the data management network element, the fourth message including first indication information, the first indication information being used to indicate a first capability of the terminal device, the first capability being a capability of the terminal device to provide its own first location information; the fourth message being used to request an identification of a terminal device having the first capability; The network data analysis function network element receives identification information of the terminal device corresponding to the first indication information from the data management network element; The identification information of the terminal device is carried in the third message, and the identification information of the terminal device is used by the location management function network element to determine the first location information of the terminal device.

43. The method according to any one of claims 28 to 42, characterized in that The method further comprises: The network data analysis function network element sends a third message to the data management network element, where the third message is used to request to obtain the location information of the terminal device; The network data analysis function network element receives the first location information of the terminal device from the data management network element; The network data analysis function network element trains a first positioning model, including: The network data analysis function network element trains the first positioning model according to the first location information of the terminal device.

44. The method according to claim 43, characterized in that The method also includes: the network data analysis function network element receives information on the effective time corresponding to the first location information of the terminal device from the data management network element.

45. A data acquisition method, characterized in that: include: The network data analysis function network element sends a second request message to the first network element: wherein the second request message is used to request to obtain the location information of the terminal device; The network data analysis function network element receives a second response message from the first network element; wherein the second response message includes location information of M terminal devices; M is a positive integer; The network data analysis function network element determines the location information of N terminal devices according to the second response message; the network data analysis function network element trains a first positioning model according to the location information of the N terminal devices; wherein N is a positive integer.

46. ​​The method according to claim 45, characterized in that The second request message includes identification information of a positioning reference unit PRU of the terminal device; or, The network data analysis function network element sends identification information of the PRU of the terminal device to the first network element; The location information of the M terminal devices is the location information corresponding to the identification information of the PRU of the M terminal devices.

47. The method according to claim 46, characterized in that The identification information of the PRU of the terminal device is pre-stored.

48. The method according to any one of claims 45 to 47, characterized in that The network data analysis function network element sends second indication information to the first network element; or, The second request message also includes second indication information; Among them, the second indication information is used to indicate the acquisition of location information of terminal devices used for model training; the location information of the M terminal devices is the location information of one or more terminal devices with PRU and / or the location information of one or more terminal devices without PRU.

49. The method according to any one of claims 45 to 48, characterized in that The network data analysis function network element sends third indication information to the first network element; or, The second request message also includes third indication information; The third indication information is used to indicate the acquisition of the location information of the PRU of the terminal device; the location information of the M terminal devices is the location information of the M terminal devices with PRU.

50. The method according to any one of claims 45 to 49, characterized in that The network data analysis function network element sends quantity threshold information to the first network element; or, The second request message also includes quantity threshold information; The quantity threshold information is used to indicate the quantity threshold of the location information of the terminal devices that is desired to be obtained.

51. The method according to any one of claims 45 to 50, characterized in that The second response message includes the location information of M terminal devices, including: The network data analysis function network element sends fourth indication information to the first network element; or, The second request message also includes fourth indication information; The fourth indication information is used to indicate quality requirement information; the quality of the location information of the M terminal devices meets the quality threshold.

52. The method according to any one of claims 45 to 51, characterized in that The second response message includes the location information of M terminal devices, including: The network data analysis function network element sends fifth indication information to the first network element; or, The second request message also includes fifth indication information; Among them, the fifth indication information is used to indicate the ratio threshold of the number of terminal devices with PRU in the location information of the terminal device expected to be obtained and the number of all terminal devices obtained; the ratio of the number of terminal devices with PRU in the M terminal devices to M satisfies the ratio threshold.

53. The method according to any one of claims 48 to 52, characterized in that The network data analysis function network element determines the location information of N terminal devices according to the second response message, including: The network data analysis function network element receives quality information corresponding to the location information of the M terminal devices from the first network element; or, The second response message further includes quality information corresponding to the location information of the M terminal devices; or, The network data analysis function network element determines the quality corresponding to the location information of the M terminal devices according to the positioning accuracy of the location information of the terminal device; The network data analysis function network element determines the location information of the N terminal devices based on the quality information corresponding to the location information of the M terminal devices.

54. The method according to claim 53, characterized in that The method further comprises: The network data analysis function network element sends a third request message to the first network element; or, The second request message also includes third request information; The third request information is used to request quality information corresponding to the location information of the terminal device.

55. The method according to any one of claims 45 to 54, characterized in that The network data analysis function network element determines the location information of N terminal devices according to the second response message, including: The network data analysis function network element receives sixth indication information from the first network element; or, The second response message also includes sixth indication information; The network data analysis function network element determines the location information of the N terminal devices from the location information of the M terminal devices according to the sixth indication information; The sixth indication information is used to indicate whether each of the M terminal devices has a PRU; the location information of the N terminal devices includes the location information of the terminal device with the PRU.

56. The method according to any one of claims 45 to 55, characterized in that The network data analysis function network element determines the location information of N terminal devices according to the second response message, including: The network data analysis function network element receives seventh indication information from the first network element; or, The second response message also includes seventh indication information; The network data analysis function network element determines the location information of the N terminal devices from the location information of the M terminal devices according to the seventh indication information; Among them, the seventh indication information is used to indicate the location generation method corresponding to the location information of each terminal device among the M terminal devices.

57. The method according to any one of claims 45 to 56, characterized in that The training of the first positioning model comprises: The network data analysis function network element sends a fourth request message to the second network element; wherein the fourth request message is used to request to obtain the first data corresponding to the location information of the M terminal devices; The network data analysis function network element receives first data corresponding to the location information of the M terminal devices from the second network element; The network data analysis function network element trains the first positioning model based on the location information of the M terminal devices and the first data corresponding to the location information of the M terminal devices.

58. The method according to any one of claims 45 to 57, characterized in that The location information of each terminal device also includes time information; or, The second response message also includes time information corresponding to the location information of each terminal device; The time information is used to indicate the time for acquiring the location information.

59. The method according to claim 58, characterized in that The training of the first positioning model comprises: The network data analysis function network element receives the first data corresponding to the M terminal devices from the third network element; The network data analysis function network element trains the first positioning model according to the location information corresponding to the time information and the first data.

60. The method according to claim 59, characterized in that The third network element is the location management function network element, the operation, supervision and management function network element, the gateway mobile positioning center network element, the session management function network element, the access and mobility management function network element, or the application function network element.

61. The method according to any one of claims 56 to 60, characterized in that The second network element is the location management function network element, the operation, supervision and management function network element, the gateway mobile positioning center network element, the session management function network element, the access and mobility management function network element, or the application function network element.

62. The method according to any one of claims 45 to 61, characterized in that The first network element is the location management function network element, the operation, supervision and management function network element, the gateway mobile positioning center network element, Call management function network element, access and mobility management function network element, or application function network element.

63. A model acquisition method, characterized in that: The method comprises: The location management function network element sends a first message to the network data analysis function network element, where the first message is used to request to obtain a positioning model; The network data analysis function network element receives the first message; The network data analysis function network element trains a first positioning model according to the first message; the first positioning model is used to locate the position of the terminal device; The network data analysis function network element sends the first positioning model to the location management function network element; The location management function network element receives the first positioning model.

64. A communication device, characterized in that: The apparatus comprises: a module for executing the method according to any one of claims 1 to 14, or a module for executing the method according to any one of claims 15 to 27.

65. A communication device, characterized in that: The apparatus comprises: a module for executing the method as claimed in any one of claims 28-44, or a module for executing the method as claimed in any one of claims 45-62.

66. A communication device, characterized in that: The communication device comprises: a processor and a memory; the memory is used to store computer instructions, and when the processor executes the instructions, the communication device executes the method as described in any one of claims 1-63.

67. A computer-readable storage medium, characterized in that The computer-readable storage medium comprises a computer program or instructions, and when the computer program or instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 63.

68. A communication system, characterized in that: The communication system includes a location management function network element and a network data analysis function network element, the location management function network element is used to execute the method as described in any one of claims 1-14, or the location management function network element is used to execute the method as described in any one of claims 15-27; the network data analysis function network element is used to execute the method as described in any one of claims 28-44, or the network data analysis function network element is used to execute the method as described in any one of claims 45-62.

Images