Location data reporting method, positioning method, and related apparatuses

Abstract

Provided in the present application are a location data reporting method, a positioning method, and related apparatuses. The location data reporting method comprises: in response to signaling that indicates the reporting of location ground truths, a terminal acquiring the location coordinates of the terminal; and sending a location ground truth to a base station, wherein the location ground truth comprises the location coordinates of the terminal. A base station sends a location ground truth to a core network device, and the location ground truth, which comprises location coordinates, can serve as sample data for the core network device to train a positioning model for a terminal, thereby facilitating training for obtaining a model having high levels of prediction accuracy, and thus being conducive to obtaining a more accurate terminal positioning result.

Description

Position data reporting and positioning method, and related apparatus

[0001] The present application claims priority to the Chinese patent application No. 202410886763.4, filed on July 3, 2024, and entitled "Position data reporting and positioning method, and related apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of positioning technology of mobile communication, in particular to a position data reporting and positioning method, and related apparatus. BACKGROUND

[0003] In the field of mobile communication, one way for a network to obtain the position information of a terminal is to use artificial intelligence (AI) technology to implement positioning of the terminal.

[0004] At present, there is still room for improvement in the function of the network using AI technology to position the terminal.

[0005] SUMMARY

[0006] Therefore, the present application provides a position data reporting and positioning method, and related apparatus to improve the function of the network using AI technology to position the terminal, and the disclosed technical solutions are as follows:

[0007] The present application provides a position data reporting method applied to a terminal, which comprises: obtaining the position coordinates of the terminal in response to signaling indicating reporting of position true values; and sending the position true values to a base station, wherein the position true values comprise the position coordinates of the terminal. The position coordinates sent by the terminal can be used as sample data for training a positioning model of the terminal, which is conducive to training a model with high prediction accuracy, and thus is conducive to obtaining a more accurate terminal positioning result.

[0008] In some implementations, the position true values further comprise a first accuracy (also referred to as a comprehensive accuracy), and the first accuracy represents at least one of the credibility and the accuracy of the position coordinates of the terminal, thereby providing a screening basis for whether the position true values can be used as training data, and is conducive to screening sample data that contributes to improving the accuracy of the model and the prediction result of the model.

[0009] In some implementations, the first accuracy is obtained based on a preset credibility of the positioning method and the accuracy ACC of the position coordinates of the terminal, and the positioning method is used to obtain the position coordinates of the terminal. Compared with relying on ACC alone, the first accuracy can better reflect the contribution of the position coordinates of the terminal to improving the accuracy of the model and the prediction result of the model.

[0010] In some embodiments, the preset credibility is a first credibility which is a value in a credibility set, the credibility set includes a first number of integer values greater than 0, and each value in the credibility set represents a credibility; the first precision is obtained based on the preset credibility of the positioning manner and an accuracy ACC of the position coordinate of the terminal, and includes that a value of the first precision is positively correlated with a value of the preset credibility, and the value of the first precision is greater than or equal to the ACC.

[0011] In some embodiments, the first precision is equal to a product of a first value and the ACC, and the first value is obtained based on the credibility.

[0012] In some embodiments, the position truth value further includes at least one of information of the positioning manner and positioning precision, the positioning manner is used to obtain the position coordinate of the terminal, and the positioning precision represents the ACC of the position coordinate of the terminal obtained by the positioning manner.

[0013] The second aspect of the present application provides a position data reporting method applied to a base station, the method including: sending signaling indicating reporting of a position truth value to a terminal; receiving a position coordinate of the terminal sent by the terminal; and sending the position truth value to a core network device, the position truth value including the position coordinate of the terminal and a first precision, the first precision representing at least one of credibility and accuracy of the position coordinate of the terminal, which lays a foundation for the core network device to take the position coordinate as sample data for training a positioning model of the terminal, is conducive to training a model with high prediction accuracy, and is further conducive to obtaining a more accurate terminal positioning result.

[0014] In some embodiments, the first precision is obtained based on a preset credibility of the positioning manner and an accuracy ACC of the position coordinate of the terminal.

[0015] In some embodiments, the preset credibility is a first credibility which is a value in a credibility set, the credibility set includes a first number of integer values greater than 0, and each value in the credibility set represents a credibility; the first precision is obtained based on the preset credibility of the positioning manner and an accuracy ACC of the position coordinate of the terminal, and includes that a value of the first precision is positively correlated with a value of the preset credibility, and the value of the first precision is greater than or equal to the ACC.

[0016] In some embodiments, the first precision is equal to a product of a first value and the ACC, and the first value is obtained based on the credibility.

[0017] In some embodiments, the position truth value further includes at least one of information of the positioning manner and positioning precision, the positioning manner is used to obtain the position coordinate of the terminal, and the positioning precision represents the ACC of the position coordinate of the terminal obtained by the positioning manner.

[0018] In some implementations, the receiving the position coordinates of the terminal sent by the terminal comprises: receiving a first position truth value sent by the terminal, the first position truth value comprising the position coordinates of the terminal and a first precision; and the sending the position truth value to the core network device comprises: sending the first position truth value to the core network device. That is, the base station directly sends the position truth value sent by the terminal.

[0019] In some implementations, the receiving the position coordinates of the terminal sent by the terminal comprises: receiving a second position truth value sent by the terminal, the second position truth value comprising the position coordinates of the terminal, information of a positioning mode and an ACC; the sending the position truth value to the core network device comprises: obtaining the first precision based on the second position truth value; and the sending the first position truth value to the core network device comprises: sending the first position truth value to the core network device, the first position truth value comprising the position coordinates of the terminal and the first precision. The base station needs to obtain the first position truth value based on the second position truth value sent by the terminal, thereby saving the resources of the terminal.

[0020] The third aspect of the present application provides a positioning method applied to a core network device, the method comprising: receiving a position truth value sent by a base station, the position truth value comprising position coordinates of a terminal and a first precision, the first precision representing at least one of a credibility and an accuracy of the position coordinates of the terminal; filtering a target position truth value from the position truth value based on the first precision; obtaining sample data with the position truth value by adapting the target position truth value and pre-obtained training sample data; training a model using the sample data with the position truth value to obtain a first model, the first model being used for predicting the position of the terminal. Because the training sample has the position truth value, the prediction accuracy of the model obtained by training can be improved, thereby obtaining a positioning result of the terminal with higher accuracy.

[0021] In some implementations, the method further comprises: performing semi-supervised training on the model using the sample data with the position truth value and sample data without the position truth value to obtain a second model, the model obtained by semi-supervised training having higher accuracy than a model obtained by unsupervised training.

[0022] In some implementations, the method further comprises: using the first model in a target area and using the second model in a non-target area, the target area being obtained based on the position coordinates of the terminal included in the position truth value, which is conducive to significantly improving the positioning result of the terminal in the target area, and the accuracy of the positioning result of the terminal in the non-target area is also improved.

[0023] The fourth aspect of the present application provides a terminal, comprising: a processor and a memory; the memory is used for storing program code; and the processor is used for running the program code, so that the terminal implements the position data reporting method provided by the first aspect of the present application.

[0024] The fifth aspect of the present application provides a base station, comprising: a processor and a memory; the memory is configured to store program code; and the processor is configured to run the program code, so that the base station implements the position data reporting method provided by the second aspect of the present application.

[0025] The sixth aspect of the present application provides a core network device, comprising: a processor and a memory; the memory is configured to store program code; and the processor is configured to run the program code, so that the core network device implements the positioning method provided by the third aspect of the present application.

[0026] The seventh aspect of the present application provides a computer readable storage medium, which stores instructions, when the instructions are run on an electronic device, the electronic device executes the position data reporting method provided by the first aspect or the second aspect of the present application, or the positioning method provided by the third aspect of the present application.

[0027] The eighth aspect of the present application provides a chip system, comprising: at least one processor and an interface, the interface is configured to receive code instructions and transmit to the at least one processor; and the at least one processor runs the code instructions to implement the position data reporting method provided by the first aspect or the second aspect of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0029] Fig. 1 is a schematic diagram of an example of a mobile communication system;

[0030] Fig. 2 is a flowchart of a positioning method for a terminal using AI technology in a mobile communication system;

[0031] Fig. 3 is a flowchart of a positioning method for a terminal using AI technology in a mobile communication system according to an embodiment of the present application;

[0032] Fig. 4 is a flowchart of a position data reporting and positioning method according to an embodiment of the present application;

[0033] Fig. 5 is an example diagram of a position truth value according to an embodiment of the present application;

[0034] Fig. 6 is an example diagram of a corresponding credibility, positioning accuracy and comprehensive accuracy of various positioning methods according to an embodiment of the present application;

[0035] Fig. 7 is a flowchart of another position data reporting and positioning method according to an embodiment of the present application;

[0036] FIG. 8 is a structural example diagram of a terminal disclosed by embodiments of the present application. DETAILED DESCRIPTION

[0037] The terms "first", "second", and "third" and the like in the description and in the claims of the present application and the drawings are used for distinguishing between similar objects talking nothing away from the possible number of objects.

[0038] In the embodiments of the present application, the word "exemplary" or "for example" is used to mean serving as an example, instance, or illustration. Any implementation or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being preferred or advantageous over other implementations or design schemes. Rather, the word "exemplary" or "for example" is used to present concepts in a particular manner.

[0039] FIG. 1 is an example of a mobile communication system including a terminal, a base station, and a core network device.

[0040] The mobile communication system can be a second generation (2G) communication system, a third generation (3G) communication system, can be an LTE system, can be a fifth generation (5G) communication system, can be an LTE and 5G hybrid architecture, can be a 5G New Radio (5G NR) system, and a new communication system to be developed in future communication development, etc.

[0041] The terminal is connected to the base station in a wireless manner, and the base station is connected to the core network device in a wireless or wired manner.

[0042] The terminal can be various forms, for example, a mobile phone, a Pad, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a vehicle-mounted terminal device, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a wearable terminal device, and the like. The terminal can also be referred to as a terminal device, a user equipment (UE), an access terminal device, a vehicle-mounted terminal, an industrial control terminal, a UE unit, a UE station, a mobile station, a mobile station, a remote station, a remote terminal device, a mobile device, a UE terminal device, a terminal device, a wireless communication device, a UE agent, or a UE apparatus, and the like. The terminal can also be a fixed terminal or a mobile terminal.

[0043] The base station is any device located at the network side and having wireless transceiver function, including but not limited to: an evolved Node B (eNB or e-NodeB) in long term evolution (LTE), a base station (gNodeB or gNB) or transmission receiving point (TRP) in new radio (NR), a base station in subsequent evolution of 3GPP, an access node in Wi-Fi system, a wireless relay node, a wireless backhaul node, and the like. The base station can be: a macro base station, a micro base station, a pico base station, a small station, a relay station, or a balloon station, and the like. The base station can include one or more co-sited or non-co-sited transmission reception points (TRPs). The base station can also be a wireless controller in a cloud radio ACCess network (CRAN) scenario, a centralized unit (CU), and / or a distributed unit (DU). The base station can communicate with the terminal, or communicate with the terminal through the relay station.

[0044] The core network device and the base station can be independent different physical devices, or the functions of the core network device and the logical functions of the base station can be integrated on the same physical device, or a physical device can integrate part of the functions of the core network device and part of the functions of the base station.

[0045] In FIG. 1, the core network device includes a mobility management entity (MME) and a location management function (LMF) as an example.

[0046] In some implementations, an AI model for predicting location information of a terminal is configured in the LMF (not shown in FIG. 1).

[0047] An AI model is a specific implementation of an AI function, and the AI model represents a mapping relationship between inputs and outputs of the model. The AI model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q-learning model, or other machine learning models. In embodiments of the present application, the functions of the AI model can include one or more of the following: data collection (collecting training data and / or inference data), data preprocessing, model training (or model learning), model information publishing (configuring model information), model verification, model inference, or inference result publishing, and the like.

[0048] The AI model can be a neural network or other machine learning model.

[0049] FIG. 2 shows an example of a process of positioning a terminal using AI technology by the mobile communication system shown in FIG. 1:

[0050] 1. The base station issues a measurement indication of a signal to the terminal.

[0051] 2. The terminal measures the signal based on the measurement indication, obtains parameters as measurement results, and sends the parameters to the base station.

[0052] The signal measured by the terminal includes at least one signal that the base station can indicate the terminal to measure in the communication protocol, and the terminal can also measure autonomously rather than based on the measurement indication, that is, the signal measured by the terminal also includes at least one signal that the terminal can measure autonomously in the communication protocol, such as a channel frequency domain response.

[0053] In addition to the signals specified in the communication protocol, the signal measured by the terminal can also be a newly configured signal.

[0054] 3. The base station sends the parameters to the MME.

[0055] 4. The MME sends the parameters to the LMF.

[0056] 5. In the training phase of the AI model, the LMF trains the AI model based on the parameters (referred to as training in FIG. 2). In the testing phase of the AI model, the LMF inputs the parameters into the AI model to obtain the position information of the terminal output by the AI model (referred to as positioning in FIG. 2).

[0057] The inventors have found in the research that the accuracy of the measured parameters is not high due to the influence of the signal quality, and the parameters cannot directly reflect the actual position of the terminal, so the accuracy of the AI model obtained by training needs to be improved, and the accuracy of the position output by the AI model also needs to be improved.

[0058] In order to improve the prediction accuracy of the AI model, in the training phase of the AI model, the actual position data of the terminal can be used as part of the training data. The actual position data represents the actual position of the terminal.

[0059] Taking FIG. 3 as an example, on the basis of FIG. 2, the terminal also acquires the actual position coordinates of itself, and transmits the actual position coordinates to the LMF through the base station and the MME. The LMF trains the AI model using the actual position coordinates, which is conducive to improving the accuracy of the position prediction result output by the AI model.

[0060] However, training the AI model using the actual position data of the terminal has the following problems:

[0061] 1. The terminal can acquire the actual position data in multiple ways, and the accuracy of the actual position data acquired in some ways is not high, so it will not greatly contribute to the improvement of the accuracy of the AI model.

[0062] 2. The actual position data will increase the model training data, thereby increasing the resource consumption of the LMF.

[0063] In order to solve the above problems, embodiments of the present application provide a position data reporting method and a positioning method to train the AI model based on the position truth value of the terminal which greatly contributes to the improvement of the model accuracy, so as to improve the accuracy of the AI model without excessively increasing the resource consumption of training.

[0064] FIG. 4 is a position data reporting and positioning method provided by an embodiment of the present application, which is applied in the communication system shown in FIG. 1. It can be understood that FIG. 1 takes the AI model configured in the LMF as an example, in addition to this, the AI model can also be configured in other network elements of the core network, or in the base station, which is not limited by the embodiments of the present application. In the following embodiments, the AI configured in the LMF is taken as an example for description.

[0065] The following steps are included in FIG. 4:

[0066] S11, the base station sends signaling indicating reporting of the position true value to the terminal.

[0067] In this embodiment, the base station can send signaling specified in the communication standard to the terminal to indicate that the terminal reports the position true value, and can also configure new signaling for the base station and the terminal to indicate that the terminal reports the position true value.

[0068] The position true value represents the actual position of the terminal, for example, the position true value includes the actual position coordinates of the terminal. Compared with the aforementioned parameters as the measurement results of the terminal, the position true value can directly represent the position of the terminal, while the parameters as the measurement results directly represent the situation of the signal that the terminal can perceive, and cannot directly represent the position.

[0069] The position true value also represents at least one of the credibility and the accuracy of the actual position of the terminal. The credibility represents the degree of trust in the positioning method for obtaining the actual position of the terminal. The higher the credibility, the more credible the actual position of the terminal, and the greater the contribution to improving the accuracy of the prediction result of the AI model. The accuracy represents the accuracy of the actual position of the terminal. The higher the accuracy, the higher the accuracy of the actual position of the terminal, and the greater the contribution to improving the accuracy of the prediction result of the AI model.

[0070] The specific form of the position true value is a message or a data frame. The position true value includes multiple fields, and the specific content will be described in detail in subsequent steps.

[0071] S12, the terminal acquires the first position true value in response to the signaling.

[0072] The first position true value is a specific implementation of the position true value.

[0073] In this embodiment, as shown in FIG. 5, the first position true value includes the following fields: position coordinates of the terminal, information of the positioning method, positioning accuracy, and comprehensive accuracy.

[0074] The position coordinates of the terminal represent the coordinates of the geographical position where the terminal is located, that is, the position coordinates of the terminal represent the actual position of the terminal. In combination with the scenario in which the terminal acquires the first position true value, the position coordinates of the terminal are the geographical position coordinates of the position where the terminal actually locates when the terminal acquires the first position true value.

[0075] The positioning method is the positioning method used by the terminal to acquire the position coordinates of the terminal. Some types of positioning methods include the positioning function of the terminal and the positioning function of the third-party application (APP) running in the terminal.

[0076] Some examples of the positioning function of the terminal include: Global Navigation Satellite System (GNSS) positioning, GNSS and Inertia Navigation System (INS) combined positioning, cellular mobile network positioning, active positioning such as wireless fidelity (WiFi) or Bluetooth (BLE), active positioning and INS combined positioning, and pure inertial navigation calculated position positioning.

[0077] Some examples of the positioning function of the third-party application include: the positioning function provided by a trusted third-party application such as a map application, and the positioning function provided by other (i.e., without trusted authentication) third-party applications.

[0078] It can be understood that the terminal, in response to the signaling, calls one of the above positioning manners to obtain the position coordinates of the terminal.

[0079] The positioning accuracy represents the accuracy of the position coordinates of the terminal obtained by the positioning manner. In some implementations, the positioning accuracy is the accuracy (ACC), and the greater the value of the ACC, the worse the positioning accuracy. Generally, the positioning manner also provides the ACC when providing the position coordinates.

[0080] In this embodiment, on the basis of the positioning accuracy, a parameter that can more comprehensively represent the trustworthiness and accuracy of the position coordinates of the terminal, i.e., the comprehensive accuracy, is also provided. The comprehensive accuracy can integrate the trustworthiness and accuracy of the position coordinates of the terminal. Compared with the ACC, the comprehensive accuracy can better reflect the contribution of the position coordinates to the prediction accuracy of the AI model.

[0081] The manner of obtaining the comprehensive accuracy will be described in detail below with reference to FIG. 6.

[0082] In this embodiment, the trustworthiness is configured for various positioning manners. As shown in FIG. 6, the first column is various positioning manners, and the second column is the trustworthiness corresponding to various positioning manners. The trustworthiness represents the degree of trust of the positioning manner. The degree of trust can be understood as at least one of the degree of being used preferentially (the calling priority), the reliability, and the accuracy of the result. The higher the trustworthiness, the higher the priority of being used, and it can also mean the higher the reliability, and it can also mean the higher the accuracy of the result, and so on.

[0083] In some implementations, the trustworthiness is represented by a numerical value, and the smaller the numerical value, the higher the trustworthiness, i.e., the more trustworthy, and the greater the numerical value, the lower the trustworthiness, i.e., the less trustworthy.

[0084] Taking Fig. 6 as an example, the credibility of the GNSS positioning and the GNSS / INS combined positioning mode is 1, which indicates that the GNSS positioning and the GNSS / INS combined positioning mode are the most credible among the positioning modes shown in Fig. 6, and the credibility of the positioning modes provided by the other three applications is 6, which indicates that the positioning modes provided by the other three applications are the least credible among the positioning modes shown in Fig. 6.

[0085] In some implementations, the credibility of various positioning modes is configured based on empirical values.

[0086] In some implementations, a terminal can have multiple positioning modes, and the terminal invokes a positioning mode with higher credibility to obtain the position coordinates of the terminal based on the credibility of the positioning modes.

[0087] It can be understood that the integer value of the credibility in Fig. 6 is only an example and is not intended to be limiting, and the credibility can also be a non-integer value or a non-numeric value (for example, a character).

[0088] The third column in Fig. 6 is the positioning accuracy of various positioning modes.

[0089] In some implementations, the credibility is an integer value greater than 0, and the calculation method of the comprehensive accuracy is: comprehensive credibility = (1 + (positioning method credibility - 1) / (N - 1)) x positioning accuracy (1).

[0090] Wherein, N is the number of all available values of credibility, assuming that Fig. 6 contains all available values of credibility, then N = 6.

[0091] The last column in Fig. 6 is the comprehensive accuracy corresponding to each positioning mode obtained based on formula (1).

[0092] It can be understood that formula (1) is only an example and is not intended to be limiting.

[0093] The inventor summarized the rules for obtaining comprehensive accuracy in the process of research, including: 1. The value of comprehensive accuracy is positively correlated with the value of the credibility of the positioning method. Under the same positioning accuracy value, the smaller the value of the credibility of the positioning method, the smaller the value of the comprehensive accuracy, and the larger the value of the credibility, the larger the value of the comprehensive accuracy. 2. The value of the comprehensive accuracy is greater than or equal to the value of the positioning accuracy.

[0094] It can be understood that the first position true value shown in Fig. 5 includes a field as an implementation, and in another implementation, compared with Fig. 5, the first position true value does not include the positioning mode.

[0095] In addition to including the fields exemplified in FIG. 5, the first location truth value further corresponds to a timestamp and an identity of the terminal. The timestamp corresponding to the first location truth value represents a time point at which the positioning, i.e., the acquisition of the position coordinates of the terminal, is performed. The identity of the terminal corresponding to the first location truth value represents the terminal having the position coordinates of the terminal included in the first location truth value, i.e., the terminal performing the positioning.

[0096] S13. The terminal transmits the first location truth value to the base station.

[0097] The terminal can transmit the first location truth value to the base station based on an existing message of a communication standard, or can transmit the first location truth value to the base station based on a newly configured message compared with the existing message.

[0098] S14. The base station transmits the first location truth value to the MME.

[0099] S15. The MME transmits the first location truth value to the LMF.

[0100] The transmission interface between the base station and the MME, and between the MME and the LMF can refer to a communication standard, or a new interface can be configured, which is not limited here.

[0101] S16. The LMF screens the first location truth value satisfying a condition to obtain a target location truth value.

[0102] In some implementations, the condition includes that the comprehensive accuracy in the location truth value is greater than a preset threshold. Because the comprehensive accuracy fuses the credibility of the positioning manner and the accuracy of the positioning result, the comprehensive level of the credibility and the accuracy can be reflected. It can be understood that the comprehensive accuracy of the screened target location truth value satisfies the use requirement, and thus it is beneficial to improve the accuracy of the sample data, thereby being beneficial to training to obtain an AI model with high accuracy. The first location truth value not satisfying the condition indicates that the credibility of the positioning manner is not enough or the accuracy of the position coordinates of the terminal is not enough, and thus it is not used as sample data, which is beneficial to saving the resources of the LMF without interfering with the accuracy of the AI model.

[0103] S17. The LMF adapts the measurement result and the target location truth value to obtain sample data with the location truth value.

[0104] As described above, the first location truth value corresponds to a timestamp and an identity of the terminal, and thus the target truth value corresponds to a timestamp and an identity of the terminal.

[0105] The timestamp corresponding to the target location truth value represents a time point at which the position coordinates of the terminal in the target location truth value are acquired. The identity of the terminal corresponding to the target location truth value represents the terminal acquiring the target location truth value.

[0106] The measurement result also corresponds to a timestamp and an identifier of the terminal. The timestamp of the measurement result represents a time point at which the measurement result is acquired. For the convenience of distinction, the timestamp of the first position true value is referred to as a true value timestamp, and the timestamp of the measurement result is referred to as a measurement timestamp.

[0107] The LMF adapts the measurement result and the target position true value based on the timestamps, and in some implementations, the target position true value that meets an adaptation condition and the measurement result are taken as adaptation data, the adaptation condition including that the true value timestamp is the same as the measurement timestamp, and the identifier of the terminal is the same.

[0108] In this embodiment, the adapted target position true value and the measurement result are taken as a set of sample data, i.e., sample data with a position true value.

[0109] It can be understood that the measurement result (i.e., the training sample) can be acquired before S17, and the acquisition manner is not described herein.

[0110] S18, the LMF trains an AI model using the sample data with the position true value.

[0111] It can be understood that, because the sample data has the position true value, the AI model is trained using a supervised training method, which is conducive to obtaining an AI model with more accurate prediction results.

[0112] After the AI model is trained, the LMF predicts the position coordinates of the terminal using the AI model.

[0113] In the flow shown in FIG. 4, the terminal reports the first position true value, because the first position true value not only includes the position coordinates of the terminal, but also includes the comprehensive accuracy that can comprehensively reflect the credibility of the positioning method for acquiring the position coordinates of the terminal and the accuracy of the position coordinates of the terminal, so that the LMF can select the target position true value that contributes to the accuracy of the AI model based on the first position true value, and use the measurement data of the target position true value as the sample data to train the AI model, which is conducive to obtaining an AI model with high accuracy, and only using the target position true value is also conducive to reducing the amount of calculation, thereby reducing the consumption of resources.

[0114] FIG. 7 is a flow of another position data reporting and positioning method disclosed by an embodiment of the present application. Compared with the flow shown in FIG. 4, the position true value is generated by the base station, and the training manner of the LMF is different.

[0115] The flow shown in FIG. 7 includes the following steps:

[0116] S21, the base station sends signaling indicating reporting a position true value to the terminal.

[0117] S22, the terminal acquires a second position true value in response to the signaling.

[0118] The second position truth value is another specific implementation of the position truth value.

[0119] Compared with the first position truth value shown in FIG. 5, the second position truth value includes the position coordinates of the terminal and the positioning accuracy, and can also include the information of the positioning manner. That is, the second position truth value does not include the comprehensive accuracy.

[0120] The description of each field in the second position truth value can refer to the above-mentioned embodiments, which will not be repeated here.

[0121] S23, the terminal sends the second position truth value to the base station.

[0122] S24, the base station obtains the first position truth value based on the second position truth value.

[0123] In the embodiment, the second position truth value does not include the comprehensive accuracy, and the comprehensive accuracy is calculated and obtained by the base station, and in one implementation, the comprehensive accuracy is added to the second position truth value to generate the first position truth value.

[0124] The first position truth value can refer to the above-mentioned embodiments, and is shown in FIG. 5, which will not be repeated here.

[0125] S25, the base station transmits the first position truth value to the MME.

[0126] S26, the MME transmits the first position truth value to the LMF.

[0127] In another implementation, the base station sends the second position truth value and the comprehensive accuracy to the LMF through the MME. Regardless of which implementation, the LMF can obtain the position coordinates of the terminal and the comprehensive accuracy.

[0128] S27, the LMF obtains sample data with the position truth value.

[0129] For details, please refer to S16 and S17.

[0130] S28, the LMF uses the sample data with the position truth value to perform supervised training on the AI model to obtain the first model.

[0131] S29, the LMF uses the sample data with the position truth value and the measurement result (sample data) without the position truth value to train the AI model to perform semi-supervised training on the AI model to obtain the second model.

[0132] S210, the LMF uses the first model in the target area and uses the second model in the non-target area.

[0133] The target area is an area in the position coordinate set of the terminal included in the first position ground truth or the second position ground truth, such as some areas in a certain city. Because the first model is obtained by supervised training based on the position coordinates collected by the terminal in these areas, the first model is used in these areas, which is beneficial to obtaining more accurate positioning prediction results in these areas.

[0134] Based on the position coordinates of the terminal, the target area is obtained, for example, the position coordinates of the terminal are clustered to obtain the target area.

[0135] Because the second model is obtained by using the semi-supervised training method, compared with the unsupervised method in which all the training data are measurement results, the accuracy is also improved.

[0136] The flow shown in FIG. 7 is used to obtain the comprehensive accuracy by the base station, which can reduce the calculation amount of the terminal. Moreover, not only the AI model is trained by using the sample data with the position ground truth, but also the semi-supervised training is performed on the sample data without the position ground truth together with the sample data with the position ground truth, the models obtained by using different training methods for different areas are beneficial to significantly improving the prediction accuracy of the model in the target area, and the prediction accuracy of the model in the non-target area is also improved.

[0137] In addition, the position ground truth is filtered based on the comprehensive accuracy in the embodiment, so it is also beneficial to reduce the resource consumption amount of training.

[0138] It can be understood that the way in which the LMF trains the model in FIG. 4 and the way in which the model is used in FIG. 7 can be replaced with each other.

[0139] In the above embodiment, the LMF can receive the first position ground truth, and another alternative way is that the base station transmits the position coordinates and the comprehensive accuracy of the terminal to the LMF through the MME, and optionally, at least one of the information of the positioning method and the positioning accuracy is also transmitted.

[0140] The terminal described in the embodiments of the present application, as shown in FIG. 8, includes a processor 10 and a memory 11.

[0141] It can be understood that the structure shown in the embodiment does not constitute a specific limitation on the terminal. In other embodiments, the terminal can include more or fewer components than shown, or combine certain components, or split certain components, or different component arrangements. The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0142] The processor 10 includes an application processor (AP) and a baseband processor (Modem).

[0143] The memory 11 is configured to store program code, and the baseband processor (Modem) is configured to execute the program code, so that the terminal implements the steps performed by the terminal in the above embodiments.

[0144] The terminal shown in FIG. 8 can provide the first position truth value or the second position truth value, lay a foundation for the core network device to obtain the training sample with the actual position of the terminal, and be beneficial to obtain the terminal positioning model and the positioning result with higher prediction accuracy.

[0145] The base station described in the embodiments of the present application includes a processor, a memory, a transmitter and a receiver.

[0146] The memory is configured to store program code, and the processor is configured to execute the program code, so as to implement the steps performed by the base station in the above embodiments. In the process of implementing the steps performed by the base station in the above embodiments, the transmitter and the receiver are used for signal transmission.

[0147] The base station can provide the first position truth value for the core network device, lay a foundation for the core network device to obtain the training sample with the actual position of the terminal, and be beneficial to obtain the terminal positioning model and the positioning result with higher prediction accuracy.

[0148] The embodiments of the present application also provide a core network device, a processor and a memory. The memory is configured to store program code, and the processor is configured to execute the program code, so that the core network device performs the steps performed by the MME or the LMF in the above embodiments.

[0149] The core network device uses the training sample with the actual position of the terminal to train the positioning result of the terminal, so as to be beneficial to obtain the terminal positioning model and the positioning result with higher accuracy.

[0150] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any change or replacement within the technical scope disclosed in the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for reporting location data, characterized in that, Applied to a terminal, the method comprises: In response to signaling indicating reporting of a location truth value, obtaining location coordinates of the terminal; Sending the location truth value to a base station, the location truth value comprising the location coordinates of the terminal.

2. The method of claim 1, wherein, The location truth value further comprises a first accuracy, the first accuracy representing at least one of a reliability and an accuracy of the location coordinates of the terminal.

3. The method of claim 2, wherein, The first accuracy is obtained based on a preset reliability of a positioning mode and an accuracy ACC of the location coordinates of the terminal, the positioning mode being used to obtain the location coordinates of the terminal.

4. The method of claim 3, wherein, The preset reliability is a first reliability, the first reliability being one value in a reliability set, the reliability set comprising a first number of integer values greater than 0, each value in the reliability set representing a reliability; The first accuracy is obtained based on the preset reliability of the positioning mode and the accuracy ACC of the location coordinates of the terminal, comprising: The value of the first accuracy is positively correlated with the value of the preset reliability, and the value of the first accuracy is greater than or equal to the ACC.

5. The method of claim 4, wherein, The first accuracy is equal to a product of a first value and the ACC, the first value being obtained based on the reliability.

6. The method according to any one of claims 1 to 5, characterized in that, The location truth value further comprises: At least one of information of a positioning mode and a positioning accuracy, the positioning mode being used to obtain the location coordinates of the terminal, the positioning accuracy representing the ACC of the location coordinates of the terminal obtained by the positioning mode.

7. A method for reporting location data, the method comprising: Applied to a base station, the method comprises: Sending signaling indicating reporting of a location truth value to a terminal; Receiving location coordinates of the terminal sent by the terminal; Sending a location truth value to a core network device, the location truth value comprising the location coordinates of the terminal and a first accuracy, the first accuracy representing at least one of a reliability and an accuracy of the location coordinates of the terminal.

8. The method of claim 7, wherein, The first accuracy is obtained based on a preset reliability of a positioning mode and an accuracy ACC of the location coordinates of the terminal, the positioning mode being used to obtain the location coordinates of the terminal.

9. The method of claim 8, wherein, The preset reliability is a first reliability, the first reliability being one value in a reliability set, the reliability set comprising a first number of integer values greater than 0, each value in the reliability set representing a reliability; The first accuracy is obtained based on the preset reliability of the positioning mode and the accuracy ACC of the location coordinates of the terminal, comprising: The value of the first accuracy is positively correlated with the value of the preset reliability, and the value of the first accuracy is greater than or equal to the ACC.

10. The method of claim 9, wherein, The first accuracy is equal to a product of a first value and the ACC, the first value being obtained based on the reliability.

11. The method according to any one of claims 7-10, characterized in that, The location truth value further comprises: At least one of information of a positioning mode and a positioning accuracy, the positioning mode being used to obtain the location coordinates of the terminal, the positioning accuracy representing the ACC of the location coordinates of the terminal obtained by the positioning mode.

12. The method according to any one of claims 7-10, characterized in that, The receiving of the location coordinates of the terminal sent by the terminal comprises: Receiving a first location truth value sent by the terminal, the first location truth value comprising the location coordinates of the terminal and the first accuracy; The sending of the location true value to the core network device comprises: The sending of the first location true value to the core network device.

13. The method according to any one of claims 7-10, characterized in that, The receiving of the location coordinates of the terminal sent by the terminal comprises: The receiving of the second location true value sent by the terminal, the second location true value comprising the location coordinates of the terminal, information of a positioning mode and ACC; The sending of the location true value to the core network device comprises: The obtaining of the first precision based on the second location true value; The sending of the first location true value to the core network device, the first location true value comprising the location coordinates of the terminal and the first precision.

14. A positioning method characterized by, The method applied to a core network device comprises: The receiving of a location true value sent by a base station, the location true value comprising location coordinates of a terminal and a first precision, the first precision representing at least one of credibility and accuracy of the location coordinates of the terminal; The screening of a target location true value from the location true value based on the first precision: The obtaining of sample data with a location true value by adapting the target location true value and pre-acquired training sample data; The training of a model using the sample data with a location true value, to obtain a first model, the first model being used for predicting a location of a terminal.

15. The method of claim 14, wherein, Further comprising: The semi-supervised training of the model using the sample data with a location true value and sample data without a location true value, to obtain a second model.

16. The method of claim 15, wherein, Further comprising: The use of the first model in a target area and the use of the second model in a non-target area, the target area being acquired based on the location coordinates of the terminal comprised in the location true value.

17. A terminal, characterized by Comprise: A processor and a memory; The memory is used for storing program codes; The processor is used for running the program codes, so that the terminal implements the location data reporting method in any one of claims 1-6.

18. A base station, comprising: Comprise: A processor and a memory; The memory is used for storing program codes; The processor is used for running the program codes, so that the base station implements the location data reporting method in any one of claims 7-13.

19. A core network device, comprising: Comprise: A processor and a memory; The memory is used for storing program codes; The processor is used for running the program codes, so that the core network device implements the positioning method in any one of claims 14-16.

20. A computer-readable storage medium, characterized in that, The instructions stored thereon, when running on an electronic device, cause the electronic device to execute the location data reporting method in any one of claims 1-13 or the positioning method in any one of claims 14-16.

21. A chip system, characterized by Comprise: At least one processor and an interface, the interface being used for receiving code instructions and transmitting to the at least one processor; The at least one processor runs the code instructions, to implement the location data reporting method in any one of claims 1-13.

Images